diff --git a/.github/workflows/ab-testing-advisor.lock.yml b/.github/workflows/ab-testing-advisor.lock.yml index fa8c891ac94..f8d043103d1 100644 --- a/.github/workflows/ab-testing-advisor.lock.yml +++ b/.github/workflows/ab-testing-advisor.lock.yml @@ -468,6 +468,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1212,6 +1213,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1470,6 +1472,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1477,6 +1480,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/ace-editor.lock.yml b/.github/workflows/ace-editor.lock.yml index 8ee1ce9f6f5..f8a2a885bb8 100644 --- a/.github/workflows/ace-editor.lock.yml +++ b/.github/workflows/ace-editor.lock.yml @@ -503,6 +503,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1248,6 +1249,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/agent-job-health.lock.yml b/.github/workflows/agent-job-health.lock.yml index 5b23117714d..4689e7ccdf3 100644 --- a/.github/workflows/agent-job-health.lock.yml +++ b/.github/workflows/agent-job-health.lock.yml @@ -470,6 +470,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1386,6 +1387,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1645,6 +1647,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1652,6 +1655,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/agent-performance-analyzer.lock.yml b/.github/workflows/agent-performance-analyzer.lock.yml index 2cb72f541de..8a29ce17784 100644 --- a/.github/workflows/agent-performance-analyzer.lock.yml +++ b/.github/workflows/agent-performance-analyzer.lock.yml @@ -506,6 +506,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1416,6 +1417,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1446,6 +1448,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1680,6 +1683,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1687,6 +1691,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/agent-persona-explorer.lock.yml b/.github/workflows/agent-persona-explorer.lock.yml index 79113bb788f..db653590b01 100644 --- a/.github/workflows/agent-persona-explorer.lock.yml +++ b/.github/workflows/agent-persona-explorer.lock.yml @@ -505,6 +505,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1304,6 +1305,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1567,6 +1569,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1574,6 +1577,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/agentic-token-audit.lock.yml b/.github/workflows/agentic-token-audit.lock.yml index 47bb2de8539..3ea14d5e1e5 100644 --- a/.github/workflows/agentic-token-audit.lock.yml +++ b/.github/workflows/agentic-token-audit.lock.yml @@ -452,6 +452,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1312,6 +1313,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1339,6 +1341,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1568,6 +1571,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1575,6 +1579,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/agentic-token-optimizer.lock.yml b/.github/workflows/agentic-token-optimizer.lock.yml index b9fc6686d58..fd785bb9f38 100644 --- a/.github/workflows/agentic-token-optimizer.lock.yml +++ b/.github/workflows/agentic-token-optimizer.lock.yml @@ -448,6 +448,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1206,6 +1207,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1233,6 +1235,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1433,6 +1436,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/agentic-token-trend-audit.lock.yml b/.github/workflows/agentic-token-trend-audit.lock.yml index c6d2d514b05..df7cc8c91b6 100644 --- a/.github/workflows/agentic-token-trend-audit.lock.yml +++ b/.github/workflows/agentic-token-trend-audit.lock.yml @@ -451,6 +451,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1272,6 +1273,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1530,6 +1532,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1537,6 +1540,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/ai-moderator.lock.yml b/.github/workflows/ai-moderator.lock.yml index 6468caa0984..840a6561437 100644 --- a/.github/workflows/ai-moderator.lock.yml +++ b/.github/workflows/ai-moderator.lock.yml @@ -1247,6 +1247,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/api-consumption-report.lock.yml b/.github/workflows/api-consumption-report.lock.yml index b16484bfb9f..3f34a998fb4 100644 --- a/.github/workflows/api-consumption-report.lock.yml +++ b/.github/workflows/api-consumption-report.lock.yml @@ -473,6 +473,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1316,6 +1317,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1575,6 +1577,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1582,6 +1585,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/approach-validator.lock.yml b/.github/workflows/approach-validator.lock.yml index b116f896e19..83383468c9b 100644 --- a/.github/workflows/approach-validator.lock.yml +++ b/.github/workflows/approach-validator.lock.yml @@ -552,6 +552,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1378,6 +1379,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1630,6 +1632,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1637,6 +1640,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/archie.lock.yml b/.github/workflows/archie.lock.yml index b1114aeb2a2..ff0fe127948 100644 --- a/.github/workflows/archie.lock.yml +++ b/.github/workflows/archie.lock.yml @@ -512,6 +512,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1283,6 +1284,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1313,6 +1315,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1535,6 +1538,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1542,6 +1546,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/architecture-guardian.lock.yml b/.github/workflows/architecture-guardian.lock.yml index e6564afcaf1..0f2a3b39ff1 100644 --- a/.github/workflows/architecture-guardian.lock.yml +++ b/.github/workflows/architecture-guardian.lock.yml @@ -452,6 +452,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1209,6 +1210,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1239,6 +1241,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1466,6 +1469,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1473,6 +1477,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/archivx-agentic-workflows-analyzer.lock.yml b/.github/workflows/archivx-agentic-workflows-analyzer.lock.yml index a0a04cf4ad6..c99e40f9763 100644 --- a/.github/workflows/archivx-agentic-workflows-analyzer.lock.yml +++ b/.github/workflows/archivx-agentic-workflows-analyzer.lock.yml @@ -518,6 +518,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1412,6 +1413,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1670,6 +1672,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1677,6 +1680,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/artifacts-summary.lock.yml b/.github/workflows/artifacts-summary.lock.yml index 6eaa1d8fa8c..fc201c786d3 100644 --- a/.github/workflows/artifacts-summary.lock.yml +++ b/.github/workflows/artifacts-summary.lock.yml @@ -477,6 +477,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1220,6 +1221,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/audit-workflows.lock.yml b/.github/workflows/audit-workflows.lock.yml index 4b4a9309b5f..faf860769d4 100644 --- a/.github/workflows/audit-workflows.lock.yml +++ b/.github/workflows/audit-workflows.lock.yml @@ -521,6 +521,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1480,6 +1481,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1751,6 +1753,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1758,6 +1761,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/auto-triage-issues.lock.yml b/.github/workflows/auto-triage-issues.lock.yml index 7d838cdd28b..ea78f481025 100644 --- a/.github/workflows/auto-triage-issues.lock.yml +++ b/.github/workflows/auto-triage-issues.lock.yml @@ -475,6 +475,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1279,6 +1280,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1534,6 +1536,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1541,6 +1544,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/avenger.lock.yml b/.github/workflows/avenger.lock.yml index a33e4d89e29..eab50a1649b 100644 --- a/.github/workflows/avenger.lock.yml +++ b/.github/workflows/avenger.lock.yml @@ -492,6 +492,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1260,6 +1261,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1290,6 +1292,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1581,6 +1584,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1588,6 +1592,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/aw-failure-investigator.lock.yml b/.github/workflows/aw-failure-investigator.lock.yml index f05787c76f8..69fa6232424 100644 --- a/.github/workflows/aw-failure-investigator.lock.yml +++ b/.github/workflows/aw-failure-investigator.lock.yml @@ -511,6 +511,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1468,6 +1469,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1735,6 +1737,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1742,6 +1745,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/aw-issue-clustering.lock.yml b/.github/workflows/aw-issue-clustering.lock.yml index bc299c1924d..d6fcd05e6c1 100644 --- a/.github/workflows/aw-issue-clustering.lock.yml +++ b/.github/workflows/aw-issue-clustering.lock.yml @@ -427,6 +427,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1112,6 +1113,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1139,6 +1141,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1391,12 +1394,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/blog-auditor.lock.yml b/.github/workflows/blog-auditor.lock.yml index 497d55d05ce..84daf9725db 100644 --- a/.github/workflows/blog-auditor.lock.yml +++ b/.github/workflows/blog-auditor.lock.yml @@ -510,6 +510,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1358,6 +1359,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1626,6 +1628,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1633,6 +1636,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/bot-detection.lock.yml b/.github/workflows/bot-detection.lock.yml index 9eb01d53865..5db0958d997 100644 --- a/.github/workflows/bot-detection.lock.yml +++ b/.github/workflows/bot-detection.lock.yml @@ -473,6 +473,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1240,6 +1241,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1466,6 +1468,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/breaking-change-checker.lock.yml b/.github/workflows/breaking-change-checker.lock.yml index 0d2b26dd180..65c8449088c 100644 --- a/.github/workflows/breaking-change-checker.lock.yml +++ b/.github/workflows/breaking-change-checker.lock.yml @@ -497,6 +497,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1249,6 +1250,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1279,6 +1281,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1516,6 +1519,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1523,6 +1527,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/changeset.lock.yml b/.github/workflows/changeset.lock.yml index b5dde932de8..b9e0c09df93 100644 --- a/.github/workflows/changeset.lock.yml +++ b/.github/workflows/changeset.lock.yml @@ -509,6 +509,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1246,6 +1247,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1499,6 +1501,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1506,6 +1509,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/chaos-pr-bundle-fuzzer.lock.yml b/.github/workflows/chaos-pr-bundle-fuzzer.lock.yml index 4aeefce9aa9..9902d4f0b00 100644 --- a/.github/workflows/chaos-pr-bundle-fuzzer.lock.yml +++ b/.github/workflows/chaos-pr-bundle-fuzzer.lock.yml @@ -461,6 +461,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1225,6 +1226,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1467,12 +1469,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/ci-coach.lock.yml b/.github/workflows/ci-coach.lock.yml index 03f3ba998b2..3bab387eae8 100644 --- a/.github/workflows/ci-coach.lock.yml +++ b/.github/workflows/ci-coach.lock.yml @@ -529,6 +529,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1337,6 +1338,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1367,6 +1369,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1608,6 +1611,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "50000" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1615,6 +1619,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/claude-code-user-docs-review.lock.yml b/.github/workflows/claude-code-user-docs-review.lock.yml index b440663d3e8..b5a655ccbc9 100644 --- a/.github/workflows/claude-code-user-docs-review.lock.yml +++ b/.github/workflows/claude-code-user-docs-review.lock.yml @@ -463,6 +463,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1270,6 +1271,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1529,6 +1531,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1536,6 +1539,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/cli-consistency-checker.lock.yml b/.github/workflows/cli-consistency-checker.lock.yml index 90d5b045275..18499d4b61d 100644 --- a/.github/workflows/cli-consistency-checker.lock.yml +++ b/.github/workflows/cli-consistency-checker.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1181,6 +1182,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1211,6 +1213,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1433,6 +1436,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1440,6 +1444,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/cli-version-checker.lock.yml b/.github/workflows/cli-version-checker.lock.yml index 562f0cfe7a9..29d9996b0e8 100644 --- a/.github/workflows/cli-version-checker.lock.yml +++ b/.github/workflows/cli-version-checker.lock.yml @@ -1171,6 +1171,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1425,6 +1426,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/cloclo.lock.yml b/.github/workflows/cloclo.lock.yml index b995f1ad3d1..4acc42efc71 100644 --- a/.github/workflows/cloclo.lock.yml +++ b/.github/workflows/cloclo.lock.yml @@ -603,6 +603,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1527,6 +1528,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1784,6 +1786,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1791,6 +1794,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/code-scanning-fixer.lock.yml b/.github/workflows/code-scanning-fixer.lock.yml index 22e0446bbc7..ae61f8015f6 100644 --- a/.github/workflows/code-scanning-fixer.lock.yml +++ b/.github/workflows/code-scanning-fixer.lock.yml @@ -487,6 +487,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1362,6 +1363,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1392,6 +1394,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1618,6 +1621,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1625,6 +1629,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/code-simplifier.lock.yml b/.github/workflows/code-simplifier.lock.yml index 269d56578e8..8b79c7df13f 100644 --- a/.github/workflows/code-simplifier.lock.yml +++ b/.github/workflows/code-simplifier.lock.yml @@ -481,6 +481,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1239,6 +1240,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1269,6 +1271,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1502,6 +1505,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1000" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1509,6 +1513,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/codex-github-remote-mcp-test.lock.yml b/.github/workflows/codex-github-remote-mcp-test.lock.yml index 282663b0947..98b0666625c 100644 --- a/.github/workflows/codex-github-remote-mcp-test.lock.yml +++ b/.github/workflows/codex-github-remote-mcp-test.lock.yml @@ -442,6 +442,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1195,6 +1196,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/commit-changes-analyzer.lock.yml b/.github/workflows/commit-changes-analyzer.lock.yml index c6082996d32..9c80599bd12 100644 --- a/.github/workflows/commit-changes-analyzer.lock.yml +++ b/.github/workflows/commit-changes-analyzer.lock.yml @@ -444,6 +444,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1111,6 +1112,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1358,6 +1360,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1365,6 +1368,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/constraint-solving-potd.lock.yml b/.github/workflows/constraint-solving-potd.lock.yml index 8be036f5253..94ce7f9625d 100644 --- a/.github/workflows/constraint-solving-potd.lock.yml +++ b/.github/workflows/constraint-solving-potd.lock.yml @@ -445,6 +445,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1146,6 +1147,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1173,6 +1175,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1395,6 +1398,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1402,6 +1406,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/contribution-check.lock.yml b/.github/workflows/contribution-check.lock.yml index 5c9281650d5..a0b229a878f 100644 --- a/.github/workflows/contribution-check.lock.yml +++ b/.github/workflows/contribution-check.lock.yml @@ -451,6 +451,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1319,6 +1320,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1348,6 +1350,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1569,6 +1572,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1576,6 +1580,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-agent-analysis.lock.yml b/.github/workflows/copilot-agent-analysis.lock.yml index c2c6d7e7a82..38330c72bf7 100644 --- a/.github/workflows/copilot-agent-analysis.lock.yml +++ b/.github/workflows/copilot-agent-analysis.lock.yml @@ -517,6 +517,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1334,6 +1335,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1593,6 +1595,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1600,6 +1603,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-centralization-drilldown.lock.yml b/.github/workflows/copilot-centralization-drilldown.lock.yml index b22d9e18172..291fcc545a3 100644 --- a/.github/workflows/copilot-centralization-drilldown.lock.yml +++ b/.github/workflows/copilot-centralization-drilldown.lock.yml @@ -444,6 +444,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1133,6 +1134,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1379,6 +1381,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "120" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1386,6 +1389,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-centralization-optimizer.lock.yml b/.github/workflows/copilot-centralization-optimizer.lock.yml index 5889d9379fe..84b61d4a833 100644 --- a/.github/workflows/copilot-centralization-optimizer.lock.yml +++ b/.github/workflows/copilot-centralization-optimizer.lock.yml @@ -446,6 +446,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1319,6 +1320,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1566,6 +1568,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "250" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1573,6 +1576,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-cli-deep-research.lock.yml b/.github/workflows/copilot-cli-deep-research.lock.yml index 30704eb4686..0248db3aa70 100644 --- a/.github/workflows/copilot-cli-deep-research.lock.yml +++ b/.github/workflows/copilot-cli-deep-research.lock.yml @@ -450,6 +450,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1204,6 +1205,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1231,6 +1233,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1451,6 +1454,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1458,6 +1462,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-opt.lock.yml b/.github/workflows/copilot-opt.lock.yml index 05b299f219f..2a6ded5155c 100644 --- a/.github/workflows/copilot-opt.lock.yml +++ b/.github/workflows/copilot-opt.lock.yml @@ -457,6 +457,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1246,6 +1247,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1273,6 +1275,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1495,6 +1498,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1502,6 +1506,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-pr-merged-report.lock.yml b/.github/workflows/copilot-pr-merged-report.lock.yml index 2df4b947654..7467131ccdb 100644 --- a/.github/workflows/copilot-pr-merged-report.lock.yml +++ b/.github/workflows/copilot-pr-merged-report.lock.yml @@ -438,6 +438,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1130,6 +1131,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1157,6 +1159,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1378,6 +1381,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1385,6 +1389,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-pr-nlp-analysis.lock.yml b/.github/workflows/copilot-pr-nlp-analysis.lock.yml index 5ead3051952..40acae272d8 100644 --- a/.github/workflows/copilot-pr-nlp-analysis.lock.yml +++ b/.github/workflows/copilot-pr-nlp-analysis.lock.yml @@ -517,6 +517,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1364,6 +1365,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1391,6 +1393,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1624,6 +1627,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1631,6 +1635,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-pr-prompt-analysis.lock.yml b/.github/workflows/copilot-pr-prompt-analysis.lock.yml index 8ec5cdcb889..af3c88d7b2b 100644 --- a/.github/workflows/copilot-pr-prompt-analysis.lock.yml +++ b/.github/workflows/copilot-pr-prompt-analysis.lock.yml @@ -465,6 +465,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1251,6 +1252,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1278,6 +1280,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1500,6 +1503,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1507,6 +1511,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/copilot-session-insights.lock.yml b/.github/workflows/copilot-session-insights.lock.yml index c164cd58a49..5c4e1cd4dc1 100644 --- a/.github/workflows/copilot-session-insights.lock.yml +++ b/.github/workflows/copilot-session-insights.lock.yml @@ -489,6 +489,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1361,6 +1362,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1611,6 +1613,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1618,6 +1621,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/craft.lock.yml b/.github/workflows/craft.lock.yml index 2c1d41473ca..1debec339ba 100644 --- a/.github/workflows/craft.lock.yml +++ b/.github/workflows/craft.lock.yml @@ -498,6 +498,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1234,6 +1235,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1261,6 +1263,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1481,6 +1484,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1488,6 +1492,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-action-setup-security-audit.lock.yml b/.github/workflows/daily-action-setup-security-audit.lock.yml index b7c5ba797b5..5cc7e34033f 100644 --- a/.github/workflows/daily-action-setup-security-audit.lock.yml +++ b/.github/workflows/daily-action-setup-security-audit.lock.yml @@ -448,6 +448,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1185,6 +1186,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1212,6 +1214,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1439,6 +1442,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1446,6 +1450,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-agent-of-the-day-blog-writer.lock.yml b/.github/workflows/daily-agent-of-the-day-blog-writer.lock.yml index c65175dd353..6b6eb968751 100644 --- a/.github/workflows/daily-agent-of-the-day-blog-writer.lock.yml +++ b/.github/workflows/daily-agent-of-the-day-blog-writer.lock.yml @@ -487,6 +487,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1349,6 +1350,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1378,6 +1380,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1610,6 +1613,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1617,6 +1621,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-agentrx-trace-optimizer.lock.yml b/.github/workflows/daily-agentrx-trace-optimizer.lock.yml index c2615bddb51..92c2ed39885 100644 --- a/.github/workflows/daily-agentrx-trace-optimizer.lock.yml +++ b/.github/workflows/daily-agentrx-trace-optimizer.lock.yml @@ -505,6 +505,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1387,6 +1388,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1650,6 +1652,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1657,6 +1660,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-ambient-context-optimizer.lock.yml b/.github/workflows/daily-ambient-context-optimizer.lock.yml index 5eecf73cd88..51e0007ff28 100644 --- a/.github/workflows/daily-ambient-context-optimizer.lock.yml +++ b/.github/workflows/daily-ambient-context-optimizer.lock.yml @@ -437,6 +437,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1223,6 +1224,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1250,6 +1252,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1474,6 +1477,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1481,6 +1485,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-architecture-diagram.lock.yml b/.github/workflows/daily-architecture-diagram.lock.yml index b44b4906da0..dfa62078355 100644 --- a/.github/workflows/daily-architecture-diagram.lock.yml +++ b/.github/workflows/daily-architecture-diagram.lock.yml @@ -521,6 +521,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1321,6 +1322,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1583,6 +1585,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1590,6 +1593,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-arxiv-researcher.lock.yml b/.github/workflows/daily-arxiv-researcher.lock.yml index 2b991db6c45..84e8214f3d2 100644 --- a/.github/workflows/daily-arxiv-researcher.lock.yml +++ b/.github/workflows/daily-arxiv-researcher.lock.yml @@ -461,6 +461,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1260,6 +1261,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1497,12 +1499,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "300" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-assign-issue-to-user.lock.yml b/.github/workflows/daily-assign-issue-to-user.lock.yml index af8c02b1afe..c8bdef195e3 100644 --- a/.github/workflows/daily-assign-issue-to-user.lock.yml +++ b/.github/workflows/daily-assign-issue-to-user.lock.yml @@ -430,6 +430,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1175,6 +1176,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1202,6 +1204,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1421,6 +1424,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1428,6 +1432,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-astrostylelite-markdown-spellcheck.lock.yml b/.github/workflows/daily-astrostylelite-markdown-spellcheck.lock.yml index fcd77292e5e..9a5ba944046 100644 --- a/.github/workflows/daily-astrostylelite-markdown-spellcheck.lock.yml +++ b/.github/workflows/daily-astrostylelite-markdown-spellcheck.lock.yml @@ -507,6 +507,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1265,6 +1266,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1531,6 +1533,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1538,6 +1541,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-aw-cross-repo-compile-check.lock.yml b/.github/workflows/daily-aw-cross-repo-compile-check.lock.yml index ff9712945ae..3af4d35c9e1 100644 --- a/.github/workflows/daily-aw-cross-repo-compile-check.lock.yml +++ b/.github/workflows/daily-aw-cross-repo-compile-check.lock.yml @@ -452,6 +452,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1225,6 +1226,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1478,6 +1480,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1485,6 +1488,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-awf-spec-compiler-surfacing.lock.yml b/.github/workflows/daily-awf-spec-compiler-surfacing.lock.yml index d608e4b3900..1a49097d9d8 100644 --- a/.github/workflows/daily-awf-spec-compiler-surfacing.lock.yml +++ b/.github/workflows/daily-awf-spec-compiler-surfacing.lock.yml @@ -439,6 +439,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1236,6 +1237,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1488,6 +1490,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1495,6 +1498,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-byok-ollama-test.lock.yml b/.github/workflows/daily-byok-ollama-test.lock.yml index f60efc9427f..e275aeab77a 100644 --- a/.github/workflows/daily-byok-ollama-test.lock.yml +++ b/.github/workflows/daily-byok-ollama-test.lock.yml @@ -433,6 +433,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1167,6 +1168,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1194,6 +1196,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1401,12 +1404,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-cache-strategy-analyzer.lock.yml b/.github/workflows/daily-cache-strategy-analyzer.lock.yml index 810b93f1fdf..088b05255e2 100644 --- a/.github/workflows/daily-cache-strategy-analyzer.lock.yml +++ b/.github/workflows/daily-cache-strategy-analyzer.lock.yml @@ -509,6 +509,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1317,6 +1318,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1580,6 +1582,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1587,6 +1590,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-caveman-optimizer.lock.yml b/.github/workflows/daily-caveman-optimizer.lock.yml index 62356e298e9..f08975a4317 100644 --- a/.github/workflows/daily-caveman-optimizer.lock.yml +++ b/.github/workflows/daily-caveman-optimizer.lock.yml @@ -517,6 +517,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1433,6 +1434,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1700,6 +1702,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1707,6 +1710,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-choice-test.lock.yml b/.github/workflows/daily-choice-test.lock.yml index 0143326962c..2520d4543b9 100644 --- a/.github/workflows/daily-choice-test.lock.yml +++ b/.github/workflows/daily-choice-test.lock.yml @@ -437,6 +437,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1161,6 +1162,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1401,12 +1403,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-cli-performance.lock.yml b/.github/workflows/daily-cli-performance.lock.yml index 858d7d09615..18cafd068f4 100644 --- a/.github/workflows/daily-cli-performance.lock.yml +++ b/.github/workflows/daily-cli-performance.lock.yml @@ -478,6 +478,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1434,6 +1435,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1687,6 +1689,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1694,6 +1697,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-cli-tools-tester.lock.yml b/.github/workflows/daily-cli-tools-tester.lock.yml index 1a31d52aa5a..39df16fa531 100644 --- a/.github/workflows/daily-cli-tools-tester.lock.yml +++ b/.github/workflows/daily-cli-tools-tester.lock.yml @@ -450,6 +450,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1212,6 +1213,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1459,6 +1461,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1466,6 +1469,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-code-debt-aider.lock.yml b/.github/workflows/daily-code-debt-aider.lock.yml index d8c06bb4c4d..36485420676 100644 --- a/.github/workflows/daily-code-debt-aider.lock.yml +++ b/.github/workflows/daily-code-debt-aider.lock.yml @@ -1,4 +1,4 @@ -# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"431e1156eeaf9948a5e1880c31f3f563e2d196714dc459caad7ae994f58f1396","body_hash":"7b39053084c924dcdd876e1a211d1927477965fc6f51da48e3dbfa5316ee328b","strict":true,"agent_id":"aider","agent_model":"copilot/auto","engine_versions":{"aider":"0.86.2"}} +# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"becf6b4f19b18ef07d348b39957fd127b593b346cee9c6bba5921bcfe8782e65","body_hash":"7b39053084c924dcdd876e1a211d1927477965fc6f51da48e3dbfa5316ee328b","strict":true,"agent_id":"aider","agent_model":"copilot/auto","engine_versions":{"aider":"0.86.2"}} # gh-aw-manifest: {"version":1,"secrets":["GH_AW_CI_TRIGGER_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GH_AW_OTEL_GRAFANA_AUTHORIZATION","GH_AW_OTEL_GRAFANA_ENDPOINT","GH_AW_OTEL_SENTRY_AUTHORIZATION","GH_AW_OTEL_SENTRY_ENDPOINT","GITHUB_TOKEN"],"actions":[{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/download-artifact","sha":"9000827ccba6bdab643e8b6fd33ac0654aef8333","version":"v8.0.2"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"949feb2413d6458794dcd2491c4babbbce0c15c1","version":"v7.1.0"},{"repo":"actions/setup-python","sha":"5fda3b95a4ea91299a34e894583c3862153e4b97","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"cf430e030ddbb5b0abf93d22962f4752f3646cd9","version":"v7.0.2"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50","digest":"sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50@sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50","digest":"sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50@sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965"},{"image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50","digest":"sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce","pinned_image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50@sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50","digest":"sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50@sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.30","digest":"sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.30@sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f","pinned_image":"ghcr.io/github/gh-aw-node@sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f"},{"image":"ghcr.io/github/github-mcp-server:v1.12.2","digest":"sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6","pinned_image":"ghcr.io/github/github-mcp-server:v1.12.2@sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6"}],"mcp_servers":[{"name":"safeoutputs","tools":["create_pull_request","missing_data","missing_tool","noop","report_incomplete"]}],"threat_detection":{"mode":"enabled"}} # This file was automatically generated by gh-aw. DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md # @@ -1041,6 +1041,7 @@ jobs: "mcp.guard.blocked", "mcp.tool_call", "mcp.event", "firewall.http_access", "firewall.token_usage", "firewall.model_routing", "firewall.steering", "firewall.event", "model_routing.outcome", + "model_endpoint.mismatch", "safe_output.request", "safe_output.result", "safe_output.error", "experiment.state", "experiment.assignment", "grader.manifest", "grader.result", "eval.result", "github_api.rate_limit", "usage.report", "execution.result", @@ -1542,6 +1543,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1784,6 +1786,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_FAILURE_ISSUE_NUMBER: ${{ needs.activation.outputs.steering_issue_number }} diff --git a/.github/workflows/daily-code-metrics.lock.yml b/.github/workflows/daily-code-metrics.lock.yml index 4e1c6128737..99a008f9ca7 100644 --- a/.github/workflows/daily-code-metrics.lock.yml +++ b/.github/workflows/daily-code-metrics.lock.yml @@ -498,6 +498,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1326,6 +1327,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1353,6 +1355,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1591,6 +1594,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1598,6 +1602,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-community-attribution.lock.yml b/.github/workflows/daily-community-attribution.lock.yml index 71c554889b1..c62e4b59d3d 100644 --- a/.github/workflows/daily-community-attribution.lock.yml +++ b/.github/workflows/daily-community-attribution.lock.yml @@ -509,6 +509,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1352,6 +1353,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1379,6 +1381,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1615,6 +1618,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1622,6 +1626,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-compiler-quality.lock.yml b/.github/workflows/daily-compiler-quality.lock.yml index cf75d40924f..9afd061041f 100644 --- a/.github/workflows/daily-compiler-quality.lock.yml +++ b/.github/workflows/daily-compiler-quality.lock.yml @@ -527,6 +527,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1375,6 +1376,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1402,6 +1404,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/daily-compiler-threat-spec-optimizer.lock.yml b/.github/workflows/daily-compiler-threat-spec-optimizer.lock.yml index 7a6d8cdd0dc..d70c6a73544 100644 --- a/.github/workflows/daily-compiler-threat-spec-optimizer.lock.yml +++ b/.github/workflows/daily-compiler-threat-spec-optimizer.lock.yml @@ -463,6 +463,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1246,6 +1247,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1273,6 +1275,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1504,6 +1507,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1511,6 +1515,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-credit-limit-test.lock.yml b/.github/workflows/daily-credit-limit-test.lock.yml index 8642f1e6f51..26c72ba002c 100644 --- a/.github/workflows/daily-credit-limit-test.lock.yml +++ b/.github/workflows/daily-credit-limit-test.lock.yml @@ -1075,6 +1075,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1310,6 +1311,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/daily-doc-healer.lock.yml b/.github/workflows/daily-doc-healer.lock.yml index a34c8ee8bcd..27c15f5a52d 100644 --- a/.github/workflows/daily-doc-healer.lock.yml +++ b/.github/workflows/daily-doc-healer.lock.yml @@ -521,6 +521,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1410,6 +1411,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1677,6 +1679,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1684,6 +1687,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-doc-updater.lock.yml b/.github/workflows/daily-doc-updater.lock.yml index 82a37f491e1..893b841695d 100644 --- a/.github/workflows/daily-doc-updater.lock.yml +++ b/.github/workflows/daily-doc-updater.lock.yml @@ -520,6 +520,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1267,6 +1268,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1535,6 +1537,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1542,6 +1545,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-documentation-diagram.lock.yml b/.github/workflows/daily-documentation-diagram.lock.yml index 09329670916..9e001345dd9 100644 --- a/.github/workflows/daily-documentation-diagram.lock.yml +++ b/.github/workflows/daily-documentation-diagram.lock.yml @@ -496,6 +496,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1247,6 +1248,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1499,6 +1501,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1506,6 +1509,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-ecosystem-explorer.lock.yml b/.github/workflows/daily-ecosystem-explorer.lock.yml index 82834ccd839..4de7c09eef4 100644 --- a/.github/workflows/daily-ecosystem-explorer.lock.yml +++ b/.github/workflows/daily-ecosystem-explorer.lock.yml @@ -456,6 +456,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1243,6 +1244,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1272,6 +1274,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1498,6 +1501,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1505,6 +1509,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-elixir-credo-snippet-audit.lock.yml b/.github/workflows/daily-elixir-credo-snippet-audit.lock.yml index 6921209746a..3e0fc8d8187 100644 --- a/.github/workflows/daily-elixir-credo-snippet-audit.lock.yml +++ b/.github/workflows/daily-elixir-credo-snippet-audit.lock.yml @@ -463,6 +463,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1228,6 +1229,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1483,6 +1485,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1490,6 +1493,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-evals-report.lock.yml b/.github/workflows/daily-evals-report.lock.yml index 647e4ceb777..292e5be1f7a 100644 --- a/.github/workflows/daily-evals-report.lock.yml +++ b/.github/workflows/daily-evals-report.lock.yml @@ -475,6 +475,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1251,6 +1252,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/daily-experiment-report.lock.yml b/.github/workflows/daily-experiment-report.lock.yml index f7705af0725..535f658b618 100644 --- a/.github/workflows/daily-experiment-report.lock.yml +++ b/.github/workflows/daily-experiment-report.lock.yml @@ -455,6 +455,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1295,6 +1296,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1322,6 +1324,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1544,6 +1547,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1551,6 +1555,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-fact.lock.yml b/.github/workflows/daily-fact.lock.yml index 035a1642948..ddf091d1ecd 100644 --- a/.github/workflows/daily-fact.lock.yml +++ b/.github/workflows/daily-fact.lock.yml @@ -510,6 +510,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1287,6 +1288,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1549,6 +1551,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1556,6 +1559,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-file-diet.lock.yml b/.github/workflows/daily-file-diet.lock.yml index ab8893cbb4a..3363a227332 100644 --- a/.github/workflows/daily-file-diet.lock.yml +++ b/.github/workflows/daily-file-diet.lock.yml @@ -455,6 +455,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1251,6 +1252,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1282,6 +1284,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1510,6 +1513,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1517,6 +1521,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-firewall-report.lock.yml b/.github/workflows/daily-firewall-report.lock.yml index 5893aec9d9e..e6e46ef020d 100644 --- a/.github/workflows/daily-firewall-report.lock.yml +++ b/.github/workflows/daily-firewall-report.lock.yml @@ -485,6 +485,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1347,6 +1348,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1374,6 +1376,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/daily-formal-spec-verifier.lock.yml b/.github/workflows/daily-formal-spec-verifier.lock.yml index aca2363d2cd..607e31cf0c8 100644 --- a/.github/workflows/daily-formal-spec-verifier.lock.yml +++ b/.github/workflows/daily-formal-spec-verifier.lock.yml @@ -466,6 +466,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1280,6 +1281,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1307,6 +1309,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1521,12 +1524,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-function-namer.lock.yml b/.github/workflows/daily-function-namer.lock.yml index 05e8130b0b9..0e5363d6a0e 100644 --- a/.github/workflows/daily-function-namer.lock.yml +++ b/.github/workflows/daily-function-namer.lock.yml @@ -1205,6 +1205,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1459,6 +1460,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/daily-geo-optimizer.lock.yml b/.github/workflows/daily-geo-optimizer.lock.yml index b7cf57e1f90..de97afbf4dd 100644 --- a/.github/workflows/daily-geo-optimizer.lock.yml +++ b/.github/workflows/daily-geo-optimizer.lock.yml @@ -445,6 +445,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1198,6 +1199,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1225,6 +1227,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1451,6 +1454,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1458,6 +1462,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-github-docs-seo-optimizer.lock.yml b/.github/workflows/daily-github-docs-seo-optimizer.lock.yml index 128c1d16d00..33ff190b3d0 100644 --- a/.github/workflows/daily-github-docs-seo-optimizer.lock.yml +++ b/.github/workflows/daily-github-docs-seo-optimizer.lock.yml @@ -407,6 +407,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1076,6 +1077,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1103,6 +1105,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1322,6 +1325,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1329,6 +1333,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-go-test-parallelizer.lock.yml b/.github/workflows/daily-go-test-parallelizer.lock.yml index 181d5dc3981..b766da0d0db 100644 --- a/.github/workflows/daily-go-test-parallelizer.lock.yml +++ b/.github/workflows/daily-go-test-parallelizer.lock.yml @@ -468,6 +468,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1221,6 +1222,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1470,6 +1472,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1477,6 +1480,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-go-test-stubs-aider.lock.yml b/.github/workflows/daily-go-test-stubs-aider.lock.yml index bf84c16dce8..a6af8ee29c0 100644 --- a/.github/workflows/daily-go-test-stubs-aider.lock.yml +++ b/.github/workflows/daily-go-test-stubs-aider.lock.yml @@ -1,4 +1,4 @@ -# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"6819e667bbd000e63113ec0f6c33c3350a36a2655f9b1d2e8457891e193fbb97","body_hash":"99eb80ec2bce3938e2af26781db1b953a94cbe316d91805fc07cde14c6ecd1b9","strict":true,"agent_id":"aider","agent_model":"copilot/auto","engine_versions":{"aider":"0.86.2"}} +# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"43085e285e0ec2ade145546111e6aeefe6c46592d82130ef0ff8ed053b6f6b7d","body_hash":"99eb80ec2bce3938e2af26781db1b953a94cbe316d91805fc07cde14c6ecd1b9","strict":true,"agent_id":"aider","agent_model":"copilot/auto","engine_versions":{"aider":"0.86.2"}} # gh-aw-manifest: {"version":1,"secrets":["GH_AW_CI_TRIGGER_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GH_AW_OTEL_GRAFANA_AUTHORIZATION","GH_AW_OTEL_GRAFANA_ENDPOINT","GH_AW_OTEL_SENTRY_AUTHORIZATION","GH_AW_OTEL_SENTRY_ENDPOINT","GITHUB_TOKEN"],"actions":[{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/download-artifact","sha":"9000827ccba6bdab643e8b6fd33ac0654aef8333","version":"v8.0.2"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"949feb2413d6458794dcd2491c4babbbce0c15c1","version":"v7.1.0"},{"repo":"actions/setup-python","sha":"5fda3b95a4ea91299a34e894583c3862153e4b97","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"cf430e030ddbb5b0abf93d22962f4752f3646cd9","version":"v7.0.2"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50","digest":"sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50@sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50","digest":"sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50@sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965"},{"image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50","digest":"sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce","pinned_image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50@sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50","digest":"sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50@sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.30","digest":"sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.30@sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f","pinned_image":"ghcr.io/github/gh-aw-node@sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f"},{"image":"ghcr.io/github/github-mcp-server:v1.12.2","digest":"sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6","pinned_image":"ghcr.io/github/github-mcp-server:v1.12.2@sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6"}],"mcp_servers":[{"name":"safeoutputs","tools":["create_pull_request","missing_data","missing_tool","noop","report_incomplete"]}],"threat_detection":{"mode":"enabled"}} # This file was automatically generated by gh-aw. DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md # @@ -1041,6 +1041,7 @@ jobs: "mcp.guard.blocked", "mcp.tool_call", "mcp.event", "firewall.http_access", "firewall.token_usage", "firewall.model_routing", "firewall.steering", "firewall.event", "model_routing.outcome", + "model_endpoint.mismatch", "safe_output.request", "safe_output.result", "safe_output.error", "experiment.state", "experiment.assignment", "grader.manifest", "grader.result", "eval.result", "github_api.rate_limit", "usage.report", "execution.result", @@ -1542,6 +1543,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1784,6 +1786,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_FAILURE_ISSUE_NUMBER: ${{ needs.activation.outputs.steering_issue_number }} diff --git a/.github/workflows/daily-grader-audit.lock.yml b/.github/workflows/daily-grader-audit.lock.yml index 5d88f7bccd6..aadfa24e892 100644 --- a/.github/workflows/daily-grader-audit.lock.yml +++ b/.github/workflows/daily-grader-audit.lock.yml @@ -439,6 +439,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1245,6 +1246,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1497,6 +1499,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1504,6 +1507,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-graft-intelligence.lock.yml b/.github/workflows/daily-graft-intelligence.lock.yml index 27d9dc10d7d..ed673504edc 100644 --- a/.github/workflows/daily-graft-intelligence.lock.yml +++ b/.github/workflows/daily-graft-intelligence.lock.yml @@ -438,6 +438,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1216,6 +1217,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1243,6 +1245,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1467,6 +1470,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1474,6 +1478,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-harness-experiment-proposer.lock.yml b/.github/workflows/daily-harness-experiment-proposer.lock.yml index 8fd12308679..52cf6ba4b71 100644 --- a/.github/workflows/daily-harness-experiment-proposer.lock.yml +++ b/.github/workflows/daily-harness-experiment-proposer.lock.yml @@ -461,6 +461,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1265,6 +1266,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1489,6 +1491,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-hippo-learn.lock.yml b/.github/workflows/daily-hippo-learn.lock.yml index 3eeec28c8a6..91672b27846 100644 --- a/.github/workflows/daily-hippo-learn.lock.yml +++ b/.github/workflows/daily-hippo-learn.lock.yml @@ -1296,6 +1296,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1551,6 +1552,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/daily-issues-report.lock.yml b/.github/workflows/daily-issues-report.lock.yml index 1f3127588df..1afde127c7f 100644 --- a/.github/workflows/daily-issues-report.lock.yml +++ b/.github/workflows/daily-issues-report.lock.yml @@ -543,6 +543,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1546,6 +1547,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1575,6 +1577,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/daily-malicious-code-scan.lock.yml b/.github/workflows/daily-malicious-code-scan.lock.yml index f8a2216b04e..76b677cc87d 100644 --- a/.github/workflows/daily-malicious-code-scan.lock.yml +++ b/.github/workflows/daily-malicious-code-scan.lock.yml @@ -438,6 +438,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1170,6 +1171,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1197,6 +1199,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1396,6 +1399,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-max-ai-credits-test.lock.yml b/.github/workflows/daily-max-ai-credits-test.lock.yml index 70f53dad746..c45cecd25b3 100644 --- a/.github/workflows/daily-max-ai-credits-test.lock.yml +++ b/.github/workflows/daily-max-ai-credits-test.lock.yml @@ -378,6 +378,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1051,6 +1052,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1284,12 +1286,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "1" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-mcp-concurrency-analysis.lock.yml b/.github/workflows/daily-mcp-concurrency-analysis.lock.yml index 48a365f1047..a81af768c7b 100644 --- a/.github/workflows/daily-mcp-concurrency-analysis.lock.yml +++ b/.github/workflows/daily-mcp-concurrency-analysis.lock.yml @@ -454,6 +454,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1408,6 +1409,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1435,6 +1437,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1662,6 +1665,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1669,6 +1673,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-model-inventory.lock.yml b/.github/workflows/daily-model-inventory.lock.yml index 4c5381b48d8..3b1ed86dbf6 100644 --- a/.github/workflows/daily-model-inventory.lock.yml +++ b/.github/workflows/daily-model-inventory.lock.yml @@ -442,6 +442,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1177,6 +1178,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1204,6 +1206,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1747,6 +1750,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1754,6 +1758,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-model-resolution.lock.yml b/.github/workflows/daily-model-resolution.lock.yml index b6b6d2ce7a8..c8e48f80199 100644 --- a/.github/workflows/daily-model-resolution.lock.yml +++ b/.github/workflows/daily-model-resolution.lock.yml @@ -449,6 +449,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1213,6 +1214,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1240,6 +1242,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1454,12 +1457,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-multi-device-docs-tester.lock.yml b/.github/workflows/daily-multi-device-docs-tester.lock.yml index 70e4b24bf87..bf48baab5c4 100644 --- a/.github/workflows/daily-multi-device-docs-tester.lock.yml +++ b/.github/workflows/daily-multi-device-docs-tester.lock.yml @@ -1215,6 +1215,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1468,6 +1469,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/daily-news.lock.yml b/.github/workflows/daily-news.lock.yml index ba2213f8ab0..9ac739ae86d 100644 --- a/.github/workflows/daily-news.lock.yml +++ b/.github/workflows/daily-news.lock.yml @@ -1417,6 +1417,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1683,6 +1684,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/daily-observability-report.lock.yml b/.github/workflows/daily-observability-report.lock.yml index cc706a6e28a..d1d0dd87819 100644 --- a/.github/workflows/daily-observability-report.lock.yml +++ b/.github/workflows/daily-observability-report.lock.yml @@ -480,6 +480,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1248,6 +1249,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/daily-performance-summary.lock.yml b/.github/workflows/daily-performance-summary.lock.yml index f34cb3d28cd..246402f4365 100644 --- a/.github/workflows/daily-performance-summary.lock.yml +++ b/.github/workflows/daily-performance-summary.lock.yml @@ -1853,6 +1853,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -2109,6 +2110,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/daily-pr-review-cursor.lock.yml b/.github/workflows/daily-pr-review-cursor.lock.yml index 97455bef53f..98ed0d96f7e 100644 --- a/.github/workflows/daily-pr-review-cursor.lock.yml +++ b/.github/workflows/daily-pr-review-cursor.lock.yml @@ -440,6 +440,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1158,6 +1159,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1185,6 +1187,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1400,12 +1403,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-regression-audit-kiro.lock.yml b/.github/workflows/daily-regression-audit-kiro.lock.yml index 28c1a503f15..1e22c9a719d 100644 --- a/.github/workflows/daily-regression-audit-kiro.lock.yml +++ b/.github/workflows/daily-regression-audit-kiro.lock.yml @@ -441,6 +441,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1161,6 +1162,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1188,6 +1190,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1403,12 +1406,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-regulatory.lock.yml b/.github/workflows/daily-regulatory.lock.yml index 20cf9315ccf..25328d072bd 100644 --- a/.github/workflows/daily-regulatory.lock.yml +++ b/.github/workflows/daily-regulatory.lock.yml @@ -473,6 +473,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1856,6 +1857,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/daily-reliability-review.lock.yml b/.github/workflows/daily-reliability-review.lock.yml index 10bafb6def9..f73afe25bd5 100644 --- a/.github/workflows/daily-reliability-review.lock.yml +++ b/.github/workflows/daily-reliability-review.lock.yml @@ -446,6 +446,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1212,6 +1213,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1239,6 +1241,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1465,6 +1468,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1472,6 +1476,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-rendering-scripts-verifier.lock.yml b/.github/workflows/daily-rendering-scripts-verifier.lock.yml index bce88b486df..84dd5020d1c 100644 --- a/.github/workflows/daily-rendering-scripts-verifier.lock.yml +++ b/.github/workflows/daily-rendering-scripts-verifier.lock.yml @@ -538,6 +538,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1490,6 +1491,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1763,6 +1765,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1770,6 +1773,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-repo-chronicle.lock.yml b/.github/workflows/daily-repo-chronicle.lock.yml index 6c6adabc379..76a39c9436b 100644 --- a/.github/workflows/daily-repo-chronicle.lock.yml +++ b/.github/workflows/daily-repo-chronicle.lock.yml @@ -1252,6 +1252,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/daily-report-dispatcher.lock.yml b/.github/workflows/daily-report-dispatcher.lock.yml index 4998d0d0835..c26c5ed0e6c 100644 --- a/.github/workflows/daily-report-dispatcher.lock.yml +++ b/.github/workflows/daily-report-dispatcher.lock.yml @@ -448,6 +448,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1199,6 +1200,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1226,6 +1228,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/daily-safe-output-integrator.lock.yml b/.github/workflows/daily-safe-output-integrator.lock.yml index 7494480dabb..816b6d725a4 100644 --- a/.github/workflows/daily-safe-output-integrator.lock.yml +++ b/.github/workflows/daily-safe-output-integrator.lock.yml @@ -458,6 +458,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1209,6 +1210,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1236,6 +1238,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1464,6 +1467,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1471,6 +1475,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-safe-output-optimizer.lock.yml b/.github/workflows/daily-safe-output-optimizer.lock.yml index db119efa323..acd1530b5fa 100644 --- a/.github/workflows/daily-safe-output-optimizer.lock.yml +++ b/.github/workflows/daily-safe-output-optimizer.lock.yml @@ -515,6 +515,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1398,6 +1399,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1656,6 +1658,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1663,6 +1666,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-safe-outputs-conformance.lock.yml b/.github/workflows/daily-safe-outputs-conformance.lock.yml index c0ba401f589..cf44adee2b5 100644 --- a/.github/workflows/daily-safe-outputs-conformance.lock.yml +++ b/.github/workflows/daily-safe-outputs-conformance.lock.yml @@ -443,6 +443,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1204,6 +1205,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1456,6 +1458,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1463,6 +1466,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-safeoutputs-git-simulator.lock.yml b/.github/workflows/daily-safeoutputs-git-simulator.lock.yml index 851e26f0ed3..4d1fad78aa0 100644 --- a/.github/workflows/daily-safeoutputs-git-simulator.lock.yml +++ b/.github/workflows/daily-safeoutputs-git-simulator.lock.yml @@ -468,6 +468,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1344,6 +1345,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1595,6 +1597,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1602,6 +1605,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-schema-audit-cursor.lock.yml b/.github/workflows/daily-schema-audit-cursor.lock.yml index 0152aaed949..5475c85b068 100644 --- a/.github/workflows/daily-schema-audit-cursor.lock.yml +++ b/.github/workflows/daily-schema-audit-cursor.lock.yml @@ -439,6 +439,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1157,6 +1158,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1184,6 +1186,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1399,12 +1402,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-secrets-analysis.lock.yml b/.github/workflows/daily-secrets-analysis.lock.yml index 0c717627dc2..1c569631064 100644 --- a/.github/workflows/daily-secrets-analysis.lock.yml +++ b/.github/workflows/daily-secrets-analysis.lock.yml @@ -474,6 +474,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1248,6 +1249,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1275,6 +1277,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/daily-security-observability.lock.yml b/.github/workflows/daily-security-observability.lock.yml index 8268b4a9104..ba8c10c9696 100644 --- a/.github/workflows/daily-security-observability.lock.yml +++ b/.github/workflows/daily-security-observability.lock.yml @@ -474,6 +474,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1346,6 +1347,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1373,6 +1375,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1602,6 +1605,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1609,6 +1613,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-security-red-team.lock.yml b/.github/workflows/daily-security-red-team.lock.yml index a71291701ff..9083375862e 100644 --- a/.github/workflows/daily-security-red-team.lock.yml +++ b/.github/workflows/daily-security-red-team.lock.yml @@ -1405,6 +1405,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1667,6 +1668,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/daily-semgrep-scan.lock.yml b/.github/workflows/daily-semgrep-scan.lock.yml index eeb7e3c8f9b..8d66914c0ba 100644 --- a/.github/workflows/daily-semgrep-scan.lock.yml +++ b/.github/workflows/daily-semgrep-scan.lock.yml @@ -485,6 +485,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1163,6 +1164,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1421,6 +1423,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1428,6 +1431,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-spdd-spec-planner.lock.yml b/.github/workflows/daily-spdd-spec-planner.lock.yml index 445de840490..a70858cd19a 100644 --- a/.github/workflows/daily-spdd-spec-planner.lock.yml +++ b/.github/workflows/daily-spdd-spec-planner.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1216,6 +1217,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1243,6 +1245,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1468,6 +1471,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1475,6 +1479,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-spec-coverage-kiro.lock.yml b/.github/workflows/daily-spec-coverage-kiro.lock.yml index fe853c22813..43a082209c7 100644 --- a/.github/workflows/daily-spec-coverage-kiro.lock.yml +++ b/.github/workflows/daily-spec-coverage-kiro.lock.yml @@ -440,6 +440,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1158,6 +1159,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1185,6 +1187,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1400,12 +1403,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-spending-forecast.lock.yml b/.github/workflows/daily-spending-forecast.lock.yml index b7b2e4ce0a2..8e291d65fb3 100644 --- a/.github/workflows/daily-spending-forecast.lock.yml +++ b/.github/workflows/daily-spending-forecast.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1303,6 +1304,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1550,6 +1552,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1557,6 +1560,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-squid-image-scan.lock.yml b/.github/workflows/daily-squid-image-scan.lock.yml index 245949f5fdf..0e283bfef64 100644 --- a/.github/workflows/daily-squid-image-scan.lock.yml +++ b/.github/workflows/daily-squid-image-scan.lock.yml @@ -422,6 +422,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1303,6 +1304,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1330,6 +1332,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1549,6 +1552,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1556,6 +1560,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-storify.lock.yml b/.github/workflows/daily-storify.lock.yml index 67760331329..4ca19adc43a 100644 --- a/.github/workflows/daily-storify.lock.yml +++ b/.github/workflows/daily-storify.lock.yml @@ -476,6 +476,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1295,6 +1296,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1549,6 +1551,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1556,6 +1559,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-syntax-error-quality.lock.yml b/.github/workflows/daily-syntax-error-quality.lock.yml index a22a33e7408..db0a976393c 100644 --- a/.github/workflows/daily-syntax-error-quality.lock.yml +++ b/.github/workflows/daily-syntax-error-quality.lock.yml @@ -434,6 +434,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1150,6 +1151,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1177,6 +1179,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1401,6 +1404,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1408,6 +1412,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-team-evolution-insights.lock.yml b/.github/workflows/daily-team-evolution-insights.lock.yml index 931d7ffa140..351ad7442c1 100644 --- a/.github/workflows/daily-team-evolution-insights.lock.yml +++ b/.github/workflows/daily-team-evolution-insights.lock.yml @@ -1292,6 +1292,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/daily-team-status.lock.yml b/.github/workflows/daily-team-status.lock.yml index 7c4acb6f94f..59bf2c49a54 100644 --- a/.github/workflows/daily-team-status.lock.yml +++ b/.github/workflows/daily-team-status.lock.yml @@ -436,6 +436,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1165,6 +1166,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1194,6 +1196,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1409,12 +1412,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-testify-uber-super-expert.lock.yml b/.github/workflows/daily-testify-uber-super-expert.lock.yml index 33d21b7a9fa..698a4c2681f 100644 --- a/.github/workflows/daily-testify-uber-super-expert.lock.yml +++ b/.github/workflows/daily-testify-uber-super-expert.lock.yml @@ -467,6 +467,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1264,6 +1265,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1291,6 +1293,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1504,12 +1507,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-token-consumption-report.lock.yml b/.github/workflows/daily-token-consumption-report.lock.yml index 4343190cbeb..946cc00e5bd 100644 --- a/.github/workflows/daily-token-consumption-report.lock.yml +++ b/.github/workflows/daily-token-consumption-report.lock.yml @@ -1387,6 +1387,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/daily-trajectory-grader-implementer.lock.yml b/.github/workflows/daily-trajectory-grader-implementer.lock.yml index c67a216b2af..5fe2cc6f711 100644 --- a/.github/workflows/daily-trajectory-grader-implementer.lock.yml +++ b/.github/workflows/daily-trajectory-grader-implementer.lock.yml @@ -464,6 +464,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1237,6 +1238,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1267,6 +1269,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1488,12 +1491,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-vulnhunter-scan.lock.yml b/.github/workflows/daily-vulnhunter-scan.lock.yml index 5a1e523bfd4..61617165113 100644 --- a/.github/workflows/daily-vulnhunter-scan.lock.yml +++ b/.github/workflows/daily-vulnhunter-scan.lock.yml @@ -443,6 +443,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1180,6 +1181,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1427,6 +1429,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1434,6 +1437,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-windows-defender-scan.lock.yml b/.github/workflows/daily-windows-defender-scan.lock.yml index a712c40279d..190d04006db 100644 --- a/.github/workflows/daily-windows-defender-scan.lock.yml +++ b/.github/workflows/daily-windows-defender-scan.lock.yml @@ -440,6 +440,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1192,6 +1193,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1432,12 +1434,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-windows-terminal-integration-builder.lock.yml b/.github/workflows/daily-windows-terminal-integration-builder.lock.yml index 08802e4dd20..611cec6ec91 100644 --- a/.github/workflows/daily-windows-terminal-integration-builder.lock.yml +++ b/.github/workflows/daily-windows-terminal-integration-builder.lock.yml @@ -439,6 +439,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1119,6 +1120,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1365,6 +1367,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1372,6 +1375,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-work-queue-formal-verification.lock.yml b/.github/workflows/daily-work-queue-formal-verification.lock.yml index 31e497e7ec7..a68ce5a4812 100644 --- a/.github/workflows/daily-work-queue-formal-verification.lock.yml +++ b/.github/workflows/daily-work-queue-formal-verification.lock.yml @@ -426,6 +426,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1163,6 +1164,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1350,12 +1352,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-work-queues-report.lock.yml b/.github/workflows/daily-work-queues-report.lock.yml index 6443b5faf0c..517ab12529a 100644 --- a/.github/workflows/daily-work-queues-report.lock.yml +++ b/.github/workflows/daily-work-queues-report.lock.yml @@ -452,6 +452,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1185,6 +1186,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1212,6 +1214,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1439,12 +1442,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-workflow-security-model.lock.yml b/.github/workflows/daily-workflow-security-model.lock.yml index 12d1bffc530..602941e3a1d 100644 --- a/.github/workflows/daily-workflow-security-model.lock.yml +++ b/.github/workflows/daily-workflow-security-model.lock.yml @@ -443,6 +443,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1282,6 +1283,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1309,6 +1311,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1518,12 +1521,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-workflow-updater.lock.yml b/.github/workflows/daily-workflow-updater.lock.yml index 3ba90977fef..e3c88e8f501 100644 --- a/.github/workflows/daily-workflow-updater.lock.yml +++ b/.github/workflows/daily-workflow-updater.lock.yml @@ -452,6 +452,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1175,6 +1176,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1202,6 +1204,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1429,6 +1432,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1436,6 +1440,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/daily-yamllint-fixer.lock.yml b/.github/workflows/daily-yamllint-fixer.lock.yml index 406a5554e02..0fa882d1068 100644 --- a/.github/workflows/daily-yamllint-fixer.lock.yml +++ b/.github/workflows/daily-yamllint-fixer.lock.yml @@ -471,6 +471,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1235,6 +1236,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1486,6 +1488,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1493,6 +1496,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/dataflow-pr-discussion-dataset.lock.yml b/.github/workflows/dataflow-pr-discussion-dataset.lock.yml index 247b974c499..147c2b1e84a 100644 --- a/.github/workflows/dataflow-pr-discussion-dataset.lock.yml +++ b/.github/workflows/dataflow-pr-discussion-dataset.lock.yml @@ -508,6 +508,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1573,6 +1574,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1602,6 +1604,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1840,6 +1843,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1847,6 +1851,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/dead-code-remover.lock.yml b/.github/workflows/dead-code-remover.lock.yml index 9c11dbd6f25..752103aacba 100644 --- a/.github/workflows/dead-code-remover.lock.yml +++ b/.github/workflows/dead-code-remover.lock.yml @@ -480,6 +480,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1248,6 +1249,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1275,6 +1277,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1486,12 +1489,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/deep-report.lock.yml b/.github/workflows/deep-report.lock.yml index ec2258eadb9..456e360c87e 100644 --- a/.github/workflows/deep-report.lock.yml +++ b/.github/workflows/deep-report.lock.yml @@ -546,6 +546,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -2037,6 +2038,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/deepsec-security-scan.lock.yml b/.github/workflows/deepsec-security-scan.lock.yml index 03f508db9f7..7bdce08e2ac 100644 --- a/.github/workflows/deepsec-security-scan.lock.yml +++ b/.github/workflows/deepsec-security-scan.lock.yml @@ -472,6 +472,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1194,6 +1195,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1439,6 +1441,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "false" @@ -1446,6 +1449,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/delight.lock.yml b/.github/workflows/delight.lock.yml index 14679b80d7b..cfdf66b8014 100644 --- a/.github/workflows/delight.lock.yml +++ b/.github/workflows/delight.lock.yml @@ -451,6 +451,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1262,6 +1263,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1289,6 +1291,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1515,6 +1518,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1522,6 +1526,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/dependabot-burner.lock.yml b/.github/workflows/dependabot-burner.lock.yml index 253dc064f74..03174504fac 100644 --- a/.github/workflows/dependabot-burner.lock.yml +++ b/.github/workflows/dependabot-burner.lock.yml @@ -539,6 +539,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1341,6 +1342,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1368,6 +1370,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1593,6 +1596,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1600,6 +1604,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/dependabot-go-checker.lock.yml b/.github/workflows/dependabot-go-checker.lock.yml index 3a06f6076a4..1a5ff63da07 100644 --- a/.github/workflows/dependabot-go-checker.lock.yml +++ b/.github/workflows/dependabot-go-checker.lock.yml @@ -488,6 +488,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1227,6 +1228,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1483,6 +1485,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1490,6 +1493,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/deployment-incident-monitor.lock.yml b/.github/workflows/deployment-incident-monitor.lock.yml index 7aba91a4110..4e75bdb22d1 100644 --- a/.github/workflows/deployment-incident-monitor.lock.yml +++ b/.github/workflows/deployment-incident-monitor.lock.yml @@ -453,6 +453,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1155,6 +1156,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1182,6 +1184,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1402,6 +1405,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1409,6 +1413,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/design-decision-gate.lock.yml b/.github/workflows/design-decision-gate.lock.yml index c2b63c98f11..7412a9f005d 100644 --- a/.github/workflows/design-decision-gate.lock.yml +++ b/.github/workflows/design-decision-gate.lock.yml @@ -1228,6 +1228,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1476,6 +1477,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/designer-drift-audit.lock.yml b/.github/workflows/designer-drift-audit.lock.yml index fb1c0c3b1b4..e5673e786e7 100644 --- a/.github/workflows/designer-drift-audit.lock.yml +++ b/.github/workflows/designer-drift-audit.lock.yml @@ -434,6 +434,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1121,6 +1122,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1355,12 +1357,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/detection-analysis-report.lock.yml b/.github/workflows/detection-analysis-report.lock.yml index 68341c97574..5b9b0721da6 100644 --- a/.github/workflows/detection-analysis-report.lock.yml +++ b/.github/workflows/detection-analysis-report.lock.yml @@ -465,6 +465,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1341,6 +1342,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1595,6 +1597,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1602,6 +1605,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/dev-hawk.lock.yml b/.github/workflows/dev-hawk.lock.yml index 3ad6a1f24a0..5d49da07b4e 100644 --- a/.github/workflows/dev-hawk.lock.yml +++ b/.github/workflows/dev-hawk.lock.yml @@ -474,6 +474,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1255,6 +1256,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1282,6 +1284,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1500,6 +1503,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1507,6 +1511,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/developer-docs-consolidator.lock.yml b/.github/workflows/developer-docs-consolidator.lock.yml index d55c71fe8cc..7de109df83c 100644 --- a/.github/workflows/developer-docs-consolidator.lock.yml +++ b/.github/workflows/developer-docs-consolidator.lock.yml @@ -495,6 +495,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1421,6 +1422,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1674,6 +1676,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1681,6 +1684,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/dictation-prompt.lock.yml b/.github/workflows/dictation-prompt.lock.yml index 41996305f9d..02a61feb3cc 100644 --- a/.github/workflows/dictation-prompt.lock.yml +++ b/.github/workflows/dictation-prompt.lock.yml @@ -453,6 +453,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1176,6 +1177,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1203,6 +1205,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1425,6 +1428,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1432,6 +1436,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/docs-noob-tester.lock.yml b/.github/workflows/docs-noob-tester.lock.yml index cb4884862c8..9dd4d009a7f 100644 --- a/.github/workflows/docs-noob-tester.lock.yml +++ b/.github/workflows/docs-noob-tester.lock.yml @@ -441,6 +441,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1198,6 +1199,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1225,6 +1227,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1446,6 +1449,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1453,6 +1457,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/draft-pr-cleanup.lock.yml b/.github/workflows/draft-pr-cleanup.lock.yml index 77dd0677a75..fd04f35ad8b 100644 --- a/.github/workflows/draft-pr-cleanup.lock.yml +++ b/.github/workflows/draft-pr-cleanup.lock.yml @@ -431,6 +431,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1187,6 +1188,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1214,6 +1216,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1433,6 +1436,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1440,6 +1444,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/duplicate-code-detector.lock.yml b/.github/workflows/duplicate-code-detector.lock.yml index e2d4272e237..e2de737a02c 100644 --- a/.github/workflows/duplicate-code-detector.lock.yml +++ b/.github/workflows/duplicate-code-detector.lock.yml @@ -1134,6 +1134,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1381,6 +1382,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/engine-conformance-aider.lock.yml b/.github/workflows/engine-conformance-aider.lock.yml index db6bf80b709..9fd05aed4c3 100644 --- a/.github/workflows/engine-conformance-aider.lock.yml +++ b/.github/workflows/engine-conformance-aider.lock.yml @@ -1,4 +1,4 @@ -# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"6b95f91340c46d3108c818e3405625cce4bc74331c8811deee8c489d8ccbd46d","body_hash":"07595cb78705e3076f05c86c91a3ac8249cbe4915b41a419acd31b5ec956ca36","strict":true,"agent_id":"aider","agent_model":"copilot/gpt-5.4","engine_versions":{"aider":"0.86.2"}} +# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"a0d366a67887bf0a2a42b5e40f67a3010d15b5825a4a16ba86957e4cc31e4af7","body_hash":"07595cb78705e3076f05c86c91a3ac8249cbe4915b41a419acd31b5ec956ca36","strict":true,"agent_id":"aider","agent_model":"copilot/gpt-5.4","engine_versions":{"aider":"0.86.2"}} # gh-aw-manifest: {"version":1,"secrets":["GH_AW_DEFAULT_OTLP_ENDPOINT","GH_AW_DEFAULT_OTLP_HEADERS","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GITHUB_TOKEN"],"actions":[{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/download-artifact","sha":"9000827ccba6bdab643e8b6fd33ac0654aef8333","version":"v8.0.2"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"949feb2413d6458794dcd2491c4babbbce0c15c1","version":"v7.1.0"},{"repo":"actions/setup-python","sha":"5fda3b95a4ea91299a34e894583c3862153e4b97","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"cf430e030ddbb5b0abf93d22962f4752f3646cd9","version":"v7.0.2"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50","digest":"sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50@sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50","digest":"sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50@sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965"},{"image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50","digest":"sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce","pinned_image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50@sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50","digest":"sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50@sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.30","digest":"sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.30@sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f","pinned_image":"ghcr.io/github/gh-aw-node@sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f"},{"image":"ghcr.io/github/github-mcp-server:v1.12.2","digest":"sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6","pinned_image":"ghcr.io/github/github-mcp-server:v1.12.2@sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6"}],"mcp_servers":[{"name":"mcpscripts","tools":["conformance-challenge"]},{"name":"safeoutputs","tools":["create_issue","missing_data","missing_tool","noop","report_incomplete"]},{"name":"work-queue","tools":["work_queue_claim_finish","work_queue_dispatch_next","work_queue_explain","work_queue_read","work_queue_submit"]}],"threat_detection":{"mode":"disabled"}} # This file was automatically generated by gh-aw. DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md # @@ -1185,6 +1185,7 @@ jobs: "mcp.guard.blocked", "mcp.tool_call", "mcp.event", "firewall.http_access", "firewall.token_usage", "firewall.model_routing", "firewall.steering", "firewall.event", "model_routing.outcome", + "model_endpoint.mismatch", "safe_output.request", "safe_output.result", "safe_output.error", "experiment.state", "experiment.assignment", "grader.manifest", "grader.result", "eval.result", "github_api.rate_limit", "usage.report", "execution.result", diff --git a/.github/workflows/engine-conformance-claude.lock.yml b/.github/workflows/engine-conformance-claude.lock.yml index 6b1de9e00ed..4b69bd091ab 100644 --- a/.github/workflows/engine-conformance-claude.lock.yml +++ b/.github/workflows/engine-conformance-claude.lock.yml @@ -419,6 +419,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} diff --git a/.github/workflows/engine-conformance-codex.lock.yml b/.github/workflows/engine-conformance-codex.lock.yml index aa42c81b189..c84d71f695c 100644 --- a/.github/workflows/engine-conformance-codex.lock.yml +++ b/.github/workflows/engine-conformance-codex.lock.yml @@ -421,6 +421,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} diff --git a/.github/workflows/engine-conformance-copilot.lock.yml b/.github/workflows/engine-conformance-copilot.lock.yml index af1283ea44a..94f063fa3ab 100644 --- a/.github/workflows/engine-conformance-copilot.lock.yml +++ b/.github/workflows/engine-conformance-copilot.lock.yml @@ -411,6 +411,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1272,6 +1273,7 @@ jobs: /tmp/gh-aw/mcp-scripts/logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/engine-conformance-dispatcher.lock.yml b/.github/workflows/engine-conformance-dispatcher.lock.yml index f6ae83808af..8f73b6cee60 100644 --- a/.github/workflows/engine-conformance-dispatcher.lock.yml +++ b/.github/workflows/engine-conformance-dispatcher.lock.yml @@ -450,6 +450,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1201,6 +1202,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1228,6 +1230,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/eslint-factory-dispatcher.lock.yml b/.github/workflows/eslint-factory-dispatcher.lock.yml index 42c3aad59b4..980759c17ff 100644 --- a/.github/workflows/eslint-factory-dispatcher.lock.yml +++ b/.github/workflows/eslint-factory-dispatcher.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1197,6 +1198,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1224,6 +1226,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/eslint-miner.lock.yml b/.github/workflows/eslint-miner.lock.yml index 3de7db5e65f..3e78e15b44f 100644 --- a/.github/workflows/eslint-miner.lock.yml +++ b/.github/workflows/eslint-miner.lock.yml @@ -484,6 +484,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1302,6 +1303,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1329,6 +1331,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl diff --git a/.github/workflows/eslint-monster.lock.yml b/.github/workflows/eslint-monster.lock.yml index c7ed41b2497..8d49805dee1 100644 --- a/.github/workflows/eslint-monster.lock.yml +++ b/.github/workflows/eslint-monster.lock.yml @@ -466,6 +466,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1372,6 +1373,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/eslint-refiner.lock.yml b/.github/workflows/eslint-refiner.lock.yml index 6c38b1d7e51..7d84b40b52e 100644 --- a/.github/workflows/eslint-refiner.lock.yml +++ b/.github/workflows/eslint-refiner.lock.yml @@ -467,6 +467,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1367,6 +1368,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/evoskill-evolver.lock.yml b/.github/workflows/evoskill-evolver.lock.yml index 025d16bd507..ed679c3a755 100644 --- a/.github/workflows/evoskill-evolver.lock.yml +++ b/.github/workflows/evoskill-evolver.lock.yml @@ -462,6 +462,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1242,6 +1243,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1269,6 +1271,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1497,6 +1500,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1504,6 +1508,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/example-failure-category-filter.lock.yml b/.github/workflows/example-failure-category-filter.lock.yml index 707494e13f6..7e1c4a98851 100644 --- a/.github/workflows/example-failure-category-filter.lock.yml +++ b/.github/workflows/example-failure-category-filter.lock.yml @@ -428,6 +428,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1107,6 +1108,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1341,12 +1343,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/example-permissions-warning.lock.yml b/.github/workflows/example-permissions-warning.lock.yml index e0485a61c63..12ec6b61169 100644 --- a/.github/workflows/example-permissions-warning.lock.yml +++ b/.github/workflows/example-permissions-warning.lock.yml @@ -436,6 +436,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1157,6 +1158,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/example-workflow-analyzer.lock.yml b/.github/workflows/example-workflow-analyzer.lock.yml index 63dfb38ae8f..a9618234d78 100644 --- a/.github/workflows/example-workflow-analyzer.lock.yml +++ b/.github/workflows/example-workflow-analyzer.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1228,6 +1229,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1463,12 +1465,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/feature-grower.lock.yml b/.github/workflows/feature-grower.lock.yml index 4374ae53863..e4419aee1e6 100644 --- a/.github/workflows/feature-grower.lock.yml +++ b/.github/workflows/feature-grower.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1167,6 +1168,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1402,12 +1404,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/firewall-escape.lock.yml b/.github/workflows/firewall-escape.lock.yml index ea80d4456d1..656acab4454 100644 --- a/.github/workflows/firewall-escape.lock.yml +++ b/.github/workflows/firewall-escape.lock.yml @@ -487,6 +487,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1248,6 +1249,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1275,6 +1277,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1491,12 +1494,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/firewall.lock.yml b/.github/workflows/firewall.lock.yml index 706909013ea..05d523860cc 100644 --- a/.github/workflows/firewall.lock.yml +++ b/.github/workflows/firewall.lock.yml @@ -431,6 +431,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1080,6 +1081,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1193,6 +1195,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/front-page-copy-guard.lock.yml b/.github/workflows/front-page-copy-guard.lock.yml index 83d7ba7adce..cce9f10085e 100644 --- a/.github/workflows/front-page-copy-guard.lock.yml +++ b/.github/workflows/front-page-copy-guard.lock.yml @@ -454,6 +454,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1134,6 +1135,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1366,12 +1368,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/functional-pragmatist.lock.yml b/.github/workflows/functional-pragmatist.lock.yml index b14220e35f3..844122972b4 100644 --- a/.github/workflows/functional-pragmatist.lock.yml +++ b/.github/workflows/functional-pragmatist.lock.yml @@ -465,6 +465,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1163,6 +1164,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1418,6 +1420,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1425,6 +1428,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/github-mcp-structural-analysis.lock.yml b/.github/workflows/github-mcp-structural-analysis.lock.yml index 01c52702fd2..9f6ffbafeb9 100644 --- a/.github/workflows/github-mcp-structural-analysis.lock.yml +++ b/.github/workflows/github-mcp-structural-analysis.lock.yml @@ -467,6 +467,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1556,6 +1557,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1794,12 +1796,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/github-mcp-tools-report.lock.yml b/.github/workflows/github-mcp-tools-report.lock.yml index 22ffb7da424..c0022d3cdb9 100644 --- a/.github/workflows/github-mcp-tools-report.lock.yml +++ b/.github/workflows/github-mcp-tools-report.lock.yml @@ -476,6 +476,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1293,6 +1294,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1533,12 +1535,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/github-remote-mcp-auth-test.lock.yml b/.github/workflows/github-remote-mcp-auth-test.lock.yml index 0d11e15972e..8851a4f3ca8 100644 --- a/.github/workflows/github-remote-mcp-auth-test.lock.yml +++ b/.github/workflows/github-remote-mcp-auth-test.lock.yml @@ -439,6 +439,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1105,6 +1106,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1340,12 +1342,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/glossary-maintainer.lock.yml b/.github/workflows/glossary-maintainer.lock.yml index a815c7cf262..a7d24935c20 100644 --- a/.github/workflows/glossary-maintainer.lock.yml +++ b/.github/workflows/glossary-maintainer.lock.yml @@ -497,6 +497,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1343,6 +1344,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1370,6 +1372,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1597,6 +1600,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1604,6 +1608,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/go-fan.lock.yml b/.github/workflows/go-fan.lock.yml index 48eb63ee916..6e7ef38c320 100644 --- a/.github/workflows/go-fan.lock.yml +++ b/.github/workflows/go-fan.lock.yml @@ -464,6 +464,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1307,6 +1308,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1547,12 +1549,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/go-logger.lock.yml b/.github/workflows/go-logger.lock.yml index 2ccacf05079..493d1bec613 100644 --- a/.github/workflows/go-logger.lock.yml +++ b/.github/workflows/go-logger.lock.yml @@ -477,6 +477,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1320,6 +1321,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1571,6 +1573,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1578,6 +1581,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/go-pattern-detector.lock.yml b/.github/workflows/go-pattern-detector.lock.yml index 6f3072802f8..4700682dd25 100644 --- a/.github/workflows/go-pattern-detector.lock.yml +++ b/.github/workflows/go-pattern-detector.lock.yml @@ -450,6 +450,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1207,6 +1208,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1486,12 +1488,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/gpclean.lock.yml b/.github/workflows/gpclean.lock.yml index 2e091eafb10..c558db43aa2 100644 --- a/.github/workflows/gpclean.lock.yml +++ b/.github/workflows/gpclean.lock.yml @@ -502,6 +502,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1221,6 +1222,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1478,6 +1480,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1485,6 +1488,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/grumpy-reviewer.lock.yml b/.github/workflows/grumpy-reviewer.lock.yml index 45cbefb6cf7..4b338ee2203 100644 --- a/.github/workflows/grumpy-reviewer.lock.yml +++ b/.github/workflows/grumpy-reviewer.lock.yml @@ -506,6 +506,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1270,6 +1271,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1507,12 +1509,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/hourly-ci-cleaner.lock.yml b/.github/workflows/hourly-ci-cleaner.lock.yml index 790487848fd..9eb8d749358 100644 --- a/.github/workflows/hourly-ci-cleaner.lock.yml +++ b/.github/workflows/hourly-ci-cleaner.lock.yml @@ -481,6 +481,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1269,6 +1270,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1583,6 +1585,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1590,6 +1593,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/impeccable-skills-reviewer.lock.yml b/.github/workflows/impeccable-skills-reviewer.lock.yml index 1e8c3658cee..60cd8ce368d 100644 --- a/.github/workflows/impeccable-skills-reviewer.lock.yml +++ b/.github/workflows/impeccable-skills-reviewer.lock.yml @@ -517,6 +517,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1358,6 +1359,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1387,6 +1389,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1596,12 +1599,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/instructions-janitor.lock.yml b/.github/workflows/instructions-janitor.lock.yml index c1e6c2d3201..5573568dbcc 100644 --- a/.github/workflows/instructions-janitor.lock.yml +++ b/.github/workflows/instructions-janitor.lock.yml @@ -472,6 +472,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1293,6 +1294,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1532,12 +1534,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/issue-arborist.lock.yml b/.github/workflows/issue-arborist.lock.yml index 4067ee6c0da..328a66ca7e0 100644 --- a/.github/workflows/issue-arborist.lock.yml +++ b/.github/workflows/issue-arborist.lock.yml @@ -487,6 +487,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1279,6 +1280,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1538,6 +1540,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1545,6 +1548,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/issue-monster.lock.yml b/.github/workflows/issue-monster.lock.yml index e9b61e21f5b..34b31268ad0 100644 --- a/.github/workflows/issue-monster.lock.yml +++ b/.github/workflows/issue-monster.lock.yml @@ -1659,6 +1659,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1908,6 +1909,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/issue-triage-agent.lock.yml b/.github/workflows/issue-triage-agent.lock.yml index ffddef55a05..f958802a7bc 100644 --- a/.github/workflows/issue-triage-agent.lock.yml +++ b/.github/workflows/issue-triage-agent.lock.yml @@ -431,6 +431,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1335,6 +1336,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1581,6 +1583,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1588,6 +1591,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/jsweep.lock.yml b/.github/workflows/jsweep.lock.yml index 049c79dd1c7..65e1867df91 100644 --- a/.github/workflows/jsweep.lock.yml +++ b/.github/workflows/jsweep.lock.yml @@ -451,6 +451,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1223,6 +1224,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1250,6 +1252,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1466,12 +1469,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/layout-spec-maintainer.lock.yml b/.github/workflows/layout-spec-maintainer.lock.yml index 5ae62a9dd2d..479a067d262 100644 --- a/.github/workflows/layout-spec-maintainer.lock.yml +++ b/.github/workflows/layout-spec-maintainer.lock.yml @@ -463,6 +463,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1229,6 +1230,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1256,6 +1258,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1474,12 +1477,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/lint-monster.lock.yml b/.github/workflows/lint-monster.lock.yml index 225eed966b0..91c5e105823 100644 --- a/.github/workflows/lint-monster.lock.yml +++ b/.github/workflows/lint-monster.lock.yml @@ -443,6 +443,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1297,6 +1298,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1537,12 +1539,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/linter-miner.lock.yml b/.github/workflows/linter-miner.lock.yml index 02a48419083..a9b8f2293ed 100644 --- a/.github/workflows/linter-miner.lock.yml +++ b/.github/workflows/linter-miner.lock.yml @@ -479,6 +479,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1282,6 +1283,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1309,6 +1311,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1525,12 +1528,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/lockfile-stats.lock.yml b/.github/workflows/lockfile-stats.lock.yml index a7082b52b37..8c93bbf0e51 100644 --- a/.github/workflows/lockfile-stats.lock.yml +++ b/.github/workflows/lockfile-stats.lock.yml @@ -451,6 +451,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1208,6 +1209,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1444,12 +1446,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/mattpocock-skills-reviewer.lock.yml b/.github/workflows/mattpocock-skills-reviewer.lock.yml index aefb34d8531..d86ed766145 100644 --- a/.github/workflows/mattpocock-skills-reviewer.lock.yml +++ b/.github/workflows/mattpocock-skills-reviewer.lock.yml @@ -617,6 +617,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1459,6 +1460,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1488,6 +1490,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1697,12 +1700,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/mcp-inspector.lock.yml b/.github/workflows/mcp-inspector.lock.yml index 27396695c71..d051334ef89 100644 --- a/.github/workflows/mcp-inspector.lock.yml +++ b/.github/workflows/mcp-inspector.lock.yml @@ -489,6 +489,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1534,6 +1535,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1561,6 +1563,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1773,12 +1776,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/mergefest.lock.yml b/.github/workflows/mergefest.lock.yml index 41dd17747c9..3984998eba7 100644 --- a/.github/workflows/mergefest.lock.yml +++ b/.github/workflows/mergefest.lock.yml @@ -499,6 +499,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1226,6 +1227,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1253,6 +1255,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1463,12 +1466,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/metrics-collector.lock.yml b/.github/workflows/metrics-collector.lock.yml index bf647275615..e02e92bce77 100644 --- a/.github/workflows/metrics-collector.lock.yml +++ b/.github/workflows/metrics-collector.lock.yml @@ -459,6 +459,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1466,12 +1467,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/necromancer.lock.yml b/.github/workflows/necromancer.lock.yml index cbb82a1eedc..cbdcf2f9b79 100644 --- a/.github/workflows/necromancer.lock.yml +++ b/.github/workflows/necromancer.lock.yml @@ -1190,6 +1190,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1438,6 +1439,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/notion-issue-summary.lock.yml b/.github/workflows/notion-issue-summary.lock.yml index bd25e674086..8d44080d7d1 100644 --- a/.github/workflows/notion-issue-summary.lock.yml +++ b/.github/workflows/notion-issue-summary.lock.yml @@ -446,6 +446,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1166,6 +1167,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/objective-impact-report.lock.yml b/.github/workflows/objective-impact-report.lock.yml index aba488f5444..668b05f00ba 100644 --- a/.github/workflows/objective-impact-report.lock.yml +++ b/.github/workflows/objective-impact-report.lock.yml @@ -433,6 +433,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1232,6 +1233,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1259,6 +1261,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1468,12 +1471,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/org-health-report.lock.yml b/.github/workflows/org-health-report.lock.yml index 7d61d7197b1..641b124a9bb 100644 --- a/.github/workflows/org-health-report.lock.yml +++ b/.github/workflows/org-health-report.lock.yml @@ -462,6 +462,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1275,6 +1276,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1304,6 +1306,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1516,12 +1519,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/outcome-collector.lock.yml b/.github/workflows/outcome-collector.lock.yml index 934245c8e12..c7b3aadad87 100644 --- a/.github/workflows/outcome-collector.lock.yml +++ b/.github/workflows/outcome-collector.lock.yml @@ -447,6 +447,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1310,6 +1311,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1551,12 +1553,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/pdf-summary.lock.yml b/.github/workflows/pdf-summary.lock.yml index b50fad4b9e5..c0d3d8ce027 100644 --- a/.github/workflows/pdf-summary.lock.yml +++ b/.github/workflows/pdf-summary.lock.yml @@ -537,6 +537,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1280,6 +1281,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1516,12 +1518,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/plan.lock.yml b/.github/workflows/plan.lock.yml index 4c5ce5ad9e5..461d1116ee5 100644 --- a/.github/workflows/plan.lock.yml +++ b/.github/workflows/plan.lock.yml @@ -551,6 +551,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1310,6 +1311,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1339,6 +1341,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1571,6 +1574,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1578,6 +1582,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/poem-bot.lock.yml b/.github/workflows/poem-bot.lock.yml index bdc93baf08d..875273b309d 100644 --- a/.github/workflows/poem-bot.lock.yml +++ b/.github/workflows/poem-bot.lock.yml @@ -523,6 +523,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1579,6 +1580,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1827,6 +1829,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1834,6 +1837,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/ponytail-reviewer.lock.yml b/.github/workflows/ponytail-reviewer.lock.yml index 52ad41613e8..3f4772e352d 100644 --- a/.github/workflows/ponytail-reviewer.lock.yml +++ b/.github/workflows/ponytail-reviewer.lock.yml @@ -554,6 +554,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1345,6 +1346,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1583,12 +1585,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/portfolio-analyst.lock.yml b/.github/workflows/portfolio-analyst.lock.yml index e5ad9b7061e..3eacc8f8d3f 100644 --- a/.github/workflows/portfolio-analyst.lock.yml +++ b/.github/workflows/portfolio-analyst.lock.yml @@ -463,6 +463,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1376,6 +1377,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1618,12 +1620,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "250" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/pr-code-quality-reviewer.lock.yml b/.github/workflows/pr-code-quality-reviewer.lock.yml index 163ac9212fa..6aa35f2606f 100644 --- a/.github/workflows/pr-code-quality-reviewer.lock.yml +++ b/.github/workflows/pr-code-quality-reviewer.lock.yml @@ -517,6 +517,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1388,6 +1389,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1417,6 +1419,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1638,6 +1641,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1645,6 +1649,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/pr-description-caveman.lock.yml b/.github/workflows/pr-description-caveman.lock.yml index 31338b7858a..5f6aa1cc2a9 100644 --- a/.github/workflows/pr-description-caveman.lock.yml +++ b/.github/workflows/pr-description-caveman.lock.yml @@ -462,6 +462,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1193,6 +1194,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1220,6 +1222,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1428,12 +1431,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/pr-nitpick-reviewer.lock.yml b/.github/workflows/pr-nitpick-reviewer.lock.yml index 63ce2c9b0f0..1f22ad970bc 100644 --- a/.github/workflows/pr-nitpick-reviewer.lock.yml +++ b/.github/workflows/pr-nitpick-reviewer.lock.yml @@ -509,6 +509,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1326,6 +1327,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1355,6 +1357,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1566,12 +1569,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/pr-sous-chef.lock.yml b/.github/workflows/pr-sous-chef.lock.yml index c45cb7f6f11..c1ffbe0f89a 100644 --- a/.github/workflows/pr-sous-chef.lock.yml +++ b/.github/workflows/pr-sous-chef.lock.yml @@ -2891,6 +2891,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -3145,6 +3146,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/pr-triage-agent.lock.yml b/.github/workflows/pr-triage-agent.lock.yml index 9bd0fa61e66..00bae1b142d 100644 --- a/.github/workflows/pr-triage-agent.lock.yml +++ b/.github/workflows/pr-triage-agent.lock.yml @@ -459,6 +459,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1651,6 +1652,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1680,6 +1682,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1903,6 +1906,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1910,6 +1914,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/prompt-clustering-analysis.lock.yml b/.github/workflows/prompt-clustering-analysis.lock.yml index 0da74719a8c..4ff1032b73d 100644 --- a/.github/workflows/prompt-clustering-analysis.lock.yml +++ b/.github/workflows/prompt-clustering-analysis.lock.yml @@ -473,6 +473,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1371,6 +1372,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1608,12 +1610,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/purelock.lock.yml b/.github/workflows/purelock.lock.yml index ccae8b3c875..efccbf186a3 100644 --- a/.github/workflows/purelock.lock.yml +++ b/.github/workflows/purelock.lock.yml @@ -483,6 +483,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1316,6 +1317,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1567,6 +1569,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1574,6 +1577,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/python-data-charts.lock.yml b/.github/workflows/python-data-charts.lock.yml index d6f31581cf8..73415d90f21 100644 --- a/.github/workflows/python-data-charts.lock.yml +++ b/.github/workflows/python-data-charts.lock.yml @@ -462,6 +462,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1300,6 +1301,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1537,12 +1539,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/q.lock.yml b/.github/workflows/q.lock.yml index e41a806903f..84c2bd33d58 100644 --- a/.github/workflows/q.lock.yml +++ b/.github/workflows/q.lock.yml @@ -559,6 +559,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1410,6 +1411,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1439,6 +1441,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1651,12 +1654,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/refactoring-cadence.lock.yml b/.github/workflows/refactoring-cadence.lock.yml index 173648b3065..3b8bae3d6ef 100644 --- a/.github/workflows/refactoring-cadence.lock.yml +++ b/.github/workflows/refactoring-cadence.lock.yml @@ -1138,6 +1138,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1379,6 +1380,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/refiner.lock.yml b/.github/workflows/refiner.lock.yml index 506002143bf..4e801055313 100644 --- a/.github/workflows/refiner.lock.yml +++ b/.github/workflows/refiner.lock.yml @@ -506,6 +506,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1389,6 +1390,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1418,6 +1420,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1644,6 +1647,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1651,6 +1655,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/release.lock.yml b/.github/workflows/release.lock.yml index ae575e277bc..38dbcee9172 100644 --- a/.github/workflows/release.lock.yml +++ b/.github/workflows/release.lock.yml @@ -460,6 +460,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1174,6 +1175,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1201,6 +1203,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1559,6 +1562,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/repo-audit-analyzer.lock.yml b/.github/workflows/repo-audit-analyzer.lock.yml index 5aafc376a9a..5d613dc78fc 100644 --- a/.github/workflows/repo-audit-analyzer.lock.yml +++ b/.github/workflows/repo-audit-analyzer.lock.yml @@ -458,6 +458,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1161,6 +1162,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1411,6 +1413,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1418,6 +1421,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/repo-tree-map.lock.yml b/.github/workflows/repo-tree-map.lock.yml index 46c0b572692..f2bd8f75207 100644 --- a/.github/workflows/repo-tree-map.lock.yml +++ b/.github/workflows/repo-tree-map.lock.yml @@ -1139,6 +1139,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl diff --git a/.github/workflows/repository-quality-improver.lock.yml b/.github/workflows/repository-quality-improver.lock.yml index 4d34a3635b2..a045e265ad4 100644 --- a/.github/workflows/repository-quality-improver.lock.yml +++ b/.github/workflows/repository-quality-improver.lock.yml @@ -460,6 +460,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1183,6 +1184,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1210,6 +1212,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1421,12 +1424,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/research.lock.yml b/.github/workflows/research.lock.yml index c04e7e260b5..643ea5976bd 100644 --- a/.github/workflows/research.lock.yml +++ b/.github/workflows/research.lock.yml @@ -1097,6 +1097,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1345,6 +1346,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/safe-output-health.lock.yml b/.github/workflows/safe-output-health.lock.yml index ccac2bbc739..31b8ee4f7d0 100644 --- a/.github/workflows/safe-output-health.lock.yml +++ b/.github/workflows/safe-output-health.lock.yml @@ -460,6 +460,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1310,6 +1311,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1546,12 +1548,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/schema-consistency-checker.lock.yml b/.github/workflows/schema-consistency-checker.lock.yml index d5288f8ae40..710f850eef6 100644 --- a/.github/workflows/schema-consistency-checker.lock.yml +++ b/.github/workflows/schema-consistency-checker.lock.yml @@ -455,6 +455,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1156,6 +1157,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1392,12 +1394,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/schema-feature-coverage.lock.yml b/.github/workflows/schema-feature-coverage.lock.yml index 13474c50b25..9cd64ee9f39 100644 --- a/.github/workflows/schema-feature-coverage.lock.yml +++ b/.github/workflows/schema-feature-coverage.lock.yml @@ -442,6 +442,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1141,6 +1142,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1376,12 +1378,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/scout.lock.yml b/.github/workflows/scout.lock.yml index 727917981ef..2cd2392d6a6 100644 --- a/.github/workflows/scout.lock.yml +++ b/.github/workflows/scout.lock.yml @@ -548,6 +548,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1430,6 +1431,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1667,12 +1669,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/security-compliance.lock.yml b/.github/workflows/security-compliance.lock.yml index 00a256cb261..2555d865a66 100644 --- a/.github/workflows/security-compliance.lock.yml +++ b/.github/workflows/security-compliance.lock.yml @@ -469,6 +469,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1216,6 +1217,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1243,6 +1245,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1453,12 +1456,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/security-review.lock.yml b/.github/workflows/security-review.lock.yml index 6124f77765a..c15a5266b3c 100644 --- a/.github/workflows/security-review.lock.yml +++ b/.github/workflows/security-review.lock.yml @@ -517,6 +517,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1549,6 +1550,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1798,6 +1800,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1805,6 +1808,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/semantic-function-refactor.lock.yml b/.github/workflows/semantic-function-refactor.lock.yml index 75df2e67694..c1d464d50cd 100644 --- a/.github/workflows/semantic-function-refactor.lock.yml +++ b/.github/workflows/semantic-function-refactor.lock.yml @@ -450,6 +450,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1306,6 +1307,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1540,12 +1542,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "300" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/sergo.lock.yml b/.github/workflows/sergo.lock.yml index 59619ac8fba..5c4bfbeb761 100644 --- a/.github/workflows/sergo.lock.yml +++ b/.github/workflows/sergo.lock.yml @@ -464,6 +464,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1339,6 +1340,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1580,12 +1582,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/shared/aider.md b/.github/workflows/shared/aider.md index fd3fdae355e..c5f5f852078 100644 --- a/.github/workflows/shared/aider.md +++ b/.github/workflows/shared/aider.md @@ -412,6 +412,7 @@ engine: "mcp.guard.blocked", "mcp.tool_call", "mcp.event", "firewall.http_access", "firewall.token_usage", "firewall.model_routing", "firewall.steering", "firewall.event", "model_routing.outcome", + "model_endpoint.mismatch", "safe_output.request", "safe_output.result", "safe_output.error", "experiment.state", "experiment.assignment", "grader.manifest", "grader.result", "eval.result", "github_api.rate_limit", "usage.report", "execution.result", diff --git a/.github/workflows/sighthound-security-scan.lock.yml b/.github/workflows/sighthound-security-scan.lock.yml index 8d23dea6085..3a59e0d7e47 100644 --- a/.github/workflows/sighthound-security-scan.lock.yml +++ b/.github/workflows/sighthound-security-scan.lock.yml @@ -430,6 +430,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1252,6 +1253,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1487,12 +1489,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/skillet.lock.yml b/.github/workflows/skillet.lock.yml index 50118ec9639..cb35961b0e9 100644 --- a/.github/workflows/skillet.lock.yml +++ b/.github/workflows/skillet.lock.yml @@ -530,6 +530,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1290,6 +1291,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1528,12 +1530,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/slide-deck-maintainer.lock.yml b/.github/workflows/slide-deck-maintainer.lock.yml index 16db9736b01..650fce89b20 100644 --- a/.github/workflows/slide-deck-maintainer.lock.yml +++ b/.github/workflows/slide-deck-maintainer.lock.yml @@ -496,6 +496,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1334,6 +1335,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1361,6 +1363,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1580,12 +1583,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-agent-all-merged.lock.yml b/.github/workflows/smoke-agent-all-merged.lock.yml index d3335dd9980..c764be248c1 100644 --- a/.github/workflows/smoke-agent-all-merged.lock.yml +++ b/.github/workflows/smoke-agent-all-merged.lock.yml @@ -509,6 +509,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1256,6 +1257,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1492,12 +1494,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-agent-all-none.lock.yml b/.github/workflows/smoke-agent-all-none.lock.yml index 1b146cb60db..c07bb00b98e 100644 --- a/.github/workflows/smoke-agent-all-none.lock.yml +++ b/.github/workflows/smoke-agent-all-none.lock.yml @@ -507,6 +507,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1251,6 +1252,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1487,12 +1489,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-agent-public-approved.lock.yml b/.github/workflows/smoke-agent-public-approved.lock.yml index deca5be1410..023763bcc37 100644 --- a/.github/workflows/smoke-agent-public-approved.lock.yml +++ b/.github/workflows/smoke-agent-public-approved.lock.yml @@ -512,6 +512,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1305,6 +1306,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1541,12 +1543,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-agent-public-none.lock.yml b/.github/workflows/smoke-agent-public-none.lock.yml index eb59f0f522d..57a57755250 100644 --- a/.github/workflows/smoke-agent-public-none.lock.yml +++ b/.github/workflows/smoke-agent-public-none.lock.yml @@ -507,6 +507,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1251,6 +1252,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1487,12 +1489,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-agent-scoped-approved.lock.yml b/.github/workflows/smoke-agent-scoped-approved.lock.yml index 02f394a6e24..421d425b6cb 100644 --- a/.github/workflows/smoke-agent-scoped-approved.lock.yml +++ b/.github/workflows/smoke-agent-scoped-approved.lock.yml @@ -514,6 +514,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1316,6 +1317,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1552,12 +1554,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-aider.lock.yml b/.github/workflows/smoke-aider.lock.yml index 304b190e5d3..b4dc38429aa 100644 --- a/.github/workflows/smoke-aider.lock.yml +++ b/.github/workflows/smoke-aider.lock.yml @@ -1,4 +1,4 @@ -# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"de81ec8f5ebce6eda7fd39fbf338a7b115a3f981835ce80adf46acacb97f3d67","body_hash":"0974965a5c4bf509abd6408788f035d628d5ab213a7411ade6394d8383edd918","strict":true,"agent_id":"aider","agent_model":"copilot/gpt-5.4","engine_versions":{"aider":"0.86.2"}} +# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"ce776307f4e7e57eb4ba45b87a08d86815564acc90fc9bc8dd874bc0e7fb3637","body_hash":"0974965a5c4bf509abd6408788f035d628d5ab213a7411ade6394d8383edd918","strict":true,"agent_id":"aider","agent_model":"copilot/gpt-5.4","engine_versions":{"aider":"0.86.2"}} # gh-aw-manifest: {"version":1,"secrets":["GH_AW_DEFAULT_OTLP_ENDPOINT","GH_AW_DEFAULT_OTLP_HEADERS","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GITHUB_TOKEN"],"actions":[{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/download-artifact","sha":"9000827ccba6bdab643e8b6fd33ac0654aef8333","version":"v8.0.2"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"949feb2413d6458794dcd2491c4babbbce0c15c1","version":"v7.1.0"},{"repo":"actions/setup-python","sha":"5fda3b95a4ea91299a34e894583c3862153e4b97","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"cf430e030ddbb5b0abf93d22962f4752f3646cd9","version":"v7.0.2"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50","digest":"sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.28.50@sha256:91fe4af8373c723d4d2e0706a0c35d310c2eeadaea5e0738c725b3861042f620"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50","digest":"sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.28.50@sha256:11f12bcd3dde377ba822df7c670d6b937e9e0cebc46218946d4edc972d7fd965"},{"image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50","digest":"sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce","pinned_image":"ghcr.io/github/gh-aw-firewall/cli-proxy:0.28.50@sha256:afa9c2c1ef66009ab88eee8af0dd43a31b6cc5a481a990d0b1b93ebda4f744ce"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50","digest":"sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.28.50@sha256:cc9b6b979edf4aafbb3811c2bdc4891039d5346473afa88e304aa692167004f9"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.30","digest":"sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.30@sha256:ab5a436a1490438db473e4e3d4c973cb1d75e3cb233fb08b73d31b42d7d18fba"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f","pinned_image":"ghcr.io/github/gh-aw-node@sha256:11c2c544876cdbaffefe0f7f1283b74838c209654b4934a78e23ed11f750490f"},{"image":"ghcr.io/github/github-mcp-server:v1.12.2","digest":"sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6","pinned_image":"ghcr.io/github/github-mcp-server:v1.12.2@sha256:508a0857ec762b1ab1cece29193345b501fab1dd9d1228a7b617062954cecac6"}],"has_pull_request":true,"mcp_servers":[{"name":"safeoutputs","tools":["add_comment","add_labels","create_issue","missing_data","missing_tool","noop","report_incomplete"]}],"threat_detection":{"mode":"enabled"}} # This file was automatically generated by gh-aw. DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md # @@ -1132,6 +1132,7 @@ jobs: "mcp.guard.blocked", "mcp.tool_call", "mcp.event", "firewall.http_access", "firewall.token_usage", "firewall.model_routing", "firewall.steering", "firewall.event", "model_routing.outcome", + "model_endpoint.mismatch", "safe_output.request", "safe_output.result", "safe_output.error", "experiment.state", "experiment.assignment", "grader.manifest", "grader.result", "eval.result", "github_api.rate_limit", "usage.report", "execution.result", @@ -1641,6 +1642,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1874,6 +1876,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-builtin-ledgers.lock.yml b/.github/workflows/smoke-builtin-ledgers.lock.yml index b09e87dc9e7..164bfb6637a 100644 --- a/.github/workflows/smoke-builtin-ledgers.lock.yml +++ b/.github/workflows/smoke-builtin-ledgers.lock.yml @@ -429,6 +429,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1393,6 +1394,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1420,6 +1422,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1628,12 +1631,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-call-workflow.lock.yml b/.github/workflows/smoke-call-workflow.lock.yml index a81a71435e7..b7e29d4d73a 100644 --- a/.github/workflows/smoke-call-workflow.lock.yml +++ b/.github/workflows/smoke-call-workflow.lock.yml @@ -508,6 +508,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1188,6 +1189,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1449,12 +1451,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-checkout-pr-dispatch.lock.yml b/.github/workflows/smoke-checkout-pr-dispatch.lock.yml index b7b2454ce83..ebf9babefb0 100644 --- a/.github/workflows/smoke-checkout-pr-dispatch.lock.yml +++ b/.github/workflows/smoke-checkout-pr-dispatch.lock.yml @@ -514,6 +514,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1230,6 +1231,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1257,6 +1259,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1466,12 +1469,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-ci.lock.yml b/.github/workflows/smoke-ci.lock.yml index 6a6126fbbc6..7bacde309b4 100644 --- a/.github/workflows/smoke-ci.lock.yml +++ b/.github/workflows/smoke-ci.lock.yml @@ -503,6 +503,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1412,6 +1413,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1620,6 +1622,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-claude-auto.lock.yml b/.github/workflows/smoke-claude-auto.lock.yml index e22ec44d103..810fd53f85a 100644 --- a/.github/workflows/smoke-claude-auto.lock.yml +++ b/.github/workflows/smoke-claude-auto.lock.yml @@ -393,6 +393,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1184,6 +1185,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-claude-copilot-auto.lock.yml b/.github/workflows/smoke-claude-copilot-auto.lock.yml index f36bdeecbf1..dc1242d8c15 100644 --- a/.github/workflows/smoke-claude-copilot-auto.lock.yml +++ b/.github/workflows/smoke-claude-copilot-auto.lock.yml @@ -393,6 +393,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1183,6 +1184,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-claude-copilot.lock.yml b/.github/workflows/smoke-claude-copilot.lock.yml index fa0e5238aa2..9e18eaf3a00 100644 --- a/.github/workflows/smoke-claude-copilot.lock.yml +++ b/.github/workflows/smoke-claude-copilot.lock.yml @@ -372,6 +372,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1289,6 +1290,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-claude-dynamic.lock.yml b/.github/workflows/smoke-claude-dynamic.lock.yml index 78a5246a746..bac848885f1 100644 --- a/.github/workflows/smoke-claude-dynamic.lock.yml +++ b/.github/workflows/smoke-claude-dynamic.lock.yml @@ -416,6 +416,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1275,12 +1276,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-claude-on-copilot.lock.yml b/.github/workflows/smoke-claude-on-copilot.lock.yml index fa0698b37eb..46ed4e3f723 100644 --- a/.github/workflows/smoke-claude-on-copilot.lock.yml +++ b/.github/workflows/smoke-claude-on-copilot.lock.yml @@ -495,6 +495,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1236,6 +1237,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1470,12 +1472,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-claude.lock.yml b/.github/workflows/smoke-claude.lock.yml index 58fa62587d6..41228d87025 100644 --- a/.github/workflows/smoke-claude.lock.yml +++ b/.github/workflows/smoke-claude.lock.yml @@ -552,6 +552,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1981,6 +1982,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -2293,12 +2295,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-codex-auto.lock.yml b/.github/workflows/smoke-codex-auto.lock.yml index 7335a23a73d..08092660e59 100644 --- a/.github/workflows/smoke-codex-auto.lock.yml +++ b/.github/workflows/smoke-codex-auto.lock.yml @@ -393,6 +393,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1172,6 +1173,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-codex-bare-auto.lock.yml b/.github/workflows/smoke-codex-bare-auto.lock.yml index e83dbb8b032..dc56f97defc 100644 --- a/.github/workflows/smoke-codex-bare-auto.lock.yml +++ b/.github/workflows/smoke-codex-bare-auto.lock.yml @@ -393,6 +393,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1173,6 +1174,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-codex.lock.yml b/.github/workflows/smoke-codex.lock.yml index 4d00fc1830a..489417ab86e 100644 --- a/.github/workflows/smoke-codex.lock.yml +++ b/.github/workflows/smoke-codex.lock.yml @@ -556,6 +556,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1587,6 +1588,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1927,12 +1929,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-aoai-apikey.lock.yml b/.github/workflows/smoke-copilot-aoai-apikey.lock.yml index c7d4c89b4ed..5d57509ebce 100644 --- a/.github/workflows/smoke-copilot-aoai-apikey.lock.yml +++ b/.github/workflows/smoke-copilot-aoai-apikey.lock.yml @@ -613,6 +613,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -2551,6 +2552,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -2581,6 +2583,7 @@ jobs: /tmp/gh-aw/mcp-scripts/logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -2888,6 +2891,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "60" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -2895,6 +2899,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-aoai-entra.lock.yml b/.github/workflows/smoke-copilot-aoai-entra.lock.yml index 2ea3f863489..7711a28f2c5 100644 --- a/.github/workflows/smoke-copilot-aoai-entra.lock.yml +++ b/.github/workflows/smoke-copilot-aoai-entra.lock.yml @@ -620,6 +620,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -2569,6 +2570,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -2599,6 +2601,7 @@ jobs: /tmp/gh-aw/mcp-scripts/logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -2907,6 +2910,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: "60" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -2914,6 +2918,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-arm.lock.yml b/.github/workflows/smoke-copilot-arm.lock.yml index ec607318a6e..8315fd973bf 100644 --- a/.github/workflows/smoke-copilot-arm.lock.yml +++ b/.github/workflows/smoke-copilot-arm.lock.yml @@ -552,6 +552,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -2306,6 +2307,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -2334,6 +2336,7 @@ jobs: /tmp/gh-aw/mcp-scripts/logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -2619,12 +2622,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-auto.lock.yml b/.github/workflows/smoke-copilot-auto.lock.yml index 9bc3e913ac7..6c5c46b429a 100644 --- a/.github/workflows/smoke-copilot-auto.lock.yml +++ b/.github/workflows/smoke-copilot-auto.lock.yml @@ -491,6 +491,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1193,6 +1194,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1220,6 +1222,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1427,12 +1430,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-dynamic-workflow.lock.yml b/.github/workflows/smoke-copilot-dynamic-workflow.lock.yml index 060b7ead4ca..36b4aebb548 100644 --- a/.github/workflows/smoke-copilot-dynamic-workflow.lock.yml +++ b/.github/workflows/smoke-copilot-dynamic-workflow.lock.yml @@ -489,6 +489,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1167,6 +1168,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1194,6 +1196,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1415,6 +1418,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1422,6 +1426,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-mai.lock.yml b/.github/workflows/smoke-copilot-mai.lock.yml index 2235afe9734..3e2cb4e0109 100644 --- a/.github/workflows/smoke-copilot-mai.lock.yml +++ b/.github/workflows/smoke-copilot-mai.lock.yml @@ -527,6 +527,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1274,6 +1275,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1301,6 +1303,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1510,12 +1513,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-routed.lock.yml b/.github/workflows/smoke-copilot-routed.lock.yml index 40ebfe4660e..07fef0b053a 100644 --- a/.github/workflows/smoke-copilot-routed.lock.yml +++ b/.github/workflows/smoke-copilot-routed.lock.yml @@ -500,6 +500,7 @@ jobs: missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ steps.parse-token-usage.outputs.model || needs.activation.outputs.model }} model_effort: ${{ steps.parse-token-usage.outputs.model_effort }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} model_routing_status: ${{ steps.parse-token-usage.outputs.model_routing_status }} output: ${{ steps.collect_output.outputs.output }} @@ -1230,6 +1231,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1259,6 +1261,7 @@ jobs: /tmp/gh-aw/agent/aw_info.json /tmp/gh-aw/agent/awf-routing-outcome.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1475,12 +1478,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-sdk-routed.lock.yml b/.github/workflows/smoke-copilot-sdk-routed.lock.yml index 41b9276697f..19330b9fce1 100644 --- a/.github/workflows/smoke-copilot-sdk-routed.lock.yml +++ b/.github/workflows/smoke-copilot-sdk-routed.lock.yml @@ -499,6 +499,7 @@ jobs: missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ steps.parse-token-usage.outputs.model || needs.activation.outputs.model }} model_effort: ${{ steps.parse-token-usage.outputs.model_effort }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} model_routing_status: ${{ steps.parse-token-usage.outputs.model_routing_status }} output: ${{ steps.collect_output.outputs.output }} @@ -1222,6 +1223,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1251,6 +1253,7 @@ jobs: /tmp/gh-aw/agent/aw_info.json /tmp/gh-aw/agent/awf-routing-outcome.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1467,12 +1470,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-sdk.lock.yml b/.github/workflows/smoke-copilot-sdk.lock.yml index d7afcba0a76..8d35c737f5d 100644 --- a/.github/workflows/smoke-copilot-sdk.lock.yml +++ b/.github/workflows/smoke-copilot-sdk.lock.yml @@ -523,6 +523,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1229,6 +1230,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1256,6 +1258,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1465,12 +1468,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-small.lock.yml b/.github/workflows/smoke-copilot-small.lock.yml index 271daa054dd..1273050e1c6 100644 --- a/.github/workflows/smoke-copilot-small.lock.yml +++ b/.github/workflows/smoke-copilot-small.lock.yml @@ -526,6 +526,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1264,6 +1265,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1291,6 +1293,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1500,12 +1503,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot-sub-agents.lock.yml b/.github/workflows/smoke-copilot-sub-agents.lock.yml index 5faa07a089b..e7bc91c83f8 100644 --- a/.github/workflows/smoke-copilot-sub-agents.lock.yml +++ b/.github/workflows/smoke-copilot-sub-agents.lock.yml @@ -478,6 +478,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1191,6 +1192,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1218,6 +1220,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1447,6 +1450,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1454,6 +1458,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-copilot.lock.yml b/.github/workflows/smoke-copilot.lock.yml index 1a50db0534c..85cb06ee734 100644 --- a/.github/workflows/smoke-copilot.lock.yml +++ b/.github/workflows/smoke-copilot.lock.yml @@ -625,6 +625,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -2585,6 +2586,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -2615,6 +2617,7 @@ jobs: /tmp/gh-aw/mcp-scripts/logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -2924,6 +2927,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -2931,6 +2935,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-create-cross-repo-pr.lock.yml b/.github/workflows/smoke-create-cross-repo-pr.lock.yml index 78edc2c36af..d3d7411850d 100644 --- a/.github/workflows/smoke-create-cross-repo-pr.lock.yml +++ b/.github/workflows/smoke-create-cross-repo-pr.lock.yml @@ -510,6 +510,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1331,6 +1332,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1358,6 +1360,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1566,12 +1569,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-crush.lock.yml b/.github/workflows/smoke-crush.lock.yml index ed14a81dee5..294e9d39845 100644 --- a/.github/workflows/smoke-crush.lock.yml +++ b/.github/workflows/smoke-crush.lock.yml @@ -1517,6 +1517,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1823,6 +1824,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-cursor.lock.yml b/.github/workflows/smoke-cursor.lock.yml index 2a0e2cb05ba..95e9c003818 100644 --- a/.github/workflows/smoke-cursor.lock.yml +++ b/.github/workflows/smoke-cursor.lock.yml @@ -1398,6 +1398,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1701,6 +1702,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-deepseek-harness.lock.yml b/.github/workflows/smoke-deepseek-harness.lock.yml index 2a303b2b20c..0cebf4224b2 100644 --- a/.github/workflows/smoke-deepseek-harness.lock.yml +++ b/.github/workflows/smoke-deepseek-harness.lock.yml @@ -1349,6 +1349,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1656,6 +1657,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-drive.lock.yml b/.github/workflows/smoke-drive.lock.yml index fd0a6994eae..761952a001b 100644 --- a/.github/workflows/smoke-drive.lock.yml +++ b/.github/workflows/smoke-drive.lock.yml @@ -519,6 +519,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1328,6 +1329,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1563,12 +1565,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-gemini.lock.yml b/.github/workflows/smoke-gemini.lock.yml index 5d8540e0138..cd8f083127a 100644 --- a/.github/workflows/smoke-gemini.lock.yml +++ b/.github/workflows/smoke-gemini.lock.yml @@ -1362,6 +1362,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1695,6 +1696,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/smoke-github-claude.lock.yml b/.github/workflows/smoke-github-claude.lock.yml index 26f14d701c6..c5db85e0fca 100644 --- a/.github/workflows/smoke-github-claude.lock.yml +++ b/.github/workflows/smoke-github-claude.lock.yml @@ -500,6 +500,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1241,6 +1242,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1475,12 +1477,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-github-codex.lock.yml b/.github/workflows/smoke-github-codex.lock.yml index 408f69cd493..aa16aceffea 100644 --- a/.github/workflows/smoke-github-codex.lock.yml +++ b/.github/workflows/smoke-github-codex.lock.yml @@ -388,6 +388,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1167,6 +1168,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-goose.lock.yml b/.github/workflows/smoke-goose.lock.yml index 8b675da3cb6..f1cea4ea439 100644 --- a/.github/workflows/smoke-goose.lock.yml +++ b/.github/workflows/smoke-goose.lock.yml @@ -1558,6 +1558,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1866,6 +1867,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "20" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-issues.lock.yml b/.github/workflows/smoke-issues.lock.yml index 695aaaaba9f..77705a505c2 100644 --- a/.github/workflows/smoke-issues.lock.yml +++ b/.github/workflows/smoke-issues.lock.yml @@ -457,6 +457,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1243,6 +1244,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1270,6 +1272,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1479,12 +1482,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-kiro.lock.yml b/.github/workflows/smoke-kiro.lock.yml index 22c6e53433b..8f16d878be2 100644 --- a/.github/workflows/smoke-kiro.lock.yml +++ b/.github/workflows/smoke-kiro.lock.yml @@ -1424,6 +1424,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1731,6 +1732,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-multi-pr.lock.yml b/.github/workflows/smoke-multi-pr.lock.yml index bea09eba599..c1202d1a734 100644 --- a/.github/workflows/smoke-multi-pr.lock.yml +++ b/.github/workflows/smoke-multi-pr.lock.yml @@ -508,6 +508,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1289,6 +1290,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1316,6 +1318,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1526,12 +1529,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-opencode.lock.yml b/.github/workflows/smoke-opencode.lock.yml index 73b331da28b..17cc1b7c6e6 100644 --- a/.github/workflows/smoke-opencode.lock.yml +++ b/.github/workflows/smoke-opencode.lock.yml @@ -1480,6 +1480,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1788,6 +1789,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-otel-backends.lock.yml b/.github/workflows/smoke-otel-backends.lock.yml index eca3c879e5d..332a4da528d 100644 --- a/.github/workflows/smoke-otel-backends.lock.yml +++ b/.github/workflows/smoke-otel-backends.lock.yml @@ -548,6 +548,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1352,6 +1353,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1586,12 +1588,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-pi-routed.lock.yml b/.github/workflows/smoke-pi-routed.lock.yml index fa5266298d0..6e7cd70856d 100644 --- a/.github/workflows/smoke-pi-routed.lock.yml +++ b/.github/workflows/smoke-pi-routed.lock.yml @@ -1166,6 +1166,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1412,6 +1413,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-pi-sub-agents.lock.yml b/.github/workflows/smoke-pi-sub-agents.lock.yml index 0ef3e44dd11..e30f33bb1fd 100644 --- a/.github/workflows/smoke-pi-sub-agents.lock.yml +++ b/.github/workflows/smoke-pi-sub-agents.lock.yml @@ -1073,6 +1073,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1308,6 +1309,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-pi.lock.yml b/.github/workflows/smoke-pi.lock.yml index b0bc057bbdf..9d217feaace 100644 --- a/.github/workflows/smoke-pi.lock.yml +++ b/.github/workflows/smoke-pi.lock.yml @@ -1274,6 +1274,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1510,6 +1511,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-project.lock.yml b/.github/workflows/smoke-project.lock.yml index c8a948374ac..147b68ba5f8 100644 --- a/.github/workflows/smoke-project.lock.yml +++ b/.github/workflows/smoke-project.lock.yml @@ -577,6 +577,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1523,6 +1524,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1550,6 +1552,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1858,6 +1861,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1865,6 +1869,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-pydantic.lock.yml b/.github/workflows/smoke-pydantic.lock.yml index 3745fe390bc..1bcd9e218c5 100644 --- a/.github/workflows/smoke-pydantic.lock.yml +++ b/.github/workflows/smoke-pydantic.lock.yml @@ -1698,6 +1698,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1931,6 +1932,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-repo-memory-ledger.lock.yml b/.github/workflows/smoke-repo-memory-ledger.lock.yml index 0c6efbeaec3..87a91bba6ba 100644 --- a/.github/workflows/smoke-repo-memory-ledger.lock.yml +++ b/.github/workflows/smoke-repo-memory-ledger.lock.yml @@ -433,6 +433,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1239,6 +1240,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1266,6 +1268,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1486,6 +1489,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1493,6 +1497,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-service-ports.lock.yml b/.github/workflows/smoke-service-ports.lock.yml index 879bd18580d..f2809891aa7 100644 --- a/.github/workflows/smoke-service-ports.lock.yml +++ b/.github/workflows/smoke-service-ports.lock.yml @@ -1159,6 +1159,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1467,6 +1468,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-temporary-id.lock.yml b/.github/workflows/smoke-temporary-id.lock.yml index 498d9cc809d..f216ab117a8 100644 --- a/.github/workflows/smoke-temporary-id.lock.yml +++ b/.github/workflows/smoke-temporary-id.lock.yml @@ -1257,6 +1257,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1587,6 +1588,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/smoke-test-tools.lock.yml b/.github/workflows/smoke-test-tools.lock.yml index 3dd19826eca..facd0b74a6a 100644 --- a/.github/workflows/smoke-test-tools.lock.yml +++ b/.github/workflows/smoke-test-tools.lock.yml @@ -1214,6 +1214,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1522,6 +1523,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/smoke-update-cross-repo-pr.lock.yml b/.github/workflows/smoke-update-cross-repo-pr.lock.yml index b41e95e3c3d..969ab7b0b87 100644 --- a/.github/workflows/smoke-update-cross-repo-pr.lock.yml +++ b/.github/workflows/smoke-update-cross-repo-pr.lock.yml @@ -521,6 +521,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1347,6 +1348,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1374,6 +1376,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1583,12 +1586,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-work-queue.lock.yml b/.github/workflows/smoke-work-queue.lock.yml index 0454cd6d44a..b9a72a20666 100644 --- a/.github/workflows/smoke-work-queue.lock.yml +++ b/.github/workflows/smoke-work-queue.lock.yml @@ -445,6 +445,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1183,6 +1184,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1210,6 +1212,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1436,12 +1439,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-workflow-call-with-inputs.lock.yml b/.github/workflows/smoke-workflow-call-with-inputs.lock.yml index 4c5ee315bce..5bcbd0990af 100644 --- a/.github/workflows/smoke-workflow-call-with-inputs.lock.yml +++ b/.github/workflows/smoke-workflow-call-with-inputs.lock.yml @@ -536,6 +536,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1250,6 +1251,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1459,12 +1461,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/smoke-workflow-call.lock.yml b/.github/workflows/smoke-workflow-call.lock.yml index 1ccb5c05707..8207d7bd99f 100644 --- a/.github/workflows/smoke-workflow-call.lock.yml +++ b/.github/workflows/smoke-workflow-call.lock.yml @@ -529,6 +529,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1280,6 +1281,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1514,12 +1516,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/spec-enforcer.lock.yml b/.github/workflows/spec-enforcer.lock.yml index 912ff7f11f2..96c43797d8c 100644 --- a/.github/workflows/spec-enforcer.lock.yml +++ b/.github/workflows/spec-enforcer.lock.yml @@ -490,6 +490,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1257,6 +1258,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1514,6 +1516,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1521,6 +1524,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/spec-extractor.lock.yml b/.github/workflows/spec-extractor.lock.yml index 172292d9c58..bc2e5b6b224 100644 --- a/.github/workflows/spec-extractor.lock.yml +++ b/.github/workflows/spec-extractor.lock.yml @@ -475,6 +475,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1305,6 +1306,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1332,6 +1334,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1548,12 +1551,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/spec-librarian.lock.yml b/.github/workflows/spec-librarian.lock.yml index 87838369478..6b16f4e4fb3 100644 --- a/.github/workflows/spec-librarian.lock.yml +++ b/.github/workflows/spec-librarian.lock.yml @@ -453,6 +453,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1232,6 +1233,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1259,6 +1261,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1471,12 +1474,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/squad-game-planner.lock.yml b/.github/workflows/squad-game-planner.lock.yml index 568db69ded0..b62f6aa04fb 100644 --- a/.github/workflows/squad-game-planner.lock.yml +++ b/.github/workflows/squad-game-planner.lock.yml @@ -473,6 +473,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1195,6 +1196,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1222,6 +1224,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1429,12 +1432,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/squad-implement-worker.lock.yml b/.github/workflows/squad-implement-worker.lock.yml index 0570cc59315..20b072c641c 100644 --- a/.github/workflows/squad-implement-worker.lock.yml +++ b/.github/workflows/squad-implement-worker.lock.yml @@ -512,6 +512,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1345,6 +1346,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1372,6 +1374,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1586,12 +1589,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/squad-plan.lock.yml b/.github/workflows/squad-plan.lock.yml index 56b09c37cb3..68cd49cee5d 100644 --- a/.github/workflows/squad-plan.lock.yml +++ b/.github/workflows/squad-plan.lock.yml @@ -533,6 +533,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1253,6 +1254,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1280,6 +1282,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1487,12 +1490,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/squad.lock.yml b/.github/workflows/squad.lock.yml index e648bb3bef7..c98c2be637f 100644 --- a/.github/workflows/squad.lock.yml +++ b/.github/workflows/squad.lock.yml @@ -562,6 +562,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1883,6 +1884,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1910,6 +1912,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -2124,12 +2127,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/stale-pr-cleanup.lock.yml b/.github/workflows/stale-pr-cleanup.lock.yml index 76ae05a2fb0..781e01d49e9 100644 --- a/.github/workflows/stale-pr-cleanup.lock.yml +++ b/.github/workflows/stale-pr-cleanup.lock.yml @@ -432,6 +432,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1181,6 +1182,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1208,6 +1210,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1427,6 +1430,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1434,6 +1438,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/stale-repo-identifier.lock.yml b/.github/workflows/stale-repo-identifier.lock.yml index 050a28f3415..bf6e3121b9b 100644 --- a/.github/workflows/stale-repo-identifier.lock.yml +++ b/.github/workflows/stale-repo-identifier.lock.yml @@ -1385,6 +1385,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1636,6 +1637,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/static-analysis-report.lock.yml b/.github/workflows/static-analysis-report.lock.yml index 9dce4d9628d..fb54015ebc7 100644 --- a/.github/workflows/static-analysis-report.lock.yml +++ b/.github/workflows/static-analysis-report.lock.yml @@ -462,6 +462,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1358,6 +1359,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1593,12 +1595,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/step-name-alignment.lock.yml b/.github/workflows/step-name-alignment.lock.yml index fdf4f3e9e00..712e3d5bc7f 100644 --- a/.github/workflows/step-name-alignment.lock.yml +++ b/.github/workflows/step-name-alignment.lock.yml @@ -452,6 +452,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1250,6 +1251,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1485,12 +1487,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/sub-issue-closer.lock.yml b/.github/workflows/sub-issue-closer.lock.yml index 5a0da31ac7d..7af6b2be818 100644 --- a/.github/workflows/sub-issue-closer.lock.yml +++ b/.github/workflows/sub-issue-closer.lock.yml @@ -1135,6 +1135,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1382,6 +1383,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" diff --git a/.github/workflows/super-linter.lock.yml b/.github/workflows/super-linter.lock.yml index fdbce32e2cb..7d5d194b96b 100644 --- a/.github/workflows/super-linter.lock.yml +++ b/.github/workflows/super-linter.lock.yml @@ -1141,6 +1141,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1378,6 +1379,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/technical-doc-writer.lock.yml b/.github/workflows/technical-doc-writer.lock.yml index 04519ccd1b8..95b26476cee 100644 --- a/.github/workflows/technical-doc-writer.lock.yml +++ b/.github/workflows/technical-doc-writer.lock.yml @@ -493,6 +493,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1375,6 +1376,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1402,6 +1404,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1629,6 +1632,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1636,6 +1640,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/terminal-stylist.lock.yml b/.github/workflows/terminal-stylist.lock.yml index f0ad32e98ba..49ad2659528 100644 --- a/.github/workflows/terminal-stylist.lock.yml +++ b/.github/workflows/terminal-stylist.lock.yml @@ -1115,6 +1115,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1351,6 +1352,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_CREATE_DISCUSSION_ERRORS: ${{ needs.safe_outputs.outputs.create_discussion_errors }} diff --git a/.github/workflows/test-quality-sentinel.lock.yml b/.github/workflows/test-quality-sentinel.lock.yml index 771e3eaea9f..57b3092fa90 100644 --- a/.github/workflows/test-quality-sentinel.lock.yml +++ b/.github/workflows/test-quality-sentinel.lock.yml @@ -553,6 +553,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1313,6 +1314,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1340,6 +1342,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1569,6 +1572,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1576,6 +1580,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/tidy.lock.yml b/.github/workflows/tidy.lock.yml index 3f3c330bb46..27b1dd60c54 100644 --- a/.github/workflows/tidy.lock.yml +++ b/.github/workflows/tidy.lock.yml @@ -521,6 +521,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1299,6 +1300,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1326,6 +1328,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1552,6 +1555,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1559,6 +1563,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/typist.lock.yml b/.github/workflows/typist.lock.yml index 732f64a6022..559e33c0330 100644 --- a/.github/workflows/typist.lock.yml +++ b/.github/workflows/typist.lock.yml @@ -494,6 +494,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1276,6 +1277,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1533,6 +1535,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1540,6 +1543,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/ubuntu-image-analyzer.lock.yml b/.github/workflows/ubuntu-image-analyzer.lock.yml index 5a78642801a..d3b81df667d 100644 --- a/.github/workflows/ubuntu-image-analyzer.lock.yml +++ b/.github/workflows/ubuntu-image-analyzer.lock.yml @@ -472,6 +472,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1213,6 +1214,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1240,6 +1242,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1458,12 +1461,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/uk-ai-operational-resilience.lock.yml b/.github/workflows/uk-ai-operational-resilience.lock.yml index b0c2c186639..ac1fb8f8f0f 100644 --- a/.github/workflows/uk-ai-operational-resilience.lock.yml +++ b/.github/workflows/uk-ai-operational-resilience.lock.yml @@ -453,6 +453,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1200,6 +1201,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1227,6 +1229,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1442,12 +1445,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/unbloat-docs.lock.yml b/.github/workflows/unbloat-docs.lock.yml index 386b6bb3755..7f1ef2f571e 100644 --- a/.github/workflows/unbloat-docs.lock.yml +++ b/.github/workflows/unbloat-docs.lock.yml @@ -1276,6 +1276,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1526,6 +1527,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "false" diff --git a/.github/workflows/update-astro.lock.yml b/.github/workflows/update-astro.lock.yml index fed49003f7b..cc490d08d03 100644 --- a/.github/workflows/update-astro.lock.yml +++ b/.github/workflows/update-astro.lock.yml @@ -482,6 +482,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1186,6 +1187,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1477,12 +1479,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/video-analyzer.lock.yml b/.github/workflows/video-analyzer.lock.yml index 587652a64fe..077df7b677b 100644 --- a/.github/workflows/video-analyzer.lock.yml +++ b/.github/workflows/video-analyzer.lock.yml @@ -1091,6 +1091,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1326,6 +1327,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/visual-regression-checker.lock.yml b/.github/workflows/visual-regression-checker.lock.yml index b9007808507..d9f4e9b44d2 100644 --- a/.github/workflows/visual-regression-checker.lock.yml +++ b/.github/workflows/visual-regression-checker.lock.yml @@ -460,6 +460,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1194,6 +1195,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1221,6 +1223,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1428,12 +1431,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "false" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/weekly-blog-post-writer.lock.yml b/.github/workflows/weekly-blog-post-writer.lock.yml index 3c9c9319bdf..a338591f295 100644 --- a/.github/workflows/weekly-blog-post-writer.lock.yml +++ b/.github/workflows/weekly-blog-post-writer.lock.yml @@ -529,6 +529,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1396,6 +1397,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1425,6 +1427,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1666,6 +1669,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_EVALS_AIC: ${{ needs.evals.outputs.aic }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" @@ -1673,6 +1677,7 @@ jobs: GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/weekly-editors-health-check.lock.yml b/.github/workflows/weekly-editors-health-check.lock.yml index e23ce5f20c8..a8d88ebaccb 100644 --- a/.github/workflows/weekly-editors-health-check.lock.yml +++ b/.github/workflows/weekly-editors-health-check.lock.yml @@ -463,6 +463,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1248,6 +1249,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1275,6 +1277,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1494,12 +1497,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/weekly-issue-summary.lock.yml b/.github/workflows/weekly-issue-summary.lock.yml index ffc8a4f23d9..eaffeaa3964 100644 --- a/.github/workflows/weekly-issue-summary.lock.yml +++ b/.github/workflows/weekly-issue-summary.lock.yml @@ -1164,6 +1164,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1408,6 +1409,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_CREATE_DISCUSSION_ERRORS: ${{ needs.safe_outputs.outputs.create_discussion_errors }} diff --git a/.github/workflows/weekly-network-domains-audit.lock.yml b/.github/workflows/weekly-network-domains-audit.lock.yml index aa11b75c6c5..9ca6870e181 100644 --- a/.github/workflows/weekly-network-domains-audit.lock.yml +++ b/.github/workflows/weekly-network-domains-audit.lock.yml @@ -1119,6 +1119,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1360,6 +1361,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }} diff --git a/.github/workflows/weekly-safe-outputs-spec-review.lock.yml b/.github/workflows/weekly-safe-outputs-spec-review.lock.yml index f86c29f9df5..082016b7e08 100644 --- a/.github/workflows/weekly-safe-outputs-spec-review.lock.yml +++ b/.github/workflows/weekly-safe-outputs-spec-review.lock.yml @@ -1131,6 +1131,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1376,6 +1377,7 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_FAILURE_ISSUE_NUMBER: ${{ needs.activation.outputs.steering_issue_number }} diff --git a/.github/workflows/windows-grower.lock.yml b/.github/workflows/windows-grower.lock.yml index e1d6826adbe..b4446cdc415 100644 --- a/.github/workflows/windows-grower.lock.yml +++ b/.github/workflows/windows-grower.lock.yml @@ -453,6 +453,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1167,6 +1168,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1404,12 +1406,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/windows.lock.yml b/.github/workflows/windows.lock.yml index 07b56c62703..83d65c01d29 100644 --- a/.github/workflows/windows.lock.yml +++ b/.github/workflows/windows.lock.yml @@ -549,6 +549,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1253,6 +1254,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1487,12 +1489,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/workflow-generator.lock.yml b/.github/workflows/workflow-generator.lock.yml index 12a85e86fcc..c09c13e6136 100644 --- a/.github/workflows/workflow-generator.lock.yml +++ b/.github/workflows/workflow-generator.lock.yml @@ -483,6 +483,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1244,6 +1245,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1273,6 +1275,7 @@ jobs: !/tmp/gh-aw/proxy-logs/proxy-tls/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1482,12 +1485,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/workflow-health-manager.lock.yml b/.github/workflows/workflow-health-manager.lock.yml index a4fe013ede5..fcbdb972df2 100644 --- a/.github/workflows/workflow-health-manager.lock.yml +++ b/.github/workflows/workflow-health-manager.lock.yml @@ -454,6 +454,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1300,6 +1301,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1327,6 +1329,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1537,12 +1540,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: "1500" GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/workflow-normalizer.lock.yml b/.github/workflows/workflow-normalizer.lock.yml index 255dff7dc8d..8d5a28853fe 100644 --- a/.github/workflows/workflow-normalizer.lock.yml +++ b/.github/workflows/workflow-normalizer.lock.yml @@ -458,6 +458,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1237,6 +1238,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1477,12 +1479,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/.github/workflows/workflow-skill-extractor.lock.yml b/.github/workflows/workflow-skill-extractor.lock.yml index 6a6f2d829f4..ba6774cd50c 100644 --- a/.github/workflows/workflow-skill-extractor.lock.yml +++ b/.github/workflows/workflow-skill-extractor.lock.yml @@ -438,6 +438,7 @@ jobs: missing_model_pricing_error: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_error || 'false' }} missing_model_pricing_model_name: ${{ steps.detect-agent-errors.outputs.missing_model_pricing_model_name || '' }} model: ${{ needs.activation.outputs.model }} + model_endpoint_mismatch_error: ${{ steps.detect-agent-errors.outputs.model_endpoint_mismatch_error || 'false' }} model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }} output: ${{ steps.collect_output.outputs.output }} output_types: ${{ steps.collect_output.outputs.output_types }} @@ -1185,6 +1186,7 @@ jobs: /tmp/gh-aw/agent_execution_exit_code.txt /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/model-routing.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl @@ -1212,6 +1214,7 @@ jobs: /tmp/gh-aw/mcp-logs/ /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl + /tmp/gh-aw/agent/model-endpoint-mismatch.json /tmp/gh-aw/agent-stdio.log /tmp/gh-aw/pre-agent-audit.txt /tmp/gh-aw/github_rate_limits.jsonl @@ -1422,12 +1425,14 @@ jobs: GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }} GH_AW_AIC: ${{ needs.agent.outputs.aic }} GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} + GH_AW_DETECTION_JOB_RESULT: ${{ needs.detection.result }} GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }} GH_AW_DEFAULT_CHECKOUT_USES_TRIGGER_REF: "true" GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }} GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }} GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }} GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }} + GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR: ${{ needs.agent.outputs.model_endpoint_mismatch_error }} GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }} GH_AW_MAX_CACHE_MISSES_EXCEEDED: ${{ needs.agent.outputs.max_cache_misses_exceeded }} GH_AW_MISSING_MODEL_PRICING_ERROR: ${{ needs.agent.outputs.missing_model_pricing_error }} diff --git a/actions/setup/js/agent_error_patterns.cjs b/actions/setup/js/agent_error_patterns.cjs index 34637d6db46..d9eb1e95e5a 100644 --- a/actions/setup/js/agent_error_patterns.cjs +++ b/actions/setup/js/agent_error_patterns.cjs @@ -1,6 +1,6 @@ // @ts-check -const { MAX_RUNS_EXCEEDED_PATTERNS, isMaxRunsExceededError } = require("./harness_error_patterns.cjs"); +const { MAX_RUNS_EXCEEDED_PATTERNS, isMaxRunsExceededError, parseModelEndpointMismatch } = require("./harness_error_patterns.cjs"); const STEP_TIMEOUT_TOLERANCE_MS = 30_000; // Pattern: Copilot CLI inference access denied @@ -284,7 +284,7 @@ function extractMissingModelPricingModelName(logContent) { /** * Detect known error patterns in a log string and return detection results. * @param {string} logContent - Contents of the agent stdio log - * @returns {{ inferenceAccessError: boolean, mcpPolicyError: boolean, agenticEngineTimeout: boolean, modelNotSupportedError: boolean, http400ResponseError: boolean, capiQuotaExceededError: boolean, invocationCapExceeded: boolean, maxCacheMissesExceeded: boolean, missingModelPricingError: boolean, missingModelPricingModelName: string, shellExpansionGuardRejected: boolean }} + * @returns {{ inferenceAccessError: boolean, mcpPolicyError: boolean, agenticEngineTimeout: boolean, modelNotSupportedError: boolean, modelEndpointMismatchError: boolean, http400ResponseError: boolean, capiQuotaExceededError: boolean, invocationCapExceeded: boolean, maxCacheMissesExceeded: boolean, missingModelPricingError: boolean, missingModelPricingModelName: string, shellExpansionGuardRejected: boolean }} */ function detectErrors(logContent) { const missingModelPricingModelName = extractMissingModelPricingModelName(logContent); @@ -297,6 +297,7 @@ function detectErrors(logContent) { mcpPolicyError: MCP_POLICY_BLOCKED_PATTERN.test(logContent), agenticEngineTimeout: isAgenticEngineTimeout(logContent), modelNotSupportedError: MODEL_NOT_SUPPORTED_PATTERN.test(modelDiagnostics) || isUnsupportedModelToolsError(logContent), + modelEndpointMismatchError: parseModelEndpointMismatch(logContent) !== null, http400ResponseError: HTTP_400_RESPONSE_ERROR_PATTERN.test(logContent), capiQuotaExceededError: isCAPIQuotaExceededError(logContent), invocationCapExceeded: isInvocationCapExceededError(logContent), @@ -309,7 +310,7 @@ function detectErrors(logContent) { /** * Build GitHub Actions output lines from detection results. - * @param {{ inferenceAccessError: boolean, mcpPolicyError: boolean, agenticEngineTimeout: boolean, modelNotSupportedError: boolean, http400ResponseError: boolean, capiQuotaExceededError: boolean, invocationCapExceeded: boolean, maxCacheMissesExceeded: boolean, missingModelPricingError: boolean, missingModelPricingModelName: string, shellExpansionGuardRejected: boolean }} results + * @param {{ inferenceAccessError: boolean, mcpPolicyError: boolean, agenticEngineTimeout: boolean, modelNotSupportedError: boolean, modelEndpointMismatchError: boolean, http400ResponseError: boolean, capiQuotaExceededError: boolean, invocationCapExceeded: boolean, maxCacheMissesExceeded: boolean, missingModelPricingError: boolean, missingModelPricingModelName: string, shellExpansionGuardRejected: boolean }} results * @returns {string[]} */ function buildOutputLines(results) { @@ -319,6 +320,7 @@ function buildOutputLines(results) { `mcp_policy_error=${results.mcpPolicyError}`, `agentic_engine_timeout=${results.agenticEngineTimeout}`, `model_not_supported_error=${results.modelNotSupportedError}`, + `model_endpoint_mismatch_error=${results.modelEndpointMismatchError === true}`, `http_400_response_error=${results.http400ResponseError}`, `capi_quota_exceeded_error=${effectiveCAPIQuotaExceeded}`, `invocation_cap_exceeded=${results.invocationCapExceeded}`, diff --git a/actions/setup/js/copilot_harness.cjs b/actions/setup/js/copilot_harness.cjs index c3a541002cd..ce13be130d7 100644 --- a/actions/setup/js/copilot_harness.cjs +++ b/actions/setup/js/copilot_harness.cjs @@ -82,7 +82,6 @@ const { fetchAWFReflect, fetchModelsFromUrl, inferProviderTypeForModel, - getCatalogModelEntry, resolveMultiProviderFromReflect, } = require("./awf_reflect.cjs"); const { runSafeOutputsCLI, buildMissingToolAlternatives, emitMissingToolPermissionIssue, emitInfrastructureIncomplete, hasExpectedSafeOutputs, hasTerminalSafeOutput, hasNoopInSafeOutputs } = require("./safeoutputs_cli.cjs"); @@ -97,6 +96,7 @@ const { resolveAWFModelRoutingSelection, isModelAvailableInReflectData, getAWFMo const { recordAWFModelRoutingOutcome } = require("./awf_model_routing.cjs"); const COPILOT_ROUTING_POLICY = getAWFModelRoutingPolicy("copilot"); const { loadModelsJson } = require("./model_costs.cjs"); +const { applyCopilotWireAPI: configureCopilotWireAPI, warnCopilotSubagentEndpoints, recordModelEndpointMismatch, getSupportedEndpoints, MODEL_ENDPOINT_FIX } = require("./copilot_wire_api.cjs"); const { resolveConfiguredCopilotModel, ModelAliasResolutionError } = require("./resolve_model_alias.cjs"); const { parseAICreditsErrorInfoFromAuditLog, parseMaxAICreditsFromAuditLog, parseMaxAICreditsExceededFromAuditLog, parseAPIProxyGuardRejectionFromEventLog, formatAPIProxyGuardRejection } = require("./ai_credits_context.cjs"); @@ -457,38 +457,18 @@ async function applyCopilotModelAliasResolution(options) { } /** - * Auto-configure COPILOT_PROVIDER_WIRE_API based on the resolved COPILOT_MODEL. - * - * Skips configuration when COPILOT_PROVIDER_WIRE_API is already set so that - * explicit engine.env values always take precedence. Looks up the wire_api for - * the current COPILOT_MODEL in the github-copilot provider section of models.json, - * defaulting GPT models to the responses API when the catalog does not specify one. + * Configure and validate COPILOT_PROVIDER_WIRE_API using AWF endpoint metadata. * * @param {{ * modelsJson: Record | null, + * awfReflectData?: any, + * configuredModel?: string, + * overrideSource?: string, * logger?: (msg: string) => void, * }} options */ -function applyCopilotWireAPI({ modelsJson, logger = log }) { - if (process.env.COPILOT_PROVIDER_WIRE_API) { - logger(`COPILOT_PROVIDER_WIRE_API already set to ${process.env.COPILOT_PROVIDER_WIRE_API} — skipping auto-configure`); - return; // User override wins — do not auto-configure. - } - const modelName = typeof process.env.COPILOT_MODEL === "string" ? process.env.COPILOT_MODEL.trim() : ""; - if (!modelName) return; - - const catalogEntry = getCatalogModelEntry(modelsJson, modelName, "github-copilot"); - const wireApi = catalogEntry && typeof catalogEntry.wire_api === "string" ? catalogEntry.wire_api : null; - if (wireApi) { - logger(`auto-configuring COPILOT_PROVIDER_WIRE_API=${wireApi} for model ${modelName}`); - process.env.COPILOT_PROVIDER_WIRE_API = wireApi; - return; - } - - if (/^gpt-(?:[5-9]|\d{2,})(?:[.-]|$)/i.test(modelName.split("?")[0])) { - logger(`auto-configuring COPILOT_PROVIDER_WIRE_API=responses for GPT model ${modelName}`); - process.env.COPILOT_PROVIDER_WIRE_API = "responses"; - } +function applyCopilotWireAPI(options) { + return configureCopilotWireAPI({ logger: log, ...options }); } /** @@ -722,12 +702,14 @@ function extractTokenCountFromOutput(output) { * isTrustedAICreditsBudgetExhausted?: boolean, * isSDKSessionIdleTimeout?: boolean, * isModelRoutingFailure?: boolean, + * isModelEndpointMismatch?: boolean, * hasNumerousPermissionDenied?: boolean, * tokenCount?: number, * }} detection * @returns {string} */ function classifyCopilotFailure(detection) { + if (detection.isModelEndpointMismatch) return "model_endpoint_mismatch"; if (detection.isModelRoutingFailure) return "model_routing_failed"; if (detection.isInvocationCapExceeded) return "invocation_cap_exceeded"; if (detection.isTrustedAICreditsBudgetExhausted) return "ai_credits_exhausted"; @@ -765,6 +747,7 @@ function shouldRetryFailedExecution(params) { if (hasNumerousPermissionDeniedIssues(params.output)) return false; if (isCAPIQuotaExceededError(params.output)) return false; const nonRetryableGuard = detectNonRetryableHarnessGuard(params.output); + if (nonRetryableGuard.modelEndpointMismatch) return false; if (nonRetryableGuard.maxRunsExceeded) return false; if (nonRetryableGuard.apiProxyGuardRejection) return false; return params.attempt < params.maxRetries && (params.hasOutput || isCAPIServerError(params.output)); @@ -1212,6 +1195,8 @@ async function main() { // Skip when AWF_REFLECT_ENABLED is not "1" (e.g. sandbox.agent: false — no api-proxy running). /** @type {any} */ let awfReflectData = null; + const configuredCopilotModel = process.env.COPILOT_MODEL || ""; + const configuredWireAPI = process.env.COPILOT_PROVIDER_WIRE_API; const modelRoutingRequired = process.env.GH_AW_MODEL_ROUTING === "1"; /** @type {any} */ let modelRoutingSelection = null; @@ -1232,6 +1217,7 @@ async function main() { if (modelRoutingSelection) { if (!copilotSDKMode) { resolvedArgs = applyCopilotRoutingArgs(resolvedArgs, modelRoutingSelection); + if (configuredWireAPI) process.env.COPILOT_PROVIDER_WIRE_API = configuredWireAPI; } } else { applyModelFallback(process.env, "COPILOT_MODEL", log); @@ -1243,12 +1229,26 @@ async function main() { return null; } const refreshed = await fetchAWFReflect({ logger: log }); + if (refreshed.ok && refreshed.reflectData) awfReflectData = refreshed.reflectData; return refreshed.ok && refreshed.reflectData ? refreshed.reflectData : null; }, }); - if (!copilotSDKMode) { - applyCopilotWireAPI({ modelsJson: loadModelsJson(), logger: log }); + } + if (!copilotSDKMode) { + try { + applyCopilotWireAPI({ + modelsJson: loadModelsJson(), + awfReflectData, + configuredModel: configuredCopilotModel, + overrideSource: modelRoutingSelection && !configuredWireAPI ? "routing" : "override", + logger: log, + }); + } catch (err) { + log(getErrorMessage(err)); + process.exit(1); + return; } + warnCopilotSubagentEndpoints({ awfReflectData, logger: log }); } // Pre-flight: skip the agent entirely when a noop has already been written by a prior step. @@ -1510,6 +1510,7 @@ async function main() { const failureClass = classifyCopilotFailure({ hasOutput: result.hasOutput, isModelRoutingFailure, + isModelEndpointMismatch: !!nonRetryableGuard.modelEndpointMismatch, isAuthErr, isAuthenticationFailed, isTransientCAPIError: isCAPIError, @@ -1573,6 +1574,20 @@ async function main() { ); } + if (nonRetryableGuard.modelEndpointMismatch) { + const mismatch = nonRetryableGuard.modelEndpointMismatch; + recordModelEndpointMismatch({ + ...mismatch, + phase: "runtime", + configured_model: configuredCopilotModel, + resolved_model: childEnv?.COPILOT_MODEL || process.env.COPILOT_MODEL || "", + wire_api: childEnv?.COPILOT_PROVIDER_WIRE_API || process.env.COPILOT_PROVIDER_WIRE_API || "completions", + wire_api_source: configuredWireAPI ? "override" : "inferred", + supported_endpoints: getSupportedEndpoints(awfReflectData, mismatch.model || childEnv?.COPILOT_MODEL || process.env.COPILOT_MODEL) || [], + }); + log(`model endpoint mismatch — not retrying: ${mismatch.detail} ${MODEL_ENDPOINT_FIX}`); + return { action: "stop" }; + } if (shouldStopForNoopSafeOutputs({ attempt, safeOutputsPath, hasNoopInSafeOutputs, log })) { return { action: "stop", exitCode: 0 }; } @@ -1889,6 +1904,7 @@ if (typeof module !== "undefined" && module.exports) { applyModelFallback, applyCopilotModelAliasResolution, applyCopilotWireAPI, + warnCopilotSubagentEndpoints, resolveAWFModelRoutingSelection, resolveCopilotModelRouting, applyCopilotRoutingSelection, diff --git a/actions/setup/js/copilot_harness.test.cjs b/actions/setup/js/copilot_harness.test.cjs index 9ad462c9ab7..c1c3984bc99 100644 --- a/actions/setup/js/copilot_harness.test.cjs +++ b/actions/setup/js/copilot_harness.test.cjs @@ -66,6 +66,7 @@ const { writeCopilotOutputs, parseCopilotSDKServerArgsFromEnv, applyCopilotWireAPI, + warnCopilotSubagentEndpoints, applyCopilotModelAliasResolution, formatInferenceEndpointForLog, logCopilotInferenceConfiguration, @@ -3642,6 +3643,70 @@ process.exit(1);`, }); }); + describe("model endpoint mismatch retries", () => { + it("fails before spawning the CLI for an incompatible override", () => { + const tempDir = makeHarnessTempDir("copilot-endpoint-startup-"); + const callsPath = path.join(tempDir, "spawned"); + const preloadPath = path.join(tempDir, "reflect.cjs"); + const stubPath = path.join(tempDir, "stub.cjs"); + fs.writeFileSync( + preloadPath, + `const reflect = require(${JSON.stringify(require.resolve("./awf_reflect.cjs"))}); +reflect.fetchAWFReflect = async () => ({ok: true, reflectData: {endpoints: [{provider: "github", configured: true, routing_models: [{model_id: "gpt-5.6-luna", candidate_metadata_complete: true, supported_endpoints: ["/responses"]}]}]}});` + ); + fs.writeFileSync(stubPath, `require("fs").writeFileSync(${JSON.stringify(callsPath)}, "spawned");`); + const result = spawnSync(process.execPath, ["--require", preloadPath, "copilot_harness.cjs", process.execPath, stubPath], { + cwd: path.dirname(require.resolve("./copilot_harness.cjs")), + env: { ...harnessChildEnv, GH_AW_TMP_DIR: tempDir, AWF_REFLECT_ENABLED: "1", GH_AW_MODEL_ROUTING: "0", COPILOT_MODEL: "gpt-5.6-luna", COPILOT_PROVIDER_WIRE_API: "completions" }, + encoding: "utf8", + timeout: 15000, + }); + expect(result.status).toBe(1); + expect(fs.existsSync(callsPath)).toBe(false); + expect(result.stderr).toMatch(/gpt-5.6-luna.*completions.*\/chat\/completions.*\/responses.*Pin a compatible model.*remove.*upgrade/); + expect(JSON.parse(fs.readFileSync(path.join(tempDir, "agent", "model-endpoint-mismatch.json"), "utf8"))).toMatchObject({ phase: "startup" }); + }); + + const messages = [ + "400 Cannot translate Copilot request feature 'tools[custom]' between Responses and Chat Completions. Routing model \"gpt-5.6-luna\" to /responses is incompatible", + "400 Unsupported Responses custom tool '(unknown)'", + "400 model_endpoint_incompatible", + "400 Model gpt-5.6-luna is not accessible via the /chat/completions endpoint", + ]; + it.each(messages.flatMap(message => [false, true].map(partial => [message, partial])))("stops %s after partial=%s", (message, partial) => { + const tempDir = makeHarnessTempDir("copilot-endpoint-retry-"); + const stubPath = path.join(tempDir, "stub.cjs"); + const callsPath = path.join(tempDir, "calls.jsonl"); + fs.writeFileSync( + stubPath, + `const fs = require("fs"); +const callsPath = process.env.COPILOT_HARNESS_STUB_CALLS; +const prior = fs.existsSync(callsPath); +fs.appendFileSync(callsPath, JSON.stringify(process.argv.slice(2)) + "\\n"); +if (${partial} && !prior) process.stdout.write("partial work done\\n"); +else process.stderr.write(${JSON.stringify(message)} + "\\n"); +process.exit(1);` + ); + const result = spawnSync(process.execPath, ["copilot_harness.cjs", process.execPath, stubPath], { + cwd: path.dirname(require.resolve("./copilot_harness.cjs")), + env: { ...harnessChildEnv, GH_AW_TMP_DIR: tempDir, COPILOT_HARNESS_STUB_CALLS: callsPath, GH_AW_SAFE_OUTPUTS: path.join(tempDir, "safe-outputs.jsonl") }, + encoding: "utf8", + timeout: 15000, + }); + expect(result.status).toBe(1); + const calls = fs + .readFileSync(callsPath, "utf8") + .trim() + .split("\n") + .map(line => JSON.parse(line)); + expect(calls).toHaveLength(partial ? 2 : 1); + if (partial) expect(calls[1]).toContain("--continue"); + expect(result.stderr).toContain("failureClass=model_endpoint_mismatch"); + expect(result.stderr).toContain("model endpoint mismatch — not retrying"); + expect(JSON.parse(fs.readFileSync(path.join(tempDir, "agent", "model-endpoint-mismatch.json"), "utf8"))).toMatchObject({ phase: "runtime", category: "model_endpoint_mismatch", detail: message }); + }); + }); + describe("applyCopilotWireAPI", () => { afterEach(() => { delete process.env.COPILOT_MODEL; @@ -3667,6 +3732,155 @@ process.exit(1);`, }; } + function reflectModels(models) { + return { endpoints: [{ provider: "github", configured: true, routing_models: models.map(([model_id, supported_endpoints]) => ({ model_id, supported_endpoints, candidate_metadata_complete: true })) }] }; + } + + it("rejects an incompatible override and records the startup failure", () => { + const tempDir = makeHarnessTempDir("copilot-wire-mismatch-"); + vi.stubEnv("GH_AW_TMP_DIR", tempDir); + process.env.COPILOT_MODEL = "gpt-5.6-luna"; + process.env.COPILOT_PROVIDER_WIRE_API = "completions"; + expect(() => applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([["gpt-5.6-luna", ["/responses"]]]), configuredModel: "auto" })).toThrow( + /auto.*gpt-5.6-luna.*completions.*override.*\/chat\/completions.*\/responses.*Pin a compatible model.*remove.*upgrade/ + ); + const record = JSON.parse(fs.readFileSync(path.join(tempDir, "agent", "model-endpoint-mismatch.json"), "utf8")); + expect(record).toMatchObject({ phase: "startup", configured_model: "auto", resolved_model: "gpt-5.6-luna", supported_endpoints: ["/responses"] }); + }); + + it.each(["gpt-5.6-luna-utility", "new-model-not-in-catalog"])("uses endpoint metadata for %s", model => { + process.env.COPILOT_MODEL = model; + const logs = []; + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([[model, ["/responses"]]]), logger: message => logs.push(message) }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + expect(logs.join("\n")).toContain(model.startsWith("gpt-5") ? "source=model-name rule" : "source=AWF /reflect"); + }); + + it("resolves auto to a utility model before selecting its advertised endpoint", async () => { + process.env.COPILOT_MODEL = "auto"; + const reflect = reflectModels([["gpt-5.6-luna-utility", ["/responses"]]]); + reflect.endpoints[0].provider = "copilot"; + reflect.endpoints[0].models = ["gpt-5.6-luna-utility"]; + const read = vi.spyOn(fs, "readFileSync").mockReturnValueOnce(JSON.stringify({ apiProxy: { models: { auto: ["copilot/gpt-5.6-luna-utility"] } } })); + try { + await applyCopilotModelAliasResolution({ awfReflectData: reflect, logger: () => {} }); + } finally { + read.mockRestore(); + } + expect(process.env.COPILOT_MODEL).toBe("gpt-5.6-luna-utility"); + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflect, configuredModel: "auto" }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + }); + + it("retains the CLI completions default when both endpoints are supported without a preference", () => { + process.env.COPILOT_MODEL = "new-model"; + const logs = []; + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([["new-model", ["/responses", "/chat/completions"]]]), logger: message => logs.push(message) }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("completions"); + expect(logs.join("\n")).toContain("source=CLI default"); + expect(logs.join("\n")).not.toContain("source=AWF /reflect"); + }); + + it("looks up endpoint metadata without model effort query parameters", () => { + process.env.COPILOT_MODEL = "new-model?effort=high"; + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([["new-model", ["/responses"]]]) }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + }); + + it("uses the only supported endpoint even when the name suggests responses", () => { + process.env.COPILOT_MODEL = "gpt-5.6-luna"; + applyCopilotWireAPI({ modelsJson: makeModelsJson(), awfReflectData: reflectModels([["gpt-5.6-luna", ["/chat/completions"]]]) }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("completions"); + }); + + it("keeps the catalog preference when both endpoints are supported", () => { + process.env.COPILOT_MODEL = "gpt-5-mini"; + const logs = []; + applyCopilotWireAPI({ modelsJson: makeModelsJson(), awfReflectData: reflectModels([["gpt-5-mini", ["/chat/completions", "/responses"]]]), logger: message => logs.push(message) }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + expect(logs.join("\n")).toContain("source=catalog"); + expect(logs.join("\n")).not.toContain("source=AWF /reflect"); + }); + + it("preserves a model-name preference when both endpoints are supported", () => { + process.env.COPILOT_MODEL = "gpt-5-unknown"; + const logs = []; + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([["gpt-5-unknown", ["/chat/completions", "/responses"]]]), logger: message => logs.push(message) }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + expect(logs.join("\n")).toContain("source=model-name rule"); + expect(logs.join("\n")).not.toContain("source=AWF /reflect"); + }); + + it("labels a routing-selected endpoint as routing rather than an override", () => { + process.env.COPILOT_MODEL = "new-model"; + process.env.COPILOT_PROVIDER_WIRE_API = "responses"; + const logs = []; + applyCopilotWireAPI({ + modelsJson: null, + awfReflectData: reflectModels([["new-model", ["/responses", "/chat/completions"]]]), + overrideSource: "routing", + logger: message => logs.push(message), + }); + expect(logs.join("\n")).toContain("source=routing (verified against AWF /reflect)"); + }); + + it("rejects a model with no CLI-compatible endpoints", () => { + vi.stubEnv("GH_AW_TMP_DIR", makeHarnessTempDir("copilot-wire-unusable-")); + process.env.COPILOT_MODEL = "new-model"; + expect(() => applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([["new-model", ["/messages"]]]) })).toThrow(/no usable endpoint.*\/messages.*Pin a compatible model/); + }); + + it("falls back when candidate metadata is incomplete", () => { + process.env.COPILOT_MODEL = "gpt-5.6-luna"; + const reflect = reflectModels([["gpt-5.6-luna", ["/chat/completions"]]]); + reflect.endpoints[0].routing_models[0].candidate_metadata_complete = false; + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflect }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + }); + + it("does not select from ambiguous configured endpoint metadata", () => { + process.env.COPILOT_MODEL = "gpt-5.6-luna"; + const reflect = reflectModels([["gpt-5.6-luna", ["/chat/completions"]]]); + reflect.endpoints.push({ ...reflect.endpoints[0], provider: "copilot" }); + applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflect }); + expect(process.env.COPILOT_PROVIDER_WIRE_API).toBe("responses"); + }); + + it("redacts secrets before saving mismatch evidence", () => { + const tempDir = makeHarnessTempDir("copilot-wire-redaction-"); + vi.stubEnv("GH_AW_TMP_DIR", tempDir); + vi.stubEnv("GH_AW_SECRET_NAMES", "DIAGNOSTIC_TEST"); + vi.stubEnv("SECRET_DIAGNOSTIC_TEST", "test-secret-value-for-redaction"); + process.env.COPILOT_MODEL = "new-model"; + process.env.COPILOT_PROVIDER_WIRE_API = "test-secret-value-for-redaction"; + expect(() => applyCopilotWireAPI({ modelsJson: null, awfReflectData: reflectModels([["new-model", ["/responses"]]]) })).toThrow(); + expect(fs.readFileSync(path.join(tempDir, "agent", "model-endpoint-mismatch.json"), "utf8")).not.toContain("test-secret-value-for-redaction"); + }); + + it("warns only for custom agents incompatible with the session endpoint", () => { + const agentsDir = makeHarnessTempDir("copilot-subagents-"); + fs.writeFileSync(path.join(agentsDir, "other.md"), "---\nmodel: 'claude-haiku-5.5'\n---\nAgent"); + fs.writeFileSync(path.join(agentsDir, "same.md"), "---\nmodel: gpt-5-mini\n---\nAgent"); + fs.writeFileSync(path.join(agentsDir, "unknown.md"), "---\nmodel: unknown\n---\nAgent"); + process.env.COPILOT_MODEL = "gpt-5.6-luna"; + process.env.COPILOT_PROVIDER_WIRE_API = "responses"; + const logs = []; + warnCopilotSubagentEndpoints({ + agentsDir, + awfReflectData: reflectModels([ + ["gpt-5.6-luna", ["/responses"]], + ["gpt-5-mini", ["/responses"]], + ["claude-haiku-5.5", ["/chat/completions"]], + ]), + logger: message => logs.push(message), + }); + expect(logs).toHaveLength(1); + expect(logs[0]).toMatch(/other.md.*claude-haiku-5.5.*\/chat\/completions.*\/responses.*67460.*5103/); + logs.length = 0; + warnCopilotSubagentEndpoints({ agentsDir, awfReflectData: null, logger: message => logs.push(message) }); + expect(logs).toHaveLength(0); + }); + it("sets COPILOT_PROVIDER_WIRE_API=responses for a responses model", () => { process.env.COPILOT_MODEL = "gpt-5-mini"; applyCopilotWireAPI({ modelsJson: makeModelsJson(), logger: () => {} }); diff --git a/actions/setup/js/copilot_wire_api.cjs b/actions/setup/js/copilot_wire_api.cjs new file mode 100644 index 00000000000..375868ea30f --- /dev/null +++ b/actions/setup/js/copilot_wire_api.cjs @@ -0,0 +1,105 @@ +// @ts-check +"use strict"; + +const fs = require("fs"); +const path = require("path"); +const { getCatalogModelEntry } = require("./awf_reflect.cjs"); +const { getAWFRoutingModel, getAWFRoutingModelAmbiguityError } = require("./awf_model_routing.cjs"); +const { redactDiagnosticText } = require("./diagnostic_sanitization.cjs"); + +const WIRE_ENDPOINTS = { responses: "/responses", completions: "/chat/completions" }; +const MODEL_ENDPOINT_FIX = "Pin a compatible model, remove the COPILOT_PROVIDER_WIRE_API override, or upgrade gh-aw."; + +function getSupportedEndpoints(reflectData, model) { + model = typeof model === "string" ? model.split("?")[0] : ""; + if (!model || getAWFRoutingModelAmbiguityError(reflectData, model)) return null; + const entry = getAWFRoutingModel(reflectData, model); + return entry?.candidate_metadata_complete === true && Array.isArray(entry.supported_endpoints) && entry.supported_endpoints.every(endpoint => typeof endpoint === "string") ? entry.supported_endpoints : null; +} + +function recordModelEndpointMismatch(record, env = process.env) { + try { + const file = path.join(env.GH_AW_TMP_DIR || "/tmp/gh-aw", "agent", "model-endpoint-mismatch.json"); + fs.mkdirSync(path.dirname(file), { recursive: true }); + const safeRecord = Object.fromEntries( + Object.entries(record).map(([key, value]) => [key, typeof value === "string" ? redactDiagnosticText(value).slice(0, 2500) : Array.isArray(value) ? value.map(endpoint => redactDiagnosticText(endpoint).slice(0, 200)) : value]) + ); + fs.writeFileSync(file, JSON.stringify({ category: "model_endpoint_mismatch", ...safeRecord, fix: MODEL_ENDPOINT_FIX }) + "\n"); + return true; + } catch { + return false; + } +} + +/** + * Prefer complete AWF endpoint metadata, retaining the catalog/name preference + * only when supported or when endpoint metadata is unavailable. + * @param {{modelsJson: Record|null, awfReflectData?: any, configuredModel?: string, overrideSource?: string, logger?: (msg: string) => void}} options + */ +function applyCopilotWireAPI({ modelsJson, awfReflectData = null, configuredModel = process.env.COPILOT_MODEL || "", overrideSource = "override", logger = () => {} }) { + const model = (process.env.COPILOT_MODEL || "").trim(); + const override = process.env.COPILOT_PROVIDER_WIRE_API; + const supported = getSupportedEndpoints(awfReflectData, model); + const catalog = getCatalogModelEntry(modelsJson, model, "github-copilot"); + const catalogAPI = typeof catalog?.wire_api === "string" ? catalog.wire_api : null; + const nameAPI = /^gpt-(?:[5-9]|\d{2,})(?:[.-]|$)/i.test(model.split("?")[0]) ? "responses" : null; + let wireAPI = override || catalogAPI || nameAPI; + let source = override ? overrideSource : catalogAPI ? "catalog" : nameAPI ? "model-name rule" : "CLI default"; + if (supported !== null) { + const usable = Object.keys(WIRE_ENDPOINTS).filter(api => supported.includes(WIRE_ENDPOINTS[api])); + if (!override) { + const preferred = wireAPI || "completions"; + if (usable.includes(preferred)) { + wireAPI = preferred; + } else { + wireAPI = usable[0]; + source = "AWF /reflect"; + } + } + if (!wireAPI || !supported.includes(WIRE_ENDPOINTS[wireAPI])) { + const detail = redactDiagnosticText( + `Model endpoint mismatch: configured model '${configuredModel}'${configuredModel !== model ? ` resolved to '${model}'` : ""}; COPILOT_PROVIDER_WIRE_API=${wireAPI || "(none)"} (${source}, ${WIRE_ENDPOINTS[wireAPI] || "(no usable endpoint)"}); supported endpoints: [${supported.join(", ")}].` + ); + recordModelEndpointMismatch({ phase: "startup", configured_model: configuredModel, resolved_model: model, wire_api: wireAPI || "", wire_api_source: source, supported_endpoints: supported, detail }); + throw new Error(`${detail} ${MODEL_ENDPOINT_FIX}`); + } + } + if (override) { + logger(`COPILOT_PROVIDER_WIRE_API already set to ${override} — source=${source}${supported !== null ? " (verified against AWF /reflect)" : ""}`); + } else if (wireAPI && model) { + process.env.COPILOT_PROVIDER_WIRE_API = wireAPI; + logger(`auto-configuring COPILOT_PROVIDER_WIRE_API=${wireAPI} for model ${model} — source=${source}`); + } else { + logger(`COPILOT_PROVIDER_WIRE_API unset — source=CLI default`); + } +} + +/** + * @param {{awfReflectData: any, agentsDir?: string, logger?: (message: string) => void}} options + */ +function warnCopilotSubagentEndpoints({ awfReflectData, agentsDir = path.join(process.env.GITHUB_WORKSPACE || process.cwd(), ".github", "agents"), logger = () => {} }) { + const mainModel = process.env.COPILOT_MODEL || ""; + const mainEndpoints = getSupportedEndpoints(awfReflectData, mainModel); + const endpoint = WIRE_ENDPOINTS[process.env.COPILOT_PROVIDER_WIRE_API || "completions"]; + if (!mainEndpoints || !mainEndpoints.includes(endpoint)) return; + try { + for (const file of fs.readdirSync(agentsDir, { withFileTypes: true })) { + if (!file.isFile() || !file.name.endsWith(".md")) continue; + const text = fs.readFileSync(path.join(agentsDir, file.name), "utf8"); + const frontmatter = /^---\r?\n([\s\S]*?)\r?\n---(?:\r?\n|$)/.exec(text)?.[1]; + const scalar = frontmatter?.match(/^model:[ \t]*(.+)$/m)?.[1]?.trim(); + const model = scalar?.match(/^(?:"([^"]+)"|'([^']+)'|([^#\s]+))(?:\s*(?:#.*)?)?$/); + const agentModel = model?.[1] || model?.[2] || model?.[3]; + const supported = getSupportedEndpoints(awfReflectData, agentModel); + if (supported && !supported.includes(endpoint)) { + logger( + `warning: custom agent '${file.name}' model '${agentModel}' supports [${supported.join(", ")}], incompatible with main model '${mainModel}' session endpoint ${endpoint}. See https://github.com/github/gh-aw/issues/67460 and https://github.com/github/copilot-cli/issues/5103` + ); + } + } + } catch (err) { + logger(`custom agent endpoint validation skipped: ${err instanceof Error ? err.message : "unable to read optional custom agents"}`); + } +} + +module.exports = { applyCopilotWireAPI, getSupportedEndpoints, warnCopilotSubagentEndpoints, recordModelEndpointMismatch, MODEL_ENDPOINT_FIX }; diff --git a/actions/setup/js/detect_agent_errors.cjs b/actions/setup/js/detect_agent_errors.cjs index 0b06bd93f73..4dd513ba3d8 100644 --- a/actions/setup/js/detect_agent_errors.cjs +++ b/actions/setup/js/detect_agent_errors.cjs @@ -21,6 +21,8 @@ * - model_not_supported_error: The configured model is invalid or unsupported * for the selected engine/account (for example unknown model name, model not * found, or model unavailable for the plan). + * - model_endpoint_mismatch_error: The configured model cannot serve the request + * endpoint or tool protocol; changing the model or endpoint is required. * - http_400_response_error: The engine surfaced a generic HTTP 400 Bad Request * response (for example "Response status code does not indicate success: 400 (Bad Request)"). * - capi_quota_exceeded_error: The Copilot CAPI quota has been exhausted @@ -79,8 +81,6 @@ const { collectAgentExecution, agentErrorDiagnosticText, parseAgentExitCode } = const { writeSessionArtifact } = require("./session_artifact.cjs"); const { collectAddMaskedValues } = require("./add_mask_redaction.cjs"); -const LOG_FILE = "/tmp/gh-aw/agent-stdio.log"; - // File written by the engine execution step with the epoch milliseconds at which the // engine CLI was started. Used to measure how long the engine ran before it was killed. const AGENT_CLI_START_MS_FILE = "/tmp/gh-aw/agent_cli_start_ms.txt"; @@ -113,7 +113,7 @@ function detectStepTimeoutFromEnvironment() { /** * Write GitHub Actions outputs to $GITHUB_OUTPUT. - * @param {{ inferenceAccessError: boolean, mcpPolicyError: boolean, agenticEngineTimeout: boolean, modelNotSupportedError: boolean, http400ResponseError: boolean, capiQuotaExceededError: boolean, invocationCapExceeded: boolean, maxCacheMissesExceeded: boolean, missingModelPricingError: boolean, missingModelPricingModelName: string, shellExpansionGuardRejected: boolean }} results + * @param {ReturnType} results */ function writeOutputs(results) { const outputFile = process.env.GITHUB_OUTPUT; @@ -121,7 +121,6 @@ function writeOutputs(results) { process.stderr.write("[detect-agent-errors] GITHUB_OUTPUT not set — skipping output\n"); return; } - const lines = buildOutputLines(results); try { fs.appendFileSync(outputFile, lines.join("\n") + "\n"); @@ -130,6 +129,21 @@ function writeOutputs(results) { } } +function hasModelEndpointMismatchRecord(rootDir = process.env.GH_AW_TMP_DIR || "/tmp/gh-aw") { + try { + const record = JSON.parse(fs.readFileSync(path.join(rootDir, "agent", "model-endpoint-mismatch.json"), "utf8")); + return ( + record?.category === "model_endpoint_mismatch" && + ["startup", "runtime"].includes(record.phase) && + ["configured_model", "resolved_model", "wire_api", "wire_api_source", "detail", "fix"].every(key => typeof record[key] === "string") && + Array.isArray(record.supported_endpoints) && + record.supported_endpoints.every(endpoint => typeof endpoint === "string") + ); + } catch { + return false; + } +} + /** * Finds the most recently modified `*.log` file under `dir`, recursing into subdirectories. * @param {string} dir @@ -214,7 +228,7 @@ async function renderInternalEngineLogOnFailure() { * @param {ReturnType} results * @param {string} [rootDir] */ -function persistAgentExecution(logContent, results, rootDir = path.dirname(LOG_FILE)) { +function persistAgentExecution(logContent, results, rootDir = process.env.GH_AW_TMP_DIR || "/tmp/gh-aw") { const exitPath = path.join(rootDir, "agent_execution_exit_code.txt"); const execution = collectAgentExecution({ content: logContent, @@ -227,17 +241,18 @@ function persistAgentExecution(logContent, results, rootDir = path.dirname(LOG_F writeSessionArtifact(path.join(rootDir, "agent-errors.jsonl"), execution ? [execution] : [], collectAddMaskedValues(logContent)); } -async function main() { +async function main({ rootDir = process.env.GH_AW_TMP_DIR || "/tmp/gh-aw" } = {}) { let logContent = ""; + const logFile = path.join(rootDir, "agent-stdio.log"); - if (fs.existsSync(LOG_FILE)) { + if (fs.existsSync(logFile)) { try { - logContent = fs.readFileSync(LOG_FILE, "utf8"); + logContent = fs.readFileSync(logFile, "utf8"); } catch (err) { - throw new Error(`Failed to read file ${LOG_FILE}: ${getErrorMessage(err)}`, { cause: err }); + throw new Error(`Failed to read file ${logFile}: ${getErrorMessage(err)}`, { cause: err }); } } else { - process.stderr.write(`[detect-agent-errors] Log file not found: ${LOG_FILE}\n`); + process.stderr.write(`[detect-agent-errors] Log file not found: ${logFile}\n`); } const stdioResults = detectErrors(agentErrorDiagnosticText(logContent, process.env.GH_AW_ENGINE_ID === "aider" ? "aider" : undefined)); @@ -269,6 +284,7 @@ async function main() { const results = { ...stdioResults, + modelEndpointMismatchError: stdioResults.modelEndpointMismatchError || hasModelEndpointMismatchRecord(rootDir), agenticEngineTimeout: stdioResults.agenticEngineTimeout || stepTimeout, maxCacheMissesExceeded: stdioResults.maxCacheMissesExceeded || eventLogCacheMissesExceeded, missingModelPricingError: stdioResults.missingModelPricingError || auditMissingPricing, @@ -287,6 +303,9 @@ async function main() { if (results.modelNotSupportedError) { process.stderr.write("[detect-agent-errors] Detected model configuration error: configured model is invalid or unavailable for this engine/account\n"); } + if (results.modelEndpointMismatchError) { + process.stderr.write("[detect-agent-errors] Detected model endpoint mismatch: select a model compatible with the configured endpoint and tool protocol; retrying the same configuration will not resolve this error\n"); + } if (results.http400ResponseError) { process.stderr.write("[detect-agent-errors] Detected HTTP 400 response error in agent log\n"); } @@ -310,7 +329,7 @@ async function main() { writeOutputs(results); - persistAgentExecution(logContent, results); + persistAgentExecution(logContent, results, rootDir); await renderInternalEngineLogOnFailure(); } @@ -323,6 +342,7 @@ if (require.main === module) { module.exports = { ...errorPatterns, + hasModelEndpointMismatchRecord, persistAgentExecution, main, detectStepTimeoutFromEnvironment, diff --git a/actions/setup/js/detect_agent_errors.test.cjs b/actions/setup/js/detect_agent_errors.test.cjs index b8adf6820c9..cece201bdd6 100644 --- a/actions/setup/js/detect_agent_errors.test.cjs +++ b/actions/setup/js/detect_agent_errors.test.cjs @@ -37,12 +37,98 @@ const { isShellExpansionGuardRejectedError, extractMissingModelPricingModelName, buildOutputLines, + main, persistAgentExecution, findMostRecentLogFile, renderInternalEngineLogOnFailure, } = require("./detect_agent_errors.cjs"); describe("detect_agent_errors.cjs", () => { + describe("model endpoint mismatch", () => { + it.each([ + "400 Cannot translate Copilot request feature: tool_search", + "400 Unsupported Responses custom tool: web_search", + '{"type":"model_endpoint_incompatible","model":"gpt-5","endpoint":"/responses"}', + "Model 'gpt-5' is not accessible via the /responses endpoint.", + ])("detects and emits the dedicated category for %s", message => { + const results = detectErrors(message); + expect(results.modelEndpointMismatchError).toBe(true); + expect(results.modelNotSupportedError).toBe(false); + expect(results.inferenceAccessError).toBe(false); + expect(buildOutputLines(results)).toContain("model_endpoint_mismatch_error=true"); + }); + + it("does not classify an unrelated HTTP 400 as endpoint mismatch", () => { + const results = detectErrors("Response status code does not indicate success: 400 (Bad Request)"); + expect(results.http400ResponseError).toBe(true); + expect(results.modelEndpointMismatchError).toBe(false); + expect(buildOutputLines(results)).toContain("model_endpoint_mismatch_error=false"); + }); + + it("does not classify empty logs as endpoint mismatch", () => { + expect(detectErrors("").modelEndpointMismatchError).toBe(false); + }); + + it("prints actionable mismatch diagnostics and writes the category", async () => { + const previousOutput = process.env.GITHUB_OUTPUT; + const previousInternalLogs = process.env.GH_AW_ENGINE_INTERNAL_LOGS_DIR; + const exists = vi.spyOn(fs, "existsSync").mockImplementation(file => String(file).endsWith("/agent-stdio.log")); + const read = vi.spyOn(fs, "readFileSync").mockReturnValue('{"type":"session.error","data":{"message":"Unsupported Responses custom tool: web_search"}}'); + const append = vi.spyOn(fs, "appendFileSync").mockImplementation(() => {}); + const mkdir = vi.spyOn(fs, "mkdirSync").mockImplementation(() => undefined); + const write = vi.spyOn(fs, "writeFileSync").mockImplementation(() => {}); + const rename = vi.spyOn(fs, "renameSync").mockImplementation(() => {}); + const stderr = vi.spyOn(process.stderr, "write").mockReturnValue(true); + try { + process.env.GITHUB_OUTPUT = "mock-output"; + delete process.env.GH_AW_ENGINE_INTERNAL_LOGS_DIR; + await main(); + expect(append.mock.calls[0][1]).toContain("model_endpoint_mismatch_error=true"); + expect(stderr.mock.calls.map(([message]) => message).join("")).toContain("select a model compatible with the configured endpoint and tool protocol"); + } finally { + for (const spy of [exists, read, append, mkdir, write, rename, stderr]) spy.mockRestore(); + if (previousOutput === undefined) delete process.env.GITHUB_OUTPUT; + else process.env.GITHUB_OUTPUT = previousOutput; + if (previousInternalLogs === undefined) delete process.env.GH_AW_ENGINE_INTERNAL_LOGS_DIR; + else process.env.GH_AW_ENGINE_INTERNAL_LOGS_DIR = previousInternalLogs; + } + }); + + it("persists startup mismatch evidence when the harness never starts a session", async () => { + const rootDir = fs.mkdtempSync(path.join(os.tmpdir(), "gh-aw-startup-model-mismatch-")); + const outputFile = path.join(rootDir, "github-output"); + const record = { + category: "model_endpoint_mismatch", + phase: "startup", + configured_model: "gpt-5.6-luna", + resolved_model: "gpt-5.6-luna", + wire_api: "completions", + wire_api_source: "override", + supported_endpoints: ["/responses"], + detail: "Configured model does not support the selected endpoint", + fix: "Select a compatible model", + }; + const previousOutput = process.env.GITHUB_OUTPUT; + try { + fs.mkdirSync(path.join(rootDir, "agent"), { recursive: true }); + fs.writeFileSync(path.join(rootDir, "agent", "model-endpoint-mismatch.json"), JSON.stringify(record)); + process.env.GITHUB_OUTPUT = outputFile; + + await main({ rootDir }); + + expect(fs.readFileSync(outputFile, "utf8")).toContain("model_endpoint_mismatch_error=true"); + expect(fs.existsSync(path.join(rootDir, "agent-session.jsonl"))).toBe(false); + expect(fs.readFileSync(path.join(rootDir, "agent-errors.jsonl"), "utf8")).toContain('"model_endpoint_mismatch_error"'); + const { writeUnifiedSession } = require("./unified_session.cjs"); + expect(writeUnifiedSession({ rootDir, engine: "copilot" }).some(event => event.type === "model_endpoint.mismatch")).toBe(true); + } finally { + if (previousOutput === undefined) delete process.env.GITHUB_OUTPUT; + else process.env.GITHUB_OUTPUT = previousOutput; + fs.rmSync(rootDir, { recursive: true, force: true }); + } + }); + }); + it("does not persist rejected Aider JSON errors through live detection", () => { const root = fs.mkdtempSync(path.join(os.tmpdir(), "gh-aw-aider-errors-")); const previousEngine = process.env.GH_AW_ENGINE_ID; diff --git a/actions/setup/js/handle_agent_failure.cjs b/actions/setup/js/handle_agent_failure.cjs index ca2175cc0de..055cc75e85e 100644 --- a/actions/setup/js/handle_agent_failure.cjs +++ b/actions/setup/js/handle_agent_failure.cjs @@ -32,6 +32,8 @@ const { resolveFailureIssueRepo } = require("./repo_helpers.cjs"); const { GITHUB_API_VERSION } = require("./constants.cjs"); const { EMPTY_OUTPUT_CAUSES, EMPTY_OUTPUT_FAILURE_CAUSES } = require("./empty_output_outcome.cjs"); const { isAgentExecutionEvent } = require("./agent_execution.cjs"); +const { collectUnifiedSession, isModelEndpointMismatchData } = require("./unified_session.cjs"); +const { validateSessionFileHeader } = require("./unified_session_render.cjs"); const fs = require("fs"); const https = require("https"); const os = require("os"); @@ -309,6 +311,7 @@ function buildFailureMatchCategories(options) { if (options.copilotAgentNotFound) categories.push("copilot_agent_not_found"); if (options.mcpPolicyError) categories.push("mcp_policy_error"); if (options.modelNotSupportedError) categories.push("model_not_supported_error"); + if (options.modelEndpointMismatch) categories.push("model_endpoint_mismatch"); if (options.http400ResponseError) categories.push("http_400_response_error"); if (options.aiCreditsRateLimitError) categories.push("ai_credits_rate_limit_error"); if (options.hasEngineRateLimit429) categories.push("engine_rate_limit_429"); @@ -354,6 +357,66 @@ function getAgentSessionPath(agentOutputFile = process.env.GH_AW_AGENT_OUTPUT) { return agentOutputFile ? path.join(path.dirname(agentOutputFile), "agent-session.jsonl") : "/tmp/gh-aw/agent-session.jsonl"; } +/** Read mismatch evidence only from the collector's unified session, never raw logs. */ +function readModelEndpointMismatch() { + const root = process.env.GH_AW_AGENT_OUTPUT ? path.dirname(process.env.GH_AW_AGENT_OUTPUT) : "/tmp/gh-aw"; + const file = process.env.GH_AW_UNIFIED_SESSION || path.join(root, "usage/aw_session.jsonl"); + try { + /** @type {any[]} */ + let events; + try { + events = fs + .readFileSync(file, "utf8") + .split(/\r?\n/) + .filter(line => line.trim()) + .map(line => JSON.parse(line)); + } catch (error) { + const missing = error && typeof error === "object" && "code" in error && error.code === "ENOENT"; + if (process.env.GH_AW_UNIFIED_SESSION || !missing) throw error; + // The conclusion job reports failures before the usage artifact step writes the + // session file, so collect the downloaded agent artifacts in memory instead. + events = collectUnifiedSession({ rootDir: root, warn: () => {} }).events; + } + validateSessionFileHeader(events); + const matches = events.filter( + event => + event.type === "model_endpoint.mismatch" && + event.provenance?.component === "model_endpoint" && + event.provenance?.path === "agent/model-endpoint-mismatch.json" && + event.provenance?.phase === event.data?.phase && + isModelEndpointMismatchData(event.data) + ); + return matches.at(-1)?.data; + } catch { + core.debug("Unified session unavailable for model/endpoint mismatch classification"); + return undefined; + } +} + +/** @param {import("./types/unified_session").ModelEndpointMismatchData | undefined} mismatch @returns {string} */ +function buildModelEndpointMismatchContext(mismatch, detectionJobResult = process.env.GH_AW_DETECTION_JOB_RESULT) { + if (!mismatch || !isModelEndpointMismatchData(mismatch)) return ""; + const text = redactAndBoundDiagnostics( + [ + `Phase: ${mismatch.phase}`, + `Configured model: ${mismatch.configured_model}`, + `Resolved model: ${mismatch.resolved_model}`, + `Wire API: ${mismatch.wire_api} (source: ${mismatch.wire_api_source})`, + `Supported endpoints: ${mismatch.supported_endpoints.join(", ")}`, + ...(mismatch.model !== undefined ? [`Model: ${mismatch.model}`] : []), + ...(mismatch.endpoint !== undefined ? [`Endpoint: ${mismatch.endpoint}`] : []), + `Cause: ${redactAndBoundDiagnostics(mismatch.detail, { maxLength: 2500 })}`, + `Fix: ${redactAndBoundDiagnostics(mismatch.fix, { maxLength: 2500 })}`, + ...(detectionJobResult === "failure" ? ["Threat detection also failed while using this engine configuration; its missing result may be a consequence of the same model/endpoint mismatch."] : []), + ].join("\n") + ); + const fence = safeMarkdownCodeFence([text]); + return `\n> [!WARNING]\n> **Model/Endpoint Mismatch**\n>\n> ${fence}text\n${text + .split("\n") + .map(line => `> ${line}`) + .join("\n")}\n> ${fence}\n`; +} + /** * Build a precise failure issue title for known failure classes. * Falls back to the generic failure title when no specific class matches. @@ -378,6 +441,7 @@ function getAgentSessionPath(agentOutputFile = process.env.GH_AW_AGENT_OUTPUT) { * @param {boolean} options.maxAICreditsExceeded * @param {boolean} options.hasAssignmentErrors * @param {boolean} options.http400ResponseError + * @param {boolean} [options.hasModelEndpointMismatch] * @param {boolean} options.unknownModelAICredits * @param {boolean} [options.copilotOrgBillingError] * @param {string} [options.copilotAgentNotFound] - Requested agent identifier if a "No such agent" failure was detected @@ -401,6 +465,7 @@ function buildFailureIssueTitle(options) { const modelSuffix = options.missingModelPricingModelName ? ` (${options.missingModelPricingModelName})` : ""; return `[aw] ${workflowName} has no AI credits pricing for model${modelSuffix}`; } + if (options.hasModelEndpointMismatch) return `[aw] ${workflowName} has model/endpoint mismatch`; // Keep HTTP 400 below AI-credits signals: quota/rate-limit indicates an account-level // budget state that should take precedence when both classes are detected. if (options.http400ResponseError) return `[aw] ${workflowName} hit HTTP 400 bad request`; @@ -1818,7 +1883,8 @@ async function getFailedAgentDiagnostics() { function buildFailureDiagnosticsContext({ failureCategories, failingStep, agentConclusion = "", attributionUnavailable = "", engineFailureContext, items = [] }) { const infrastructureMessages = items.filter(item => item?.type === "report_incomplete" && item.reason === "infrastructure_error"); const isGenericFailure = failureCategories.includes("agent_failure") || failureCategories.includes("engine_driver_failure") || infrastructureMessages.length > 0; - if (!isGenericFailure) { + const hasModelEndpointMismatch = failureCategories.includes("model_endpoint_mismatch"); + if (!isGenericFailure && !hasModelEndpointMismatch) { return ""; } @@ -1841,6 +1907,8 @@ function buildFailureDiagnosticsContext({ failureCategories, failingStep, agentC } if (engineFailureContext.trim()) { context += engineFailureContext.trim() + "\n\n"; + } else if (hasModelEndpointMismatch) { + context += "The model/endpoint mismatch above is the classified cause.\n\n"; } else { context += "The runtime did not record a specific cause. Check the linked run for failure details.\n\n"; } @@ -3931,6 +3999,11 @@ async function main() { const { aiCredits, maxAICredits, aiCreditsRateLimitError: detectedAICreditsRateLimitError, maxAICreditsExceeded } = resolveAICreditsFailureState(); const aiCreditsRateLimitError = agentConclusion === "failure" && detectedAICreditsRateLimitError; const inferenceAccessError = process.env.GH_AW_INFERENCE_ACCESS_ERROR === "true"; + const modelEndpointMismatchSignal = process.env.GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR === "true"; + const signaledModelEndpointMismatch = modelEndpointMismatchSignal ? readModelEndpointMismatch() : undefined; + // A sub-agent that hit a mismatch and recovered does not fail a successful run; + // only a failed agent job or startup mismatch evidence is reported. + const modelEndpointMismatchError = modelEndpointMismatchSignal && (agentConclusion !== "success" || signaledModelEndpointMismatch?.phase === "startup"); const copilotOrgBillingError = !maxAICreditsExceeded && detectCopilotOrgBillingErrorFromLog(); const copilotAgentNotFound = detectCopilotAgentNotFoundFromLog(); const mcpPolicyError = process.env.GH_AW_MCP_POLICY_ERROR === "true"; @@ -4277,7 +4350,8 @@ async function main() { !maxAICreditsExceeded && !hasMissingTool && !hasMissingData && - !hasToolDenialsExceeded + !hasToolDenialsExceeded && + !modelEndpointMismatchError ) { core.info( `Agent job did not fail and no assignment/discussion/code-push/push-repo-memory/app-token/lockdown/oauth-token-check/stale-lock-file/daily-workflow-aic/daily-workflow-aic-accounting/ai-credits/max-ai-credits-exceeded/report-incomplete/cache-miss/missing-tool/missing-data/tool-denials-exceeded/secret-verification errors and has safe outputs (conclusion: ${agentConclusion}), skipping failure handling` @@ -4286,7 +4360,7 @@ async function main() { } // If we only have noop outputs (and no report_incomplete/cache-miss/missing-tool/data/tool-denials-exceeded), skip failure handling - if (hasOnlyNoopOutputs && !hasReportIncomplete && !hasCacheMissMisconfiguration && !hasMissingTool && !hasMissingData && !hasToolDenialsExceeded) { + if (hasOnlyNoopOutputs && !hasReportIncomplete && !hasCacheMissMisconfiguration && !hasMissingTool && !hasMissingData && !hasToolDenialsExceeded && !modelEndpointMismatchError) { core.info("Agent completed with only noop outputs - skipping failure handling"); return; } @@ -4296,7 +4370,7 @@ async function main() { // This prevents false-positive failure issues when a transient AI model error occurs // after the agent has already finished its task (e.g., create_discussion produced but // the server returned a spurious error on teardown). - if (hasCompletedDespiteJobFailure && !hasReportIncomplete && !hasCacheMissMisconfiguration) { + if (hasCompletedDespiteJobFailure && !hasReportIncomplete && !hasCacheMissMisconfiguration && !modelEndpointMismatchError) { core.info("Agent completed with valid safe outputs despite job failure (terminal_reason: completed) — skipping failure handling"); return; } @@ -4379,16 +4453,28 @@ async function main() { } } // Only the collector-written root metadata is trusted; report_incomplete.reason is agent-controlled. - const emptyOutputCause = agentOutputResult.success ? agentOutputResult.collectorEmptyOutputCause : undefined; - const terminalOutputFailureCause = agentOutputResult.success ? agentOutputResult.collectorFailureCause : undefined; + const modelEndpointMismatchCandidate = modelEndpointMismatchSignal ? signaledModelEndpointMismatch : readModelEndpointMismatch(); + const modelEndpointMismatch = agentConclusion === "success" && modelEndpointMismatchCandidate?.phase !== "startup" ? undefined : modelEndpointMismatchCandidate; + const hasModelEndpointMismatch = modelEndpointMismatchError || Boolean(modelEndpointMismatch); + const modelEndpointMismatchContext = buildModelEndpointMismatchContext(modelEndpointMismatch); + // A model/endpoint mismatch explains the missing terminal output, so the collector's + // generic empty-output classification (e.g. engine_outage) must not override it. + const collectorEmptyOutputCause = agentOutputResult.success ? agentOutputResult.collectorEmptyOutputCause : undefined; + const emptyOutputCause = hasModelEndpointMismatch ? undefined : collectorEmptyOutputCause; + const terminalOutputFailureCause = hasModelEndpointMismatch || !agentOutputResult.success ? undefined : agentOutputResult.collectorFailureCause; + const reportItems = (Array.isArray(agentOutputResult.items) ? agentOutputResult.items : []).filter( + item => !(hasModelEndpointMismatch && collectorEmptyOutputCause && item?.type === "report_incomplete" && item.reason === collectorEmptyOutputCause && typeof item.failureCause === "string") + ); + const hasReportedIncomplete = hasReportIncomplete && reportItems.some(item => item?.type === "report_incomplete"); const issueTitle = buildFailureIssueTitle({ workflowName: sanitizedWorkflowName, + hasModelEndpointMismatch, transportWedge, emptyOutputCause, terminalOutputFailureCause, isTimedOut, hasMissingSafeOutputs, - hasReportIncomplete, + hasReportIncomplete: hasReportedIncomplete, hasMissingTool, hasMissingData, hasCacheMissMisconfiguration, @@ -4424,7 +4510,7 @@ async function main() { hasRepoMemoryValidationErrors: repoMemoryValidationErrors.length > 0, hasPushRepoMemoryFailure, hasMissingSafeOutputs, - hasReportIncomplete, + hasReportIncomplete: hasReportedIncomplete, hasMissingTool, hasToolDenialsExceeded, hasMissingData, @@ -4435,6 +4521,7 @@ async function main() { copilotAgentNotFound: Boolean(copilotAgentNotFound), mcpPolicyError, modelNotSupportedError, + modelEndpointMismatch: hasModelEndpointMismatch, http400ResponseError, aiCreditsRateLimitError, hasEngineRateLimit429, @@ -4506,10 +4593,10 @@ async function main() { } } - const agentOutputItems = Array.isArray(agentOutputResult.items) ? agentOutputResult.items : []; + const agentOutputItems = reportItems; const needsFailureDiagnostics = failureCategories.includes("agent_failure") || failureCategories.includes("engine_driver_failure") || agentOutputItems.some(item => item?.type === "report_incomplete" && item.reason === "infrastructure_error"); - const failureDiagnostics = needsFailureDiagnostics ? await getFailedAgentDiagnostics() : { failingStep: "" }; + const failureDiagnostics = needsFailureDiagnostics || hasModelEndpointMismatch ? await getFailedAgentDiagnostics() : { failingStep: "" }; // Check if parent issue creation is enabled (defaults to false) const groupReports = process.env.GH_AW_GROUP_REPORTS === "true"; @@ -4594,7 +4681,7 @@ async function main() { // Suppress when tool-denials-exceeded is present: that context already covers the denied errors. const permissionDeniedContext = hasToolDenialsExceeded ? "" : buildPermissionDeniedContext(agentOutputResult.items, workflowID); // Build report_incomplete context - const reportIncompleteContext = buildReportIncompleteContext(agentOutputResult.items, { includeAgentText: !needsFailureDiagnostics }); + const reportIncompleteContext = buildReportIncompleteContext(reportItems, { includeAgentText: !needsFailureDiagnostics }); // Build missing safe outputs context let missingSafeOutputsContext = ""; @@ -4620,7 +4707,14 @@ async function main() { // context is the more actionable signal. // Also suppress when missing-model-pricing is detected: the pricing error is the // root cause and the engine error block would be redundant noise. - const engineFailureContext = shouldBuildEngineFailureContext(agentConclusion, hasToolDenialsExceeded, isTimedOut, missingModelPricingError, shellExpansionGuardRejected, Boolean(terminalOutputFailureCause)) + const engineFailureContext = shouldBuildEngineFailureContext( + agentConclusion, + hasToolDenialsExceeded, + isTimedOut, + missingModelPricingError, + shellExpansionGuardRejected, + Boolean(terminalOutputFailureCause || modelEndpointMismatchContext) + ) ? buildEngineFailureContext({ suppressEngineRateLimit429: maxAICreditsExceeded, maxCacheMissesExceeded, @@ -4705,6 +4799,7 @@ async function main() { inference_access_error_context: inferenceAccessErrorContext, mcp_policy_error_context: mcpPolicyErrorContext, model_not_supported_error_context: modelNotSupportedErrorContext, + model_endpoint_mismatch_context: modelEndpointMismatchContext, http_400_response_error_context: http400ResponseErrorContext, ai_credits_rate_limit_error_context: aiCreditsRateLimitErrorContext, unknown_model_ai_credits_context: unknownModelAICreditsContext, @@ -4835,7 +4930,7 @@ async function main() { const missingToolContext = missingToolReportAsFailure && !hasToolDenialsExceeded ? buildMissingToolContext(agentOutputResult.items) : ""; // Build report_incomplete context - const reportIncompleteContext = buildReportIncompleteContext(agentOutputResult.items, { includeAgentText: !needsFailureDiagnostics }); + const reportIncompleteContext = buildReportIncompleteContext(reportItems, { includeAgentText: !needsFailureDiagnostics }); // Build permission denied context (denied commands list + fix prompt). // Suppress when tool-denials-exceeded is present: that context already covers the denied errors. @@ -4865,7 +4960,14 @@ async function main() { // context is the more actionable signal. // Also suppress when missing-model-pricing is detected: the pricing error is the // root cause and the engine error block would be redundant noise. - const engineFailureContext = shouldBuildEngineFailureContext(agentConclusion, hasToolDenialsExceeded, isTimedOut, missingModelPricingError, shellExpansionGuardRejected, Boolean(terminalOutputFailureCause)) + const engineFailureContext = shouldBuildEngineFailureContext( + agentConclusion, + hasToolDenialsExceeded, + isTimedOut, + missingModelPricingError, + shellExpansionGuardRejected, + Boolean(terminalOutputFailureCause || modelEndpointMismatchContext) + ) ? buildEngineFailureContext({ suppressEngineRateLimit429: maxAICreditsExceeded, metadataOnly: needsFailureDiagnostics }) : ""; const failureDiagnosticsContext = buildFailureDiagnosticsContext({ @@ -4951,6 +5053,7 @@ async function main() { inference_access_error_context: inferenceAccessErrorContext, mcp_policy_error_context: mcpPolicyErrorContext, model_not_supported_error_context: modelNotSupportedErrorContext, + model_endpoint_mismatch_context: modelEndpointMismatchContext, http_400_response_error_context: http400ResponseErrorContext, ai_credits_rate_limit_error_context: aiCreditsRateLimitErrorContext, unknown_model_ai_credits_context: unknownModelAICreditsContext, @@ -5057,6 +5160,8 @@ async function main() { } module.exports = { + readModelEndpointMismatch, + buildModelEndpointMismatchContext, isInvalidatedPRMergeCheckout, main, buildCodePushFailureContext, diff --git a/actions/setup/js/handle_agent_failure.test.cjs b/actions/setup/js/handle_agent_failure.test.cjs index 52b9c4e0f0b..ad8aa219de0 100644 --- a/actions/setup/js/handle_agent_failure.test.cjs +++ b/actions/setup/js/handle_agent_failure.test.cjs @@ -82,6 +82,130 @@ describe("handle_agent_failure", () => { delete process.env.GH_AW_GROUP_REPORTS; }); + describe("model/endpoint mismatch context", () => { + const mismatch = { + category: "model_endpoint_mismatch", + phase: "runtime", + configured_model: "model-alias", + resolved_model: "model-resolved", + wire_api: "responses", + wire_api_source: "engine", + supported_endpoints: ["/chat/completions"], + detail: "Unsupported endpoint", + fix: "Select a compatible model", + model: "provider-model", + endpoint: "/responses", + }; + const header = { type: "session.format", data: { version: 1 }, provenance: { component: "collector", phase: "conclusion", path: "usage/aw_session.jsonl", index: 0 } }; + const record = { type: "model_endpoint.mismatch", data: mismatch, provenance: { component: "model_endpoint", phase: "runtime", path: "agent/model-endpoint-mismatch.json", index: 0 } }; + + it("reads only the unified session and uses the dedicated grouping category", () => { + const fs = require("fs"); + const { readModelEndpointMismatch, buildModelEndpointMismatchContext, buildFailureMatchCategories } = require("./handle_agent_failure.cjs"); + const read = vi.spyOn(fs, "readFileSync").mockReturnValue([header, record].map(event => JSON.stringify(event)).join("\n")); + vi.stubEnv("GH_AW_AGENT_OUTPUT", join(promptRoot, "agent-output.json")); + vi.stubEnv("GH_AW_UNIFIED_SESSION", ""); + try { + expect(readModelEndpointMismatch()).toEqual(mismatch); + expect(read).toHaveBeenCalledTimes(1); + expect(read).toHaveBeenCalledWith(join(promptRoot, "usage/aw_session.jsonl"), "utf8"); + const context = buildModelEndpointMismatchContext(mismatch); + expect(context).toContain("Cause: Unsupported endpoint"); + expect(context).toContain("Fix: Select a compatible model"); + expect(context).toContain("Configured model: model-alias"); + expect(context).toContain("Endpoint: /responses"); + expect(buildFailureMatchCategories({ agentConclusion: "failure", modelEndpointMismatch: true })).toEqual(["model_endpoint_mismatch"]); + expect(buildModelEndpointMismatchContext(mismatch, "failure")).toContain("same model/endpoint mismatch"); + expect(buildModelEndpointMismatchContext(mismatch, "success")).not.toContain("Threat detection also failed"); + expect(require("./handle_agent_failure.cjs").buildFailureIssueTitle({ workflowName: "Test", hasModelEndpointMismatch: true })).toContain("model/endpoint mismatch"); + } finally { + read.mockRestore(); + vi.unstubAllEnvs(); + } + }); + + it.each(["missing", "malformed", "headerless", "agent-forged", "wrong-phase", "wrong-path", "invalid"])("does not rescan logs when unified evidence is %s", kind => { + const fs = require("fs"); + const { readModelEndpointMismatch } = require("./handle_agent_failure.cjs"); + const records = + kind === "headerless" + ? [record] + : [ + header, + kind === "agent-forged" + ? { ...record, provenance: { ...record.provenance, component: "agent" } } + : kind === "wrong-phase" + ? { ...record, provenance: { ...record.provenance, phase: "startup" } } + : kind === "wrong-path" + ? { ...record, provenance: { ...record.provenance, path: "agent-session.jsonl" } } + : kind === "invalid" + ? { ...record, data: { ...mismatch, supported_endpoints: "bad" } } + : record, + ]; + const read = vi.spyOn(fs, "readFileSync").mockImplementation(() => { + if (kind === "missing") throw new Error("missing"); + return kind === "malformed" ? "{" : records.map(event => JSON.stringify(event)).join("\n"); + }); + try { + expect(readModelEndpointMismatch()).toBeUndefined(); + expect(read).toHaveBeenCalledTimes(1); + } finally { + read.mockRestore(); + } + }); + + it("bounds and redacts mismatch details and omits absent optional observations", () => { + const { buildModelEndpointMismatchContext } = require("./handle_agent_failure.cjs"); + vi.stubEnv("GH_AW_SECRET_NAMES", "MISMATCH_TEST"); + vi.stubEnv("SECRET_MISMATCH_TEST", "mismatch-secret-fixture"); + try { + const context = buildModelEndpointMismatchContext({ ...mismatch, model: undefined, endpoint: undefined, detail: "mismatch-secret-fixture " + "x".repeat(20000) }); + // Explicit undefined optional fields are not valid JSON contract values. + expect(context).toBe(""); + const { model, endpoint, ...startup } = mismatch; + const redacted = buildModelEndpointMismatchContext({ ...startup, phase: "startup", detail: "mismatch-secret-fixture", fix: "x".repeat(20000) }); + expect(redacted).not.toContain("mismatch-secret-fixture"); + expect(redacted).not.toContain("> Model:"); + expect(redacted).not.toContain("> Endpoint:"); + expect(redacted.length).toBeLessThan(8500); + const bounded = buildModelEndpointMismatchContext({ ...mismatch, detail: "x".repeat(20000), fix: "Preserved corrective action" }); + expect(bounded).toContain("Fix: Preserved corrective action"); + expect(buildModelEndpointMismatchContext(undefined)).toBe(""); + } finally { + vi.unstubAllEnvs(); + } + }); + + it("renders hostile model, endpoint, and detail values as literal redacted diagnostics", () => { + const { buildModelEndpointMismatchContext } = require("./handle_agent_failure.cjs"); + vi.stubEnv("GH_AW_SECRET_NAMES", "MISMATCH_TEST"); + vi.stubEnv("SECRET_MISMATCH_TEST", "mismatch-secret-fixture"); + try { + const hostile = "````\n# Injected heading\n[click](https://evil.example)\n\nmismatch-secret-fixture"; + const result = buildModelEndpointMismatchContext({ + ...mismatch, + configured_model: hostile, + resolved_model: hostile, + supported_endpoints: [hostile], + model: hostile, + endpoint: hostile, + detail: hostile, + fix: hostile, + }); + expect(result).not.toContain("mismatch-secret-fixture"); + const opening = result.match(/^> (`{3,})text$/m)?.[1]; + expect(opening).toBeTruthy(); + expect(result.indexOf(" { const closedAt = "2026-10-03T12:00:00Z"; const checkoutCompletedAt = "2026-10-03T12:00:01Z"; @@ -1136,6 +1260,251 @@ describe("handle_agent_failure", () => { expect(createIssueMock).not.toHaveBeenCalled(); }); + it.each([false, true])("publishes unified mismatch context and grouping in a failure report (reuse=%s)", async reuse => { + const mismatch = { + category: "model_endpoint_mismatch", + phase: "startup", + configured_model: "model-alias", + resolved_model: "model-resolved", + wire_api: "responses", + wire_api_source: "engine", + supported_endpoints: ["/chat/completions"], + detail: "Unsupported model API", + fix: "Select a compatible model", + }; + fs.mkdirSync(path.join(tmpDir, "usage"), { recursive: true }); + fs.writeFileSync( + path.join(tmpDir, "usage/aw_session.jsonl"), + [ + { type: "session.format", data: { version: 1 }, provenance: { component: "collector", phase: "conclusion", path: "usage/aw_session.jsonl", index: 0 } }, + { type: "model_endpoint.mismatch", data: mismatch, provenance: { component: "model_endpoint", phase: "startup", path: "agent/model-endpoint-mismatch.json", index: 0 } }, + ] + .map(event => JSON.stringify(event)) + .join("\n") + ); + const output = path.join(tmpDir, "output.json"); + fs.writeFileSync(output, JSON.stringify({ items: [{ type: "create_issue", title: "Result", body: "Done" }] })); + process.env.GH_AW_AGENT_CONCLUSION = "failure"; + process.env.GH_AW_FAILURE_REPORT_AS_ISSUE = "true"; + vi.stubEnv("GH_AW_AGENT_OUTPUT", output); + vi.stubEnv("GH_AW_UNIFIED_SESSION", ""); + for (const template of ["agent_failure_issue.md", "agent_failure_comment.md"]) { + fs.writeFileSync(path.join(promptsDir, template), fs.readFileSync(new URL(`../md/${template}`, import.meta.url), "utf8")); + } + const create = vi.fn().mockResolvedValue({ data: { number: 101, html_url: "https://github.com/owner/repo/issues/101", node_id: "I_101" } }); + const createComment = vi.fn().mockResolvedValue({ data: { id: 1001 } }); + global.github = { + rest: { + search: { + issuesAndPullRequests: vi.fn(async ({ q }) => ({ + data: { + total_count: reuse && q.includes("is:issue") ? 1 : 0, + items: + reuse && q.includes("is:issue") + ? [ + { + number: 42, + html_url: "https://github.com/owner/repo/issues/42", + body: buildExistingIssueBody({ branch: "feature/current", categories: ["model_endpoint_mismatch"] }), + }, + ] + : [], + }, + })), + }, + issues: { create, createComment }, + pulls: { get: vi.fn() }, + }, + graphql: vi.fn(), + }; + try { + await main(); + const called = reuse ? createComment : create; + expect(called).toHaveBeenCalledOnce(); + const body = called.mock.calls[0][0].body; + expect(body).toContain("**Model/Endpoint Mismatch**"); + expect(body).toContain("Cause: Unsupported model API"); + expect(body).toContain("Fix: Select a compatible model"); + expect(body).not.toContain("{model_endpoint_mismatch_context}"); + if (!reuse) expect(body).toContain("failure_categories: model_endpoint_mismatch"); + } finally { + vi.unstubAllEnvs(); + } + }); + + it("reports a startup mismatch instead of the collector's engine outage when no session or terminal output exists", async () => { + fs.mkdirSync(path.join(tmpDir, "agent"), { recursive: true }); + fs.writeFileSync( + path.join(tmpDir, "agent/model-endpoint-mismatch.json"), + JSON.stringify({ + category: "model_endpoint_mismatch", + phase: "startup", + configured_model: "gpt-5.6-luna", + resolved_model: "gpt-5.6-luna", + wire_api: "completions", + wire_api_source: "override", + supported_endpoints: ["/responses", "ws:/responses"], + detail: "Model gpt-5.6-luna does not support /chat/completions", + fix: "Pin a compatible model, remove the COPILOT_PROVIDER_WIRE_API override, or upgrade gh-aw.", + }) + ); + const output = path.join(tmpDir, "agent_output.json"); + fs.writeFileSync( + output, + JSON.stringify({ + items: [ + { + type: "report_incomplete", + reason: "engine_driver_failure", + failureCause: "engine_outage", + driverExitCode: 1, + retryCount: 0, + details: + "Agent finished without emitting a terminal safe output; task completion could not be confirmed.\nDriver exit code: 1. The engine driver exited before a terminal safe output was recorded.\nFailure classification: engine_outage\nLast engine error type: unknown\nRetry attempts observed: 0", + }, + ], + errors: [], + collectorEmptyOutputCause: "engine_driver_failure", + collectorFailureCause: "engine_outage", + collectorDriverExitCode: 1, + collectorRetryCount: 0, + }) + ); + process.env.GH_AW_AGENT_CONCLUSION = "failure"; + process.env.GH_AW_FAILURE_REPORT_AS_ISSUE = "true"; + vi.stubEnv("GH_AW_AGENT_OUTPUT", output); + vi.stubEnv("GH_AW_UNIFIED_SESSION", ""); + vi.stubEnv("GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR", "true"); + for (const template of ["agent_failure_issue.md", "agent_failure_comment.md"]) { + fs.writeFileSync(path.join(promptsDir, template), fs.readFileSync(new URL(`../md/${template}`, import.meta.url), "utf8")); + } + const create = vi.fn().mockResolvedValue({ data: { number: 101, html_url: "https://github.com/owner/repo/issues/101", node_id: "I_101" } }); + const createComment = vi.fn().mockResolvedValue({ data: { id: 1001 } }); + global.github = { + rest: { + search: { issuesAndPullRequests: vi.fn(async () => ({ data: { total_count: 0, items: [] } })) }, + issues: { create, createComment }, + pulls: { get: vi.fn() }, + actions: { listJobsForWorkflowRun: vi.fn() }, + }, + paginate: vi.fn(async () => []), + graphql: vi.fn(), + }; + try { + await main(); + expect(create).toHaveBeenCalledOnce(); + const { title, body } = create.mock.calls[0][0]; + expect(title).toContain("model/endpoint mismatch"); + expect(body).toContain("**Model/Endpoint Mismatch**"); + expect(body).toContain("Cause: Model gpt-5.6-luna does not support /chat/completions"); + expect(body).toContain("Fix: Pin a compatible model, remove the COPILOT_PROVIDER_WIRE_API override, or upgrade gh-aw."); + expect(body).toContain("model_endpoint_mismatch"); + expect(body).not.toContain("engine_outage"); + expect(body).not.toContain("Last engine error type: unknown"); + } finally { + vi.unstubAllEnvs(); + } + }); + + it("reports a startup mismatch together with failed-step diagnostics when step data is available", async () => { + fs.mkdirSync(path.join(tmpDir, "agent"), { recursive: true }); + fs.writeFileSync( + path.join(tmpDir, "agent/model-endpoint-mismatch.json"), + JSON.stringify({ + category: "model_endpoint_mismatch", + phase: "startup", + configured_model: "gpt-5.6-luna", + resolved_model: "gpt-5.6-luna", + wire_api: "completions", + wire_api_source: "override", + supported_endpoints: ["/responses"], + detail: "Model gpt-5.6-luna does not support /chat/completions", + fix: "Remove the COPILOT_PROVIDER_WIRE_API override.", + }) + ); + const output = path.join(tmpDir, "agent_output.json"); + fs.writeFileSync( + output, + JSON.stringify({ + items: [{ type: "report_incomplete", reason: "engine_driver_failure", failureCause: "engine_outage", driverExitCode: 1, retryCount: 0, details: "Failure classification: engine_outage" }], + errors: [], + collectorEmptyOutputCause: "engine_driver_failure", + collectorFailureCause: "engine_outage", + collectorDriverExitCode: 1, + collectorRetryCount: 0, + }) + ); + process.env.GH_AW_AGENT_CONCLUSION = "failure"; + process.env.GH_AW_FAILURE_REPORT_AS_ISSUE = "true"; + vi.stubEnv("GH_AW_AGENT_OUTPUT", output); + vi.stubEnv("GH_AW_UNIFIED_SESSION", ""); + vi.stubEnv("GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR", "true"); + for (const template of ["agent_failure_issue.md", "agent_failure_comment.md"]) { + fs.writeFileSync(path.join(promptsDir, template), fs.readFileSync(new URL(`../md/${template}`, import.meta.url), "utf8")); + } + const create = vi.fn().mockResolvedValue({ data: { number: 101, html_url: "https://github.com/owner/repo/issues/101", node_id: "I_101" } }); + global.github = { + rest: { + search: { issuesAndPullRequests: vi.fn(async () => ({ data: { total_count: 0, items: [] } })) }, + issues: { create, createComment: vi.fn() }, + pulls: { get: vi.fn() }, + actions: { listJobsForWorkflowRun: vi.fn() }, + }, + paginate: vi.fn(async () => [{ id: 456, name: "agent", conclusion: "failure", steps: [{ name: "Run agent", conclusion: "failure" }] }]), + request: vi.fn().mockResolvedValue({ data: "Error: agent-generated step log" }), + graphql: vi.fn(), + }; + try { + await main(); + expect(create).toHaveBeenCalledOnce(); + const { title, body } = create.mock.calls[0][0]; + expect(title).toContain("model/endpoint mismatch"); + expect(body).toContain("**Model/Endpoint Mismatch**"); + expect(body).toContain("Cause: Model gpt-5.6-luna does not support /chat/completions"); + expect(body).toContain("Fix: Remove the COPILOT_PROVIDER_WIRE_API override."); + expect(body).toContain("failure_categories: model_endpoint_mismatch"); + expect(body).toContain("### Failure Diagnostics"); + expect(body).toContain("**Agent job conclusion:** `failure`"); + expect(body).toContain("**Failing step:** `Run agent`"); + expect(body).toContain("The model/endpoint mismatch above is the classified cause."); + expect(body.indexOf("**Model/Endpoint Mismatch**")).toBeLessThan(body.indexOf("### Failure Diagnostics")); + expect(body).not.toContain("engine_outage"); + expect(body).not.toContain("engine_driver_failure"); + expect(body).not.toContain("agent-generated step log"); + } finally { + vi.unstubAllEnvs(); + } + }); + + it("does not file a failure issue for a recovered sub-agent mismatch in a successful run", async () => { + const output = path.join(tmpDir, "agent_output.json"); + fs.writeFileSync(output, JSON.stringify({ items: [{ type: "create_issue", title: "Result", body: "Done" }], errors: [] })); + process.env.GH_AW_AGENT_CONCLUSION = "success"; + process.env.GH_AW_FAILURE_REPORT_AS_ISSUE = "true"; + vi.stubEnv("GH_AW_AGENT_OUTPUT", output); + vi.stubEnv("GH_AW_UNIFIED_SESSION", ""); + vi.stubEnv("GH_AW_MODEL_ENDPOINT_MISMATCH_ERROR", "true"); + const create = vi.fn(); + const createComment = vi.fn(); + const search = vi.fn(async () => ({ data: { total_count: 0, items: [] } })); + global.github = { + rest: { + search: { issuesAndPullRequests: search }, + issues: { create, createComment }, + pulls: { get: vi.fn() }, + }, + graphql: vi.fn(), + }; + try { + await main(); + expect(create).not.toHaveBeenCalled(); + expect(createComment).not.toHaveBeenCalled(); + expect(search).not.toHaveBeenCalled(); + } finally { + vi.unstubAllEnvs(); + } + }); + it.each(["&#38;#96;", "&\x00#96;", "&#96;"])("omits agent-generated diagnostics from the final posted failure comment: %s", async entity => { fs.writeFileSync(path.join(promptsDir, "agent_failure_comment.md"), "{report_incomplete_context}"); const outputPath = path.join(tmpDir, "agent_output.json"); diff --git a/actions/setup/js/harness_error_patterns.cjs b/actions/setup/js/harness_error_patterns.cjs index c94248fc7c1..44eefb6dd64 100644 --- a/actions/setup/js/harness_error_patterns.cjs +++ b/actions/setup/js/harness_error_patterns.cjs @@ -2,6 +2,9 @@ "use strict"; +const { BUILT_IN_PATTERNS } = require("./redact_secrets.cjs"); +const { collectAddMaskedValues, redactMaskedValues } = require("./add_mask_redaction.cjs"); + const AI_CREDITS_EXCEEDED_PATTERNS = [/\bmax[\s_-]*ai[\s_-]*credits[\s_-]*exceeded\b/i, /\bai[\s_-]*credits[\s_-]*rate[\s_-]*limit[\s_-]*error\b/i, /ai[\s_-]*credits?.*(?:rate[\s-]*limit|limit exceeded|budget exceeded|exceeded)/i]; // Canonical rejection emitted by the AWF API proxy once the configured `apiProxy.maxAiCredits` @@ -24,6 +27,40 @@ const GOAL_ALREADY_ACTIVE_PATTERNS = [/\bthis thread already has a goal\b[\s\S]* // ("Maximum LLM invocations exceeded"). const MAX_RUNS_EXCEEDED_PATTERNS = [/\bmax_runs_exceeded\b/i, /Maximum LLM invocations exceeded/i]; +const MODEL_ENDPOINT_MISMATCH_PATTERN = + /\bCannot translate Copilot request feature\b|\bUnsupported Responses custom tool\b|\bmodel_endpoint_incompatible\b|\bnot accessible via the [^\r\n]{1,160}? endpoint\b|\bRouting model\s+["'`][a-z0-9._:/@-]{1,200}["'`]\s+to\s+\/[a-z0-9._/-]{1,160}\s+is incompatible\b/i; + +/** + * Extract a model/endpoint incompatibility, retaining only the matching message line. + * @param {unknown} output + * @returns {{ model?: string, endpoint?: string, detail: string } | null} + */ +function parseModelEndpointMismatch(output) { + if (typeof output !== "string") return null; + const maskedValues = collectAddMaskedValues(output); + for (const line of output.split(/\r\n|\r|\n/)) { + if (!MODEL_ENDPOINT_MISMATCH_PATTERN.test(line)) continue; + // Redact before bounding so truncation cannot leave a partial credential exposed. + let redactedLine = redactMaskedValues(line, maskedValues); + for (const { pattern } of BUILT_IN_PATTERNS) redactedLine = redactedLine.replace(pattern, "***REDACTED***"); + redactedLine = redactedLine.replace(/\bBearer\s+[a-z0-9._~+/-]+=*/gi, "******"); + const match = MODEL_ENDPOINT_MISMATCH_PATTERN.exec(redactedLine); + if (!match) continue; + // Keep the actual signature even when a long log prefix precedes it. + const start = Math.max(0, match.index - 200); + const detail = redactedLine.slice(start, start + 1000).trim(); + const message = redactedLine.replace(/\\"/g, '"'); + const model = /\bmodel(?:[_ -]name)?["'`]?\s*(?:[:=]\s*|\s+)["'`]?([a-z0-9][a-z0-9._:/@-]{0,199})/i.exec(message)?.[1]; + const endpoint = + /\bnot accessible via the\s+["'`]?([a-z0-9/][a-z0-9._:/ -]{0,159}?)["'`]?\s+endpoint\b/i.exec(message)?.[1] || + /\bendpoint["'`]?\s*[:=]\s*["'`]?([a-z0-9/][a-z0-9._:/-]{0,159})/i.exec(message)?.[1] || + /\bRouting model\s+["'`][a-z0-9._:/@-]{1,200}["'`]\s+to\s+(\/[a-z0-9._/-]{1,160})\s+is incompatible\b/i.exec(message)?.[1] || + (/\bUnsupported Responses custom tool\b/i.test(message) ? "responses" : undefined); + return { ...(model && !/^(?:is|not|endpoint|request|policy)$/i.test(model) ? { model } : {}), ...(endpoint ? { endpoint } : {}), detail }; + } + return null; +} + // Guardrail rejections emitted by the AWF API proxy as HTTP 403 responses. These are // deliberate policy decisions by the proxy, never credential problems: the offending counter // is not reset by a fresh attempt, so retrying against the same proxy is guaranteed to fail @@ -69,6 +106,8 @@ function parseAPIProxyGuardRejection(output) { if (!safeOutput) return null; for (const { guard, pattern, counterRe, counterNames } of API_PROXY_GUARD_REJECTION_PATTERNS) { if (!pattern.test(safeOutput)) continue; + // Endpoint incompatibility has its own diagnostic, even if wrapped as a policy violation. + if (guard === "model_policy_violation" && parseModelEndpointMismatch(safeOutput)) continue; /** @type {Record} */ const counters = {}; const match = counterRe ? counterRe.exec(safeOutput) : null; @@ -165,7 +204,7 @@ function parseAICreditsExceededProxyRejection(output) { /** * Detect retry guard conditions that should stop harness retries immediately. * @param {unknown} output - * @returns {{ aiCreditsExceeded: boolean, awfAPIProxyBlockingRequests: boolean, goalAlreadyActive: boolean, maxRunsExceeded: boolean, apiProxyGuardRejection: { guard: string, counters: Record } | null }} + * @returns {{ aiCreditsExceeded: boolean, awfAPIProxyBlockingRequests: boolean, goalAlreadyActive: boolean, maxRunsExceeded: boolean, modelEndpointMismatch: { model?: string, endpoint?: string, detail: string } | null, apiProxyGuardRejection: { guard: string, counters: Record } | null }} */ function detectNonRetryableHarnessGuard(output) { const safeOutput = typeof output === "string" ? output : ""; @@ -174,6 +213,7 @@ function detectNonRetryableHarnessGuard(output) { awfAPIProxyBlockingRequests: AWF_API_PROXY_BLOCKING_REQUESTS_PATTERNS.some(pattern => pattern.test(safeOutput)), goalAlreadyActive: GOAL_ALREADY_ACTIVE_PATTERNS.some(pattern => pattern.test(safeOutput)), maxRunsExceeded: isMaxRunsExceededError(safeOutput), + modelEndpointMismatch: parseModelEndpointMismatch(safeOutput), apiProxyGuardRejection: parseAPIProxyGuardRejection(safeOutput), }; } @@ -189,6 +229,8 @@ module.exports = { AUTHENTICATION_FAILED_PATTERNS, isMaxRunsExceededError, isAuthenticationFailedError, + MODEL_ENDPOINT_MISMATCH_PATTERN, + parseModelEndpointMismatch, parseAPIProxyGuardRejection, parseAICreditsExceededProxyRejection, }; diff --git a/actions/setup/js/harness_retry_guard.test.cjs b/actions/setup/js/harness_retry_guard.test.cjs index 68f16bced6c..e019ef7944f 100644 --- a/actions/setup/js/harness_retry_guard.test.cjs +++ b/actions/setup/js/harness_retry_guard.test.cjs @@ -5,8 +5,82 @@ import { createRequire } from "node:module"; const require = createRequire(import.meta.url); const { detectNonRetryableHarnessGuard, buildSoftTimeoutGuard, isMaxRunsExceededError, isAuthenticationFailedError, parseAICreditsExceededProxyRejection, parseAPIProxyGuardRejection } = require("./harness_retry_guard.cjs"); +const { parseModelEndpointMismatch, MODEL_ENDPOINT_MISMATCH_PATTERN } = require("./harness_error_patterns.cjs"); describe("harness_retry_guard.cjs", () => { + it.each([ + "400 Cannot translate Copilot request feature: tool_search", + "400 Unsupported Responses custom tool: web_search", + '{"error":{"type":"model_endpoint_incompatible","model":"gpt-5","endpoint":"/responses"}}', + "Model 'gpt-5' is not accessible via the /v1/responses endpoint.", + ])("detects model endpoint mismatch: %s", message => { + const parsed = parseModelEndpointMismatch(`unrelated first line\n${message}\nunrelated last line`); + expect(parsed?.detail).toBe(message); + expect(detectNonRetryableHarnessGuard(message).modelEndpointMismatch).toEqual(parsed); + }); + + it("extracts the model and endpoint from matching text and JSON", () => { + expect(parseModelEndpointMismatch("Model 'gpt-5' is not accessible via the /v1/responses endpoint.")).toEqual({ + model: "gpt-5", + endpoint: "/v1/responses", + detail: "Model 'gpt-5' is not accessible via the /v1/responses endpoint.", + }); + const message = '{"type":"model_endpoint_incompatible","model":"gpt-5","endpoint":"/responses"}'; + expect(parseModelEndpointMismatch(message)).toEqual({ model: "gpt-5", endpoint: "/responses", detail: message }); + expect(parseModelEndpointMismatch("Unsupported Responses custom tool: web_search")?.endpoint).toBe("responses"); + expect(parseModelEndpointMismatch("Model gpt-5 is not accessible via the Chat Completions API endpoint.")?.endpoint).toBe("Chat Completions API"); + expect(parseModelEndpointMismatch("Cannot translate Copilot request feature: tool_search")).toEqual({ detail: "Cannot translate Copilot request feature: tool_search" }); + }); + + it("extracts model and endpoint from an escaped structured provider error", () => { + const message = JSON.stringify({ type: "error", message: JSON.stringify({ type: "model_endpoint_incompatible", model: "gpt-5", endpoint: "/responses" }) }); + expect(parseModelEndpointMismatch(message)).toEqual({ model: "gpt-5", endpoint: "/responses", detail: message }); + expect(parseModelEndpointMismatch("cannot translate copilot request feature: tool_search")).not.toBeNull(); + }); + + it("captures the actual routing model and endpoint", () => { + const detail = 'Routing model "gpt-5.6-luna" to /responses is incompatible'; + expect(parseModelEndpointMismatch(detail)).toEqual({ model: "gpt-5.6-luna", endpoint: "/responses", detail }); + expect(parseModelEndpointMismatch(`model_endpoint_incompatible: ${detail}`)?.endpoint).toBe("/responses"); + }); + + it("redacts credentials and registered masks before bounding matching details", () => { + const token = "ghp_" + "A".repeat(36); + const output = `::add-mask::private-secret-value\nAuthorization: ${"Bearer"} ${"arbitrary-" + "credential"} ${token} private-secret-value Cannot translate Copilot request feature: tool_search`; + const detail = parseModelEndpointMismatch(output)?.detail; + expect(detail).toContain("Cannot translate Copilot request feature"); + expect(detail).not.toContain(token); + expect(detail).not.toContain("arbitrary-credential"); + expect(detail).not.toContain("private-secret-value"); + expect(detail).toContain("***"); + }); + + it("bounds details around the actual mismatch rather than the first log line", () => { + const message = "Cannot translate Copilot request feature"; + const parsed = parseModelEndpointMismatch(`unrelated\n${"x".repeat(2000)} ${message}: ${"y".repeat(2000)}\ntrailing`); + expect(parsed?.detail.length).toBeLessThanOrEqual(1000); + expect(parsed?.detail).toContain(message); + expect(parsed?.detail).not.toContain("unrelated"); + expect(parsed?.detail).not.toContain("trailing"); + }); + + it("does not mask endpoint mismatch with a generic model policy rejection", () => { + const message = '{"type":"model_policy_violation","message":"model_endpoint_incompatible: model gpt-5 is not accessible via the responses endpoint"}'; + expect(detectNonRetryableHarnessGuard(message).modelEndpointMismatch).not.toBeNull(); + expect(parseAPIProxyGuardRejection(message)).toBeNull(); + expect(parseAPIProxyGuardRejection('{"type":"model_policy_violation"}')?.guard).toBe("model_policy_violation"); + }); + + it.each(["400 Bad Request", "400 invalid input", "normal output", "", null, undefined])("does not detect unrelated output: %s", output => { + expect(parseModelEndpointMismatch(output)).toBeNull(); + expect(detectNonRetryableHarnessGuard(output).modelEndpointMismatch).toBeNull(); + }); + + it("does not match empty strings or join endpoint phrases across lines", () => { + expect(MODEL_ENDPOINT_MISMATCH_PATTERN.test("")).toBe(false); + expect(parseModelEndpointMismatch("not accessible via the responses\nendpoint")).toBeNull(); + }); + it.each([ { type: "turn.failed", error: { message: "unexpected status 403 Forbidden: Maximum AI credits exceeded (301 / 300)." } }, { type: "error", message: "unexpected status 403 Forbidden: Maximum AI credits exceeded (301 / 300)." }, diff --git a/actions/setup/js/types/unified_session.d.ts b/actions/setup/js/types/unified_session.d.ts index f0c50449a5e..8ab8fd2d729 100644 --- a/actions/setup/js/types/unified_session.d.ts +++ b/actions/setup/js/types/unified_session.d.ts @@ -135,6 +135,20 @@ export interface ModelRoutingData { requestedEffort?: JsonValue; } +export interface ModelEndpointMismatchData { + category: "model_endpoint_mismatch"; + phase: "startup" | "runtime"; + configured_model: string; + resolved_model: string; + wire_api: string; + wire_api_source: string; + supported_endpoints: string[]; + detail: string; + fix: string; + model?: string; + endpoint?: string; +} + export interface UnifiedModelRoutingData { status?: JsonValue; source?: JsonValue; @@ -416,6 +430,7 @@ export interface UnifiedSessionEventDataMap { "firewall.token_usage": UsageReportData; "firewall.model_routing": ModelRoutingData; "model_routing.outcome": ModelRoutingOutcomeData; + "model_endpoint.mismatch": ModelEndpointMismatchData; "firewall.steering": RuntimeObservationData; "firewall.event": RuntimeObservationData; "safe_output.request": SafeOutputData; diff --git a/actions/setup/js/unified_session.cjs b/actions/setup/js/unified_session.cjs index c98ca057673..3d68a2f7a67 100644 --- a/actions/setup/js/unified_session.cjs +++ b/actions/setup/js/unified_session.cjs @@ -13,6 +13,21 @@ const { normalizeEngineLogEntries, normalizeEngineSessionEvents, parseEngineLog const SESSION_FILE_FORMAT_VERSION = 1; +/** @param {any} data @returns {boolean} */ +function isModelEndpointMismatchData(data) { + return ( + data !== null && + typeof data === "object" && + !Array.isArray(data) && + data.category === "model_endpoint_mismatch" && + ["startup", "runtime"].includes(data.phase) && + ["configured_model", "resolved_model", "wire_api", "wire_api_source", "detail", "fix"].every(key => typeof data[key] === "string") && + Array.isArray(data.supported_endpoints) && + data.supported_endpoints.every(endpoint => typeof endpoint === "string") && + ["model", "endpoint"].every(key => !Object.hasOwn(data, key) || typeof data[key] === "string") + ); +} + /** @typedef {import("./types/agent_session").SessionEvent} SessionEvent */ /** @typedef {{component: string, phase: string, path: string, events: SessionEvent[], timestampUnit?: "seconds" | "milliseconds"}} SessionSource */ @@ -454,6 +469,22 @@ function collectUnifiedSession({ rootDir = "/tmp/gh-aw", engine, warn = message // The sanitized conclusion result includes job outcomes as well as structured or inline verdicts. [["usage/detection/detection_result.json", "threat-detection/detection_result.json"], "detection", "detection", "detection.result"], ]; + const mismatchFile = path.join(rootDir, "agent/model-endpoint-mismatch.json"); + if (exists(mismatchFile)) { + try { + const record = JSON.parse(read(mismatchFile)); + if (!isModelEndpointMismatchData(record)) { + report(mismatchFile, "invalid_model_endpoint_mismatch", undefined); + } else { + const keys = ["category", "phase", "configured_model", "resolved_model", "wire_api", "wire_api_source", "supported_endpoints", "detail", "fix", "model", "endpoint"]; + const data = Object.fromEntries(keys.filter(key => Object.hasOwn(record, key)).map(key => [key, record[key]])); + sources.push({ component: "model_endpoint", phase: record.phase, path: "agent/model-endpoint-mismatch.json", events: [{ type: "model_endpoint.mismatch", data }] }); + } + } catch (error) { + if (!(error instanceof SyntaxError)) throw error; + report(mismatchFile, "malformed_json", undefined); + } + } for (const [candidates, component, phase, type] of observations) { const file = choose(candidates); if (type === "model_routing.outcome" && file) { @@ -464,6 +495,7 @@ function collectUnifiedSession({ rootDir = "/tmp/gh-aw", engine, warn = message report(file, "non_object_record", undefined); return []; } + return [/** @type {SessionEvent} */ { type, data: record, ...(record.timestamp !== undefined ? { timestamp: record.timestamp } : {}) }]; }); sources.push({ component, phase, path: path.relative(rootDir, file), events }); @@ -582,4 +614,4 @@ if (require.main === module) { }); } -module.exports = { SESSION_FILE_FORMAT_VERSION, sessionTimestamp, mergeSessionSources, normalizeRuntimeEvent, parseEngineSession, collectUnifiedSession, writeUnifiedSession, main }; +module.exports = { SESSION_FILE_FORMAT_VERSION, sessionTimestamp, mergeSessionSources, normalizeRuntimeEvent, parseEngineSession, collectUnifiedSession, isModelEndpointMismatchData, writeUnifiedSession, main }; diff --git a/actions/setup/js/unified_session.test.cjs b/actions/setup/js/unified_session.test.cjs index 226ba8f181b..4397455c182 100644 --- a/actions/setup/js/unified_session.test.cjs +++ b/actions/setup/js/unified_session.test.cjs @@ -38,6 +38,35 @@ describe("Unified conclusion session", () => { return target; } + it.each(["startup", "runtime"])("collects a single model/endpoint mismatch record in the %s phase", phase => { + const data = { + category: "model_endpoint_mismatch", + phase, + configured_model: "model-alias", + resolved_model: "model-resolved", + wire_api: "responses", + wire_api_source: "engine", + supported_endpoints: ["/chat/completions"], + detail: "The model does not support the responses API", + fix: "Use a chat/completions-compatible engine", + ...(phase === "runtime" ? { model: "provider-model", endpoint: "/responses" } : {}), + }; + write("agent/model-endpoint-mismatch.json", { ...data, private: "omitted" }); + const events = writeUnifiedSession({ rootDir: root }); + expect(events.filter(event => event.type === "model_endpoint.mismatch")).toEqual([{ type: "model_endpoint.mismatch", data, provenance: { component: "model_endpoint", phase, path: "agent/model-endpoint-mismatch.json", index: 0 } }]); + expect(writeUnifiedSession({ rootDir: root })).toEqual(events); + expect(events.at(-1).data.sources).toContainEqual({ component: "model_endpoint", phase, path: "agent/model-endpoint-mismatch.json", events: 1 }); + }); + + it.each(["{broken", "[]", "null", '{"category":"model_endpoint_mismatch","phase":"other"}'])("warns rather than collecting an invalid mismatch record: %s", record => { + write("agent/model-endpoint-mismatch.json", record); + const warn = vi.fn(); + const { events } = collectUnifiedSession({ rootDir: root, warn }); + expect(events.some(event => event.type === "model_endpoint.mismatch")).toBe(false); + expect(warn).toHaveBeenCalled(); + expect(events.some(event => event.type === "session.collection_warning" && event.data.path === "agent/model-endpoint-mismatch.json")).toBe(true); + }); + it.each([ { engine: "copilot", metadata: undefined, restricted: false }, { engine: "custom", metadata: undefined, restricted: false }, diff --git a/actions/setup/js/unified_session_render.cjs b/actions/setup/js/unified_session_render.cjs index 764d8dad83a..5974e62ff15 100644 --- a/actions/setup/js/unified_session_render.cjs +++ b/actions/setup/js/unified_session_render.cjs @@ -28,6 +28,7 @@ const RUNTIME_TYPES = new Set([ "firewall.token_usage", "firewall.model_routing", "model_routing.outcome", + "model_endpoint.mismatch", "firewall.steering", "firewall.event", "safe_output.request", @@ -148,6 +149,8 @@ function eventDetail(event) { return fields(data, ["stage", "routed", "outcome", "selectedModel", "selectedEffort", "router"]); case "model_routing.outcome": return fields(data, ["status", "wireModel", "effectiveEndpoint", "selectedEndpoint", "effort", "appliedEffort", "failureCode"]); + case "model_endpoint.mismatch": + return `${fields(data, ["category", "phase", "configured_model", "resolved_model", "wire_api", "wire_api_source", "supported_endpoints", "model", "endpoint"])} cause=${inline(data.detail)} fix=${inline(data.fix)}`; case "mcp.event": return fields(data, ["event", "serverName", "level", "status"]); case "firewall.event": diff --git a/actions/setup/js/unified_session_render.test.cjs b/actions/setup/js/unified_session_render.test.cjs index a33c290f560..795638850fa 100644 --- a/actions/setup/js/unified_session_render.test.cjs +++ b/actions/setup/js/unified_session_render.test.cjs @@ -70,6 +70,77 @@ describe("unified session publication views", () => { fs.rmSync(directory, { recursive: true, force: true }); }); + it("renders model/endpoint mismatch cause and fix in both publication views", () => { + const events = [ + header, + event( + "model_endpoint.mismatch", + { + category: "model_endpoint_mismatch", + phase: "runtime", + configured_model: "alias", + resolved_model: "resolved", + wire_api: "responses", + wire_api_source: "engine", + supported_endpoints: ["/chat/completions"], + model: "provider-model", + endpoint: "/responses", + detail: "Unsupported API", + fix: "Select a compatible model", + }, + "model_endpoint", + 0, + undefined, + "agent/model-endpoint-mismatch.json" + ), + ]; + for (const summary of [generatePlainTextSummary(events), generateCopilotCliStyleSummary(events)]) { + expect(summary).toContain("model_endpoint.mismatch"); + expect(summary).toContain("cause=Unsupported API"); + expect(summary).toContain("fix=Select a compatible model"); + expect(summary).toContain("wire_api_source=engine"); + expect(summary).toContain("/chat/completions"); + expect(summary).toContain("model=provider-model"); + expect(summary).toContain("endpoint=/responses"); + } + }); + + it("escapes and redacts hostile mismatch model, endpoint, and detail values", () => { + process.env.GH_AW_SECRET_NAMES = "MISMATCH_TEST"; + process.env.SECRET_MISMATCH_TEST = "mismatch-secret-fixture"; + const hostile = "````\n# heading\n\n::error::oops mismatch-secret-fixture"; + const events = [ + header, + event( + "model_endpoint.mismatch", + { + category: "model_endpoint_mismatch", + phase: "runtime", + configured_model: hostile, + resolved_model: hostile, + wire_api: hostile, + wire_api_source: hostile, + supported_endpoints: [hostile], + model: hostile, + endpoint: hostile, + detail: hostile, + fix: hostile, + }, + "model_endpoint", + 0, + undefined, + "agent/model-endpoint-mismatch.json" + ), + ]; + const markdown = generateCopilotCliStyleSummary(events); + const plain = generatePlainTextSummary(events); + for (const summary of [markdown, plain]) expect(summary).not.toContain("mismatch-secret-fixture"); + expect(markdown).not.toContain(" { const events = [ header, diff --git a/actions/setup/md/agent_failure_comment.md b/actions/setup/md/agent_failure_comment.md index 982c9d60407..853141c2300 100644 --- a/actions/setup/md/agent_failure_comment.md +++ b/actions/setup/md/agent_failure_comment.md @@ -1,3 +1,3 @@ Agent job [{run_id}]({run_url}) failed. -{secret_verification_context}{copilot_org_billing_error_context}{copilot_agent_not_found_context}{credential_auth_error_context}{inference_access_error_context}{mcp_policy_error_context}{model_not_supported_error_context}{http_400_response_error_context}{ai_credits_rate_limit_error_context}{unknown_model_ai_credits_context}{missing_model_pricing_context}{shell_expansion_guard_rejected_context}{app_token_minting_failed_context}{lockdown_check_failed_context}{oauth_token_check_failed_context}{stale_lock_file_failed_context}{daily_ai_credits_exceeded_context}{daily_ai_credits_guardrail_error_context}{assignment_errors_context}{assign_copilot_failure_context}{skill_install_failure_context}{create_discussion_errors_context}{code_push_failure_context}{repo_memory_validation_context}{push_repo_memory_failure_context}{missing_data_context}{missing_tool_context}{permission_denied_context}{tool_denials_exceeded_context}{report_incomplete_context}{failure_diagnostics_context}{missing_safe_outputs_context}{engine_failure_context}{timeout_context}{fork_context} +{secret_verification_context}{copilot_org_billing_error_context}{copilot_agent_not_found_context}{credential_auth_error_context}{inference_access_error_context}{mcp_policy_error_context}{model_not_supported_error_context}{model_endpoint_mismatch_context}{http_400_response_error_context}{ai_credits_rate_limit_error_context}{unknown_model_ai_credits_context}{missing_model_pricing_context}{shell_expansion_guard_rejected_context}{app_token_minting_failed_context}{lockdown_check_failed_context}{oauth_token_check_failed_context}{stale_lock_file_failed_context}{daily_ai_credits_exceeded_context}{daily_ai_credits_guardrail_error_context}{assignment_errors_context}{assign_copilot_failure_context}{skill_install_failure_context}{create_discussion_errors_context}{code_push_failure_context}{repo_memory_validation_context}{push_repo_memory_failure_context}{missing_data_context}{missing_tool_context}{permission_denied_context}{tool_denials_exceeded_context}{report_incomplete_context}{failure_diagnostics_context}{missing_safe_outputs_context}{engine_failure_context}{timeout_context}{fork_context} diff --git a/actions/setup/md/agent_failure_issue.md b/actions/setup/md/agent_failure_issue.md index 4c13ad61d44..5b2d677d979 100644 --- a/actions/setup/md/agent_failure_issue.md +++ b/actions/setup/md/agent_failure_issue.md @@ -4,7 +4,7 @@ **Branch:** {branch} **Run:** {run_url}{pull_request_info} -{secret_verification_context}{copilot_org_billing_error_context}{copilot_agent_not_found_context}{credential_auth_error_context}{inference_access_error_context}{mcp_policy_error_context}{model_not_supported_error_context}{http_400_response_error_context}{ai_credits_rate_limit_error_context}{unknown_model_ai_credits_context}{missing_model_pricing_context}{shell_expansion_guard_rejected_context}{app_token_minting_failed_context}{lockdown_check_failed_context}{oauth_token_check_failed_context}{stale_lock_file_failed_context}{daily_ai_credits_exceeded_context}{daily_ai_credits_guardrail_error_context}{assignment_errors_context}{assign_copilot_failure_context}{skill_install_failure_context}{create_discussion_errors_context}{code_push_failure_context}{repo_memory_validation_context}{push_repo_memory_failure_context}{missing_data_context}{missing_tool_context}{permission_denied_context}{tool_denials_exceeded_context}{report_incomplete_context}{failure_diagnostics_context}{missing_safe_outputs_context}{engine_failure_context}{timeout_context}{fork_context} +{secret_verification_context}{copilot_org_billing_error_context}{copilot_agent_not_found_context}{credential_auth_error_context}{inference_access_error_context}{mcp_policy_error_context}{model_not_supported_error_context}{model_endpoint_mismatch_context}{http_400_response_error_context}{ai_credits_rate_limit_error_context}{unknown_model_ai_credits_context}{missing_model_pricing_context}{shell_expansion_guard_rejected_context}{app_token_minting_failed_context}{lockdown_check_failed_context}{oauth_token_check_failed_context}{stale_lock_file_failed_context}{daily_ai_credits_exceeded_context}{daily_ai_credits_guardrail_error_context}{assignment_errors_context}{assign_copilot_failure_context}{skill_install_failure_context}{create_discussion_errors_context}{code_push_failure_context}{repo_memory_validation_context}{push_repo_memory_failure_context}{missing_data_context}{missing_tool_context}{permission_denied_context}{tool_denials_exceeded_context}{report_incomplete_context}{failure_diagnostics_context}{missing_safe_outputs_context}{engine_failure_context}{timeout_context}{fork_context} ### Action Required diff --git a/docs/public/schemas/unified-session.schema.json b/docs/public/schemas/unified-session.schema.json index 5aab3b83b29..1a96e7db4a7 100644 --- a/docs/public/schemas/unified-session.schema.json +++ b/docs/public/schemas/unified-session.schema.json @@ -88,6 +88,7 @@ { "if": { "properties": { "type": { "const": "mcp.rpc.request" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/McpObservationData" } } } }, { "if": { "properties": { "type": { "const": "mcp.rpc.response" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/McpObservationData" } } } }, { "if": { "properties": { "type": { "const": "mcp.tool_call" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/McpObservationData" } } } }, + { "if": { "properties": { "type": { "const": "model_endpoint.mismatch" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/ModelEndpointMismatchData" } } } }, { "if": { "properties": { "type": { "const": "model_routing.outcome" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/ModelRoutingOutcomeData" } } } }, { "if": { "properties": { "type": { "const": "prompt.system" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/Pick%3CMessageData%2C%22content%22%3E" } } } }, { "if": { "properties": { "type": { "const": "prompt.user" } }, "required": ["type"] }, "then": { "properties": { "data": { "$ref": "#/definitions/Pick%3CMessageData%2C%22content%22%3E" } } } }, @@ -584,6 +585,24 @@ }, "additionalProperties": false }, + "ModelEndpointMismatchData": { + "type": "object", + "properties": { + "category": { "type": "string", "const": "model_endpoint_mismatch" }, + "phase": { "type": "string", "enum": ["startup", "runtime"] }, + "configured_model": { "type": "string" }, + "resolved_model": { "type": "string" }, + "wire_api": { "type": "string" }, + "wire_api_source": { "type": "string" }, + "supported_endpoints": { "type": "array", "items": { "type": "string" } }, + "detail": { "type": "string" }, + "fix": { "type": "string" }, + "model": { "type": "string" }, + "endpoint": { "type": "string" } + }, + "required": ["category", "phase", "configured_model", "resolved_model", "wire_api", "wire_api_source", "supported_endpoints", "detail", "fix"], + "additionalProperties": false + }, "ModelRoutingData": { "type": "object", "properties": { diff --git a/docs/src/content/docs/reference/frontmatter-full.md b/docs/src/content/docs/reference/frontmatter-full.md index df466e0a5a7..3b872199362 100644 --- a/docs/src/content/docs/reference/frontmatter-full.md +++ b/docs/src/content/docs/reference/frontmatter-full.md @@ -22602,6 +22602,7 @@ safe-outputs: # categories must match included AND not match excluded. Common categories: # agent_failure, timed_out, transport_wedge, missing_safe_outputs, # report_incomplete, missing_tool, missing_data, inference_access_error, + # model_endpoint_mismatch, # mcp_policy_error, ai_credits_rate_limit_error, max_ai_credits_exceeded, # daily_ai_credits_unknown. report-failure-as-issue: [] diff --git a/docs/src/content/docs/reference/safe-outputs.md b/docs/src/content/docs/reference/safe-outputs.md index 4add9ac697b..9936931ac48 100644 --- a/docs/src/content/docs/reference/safe-outputs.md +++ b/docs/src/content/docs/reference/safe-outputs.md @@ -1762,6 +1762,7 @@ safe-outputs: | `missing_tool` | Required functionality is not available | | `missing_data` | Required data is not accessible | | `inference_access_error` | AI inference endpoint authentication or access failures | +| `model_endpoint_mismatch` | The configured model does not support the selected API endpoint | | `copilot_org_billing_error` | Copilot authorization failed because organization billing for Copilot CLI is unavailable | | `mcp_policy_error` | MCP server policy violations | | `ai_credits_rate_limit_error` | AI credits rate limit exceeded | diff --git a/docs/src/content/docs/specs/unified-agent-session-specification.md b/docs/src/content/docs/specs/unified-agent-session-specification.md index 87d0bb67cc9..f129b0960cc 100644 --- a/docs/src/content/docs/specs/unified-agent-session-specification.md +++ b/docs/src/content/docs/specs/unified-agent-session-specification.md @@ -592,6 +592,7 @@ source for opaque fields. | `eval.result` | Evals JSONL observations, preserving answers, IDs, and observed timestamps. | | `usage.report`, `execution.result`, `detection.result`, `workflow.info` | Existing accounting, execution evidence, detection verdicts, and run metadata. `workflow.info` retains available `cliVersion` (gh-aw), `awfVersion`, `mcpgVersion`, `engineId`, `agentVersion`, observed `model`, `requestedModel`, compact `modelRouting`, and `triggerType` from `aw_info.json`. `requestedModel` prefers `requested_model` and falls back to `model` for earlier metadata. Unavailable values are not inferred. | | `model_routing.outcome` | The harness's observed routing status, wire model, effective endpoint, selected endpoint, effort, applied effort, and failure code from `agent/awf-routing-outcome.json`; free-form detail is excluded. | +| `model_endpoint.mismatch` | A single harness JSON record from `agent/model-endpoint-mismatch.json`, with the model/API mismatch cause and corrective action. | | `guardrail.daily_aic` | Activation's daily AI Credits decision (`status`, `exceeded`, and available numeric `total`, `estimated`, `threshold`). Omitted when the guardrail has no decision; an existing event is not duplicated. | | `github_api.rate_limit` | Available GitHub API rate-limit JSONL observations retain the recorded source (`response_headers`, `rate_limit_api`, or `retry`), operation, resource, limit, remaining, used, reset, and retry state. `credentialSource` identifies a known GitHub Actions token, PAT, or app token where classified by the client; absent or unknown credential types are not inferred from quota values. Raw credentials and unrecognized fields are excluded. The collector prefers `github_rate_limits.jsonl` over its `usage/` copy to avoid duplicate observations. | | `session.collection_warning`, `session.collection` | Explicit collection diagnostics and coverage. | @@ -646,6 +647,30 @@ provider, labels, mode, classifier attempts, degraded-classification state, selected ID/provider/model/effort, wire model, endpoint, router, latency, code, request ID, routed outcome, deviations, requested model, and requested effort. +#### Model/endpoint mismatch + +The collector MUST map the single JSON object in +`agent/model-endpoint-mismatch.json` to `model_endpoint.mismatch`, with provenance +component `model_endpoint`, source path `agent/model-endpoint-mismatch.json`, and +phase equal to the record's `startup` or `runtime` phase. Arrays, malformed JSON, +and records that violate the following contract MUST produce a collection +warning rather than a mismatch event. + +The payload has required fields `category: "model_endpoint_mismatch"`, +`phase: "startup" | "runtime"`, and strings `configured_model`, `resolved_model`, +`wire_api`, `wire_api_source`, `detail`, and `fix`. `supported_endpoints` is a +required array of strings. `model` and `endpoint` are optional strings describing +runtime observations. Unknown source fields are excluded; unavailable optional +fields MUST NOT be inferred. + +Default summaries MUST render the cause (`detail`) and corrective action (`fix`), +alongside the configured and resolved model, wire API and its source, and +supported endpoints. Failure reports MUST derive this context only from the +unified session, without rescanning raw agent or firewall logs or reading the +source JSON separately. Reports MUST use the `model_endpoint_mismatch` grouping +category and the `model_endpoint_mismatch_context` template placeholder, and +redact and bound diagnostic text before publication. + ### 4.8 `agent.execution` **T-UAS-067 — Unique execution diagnostics.** When an agent artifact contains an @@ -711,7 +736,7 @@ codes/types without requiring a closed enumeration. | Origin | Observed categories | | --- | --- | -| Compiler error-detection outputs | `inference_access_error`, `mcp_policy_error`, `agentic_engine_timeout`, `model_not_supported_error`, `http_400_response_error`, `capi_quota_exceeded_error`, `invocation_cap_exceeded`, `max_cache_misses_exceeded`, `missing_model_pricing_error`, `shell_expansion_guard_rejected` | +| Compiler error-detection outputs | `inference_access_error`, `mcp_policy_error`, `agentic_engine_timeout`, `model_not_supported_error`, `model_endpoint_mismatch_error`, `http_400_response_error`, `capi_quota_exceeded_error`, `invocation_cap_exceeded`, `max_cache_misses_exceeded`, `missing_model_pricing_error`, `shell_expansion_guard_rejected` | | Harness retry and proxy guards | `capi_server_error`, `authentication_failed`, `max_ai_credits_exceeded`, `effective_tokens_limit_exceeded`, `permission_denied_limit_exceeded`, `model_policy_violation`, `awf_api_proxy_blocking_requests`, `goal_already_active` | | Harness failure reasons and fatal signals | Observed `failure_reason` identifiers such as `harness_retry_path_invalid`, `cancelled_or_timed_out`, and `sandbox_runtime_crash`; crash exit codes preserve the corresponding native signal name. | diff --git a/pkg/cli/audit_report.go b/pkg/cli/audit_report.go index 9f450391981..56d468b2392 100644 --- a/pkg/cli/audit_report.go +++ b/pkg/cli/audit_report.go @@ -57,6 +57,7 @@ type AuditData struct { GatewaySteeringEvents []GatewaySteeringEvent `json:"gateway_steering_events,omitempty"` FirewallTokenUsage *TokenUsageSummary `json:"firewall_token_usage,omitempty"` ModelRouting *ModelRoutingSummary `json:"model_routing,omitempty"` + ModelEndpointMismatches []ModelEndpointMismatch `json:"model_endpoint_mismatches,omitempty"` GitHubRateLimitUsage *GitHubRateLimitUsage `json:"github_rate_limit_usage,omitempty"` FirewallAnalysis *FirewallAnalysis `json:"firewall_analysis,omitempty"` PolicyAnalysis *PolicyAnalysis `json:"policy_analysis,omitempty"` @@ -347,6 +348,7 @@ func buildLocalAuditData(processedRun ProcessedRun, metrics LogMetrics, mcpToolU observabilityInsights: observabilityInsights, }) auditData.ModelRouting = applyAwInfoModelRouting(processedRun.ModelRouting, processedRun.Run.LogsPath) + auditData.ModelEndpointMismatches = readSessionModelEndpointMismatches(processedRun.Run.LogsPath) return auditData, createdItems } diff --git a/pkg/cli/audit_report_render.go b/pkg/cli/audit_report_render.go index b8eb9656874..886929806c4 100644 --- a/pkg/cli/audit_report_render.go +++ b/pkg/cli/audit_report_render.go @@ -46,6 +46,7 @@ func renderConsole(data AuditData, logsPath string) { renderConsoleSession(data.SessionAnalysis) renderConsoleTokenUsage(data.FirewallTokenUsage) renderConsoleModelRouting(data.ModelRouting) + renderConsoleModelEndpointMismatches(data.ModelEndpointMismatches) renderConsoleGitHubAPIUsage(data.GitHubRateLimitUsage) renderConsoleJobs(data.Jobs) renderConsolePrompt(data.PromptAnalysis) @@ -55,6 +56,19 @@ func renderConsole(data AuditData, logsPath string) { renderConsoleLogsPath(logsPath) } +func renderConsoleModelEndpointMismatches(mismatches []ModelEndpointMismatch) { + for _, mismatch := range mismatches { + fmt.Fprintf(os.Stderr, " model_endpoint_mismatch: phase=%s configured_model=%s resolved_model=%s wire_api=%s wire_api_source=%s supported_endpoints=%s\n", + safeModelRoutingText(mismatch.Phase), safeModelRoutingText(mismatch.ConfiguredModel), + safeModelRoutingText(mismatch.ResolvedModel), safeModelRoutingText(mismatch.WireAPI), + safeModelRoutingText(mismatch.WireAPISource), safeModelRoutingText(strings.Join(mismatch.SupportedEndpoints, ", "))) + if mismatch.Model != "" || mismatch.Endpoint != "" { + fmt.Fprintf(os.Stderr, " model=%s endpoint=%s\n", safeModelRoutingText(mismatch.Model), safeModelRoutingText(mismatch.Endpoint)) + } + fmt.Fprintf(os.Stderr, " detail: %s\n fix: %s\n", safeModelRoutingText(mismatch.Detail), safeModelRoutingText(mismatch.Fix)) + } +} + func renderConsoleOverview(data AuditData) { fmt.Fprintf(os.Stderr, "%s %s | %s | %s | %s\n", renderConsoleStatusIcon(data.Overview.Conclusion), diff --git a/pkg/cli/model_endpoint_mismatch_test.go b/pkg/cli/model_endpoint_mismatch_test.go new file mode 100644 index 00000000000..f23ef0433a4 --- /dev/null +++ b/pkg/cli/model_endpoint_mismatch_test.go @@ -0,0 +1,192 @@ +//go:build !integration + +package cli + +import ( + "encoding/json" + "os" + "path/filepath" + "strings" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +const modelEndpointMismatchTestData = `{"category":"model_endpoint_mismatch","phase":"startup","configured_model":"configured-alias","resolved_model":"resolved-model","wire_api":"responses","wire_api_source":"engine-default","supported_endpoints":["/chat/completions","/v1/messages"],"detail":"The model does not support /responses.","fix":"Set wire_api to chat or select a compatible model."}` + +func modelEndpointMismatchTestEvent(data string) string { + phase := "startup" + if strings.Contains(data, `"phase":"runtime"`) { + phase = "runtime" + } + return `{"type":"model_endpoint.mismatch","data":` + data + `,"provenance":{"component":"model_endpoint","phase":"` + phase + `","path":"agent/model-endpoint-mismatch.json"}}` + "\n" +} + +func TestModelEndpointMismatchAuditFromUnifiedSession(t *testing.T) { + for _, relative := range []string{"usage/aw_session.jsonl", "aw_session.jsonl"} { + t.Run(relative, func(t *testing.T) { + runDir := t.TempDir() + sessionPath := filepath.Join(runDir, relative) + require.NoError(t, os.MkdirAll(filepath.Dir(sessionPath), 0o700)) + runtimeData := strings.Replace(modelEndpointMismatchTestData, `"phase":"startup"`, `"phase":"runtime"`, 1) + runtimeData = strings.TrimSuffix(runtimeData, "}") + `,"model":"request-model","endpoint":"/responses"}` + require.NoError(t, os.WriteFile(sessionPath, []byte( + modelEndpointMismatchTestEvent(modelEndpointMismatchTestData)+modelEndpointMismatchTestEvent(runtimeData)), 0o600)) + + data, _ := buildLocalAuditData(ProcessedRun{Run: WorkflowRun{LogsPath: runDir}}, LogMetrics{}, nil) + require.Len(t, data.ModelEndpointMismatches, 2) + assert.Equal(t, "startup", data.ModelEndpointMismatches[0].Phase) + assert.Equal(t, "runtime", data.ModelEndpointMismatches[1].Phase) + assert.Equal(t, "request-model", data.ModelEndpointMismatches[1].Model) + assert.Equal(t, "/responses", data.ModelEndpointMismatches[1].Endpoint) + var expected ModelEndpointMismatch + require.NoError(t, json.Unmarshal([]byte(modelEndpointMismatchTestData), &expected)) + assert.Equal(t, expected, data.ModelEndpointMismatches[0]) + + encoded, err := json.Marshal(data) + require.NoError(t, err) + var report map[string]json.RawMessage + require.NoError(t, json.Unmarshal(encoded, &report)) + var diagnostics []ModelEndpointMismatch + require.NoError(t, json.Unmarshal(report["model_endpoint_mismatches"], &diagnostics)) + assert.Equal(t, data.ModelEndpointMismatches, diagnostics) + + output := captureStderrForGuardPolicyReportTest(func() { renderConsole(data, runDir) }) + for _, text := range []string{ + "model_endpoint_mismatch: phase=startup", "phase=runtime", + "configured_model=configured-alias", "resolved_model=resolved-model", + "wire_api=responses", "wire_api_source=engine-default", + "supported_endpoints=/chat/completions, /v1/messages", + "model=request-model endpoint=/responses", "detail: " + expected.Detail, "fix: " + expected.Fix, + } { + assert.Contains(t, output, text) + } + }) + } +} + +func TestModelEndpointMismatchDoesNotInferCauseFromRawArtifacts(t *testing.T) { + for _, session := range []struct { + name string + content string + }{ + {"missing", ""}, + {"unrelated", `{"type":"model_routing.outcome","data":{"status":"rejected","failureCode":"unsupported_endpoint"},"provenance":{"component":"agent","phase":"agent"}}`}, + {"corrupt", modelEndpointMismatchTestEvent(modelEndpointMismatchTestData) + "invalid\n"}, + } { + t.Run(session.name, func(t *testing.T) { + runDir := t.TempDir() + require.NoError(t, os.MkdirAll(filepath.Join(runDir, "agent"), 0o700)) + for _, file := range []string{"model-endpoint-mismatch.json", "awf-routing-outcome.json", "agent-stdio.log"} { + require.NoError(t, os.WriteFile(filepath.Join(runDir, "agent", file), []byte(modelEndpointMismatchTestData), 0o600)) + } + if session.content != "" { + require.NoError(t, os.WriteFile(filepath.Join(runDir, "aw_session.jsonl"), []byte(session.content), 0o600)) + } + data, _ := buildLocalAuditData(ProcessedRun{Run: WorkflowRun{LogsPath: runDir}}, LogMetrics{}, nil) + assert.Empty(t, data.ModelEndpointMismatches) + encoded, err := json.Marshal(data) + require.NoError(t, err) + assert.NotContains(t, string(encoded), `"model_endpoint_mismatches"`) + }) + } +} + +func TestModelEndpointMismatchSessionValidation(t *testing.T) { + for _, data := range []string{ + `{"category":"other","phase":"startup"}`, + `{"category":"model_endpoint_mismatch","phase":"other"}`, + `{"category":"model_endpoint_mismatch","phase":"runtime","supported_endpoints":42}`, + `null`, + strings.Replace(modelEndpointMismatchTestData, `"configured_model":"configured-alias",`, "", 1), + strings.Replace(modelEndpointMismatchTestData, `"fix":"Set wire_api to chat or select a compatible model."`, `"fix":null`, 1), + strings.Replace(modelEndpointMismatchTestData, `["/chat/completions","/v1/messages"]`, `null`, 1), + strings.Replace(modelEndpointMismatchTestData, `["/chat/completions","/v1/messages"]`, `[null]`, 1), + strings.TrimSuffix(modelEndpointMismatchTestData, "}") + `,"model":null}`, + } { + attribution := &sessionModelRoutingAttribution{} + err := decodeSessionModelRoutingEvent([]byte(modelEndpointMismatchTestEvent(data)), 7, attribution) + require.NoError(t, err) + assert.Empty(t, attribution.Mismatches) + } +} + +func TestModelEndpointMismatchIgnoresForgedEventsAndKeepsValidDiagnostics(t *testing.T) { + for _, replacement := range []struct{ from, to string }{ + {`"component":"model_endpoint"`, `"component":"agent"`}, + {`"path":"agent/model-endpoint-mismatch.json"`, `"path":"agent/forged.json"`}, + {`"phase":"startup","path"`, `"phase":"runtime","path"`}, + {`"configured_model":"configured-alias",`, ""}, + } { + runDir := t.TempDir() + valid := modelEndpointMismatchTestEvent(modelEndpointMismatchTestData) + forged := strings.Replace(valid, replacement.from, replacement.to, 1) + require.NoError(t, os.WriteFile(filepath.Join(runDir, "aw_session.jsonl"), []byte(forged+valid+forged), 0o600)) + mismatches := readSessionModelEndpointMismatches(runDir) + require.Len(t, mismatches, 1) + assert.Equal(t, "configured-alias", mismatches[0].ConfiguredModel) + } +} + +func TestModelEndpointMismatchUsageSessionTakesPrecedence(t *testing.T) { + runDir := t.TempDir() + require.NoError(t, os.MkdirAll(filepath.Join(runDir, "usage"), 0o700)) + require.NoError(t, os.WriteFile(filepath.Join(runDir, "usage", "aw_session.jsonl"), []byte("{}\n"), 0o600)) + require.NoError(t, os.WriteFile(filepath.Join(runDir, "aw_session.jsonl"), []byte(modelEndpointMismatchTestEvent(modelEndpointMismatchTestData)), 0o600)) + assert.Empty(t, readSessionModelEndpointMismatches(runDir)) +} + +func TestModelEndpointMismatchRejectsSymlinkSession(t *testing.T) { + for _, target := range []string{"usage", "usage/aw_session.jsonl"} { + t.Run(target, func(t *testing.T) { + root := t.TempDir() + runDir := filepath.Join(root, "run") + source := filepath.Join(root, "source") + require.NoError(t, os.MkdirAll(source, 0o700)) + require.NoError(t, os.MkdirAll(runDir, 0o700)) + require.NoError(t, os.WriteFile(filepath.Join(source, "aw_session.jsonl"), []byte(modelEndpointMismatchTestEvent(modelEndpointMismatchTestData)), 0o600)) + if target == "usage" { + require.NoError(t, os.Symlink(source, filepath.Join(runDir, target))) + } else { + require.NoError(t, os.MkdirAll(filepath.Join(runDir, "usage"), 0o700)) + require.NoError(t, os.Symlink(filepath.Join(source, "aw_session.jsonl"), filepath.Join(runDir, target))) + } + assert.Empty(t, readSessionModelEndpointMismatches(runDir)) + }) + } +} + +func TestModelEndpointMismatchConsoleEscapesControlCharacters(t *testing.T) { + mismatch := ModelEndpointMismatch{ + Phase: "startup", ConfiguredModel: "alias\nforged", ResolvedModel: "model\x1b", + SupportedEndpoints: []string{"/responses\rforged"}, Detail: "detail\nforged", Fix: "fix\tvalue", + Model: "request\nforged", Endpoint: "/responses\x1b", + } + output := captureStderrForGuardPolicyReportTest(func() { renderConsoleModelEndpointMismatches([]ModelEndpointMismatch{mismatch}) }) + assert.NotContains(t, output, "\x1b") + assert.NotContains(t, output, "\r") + assert.NotContains(t, output, "\t") + assert.NotContains(t, output, "\nforged") + assert.Contains(t, output, "fix: fix value") +} + +func TestModelEndpointMismatchJSONEscapingAndRedactionPreserved(t *testing.T) { + runDir := t.TempDir() + var mismatch ModelEndpointMismatch + require.NoError(t, json.Unmarshal([]byte(modelEndpointMismatchTestData), &mismatch)) + mismatch.Detail = "[REDACTED]\n