Process completed with exit code 1.

AssertionError: expected 500 to be 200 // Object.is equality - Expected + Received - 200 + 500 ❯ packages/codingcode/test/server/settings-routes.test.ts:218:24

AssertionError: expected 500 to be 200 // Object.is equality - Expected + Received - 200 + 500 ❯ packages/codingcode/test/server/settings-routes.test.ts:191:24

AssertionError: expected 'You are a coding assistant — an AI ag…' to contain 'User-defined Rules' - Expected + Received - User-defined Rules + You are a coding assistant — an AI agent that helps users with software engineering tasks. + + ## How you work + - Your text output is displayed to the user as formatted text. Tool calls and their results are shown separately — the user can see what tools you used and their outcomes. + - Tools run behind a permission system. If a tool call is denied, the user declined it — adjust your approach, do not retry the same call verbatim. + - Messages may contain <system-reminder> tags injected by the system, not by the user. They contain useful operational information — always read and follow them. + + ## Rules + 1. Read files before modifying them — never guess file contents + 2. Use search_code or search_files to locate code before reading — this is faster than reading entire files blindly + 3. Prefer editing existing files over creating new ones + 4. Make small, focused changes — avoid large rewrites + 5. Run tests or type-check after changes when applicable + 6. If the user's request is ambiguous, ask for clarification + 7. For complex or broad tasks (understanding a whole module, cross-file analysis, comprehensive search): + a. Briefly assess the task scope using your own reasoning — do not use tools for exploration at this stage, as that would consume your limited context window. + b. If you can clearly handle it without extensive file reading or searching, proceed yourself. + c. Otherwise, delegate to dispatch_agent with the original task and your assessment of what needs to be explored. The subagent handles discovery in its own separate context, keeping your main context clean for coordination. + + ## Using your tools + - **Prefer dedicated tools over shell commands.** Use read_file instead of cat, edit_file instead of sed, search_code instead of grep. Dedicated tools give the user better visibility into your work. + - **Call multiple tools in parallel** when they are independent — for example, reading several files at once, or searching with different patterns. Do NOT make sequential calls when the calls don't depend on each other. + - After editing a file, do NOT re-read it to verify — the edit tool already confirms success or reports failure. Only re-read if you suspect the edit did not apply correctly. + - Reserve execute_command for actual system commands and terminal operations (git, npm, build, test). Do not use it for file operations that dedicated tools can handle. + + ## Executing actions with care + Consider the reversibility and blast radius of actions before taking them: + - **Freely take** local, reversible actions: editing files, running tests, reading code. + - **Confirm with the user before** hard-to-reverse or outward-facing actions: pushing code, deleting files/branches, force-pushing, modifying CI/CD pipelines, sending messages to external services. + - **Never** use destructive commands (rm -rf /, sudo, git reset --hard, git push --force, git clean -f) unless explicitly requested and approved by the user. + - When you encounter unexpected state (unfamiliar files, branches, or configuration), investigate before deleting or overwriting — it may be the user's in-progress work. Never revert changes you did not make. + + ## Git operations + - Do NOT commit changes unless the user explicitly asks you to. + - Do NOT push to remote unless the user explicitly asks you to. + - Do NOT use destructive git commands (git reset --hard, git push --force, git clean -f, git checkout -- .) unless explicitly requested and approved. + - If you notice unexpected changes in the working tree that you did not make, investigate before acting — they may be the user's in-progress work. + + ## Professional objectivity + Prioritize technical accuracy over validating the user's beliefs. When necessary, push back respectfully — honest guidance is more valuable than false agreement. + - Do not begin responses with conversational interjections ("Got it

AssertionError: expected [Function] to not throw an error but 'Error: Command failed: pnpm run forma…' was thrown - Expected: undefined + Received: "Error: Command failed: pnpm run format:check [WARN] The \"pnpm\" field in package.json is no longer read by pnpm. The following keys were ignored: \"pnpm.overrides\". See https://pnpm.io/settings for the new home of each setting. $ prettier --check \"packages/**/*.{ts,tsx,json}\" \"*.json\" \"*.ts\" [warn] packages/codingcode/src/agent/agent.ts [warn] packages/codingcode/src/client/direct/settings.ts [warn] packages/codingcode/src/layer.ts [warn] packages/codingcode/src/server/routes/settings.ts [warn] packages/codingcode/src/subagent/registry.ts [warn] packages/codingcode/src/tools/domains/subagent/dispatch.ts [warn] packages/codingcode/src/tools/domains/web/search.ts [warn] packages/codingcode/test/prompts/system-prompt.test.ts [warn] packages/codingcode/test/tools/websearch.test.ts [warn] packages/desktop/src/agent/AutomationForm.tsx [warn] packages/desktop/src/agent/AutomationPanel.tsx [warn] packages/desktop/src/agent/MessageStream.tsx [warn] packages/desktop/src/lib/core-api.ts [warn] packages/desktop/test/assistant-content-by-turn.test.ts [warn] Code style issues found in 14 files. Run Prettier with --write to fix. " ❯ packages/codingcode/test/ci/tooling-scripts.test.ts:48:87

AssertionError: expected "spy" to be called with arguments: [ 'my-skill', false, …(1) ] Received: 1st spy call: [ - "my-skill", - false, { "cwd": "/project/dir", + "enabled": false, + "name": "my-skill", }, ] Number of calls: 1 ❯ packages/desktop/test/core-api.test.ts:219:38

AssertionError: expected "spy" to be called with arguments: [ 'my-skill', true, { cwd: '' } ] Received: 1st spy call: [ - "my-skill", - true, { "cwd": "", + "enabled": true, + "name": "my-skill", }, ] Number of calls: 1 ❯ packages/desktop/test/core-api.test.ts:213:38

Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: actions/checkout@v4, dorny/paths-filter@v3. Actions will be forced to run with Node.js 24 by default starting June 16th, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/

Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: actions/checkout@v4, actions/setup-node@v4, pnpm/action-setup@v3. Actions will be forced to run with Node.js 24 by default starting June 16th, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/

This generator function does not have 'yield'

'code' is defined but never used. Allowed unused args must match /^_/u

This generator function does not have 'yield'

'ESTIMATED_SUMMARY_TOKENS' is assigned a value but never used. Allowed unused vars must match /^_/u

'resolveHookDisabled' is defined but never used. Allowed unused vars must match /^_/u

'resolveMcpDisabled' is defined but never used. Allowed unused vars must match /^_/u

'getLLMClient' is defined but never used. Allowed unused vars must match /^_/u

Unnecessary escape character: \'

'AgentProfile' is defined but never used. Allowed unused vars must match /^_/u

'appendFileSync' is defined but never used. Allowed unused vars must match /^_/u

Node.js 20 actions are deprecated. The following actions are running on Node.js 20 and may not work as expected: actions/checkout@v4, actions/setup-node@v4, pnpm/action-setup@v3. Actions will be forced to run with Node.js 24 by default starting June 16th, 2026. Node.js 20 will be removed from the runner on September 16th, 2026. Please check if updated versions of these actions are available that support Node.js 24. To opt into Node.js 24 now, set the FORCE_JAVASCRIPT_ACTIONS_TO_NODE24=true environment variable on the runner or in your workflow file. Once Node.js 24 becomes the default, you can temporarily opt out by setting ACTIONS_ALLOW_USE_UNSECURE_NODE_VERSION=true. For more information see: https://github.blog/changelog/2025-09-19-deprecation-of-node-20-on-github-actions-runners/