First Deploy - #4
Open
AllenYGY wants to merge 31 commits into
Open
Conversation
feat: Add postorder scheduler
- Fix indentation alignment in debug_bfs.py - Improve ASCII flow diagrams formatting in System_Architecture_Flow.md - Clean up trailing whitespace in output.md - Add todolist.md for task tracking 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- ✅ Created GLMEmbeddingsService with API integration and mock mode - ✅ Extended database schema with task_embeddings table and indexes - ✅ Implemented HybridRetrievalService combining TF-IDF and semantic search - ✅ Modified context.py to use new retrieval system with fallback support - ✅ Integrated automatic embedding generation in executor.py - ✅ Added comprehensive CLI commands for embedding management - ✅ Updated API endpoints to support retrieval_method parameter - ✅ Fixed TF-IDF IDF calculation to prevent negative scores - ✅ Fixed SQL reserved word issue in embeddings queries - ✅ Added parameter passing for tfidf_min_score and tfidf_max_candidates All 65 tests passing. System now supports: - Pure TF-IDF retrieval (legacy compatible) - Pure semantic retrieval using GLM embeddings - Hybrid retrieval with weighted scoring - Automatic embedding generation for completed tasks - Batch embedding generation and statistics via CLI 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
…ostorder traversal
- Add task rerun with single task and subtree modes - Add CLI arguments for --rerun-task and --rerun-subtree - Add API endpoints for task rerun operations - Add comprehensive test coverage for rerun functionality - Maintain backward compatibility with existing features - Temporarily disable recursive decomposition features
…lish - Remove temporary and unused files: - agent_cli_new.py, test_cli_refactor.py (temporary test files) - plan.json, plan.md, output.md, todolist.md (temporary output files) - README_cn.md, docs/Future_Plan_cn.md (duplicate Chinese docs) - embeddings_old.py (obsolete implementation) - disabled test files - Translate Chinese comments to English: - app/services/glm_api_client.py: Full translation to English - app/services/embeddings.py: Full translation to English - cli/utils/io_utils.py: User-facing strings in English 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Translate all Chinese comments and docstrings to professional English across 9 core service files - Fix async task cancellation logic bug in async_embedding_manager.py - Ensure all tests pass after translation Files translated: - app/services/similarity_calculator.py - app/services/embedding_batch_processor.py - app/services/cache.py - app/services/retrieval.py - app/main.py - app/executor.py - app/services/structure_prior.py - app/services/planning.py - app/services/graph_attention.py 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Database files should not be version controlled 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Complete code structure optimization and Chinese to English translation: - Remove 15 unused and temporary files (test files, temp outputs, duplicates) - Translate all Chinese comments and docstrings to professional English - Fix async task cancellation logic bug - Add embedding_cache.db to .gitignore - Ensure all 119 tests pass after refactoring Major files translated: - GLM API client, embeddings service, cache, retrieval - Similarity calculator, batch processor, structure prior - Graph attention, planning service, executor, main.py - CLI utilities and all supporting components This significantly improves code maintainability and internationalization. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
## 核心功能 - 替换规则评估为LLM智能评估系统 - 实现多专家角色评估机制(5个专业角色) - 添加对抗性评估系统(生成器vs批评者) - 建立迭代质量优化工作流 ## 技术实现 - 新增LLM评估器与多专家评估器 - 实现对抗性评估的Generator/Critic架构 - 添加评估缓存与监督系统 - 集成CLI命令支持所有评估模式 ## 系统优化 - 重构文档结构，删除冗余文件 - 更新主README突出评估系统 - 完善测试覆盖与端到端论文生成 - 修复测试兼容性问题 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.