Commit Graph

139 Commits

Author SHA1 Message Date
Woody be5e75e67c test(backend): update unit tests for LLM monitoring changes
- Fixed MockLLMClient to accept step_name parameter

- Updated test mocks for OpenAI SDK structure

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 14:52:41 +08:00
Woody f5cfe44183 feat(backend): add LLM monitoring with step names, timing, and prompt logging
- LLMClient.complete() now accepts step_name parameter to identify processing step

- Logs prompt preview (first 100 + last 100 chars) at INFO level

- Logs processing time in milliseconds with token usage stats

- Updated QueryDecomposer, RelevanceFilter, and RAGService to pass step names

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 14:51:57 +08:00
Woody 74cb8b83d5 feat(backend): migrate LLM client to OpenAI SDK with thinking control
- Replace httpx with openai.AsyncOpenAI

- Add llm_enable_thinking config (default False)

- Add _build_extra_body() for Qwen3.5 thinking mode control

- Use chat_template_kwargs for vLLM/SGLang compatibility

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 14:10:26 +08:00
Woody 2f896052a1 docs: add logging anti-patterns to AGENTS.md
- Log to console only (must use backend/app/log/)

- Commit log files to git (must be .gitignored)

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 14:10:09 +08:00
Woody e83a4708b5 feat(backend): add rotating file logging to backend/app/log/
- Configure RotatingFileHandler in main.py (10MB per file, 5 backups)

- Log directory auto-created on startup

- Add backend/app/log/ to .gitignore

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 14:09:48 +08:00
Woody 2b68888838 test: add sample documents for manual testing
- NEC4 ACC.docx, .pdf for upload testing

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:28:13 +08:00
Woody 12f4705b72 docs: update development plans with Phase 1 completion status
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:27:52 +08:00
Woody 351950f512 test(backend): update Phase 1 test suite
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:27:40 +08:00
Woody 4cf930dc59 feat(backend): add dependency injection and update main entry point
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:27:30 +08:00
Woody 44028ebd6e refactor(backend): update document parsers for DOCX and PDF
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:27:08 +08:00
Woody f4d78b0b77 refactor(backend): update query decomposer, relevance filter, and RAG service
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:26:56 +08:00
Woody 38f4c70762 feat(backend): add embedding client and update LLM client
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:26:43 +08:00
Woody 4a22b906e4 refactor(backend): update ingest and query routers
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:26:32 +08:00
Woody 09f8cb7e6d refactor(backend): update Pydantic models for ingestion and query
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:26:20 +08:00
Woody b93fc2e05b chore(backend): update config, env template, and pytest settings
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:26:08 +08:00
Woody 95ef502bfa docs: add debug logs for upload 500 error investigation
- Document root causes: missing python-docx, ChromaDB version mismatch, NumPy 2.x incompatibility

- Document fixes: venv setup, embedding wrapper rewrite, DB clear

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:25:23 +08:00
Woody c9f330d57e fix(backend): wrap embedding function for ChromaDB 0.4.22 compatibility
- Add _EmbeddingFunctionWrapper class with __call__(self, input) signature

- Use ThreadPoolExecutor to run async embed in isolated thread with fresh event loop

- Fixes asyncio.run() cannot be called from a running event loop

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:25:08 +08:00
Woody 4b633d86f7 fix(backend): resolve pytest dependency conflict and remove sentence-transformers
- Change pytest==8.0.0 to pytest==7.4.4 (conflict with pytest-asyncio<8)

- Remove sentence-transformers (not used with API-based embeddings)

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 13:24:54 +08:00
Woody e927e5fc60 feat(frontend): polish styling, spacing, and add e2e integration tests for Phase 1.3
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:46:53 +08:00
Woody f6618fd57e feat(frontend): polish ResponsePanel with collapsible sources, copy button, and enhanced skeletons
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:46:40 +08:00
Woody 864b684d32 feat(frontend): add PipelineProgress component with 4-stage stepper and tests
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:46:23 +08:00
Woody 6b544808de feat(frontend): wire Phase 1.2 components into App layout
Replaces placeholder areas with QueryInput, KeywordsDisplay, ResponsePanel, IngestPanel, and ErrorBoundary. App.tsx now holds TanStack Query mutation state and passes props to all components.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:24:46 +08:00
Woody a7d5dc610a feat(frontend): add IngestPanel and ErrorBoundary components with tests
IngestPanel: file upload for PDF/DOCX/TXT with progress and success/error feedback.

ErrorBoundary: React error boundary with fallback UI and reload button.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:24:29 +08:00
Woody 3d76b894cb feat(frontend): add ResponsePanel component with bullet-point rendering and tests
Displays bullet-point answer with source metadata cards. Handles empty, loading, error, and success states.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:23:54 +08:00
Woody fa94b7c9a3 feat(frontend): add QueryInput and KeywordsDisplay components with tests
QueryInput: textarea with submit button, loading state, Enter-to-submit, clears on submit.

KeywordsDisplay: keyword chips with loading skeletons, animated entrance.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 11:23:08 +08:00
Woody 3923e20d8a feat(frontend): Phase 1.1 grid layout with Phase 2 pre-allocation and tests
App layout uses CSS Grid with Top-Left video placeholder (Film icon), Top-Right empty container for Phase 1.2 input, and Bottom full-width container for Phase 1.2 response. Includes Layout test verifying Phase 2 placeholder text and API client tests verifying baseURL and mocked endpoint calls.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 10:58:03 +08:00
Woody d3bf13142b feat(frontend): Phase 1.1 project scaffold with Vite, Tailwind, and API client
Set up Vite + React 18 + TypeScript project with Tailwind CSS, Axios API client matching backend Pydantic schemas (QueryRequest, QueryResponse, IngestResponse, SourceMetadata), and TanStack Query mutation hooks for /query and /ingest endpoints.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 10:57:20 +08:00
Woody 02e401740a chore: update .gitignore for frontend lib/ and Vite cache
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-23 10:56:35 +08:00
Woody 7493b3aaf6 feat: Phase 1.4 acceptance tests, error handling, and polish
- Implement acceptance tests for ingest (real ChromaDB) and query (real LLM)
- Full 3-step RAG pipeline verified: decompose → retrieve → filter → generate
- Add logging to ingest and query routers
- Improve error handling: empty doc detection, proper HTTPException re-raising
- Add .txt file support to ingest endpoint
- Fix query router: strip distance from retrieve tuples before relevance filter
- Update plan: Phase 1 backend complete (all acceptance criteria met)
- Tests: 41 unit passed, 5 acceptance passed (real OpenRouter calls)
2026-04-22 17:45:50 +08:00
Woody 181f4eca5b feat: Phase 1.3 query pipeline with decomposition, relevance filter, and response
- Add QueryDecomposer: extracts keywords from question via LLM JSON response
- Add RelevanceFilter: batch scores chunks 0-10, filters by threshold
- Add POST /api/v1/query endpoint with full 3-step pipeline:
  1. QueryDecomposer.decompose() → keywords
  2. RAGService.retrieve() → chunks from ChromaDB
  3. RelevanceFilter.filter() → score and filter chunks
  4. RAGService.generate_response() → bullet-point answer
- Fix SourceMetadata.upload_date type from datetime to str for flexibility
- Test-first: 13 new tests pass (5 decomposer, 5 relevance filter, 3 query endpoint)
- All Phase 1 tests: 41 passed, 2 skipped
2026-04-22 17:19:21 +08:00
Woody 4d346dc1c6 docs: Update Phase 1 backend plan with completion status
- Mark Phase 1.1 and 1.2 as complete with test results
- Update acceptance criteria checklist
- Add Services Status table showing implemented/pending components
- Mark Phase 1.3 tasks that are already done (LLM client, retrieval, response gen)
2026-04-22 16:55:17 +08:00
Woody d94abaac77 feat: Phase 1.2 ingestion pipeline with chunking and metadata
- Add document parsers (DOCX, PDF) with lazy imports
- Add TokenChunkingStrategy with ABC for future replacement
- Add metadata extraction (filename, upload_date, content_summary)
- Add RAGService for ChromaDB ingestion/retrieval/response generation
- Add POST /api/v1/ingest endpoint with file validation
- Test-first: 20 passed, 2 skipped (python-docx not installed)
2026-04-22 16:49:52 +08:00
Woody 3712397d64 feat: Phase 1.1 project setup with config, database, and models
- Add requirements.txt with all dependencies
- Add .env.example with required environment variables
- Add Pydantic Settings (config.py) with .env loading
- Add ChromaDB persistent client (database.py)
- Add Pydantic schemas (ingest.py) for request/response
- Add FastAPI main.py with CORS middleware
- Add package __init__.py files
- Add tests: test_phase1_config.py, test_phase1_database.py
- All 5 tests pass
2026-04-22 16:13:52 +08:00
Woody abffc9cf1d docs: add PDF support alongside DOCX in all plans 2026-04-22 15:59:55 +08:00
Woody 1518b72969 chore: add .gitignore with Python, Node, env, and ChromaDB exclusions 2026-04-22 15:57:04 +08:00
Woody eeb464528a docs: add test-first and Phase X.Y sub-phase naming to AGENTS.md and plans 2026-04-22 15:54:34 +08:00
Woody 1f4e3a2572 docs: add Phase 1 backend and frontend development plans 2026-04-22 15:47:27 +08:00
Woody be48b1d8c7 docs: add sub-phase development rules and acceptance test structure 2026-04-22 15:27:31 +08:00
Woody 3c2d647943 init: project setup with AGENTS.md, test structure, and plan directory 2026-04-22 15:22:29 +08:00