vLLM servers support JSON schema enforcement via extra_body (guided_json
or structured_outputs), not OpenAI's response_format protocol. LangChain's
with_structured_output(method='json_schema') sends response_format which
vLLM ignores, causing NoneType not iterable parsing errors.
- vLLM path: direct OpenAI SDK call with extra_body={guided_json|structured_outputs}
- OpenRouter path: unchanged with_structured_output(method='json_schema')
- Try new 'structured_outputs' format first, fall back to legacy 'guided_json'
- Update _SEED_DECOMPOSE with explicit JSON array instruction
- Add diagnostic logging: exc_info=True, schema preview, prompt template preview
- Add logging in _parse_legacy_json for fallback failure debugging
vLLM's chat_template_kwargs leaked into LangChain's AsyncCompletions.parse()
via _get_langchain_model's model_kwargs, causing structured decomposition
to fail on vLLM backends. Skip vLLM-specific params when building the
LangChain model — only provider-agnostic params (OpenAI reasoning) pass through.
- POST /api/v1/v2/highlights/batch: compute and cache highlights for cited chunks
- GET /api/v1/v2/highlights: serve cached highlighted HTML pages
- chunks.py router registered in main.py
- Dynamic DB path computation (prompts.db -> highlights.db), no Settings changes
- 7 endpoint tests: POST 200/422, GET 200/404, mock service verification
- ChunkHighlightService.compute_highlights_batch(): single LLM call across
all cited chunks, grouped by sub-question, with structured output
- render_highlight_html(): self-contained HTML page with yellow-highlighted
relevant sentences, LLM reason annotations, and View Original PDF footer
- Per-target error isolation, ChromaDB miss handling, graceful degradation
- 14 tests: 7 batch service + 7 HTML rendering
DOCX and TXT ingestion now produces chunk_file_path + per-chunk PDF files matching the PDF ingestion flow. Uses reportlab to render chunk text as simple PDFs with automatic text wrapping.
- Add reportlab==4.2.5 to requirements.txt
- New utils/text_to_pdf.py: generate_text_pdf() renders chunk text as PDF
- Ingest router DOCX/TXT branches: generate chunk_N.pdf per chunk, store in chunk_file_paths
- Graceful degradation: chunk_file_path stays None if PDF generation fails
- Update test_phase1_ingest_page_aware.py assertions: DOCX chunks now HAVE chunk_file_path
- New test_phase5_docx_pdf_generation.py: 5 tests (DOCX PDF gen, TXT PDF gen, PDF regression, file count, graceful degradation)
- 361 backend tests pass (4 pre-existing embedding failures unrelated)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Multi-stage Dockerfile: Node builds frontend, Python serves both API
and static files. docker-compose.yml with named volumes for ChromaDB,
chunks, and SQLite data. nginx.conf as reverse proxy with 350M upload
limit and 300s LLM proxy timeout. README with dev setup, deploy steps,
env vars table, and architecture diagram.
Backend main.py: add catch-all route to serve frontend/dist/static
files in production. Only activates when dist/ exists.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add INFO log in get_settings() to print the actual model names
after merging .env and class defaults. Confirms pydantic-settings
priority: env values override class defaults as expected.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
The per-sub-question filter was all-or-nothing: if the LLM returned
9 scores for 10 chunks (common with qwen3.5-35b), every chunk was
discarded and the user got 'no relevant information found'.
Now: fewer scores → pad with 0.0; more scores → truncate. Changed
from error→warning since this is recoverable.
Also improve LTT page UI: sources collapsed by default in per-sub-q
sections, and the 'Your question' text now shows the full question
instead of being truncated.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Replace mocked DB/internal-services with real ChromaDB/SQLite via tmp_path.
Only mock truly external APIs (LLM, embedding for deterministic vectors).
13 test files rewritten (314 pass, 0 fail):
- Route tests: use TestClient + real ChromaDB, seed test data
- Service tests: use real PersistentClient/SQLite instances
- Pipeline tests: TestClient hits SSE /query endpoint, verify history
- Converted unittest.TestCase to pytest where applicable
Plus: fix metadata.py to filter None values from ChromaDB metadata
(pre-existing bug caught by real-DB ingestion tests)
Break the hardcoded per-sub-q filter prompt into 3 editable PromptService templates (filter_intro, filter_section, filter_outro) with placeholders for the for-loop iteration pattern. Refactor RelevanceFilter._build_per_subq_prompt() to compose them at runtime, falling back to built-in defaults when PromptService is unavailable.
Fix two latent bugs from Package 4:
- generate_per_subq was called by rag.py but never added to _VALID_STEPS or DB seed (would ValueError at runtime)
- _SEED_GENERATE placeholder mismatch: flat generate_response() expects {question}/{context} but Package 4 changed it to {context_sections}. Restored flat template; generate_per_subq now holds {context_sections}.
Add database backfill migration in seed_default_profiles() to INSERT OR IGNORE missing steps into existing profile rows, ensuring all 7 steps exist on restart.
Restructure System Prompts UI: remove unused flat filter/generate steps, replace with Step 2.1-2.3 (filter_intro/section/outro) and Step 3 (generate_per_subq). Update PlaceholderDocs with {context_sections}, {subq_idx}, {subq_question}.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add 6 tests for retrieve_per_subquestion and generate_response_per_subquestion to Phase 1 rag service tests. Add 4 tests for filter_per_subquestion to Phase 1 relevance filter tests. Add 2 tests for new {context_sections} generate template to Phase 3 prompt injection tests. Add TestPerSubQPipelineHistory class with 3 per-sub-q pipeline simulation tests to Phase 3 integration tests. Add generate_per_subq template seed to conftest mock_prompt_service fixture.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
5 integration tests simulating full per-sub-question pipeline with mocked services covering 2-sub-q, empty decomposition fallback, single sub-q, all-filtered, and partial retrieval. 2 acceptance tests (manual run) for real LLM verification of per-sub-question organized answers with grouped sources and ## Sub-question headers.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
9 tests for generate_response_per_subquestion() and answer format validation covering multi-sub-q, empty, prompt construction, and markdown format. 8 tests for new history XML/JSON formats (sources as list-of-lists, <sub_q> wrappers in XML) and new {context_sections} prompt template.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add chunks_retrieved_per_subq_count and chunks_filtered_per_subq_count columns to query_history table with safe ALTER TABLE migration. Replace generate template {question}/{context} placeholders with {context_sections} for per-sub-question organized context sections. Update Phase 3 test assertions to match new template and schema shapes.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add SubQuestionSources, SubQuestionResult, GeneratingSubquestionEvent Pydantic models for the new per-sub-question response format. Add chunks_retrieved_per_subq_count and chunks_filtered_per_subq_count optional fields to QueryHistoryRecord and QueryHistoryDetail for per-sub-question chunk count tracking.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Restructure _query_stream() to use per-sub-question retrieval, filtering, and generation. Add generative_subquestion SSE events for progressive frontend rendering. Add format_chunks_retrieved_per_subq() and format_chunks_filtered_per_subq() with <sub_q> XML wrappers. Add empty decomposition fallback using original question as single sub-q. Update history recording for grouped sources JSON (list-of-lists format).
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add retrieve_per_subquestion() that queries ChromaDB independently per sub-question instead of joining all sub-qs into one query string. Add filter_per_subquestion() that evaluates each chunk against its own originating sub-question in a single LLM call with a redesigned grouped prompt. Add generate_response_per_subquestion() that produces markdown sections per sub-question with grouped sources and {context_sections} template support. All existing methods preserved for backward compatibility.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Convert /query endpoint from synchronous JSON to Server-Sent Events (SSE)
streaming. The frontend now receives extracted_questions as soon as the
first LLM call completes, without waiting for retrieval, filtering, and
answer generation.
Backend:
- Add StreamingQueryEvent union type (Decomposed, Retrieving, Filtering,
Generating, Completed, Error)
- Convert /query to return StreamingResponse with SSE format
- Yield events after each pipeline phase
Frontend:
- Add queryDocumentStream() using fetch + ReadableStream
- Add useQueryDocumentStream() hook with phase-aware state
- Update LTTPage to use streaming instead of mutation
- Update ResponsePanel to show phase messages (Searching documents...,
Filtering passages..., Generating answer...)
- Update ExtractedQuestionsDisplay to accept null
Tests:
- Update query_flow e2e test to mock queryDocumentStream
- 84/85 tests pass (1 pre-existing failure from removed file-input)
Replace numeric [1] labels with [filename, page N] format in context chunks.
Update LLM prompt to instruct inline citation using bracket labels.
Enables traceable source references in generated answers.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Update prompt assertion in decomposer test and field assertions in query endpoint tests to match extracted_questions rename.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Change QueryDecomposer prompt to generate 2-5 sub-questions instead of keywords. Rename API field from keywords to extracted_questions across models, service, and router.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Add page_number and chunk_file_path to SourceMetadata model and query router
- Add GET /chunks/{file_path}/pdf endpoint with path traversal protection
- Add View PDF links in ResponsePanel source cards and ChunkList component
- Update TypeScript types and API helper for chunk PDF URLs
- Add backend tests (5) and frontend ChunkList tests (7)
- Update enhancement plan: all 3 features complete
Delete document endpoint now removes associated chunk PDF files from document_chunk/ before ChromaDB deletion. Delete chunk endpoint removes individual chunk PDF. Missing files logged as warnings, not errors.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
PDF uploads now use parse_pdf_by_page() -> chunk_pages() -> extract page PDFs -> enhanced metadata with page_number, chunk_file_path, and document_id. Same-filename replacement deletes old chunks and PDFs before re-ingest. DOCX/TXT keep original flat flow with document_id added. RAGService.ingest_document() accepts optional document_id parameter.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
New pdf_extractor.py with extract_page_as_pdf() and extract_pages_as_pdf() for extracting individual PDF pages as separate files. Adds document_chunk_path setting to config and document_chunk/ to .gitignore.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Enhance extract_metadata() with three new optional fields for page-aware chunking support. Validates list length mismatches. Fully backward compatible — existing callers unaffected.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add chunk_pages() to TokenChunkingStrategy: one chunk per page with 200-token overlap from adjacent pages. Uses original page text for main content, decoded tokens for overlap. Never splits a page regardless of size.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add parse_pdf_by_page() that returns List[Tuple[int, str]] with 1-indexed page numbers. Pages with no extractable text are skipped. Follows same error handling as existing parse_pdf().
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
ChromaDB 1.5.8 calls embed_query() during collection.query(), but the wrapper only implemented __call__ (used by collection.add()). Added embed_query() as alias and refactored to shared _embed() method.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
When uploading files, the backend passes them through NamedTemporaryFile, causing os.path.basename to return temp names like 'tmp90i7xqa8.pdf'. Added original_filename parameter to extract_metadata() so the actual upload filename is stored.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
ChromaDB 1.5.8 requires embedding functions to implement the name() method from the EmbeddingFunction protocol. Without this, collection.get() fails with AttributeError.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Add 4 REST endpoints for RAG database management: GET /documents, GET /documents/{id}/chunks, DELETE /documents/{id}, DELETE /chunks/{id}. Register documents router in main.py. 8 unit tests covering all CRUD operations.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Add react-router-dom with NavBar component (LTT + RAG Database tabs)
- Extract AppContent into LTTPage, add RAGDatabasePage placeholder
- Refactor App.tsx to BrowserRouter + Routes layout
- Switch ResponsePanel to react-markdown for rich formatting
- Fix ResponsePanel test for markdown rendering
- Update RAG prompt to cite source name instead of number
- Save Phase 1 enhancement plan (.plans/phase1_enhancement_plan.md)
- Log extra_body contents before sending to LLM
- Log full LLM response object for debugging
- Changed extra_body format to OpenRouter reasoning format
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus \u003cclio-agent@sisyphuslabs.ai\u003e
Woody