legco_ai_assistant/.plans
Woody 2aca18d30e docs: add vLLM structured output fix plan
- Diagnose: vLLM ignores OpenAI-native response_format, causing NoneType error
- Diagnose: legacy fallback prompt lacks JSON instruction → empty questions
- Plan: use vLLM-native guided_json via extra_body instead of with_structured_output
- Plan: update _SEED_DECOMPOSE with JSON format instruction
- Plan: add diagnostic logging (exc_info, method, schema preview)

wip: temporary function_calling switch for vLLM (to be replaced by guided_json)
2026-04-29 16:42:23 +08:00
..
debug_2026-04-23_upload_500_error.md docs: add debug logs for upload 500 error investigation 2026-04-23 13:25:23 +08:00
debug_vllm_structured_output.md docs: add vLLM structured output fix plan 2026-04-29 16:42:23 +08:00
package2_enhancement_plan.md docs: mark sub-phase 2.6 complete — Package 2 all done 2026-04-24 17:53:56 +08:00
package3_enhancement_plan.md feat(frontend): Phase 3.6 — History page with timing bars, expandable cards, and pagination 2026-04-26 13:19:52 +08:00
package4_enhancement_plan.md docs(plan): add Phase PX profile export/import feature plan 2026-04-27 19:26:33 +08:00
package5_enhancement_plan.md feat: track highlight generation prompt, response, and timing in history (Phase 5.5) 2026-04-29 11:18:21 +08:00
phase1_backend_plan.md feat: Phase 1.4 acceptance tests, error handling, and polish 2026-04-22 17:45:50 +08:00
phase1_debug_plan.md docs: add debug logs for upload 500 error investigation 2026-04-23 13:25:23 +08:00
phase1_enhancement_plan.md feat: add chunk PDF serving endpoint and frontend clickable source links (1.5.6) 2026-04-24 11:49:39 +08:00
phase1_frontend_plan.md docs: update development plans with Phase 1 completion status 2026-04-23 13:27:52 +08:00
streaming_extracted_questions_plan.md feat(query): stream extracted questions immediately via SSE 2026-04-25 18:29:22 +08:00