Woody a7a22f1494 fix(relevance): tolerate LLM score count mismatches via padding instead of discarding ... 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>		2026-04-27 14:31:18 +08:00
..
app	fix(relevance): tolerate LLM score count mismatches via padding instead of discarding	2026-04-27 14:31:18 +08:00
uploads	chore: add .gitignore with Python, Node, env, and ChromaDB exclusions	2026-04-22 15:57:04 +08:00
.env.example	feat(db): Phase 3.1 — SQLite infrastructure (prompts.db + history.db)	2026-04-25 20:29:29 +08:00
pytest.ini	chore(backend): update config, env template, and pytest settings	2026-04-23 13:26:08 +08:00
requirements.txt	feat(backend): migrate LLM client to OpenAI SDK with thinking control	2026-04-23 14:10:26 +08:00