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
.plans	feat(prompts): integrate filter_per_subq with PromptService, fix seed bugs, restructure UI	2026-04-27 11:14:27 +08:00
backend	fix(relevance): tolerate LLM score count mismatches via padding instead of discarding	2026-04-27 14:31:18 +08:00
frontend	fix(relevance): tolerate LLM score count mismatches via padding instead of discarding	2026-04-27 14:31:18 +08:00
.env.txt	init: project setup with AGENTS.md, test structure, and plan directory	2026-04-22 15:22:29 +08:00
.gitignore	feat(db): Phase 3.1 — SQLite infrastructure (prompts.db + history.db)	2026-04-25 20:29:29 +08:00
AGENTS.md	docs: update testing rules to integration-first approach	2026-04-27 10:55:43 +08:00
development_plan.md	docs: update development plans with Phase 1 completion status	2026-04-23 13:27:52 +08:00