Files
windmill/frontend/src/lib/components
Ruben FiszelandClaude Opus 4.8 ad53673a28 fix(ai-chat): improve resource-type search tool description and scoring (#10272)
The global-mode search_resource_types tool described its query as a
substring match, but the backend does semantic embedding search. Rewrite
the description so the LLM sends natural-language intent instead of literal
name guesses.

Apply the top-score trim to query_resource_types so a strong match isn't
diluted by weakly-related types that merely clear the 0.75 similarity floor.
The trim was previously inlined only in query_hub_scripts; extract it into a
shared trim_to_top_score helper, use it from both search paths, and add a
unit test pinning the 5% cutoff boundary.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-23 00:54:18 +02:00
..
2025-09-11 07:57:01 +00:00
2026-03-05 18:11:40 +01:00
2025-10-30 06:47:26 +00:00
2025-10-28 17:52:04 +00:00
2026-03-05 18:11:40 +01:00
2025-11-29 01:23:47 +00:00
2026-03-05 18:11:40 +01:00
2025-11-04 19:13:09 +00:00
2026-02-11 06:27:21 +00:00
2026-02-19 09:33:33 +00:00
2025-11-29 01:23:47 +00:00
2026-03-05 18:11:40 +01:00
2026-03-05 18:11:40 +01:00
2026-03-05 18:11:40 +01:00