Piotr Oleszczyk cc657998e8 fix(llm): switch from thinking_budget to thinking_level=LOW for Gemini 3 ... gemini-flash-latest resolves to gemini-3-flash-preview which uses thinking_level instead of the legacy thinking_budget (mixing both returns HTTP 400). Use LOW to reduce thinking overhead while keeping basic reasoning, replacing the now-incompatible thinking_budget=0. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>		2026-03-01 20:15:49 +01:00
..
api	feat(routines): add minoxidil beard/mustache option to routine suggestions	2026-03-01 19:46:07 +01:00
models	fix(llm): log and handle non-STOP finish_reason from Gemini	2026-03-01 20:08:22 +01:00
llm.py	fix(llm): switch from thinking_budget to thinking_level=LOW for Gemini 3	2026-03-01 20:15:49 +01:00
mcp_server.py	fix(backend): apply black/isort formatting and fix ruff noqa annotations	2026-03-01 17:27:07 +01:00