Apoorv Saxena e2b69a0bb1 fix(ai): mark inception/mercury-2 thinkingLevelMap.off as null ... Mercury 2 in instant mode (reasoning_effort: "none") disables tool calling. The openai-completions provider hardcodes {reasoning:{effort:"none"}} when no explicit reasoning level is passed and thinkingLevelMap.off isn't null (openai-completions.ts:575), so every caller that doesn't opt in to a level silently breaks Mercury 2's agentic use cases. Setting thinkingLevelMap.off = null on the Mercury 2 catalog entry causes the provider to omit the reasoning param entirely, letting Mercury 2's own default take over. Low/medium/high pass through verbatim; OpenRouter normalizes them to Mercury's vocabulary. Prefix-matched on "inception/mercury-2" so future Mercury 2 variants on OpenRouter inherit the fix.		2026-05-13 19:17:36 +05:30
..
generate-image-models.ts	feat: image models	2026-05-04 17:07:02 +02:00
generate-models.ts	fix(ai): mark inception/mercury-2 thinkingLevelMap.off as null	2026-05-13 19:17:36 +05:30
generate-test-image.ts	feat(ai): Add image input tests for vision-capable models	2025-08-30 18:37:17 +02:00