shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ai): mark inception/mercury-2 thinkingLevelMap.off as null

Browse Source 
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.
This commit is contained in:
Apoorv Saxena
2026-05-13 19:16:26 +05:30
parent c08c462461
commit e2b69a0bb1
3 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
packages/ai/CHANGELOG.md
View File

@@ -10,6 +10,7 @@
- Fixed GitHub Copilot Claude test coverage to use the current Claude Sonnet 4.6 model ID.
- Fixed OpenAI Responses requests for models that support disabling reasoning to send `reasoning.effort: "none"` when thinking is off.
- Fixed Inception Mercury 2 tool calling on OpenRouter by marking `off` as unsupported in `thinkingLevelMap`, so the openai-completions provider omits the reasoning param instead of defaulting to `{reasoning:{effort:"none"}}` (which puts Mercury 2 in instant mode, disabling tool calls).
## [0.74.0] - 2026-05-07