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

fix(ai): explicitly disable Anthropic thinking when off closes #2022

Browse Source
This commit is contained in:
Mario Zechner
2026-03-22 19:38:54 +01:00
parent 74073e5227
commit 6129971c04
3 changed files with 146 additions and 13 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
- Fixed OpenAI Responses replay for foreign tool-call item IDs by hashing foreign `function_call.id` values into bounded `fc_<hash>` IDs instead of preserving backend-specific normalized shapes that OpenAI Codex rejects.
- Fixed Anthropic thinking disable handling to send `thinking: { type: "disabled" }` for reasoning-capable models when thinking is explicitly off, and added payload and env-gated end-to-end coverage for the Anthropic provider ([#2022](https://github.com/badlogic/pi-mono/issues/2022))
## [0.61.1] - 2026-03-20