let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(agents): strip tool leak text (#905)

Browse Source 
Thanks @erikpr1994.

Co-authored-by: Erik Pastor Rios <erikpastorrios1994@gmail.com>
This commit is contained in:
Peter Steinberger
2026-01-15 05:57:44 +00:00
parent 5c2eedc340
commit 2bd9e84851
3 changed files with 159 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@@ -23,6 +23,7 @@
- Browser: add tests for snapshot labels/efficient query params and labeled image responses.
- Telegram: register dock native commands with underscores to avoid `BOT_COMMAND_INVALID` (#929, fixes #901) — thanks @grp06.
- Google: downgrade unsigned thinking blocks before send to avoid missing signature errors.
- Agents: strip downgraded tool call text without eating adjacent replies and filter thinking-tag leaks. (#905) — thanks @erikpr1994.
- Agents: cap tool call IDs for OpenAI/OpenRouter to avoid request rejections. (#875) — thanks @j1philli.
- Doctor: avoid re-adding WhatsApp config when only legacy ack reactions are set. (#927, fixes #900) — thanks @grp06.
- Agents: scrub tuple `items` schemas for Gemini tool calls. (#926, fixes #746) — thanks @grp06.