farcasclaudiu/openclaw
1
0
Fork 0
mirror of https://github.com/farcasclaudiu/openclaw.git synced 2026-06-28 21:01:43 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix: prevent false positive context overflow detection in conversation text (#2078)

Browse Source
This commit is contained in:
Stephen Brian King
2026-02-09 00:22:57 -07:00
committed by GitHub
parent 71b4be8799
commit c984e6d8df
4 changed files with 20 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+1
View File
@@ -15,6 +15,7 @@ Docs: https://docs.openclaw.ai
### Fixes
- Errors: prevent false positive context overflow detection when conversation mentions "context overflow" topic. (#2078) Thanks @sbking.
- Model failover: treat HTTP 400 errors as failover-eligible, enabling automatic model fallback when providers return bad request errors. (#1879) Thanks @orenyomtov.
- Exec approvals: format forwarded command text as inline/fenced monospace for safer approval scanning across channels. (#11937)
- Config: clamp `maxTokens` to `contextWindow` to prevent invalid model configs. (#5516) Thanks @lailoo.