revert: per-model thinkingDefault override (#19195)

Merged via /review-pr -> /prepare-pr -> /merge-pr.

Prepared head SHA: fe2c59e222a71086864f8abfae05d2da03ad4066
Co-authored-by: sebslight <19554889+sebslight@users.noreply.github.com>
Co-authored-by: sebslight <19554889+sebslight@users.noreply.github.com>
Reviewed-by: @sebslight
This commit is contained in:
Seb Slight
2026-02-17 09:25:18 -05:00
committed by GitHub
parent 5d1bcc76cc
commit 3211280bed
4 changed files with 1 additions and 32 deletions

View File

@@ -20,6 +20,7 @@ Docs: https://docs.openclaw.ai
### Fixes
- Agents: revert accidental per-model thinkingDefault override merge. (#19195) Thanks @sebslight.
- Voice call/Gateway: prevent overlapping closed-loop turn races with per-call turn locking, route transcript dedupe via source-aware fingerprints with strict cache eviction bounds, and harden `voicecall latency` stats for large logs without spread-operator stack overflow. (#19140) Thanks @mbelinky.
- iOS/Onboarding: stop auth Step 3 retry-loop churn by pausing reconnect attempts on unauthorized/missing-token gateway errors and keeping auth/pairing issue state sticky during manual retry. (#19153) Thanks @mbelinky.
- Fix types in all tests. Typecheck the whole repository.