romtuck/openclaw
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: gate openai reasoning downgrade on model switches (#1562) (thanks @roshanasingh4)

Browse Source
This commit is contained in:
Peter Steinberger committed 2026-01-24 07:58:04 +00:00
1 parent aa02b5d7a9
commit 3a8101a96b
6 files changed
+238 -40
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/reference/transcript-hygiene.md
+1
View File
@@ -48,6 +48,7 @@ Implementation:
**OpenAI / OpenAI Codex**
- Image sanitization only.
- On model switch into OpenAI Responses/Codex, drop orphaned reasoning signatures (standalone reasoning items without a following content block).
- No tool call id sanitization.
- No tool result pairing repair.
- No turn validation or reordering.