fix: strip incompatible thinking blocks when switching to Anthropic models #6748
+26
−8
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…odels When switching from a model like minimax to Claude/Opus, the session contains thinking blocks with signatures that Anthropic's API rejects with 'Invalid signature in thinking block' error. This fix: - Filters out thinking blocks with signatures when targeting Claude - Converts reasoning parts to text wrapped in <thinking> tags to preserve the content while making it compatible
This was referenced Jan 6, 2026
Contributor
|
can validate this is still an issue |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Problem
When switching from a model like minimax to Claude/Opus mid-session, the API returns:
This happens because the session contains cached messages with thinking blocks that have signatures from the previous model (minimax), which Anthropic's API rejects.
Solution
In
normalizeMessages(), when the target model is Claude:thinkingblocks that have signatures (from other providers)reasoningparts to text wrapped in<thinking>tags to preserve contentTesting