fix(chatcmpl): preserve text content when adding Anthropic thinking blocks to tool calls #1784
+26
−6
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
…locks to tool calls
In the case of Anthropic Claude with extended thinking, this ensures that existing text content is properly converted to content array format before appending thinking blocks, preventing overwriting of original assistant message content.
This happens in a rare case where there is a (output text, thinking block, tool call) all in one response. Error message is like below:
```
"litellm.BadRequestError: BedrockException - {\"message\":\"The model returned the following errors: messages.1.content.49: `thinking` or `redacted_thinking` blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response.\"}"
```
The error is misleading because the actual reason is because we didn't provide the text content along side the thinking blocks.
seratch
approved these changes
Sep 22, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
In the case of Anthropic Claude with extended thinking, this ensures that existing text content is properly converted to content array format before appending thinking blocks, preventing overwriting of original assistant message content.
This happens in a rare case where there is a (output text, thinking block, tool call) all in one response. Error message is like below:
The error is misleading because the actual reason is because we didn't provide the text content along side the thinking blocks.
This rarely happens. (0.5%) But in our agent evaluation suite, this happens when doing agents handoffs to a reflection style agent.