fix(gemini): fix reasoning_content showing duplicate content in streaming responses #17266
+83
−19
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
…hinking blocks
The previous implementation incorrectly used `thoughtSignature` as the criterion
to detect thinking blocks. However, per Google's docs:
- `thought: true` indicates that a part contains reasoning/thinking content
- `thoughtSignature` is just a token for multi-turn context preservation
(a part can have thoughtSignature without thought:true, e.g., function calls)
This caused functionCall data to leak into reasoning_content when using
Gemini 2.5 Pro with streaming + tools enabled.
Changes:
- _extract_thinking_blocks_from_parts now checks `part.get("thought") is True`
- Extract actual text content instead of json.dumps(part)
- Include signature only when present (optional in Gemini 2.5)
Refs:
- https://ai.google.dev/gemini-api/docs/thinking
- https://ai.google.dev/gemini-api/docs/thought-signatures
|
@Chesars is attempting to deploy a commit to the CLERKIEAI Team on Vercel. A member of the Team first needs to authorize it. |
Chesars
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Title
fix(gemini): use thought:true instead of thoughtSignature to detect thinking blocks
Relevant issues
Fixes the issue reported in #16854 (comment)
Pre-Submission checklist
tests/litellm/directorymake test-unitType
🐛 Bug Fix
Changes
The previous implementation of
_extract_thinking_blocks_from_partsincorrectly used"thoughtSignature" in partas the criterion to detect thinking blocks.Per Google's docs:
thought: trueindicates that a part contains reasoning/thinking contentthoughtSignatureis just a token for multi-turn context preservation (docs)A part can have
thoughtSignaturewithoutthought: true(e.g., function calls), which causedfunctionCalldata to leak intoreasoning_contentwhen using Gemini 2.5 Pro with streaming + tools.Before:
content: "Hello! How can I help you today?"
reasoning_content: { text: "Hello! How can I help you today?" } // duplicated!
After:
content: "Hello! How can I help you today?"
reasoning_content: None // correct - only shows reasoning when thought: true
Changes:
_extract_thinking_blocks_from_parts checkspart.get("thought") is True`json.dumps(part)