Skip to content

Conversation

@QIN2DIM
Copy link
Contributor

@QIN2DIM QIN2DIM commented Nov 19, 2025

Note

DRAFT DRAFT DRAFT DRAFT DRAFT DRAFT DRAFT DRAFT DRAFT DRAFT DRAFT

Related Issues or Context

fixed: #2088

This commit enables the capture and propagation of thought signatures from the Gemini 3 Pro Preview model, allowing for better tracking of reasoning steps and intermediate thoughts during model execution.

  • Updated manifest.yaml and google.yaml to reflect 'Gemini dev' label and version 0.6.1
  • Modified gemini-3-pro-preview.yaml to enforce temperature = 1.0 as required by the model
  • Enhanced LLM implementation to extract and attach thought signatures to message content
  • Added debug logging and print statements for tracing thought signature flow
  • Updated message parsing to preserve thought signatures across different content types (text, code, execution results)
  • Added support for interleaved thinking via thought_signature handling

Documentation: https://ai.google.dev/gemini-api/docs/gemini-3?hl=zh-cn&thinking=high#thought_signatures

This PR contains Changes to Non-Plugin

  • Documentation
  • Other

This PR contains Changes to Non-LLM Models Plugin

  • I have Run Comprehensive Tests Relevant to My Changes

This PR contains Changes to LLM Models Plugin

  • My Changes Affect Message Flow Handling (System Messages and User→Assistant Turn-Taking)
  • My Changes Affect Tool Interaction Flow (Multi-Round Usage and Output Handling, for both Agent App and Agent Node)
  • My Changes Affect Multimodal Input Handling (Images, PDFs, Audio, Video, etc.)
  • My Changes Affect Multimodal Output Generation (Images, Audio, Video, etc.)
  • My Changes Affect Structured Output Format (JSON, XML, etc.)
  • My Changes Affect Token Consumption Metrics
  • My Changes Affect Other LLM Functionalities (Reasoning Process, Grounding, Prompt Caching, etc.)
  • Other Changes (Add New Models, Fix Model Parameters etc.)

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

  • I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Dify Plugin SDK Version

  • I have Ensured dify_plugin>=0.3.0,<0.6.0 is in requirements.txt (SDK docs)

Environment Verification (If Any Code Changes)

Local Deployment Environment

  • Dify Version is: , I have Tested My Changes on Local Deployment Dify with a Clean Environment That Matches the Production Configuration.

SaaS Environment

  • I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration

This commit enables the capture and propagation of thought signatures from the Gemini 3 Pro Preview model, allowing for better tracking of reasoning steps and intermediate thoughts during model execution.

- Updated manifest.yaml and google.yaml to reflect 'Gemini dev' label and version 0.6.1
- Modified gemini-3-pro-preview.yaml to enforce temperature = 1.0 as required by the model
- Enhanced LLM implementation to extract and attach thought signatures to message content
- Added debug logging and print statements for tracing thought signature flow
- Updated message parsing to preserve thought signatures across different content types (text, code, execution results)
- Added support for interleaved thinking via thought_signature handling

Documentation: https://ai.google.dev/gemini-api/docs/gemini-3?hl=zh-cn&thinking=high#thought_signatures
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

fix(gemini): gemini-3-pro-preview function call is missing a thought_signature in functionCall parts.

1 participant