fix AI-63
fix PD-2567
fix AI-150
fix AI-149
fix AI-148
fix AI-147
fix AI-146
fix AI-145
fix AI-144
fix AI-143
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Enhanced AI-generated responses for writing and code-related prompts with detailed, structured instructions for improved clarity and consistency.
- Updated AI model for multiple prompts to deliver faster and more accurate results.
- **Bug Fixes**
- Improved test validation for code explanation and error-checking prompts to better recognize correct outputs.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-125](https://linear.app/affine-design/issue/AI-125)
What Changed?
- Add `gemini-2.5-flash-preview-04-17` model
- Add `thinkingConfig` provider options
- Add callout syntax highlighting
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added support for the "Gemini 2.5 Flash" model and updated the "Gemini 2.5 Pro" model to a newer version.
- Enhanced streaming responses to better format reasoning outputs and provide clearer callouts in AI-generated content.
- **Bug Fixes**
- Improved audio transcription prompts in test cases for more accurate and explicit testing.
- **Documentation**
- Expanded citation instructions for AI chat responses, including examples for multiple citations.
- **Chores**
- Updated the "@ai-sdk/google" dependency to a newer version.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
fix AI-4
fix AI-18
better provider/model choose to allow fallback to similar models (e.g., self-hosted) when the provider is not fully configured
split functions of different output types
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Expanded file chunk matching to include both context and workspace file embeddings, providing broader and more relevant search results.
- **Improvements**
- Enhanced result ranking by introducing a re-ranking step for combined embedding matches, improving the relevance of returned file chunks.
- Adjusted file count reporting to reflect the total number of workspace files instead of ignored documents for more accurate workspace file statistics.
- Renamed and streamlined workspace file management methods for clearer and more consistent API usage.
- **Bug Fixes**
- Prevented embedding similarity queries when embedding is disabled for a workspace, improving system behavior consistency.
- **Tests**
- Added comprehensive tests to verify workspace embedding management, including enabling, matching, and disabling embedding functionality.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
fix AI-88
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added support for the new image generation model "gpt-image-1" in both backend and frontend.
- Updated available prompt options to include "gpt-image-1" for image creation actions.
- **Improvements**
- Set a 5-minute timeout for image generation requests to improve reliability.
- **Tests**
- Expanded test coverage to validate image generation using the new "gpt-image-1" prompt.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [BS-2834](https://linear.app/affine-design/issue/BS-2834).
### What Changed?
- Change `reference_index` from chip order to increasing positive integer.
- Add matched context documents to ai prompt.
darkskygit