Close [AI-160](https://linear.app/affine-design/issue/AI-160)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Improved preview state management for code blocks, ensuring consistent behavior in both editable and readonly modes.
- **Refactor**
- Streamlined the way preview state is toggled and displayed for code blocks, resulting in a more reliable and maintainable user experience.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-165](https://linear.app/affine-design/issue/AI-165)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Enhanced chat components to support advanced reasoning and network search options, providing more control over AI-powered interactions.
- Improved polling for context documents and files, now also triggered by additional chip types for more comprehensive updates.
- **Bug Fixes**
- Ensured consistent application of configuration settings across all relevant chat components.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Support [AI-59](https://linear.app/affine-design/issue/AI-59)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Updated the default AI model for chat prompts to use Claude Sonnet 4.
- **Bug Fixes**
- Improved model selection logic to better support reasoning features across more AI models.
- **Tests**
- Enhanced test cases with consistent instructions for response length.
- Skipped certain chat-related tests to refine test suite stability.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-86](https://linear.app/affine-design/issue/AI-86)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Introduced an AI Playground accessible from the chat panel, allowing users to experiment with AI chat sessions in a dedicated modal interface.
- Added a playground icon to the chat panel for quick access to the new playground feature.
- Added new interactive components for managing AI chat sessions, including chat panels, session lists, and modal dialogs.
- **Improvements**
- Enhanced chat panel session management for a smoother experience by simplifying session filtering.
- Updated property names in chat input and composer components for improved clarity and consistency.
- Made tracking options optional in chat input and composer components to improve flexibility.
- **Bug Fixes**
- Corrected property bindings in AI chat composer to ensure proper panel sizing.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-86](https://linear.app/affine-design/issue/AI-86)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Improved chat session forking to allow creating a fork without specifying the latest message, enabling more flexible session management.
- **Bug Fixes**
- Forking a chat session with an invalid latest message ID now correctly returns an error.
- **Tests**
- Added and updated test cases to cover session forking with missing or invalid latest message IDs, ensuring robust behavior in these scenarios.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Support [AI-82](https://linear.app/affine-design/issue/AI-82).
Added a `TextStreamParser` class to standardize formatting of different types of AI stream chunks across providers.
### What changed?
- Created a new `TextStreamParser` class in `utils.ts` that handles formatting of various chunk types (text-delta, reasoning, tool-call, tool-result, error)
- Refactored the Anthropic, Gemini, and OpenAI providers to use this shared parser instead of duplicating formatting logic
- Added comprehensive tests for the new `TextStreamParser` class, including tests for individual chunk types and sequences of chunks
- Defined a common `AITools` type to standardize tool interfaces across providers
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Enhanced formatting and structure for streamed AI responses, including improved handling of callouts, web search, and web crawl results.
- **Refactor**
- Streamlined and unified the processing of streamed AI response chunks across providers for more consistent output.
- **Bug Fixes**
- Improved error handling and display for streamed responses.
- **Tests**
- Added comprehensive tests to ensure correct formatting and handling of various streamed message types.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Support [AI-59](https://linear.app/affine-design/issue/AI-59)
Deprecated use of the perplexity model. Makes chat and search use the same prompt content.
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
- **New Features**
- Added support for two new AI models: Claude Opus 4 and Claude Sonnet 4, enabling enhanced text and image input capabilities.
- Introduced a new chat prompt with detailed instructions for specialized AI interactions within AFFiNE.
- **Refactor**
- Improved prompt management for AI chat and search features by centralizing shared settings for better consistency.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-125](https://linear.app/affine-design/issue/AI-125)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added new provider configurations `geminiVertex` and `anthropicVertex` for Google Vertex AI in backend schema, provider classes, and admin config.
- Introduced `GeminiVertexProvider` and `AnthropicVertexProvider` classes supporting Vertex AI models with specific capabilities.
- Expanded model options for transcription prompts with newer Gemini models.
- Re-exported provider modules to include Vertex AI variants.
- **Improvements**
- Extended provider architecture to support separate Vertex AI configurations and models.
- Updated test setup to replace deprecated provider references with new Vertex variants.
- Consolidated environment variables for server testing with a single `SERVER_CONFIG`.
- **Bug Fixes**
- Updated mock models and import references in tests to align with new provider classes.
- **Chores**
- Added `@ai-sdk/google-vertex` dependency for Vertex AI support.
- Updated dependency list to include `@ai-sdk/google-vertex`.
<!-- 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 -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **Bug Fixes**
- Improved stability of the AI chat input to prevent errors when certain configuration options are missing.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-86](https://linear.app/affine-design/issue/AI-86)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Introduced AI model switching in chat, allowing users to select from multiple AI models during conversations.
- Added a floating menu for easy AI model selection within the chat interface.
- Enabled visibility of the AI model switcher through a new experimental feature flag, configurable in workspace settings (canary builds only).
- **Enhancements**
- Improved session management in the chat panel for smoother model switching and state handling.
- Updated localization to support the new AI model switch feature in settings.
- **Bug Fixes**
- None.
- **Chores**
- Registered new components and services to support AI model switching functionality.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-126](https://linear.app/affine-design/issue/AI-126)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Introduced a new web crawling tool, allowing users to extract live content from specific web pages in addition to traditional web search.
- **Improvements**
- Enhanced error handling for web search and web crawl operations, providing clearer failure messages.
- Updated terminology in AI prompts and user-facing messages to reflect the new web search/crawl capabilities.
- Improved formatting of web search and crawl results for better readability.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-116](https://linear.app/affine-design/issue/AI-116)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added the ability to retrieve detailed information for a specific Copilot session by its ID, including model metadata and optional models, via the user interface and API.
- Session data now includes additional fields such as the model used and a list of optional models.
- Enhanced GraphQL queries and UI components to support fetching and displaying these new session details.
- **Improvements**
- Session lists now provide richer information, including model details, for each session.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-116](https://linear.app/affine-design/issue/AI-116)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added support for specifying alternative AI models in chat prompts, enabling users to select from multiple available models.
- Expanded AI model options with new additions: 'gpt-4.1', 'o3', and 'claude-3-5-sonnet-20241022'.
- **Enhancements**
- Users can now optionally choose a specific AI model during chat interactions.
- Prompts and chat sessions reflect and support selection of alternative models where applicable.
- **Bug Fixes**
- Improved handling of prompt configuration defaults for better reliability.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-118](https://linear.app/affine-design/issue/AI-118)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- The abort button in the chat input is now available during both "transmitting" and "loading" states, giving users more control to cancel ongoing actions.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-75](https://linear.app/affine-design/issue/AI-75)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Improved formatting for AI-generated reasoning and web search results, displaying them as callout blocks for enhanced readability.
- Expanded support for rendering callout blocks in the text renderer.
- **Style**
- Adjusted layout to ensure callout blocks retain appropriate spacing and appearance.
- **Refactor**
- Simplified and unified the integration of web search tools for AI providers.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-85](https://linear.app/affine-design/issue/AI-85)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Enhanced AI chat experience with improved web search integration, including a new "AUTO" mode that allows the AI to search the web only when needed.
- Updated AI model for chat to "o4-mini" for improved performance.
- **Improvements**
- Refined instructions to reduce hallucinations and ensure the AI admits uncertainty when unsure.
- Enhanced streaming responses to display web search queries and results more clearly.
- Updated web search tool modes for more accurate and flexible search behavior.
- Centralized AI provider options and improved tool selection logic for better response quality.
- **Bug Fixes**
- Improved handling of tool calls and reasoning steps in AI chat responses.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Updated the AI model used for the "Chat With AFFiNE AI" feature to enhance chat capabilities.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **Chores**
- Updated test setup to automatically skip onboarding steps during environment initialization.
- Simplified test utility methods by removing notification handling logic from chat panel and editor mode switching processes.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-59](https://linear.app/affine-design/issue/AI-59)
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added support for two new providers, Anthropic and Exa, in test environments and configurations.
- **Chores**
- Updated workflow and test environment setup to include API keys for Anthropic and Exa providers.
- **Refactor**
- Changed the AI model used for the "Chat With AFFiNE AI" prompt to "claude-3-7-sonnet-20250219".
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Support [AI-60](https://linear.app/affine-design/issue/AI-60).
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **Refactor**
- Updated naming conventions for the web search tool to ensure consistency across AI chat features.
- Simplified internal handling of web search tool options for a more streamlined experience.
- Unified parameter naming from "mustSearch" to "webSearch" across AI chat inputs and actions.
- **Chores**
- Removed unused configuration options related to web search from prompt settings.
- Added support for enabling or disabling web search via new parameters in chat requests.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-81](https://linear.app/affine-design/issue/AI-81).
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added support for uploading and handling multiple images in the AI chat interface, with a maximum image limit enforced.
- Chat assistant avatar now visually indicates different statuses, including a transmitting animation.
- **Improvements**
- Enhanced file upload experience by allowing batch image uploads and clearer notifications for files exceeding size limits.
- Stronger status handling for chat assistant messages, improving reliability and user feedback.
- Unified image count limit across chat input components using a shared constant.
- **Bug Fixes**
- Improved consistency in how image limits are enforced across chat components.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-58](https://linear.app/affine-design/issue/AI-58).
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Introduced a toggleable AI reasoning feature in the chat interface, allowing users to enable or disable advanced reasoning during AI chat interactions.
- Added a new reasoning button to the chat input for quick access and control.
- **Enhancements**
- Improved chat configuration options to include reasoning settings, providing more flexibility for AI responses.
- Streamlined network search and image upload interactions for a smoother user experience.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [AI-40](https://linear.app/affine-design/issue/AI-40).
### What changed?
- Add anthropic provider.
<!-- This is an auto-generated comment: release notes by coderabbit.ai -->
## Summary by CodeRabbit
- **New Features**
- Added support for Anthropic as a new provider option in Copilot, enabling integration with Anthropic's text generation models.
- Users can now configure Anthropic provider settings, including API key management, through the admin interface.
- **Chores**
- Updated dependencies to include the Anthropic SDK for backend operations.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Close [BS-3079](https://linear.app/affine-design/issue/BS-3079).
- Separate the create session logic from the `createMessage function`.
- Ensure the session is created before executing any chat or actions.
- Convert the `AIActions` into asynchronous functions.
- Transfer the update prompt name logic to the chat action.
- Introduce a networkSearch field in `AITextActionOptions`.
- Eliminate the redundant `LAST_ROOT_SESSION_ID`.
Close [BS-2758](https://linear.app/affine-design/issue/BS-2758).
Support [BS-2583](https://linear.app/affine-design/issue/BS-2583).
### What changed?
- Extend `ChatPanelInput` and `ChatBlockInput` from the same abstract class `AIChatInput` to reduce duplication of code.
- Unify the context interface of `chat-panel` and `chat-block`.
- Rename `items` field to `messages`.
- Remove duplicated type declare.
Support [BS-2583](https://linear.app/affine-design/issue/BS-2583).
### What changed?
- Move chat panel chip components to `/components` folder.
- Separate `chips` and `embeddingProgress` from ChatContextValue.
### Why make this change?
Seperate front end timeout errors from server side errors.
### What changed?
- Add `RequestTimeoutError` which extends from `BaseAIError`.
- Track as `request timeout` instead of `server error`.
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.
Close [BS-2834](https://linear.app/affine-design/issue/BS-2834).
### What Changed?
- Add `addContextCategoryMutation` and `removeContextCategoryMutation` graphql apis.
- Provide tag and collection apis for front-end components.
Close [BS-2850](https://linear.app/affine-design/issue/BS-2850).
### What Changed?
- After flattening the search results, filter the current document.
- Remove duplicate results based on document id.
Close [BS-2791](https://linear.app/affine-design/issue/BS-2791).
### What Changed?
- Add status filed to `CopilotContextDoc` to querying document embedding processing progress.
- Change `ChipState` from `success` to `finished` to better align with backend server status.
- Add `pollContextDocsAndFiles` API for embedding status polling.
### About Polling
- Set the minimum interval to 1 second and the maximum interval to 30 seconds
- Use exponential backoff and increase the interval by 50% after each poll
- Make sure the interval does not exceed the maximum
Close [BS-2751](https://linear.app/affine-design/issue/BS-2751).
### What Changed?
- Do not send AI gql request when chat-panel is not open.
- When the chat-panel width is greater than 540px, adjust the padding to 24px.
- Optimize the display and hide logic of scroll to end button.
Why make this fix?
The network search flag is saved locally. If the user opens multiple clients, the local status and server status may be inconsistent.
Fix issue [AF-2252](https://linear.app/affine-design/issue/AF-2252).
## What Changed?
- Remove useless `generateAnswer` configuration for inline ask ai
- Refactor the common `updateAIPanelConfig` function
- Use empty string instead of meaningless `placeholder` string
- Remove unnecessary high-order function wrappers
Fix issue [BS-2522](https://linear.app/affine-design/issue/BS-2522).
### Why make this change?
If the user data contains illegal content, carrying the user data in the system prompt will run the risk of having the account banned.
### What Changed?
- Move the `Context Documents` to the user prompt.
- Add `withPrompt` in `QueryChatHistoriesInput` options.
- Get chat histories without prompt messages.
- Omit document context when saving messages to the `aiSessionMessage` db.
akumatus
