Preserve the temporal order of text and tool calls in Claude Code mode.
Previously, all text was concatenated together and shown before all tool
cards, losing the interleaving of the original response stream.
Now uses an ordered contentSegments array to track content in arrival
order, ensuring text after tool calls displays below the tool cards.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Replace FlexSearch with MiniSearch for improved search functionality and scoring
* Enhance QueryExpander and README for improved recall and ranking clarity
- Update QueryExpander to clearly separate salient and expanded terms for recall and ranking.
- Modify README to reflect changes in the search system's architecture and clarify the distinction between recall and ranking processes.
- Adjust FullTextEngine comments to emphasize BM25's native multi-term scoring capabilities.
* Implement weighted query expansion in FullTextEngine with 90/10 scoring for salient and expanded terms
Added <path> tag to variable_note XML format for {activeNote} and other variable types. Reordered format so path comes before title heading to match note_context structure. Updated all test expectations to reflect the new format.
This change ensures the LLM receives file path information when processing variable notes, enabling better context understanding and file reference capabilities. The consistent format with note_context also improves maintainability.
* Deprecate IntentAnalyzer and replace with model-based tool planning in CopilotPlusChainRunner
* Refine planning prompt to enforce XML-only responses and remove note extraction logic
- Added an optional `confirmation` parameter to the `writeToFile` tool, allowing users to skip the preview UI and apply changes directly to the file.
- Updated the tool's schema to include the new parameter, with a default value of true for confirmation.
- Enhanced the handler logic to manage file writing based on the user's confirmation choice, improving flexibility in file operations.
Improves AWS Bedrock support by adding user guidance for cross-region
inference profiles, addressing issue #2006.
Changes:
- ModelAddDialog: Add helper text and example for Bedrock inference profiles
- ModelEditDialog: Update region field description with shorter text
- CLAUDE.md: Add AWS Bedrock usage documentation with examples
Users are now guided to use cross-region inference profile IDs
(global., us., eu., apac. prefixes) instead of regional model IDs,
which significantly improves reliability and availability.
Fixes: logancyang/obsidian-copilot#2006🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* refactor: Simplify local search guidance handling in AutonomousAgentChainRunner and CopilotPlusChainRunner
- Removed the `appendInlineCitationReminder` function and adjusted the logic in `AutonomousAgentChainRunner` to directly manage local search guidance.
- Updated `CopilotPlusChainRunner` to retain and utilize the most recent local search guidance, ensuring it is positioned correctly adjacent to user queries.
- Modified `buildLocalSearchInnerContent` to accept introductory text instead of guidance, enhancing clarity in the payload structure.
- Removed related tests for the deprecated `appendInlineCitationReminder` function, streamlining the codebase.
* refactor: Enhance localSearch payload structure and guidance handling
- Made localSearch payload self-contained by embedding RAG instructions, documents, and citation guidance directly within the `<localSearch>` block.
- Updated AutonomousAgentChainRunner and CopilotPlusChainRunner to ensure each localSearch call carries its own guidance block, improving citation accuracy in multi-search scenarios.
- Introduced a new utility function to insert guidance before the user query label, ensuring clarity in the payload structure.
- Adjusted related tests to validate the new guidance handling logic.
* docs: Add deprecation guide for IntentAnalyzer and Broca
- Created a comprehensive document outlining the responsibilities of the `IntentAnalyzer` and Broca API within the Copilot Plus intent analysis flow.
- Detailed the current functionalities, known consumers, migration constraints, and a phased migration plan to ensure feature parity and smooth transition.
- Highlighted risks and mitigation strategies associated with the deprecation process, along with open questions for further consideration.
* fix: Prevent infinite rolling animation in ToolCallBanner when result is present
Add defensive check that stops animation when tool result exists, even if isExecuting flag wasn't updated. This fixes race conditions where marker updates fail or are delayed during streaming.
🤖 Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>
- Introduced `escapeTasksCodeBlocks` to convert ```tasks to ```text, preventing execution in AI responses and ensuring static display of task queries.
- Updated processing logic to utilize the new function, enhancing content safety and display consistency.
* Update bug report template to enhance clarity and requirements
- Changed the required checklist item from a screenshot to a log file generated via the "Copilot: Create Log File" command.
- Made the screenshot of the note and Copilot chat pane optional.
- Clarified the statement regarding bug report requirements for better understanding.
* feat: Implement embedded note processing in ContextProcessor
- Added support for processing embedded notes within markdown content, allowing for structured `<embedded_note>` blocks.
- Introduced new methods for building and formatting embedded note blocks, including error handling for missing notes.
- Enhanced logging to replace console statements with appropriate logging functions for better error tracking.
- Updated the `buildMarkdownContextContent` method to streamline content processing for markdown files.
- Added a new constant `EMBEDDED_NOTE_TAG` to manage embedded note structures.
- Introduced a new utility function `escapeYamlString` to handle escaping of special characters in modelKey values, ensuring valid YAML formatting.
- Updated the `modelKey` assignment in the generated note content to use the new escaping function.
- Added comprehensive tests to verify correct escaping for various special characters, including quotes, backslashes, and pipes, ensuring data integrity during save-load operations.
* feat: Implement model validation and resolution for temperature overrides in ChatModelManager
- Added a new private method `isModelConfigValid` to validate model configurations against API key and entitlement requirements.
- Introduced `resolveModelForTemperatureOverride` to determine the active chat model, ensuring fallback to valid models while respecting user entitlements.
- Updated `getChatModelWithTemperature` to utilize the new model resolution logic for temperature overrides.
- Enhanced error handling for cases where no valid model is found.
* refactor: Remove deprecated chat models from BUILTIN_CHAT_MODELS constant
* feat: Add GROK_4_FAST model to BUILTIN_CHAT_MODELS constant
- Introduced a new chat model, GROK_4_FAST, with capabilities for vision and enabled status, enhancing the available options for users.
* Make inline citation permanent and add image guide for local search
- Removed the `enableInlineCitations` setting from the configuration and related components to simplify citation management.
- Updated citation functions to operate without the setting, ensuring consistent behavior across the codebase.
- Adjusted tests and documentation to reflect the removal of inline citation handling logic.
- Enhanced the `renderCiCMessage` and `processInlineCitations` functions for improved clarity and functionality.
* fix: Update web search tool description for clarity
- Revised the description of the `webSearch` tool to specify that it searches the internet for information only when explicitly requested by the user.
- Enhanced the instructions for using the `webSearch` tool to clarify when it should be utilized, ensuring users understand the intent required for web searches.
- Reintroduced the `createGetTagListTool` import to maintain functionality in the `builtinTools` module.
* fix: Enhance response handling in AgentPrompt integration tests
- Updated the response processing logic in the AgentPrompt integration tests to ensure that `fullResponse` is always a string, accommodating multimodal and array content.
- Implemented a function to extract text parts from arrays and handle various content types, improving the robustness of the tests.
* Remove websearch related prompt from modelAdapter
* fix: Update time query instructions in builtinTools
- Added detailed instructions for handling time queries, including the conversion of city or timezone names to UTC offsets.
- Clarified when to use the timezoneOffset parameter and emphasized the need for user clarification if the offset cannot be determined.
- Introduced a small delay using setTimeout to ensure the React component is fully ready to receive focus events when the chat window is opened. This change addresses potential timing issues with the focus event handling.
- Introduced a wrapper function `handleFocusRegistration` to properly set the focus function state, avoiding issues with React's updater function interpretation.
- Updated the `FocusPlugin` to utilize the new focus registration method for better clarity and functionality.
- Updated `ensureInitialized` method in `LogFileManager` to start with an empty buffer, removing unnecessary file reading logic.
- Integrated log clearing functionality in `handleNewChat` to ensure a fresh start for each chat session.
- Changed the safe filename byte limit from 200 to 100 bytes to ensure compliance with filesystem constraints.
- Implemented fallback logic for filenames when encountering ENAMETOOLONG errors, allowing for minimal filenames with project prefixes.
- Added tests to verify the new fallback behavior and ensure proper handling of filenames with Cyrillic and mixed Unicode text.
- Enhanced error handling to update existing files when conflicts arise during save operations.
- Introduced `INTEGRITY_CHECK_YIELD_INTERVAL` to improve the performance of the integrity check process by yielding control to the event loop at specified intervals, preventing UI freezing during long-running checks.
- Refactored the loop for checking file embeddings to utilize an index-based approach, allowing for periodic yielding.
- Added a new private method `yieldToEventLoop` to handle yielding control, ensuring a responsive user interface during operations that may take significant time.
- Updated documentation to include a description of the new yielding mechanism for better clarity on its purpose and functionality.
* Integrate ProjectChainRunner and ChatManager with new layered context
- Introduced `ProjectChainRunner` to automatically include project context in L1 via `ChatManager.getSystemPromptForMessage()`, simplifying the class structure by inheriting behavior from `CopilotPlusChainRunner`.
- Updated `ChatManager` to build system prompts that append project context when in project mode, ensuring seamless integration without special-case logic.
- Implemented null guards for project context to prevent erroneous output when context is unavailable.
- Refactored documentation to reflect changes in context handling and the new project chain runner functionality.
* Enhance ChatManager tests with project context mocks
- Added mocks for project context retrieval and system prompt settings in `ChatManager.test.ts` to facilitate testing without relying on actual project data.
- Improved test coverage for context-related functionalities by simulating project context and system prompt retrieval, ensuring robust testing of the ChatManager's behavior in various scenarios.
* Implement context engine for a layered context
* Wire in new context library to LLM chain
- Updated the context engine to maintain a cumulative library of all context items (L2) without deduplication, enhancing cache stability.
- Introduced smart referencing in the user message (L3) to reference existing items in L2 by ID and include full content for new items.
- Improved the LayerToMessagesConverter to format and handle layered context envelopes for better debugging and clarity.
- Fixed critical bugs related to context deduplication that previously broke cache stability.
- Enhanced tests to validate the new context handling and ensure proper functionality across various scenarios.
* Enhance VaultQAChainRunner with tag extraction and inline citation detection
- Integrated tag extraction from user queries to improve context-aware retrieval.
- Implemented `hasInlineCitations` function to detect inline citation markers in responses.
- Updated message construction logic to utilize envelope-based context, enhancing the quality of AI interactions.
- Added comprehensive tests for the new inline citation detection functionality, ensuring robustness and accuracy.
- Improved logging for better debugging and traceability of the message processing flow.
Refactor VaultQAChainRunner to enhance context handling and citation instructions
- Integrated LayerToMessagesConverter for improved message construction, ensuring smart referencing and context preservation.
- Updated logging to reflect the use of the new converter in envelope-based context construction.
- Revised comments for clarity on context preparation and citation instructions.
- Minor adjustment in citation utility to improve regex handling for citation updates.
* Complete migration to envelope-based context in CopilotPlus and LLM chain runners
- Removed all legacy fallback paths, ensuring that context envelopes are now mandatory for operations in CopilotPlusChainRunner and LLMChainRunner.
- Enhanced image extraction to only pull from the active note, preventing unintended leaks from attached context notes.
- Fixed critical issues with context-in-context (CiC) formatting and added early envelope guards in VaultQAChainRunner to prevent silent failures.
- Updated message construction logic to utilize LayerToMessagesConverter for improved smart referencing and context preservation.
- Comprehensive tests added to validate the new envelope-based context handling and ensure robustness across all chain runners.
* Integrate Plus chain with context envelope
* Enhance AutonomousAgentChainRunner with envelope-based context integration
- Introduced `LayerToMessagesConverter` for improved message construction, ensuring system and user messages are derived from the context envelope.
- Implemented envelope validation to ensure context is available before processing.
- Updated message preparation logic to maintain consistency with the envelope-first architecture, preserving tool execution and multimodal support.
- Added comprehensive logging for envelope-based context construction to aid debugging.
- Documented changes in the context engineering documentation to reflect the new integration and design points.
* Support loading saved chat context to L2 context library
* Fix ChatPersistenceManager tests for context handling
* Prompt Improvement: Use getFileTree to explore ambiguous notes and folders.
* MInor
* fix: Clarify instructions for using getFileTree in note retrieval process
