- Introduced a new Simple Query Service to streamline basic AI queries, allowing for structured JSON outputs.
- Updated existing routes to utilize the new service, replacing direct SDK calls with a unified interface for querying.
- Enhanced provider handling in various routes, including generate-spec, generate-features-from-spec, and validate-issue, to support both Claude and Cursor models seamlessly.
- Added structured output support for improved response handling and error management across the application.
* memory
* feat: add smart memory selection with task context
- Add taskContext parameter to loadContextFiles for intelligent file selection
- Memory files are scored based on tag matching with task keywords
- Category name matching (e.g., "terminals" matches terminals.md) with 4x weight
- Usage statistics influence scoring (files that helped before rank higher)
- Limit to top 5 files + always include gotchas.md
- Auto-mode passes feature title/description as context
- Chat sessions pass user message as context
This prevents loading 40+ memory files and killing context limits.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: enhance auto-mode service and context loader
- Improved context loading by adding task context for better memory selection.
- Updated JSON parsing logic to handle various formats and ensure robust error handling.
- Introduced file locking mechanisms to prevent race conditions during memory file updates.
- Enhanced metadata handling in memory files, including validation and sanitization.
- Refactored scoring logic for context files to improve selection accuracy based on task relevance.
These changes optimize memory file management and enhance the overall performance of the auto-mode service.
* refactor: enhance learning extraction and formatting in auto-mode service
- Improved the learning extraction process by refining the user prompt to focus on meaningful insights and structured JSON output.
- Updated the LearningEntry interface to include additional context fields for better documentation of decisions and patterns.
- Enhanced the formatLearning function to adopt an Architecture Decision Record (ADR) style, providing richer context for recorded learnings.
- Added detailed logging for better traceability during the learning extraction and appending processes.
These changes aim to improve the quality and clarity of learnings captured during the auto-mode service's operation.
* feat: integrate stripProviderPrefix utility for model ID handling
- Added stripProviderPrefix utility to various routes to ensure providers receive bare model IDs.
- Updated model references in executeQuery calls across multiple files, enhancing consistency in model ID handling.
- Introduced memoryExtractionModel in settings for improved learning extraction tasks.
These changes streamline the model ID processing and enhance the overall functionality of the provider interactions.
* feat: enhance error handling and server offline management in board actions
- Improved error handling in the handleRunFeature and handleStartImplementation functions to throw errors for better caller management.
- Integrated connection error detection and server offline handling, redirecting users to the login page when the server is unreachable.
- Updated follow-up feature logic to include rollback mechanisms and improved user feedback for error scenarios.
These changes enhance the robustness of the board actions by ensuring proper error management and user experience during server connectivity issues.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: webdevcody <webdevcody@gmail.com>
- Updated the generateSuggestions function to accept model and thinking level overrides, allowing for more flexible suggestion generation.
- Modified the API client and UI components to support passing these new parameters, improving user control over the suggestion process.
- Introduced a new phase model for AI Suggestions in settings, enhancing the overall functionality and user experience.
- Introduced a new function, buildThinkingOptions, to handle the conversion of ThinkingLevel to maxThinkingTokens for the Claude SDK.
- Updated existing SDK option creation functions to incorporate thinking options, ensuring that maxThinkingTokens are included based on the specified thinking level.
- Enhanced the settings service to support migration of phase models to include thinking levels, improving compatibility with new configurations.
- Added comprehensive tests for thinking level integration and migration logic, ensuring robust functionality across the application.
This update significantly improves the SDK's configurability and performance by allowing for more nuanced control over reasoning capabilities.
- Add handler for type=result messages in Cursor stream processing
- Cursor provider sends final accumulated text in msg.result
- Suggestions was only handling assistant messages for Cursor
- Add detailed logging for result extraction (like backlog plan)
- Matches pattern used by github validation and backlog plan
This fixes potential parsing issues when using Cursor models
for feature suggestions, ensuring the complete response text
is captured before JSON parsing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Cursor was writing JSON to files instead of returning it in the response.
Added clear instructions to all Cursor prompts:
1. DO NOT write any files
2. Return ONLY raw JSON in the response
3. No explanations, no markdown, just JSON
Affected routes:
- generate-spec.ts
- generate-features-from-spec.ts
- validate-issue.ts
- generate-suggestions.ts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a readOnly option to ExecuteOptions that controls whether the
Cursor CLI runs with --force flag (allows edits) or without (suggest-only).
Read-only routes now pass readOnly: true:
- generate-spec.ts, generate-features-from-spec.ts (we write files ourselves)
- validate-issue.ts, generate-suggestions.ts (analysis only)
- describe-file.ts, describe-image.ts (description only)
- generate-plan.ts, enhance.ts (text generation only)
Routes that implement features (auto-mode-service, agent-service) keep
the default (readOnly: false) to allow file modifications.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Created libs/server/src/lib/json-extractor.ts with reusable JSON
extraction utilities for parsing AI responses:
- extractJson<T>(): Multi-strategy JSON extraction
- extractJsonWithKey<T>(): Extract with required key validation
- extractJsonWithArray<T>(): Extract with array property validation
Strategies (tried in order):
1. JSON in ```json code block
2. JSON in ``` code block
3. Find JSON object by matching braces (with optional required key)
4. Find any JSON object by matching braces
5. First { to last }
6. Parse entire response
Updated:
- generate-suggestions.ts: Use extractJsonWithArray('suggestions')
- validate-issue.ts: Use extractJson()
Both files now use the shared utility instead of local implementations,
following DRY principle.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Cursor responses may include text after the JSON object, causing
JSON.parse to fail. Added multi-strategy extraction similar to
validate-issue.ts:
1. Try extracting from ```json code block
2. Try extracting from ``` code block
3. Try finding {"suggestions" and matching braces
4. Try finding any JSON object with suggestions array
Uses bracket counting to find the correct closing brace.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The suggestions generation route (Feature Enhancement in UI) was not
reading from phaseModels settings and always used the default haiku model.
Changes:
- Read enhancementModel from phaseModels settings
- Add provider routing for Cursor vs Claude models
- Pass model to createSuggestionsOptions for Claude SDK
- For Cursor, include JSON schema in prompt and use ProviderFactory
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated API routes to accept an optional settings service for loading the autoLoadClaudeMd setting.
- Introduced a new settings helper utility for retrieving project-specific settings.
- Enhanced feature generation and spec generation processes to utilize the autoLoadClaudeMd setting.
- Refactored relevant route handlers to support the new settings integration across various endpoints.
- Updated 150+ files to import from @automaker/* packages
- Server imports now use @automaker/utils, @automaker/platform, @automaker/types, @automaker/model-resolver, @automaker/dependency-resolver, @automaker/git-utils
- UI imports now use @automaker/dependency-resolver and @automaker/types
- Deleted duplicate dependency-resolver files (222 lines eliminated)
- Updated dependency-resolver to use ES modules for Vite compatibility
- Added type annotation fix in auto-mode-service.ts
- Updated feature-loader to re-export Feature type from @automaker/types
- Both server and UI builds successfully verified
Phase 1 of server refactoring complete.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Updated MAX_TURNS to allow for more iterations in suggestion generation: quick (5 to 50), standard (20 to 100), and extended (50 to 250).
- Introduced a JSON schema for structured output in suggestions, improving the format and consistency of generated suggestions.
- Modified the generateSuggestions function to utilize structured output when available, with a fallback to text parsing for compatibility.
This enhances the suggestion generation process, allowing for more thorough exploration and better output formatting.
- Added a new ProjectSetupDialog component to facilitate project specification generation, enhancing user experience by guiding users through project setup.
- Refactored the Sidebar component to integrate the new ProjectSetupDialog, replacing the previous inline dialog implementation for improved code organization and maintainability.
- Updated the sidebar to handle project overview and feature generation options, streamlining the project setup process.
- Removed the old dialog implementation from the Sidebar, reducing code duplication and improving clarity.
- Added error logging for failed JSON parsing in the suggestions generation route to improve debugging capabilities.
- This change ensures that any parsing errors are captured and logged, aiding in the identification of issues with AI response handling.
