Resolves persistent 404 'Not Found' errors when calling Anthropic models via the Vercel AI SDK. The primary issue was likely related to incorrect or missing API headers.
- Refactors Anthropic provider (src/ai-providers/anthropic.js) to use the standard 'anthropic-version' header instead of potentially outdated/incorrect beta headers when creating the client instance.
- Updates the default fallback model ID in .taskmasterconfig to 'claude-3-5-sonnet-20241022'.
- Fixes the interactive model setup (task-master models --setup) in scripts/modules/commands.js to correctly filter and default the main model selection.
- Improves the cost display in the 'task-master models' command output to explicitly show 'Free' for models with zero cost.
- Updates description for the 'id' parameter in the 'set_task_status' MCP tool definition for clarity.
- Updates list of models and costs
This commit implements several related improvements to the models command and configuration system:
- Added MCP support for the models command:
- Created new direct function implementation in models.js
- Registered modelsDirect in task-master-core.js for proper export
- Added models tool registration in tools/index.js
- Ensured project name replacement when copying .taskmasterconfig in init.js
- Improved .taskmasterconfig copying during project initialization:
- Added copyTemplateFile() call in createProjectStructure()
- Ensured project name is properly replaced in the config
- Restructured tool registration in logical workflow groups:
- Organized registration into 6 functional categories
- Improved command ordering to follow typical workflow
- Added clear group comments for maintainability
- Enhanced documentation in cursor rules:
- Updated dev_workflow.mdc with clearer config management instructions
- Added comprehensive models command reference to taskmaster.mdc
- Clarified CLI vs MCP usage patterns and options
- Added warning against manual .taskmasterconfig editing
- Unified Service: Introduced 'scripts/modules/ai-services-unified.js' to centralize AI interactions using provider modules ('src/ai-providers/') and the Vercel AI SDK.
- Provider Modules: Implemented 'anthropic.js' and 'perplexity.js' wrappers for Vercel SDK.
- 'updateSubtaskById' Fix: Refactored the AI call within 'updateSubtaskById' to use 'generateTextService' from the unified layer, resolving runtime errors related to parameter passing and streaming. This serves as the pattern for refactoring other AI calls in 'scripts/modules/task-manager/'.
- Task Status: Marked Subtask 61.19 as 'done'.
- Rules: Added new 'ai-services.mdc' rule.
This centralizes AI logic, replacing previous direct SDK calls and custom implementations. API keys are resolved via 'resolveEnvVariable' within the service layer. The refactoring of 'updateSubtaskById' establishes the standard approach for migrating other AI-dependent functions in the task manager module to use the unified service.
Relates to Task 61.
This commit centralizes configuration and environment variable access across various modules by consistently utilizing getters from scripts/modules/config-manager.js. This replaces direct access to process.env and the global CONFIG object, leading to improved consistency, maintainability, testability, and better handling of session-specific configurations within the MCP context.
Key changes include:
- Centralized Getters: Replaced numerous instances of process.env.* and CONFIG.* with corresponding getter functions (e.g., getLogLevel, getMainModelId, getResearchMaxTokens, getMainTemperature, isApiKeySet, getDebugFlag, getDefaultSubtasks).
- Session Awareness: Ensured that the session object is passed to config getters where necessary, particularly within AI service calls (ai-services.js, add-task.js) and error handling (ai-services.js), allowing for session-specific environment overrides.
- API Key Checks: Standardized API key availability checks using isApiKeySet() instead of directly checking process.env.* (e.g., for Perplexity in commands.js and ai-services.js).
- Client Instantiation Cleanup: Removed now-redundant/obsolete local client instantiation functions (getAnthropicClient, getPerplexityClient) from ai-services.js and the global Anthropic client initialization from dependency-manager.js. Client creation should now rely on the config manager and factory patterns.
- Consistent Debug Flag Usage: Standardized calls to getDebugFlag() in commands.js, removing potentially unnecessary null arguments.
- Accurate Progress Calculation: Updated AI stream progress reporting (ai-services.js, add-task.js) to use getMainMaxTokens(session) for more accurate calculations.
- Minor Cleanup: Removed unused import from scripts/modules/commands.js.
Specific module updates:
- :
- Uses getLogLevel() instead of process.env.LOG_LEVEL.
- :
- Replaced direct env/config access for model IDs, tokens, temperature, API keys, and default subtasks with appropriate getters.
- Passed session to handleClaudeError.
- Removed local getPerplexityClient and getAnthropicClient functions.
- Updated progress calculations to use getMainMaxTokens(session).
- :
- Uses isApiKeySet('perplexity') for API key checks.
- Uses getDebugFlag() consistently for debug checks.
- Removed unused import.
- :
- Removed global Anthropic client initialization.
- :
- Uses config getters (getResearch..., getMain...) for Perplexity and Claude API call parameters, preserving customEnv override logic.
This refactoring also resolves a potential SyntaxError: Identifier 'getPerplexityClient' has already been declared by removing the duplicated/obsolete function definition previously present in ai-services.js.
This commit focuses on standardizing configuration and API key access patterns across key modules as part of subtask 61.34.
Key changes include:
- Refactored `ai-services.js` to remove global AI clients and use `resolveEnvVariable` for API key checks. Client instantiation now relies on `getAnthropicClient`/`getPerplexityClient` accepting a session object.
- Refactored `task-manager.js` (`analyzeTaskComplexity` function) to use the unified `generateTextService` from `ai-services-unified.js`, removing direct AI client calls.
- Replaced direct `process.env` access for model parameters and other configurations (`PERPLEXITY_MODEL`, `CONFIG.*`) in `task-manager.js` with calls to the appropriate getters from `config-manager.js` (e.g., `getResearchModelId(session)`, `getMainMaxTokens(session)`).
- Ensured `utils.js` (`resolveEnvVariable`) correctly handles potentially undefined session objects.
- Updated function signatures where necessary to propagate the `session` object for correct context-aware configuration/key retrieval.
This moves towards the goal of using `ai-client-factory.js` and `ai-services-unified.js` as the standard pattern for AI interactions and centralizing configuration management through `config-manager.js`.
