Compare commits

..

29 Commits

Author SHA1 Message Date
Ralph Khreish
d31ef7a39c Merge pull request #1015 from eyaltoledano/changeset-release/main
Version Packages
2025-07-20 00:57:39 +03:00
github-actions[bot]
66555099ca Version Packages 2025-07-19 21:56:03 +00:00
Ralph Khreish
1e565eab53 Release 0.21 (#1009)
* fix: prevent CLAUDE.md overwrite by using imports (#949)

* fix: prevent CLAUDE.md overwrite by using imports

- Copy Task Master instructions to .taskmaster/CLAUDE.md
- Add import section to user's CLAUDE.md instead of overwriting
- Preserve existing user content
- Clean removal of Task Master content on uninstall

Closes #929

* chore: add changeset for Claude import fix

* fix: task master (tm) custom slash commands w/ proper syntax (#968)

* feat: add task master (tm) custom slash commands

Add comprehensive task management system integration via custom slash commands.
Includes commands for:
- Project initialization and setup
- Task parsing from PRD documents
- Task creation, update, and removal
- Subtask management
- Dependency tracking and validation
- Complexity analysis and task expansion
- Project status and reporting
- Workflow automation

This provides a complete task management workflow directly within Claude Code.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* chore: add changeset

---------

Co-authored-by: neno-is-ooo <204701868+neno-is-ooo@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>

* chore: create extension scaffolding (#989)

* chore: create extension scaffolding

* chore: fix workspace for changeset

* chore: fix package-lock

* feat(profiles): Add MCP configuration to Claude Code rules (#980)

* add .mcp.json with claude profile

* add changeset

* update changeset

* update test

* fix: show command no longer requires complexity report to exist (#979)

Co-authored-by: Ben Vargas <ben@example.com>

* feat: complete Groq provider integration and add Kimi K2 model (#978)

* feat: complete Groq provider integration and add Kimi K2 model

- Add missing getRequiredApiKeyName() method to GroqProvider class
- Register GroqProvider in ai-services-unified.js PROVIDERS object
- Add Groq API key handling to config-manager.js (isApiKeySet and getMcpApiKeyStatus)
- Add GROQ_API_KEY to env.example with format hint
- Add moonshotai/kimi-k2-instruct model to Groq provider ($1/$3 per 1M tokens, 16k max)
- Fix import sorting for linting compliance
- Add GroqProvider mock to ai-services-unified tests

Fixes missing implementation pieces that prevented Groq provider from working.

* chore: improve changeset

---------

Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>

* docs: Auto-update and format models.md

* feat: Add Amp rule profile with AGENT.md and MCP config (#973)

* Amp profile + tests

* generatlize to Agent instead of Claude Code to support any agent

* add changeset

* unnecessary tab formatting

* fix exports

* fix formatting

* feat: Add Zed editor rule profile with agent rules and MCP config (#974)

* zed profile

* add changeset

* update changeset

* fix: Add missing API keys to .env.example and README.md (#972)

* add OLLAMA_API_KEY

* add missing API keys

* add changeset

* update keys and fix OpenAI comment

* chore: create extension scaffolding (#989)

* chore: create extension scaffolding

* chore: fix workspace for changeset

* chore: fix package-lock

* feat(profiles): Add MCP configuration to Claude Code rules (#980)

* add .mcp.json with claude profile

* add changeset

* update changeset

* update test

* fix: show command no longer requires complexity report to exist (#979)

Co-authored-by: Ben Vargas <ben@example.com>

* feat: complete Groq provider integration and add Kimi K2 model (#978)

* feat: complete Groq provider integration and add Kimi K2 model

- Add missing getRequiredApiKeyName() method to GroqProvider class
- Register GroqProvider in ai-services-unified.js PROVIDERS object
- Add Groq API key handling to config-manager.js (isApiKeySet and getMcpApiKeyStatus)
- Add GROQ_API_KEY to env.example with format hint
- Add moonshotai/kimi-k2-instruct model to Groq provider ($1/$3 per 1M tokens, 16k max)
- Fix import sorting for linting compliance
- Add GroqProvider mock to ai-services-unified tests

Fixes missing implementation pieces that prevented Groq provider from working.

* chore: improve changeset

---------

Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>

* docs: Auto-update and format models.md

* feat: Add Amp rule profile with AGENT.md and MCP config (#973)

* Amp profile + tests

* generatlize to Agent instead of Claude Code to support any agent

* add changeset

* unnecessary tab formatting

* fix exports

* fix formatting

* feat: Add Zed editor rule profile with agent rules and MCP config (#974)

* zed profile

* add changeset

* update changeset

---------

Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: Ben Vargas <ben@vargas.com>
Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* feat: Add OpenCode rule profile with AGENTS.md and MCP config (#970)

* add opencode to profile lists

* add opencode profile / modify mcp config after add

* add changeset

* not necessary; main config being updated

* add issue link

* add/fix tests

* fix url and docsUrl

* update test for new urls

* fix formatting

* update/fix tests

* chore: add coderabbit configuration (#992)

* chore: add coderabbit configuration

* chore: fix coderabbit config

* chore: improve coderabbit config

* chore: more coderabbit reviews

* chore: remove all defaults

* docs: Update MCP server name for consistency and use 'Add to Cursor' button (#995)

* update MCP server name to task-master-ai for consistency

* add changeset

* update cursor link & switch to https

* switch back to Add to Cursor button (https link)

* update changeset

* update changeset

* update changeset

* update changeset

* use GitHub markdown format

* fix(ai-validation): comprehensive fixes for AI response validation issues (#1000)

* fix(ai-validation): comprehensive fixes for AI response validation issues

  - Fix update command validation when AI omits subtasks/status/dependencies
  - Fix add-task command when AI returns non-string details field
  - Fix update-task command when AI subtasks miss required fields
  - Add preprocessing to ensure proper field types before validation
  - Prevent split() errors on non-string fields
  - Set proper defaults for missing required fields

* chore: run format

* chore: implement coderabbit suggestions

* feat: add kiro profile (#1001)

* feat: add kiro profile

* chore: fix format

* chore: implement requested changes

* chore: fix CI

* refactor: remove unused resource and resource template initialization (#1002)

* refactor: remove unused resource and resource template initialization

* chore: implement requested changes

* fix(core): Implement Boundary-First Tag Resolution (#943)

* refactor(context): Standardize tag and projectRoot handling across all task tools

This commit unifies context management by adopting a boundary-first resolution strategy. All task-scoped tools now resolve `tag` and `projectRoot` at their entry point and forward these values to the underlying direct functions.

This approach centralizes context logic, ensuring consistent behavior and enhanced flexibility in multi-tag environments.

* fix(tag): Clean up tag handling in task functions and sync process

This commit refines the handling of the `tag` parameter across multiple functions, ensuring consistent context management. The `tag` is now passed more efficiently in `listTasksDirect`, `setTaskStatusDirect`, and `syncTasksToReadme`, improving clarity and reducing redundancy. Additionally, a TODO comment has been added in `sync-readme.js` to address future tag support enhancements.

* feat(tag): Implement Boundary-First Tag Resolution for consistent tag handling

This commit introduces Boundary-First Tag Resolution in the task manager, ensuring consistent and deterministic tag handling across CLI and MCP. This change resolves potential race conditions and improves the reliability of tag-specific operations.

Additionally, the `expandTask` function has been updated to use the resolved tag when writing JSON, enhancing data integrity during task updates.

* chore(biome): formatting

* fix(expand-task): Update writeJSON call to use tag instead of resolvedTag

* fix(commands): Enhance complexity report path resolution and task initialization
`resolveComplexityReportPath` function to streamline output path generation based on tag context and user-defined output.
- Improved clarity and maintainability of command handling by centralizing path resolution logic.

* Fix: unknown currentTag

* fix(task-manager): Update generateTaskFiles calls to include tag and projectRoot parameters

This commit modifies the `moveTask` and `updateSubtaskById` functions to pass the `tag` and `projectRoot` parameters to the `generateTaskFiles` function. This ensures that task files are generated with the correct context when requested, enhancing consistency in task management operations.

* fix(commands): Refactor tag handling and complexity report path resolution
This commit updates the `registerCommands` function to utilize `taskMaster.getCurrentTag()` for consistent tag retrieval across command actions. It also enhances the initialization of `TaskMaster` by passing the tag directly, improving clarity and maintainability. The complexity report path resolution is streamlined to ensure correct file naming based on the current tag context.

* fix(task-master): Update complexity report path expectations in tests
This commit modifies the `initTaskMaster` test to expect a valid string for the complexity report path, ensuring it matches the expected file naming convention. This change enhances test reliability by verifying the correct output format when the path is generated.

* fix(set-task-status): Enhance logging and tag resolution in task status updates
This commit improves the logging output in the `registerSetTaskStatusTool` function to include the tag context when setting task statuses. It also updates the tag handling by resolving the tag using the `resolveTag` utility, ensuring that the correct tag is used when updating task statuses. Additionally, the `setTaskStatus` function is modified to remove the tag parameter from the `readJSON` and `writeJSON` calls, streamlining the data handling process.

* fix(commands, expand-task, task-manager): Add complexity report option and enhance path handling
This commit introduces a new `--complexity-report` option in the `registerCommands` function, allowing users to specify a custom path for the complexity report. The `expandTask` function is updated to accept the `complexityReportPath` from the context, ensuring it is utilized correctly during task expansion. Additionally, the `setTaskStatus` function now includes the `tag` parameter in the `readJSON` and `writeJSON` calls, improving task status updates with proper context. The `initTaskMaster` function is also modified to create parent directories for output paths, enhancing file handling robustness.

* fix(expand-task): Add complexityReportPath to context for task expansion tests

This commit updates the test for the `expandTask` function by adding the `complexityReportPath` to the context object. This change ensures that the complexity report path is correctly utilized in the test, aligning with recent enhancements to complexity report handling in the task manager.

* chore: implement suggested changes

* fix(parse-prd): Clarify tag parameter description for task organization
Updated the documentation for the `tag` parameter in the `parse-prd.js` file to provide a clearer context on its purpose for organizing tasks into separate task lists.

* Fix Inconsistent tag resolution pattern.

* fix: Enhance complexity report path handling with tag support

This commit updates various functions to incorporate the `tag` parameter when resolving complexity report paths. The `expandTaskDirect`, `resolveComplexityReportPath`, and related tools now utilize the current tag context, improving consistency in task management. Additionally, the complexity report path is now correctly passed through the context in the `expand-task` and `set-task-status` tools, ensuring accurate report retrieval based on the active tag.

* Updated the JSDoc for the `tag` parameter in the `show-task.js` file.

* Remove redundant comment on tag parameter in readJSON call

* Remove unused import for getTagAwareFilePath

* Add missed complexityReportPath to args for task expansion

* fix(tests): Enhance research tests with tag-aware functionality

This commit updates the `research.test.js` file to improve the testing of the `performResearch` function by incorporating tag-aware functionality. Key changes include mocking the `findProjectRoot` to return a valid path, enhancing the `ContextGatherer` and `FuzzyTaskSearch` mocks, and adding comprehensive tests for tag parameter handling in various scenarios. The tests now cover passing different tag values, ensuring correct behavior when tags are provided, undefined, or null, and validating the integration of tags in task discovery and context gathering processes.

* Remove unused import for

* fix: Refactor complexity report path handling and improve argument destructuring

This commit enhances the `expandTaskDirect` function by improving the destructuring of arguments for better readability. It also updates the `analyze.js` and `analyze-task-complexity.js` files to utilize the new `resolveComplexityReportOutputPath` function, ensuring tag-aware resolution of output paths. Additionally, logging has been added to provide clarity on the report path being used.

* test: Add complexity report tag isolation tests and improve path handling

This commit introduces a new test file for complexity report tag isolation, ensuring that different tags maintain separate complexity reports. It enhances the existing tests in `analyze-task-complexity.test.js` by updating expectations to use `expect.stringContaining` for file paths, improving robustness against path changes. The new tests cover various scenarios, including path resolution and report generation for both master and feature tags, ensuring no cross-tag contamination occurs.

* Update scripts/modules/task-manager/list-tasks.js

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Update scripts/modules/task-manager/list-tasks.js

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* test(complexity-report): Fix tag slugification in filename expectations

- Update mocks to use slugifyTagForFilePath for cross-platform compatibility
- Replace raw tag values with slugified versions in expected filenames
- Fix test expecting 'feature/user-auth-v2' to expect 'feature-user-auth-v2'
- Align test with actual filename generation logic that sanitizes special chars

---------

Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* fix: Update VS Code profile with MCP config transformation (#971)

* remove dash in server name

* add OLLAMA_API_KEY to VS Code MCP instructions

* transform vscode mcp to correct format

* add changeset

* switch back to task-master-ai

* use task-master-ai

* Batch fixes before release (#1011)

* fix: improve projectRoot

* fix: improve task-master lang command

* feat: add documentation to the readme so more people can access it

* fix: expand command subtask dependency validation

* fix: update command more reliable with perplexity and other models

* chore: fix CI

* chore: implement requested changes

* chore: fix CI

* chore: fix changeset release for extension package (#1012)

* chore: fix changeset release for extension package

* chore: fix CI

* chore: rc version bump

* chore: adjust kimi k2 max tokens (#1014)

* docs: Auto-update and format models.md

---------

Co-authored-by: Ben Vargas <ben@vargas.com>
Co-authored-by: neno-is-ooo <204701868+neno-is-ooo@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Joe Danziger <joe@ticc.net>
Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Parthy <52548018+mm-parthy@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-07-20 00:55:29 +03:00
github-actions[bot]
d87a7f1076 docs: Auto-update and format models.md 2025-07-20 00:51:41 +03:00
Ralph Khreish
5b3dd3f29b chore: adjust kimi k2 max tokens (#1014) 2025-07-20 00:51:41 +03:00
github-actions[bot]
b7804302a1 chore: rc version bump 2025-07-20 00:51:41 +03:00
Ralph Khreish
b2841c261f chore: fix changeset release for extension package (#1012)
* chore: fix changeset release for extension package

* chore: fix CI
2025-07-20 00:51:41 +03:00
Ralph Khreish
444aa5ae19 Batch fixes before release (#1011)
* fix: improve projectRoot

* fix: improve task-master lang command

* feat: add documentation to the readme so more people can access it

* fix: expand command subtask dependency validation

* fix: update command more reliable with perplexity and other models

* chore: fix CI

* chore: implement requested changes

* chore: fix CI
2025-07-20 00:51:41 +03:00
Joe Danziger
858d4a1c54 fix: Update VS Code profile with MCP config transformation (#971)
* remove dash in server name

* add OLLAMA_API_KEY to VS Code MCP instructions

* transform vscode mcp to correct format

* add changeset

* switch back to task-master-ai

* use task-master-ai
2025-07-20 00:51:41 +03:00
Parthy
fd005c4c54 fix(core): Implement Boundary-First Tag Resolution (#943)
* refactor(context): Standardize tag and projectRoot handling across all task tools

This commit unifies context management by adopting a boundary-first resolution strategy. All task-scoped tools now resolve `tag` and `projectRoot` at their entry point and forward these values to the underlying direct functions.

This approach centralizes context logic, ensuring consistent behavior and enhanced flexibility in multi-tag environments.

* fix(tag): Clean up tag handling in task functions and sync process

This commit refines the handling of the `tag` parameter across multiple functions, ensuring consistent context management. The `tag` is now passed more efficiently in `listTasksDirect`, `setTaskStatusDirect`, and `syncTasksToReadme`, improving clarity and reducing redundancy. Additionally, a TODO comment has been added in `sync-readme.js` to address future tag support enhancements.

* feat(tag): Implement Boundary-First Tag Resolution for consistent tag handling

This commit introduces Boundary-First Tag Resolution in the task manager, ensuring consistent and deterministic tag handling across CLI and MCP. This change resolves potential race conditions and improves the reliability of tag-specific operations.

Additionally, the `expandTask` function has been updated to use the resolved tag when writing JSON, enhancing data integrity during task updates.

* chore(biome): formatting

* fix(expand-task): Update writeJSON call to use tag instead of resolvedTag

* fix(commands): Enhance complexity report path resolution and task initialization
`resolveComplexityReportPath` function to streamline output path generation based on tag context and user-defined output.
- Improved clarity and maintainability of command handling by centralizing path resolution logic.

* Fix: unknown currentTag

* fix(task-manager): Update generateTaskFiles calls to include tag and projectRoot parameters

This commit modifies the `moveTask` and `updateSubtaskById` functions to pass the `tag` and `projectRoot` parameters to the `generateTaskFiles` function. This ensures that task files are generated with the correct context when requested, enhancing consistency in task management operations.

* fix(commands): Refactor tag handling and complexity report path resolution
This commit updates the `registerCommands` function to utilize `taskMaster.getCurrentTag()` for consistent tag retrieval across command actions. It also enhances the initialization of `TaskMaster` by passing the tag directly, improving clarity and maintainability. The complexity report path resolution is streamlined to ensure correct file naming based on the current tag context.

* fix(task-master): Update complexity report path expectations in tests
This commit modifies the `initTaskMaster` test to expect a valid string for the complexity report path, ensuring it matches the expected file naming convention. This change enhances test reliability by verifying the correct output format when the path is generated.

* fix(set-task-status): Enhance logging and tag resolution in task status updates
This commit improves the logging output in the `registerSetTaskStatusTool` function to include the tag context when setting task statuses. It also updates the tag handling by resolving the tag using the `resolveTag` utility, ensuring that the correct tag is used when updating task statuses. Additionally, the `setTaskStatus` function is modified to remove the tag parameter from the `readJSON` and `writeJSON` calls, streamlining the data handling process.

* fix(commands, expand-task, task-manager): Add complexity report option and enhance path handling
This commit introduces a new `--complexity-report` option in the `registerCommands` function, allowing users to specify a custom path for the complexity report. The `expandTask` function is updated to accept the `complexityReportPath` from the context, ensuring it is utilized correctly during task expansion. Additionally, the `setTaskStatus` function now includes the `tag` parameter in the `readJSON` and `writeJSON` calls, improving task status updates with proper context. The `initTaskMaster` function is also modified to create parent directories for output paths, enhancing file handling robustness.

* fix(expand-task): Add complexityReportPath to context for task expansion tests

This commit updates the test for the `expandTask` function by adding the `complexityReportPath` to the context object. This change ensures that the complexity report path is correctly utilized in the test, aligning with recent enhancements to complexity report handling in the task manager.

* chore: implement suggested changes

* fix(parse-prd): Clarify tag parameter description for task organization
Updated the documentation for the `tag` parameter in the `parse-prd.js` file to provide a clearer context on its purpose for organizing tasks into separate task lists.

* Fix Inconsistent tag resolution pattern.

* fix: Enhance complexity report path handling with tag support

This commit updates various functions to incorporate the `tag` parameter when resolving complexity report paths. The `expandTaskDirect`, `resolveComplexityReportPath`, and related tools now utilize the current tag context, improving consistency in task management. Additionally, the complexity report path is now correctly passed through the context in the `expand-task` and `set-task-status` tools, ensuring accurate report retrieval based on the active tag.

* Updated the JSDoc for the `tag` parameter in the `show-task.js` file.

* Remove redundant comment on tag parameter in readJSON call

* Remove unused import for getTagAwareFilePath

* Add missed complexityReportPath to args for task expansion

* fix(tests): Enhance research tests with tag-aware functionality

This commit updates the `research.test.js` file to improve the testing of the `performResearch` function by incorporating tag-aware functionality. Key changes include mocking the `findProjectRoot` to return a valid path, enhancing the `ContextGatherer` and `FuzzyTaskSearch` mocks, and adding comprehensive tests for tag parameter handling in various scenarios. The tests now cover passing different tag values, ensuring correct behavior when tags are provided, undefined, or null, and validating the integration of tags in task discovery and context gathering processes.

* Remove unused import for

* fix: Refactor complexity report path handling and improve argument destructuring

This commit enhances the `expandTaskDirect` function by improving the destructuring of arguments for better readability. It also updates the `analyze.js` and `analyze-task-complexity.js` files to utilize the new `resolveComplexityReportOutputPath` function, ensuring tag-aware resolution of output paths. Additionally, logging has been added to provide clarity on the report path being used.

* test: Add complexity report tag isolation tests and improve path handling

This commit introduces a new test file for complexity report tag isolation, ensuring that different tags maintain separate complexity reports. It enhances the existing tests in `analyze-task-complexity.test.js` by updating expectations to use `expect.stringContaining` for file paths, improving robustness against path changes. The new tests cover various scenarios, including path resolution and report generation for both master and feature tags, ensuring no cross-tag contamination occurs.

* Update scripts/modules/task-manager/list-tasks.js

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* Update scripts/modules/task-manager/list-tasks.js

Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>

* test(complexity-report): Fix tag slugification in filename expectations

- Update mocks to use slugifyTagForFilePath for cross-platform compatibility
- Replace raw tag values with slugified versions in expected filenames
- Fix test expecting 'feature/user-auth-v2' to expect 'feature-user-auth-v2'
- Align test with actual filename generation logic that sanitizes special chars

---------

Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-07-20 00:51:41 +03:00
Ralph Khreish
0451ebcc32 refactor: remove unused resource and resource template initialization (#1002)
* refactor: remove unused resource and resource template initialization

* chore: implement requested changes
2025-07-20 00:51:41 +03:00
Ralph Khreish
9c58a92243 feat: add kiro profile (#1001)
* feat: add kiro profile

* chore: fix format

* chore: implement requested changes

* chore: fix CI
2025-07-20 00:51:41 +03:00
Ralph Khreish
f772a96d00 fix(ai-validation): comprehensive fixes for AI response validation issues (#1000)
* fix(ai-validation): comprehensive fixes for AI response validation issues

  - Fix update command validation when AI omits subtasks/status/dependencies
  - Fix add-task command when AI returns non-string details field
  - Fix update-task command when AI subtasks miss required fields
  - Add preprocessing to ensure proper field types before validation
  - Prevent split() errors on non-string fields
  - Set proper defaults for missing required fields

* chore: run format

* chore: implement coderabbit suggestions
2025-07-20 00:51:41 +03:00
Joe Danziger
0886c83d0c docs: Update MCP server name for consistency and use 'Add to Cursor' button (#995)
* update MCP server name to task-master-ai for consistency

* add changeset

* update cursor link & switch to https

* switch back to Add to Cursor button (https link)

* update changeset

* update changeset

* update changeset

* update changeset

* use GitHub markdown format
2025-07-20 00:51:41 +03:00
Ralph Khreish
806ec99939 chore: add coderabbit configuration (#992)
* chore: add coderabbit configuration

* chore: fix coderabbit config

* chore: improve coderabbit config

* chore: more coderabbit reviews

* chore: remove all defaults
2025-07-20 00:51:41 +03:00
Joe Danziger
36c4a7a869 feat: Add OpenCode rule profile with AGENTS.md and MCP config (#970)
* add opencode to profile lists

* add opencode profile / modify mcp config after add

* add changeset

* not necessary; main config being updated

* add issue link

* add/fix tests

* fix url and docsUrl

* update test for new urls

* fix formatting

* update/fix tests
2025-07-20 00:51:41 +03:00
Joe Danziger
88c434a939 fix: Add missing API keys to .env.example and README.md (#972)
* add OLLAMA_API_KEY

* add missing API keys

* add changeset

* update keys and fix OpenAI comment

* chore: create extension scaffolding (#989)

* chore: create extension scaffolding

* chore: fix workspace for changeset

* chore: fix package-lock

* feat(profiles): Add MCP configuration to Claude Code rules (#980)

* add .mcp.json with claude profile

* add changeset

* update changeset

* update test

* fix: show command no longer requires complexity report to exist (#979)

Co-authored-by: Ben Vargas <ben@example.com>

* feat: complete Groq provider integration and add Kimi K2 model (#978)

* feat: complete Groq provider integration and add Kimi K2 model

- Add missing getRequiredApiKeyName() method to GroqProvider class
- Register GroqProvider in ai-services-unified.js PROVIDERS object
- Add Groq API key handling to config-manager.js (isApiKeySet and getMcpApiKeyStatus)
- Add GROQ_API_KEY to env.example with format hint
- Add moonshotai/kimi-k2-instruct model to Groq provider ($1/$3 per 1M tokens, 16k max)
- Fix import sorting for linting compliance
- Add GroqProvider mock to ai-services-unified tests

Fixes missing implementation pieces that prevented Groq provider from working.

* chore: improve changeset

---------

Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>

* docs: Auto-update and format models.md

* feat: Add Amp rule profile with AGENT.md and MCP config (#973)

* Amp profile + tests

* generatlize to Agent instead of Claude Code to support any agent

* add changeset

* unnecessary tab formatting

* fix exports

* fix formatting

* feat: Add Zed editor rule profile with agent rules and MCP config (#974)

* zed profile

* add changeset

* update changeset

---------

Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
Co-authored-by: Ben Vargas <ben@vargas.com>
Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-07-20 00:51:41 +03:00
Joe Danziger
b0e09c76ed feat: Add Zed editor rule profile with agent rules and MCP config (#974)
* zed profile

* add changeset

* update changeset
2025-07-20 00:51:41 +03:00
Joe Danziger
6c5e0f97f8 feat: Add Amp rule profile with AGENT.md and MCP config (#973)
* Amp profile + tests

* generatlize to Agent instead of Claude Code to support any agent

* add changeset

* unnecessary tab formatting

* fix exports

* fix formatting
2025-07-20 00:51:41 +03:00
github-actions[bot]
8774e7d5ae docs: Auto-update and format models.md 2025-07-20 00:51:41 +03:00
Ben Vargas
58a301c380 feat: complete Groq provider integration and add Kimi K2 model (#978)
* feat: complete Groq provider integration and add Kimi K2 model

- Add missing getRequiredApiKeyName() method to GroqProvider class
- Register GroqProvider in ai-services-unified.js PROVIDERS object
- Add Groq API key handling to config-manager.js (isApiKeySet and getMcpApiKeyStatus)
- Add GROQ_API_KEY to env.example with format hint
- Add moonshotai/kimi-k2-instruct model to Groq provider ($1/$3 per 1M tokens, 16k max)
- Fix import sorting for linting compliance
- Add GroqProvider mock to ai-services-unified tests

Fixes missing implementation pieces that prevented Groq provider from working.

* chore: improve changeset

---------

Co-authored-by: Ben Vargas <ben@example.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
2025-07-20 00:51:41 +03:00
Ben Vargas
624922ca59 fix: show command no longer requires complexity report to exist (#979)
Co-authored-by: Ben Vargas <ben@example.com>
2025-07-20 00:51:41 +03:00
Joe Danziger
0a70ab6179 feat(profiles): Add MCP configuration to Claude Code rules (#980)
* add .mcp.json with claude profile

* add changeset

* update changeset

* update test
2025-07-20 00:51:41 +03:00
Ralph Khreish
901eec1058 chore: create extension scaffolding (#989)
* chore: create extension scaffolding

* chore: fix workspace for changeset

* chore: fix package-lock
2025-07-20 00:51:41 +03:00
Ralph Khreish
4629128943 fix: task master (tm) custom slash commands w/ proper syntax (#968)
* feat: add task master (tm) custom slash commands

Add comprehensive task management system integration via custom slash commands.
Includes commands for:
- Project initialization and setup
- Task parsing from PRD documents
- Task creation, update, and removal
- Subtask management
- Dependency tracking and validation
- Complexity analysis and task expansion
- Project status and reporting
- Workflow automation

This provides a complete task management workflow directly within Claude Code.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* chore: add changeset

---------

Co-authored-by: neno-is-ooo <204701868+neno-is-ooo@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2025-07-20 00:51:41 +03:00
Ben Vargas
6d69d02fe0 fix: prevent CLAUDE.md overwrite by using imports (#949)
* fix: prevent CLAUDE.md overwrite by using imports

- Copy Task Master instructions to .taskmaster/CLAUDE.md
- Add import section to user's CLAUDE.md instead of overwriting
- Preserve existing user content
- Clean removal of Task Master content on uninstall

Closes #929

* chore: add changeset for Claude import fix
2025-07-20 00:51:41 +03:00
Ralph Khreish
458496e3b6 Merge pull request #961 from eyaltoledano/changeset-release/main 2025-07-12 22:49:56 +03:00
github-actions[bot]
fb92693d81 Version Packages 2025-07-12 19:31:08 +00:00
Ralph Khreish
f6ba4a36ee Merge pull request #958 from eyaltoledano/next 2025-07-12 22:30:36 +03:00
123 changed files with 4745 additions and 753 deletions

View File

@@ -1,12 +0,0 @@
---
"task-master-ai": patch
---
Prevent CLAUDE.md overwrite by using Claude Code's import feature
- Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
- Adds an import section to the user's CLAUDE.md that references the Task Master instructions
- Preserves existing user content in CLAUDE.md files
- Provides clean uninstall that only removes Task Master's additions
**Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.

View File

@@ -1,7 +0,0 @@
---
"task-master-ai": patch
---
Fix: show command no longer requires complexity report file to exist
The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.

View File

@@ -1,10 +0,0 @@
---
"task-master-ai": minor
---
Complete Groq provider integration and add MoonshotAI Kimi K2 model support
- Fixed Groq provider registration
- Added Groq API key validation
- Added GROQ_API_KEY to .env.example
- Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output

View File

@@ -1,7 +0,0 @@
---
"task-master-ai": minor
---
feat: Add Zed editor rule profile with agent rules and MCP config
- Resolves #637

View File

@@ -1,5 +0,0 @@
---
"task-master-ai": minor
---
Add Amp rule profile with AGENT.md and MCP config

View File

@@ -1,5 +0,0 @@
---
"task-master-ai": patch
---
Add MCP configuration support to Claude Code rules

View File

@@ -1,7 +0,0 @@
---
"task-master-ai": patch
---
Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
- Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code

View File

@@ -1,5 +0,0 @@
---
"task-master-ai": patch
---
Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.

View File

@@ -1,7 +0,0 @@
---
"task-master-ai": minor
---
Add OpenCode profile with AGENTS.md and MCP config
- Resolves #965

View File

@@ -1,5 +0,0 @@
---
"task-master-ai": patch
---
Add missing API keys to .env.example and README.md

View File

@@ -1,5 +1,139 @@
# task-master-ai
## 0.21.0
### Minor Changes
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`9c58a92`](https://github.com/eyaltoledano/claude-task-master/commit/9c58a922436c0c5e7ff1b20ed2edbc269990c772) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Kiro editor rule profile support
- Add support for Kiro IDE with custom rule files and MCP configuration
- Generate rule files in `.kiro/steering/` directory with markdown format
- Include MCP server configuration with enhanced file inclusion patterns
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`58a301c`](https://github.com/eyaltoledano/claude-task-master/commit/58a301c380d18a9d9509137f3e989d24200a5faa) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support
- Fixed Groq provider registration
- Added Groq API key validation
- Added GROQ_API_KEY to .env.example
- Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`b0e09c7`](https://github.com/eyaltoledano/claude-task-master/commit/b0e09c76ed73b00434ac95606679f570f1015a3d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - feat: Add Zed editor rule profile with agent rules and MCP config
- Resolves #637
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6c5e0f9`](https://github.com/eyaltoledano/claude-task-master/commit/6c5e0f97f8403c4da85c1abba31cb8b1789511a7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Amp rule profile with AGENT.md and MCP config
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
- No longer creates an infinite loop when unable to detect your code workspace
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`36c4a7a`](https://github.com/eyaltoledano/claude-task-master/commit/36c4a7a86924c927ad7f86a4f891f66ad55eb4d2) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add OpenCode profile with AGENTS.md and MCP config
- Resolves #965
### Patch Changes
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make `task-master update` more reliable with AI responses
The `update` command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix subtask dependency validation when expanding tasks
When using `task-master expand` to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6d69d02`](https://github.com/eyaltoledano/claude-task-master/commit/6d69d02fe03edcc785380415995d5cfcdd97acbb) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prevent CLAUDE.md overwrite by using Claude Code's import feature
- Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
- Adds an import section to the user's CLAUDE.md that references the Task Master instructions
- Preserves existing user content in CLAUDE.md files
- Provides clean uninstall that only removes Task Master's additions
**Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`fd005c4`](https://github.com/eyaltoledano/claude-task-master/commit/fd005c4c5481ffac58b11f01a448fa5b29056b8d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`624922c`](https://github.com/eyaltoledano/claude-task-master/commit/624922ca598c4ce8afe9a5646ebb375d4616db63) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix: show command no longer requires complexity report file to exist
The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`858d4a1`](https://github.com/eyaltoledano/claude-task-master/commit/858d4a1c5486d20e7e3a8e37e3329d7fb8200310) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update VS Code profile with MCP config transformation
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0451ebc`](https://github.com/eyaltoledano/claude-task-master/commit/0451ebcc32cd7e9d395b015aaa8602c4734157e1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0a70ab6`](https://github.com/eyaltoledano/claude-task-master/commit/0a70ab6179cb2b5b4b2d9dc256a7a3b69a0e5dd6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add MCP configuration support to Claude Code rules
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`4629128`](https://github.com/eyaltoledano/claude-task-master/commit/4629128943f6283385f4762c09cf2752f855cc33) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
- Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0886c83`](https://github.com/eyaltoledano/claude-task-master/commit/0886c83d0c678417c0313256a6dd96f7ee2c9ac6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`88c434a`](https://github.com/eyaltoledano/claude-task-master/commit/88c434a9393e429d9277f59b3e20f1005076bbe0) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add missing API keys to .env.example and README.md
## 0.21.0-rc.0
### Minor Changes
- [#1001](https://github.com/eyaltoledano/claude-task-master/pull/1001) [`75a36ea`](https://github.com/eyaltoledano/claude-task-master/commit/75a36ea99a1c738a555bdd4fe7c763d0c5925e37) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Kiro editor rule profile support
- Add support for Kiro IDE with custom rule files and MCP configuration
- Generate rule files in `.kiro/steering/` directory with markdown format
- Include MCP server configuration with enhanced file inclusion patterns
- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
- [#978](https://github.com/eyaltoledano/claude-task-master/pull/978) [`fedfd6a`](https://github.com/eyaltoledano/claude-task-master/commit/fedfd6a0f41a78094f7ee7f69be689b699475a79) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support
- Fixed Groq provider registration
- Added Groq API key validation
- Added GROQ_API_KEY to .env.example
- Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output
- [#974](https://github.com/eyaltoledano/claude-task-master/pull/974) [`5b0eda0`](https://github.com/eyaltoledano/claude-task-master/commit/5b0eda07f20a365aa2ec1736eed102bca81763a9) Thanks [@joedanz](https://github.com/joedanz)! - feat: Add Zed editor rule profile with agent rules and MCP config
- Resolves #637
- [#973](https://github.com/eyaltoledano/claude-task-master/pull/973) [`6d05e86`](https://github.com/eyaltoledano/claude-task-master/commit/6d05e8622c1d761acef10414940ff9a766b3b57d) Thanks [@joedanz](https://github.com/joedanz)! - Add Amp rule profile with AGENT.md and MCP config
- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
- No longer creates an infinite loop when unable to detect your code workspace
- [#970](https://github.com/eyaltoledano/claude-task-master/pull/970) [`b87499b`](https://github.com/eyaltoledano/claude-task-master/commit/b87499b56e626001371a87ed56ffc72675d829f3) Thanks [@joedanz](https://github.com/joedanz)! - Add OpenCode profile with AGENTS.md and MCP config
- Resolves #965
### Patch Changes
- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make `task-master update` more reliable with AI responses
The `update` command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.
- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix subtask dependency validation when expanding tasks
When using `task-master expand` to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.
- [#949](https://github.com/eyaltoledano/claude-task-master/pull/949) [`f662654`](https://github.com/eyaltoledano/claude-task-master/commit/f662654afb8e7a230448655265d6f41adf6df62c) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Prevent CLAUDE.md overwrite by using Claude Code's import feature
- Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
- Adds an import section to the user's CLAUDE.md that references the Task Master instructions
- Preserves existing user content in CLAUDE.md files
- Provides clean uninstall that only removes Task Master's additions
**Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
- [#943](https://github.com/eyaltoledano/claude-task-master/pull/943) [`f98df5c`](https://github.com/eyaltoledano/claude-task-master/commit/f98df5c0fdb253b2b55d4278c11d626529c4dba4) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
- [#979](https://github.com/eyaltoledano/claude-task-master/pull/979) [`ab2e946`](https://github.com/eyaltoledano/claude-task-master/commit/ab2e94608749a2f148118daa0443bd32bca6e7a1) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix: show command no longer requires complexity report file to exist
The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
- [#971](https://github.com/eyaltoledano/claude-task-master/pull/971) [`5544222`](https://github.com/eyaltoledano/claude-task-master/commit/55442226d0aa4870470d2a9897f5538d6a0e329e) Thanks [@joedanz](https://github.com/joedanz)! - Update VS Code profile with MCP config transformation
- [#1002](https://github.com/eyaltoledano/claude-task-master/pull/1002) [`6d0654c`](https://github.com/eyaltoledano/claude-task-master/commit/6d0654cb4191cee794e1c8cbf2b92dc33d4fb410) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
- [#980](https://github.com/eyaltoledano/claude-task-master/pull/980) [`cc4fe20`](https://github.com/eyaltoledano/claude-task-master/commit/cc4fe205fb468e7144c650acc92486df30731560) Thanks [@joedanz](https://github.com/joedanz)! - Add MCP configuration support to Claude Code rules
- [#968](https://github.com/eyaltoledano/claude-task-master/pull/968) [`7b4803a`](https://github.com/eyaltoledano/claude-task-master/commit/7b4803a479105691c7ed032fd878fe3d48d82724) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
- Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code
- [#995](https://github.com/eyaltoledano/claude-task-master/pull/995) [`b78de8d`](https://github.com/eyaltoledano/claude-task-master/commit/b78de8dbb4d6dc93b48e2f81c32960ef069736ed) Thanks [@joedanz](https://github.com/joedanz)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
- [#972](https://github.com/eyaltoledano/claude-task-master/pull/972) [`1c7badf`](https://github.com/eyaltoledano/claude-task-master/commit/1c7badff2f5c548bfa90a3b2634e63087a382a84) Thanks [@joedanz](https://github.com/joedanz)! - Add missing API keys to .env.example and README.md
## 0.20.0
### Minor Changes

View File

@@ -14,7 +14,13 @@ A task management system for AI-driven development with Claude, designed to work
## Documentation
For more detailed information, check out the documentation in the `docs` directory:
📚 **[View Full Documentation](https://docs.task-master.dev)**
For detailed guides, API references, and comprehensive examples, visit our documentation site.
### Quick Reference
The following documentation is also available in the `docs` directory:
- [Configuration Guide](docs/configuration.md) - Set up environment variables and customize Task Master
- [Tutorial](docs/tutorial.md) - Step-by-step guide to getting started with Task Master

View File

@@ -1,5 +1,6 @@
{
"name": "extension",
"private": true,
"version": "0.20.0",
"main": "index.js",
"scripts": {

View File

@@ -1,4 +1,4 @@
# Available Models as of July 16, 2025
# Available Models as of July 19, 2025
## Main Models

View File

@@ -16,12 +16,14 @@ import {
* @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
* @param {string|number} args.id - Task ID to add dependency to
* @param {string|number} args.dependsOn - Task ID that will become a dependency
* @param {string} args.tag - Tag for the task (optional)
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {Object} log - Logger object
* @returns {Promise<Object>} - Result object with success status and data/error information
*/
export async function addDependencyDirect(args, log) {
// Destructure expected args
const { tasksJsonPath, id, dependsOn } = args;
const { tasksJsonPath, id, dependsOn, tag, projectRoot } = args;
try {
log.info(`Adding dependency with args: ${JSON.stringify(args)}`);
@@ -76,8 +78,11 @@ export async function addDependencyDirect(args, log) {
// Enable silent mode to prevent console logs from interfering with JSON response
enableSilentMode();
// Create context object
const context = { projectRoot, tag };
// Call the core function using the provided path
await addDependency(tasksPath, taskId, dependencyId);
await addDependency(tasksPath, taskId, dependencyId, context);
// Restore normal logging
disableSilentMode();

View File

@@ -24,6 +24,7 @@ import { createLogWrapper } from '../../tools/utils.js';
* @param {string} [args.tasksJsonPath] - Path to the tasks.json file (resolved by tool)
* @param {boolean} [args.research=false] - Whether to use research capabilities for task creation
* @param {string} [args.projectRoot] - Project root path
* @param {string} [args.tag] - Tag for the task (optional)
* @param {Object} log - Logger object
* @param {Object} context - Additional context (session)
* @returns {Promise<Object>} - Result object { success: boolean, data?: any, error?: { code: string, message: string } }
@@ -36,7 +37,8 @@ export async function addTaskDirect(args, log, context = {}) {
dependencies,
priority,
research,
projectRoot
projectRoot,
tag
} = args;
const { session } = context; // Destructure session from context
@@ -121,7 +123,8 @@ export async function addTaskDirect(args, log, context = {}) {
mcpLog,
projectRoot,
commandName: 'add-task',
outputType: 'mcp'
outputType: 'mcp',
tag
},
'json', // outputFormat
manualTaskData, // Pass the manual task data
@@ -147,7 +150,8 @@ export async function addTaskDirect(args, log, context = {}) {
mcpLog,
projectRoot,
commandName: 'add-task',
outputType: 'mcp'
outputType: 'mcp',
tag
},
'json', // outputFormat
null, // manualTaskData is null for AI creation

View File

@@ -22,6 +22,7 @@ import { createLogWrapper } from '../../tools/utils.js'; // Import the new utili
* @param {number} [args.from] - Starting task ID in a range to analyze
* @param {number} [args.to] - Ending task ID in a range to analyze
* @param {string} [args.projectRoot] - Project root path.
* @param {string} [args.tag] - Tag for the task (optional)
* @param {Object} log - Logger object
* @param {Object} [context={}] - Context object containing session data
* @param {Object} [context.session] - MCP session object
@@ -37,7 +38,8 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
projectRoot,
ids,
from,
to
to,
tag
} = args;
const logWrapper = createLogWrapper(log);
@@ -91,7 +93,8 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
projectRoot: projectRoot, // Pass projectRoot here
id: ids, // Pass the ids parameter to the core function as 'id'
from: from, // Pass from parameter
to: to // Pass to parameter
to: to, // Pass to parameter
tag // forward tag
};
// --- End Initial Checks ---
@@ -112,7 +115,9 @@ export async function analyzeTaskComplexityDirect(args, log, context = {}) {
session,
mcpLog: logWrapper,
commandName: 'analyze-complexity',
outputType: 'mcp'
outputType: 'mcp',
projectRoot,
tag
});
report = coreResult.report;
} catch (error) {

View File

@@ -18,6 +18,7 @@ import path from 'path';
* @param {string} [args.id] - Task IDs (comma-separated) to clear subtasks from
* @param {boolean} [args.all] - Clear subtasks from all tasks
* @param {string} [args.tag] - Tag context to operate on (defaults to current active tag)
* @param {string} [args.projectRoot] - Project root path (for MCP/env fallback)
* @param {Object} log - Logger object
* @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
*/
@@ -80,7 +81,7 @@ export async function clearSubtasksDirect(args, log) {
};
}
const currentTag = data.tag || 'master';
const currentTag = data.tag || tag;
const tasks = data.tasks;
// If all is specified, get all task IDs

View File

@@ -18,6 +18,7 @@ import { createLogWrapper } from '../../tools/utils.js';
* @param {string} [args.prompt] - Additional context to guide subtask generation
* @param {boolean} [args.force] - Force regeneration of subtasks for tasks that already have them
* @param {string} [args.projectRoot] - Project root path.
* @param {string} [args.tag] - Tag for the task (optional)
* @param {Object} log - Logger object from FastMCP
* @param {Object} context - Context object containing session
* @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
@@ -25,7 +26,8 @@ import { createLogWrapper } from '../../tools/utils.js';
export async function expandAllTasksDirect(args, log, context = {}) {
const { session } = context; // Extract session
// Destructure expected args, including projectRoot
const { tasksJsonPath, num, research, prompt, force, projectRoot } = args;
const { tasksJsonPath, num, research, prompt, force, projectRoot, tag } =
args;
// Create logger wrapper using the utility
const mcpLog = createLogWrapper(log);
@@ -44,7 +46,7 @@ export async function expandAllTasksDirect(args, log, context = {}) {
enableSilentMode(); // Enable silent mode for the core function call
try {
log.info(
`Calling core expandAllTasks with args: ${JSON.stringify({ num, research, prompt, force, projectRoot })}`
`Calling core expandAllTasks with args: ${JSON.stringify({ num, research, prompt, force, projectRoot, tag })}`
);
// Parse parameters (ensure correct types)
@@ -60,7 +62,7 @@ export async function expandAllTasksDirect(args, log, context = {}) {
useResearch,
additionalContext,
forceFlag,
{ session, mcpLog, projectRoot },
{ session, mcpLog, projectRoot, tag },
'json'
);

View File

@@ -35,8 +35,17 @@ import { createLogWrapper } from '../../tools/utils.js';
export async function expandTaskDirect(args, log, context = {}) {
const { session } = context; // Extract session
// Destructure expected args, including projectRoot
const { tasksJsonPath, id, num, research, prompt, force, projectRoot, tag } =
args;
const {
tasksJsonPath,
id,
num,
research,
prompt,
force,
projectRoot,
tag,
complexityReportPath
} = args;
// Log session root data for debugging
log.info(
@@ -192,6 +201,7 @@ export async function expandTaskDirect(args, log, context = {}) {
useResearch,
additionalContext,
{
complexityReportPath,
mcpLog,
session,
projectRoot,

View File

@@ -53,10 +53,9 @@ export async function fixDependenciesDirect(args, log) {
// Enable silent mode to prevent console logs from interfering with JSON response
enableSilentMode();
const options = { projectRoot, tag };
// Call the original command function using the provided path and proper context
await fixDependenciesCommand(tasksPath, {
context: { projectRoot, tag }
});
await fixDependenciesCommand(tasksPath, options);
// Restore normal logging
disableSilentMode();

View File

@@ -13,12 +13,16 @@ import {
* Direct function wrapper for generateTaskFiles with error handling.
*
* @param {Object} args - Command arguments containing tasksJsonPath and outputDir.
* @param {string} args.tasksJsonPath - Path to the tasks.json file.
* @param {string} args.outputDir - Path to the output directory.
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object.
* @returns {Promise<Object>} - Result object with success status and data/error information.
*/
export async function generateTaskFilesDirect(args, log) {
// Destructure expected args
const { tasksJsonPath, outputDir } = args;
const { tasksJsonPath, outputDir, projectRoot, tag } = args;
try {
log.info(`Generating task files with args: ${JSON.stringify(args)}`);
@@ -51,8 +55,12 @@ export async function generateTaskFilesDirect(args, log) {
// Enable silent mode to prevent logs from being written to stdout
enableSilentMode();
// The function is synchronous despite being awaited elsewhere
generateTaskFiles(tasksPath, resolvedOutputDir);
// Pass projectRoot and tag so the core respects context
generateTaskFiles(tasksPath, resolvedOutputDir, {
projectRoot,
tag,
mcpLog: log
});
// Restore normal logging after task generation
disableSilentMode();

View File

@@ -13,12 +13,19 @@ import {
* Direct function wrapper for listTasks with error handling and caching.
*
* @param {Object} args - Command arguments (now expecting tasksJsonPath explicitly).
* @param {string} args.tasksJsonPath - Path to the tasks.json file.
* @param {string} args.reportPath - Path to the report file.
* @param {string} args.status - Status of the task.
* @param {boolean} args.withSubtasks - Whether to include subtasks.
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object.
* @returns {Promise<Object>} - Task list result { success: boolean, data?: any, error?: { code: string, message: string } }.
*/
export async function listTasksDirect(args, log, context = {}) {
// Destructure the explicit tasksJsonPath from args
const { tasksJsonPath, reportPath, status, withSubtasks, projectRoot } = args;
const { tasksJsonPath, reportPath, status, withSubtasks, projectRoot, tag } =
args;
const { session } = context;
if (!tasksJsonPath) {
@@ -52,8 +59,7 @@ export async function listTasksDirect(args, log, context = {}) {
reportPath,
withSubtasksFilter,
'json',
null, // tag
{ projectRoot, session } // context
{ projectRoot, session, tag }
);
if (!resultData || !resultData.tasks) {

View File

@@ -17,12 +17,14 @@ import {
* @param {string} args.destinationId - ID of the destination (e.g., '7' or '7.3' or '7,8,9')
* @param {string} args.file - Alternative path to the tasks.json file
* @param {string} args.projectRoot - Project root directory
* @param {string} args.tag - Tag for the task (optional)
* @param {boolean} args.generateFiles - Whether to regenerate task files after moving (default: true)
* @param {Object} log - Logger object
* @returns {Promise<{success: boolean, data?: Object, error?: Object}>}
*/
export async function moveTaskDirect(args, log, context = {}) {
const { session } = context;
const { projectRoot, tag } = args;
// Validate required parameters
if (!args.sourceId) {
@@ -73,8 +75,8 @@ export async function moveTaskDirect(args, log, context = {}) {
args.destinationId,
generateFiles,
{
projectRoot: args.projectRoot,
tag: args.tag
projectRoot,
tag
}
);

View File

@@ -18,12 +18,15 @@ import {
*
* @param {Object} args - Command arguments
* @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
* @param {string} args.reportPath - Path to the report file.
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object
* @returns {Promise<Object>} - Next task result { success: boolean, data?: any, error?: { code: string, message: string } }
*/
export async function nextTaskDirect(args, log, context = {}) {
// Destructure expected args
const { tasksJsonPath, reportPath, projectRoot } = args;
const { tasksJsonPath, reportPath, projectRoot, tag } = args;
const { session } = context;
if (!tasksJsonPath) {
@@ -46,7 +49,7 @@ export async function nextTaskDirect(args, log, context = {}) {
log.info(`Finding next task from ${tasksJsonPath}`);
// Read tasks data using the provided path
const data = readJSON(tasksJsonPath, projectRoot);
const data = readJSON(tasksJsonPath, projectRoot, tag);
if (!data || !data.tasks) {
disableSilentMode(); // Disable before return
return {

View File

@@ -20,6 +20,13 @@ import { TASKMASTER_TASKS_FILE } from '../../../../src/constants/paths.js';
* Direct function wrapper for parsing PRD documents and generating tasks.
*
* @param {Object} args - Command arguments containing projectRoot, input, output, numTasks options.
* @param {string} args.input - Path to the input PRD file.
* @param {string} args.output - Path to the output directory.
* @param {string} args.numTasks - Number of tasks to generate.
* @param {boolean} args.force - Whether to force parsing.
* @param {boolean} args.append - Whether to append to the output file.
* @param {boolean} args.research - Whether to use research mode.
* @param {string} args.tag - Tag context for organizing tasks into separate task lists.
* @param {Object} log - Logger object.
* @param {Object} context - Context object containing session data.
* @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -34,7 +41,8 @@ export async function parsePRDDirect(args, log, context = {}) {
force,
append,
research,
projectRoot
projectRoot,
tag
} = args;
// Create the standard logger wrapper
@@ -152,6 +160,7 @@ export async function parsePRDDirect(args, log, context = {}) {
session,
mcpLog: logWrapper,
projectRoot,
tag,
force,
append,
research,

View File

@@ -14,12 +14,14 @@ import {
* @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
* @param {string|number} args.id - Task ID to remove dependency from
* @param {string|number} args.dependsOn - Task ID to remove as a dependency
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object
* @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
*/
export async function removeDependencyDirect(args, log) {
// Destructure expected args
const { tasksJsonPath, id, dependsOn } = args;
const { tasksJsonPath, id, dependsOn, projectRoot, tag } = args;
try {
log.info(`Removing dependency with args: ${JSON.stringify(args)}`);
@@ -75,7 +77,10 @@ export async function removeDependencyDirect(args, log) {
enableSilentMode();
// Call the core function using the provided tasksPath
await removeDependency(tasksPath, taskId, dependencyId);
await removeDependency(tasksPath, taskId, dependencyId, {
projectRoot,
tag
});
// Restore normal logging
disableSilentMode();

View File

@@ -15,12 +15,14 @@ import {
* @param {string} args.id - Subtask ID in format "parentId.subtaskId" (required)
* @param {boolean} [args.convert] - Whether to convert the subtask to a standalone task
* @param {boolean} [args.skipGenerate] - Skip regenerating task files
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object
* @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
*/
export async function removeSubtaskDirect(args, log) {
// Destructure expected args
const { tasksJsonPath, id, convert, skipGenerate } = args;
const { tasksJsonPath, id, convert, skipGenerate, projectRoot, tag } = args;
try {
// Enable silent mode to prevent console logs from interfering with JSON response
enableSilentMode();
@@ -82,7 +84,11 @@ export async function removeSubtaskDirect(args, log) {
tasksPath,
id,
convertToTask,
generateFiles
generateFiles,
{
projectRoot,
tag
}
);
// Restore normal logging

View File

@@ -20,7 +20,8 @@ import {
* @param {Object} args - Command arguments
* @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
* @param {string} args.id - The ID(s) of the task(s) or subtask(s) to remove (comma-separated for multiple).
* @param {string} [args.tag] - Tag context to operate on (defaults to current active tag).
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object
* @returns {Promise<Object>} - Remove task result { success: boolean, data?: any, error?: { code: string, message: string } }
*/
@@ -117,7 +118,7 @@ export async function removeTaskDirect(args, log, context = {}) {
removedTasks: result.removedTasks,
message: result.message,
tasksPath: tasksJsonPath,
tag: data.tag || tag || 'master'
tag
}
};
} finally {

View File

@@ -24,6 +24,7 @@ import { createLogWrapper } from '../../tools/utils.js';
* @param {string} [args.saveTo] - Automatically save to task/subtask ID (e.g., "15" or "15.2")
* @param {boolean} [args.saveToFile=false] - Save research results to .taskmaster/docs/research/ directory
* @param {string} [args.projectRoot] - Project root path
* @param {string} [args.tag] - Tag for the task (optional)
* @param {Object} log - Logger object
* @param {Object} context - Additional context (session)
* @returns {Promise<Object>} - Result object { success: boolean, data?: any, error?: { code: string, message: string } }
@@ -39,7 +40,8 @@ export async function researchDirect(args, log, context = {}) {
detailLevel = 'medium',
saveTo,
saveToFile = false,
projectRoot
projectRoot,
tag
} = args;
const { session } = context; // Destructure session from context
@@ -111,6 +113,7 @@ export async function researchDirect(args, log, context = {}) {
includeProjectTree,
detailLevel,
projectRoot,
tag,
saveToFile
};
@@ -169,7 +172,8 @@ ${result.result}`;
mcpLog,
commandName: 'research-save',
outputType: 'mcp',
projectRoot
projectRoot,
tag
},
'json'
);
@@ -200,7 +204,8 @@ ${result.result}`;
mcpLog,
commandName: 'research-save',
outputType: 'mcp',
projectRoot
projectRoot,
tag
},
'json',
true // appendMode = true

View File

@@ -14,6 +14,11 @@ import { nextTaskDirect } from './next-task.js';
* Direct function wrapper for setTaskStatus with error handling.
*
* @param {Object} args - Command arguments containing id, status, tasksJsonPath, and projectRoot.
* @param {string} args.id - The ID of the task to update.
* @param {string} args.status - The new status to set for the task.
* @param {string} args.tasksJsonPath - Path to the tasks.json file.
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object.
* @param {Object} context - Additional context (session)
* @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -70,17 +75,12 @@ export async function setTaskStatusDirect(args, log, context = {}) {
enableSilentMode(); // Enable silent mode before calling core function
try {
// Call the core function
await setTaskStatus(
tasksPath,
taskId,
newStatus,
{
await setTaskStatus(tasksPath, taskId, newStatus, {
mcpLog: log,
projectRoot,
session
},
session,
tag
);
});
log.info(`Successfully set task ${taskId} status to ${newStatus}`);
@@ -103,7 +103,8 @@ export async function setTaskStatusDirect(args, log, context = {}) {
{
tasksJsonPath: tasksJsonPath,
reportPath: complexityReportPath,
projectRoot: projectRoot
projectRoot: projectRoot,
tag
},
log,
{ session }

View File

@@ -19,6 +19,7 @@ import { findTasksPath } from '../utils/path-utils.js';
* @param {string} args.reportPath - Explicit path to the complexity report file.
* @param {string} [args.status] - Optional status to filter subtasks by.
* @param {string} args.projectRoot - Absolute path to the project root directory (already normalized by tool).
* @param {string} [args.tag] - Tag for the task
* @param {Object} log - Logger object.
* @param {Object} context - Context object containing session data.
* @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -26,7 +27,7 @@ import { findTasksPath } from '../utils/path-utils.js';
export async function showTaskDirect(args, log) {
// This function doesn't need session context since it only reads data
// Destructure projectRoot and other args. projectRoot is assumed normalized.
const { id, file, reportPath, status, projectRoot } = args;
const { id, file, reportPath, status, projectRoot, tag } = args;
log.info(
`Showing task direct function. ID: ${id}, File: ${file}, Status Filter: ${status}, ProjectRoot: ${projectRoot}`
@@ -55,7 +56,7 @@ export async function showTaskDirect(args, log) {
// --- Rest of the function remains the same, using tasksJsonPath ---
try {
const tasksData = readJSON(tasksJsonPath, projectRoot);
const tasksData = readJSON(tasksJsonPath, projectRoot, tag);
if (!tasksData || !tasksData.tasks) {
return {
success: false,

View File

@@ -20,6 +20,7 @@ import { createLogWrapper } from '../../tools/utils.js';
* @param {string} args.prompt - Information to append to the subtask.
* @param {boolean} [args.research] - Whether to use research role.
* @param {string} [args.projectRoot] - Project root path.
* @param {string} [args.tag] - Tag for the task (optional)
* @param {Object} log - Logger object.
* @param {Object} context - Context object containing session data.
* @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -27,7 +28,7 @@ import { createLogWrapper } from '../../tools/utils.js';
export async function updateSubtaskByIdDirect(args, log, context = {}) {
const { session } = context;
// Destructure expected args, including projectRoot
const { tasksJsonPath, id, prompt, research, projectRoot } = args;
const { tasksJsonPath, id, prompt, research, projectRoot, tag } = args;
const logWrapper = createLogWrapper(log);
@@ -112,6 +113,7 @@ export async function updateSubtaskByIdDirect(args, log, context = {}) {
mcpLog: logWrapper,
session,
projectRoot,
tag,
commandName: 'update-subtask',
outputType: 'mcp'
},

View File

@@ -21,6 +21,7 @@ import { createLogWrapper } from '../../tools/utils.js';
* @param {boolean} [args.research] - Whether to use research role.
* @param {boolean} [args.append] - Whether to append timestamped information instead of full update.
* @param {string} [args.projectRoot] - Project root path.
* @param {string} [args.tag] - Tag for the task (optional)
* @param {Object} log - Logger object.
* @param {Object} context - Context object containing session data.
* @returns {Promise<Object>} - Result object with success status and data/error information.
@@ -28,7 +29,8 @@ import { createLogWrapper } from '../../tools/utils.js';
export async function updateTaskByIdDirect(args, log, context = {}) {
const { session } = context;
// Destructure expected args, including projectRoot
const { tasksJsonPath, id, prompt, research, append, projectRoot } = args;
const { tasksJsonPath, id, prompt, research, append, projectRoot, tag } =
args;
const logWrapper = createLogWrapper(log);
@@ -116,6 +118,7 @@ export async function updateTaskByIdDirect(args, log, context = {}) {
mcpLog: logWrapper,
session,
projectRoot,
tag,
commandName: 'update-task',
outputType: 'mcp'
},

View File

@@ -15,6 +15,12 @@ import {
* Direct function wrapper for updating tasks based on new context.
*
* @param {Object} args - Command arguments containing projectRoot, from, prompt, research options.
* @param {string} args.from - The ID of the task to update.
* @param {string} args.prompt - The prompt to update the task with.
* @param {boolean} args.research - Whether to use research mode.
* @param {string} args.tasksJsonPath - Path to the tasks.json file.
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object.
* @param {Object} context - Context object containing session data.
* @returns {Promise<Object>} - Result object with success status and data/error information.

View File

@@ -13,12 +13,14 @@ import fs from 'fs';
* Validate dependencies in tasks.json
* @param {Object} args - Function arguments
* @param {string} args.tasksJsonPath - Explicit path to the tasks.json file.
* @param {string} args.projectRoot - Project root path (for MCP/env fallback)
* @param {string} args.tag - Tag for the task (optional)
* @param {Object} log - Logger object
* @returns {Promise<{success: boolean, data?: Object, error?: {code: string, message: string}}>}
*/
export async function validateDependenciesDirect(args, log) {
// Destructure the explicit tasksJsonPath
const { tasksJsonPath } = args;
const { tasksJsonPath, projectRoot, tag } = args;
if (!tasksJsonPath) {
log.error('validateDependenciesDirect called without tasksJsonPath');
@@ -51,8 +53,9 @@ export async function validateDependenciesDirect(args, log) {
// Enable silent mode to prevent console logs from interfering with JSON response
enableSilentMode();
const options = { projectRoot, tag };
// Call the original command function using the provided tasksPath
await validateDependenciesCommand(tasksPath);
await validateDependenciesCommand(tasksPath, options);
// Restore normal logging
disableSilentMode();

View File

@@ -121,6 +121,7 @@ export function resolveComplexityReportPath(args, log = silentLogger) {
// Get explicit path from args.complexityReport if provided
const explicitPath = args?.complexityReport;
const rawProjectRoot = args?.projectRoot;
const tag = args?.tag;
// If explicit path is provided and absolute, use it directly
if (explicitPath && path.isAbsolute(explicitPath)) {
@@ -139,7 +140,11 @@ export function resolveComplexityReportPath(args, log = silentLogger) {
// Use core findComplexityReportPath with explicit path and normalized projectRoot context
if (projectRoot) {
return coreFindComplexityReportPath(explicitPath, { projectRoot }, log);
return coreFindComplexityReportPath(
explicitPath,
{ projectRoot, tag },
log
);
}
// Fallback to core function without projectRoot context

View File

@@ -32,10 +32,6 @@ class TaskMasterMCPServer {
this.server = new FastMCP(this.options);
this.initialized = false;
this.server.addResource({});
this.server.addResourceTemplate({});
// Bind methods
this.init = this.init.bind(this);
this.start = this.start.bind(this);

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { addDependencyDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the addDependency tool with the MCP server
@@ -33,14 +34,18 @@ export function registerAddDependencyTool(server) {
),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
log.info(
`Adding dependency for task ${args.id} to depend on ${args.dependsOn}`
);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
let tasksJsonPath;
try {
tasksJsonPath = findTasksPath(
@@ -61,7 +66,9 @@ export function registerAddDependencyTool(server) {
tasksJsonPath: tasksJsonPath,
// Pass other relevant args
id: args.id,
dependsOn: args.dependsOn
dependsOn: args.dependsOn,
projectRoot: args.projectRoot,
tag: resolvedTag
},
log
// Remove context object

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { addSubtaskDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the addSubtask tool with the MCP server
@@ -52,17 +53,21 @@ export function registerAddSubtaskTool(server) {
.describe(
'Absolute path to the tasks file (default: tasks/tasks.json)'
),
tag: z.string().optional().describe('Tag context to operate on'),
skipGenerate: z
.boolean()
.optional()
.describe('Skip regenerating task files'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(`Adding subtask with args: ${JSON.stringify(args)}`);
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
@@ -91,7 +96,7 @@ export function registerAddSubtaskTool(server) {
dependencies: args.dependencies,
skipGenerate: args.skipGenerate,
projectRoot: args.projectRoot,
tag: args.tag
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { addTaskDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the addTask tool with the MCP server
@@ -58,6 +59,7 @@ export function registerAddTaskTool(server) {
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on'),
research: z
.boolean()
.optional()
@@ -67,6 +69,11 @@ export function registerAddTaskTool(server) {
try {
log.info(`Starting add-task with args: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -93,7 +100,8 @@ export function registerAddTaskTool(server) {
dependencies: args.dependencies,
priority: args.priority,
research: args.research,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -13,7 +13,9 @@ import {
} from './utils.js';
import { analyzeTaskComplexityDirect } from '../core/task-master-core.js'; // Assuming core functions are exported via task-master-core.js
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
import { COMPLEXITY_REPORT_FILE } from '../../../src/constants/paths.js';
import { resolveComplexityReportOutputPath } from '../../../src/utils/path-utils.js';
/**
* Register the analyze_project_complexity tool
@@ -70,15 +72,22 @@ export function registerAnalyzeProjectComplexityTool(server) {
.describe('Ending task ID in a range to analyze.'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
const toolName = 'analyze_project_complexity'; // Define tool name for logging
try {
log.info(
`Executing ${toolName} tool with args: ${JSON.stringify(args)}`
);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
let tasksJsonPath;
try {
tasksJsonPath = findTasksPath(
@@ -93,9 +102,14 @@ export function registerAnalyzeProjectComplexityTool(server) {
);
}
const outputPath = args.output
? path.resolve(args.projectRoot, args.output)
: path.resolve(args.projectRoot, COMPLEXITY_REPORT_FILE);
const outputPath = resolveComplexityReportOutputPath(
args.output,
{
projectRoot: args.projectRoot,
tag: resolvedTag
},
log
);
log.info(`${toolName}: Report output path: ${outputPath}`);
@@ -123,6 +137,7 @@ export function registerAnalyzeProjectComplexityTool(server) {
threshold: args.threshold,
research: args.research,
projectRoot: args.projectRoot,
tag: resolvedTag,
ids: args.ids,
from: args.from,
to: args.to

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { clearSubtasksDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the clearSubtasks tool with the MCP server
@@ -46,6 +47,11 @@ export function registerClearSubtasksTool(server) {
try {
log.info(`Clearing subtasks with args: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -65,8 +71,9 @@ export function registerClearSubtasksTool(server) {
tasksJsonPath: tasksJsonPath,
id: args.id,
all: args.all,
projectRoot: args.projectRoot,
tag: args.tag || 'master'
tag: resolvedTag
},
log,
{ session }

View File

@@ -12,6 +12,7 @@ import {
import { complexityReportDirect } from '../core/task-master-core.js';
import { COMPLEXITY_REPORT_FILE } from '../../../src/constants/paths.js';
import { findComplexityReportPath } from '../core/utils/path-utils.js';
import { getCurrentTag } from '../../../scripts/modules/utils.js';
/**
* Register the complexityReport tool with the MCP server
@@ -38,12 +39,16 @@ export function registerComplexityReportTool(server) {
`Getting complexity report with args: ${JSON.stringify(args)}`
);
const resolvedTag = getCurrentTag(args.projectRoot);
const pathArgs = {
projectRoot: args.projectRoot,
complexityReport: args.file
complexityReport: args.file,
tag: resolvedTag
};
const reportPath = findComplexityReportPath(pathArgs, log);
log.info('Reading complexity report from path: ', reportPath);
if (!reportPath) {
return createErrorResponse(

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { expandAllTasksDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the expandAll tool with the MCP server
@@ -57,7 +58,8 @@ export function registerExpandAllTool(server) {
.optional()
.describe(
'Absolute path to the project root directory (derived from session if possible)'
)
),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
@@ -65,6 +67,10 @@ export function registerExpandAllTool(server) {
`Tool expand_all execution started with args: ${JSON.stringify(args)}`
);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
let tasksJsonPath;
try {
tasksJsonPath = findTasksPath(
@@ -86,7 +92,8 @@ export function registerExpandAllTool(server) {
research: args.research,
prompt: args.prompt,
force: args.force,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -10,7 +10,11 @@ import {
withNormalizedProjectRoot
} from './utils.js';
import { expandTaskDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import {
findTasksPath,
findComplexityReportPath
} from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the expand-task tool with the MCP server
@@ -51,7 +55,10 @@ export function registerExpandTaskTool(server) {
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
log.info(`Starting expand-task with args: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -66,6 +73,11 @@ export function registerExpandTaskTool(server) {
);
}
const complexityReportPath = findComplexityReportPath(
{ ...args, tag: resolvedTag },
log
);
const result = await expandTaskDirect(
{
tasksJsonPath: tasksJsonPath,
@@ -74,8 +86,9 @@ export function registerExpandTaskTool(server) {
research: args.research,
prompt: args.prompt,
force: args.force,
complexityReportPath,
projectRoot: args.projectRoot,
tag: args.tag || 'master'
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,7 +11,7 @@ import {
} from './utils.js';
import { fixDependenciesDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the fixDependencies tool with the MCP server
* @param {Object} server - FastMCP server instance
@@ -31,6 +31,11 @@ export function registerFixDependenciesTool(server) {
try {
log.info(`Fixing dependencies with args: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -49,7 +54,7 @@ export function registerFixDependenciesTool(server) {
{
tasksJsonPath: tasksJsonPath,
projectRoot: args.projectRoot,
tag: args.tag
tag: resolvedTag
},
log
);

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { generateTaskFilesDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
import path from 'path';
/**
@@ -30,12 +31,17 @@ export function registerGenerateTool(server) {
.describe('Output directory (default: same directory as tasks file)'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
log.info(`Generating task files with args: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -58,7 +64,8 @@ export function registerGenerateTool(server) {
{
tasksJsonPath: tasksJsonPath,
outputDir: outputDir,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -14,6 +14,7 @@ import {
findTasksPath,
findComplexityReportPath
} from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Custom processor function that removes allTasks from the response
@@ -67,7 +68,8 @@ export function registerShowTaskTool(server) {
.string()
.describe(
'Absolute path to the project root directory (Optional, usually from session)'
)
),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
const { id, file, status, projectRoot } = args;
@@ -76,6 +78,10 @@ export function registerShowTaskTool(server) {
log.info(
`Getting task details for ID: ${id}${status ? ` (filtering subtasks by status: ${status})` : ''} in root: ${projectRoot}`
);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Resolve the path to tasks.json using the NORMALIZED projectRoot from args
let tasksJsonPath;
@@ -99,7 +105,8 @@ export function registerShowTaskTool(server) {
complexityReportPath = findComplexityReportPath(
{
projectRoot: projectRoot,
complexityReport: args.complexityReport
complexityReport: args.complexityReport,
tag: resolvedTag
},
log
);
@@ -113,7 +120,8 @@ export function registerShowTaskTool(server) {
// Pass other relevant args
id: id,
status: status,
projectRoot: projectRoot
projectRoot: projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -15,6 +15,8 @@ import {
resolveComplexityReportPath
} from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the getTasks tool with the MCP server
* @param {Object} server - FastMCP server instance
@@ -51,12 +53,17 @@ export function registerListTasksTool(server) {
),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
log.info(`Getting tasks with filters: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Resolve the path to tasks.json using new path utilities
let tasksJsonPath;
try {
@@ -71,7 +78,10 @@ export function registerListTasksTool(server) {
// Resolve the path to complexity report
let complexityReportPath;
try {
complexityReportPath = resolveComplexityReportPath(args, session);
complexityReportPath = resolveComplexityReportPath(
{ ...args, tag: resolvedTag },
session
);
} catch (error) {
log.error(`Error finding complexity report: ${error.message}`);
// This is optional, so we don't fail the operation
@@ -84,7 +94,8 @@ export function registerListTasksTool(server) {
status: args.status,
withSubtasks: args.withSubtasks,
reportPath: complexityReportPath,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { moveTaskDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the moveTask tool with the MCP server
@@ -36,10 +37,15 @@ export function registerMoveTaskTool(server) {
.string()
.describe(
'Root directory of the project (typically derived from session)'
)
),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Find tasks.json path if not provided
let tasksJsonPath = args.file;
@@ -79,7 +85,8 @@ export function registerMoveTaskTool(server) {
sourceId: fromId,
destinationId: toId,
tasksJsonPath,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }
@@ -115,7 +122,8 @@ export function registerMoveTaskTool(server) {
sourceId: args.from,
destinationId: args.to,
tasksJsonPath,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -14,6 +14,7 @@ import {
resolveTasksPath,
resolveComplexityReportPath
} from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the nextTask tool with the MCP server
@@ -34,11 +35,16 @@ export function registerNextTaskTool(server) {
),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
log.info(`Finding next task with args: ${JSON.stringify(args)}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Resolve the path to tasks.json using new path utilities
let tasksJsonPath;
@@ -54,7 +60,10 @@ export function registerNextTaskTool(server) {
// Resolve the path to complexity report (optional)
let complexityReportPath;
try {
complexityReportPath = resolveComplexityReportPath(args, session);
complexityReportPath = resolveComplexityReportPath(
{ ...args, tag: resolvedTag },
session
);
} catch (error) {
log.error(`Error finding complexity report: ${error.message}`);
// This is optional, so we don't fail the operation
@@ -65,7 +74,8 @@ export function registerNextTaskTool(server) {
{
tasksJsonPath: tasksJsonPath,
reportPath: complexityReportPath,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -15,6 +15,7 @@ import {
TASKMASTER_DOCS_DIR,
TASKMASTER_TASKS_FILE
} from '../../../src/constants/paths.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the parse_prd tool
@@ -24,6 +25,7 @@ export function registerParsePRDTool(server) {
server.addTool({
name: 'parse_prd',
description: `Parse a Product Requirements Document (PRD) text file to automatically generate initial tasks. Reinitializing the project is not necessary to run this tool. It is recommended to run parse-prd after initializing the project and creating/importing a prd.txt file in the project root's ${TASKMASTER_DOCS_DIR} directory.`,
parameters: z.object({
input: z
.string()
@@ -33,6 +35,7 @@ export function registerParsePRDTool(server) {
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on'),
output: z
.string()
.optional()
@@ -63,7 +66,18 @@ export function registerParsePRDTool(server) {
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const result = await parsePRDDirect(args, log, { session });
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
const result = await parsePRDDirect(
{
...args,
tag: resolvedTag
},
log,
{ session }
);
return handleApiResult(
result,
log,

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { removeDependencyDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the removeDependency tool with the MCP server
@@ -31,10 +32,15 @@ export function registerRemoveDependencyTool(server) {
),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(
`Removing dependency for task ${args.id} from ${args.dependsOn} with args: ${JSON.stringify(args)}`
);
@@ -57,7 +63,9 @@ export function registerRemoveDependencyTool(server) {
{
tasksJsonPath: tasksJsonPath,
id: args.id,
dependsOn: args.dependsOn
dependsOn: args.dependsOn,
projectRoot: args.projectRoot,
tag: resolvedTag
},
log
);

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { removeSubtaskDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the removeSubtask tool with the MCP server
@@ -44,10 +45,15 @@ export function registerRemoveSubtaskTool(server) {
.describe('Skip regenerating task files'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(`Removing subtask with args: ${JSON.stringify(args)}`);
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
@@ -70,7 +76,8 @@ export function registerRemoveSubtaskTool(server) {
id: args.id,
convert: args.convert,
skipGenerate: args.skipGenerate,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { removeTaskDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the remove-task tool with the MCP server
@@ -45,6 +46,11 @@ export function registerRemoveTaskTool(server) {
try {
log.info(`Removing task(s) with ID(s): ${args.id}`);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -66,7 +72,7 @@ export function registerRemoveTaskTool(server) {
tasksJsonPath: tasksJsonPath,
id: args.id,
projectRoot: args.projectRoot,
tag: args.tag
tag: resolvedTag
},
log,
{ session }

View File

@@ -10,6 +10,7 @@ import {
withNormalizedProjectRoot
} from './utils.js';
import { researchDirect } from '../core/task-master-core.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the research tool with the MCP server
@@ -19,6 +20,7 @@ export function registerResearchTool(server) {
server.addTool({
name: 'research',
description: 'Perform AI-powered research queries with project context',
parameters: z.object({
query: z.string().describe('Research query/prompt (required)'),
taskIds: z
@@ -61,10 +63,15 @@ export function registerResearchTool(server) {
),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(
`Starting research with query: "${args.query.substring(0, 100)}${args.query.length > 100 ? '...' : ''}"`
);
@@ -80,7 +87,8 @@ export function registerResearchTool(server) {
detailLevel: args.detailLevel || 'medium',
saveTo: args.saveTo,
saveToFile: args.saveToFile || false,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -18,6 +18,7 @@ import {
findComplexityReportPath
} from '../core/utils/path-utils.js';
import { TASK_STATUS_OPTIONS } from '../../../src/constants/task-status.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the setTaskStatus tool with the MCP server
@@ -52,8 +53,15 @@ export function registerSetTaskStatusTool(server) {
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
log.info(`Setting status of task(s) ${args.id} to: ${args.status}`);
log.info(
`Setting status of task(s) ${args.id} to: ${args.status} ${
args.tag ? `in tag: ${args.tag}` : 'in current tag'
}`
);
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
let tasksJsonPath;
try {
@@ -73,7 +81,8 @@ export function registerSetTaskStatusTool(server) {
complexityReportPath = findComplexityReportPath(
{
projectRoot: args.projectRoot,
complexityReport: args.complexityReport
complexityReport: args.complexityReport,
tag: resolvedTag
},
log
);
@@ -88,7 +97,7 @@ export function registerSetTaskStatusTool(server) {
status: args.status,
complexityReportPath,
projectRoot: args.projectRoot,
tag: args.tag
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { updateSubtaskByIdDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the update-subtask tool with the MCP server
@@ -35,11 +36,17 @@ export function registerUpdateSubtaskTool(server) {
file: z.string().optional().describe('Absolute path to the tasks file'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
const toolName = 'update_subtask';
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(`Updating subtask with args: ${JSON.stringify(args)}`);
let tasksJsonPath;
@@ -61,7 +68,8 @@ export function registerUpdateSubtaskTool(server) {
id: args.id,
prompt: args.prompt,
research: args.research,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { updateTaskByIdDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the update-task tool with the MCP server
@@ -43,11 +44,16 @@ export function registerUpdateTaskTool(server) {
file: z.string().optional().describe('Absolute path to the tasks file'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
const toolName = 'update_task';
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(
`Executing ${toolName} tool with args: ${JSON.stringify(args)}`
);
@@ -74,7 +80,8 @@ export function registerUpdateTaskTool(server) {
prompt: args.prompt,
research: args.research,
append: args.append,
projectRoot: args.projectRoot
projectRoot: args.projectRoot,
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { updateTasksDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the update tool with the MCP server
@@ -50,6 +51,11 @@ export function registerUpdateTool(server) {
const toolName = 'update';
const { from, prompt, research, file, projectRoot, tag } = args;
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
try {
log.info(
`Executing ${toolName} tool with normalized root: ${projectRoot}`
@@ -73,7 +79,7 @@ export function registerUpdateTool(server) {
prompt: prompt,
research: research,
projectRoot: projectRoot,
tag: tag
tag: resolvedTag
},
log,
{ session }

View File

@@ -11,6 +11,7 @@ import {
} from './utils.js';
import { validateDependenciesDirect } from '../core/task-master-core.js';
import { findTasksPath } from '../core/utils/path-utils.js';
import { resolveTag } from '../../../scripts/modules/utils.js';
/**
* Register the validateDependencies tool with the MCP server
@@ -25,10 +26,15 @@ export function registerValidateDependenciesTool(server) {
file: z.string().optional().describe('Absolute path to the tasks file'),
projectRoot: z
.string()
.describe('The directory of the project. Must be an absolute path.')
.describe('The directory of the project. Must be an absolute path.'),
tag: z.string().optional().describe('Tag context to operate on')
}),
execute: withNormalizedProjectRoot(async (args, { log, session }) => {
try {
const resolvedTag = resolveTag({
projectRoot: args.projectRoot,
tag: args.tag
});
log.info(`Validating dependencies with args: ${JSON.stringify(args)}`);
// Use args.projectRoot directly (guaranteed by withNormalizedProjectRoot)
@@ -47,7 +53,9 @@ export function registerValidateDependenciesTool(server) {
const result = await validateDependenciesDirect(
{
tasksJsonPath: tasksJsonPath
tasksJsonPath: tasksJsonPath,
projectRoot: args.projectRoot,
tag: resolvedTag
},
log
);

View File

@@ -1,6 +1,6 @@
{
"name": "task-master-ai",
"version": "0.20.0",
"version": "0.21.0",
"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
"main": "index.js",
"type": "module",
@@ -9,7 +9,10 @@
"task-master-mcp": "mcp-server/server.js",
"task-master-ai": "mcp-server/server.js"
},
"workspaces": ["apps/*", "."],
"workspaces": [
"apps/*",
"."
],
"scripts": {
"test": "node --experimental-vm-modules node_modules/.bin/jest",
"test:fails": "node --experimental-vm-modules node_modules/.bin/jest --onlyFailures",

View File

@@ -826,7 +826,8 @@ function registerCommands(programInstance) {
let taskMaster;
try {
const initOptions = {
prdPath: file || options.input || true
prdPath: file || options.input || true,
tag: options.tag
};
// Only include tasksPath if output is explicitly specified
if (options.output) {
@@ -852,8 +853,7 @@ function registerCommands(programInstance) {
const useAppend = append;
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -966,7 +966,8 @@ function registerCommands(programInstance) {
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const fromId = parseInt(options.from, 10); // Validation happens here
@@ -976,8 +977,7 @@ function registerCommands(programInstance) {
const tasksPath = taskMaster.getTasksPath();
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -1066,13 +1066,13 @@ function registerCommands(programInstance) {
try {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const tasksPath = taskMaster.getTasksPath();
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -1238,13 +1238,13 @@ function registerCommands(programInstance) {
try {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const tasksPath = taskMaster.getTasksPath();
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -1404,11 +1404,12 @@ function registerCommands(programInstance) {
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const outputDir = options.output;
const tag = options.tag;
const tag = taskMaster.getCurrentTag();
console.log(
chalk.blue(`Generating task files from: ${taskMaster.getTasksPath()}`)
@@ -1444,12 +1445,12 @@ function registerCommands(programInstance) {
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const taskId = options.id;
const status = options.status;
const tag = options.tag;
if (!taskId || !status) {
console.error(chalk.red('Error: Both --id and --status are required'));
@@ -1465,11 +1466,9 @@ function registerCommands(programInstance) {
process.exit(1);
}
const tag = taskMaster.getCurrentTag();
// Resolve tag using standard pattern and show current tag context
const resolvedTag =
tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
displayCurrentTagIndicator(resolvedTag);
displayCurrentTagIndicator(tag);
console.log(
chalk.blue(`Setting status of task(s) ${taskId} to: ${status}`)
@@ -1501,7 +1500,8 @@ function registerCommands(programInstance) {
.action(async (options) => {
// Initialize TaskMaster
const initOptions = {
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
};
// Only pass complexityReportPath if user provided a custom path
@@ -1513,9 +1513,7 @@ function registerCommands(programInstance) {
const statusFilter = options.status;
const withSubtasks = options.withSubtasks || false;
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -1535,8 +1533,7 @@ function registerCommands(programInstance) {
taskMaster.getComplexityReportPath(),
withSubtasks,
'text',
tag,
{ projectRoot: taskMaster.getProjectRoot() }
{ projectRoot: taskMaster.getProjectRoot(), tag }
);
});
@@ -1565,18 +1562,29 @@ function registerCommands(programInstance) {
'Path to the tasks file (relative to project root)',
TASKMASTER_TASKS_FILE // Allow file override
) // Allow file override
.option(
'-cr, --complexity-report <file>',
'Path to the report file',
COMPLEXITY_REPORT_FILE
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
});
const tag = options.tag;
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
if (options.complexityReport) {
initOptions.complexityReportPath = options.complexityReport;
}
const taskMaster = initTaskMaster(initOptions);
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(
tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master'
);
displayCurrentTagIndicator(tag);
if (options.all) {
// --- Handle expand --all ---
@@ -1589,7 +1597,11 @@ function registerCommands(programInstance) {
options.research, // Pass research flag
options.prompt, // Pass additional context
options.force, // Pass force flag
{ projectRoot: taskMaster.getProjectRoot(), tag } // Pass context with projectRoot and tag
{
projectRoot: taskMaster.getProjectRoot(),
tag,
complexityReportPath: taskMaster.getComplexityReportPath()
} // Pass context with projectRoot and tag
// outputFormat defaults to 'text' in expandAllTasks for CLI
);
} catch (error) {
@@ -1616,7 +1628,11 @@ function registerCommands(programInstance) {
options.num,
options.research,
options.prompt,
{ projectRoot: taskMaster.getProjectRoot(), tag }, // Pass context with projectRoot and tag
{
projectRoot: taskMaster.getProjectRoot(),
tag,
complexityReportPath: taskMaster.getComplexityReportPath()
}, // Pass context with projectRoot and tag
options.force // Pass the force flag down
);
// expandTask logs its own success/failure for single task
@@ -1669,34 +1685,28 @@ function registerCommands(programInstance) {
.action(async (options) => {
// Initialize TaskMaster
const initOptions = {
tasksPath: options.file || true // Tasks file is required to analyze
tasksPath: options.file || true, // Tasks file is required to analyze
tag: options.tag
};
// Only include complexityReportPath if output is explicitly specified
if (options.output) {
initOptions.complexityReportPath = options.output;
}
const taskMaster = initTaskMaster(initOptions);
const tag = options.tag;
const modelOverride = options.model;
const thresholdScore = parseFloat(options.threshold);
const useResearch = options.research || false;
// Use the provided tag, or the current active tag, or default to 'master'
const targetTag =
tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const targetTag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(targetTag);
// Tag-aware output file naming: master -> task-complexity-report.json, other tags -> task-complexity-report_tagname.json
const baseOutputPath =
taskMaster.getComplexityReportPath() ||
path.join(taskMaster.getProjectRoot(), COMPLEXITY_REPORT_FILE);
const outputPath =
options.output === COMPLEXITY_REPORT_FILE && targetTag !== 'master'
? baseOutputPath.replace('.json', `_${targetTag}.json`)
: options.output || baseOutputPath;
// Use user's explicit output path if provided, otherwise use tag-aware default
const outputPath = taskMaster.getComplexityReportPath();
console.log(
chalk.blue(
@@ -1777,9 +1787,12 @@ function registerCommands(programInstance) {
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (prompt, options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
});
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
const taskMaster = initTaskMaster(initOptions);
// Parameter validation
if (!prompt || typeof prompt !== 'string' || prompt.trim().length === 0) {
@@ -1879,8 +1892,7 @@ function registerCommands(programInstance) {
}
}
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -2113,17 +2125,17 @@ ${result.result}
.action(async (options) => {
const taskIds = options.id;
const all = options.all;
const tag = options.tag;
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(
tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master'
);
displayCurrentTagIndicator(tag);
if (!taskIds && !all) {
console.error(
@@ -2219,15 +2231,16 @@ ${result.result}
// Correctly determine projectRoot
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const projectRoot = taskMaster.getProjectRoot();
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master'
);
displayCurrentTagIndicator(tag);
let manualTaskData = null;
if (isManualCreation) {
@@ -2263,7 +2276,7 @@ ${result.result}
const context = {
projectRoot,
tag: options.tag,
tag,
commandName: 'add-task',
outputType: 'cli'
};
@@ -2309,22 +2322,36 @@ ${result.result}
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
const tag = options.tag;
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
if (options.report && options.report !== COMPLEXITY_REPORT_FILE) {
initOptions.complexityReportPath = options.report;
}
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag,
complexityReportPath: options.report || false
});
const tag = taskMaster.getCurrentTag();
const context = {
projectRoot: taskMaster.getProjectRoot(),
tag
};
// Show current tag context
displayCurrentTagIndicator(
tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master'
);
displayCurrentTagIndicator(tag);
await displayNextTask(
taskMaster.getTasksPath(),
taskMaster.getComplexityReportPath(),
{ projectRoot: taskMaster.getProjectRoot(), tag }
context
);
});
@@ -2364,12 +2391,10 @@ ${result.result}
const idArg = taskId || options.id;
const statusFilter = options.status;
const tag = options.tag;
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(
tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master'
);
displayCurrentTagIndicator(tag);
if (!idArg) {
console.error(chalk.red('Error: Please provide a task ID'));
@@ -2398,8 +2423,7 @@ ${result.result}
taskIds[0],
taskMaster.getComplexityReportPath(),
statusFilter,
tag,
{ projectRoot: taskMaster.getProjectRoot() }
{ projectRoot: taskMaster.getProjectRoot(), tag }
);
}
});
@@ -2417,17 +2441,19 @@ ${result.result}
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
});
const taskMaster = initTaskMaster(initOptions);
const taskId = options.id;
const dependencyId = options.dependsOn;
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -2472,17 +2498,19 @@ ${result.result}
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
});
const taskMaster = initTaskMaster(initOptions);
const taskId = options.id;
const dependencyId = options.dependsOn;
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -2527,14 +2555,16 @@ ${result.result}
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
});
const taskMaster = initTaskMaster(initOptions);
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -2555,14 +2585,16 @@ ${result.result}
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
const initOptions = {
tasksPath: options.file || true,
tag: options.tag
};
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
});
const taskMaster = initTaskMaster(initOptions);
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -2583,26 +2615,21 @@ ${result.result}
)
.option('--tag <tag>', 'Specify tag context for task operations')
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
complexityReportPath: options.file || true
});
const initOptions = {
tag: options.tag
};
// Use the provided tag, or the current active tag, or default to 'master'
const targetTag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
if (options.file && options.file !== COMPLEXITY_REPORT_FILE) {
initOptions.complexityReportPath = options.file;
}
// Initialize TaskMaster
const taskMaster = initTaskMaster(initOptions);
// Show current tag context
displayCurrentTagIndicator(targetTag);
displayCurrentTagIndicator(taskMaster.getCurrentTag());
// Tag-aware report file naming: master -> task-complexity-report.json, other tags -> task-complexity-report_tagname.json
const baseReportPath = taskMaster.getComplexityReportPath();
const reportPath =
options.file === COMPLEXITY_REPORT_FILE && targetTag !== 'master'
? baseReportPath.replace('.json', `_${targetTag}.json`)
: baseReportPath;
await displayComplexityReport(reportPath);
await displayComplexityReport(taskMaster.getComplexityReportPath());
});
// add-subtask command
@@ -2632,7 +2659,8 @@ ${result.result}
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const parentId = options.parent;
@@ -2640,8 +2668,7 @@ ${result.result}
const generateFiles = !options.skipGenerate;
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -2816,13 +2843,14 @@ ${result.result}
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const subtaskIds = options.id;
const convertToTask = options.convert || false;
const generateFiles = !options.skipGenerate;
const tag = options.tag;
const tag = taskMaster.getCurrentTag();
if (!subtaskIds) {
console.error(
@@ -3117,14 +3145,14 @@ ${result.result}
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const taskIdsString = options.id;
// Resolve tag using standard pattern
const tag =
options.tag || getCurrentTag(taskMaster.getProjectRoot()) || 'master';
const tag = taskMaster.getCurrentTag();
// Show current tag context
displayCurrentTagIndicator(tag);
@@ -3699,10 +3727,7 @@ Examples:
const taskMaster = initTaskMaster({});
const projectRoot = taskMaster.getProjectRoot(); // Find project root for context
const { response, setup } = options;
console.log(
chalk.blue('Response language set to:', JSON.stringify(options))
);
let responseLanguage = response || 'English';
let responseLanguage = response !== undefined ? response : 'English';
if (setup) {
console.log(
chalk.blue('Starting interactive response language setup...')
@@ -3744,6 +3769,7 @@ Examples:
`❌ Error setting response language: ${result.error.message}`
)
);
process.exit(1);
}
});
@@ -3768,12 +3794,13 @@ Examples:
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const sourceId = options.from;
const destinationId = options.to;
const tag = options.tag;
const tag = taskMaster.getCurrentTag();
if (!sourceId || !destinationId) {
console.error(
@@ -4201,15 +4228,19 @@ Examples:
'-s, --status <status>',
'Show only tasks matching this status (e.g., pending, done)'
)
.option('-t, --tag <tag>', 'Tag to use for the task list (default: master)')
.action(async (options) => {
// Initialize TaskMaster
const taskMaster = initTaskMaster({
tasksPath: options.file || true
tasksPath: options.file || true,
tag: options.tag
});
const withSubtasks = options.withSubtasks || false;
const status = options.status || null;
const tag = taskMaster.getCurrentTag();
console.log(
chalk.blue(
`📝 Syncing tasks to README.md${withSubtasks ? ' (with subtasks)' : ''}${status ? ` (status: ${status})` : ''}...`
@@ -4219,7 +4250,8 @@ Examples:
const success = await syncTasksToReadme(taskMaster.getProjectRoot(), {
withSubtasks,
status,
tasksPath: taskMaster.getTasksPath()
tasksPath: taskMaster.getTasksPath(),
tag
});
if (!success) {
@@ -4941,6 +4973,33 @@ async function runCLI(argv = process.argv) {
}
}
/**
* Resolve the final complexity-report path.
* Rules:
* 1. If caller passes --output, always respect it.
* 2. If no explicit output AND tag === 'master' → default report file
* 3. If no explicit output AND tag !== 'master' → append _<tag>.json
*
* @param {string|undefined} outputOpt --output value from CLI (may be undefined)
* @param {string} targetTag resolved tag (defaults to 'master')
* @param {string} projectRoot absolute project root
* @returns {string} absolute path for the report
*/
export function resolveComplexityReportPath({
projectRoot,
tag = 'master',
output // may be undefined
}) {
// 1. user knows best
if (output) {
return path.isAbsolute(output) ? output : path.join(projectRoot, output);
}
// 2. default naming
const base = path.join(projectRoot, COMPLEXITY_REPORT_FILE);
return tag !== 'master' ? base.replace('.json', `_${tag}.json`) : base;
}
export {
registerCommands,
setupCLI,

View File

@@ -27,6 +27,8 @@ import { generateTaskFiles } from './task-manager.js';
* @param {number|string} taskId - ID of the task to add dependency to
* @param {number|string} dependencyId - ID of the task to add as dependency
* @param {Object} context - Context object containing projectRoot and tag information
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
*/
async function addDependency(tasksPath, taskId, dependencyId, context = {}) {
log('info', `Adding dependency ${dependencyId} to task ${taskId}...`);
@@ -214,6 +216,8 @@ async function addDependency(tasksPath, taskId, dependencyId, context = {}) {
* @param {number|string} taskId - ID of the task to remove dependency from
* @param {number|string} dependencyId - ID of the task to remove as dependency
* @param {Object} context - Context object containing projectRoot and tag information
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
*/
async function removeDependency(tasksPath, taskId, dependencyId, context = {}) {
log('info', `Removing dependency ${dependencyId} from task ${taskId}...`);

View File

@@ -303,7 +303,7 @@
"output": 3.0
},
"allowed_roles": ["main", "fallback"],
"max_tokens": 16384
"max_tokens": 131072
},
{
"id": "llama-3.3-70b-versatile",

View File

@@ -91,11 +91,12 @@ function createEndMarker() {
* @param {string} options.status - Filter by status (e.g., 'pending', 'done')
* @param {string} options.tasksPath - Custom path to tasks.json
* @returns {boolean} - True if sync was successful, false otherwise
* TODO: Add tag support - this is not currently supported how we want to handle this - Parthy
*/
export async function syncTasksToReadme(projectRoot = null, options = {}) {
try {
const actualProjectRoot = projectRoot || findProjectRoot() || '.';
const { withSubtasks = false, status, tasksPath } = options;
const { withSubtasks = false, status, tasksPath, tag } = options;
// Get current tasks using the list-tasks functionality with markdown-readme format
const tasksOutput = await listTasks(
@@ -104,7 +105,8 @@ export async function syncTasksToReadme(projectRoot = null, options = {}) {
status,
null,
withSubtasks,
'markdown-readme'
'markdown-readme',
{ projectRoot, tag }
);
if (!tasksOutput) {

View File

@@ -12,6 +12,8 @@ import generateTaskFiles from './generate-task-files.js';
* @param {Object} newSubtaskData - Data for creating a new subtask (used if existingTaskId is null)
* @param {boolean} generateFiles - Whether to regenerate task files after adding the subtask
* @param {Object} context - Context object containing projectRoot and tag information
* @param {string} context.projectRoot - Project root path
* @param {string} context.tag - Tag for the task
* @returns {Object} The newly created or converted subtask
*/
async function addSubtask(
@@ -22,13 +24,12 @@ async function addSubtask(
generateFiles = true,
context = {}
) {
const { projectRoot, tag } = context;
try {
log('info', `Adding subtask to parent task ${parentId}...`);
const currentTag =
context.tag || getCurrentTag(context.projectRoot) || 'master';
// Read the existing tasks with proper context
const data = readJSON(tasksPath, context.projectRoot, currentTag);
const data = readJSON(tasksPath, projectRoot, tag);
if (!data || !data.tasks) {
throw new Error(`Invalid or missing tasks file at ${tasksPath}`);
}
@@ -139,7 +140,7 @@ async function addSubtask(
}
// Write the updated tasks back to the file with proper context
writeJSON(tasksPath, data, context.projectRoot, currentTag);
writeJSON(tasksPath, data, projectRoot, tag);
// Generate task files if requested
if (generateFiles) {

View File

@@ -22,8 +22,7 @@ import {
truncate,
ensureTagMetadata,
performCompleteTagMigration,
markMigrationForNotice,
getCurrentTag
markMigrationForNotice
} from '../utils.js';
import { generateObjectService } from '../ai-services-unified.js';
import { getDefaultPriority } from '../config-manager.js';
@@ -93,7 +92,7 @@ function getAllTasks(rawData) {
* @param {string} [context.projectRoot] - Project root path (for MCP/env fallback)
* @param {string} [context.commandName] - The name of the command being executed (for telemetry)
* @param {string} [context.outputType] - The output type ('cli' or 'mcp', for telemetry)
* @param {string} [tag] - Tag for the task (optional)
* @param {string} [context.tag] - Tag for the task (optional)
* @returns {Promise<object>} An object containing newTaskId and telemetryData
*/
async function addTask(
@@ -104,10 +103,10 @@ async function addTask(
context = {},
outputFormat = 'text', // Default to text for CLI
manualTaskData = null,
useResearch = false,
tag = null
useResearch = false
) {
const { session, mcpLog, projectRoot, commandName, outputType } = context;
const { session, mcpLog, projectRoot, commandName, outputType, tag } =
context;
const isMCP = !!mcpLog;
// Create a consistent logFn object regardless of context
@@ -224,7 +223,7 @@ async function addTask(
try {
// Read the existing tasks - IMPORTANT: Read the raw data without tag resolution
let rawData = readJSON(tasksPath, projectRoot); // No tag parameter
let rawData = readJSON(tasksPath, projectRoot, tag); // No tag parameter
// Handle the case where readJSON returns resolved data with _rawTaggedData
if (rawData && rawData._rawTaggedData) {
@@ -279,8 +278,7 @@ async function addTask(
}
// Use the provided tag, or the current active tag, or default to 'master'
const targetTag =
tag || context.tag || getCurrentTag(projectRoot) || 'master';
const targetTag = tag;
// Ensure the target tag exists
if (!rawData[targetTag]) {
@@ -389,7 +387,7 @@ async function addTask(
report(`Generating task data with AI with prompt:\n${prompt}`, 'info');
// --- Use the new ContextGatherer ---
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
const gatherResult = await contextGatherer.gather({
semanticQuery: prompt,
dependencyTasks: numericDependencies,

View File

@@ -19,6 +19,7 @@ import {
COMPLEXITY_REPORT_FILE,
LEGACY_TASKS_FILE
} from '../../../src/constants/paths.js';
import { resolveComplexityReportOutputPath } from '../../../src/utils/path-utils.js';
import { ContextGatherer } from '../utils/contextGatherer.js';
import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
import { flattenTasksWithSubtasks } from '../utils.js';
@@ -71,6 +72,7 @@ Do not include any explanatory text, markdown formatting, or code block markers
* @param {string|number} [options.threshold] - Complexity threshold
* @param {boolean} [options.research] - Use research role
* @param {string} [options.projectRoot] - Project root path (for MCP/env fallback).
* @param {string} [options.tag] - Tag for the task
* @param {string} [options.id] - Comma-separated list of task IDs to analyze specifically
* @param {number} [options.from] - Starting task ID in a range to analyze
* @param {number} [options.to] - Ending task ID in a range to analyze
@@ -84,7 +86,6 @@ Do not include any explanatory text, markdown formatting, or code block markers
async function analyzeTaskComplexity(options, context = {}) {
const { session, mcpLog } = context;
const tasksPath = options.file || LEGACY_TASKS_FILE;
const outputPath = options.output || COMPLEXITY_REPORT_FILE;
const thresholdScore = parseFloat(options.threshold || '5');
const useResearch = options.research || false;
const projectRoot = options.projectRoot;
@@ -109,6 +110,13 @@ async function analyzeTaskComplexity(options, context = {}) {
}
};
// Resolve output path using tag-aware resolution
const outputPath = resolveComplexityReportOutputPath(
options.output,
{ projectRoot, tag },
reportLog
);
if (outputFormat === 'text') {
console.log(
chalk.blue(
@@ -220,7 +228,7 @@ async function analyzeTaskComplexity(options, context = {}) {
let gatheredContext = '';
if (originalData && originalData.tasks.length > 0) {
try {
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
const allTasksFlat = flattenTasksWithSubtasks(originalData.tasks);
const fuzzySearch = new FuzzyTaskSearch(
allTasksFlat,
@@ -535,7 +543,7 @@ async function analyzeTaskComplexity(options, context = {}) {
}
}
// Merge with existing report
// Merge with existing report - only keep entries from the current tag
let finalComplexityAnalysis = [];
if (existingReport && Array.isArray(existingReport.complexityAnalysis)) {
@@ -544,10 +552,14 @@ async function analyzeTaskComplexity(options, context = {}) {
complexityAnalysis.map((item) => item.taskId)
);
// Keep existing entries that weren't in this analysis run
// Keep existing entries that weren't in this analysis run AND belong to the current tag
// We determine tag membership by checking if the task ID exists in the current tag's tasks
const currentTagTaskIds = new Set(tasksData.tasks.map((t) => t.id));
const existingEntriesNotAnalyzed =
existingReport.complexityAnalysis.filter(
(item) => !analyzedTaskIds.has(item.taskId)
(item) =>
!analyzedTaskIds.has(item.taskId) &&
currentTagTaskIds.has(item.taskId) // Only keep entries for tasks in current tag
);
// Combine with new analysis
@@ -557,7 +569,7 @@ async function analyzeTaskComplexity(options, context = {}) {
];
reportLog(
`Merged ${complexityAnalysis.length} new analyses with ${existingEntriesNotAnalyzed.length} existing entries`,
`Merged ${complexityAnalysis.length} new analyses with ${existingEntriesNotAnalyzed.length} existing entries from current tag`,
'info'
);
} else {

View File

@@ -11,6 +11,8 @@ import { displayBanner } from '../ui.js';
* @param {string} tasksPath - Path to the tasks.json file
* @param {string} taskIds - Task IDs to clear subtasks from
* @param {Object} context - Context object containing projectRoot and tag
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
*/
function clearSubtasks(tasksPath, taskIds, context = {}) {
const { projectRoot, tag } = context;

View File

@@ -20,6 +20,8 @@ import boxen from 'boxen';
* @param {Object} context - Context object containing session and mcpLog.
* @param {Object} [context.session] - Session object from MCP.
* @param {Object} [context.mcpLog] - MCP logger object.
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
* @param {string} [outputFormat='text'] - Output format ('text' or 'json'). MCP calls should use 'json'.
* @returns {Promise<{success: boolean, expandedCount: number, failedCount: number, skippedCount: number, tasksToExpand: number, telemetryData: Array<Object>}>} - Result summary.
*/
@@ -32,12 +34,7 @@ async function expandAllTasks(
context = {},
outputFormat = 'text' // Assume text default for CLI
) {
const {
session,
mcpLog,
projectRoot: providedProjectRoot,
tag: contextTag
} = context;
const { session, mcpLog, projectRoot: providedProjectRoot, tag } = context;
const isMCPCall = !!mcpLog; // Determine if called from MCP
const projectRoot = providedProjectRoot || findProjectRoot();
@@ -79,7 +76,7 @@ async function expandAllTasks(
try {
logger.info(`Reading tasks from ${tasksPath}`);
const data = readJSON(tasksPath, projectRoot, contextTag);
const data = readJSON(tasksPath, projectRoot, tag);
if (!data || !data.tasks) {
throw new Error(`Invalid tasks data in ${tasksPath}`);
}
@@ -129,7 +126,7 @@ async function expandAllTasks(
numSubtasks,
useResearch,
additionalContext,
{ ...context, projectRoot, tag: data.tag || contextTag }, // Pass the whole context object with projectRoot and resolved tag
{ ...context, projectRoot, tag: data.tag || tag }, // Pass the whole context object with projectRoot and resolved tag
force
);
expandedCount++;

View File

@@ -40,8 +40,10 @@ const subtaskSchema = z
.min(10)
.describe('Detailed description of the subtask'),
dependencies: z
.array(z.number().int())
.describe('IDs of prerequisite subtasks within this expansion'),
.array(z.string())
.describe(
'Array of subtask dependencies within the same parent task. Use format ["parentTaskId.1", "parentTaskId.2"]. Subtasks can only depend on siblings, not external tasks.'
),
details: z.string().min(20).describe('Implementation details and guidance'),
status: z
.string()
@@ -235,11 +237,9 @@ function parseSubtasksFromText(
...rawSubtask,
id: currentId,
dependencies: Array.isArray(rawSubtask.dependencies)
? rawSubtask.dependencies
.map((dep) => (typeof dep === 'string' ? parseInt(dep, 10) : dep))
.filter(
(depId) =>
!Number.isNaN(depId) && depId >= startId && depId < currentId
? rawSubtask.dependencies.filter(
(dep) =>
typeof dep === 'string' && dep.startsWith(`${parentTaskId}.`)
)
: [],
status: 'pending'
@@ -290,6 +290,8 @@ function parseSubtasksFromText(
* @param {Object} context - Context object containing session and mcpLog.
* @param {Object} [context.session] - Session object from MCP.
* @param {Object} [context.mcpLog] - MCP logger object.
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
* @param {boolean} [force=false] - If true, replace existing subtasks; otherwise, append.
* @returns {Promise<Object>} The updated parent task object with new subtasks.
* @throws {Error} If task not found, AI service fails, or parsing fails.
@@ -303,7 +305,13 @@ async function expandTask(
context = {},
force = false
) {
const { session, mcpLog, projectRoot: contextProjectRoot, tag } = context;
const {
session,
mcpLog,
projectRoot: contextProjectRoot,
tag,
complexityReportPath
} = context;
const outputFormat = mcpLog ? 'json' : 'text';
// Determine projectRoot: Use from context if available, otherwise derive from tasksPath
@@ -350,7 +358,7 @@ async function expandTask(
// --- Context Gathering ---
let gatheredContext = '';
try {
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'expand-task');
const searchQuery = `${task.title} ${task.description}`;
@@ -379,17 +387,10 @@ async function expandTask(
// --- Complexity Report Integration ---
let finalSubtaskCount;
let complexityReasoningContext = '';
// Use tag-aware complexity report path
const complexityReportPath = getTagAwareFilePath(
COMPLEXITY_REPORT_FILE,
tag,
projectRoot
);
let taskAnalysis = null;
logger.info(
`Looking for complexity report at: ${complexityReportPath}${tag && tag !== 'master' ? ` (tag-specific for '${tag}')` : ''}`
`Looking for complexity report at: ${complexityReportPath}${tag !== 'master' ? ` (tag-specific for '${tag}')` : ''}`
);
try {

View File

@@ -12,16 +12,20 @@ import { getDebugFlag } from '../config-manager.js';
* @param {string} tasksPath - Path to the tasks.json file
* @param {string} outputDir - Output directory for task files
* @param {Object} options - Additional options (mcpLog for MCP mode, projectRoot, tag)
* @param {string} [options.projectRoot] - Project root path
* @param {string} [options.tag] - Tag for the task
* @param {Object} [options.mcpLog] - MCP logger object
* @returns {Object|undefined} Result object in MCP mode, undefined in CLI mode
*/
function generateTaskFiles(tasksPath, outputDir, options = {}) {
try {
const isMcpMode = !!options?.mcpLog;
const { projectRoot, tag } = options;
// 1. Read the raw data structure, ensuring we have all tags.
// We call readJSON without a specific tag to get the resolved default view,
// which correctly contains the full structure in `_rawTaggedData`.
const resolvedData = readJSON(tasksPath, options.projectRoot);
const resolvedData = readJSON(tasksPath, projectRoot, tag);
if (!resolvedData) {
throw new Error(`Could not read or parse tasks file: ${tasksPath}`);
}
@@ -29,13 +33,10 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
const rawData = resolvedData._rawTaggedData || resolvedData;
// 2. Determine the target tag we need to generate files for.
const targetTag = options.tag || resolvedData.tag || 'master';
const tagData = rawData[targetTag];
const tagData = rawData[tag];
if (!tagData || !tagData.tasks) {
throw new Error(
`Tag '${targetTag}' not found or has no tasks in the data.`
);
throw new Error(`Tag '${tag}' not found or has no tasks in the data.`);
}
const tasksForGeneration = tagData.tasks;
@@ -46,15 +47,15 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
log(
'info',
`Preparing to regenerate ${tasksForGeneration.length} task files for tag '${targetTag}'`
`Preparing to regenerate ${tasksForGeneration.length} task files for tag '${tag}'`
);
// 3. Validate dependencies using the FULL, raw data structure to prevent data loss.
validateAndFixDependencies(
rawData, // Pass the entire object with all tags
tasksPath,
options.projectRoot,
targetTag // Provide the current tag context for the operation
projectRoot,
tag // Provide the current tag context for the operation
);
const allTasksInTag = tagData.tasks;
@@ -66,14 +67,14 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
const files = fs.readdirSync(outputDir);
// Tag-aware file patterns: master -> task_001.txt, other tags -> task_001_tagname.txt
const masterFilePattern = /^task_(\d+)\.txt$/;
const taggedFilePattern = new RegExp(`^task_(\\d+)_${targetTag}\\.txt$`);
const taggedFilePattern = new RegExp(`^task_(\\d+)_${tag}\\.txt$`);
const orphanedFiles = files.filter((file) => {
let match = null;
let fileTaskId = null;
// Check if file belongs to current tag
if (targetTag === 'master') {
if (tag === 'master') {
match = file.match(masterFilePattern);
if (match) {
fileTaskId = parseInt(match[1], 10);
@@ -94,7 +95,7 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
if (orphanedFiles.length > 0) {
log(
'info',
`Found ${orphanedFiles.length} orphaned task files to remove for tag '${targetTag}'`
`Found ${orphanedFiles.length} orphaned task files to remove for tag '${tag}'`
);
orphanedFiles.forEach((file) => {
const filePath = path.join(outputDir, file);
@@ -108,13 +109,13 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
}
// Generate task files for the target tag
log('info', `Generating individual task files for tag '${targetTag}'...`);
log('info', `Generating individual task files for tag '${tag}'...`);
tasksForGeneration.forEach((task) => {
// Tag-aware file naming: master -> task_001.txt, other tags -> task_001_tagname.txt
const taskFileName =
targetTag === 'master'
tag === 'master'
? `task_${task.id.toString().padStart(3, '0')}.txt`
: `task_${task.id.toString().padStart(3, '0')}_${targetTag}.txt`;
: `task_${task.id.toString().padStart(3, '0')}_${tag}.txt`;
const taskPath = path.join(outputDir, taskFileName);
@@ -174,7 +175,7 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
log(
'success',
`All ${tasksForGeneration.length} tasks for tag '${targetTag}' have been generated into '${outputDir}'.`
`All ${tasksForGeneration.length} tasks for tag '${tag}' have been generated into '${outputDir}'.`
);
if (isMcpMode) {

View File

@@ -26,8 +26,9 @@ import {
* @param {string} reportPath - Path to the complexity report
* @param {boolean} withSubtasks - Whether to show subtasks
* @param {string} outputFormat - Output format (text or json)
* @param {string} tag - Optional tag to override current tag resolution
* @param {Object} context - Optional context object containing projectRoot and other options
* @param {Object} context - Context object (required)
* @param {string} context.projectRoot - Project root path
* @param {string} context.tag - Tag for the task
* @returns {Object} - Task list result for json format
*/
function listTasks(
@@ -36,18 +37,18 @@ function listTasks(
reportPath = null,
withSubtasks = false,
outputFormat = 'text',
tag = null,
context = {}
) {
const { projectRoot, tag } = context;
try {
// Extract projectRoot from context if provided
const projectRoot = context.projectRoot || null;
const data = readJSON(tasksPath, projectRoot, tag); // Pass projectRoot to readJSON
if (!data || !data.tasks) {
throw new Error(`No valid tasks found in ${tasksPath}`);
}
// Add complexity scores to tasks if report exists
// `reportPath` is already tag-aware (resolved at the CLI boundary).
const complexityReport = readComplexityReport(reportPath);
// Apply complexity scores to tasks
if (complexityReport && complexityReport.complexityAnalysis) {

View File

@@ -25,6 +25,10 @@ import { findConfigPath } from '../../../src/utils/path-utils.js';
import { log } from '../utils.js';
import { CUSTOM_PROVIDERS } from '../../../src/constants/providers.js';
// Constants
const CONFIG_MISSING_ERROR =
'The configuration file is missing. Run "task-master init" to create it.';
/**
* Fetches the list of models from OpenRouter API.
* @returns {Promise<Array|null>} A promise that resolves with the list of model IDs or null if fetch fails.
@@ -168,9 +172,7 @@ async function getModelConfiguration(options = {}) {
);
if (!configExists) {
throw new Error(
'The configuration file is missing. Run "task-master models --setup" to create it.'
);
throw new Error(CONFIG_MISSING_ERROR);
}
try {
@@ -298,9 +300,7 @@ async function getAvailableModelsList(options = {}) {
);
if (!configExists) {
throw new Error(
'The configuration file is missing. Run "task-master models --setup" to create it.'
);
throw new Error(CONFIG_MISSING_ERROR);
}
try {
@@ -391,9 +391,7 @@ async function setModel(role, modelId, options = {}) {
);
if (!configExists) {
throw new Error(
'The configuration file is missing. Run "task-master models --setup" to create it.'
);
throw new Error(CONFIG_MISSING_ERROR);
}
// Validate role

View File

@@ -1,11 +1,5 @@
import path from 'path';
import {
log,
readJSON,
writeJSON,
getCurrentTag,
setTasksForTag
} from '../utils.js';
import { log, readJSON, writeJSON, setTasksForTag } from '../utils.js';
import { isTaskDependentOn } from '../task-manager.js';
import generateTaskFiles from './generate-task-files.js';
@@ -27,6 +21,7 @@ async function moveTask(
generateFiles = false,
options = {}
) {
const { projectRoot, tag } = options;
// Check if we have comma-separated IDs (batch move)
const sourceIds = sourceId.split(',').map((id) => id.trim());
const destinationIds = destinationId.split(',').map((id) => id.trim());
@@ -53,7 +48,10 @@ async function moveTask(
// Generate files once at the end if requested
if (generateFiles) {
await generateTaskFiles(tasksPath, path.dirname(tasksPath));
await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
tag: tag,
projectRoot: projectRoot
});
}
return {
@@ -64,7 +62,7 @@ async function moveTask(
// Single move logic
// Read the raw data without tag resolution to preserve tagged structure
let rawData = readJSON(tasksPath, options.projectRoot); // No tag parameter
let rawData = readJSON(tasksPath, projectRoot, tag);
// Handle the case where readJSON returns resolved data with _rawTaggedData
if (rawData && rawData._rawTaggedData) {
@@ -72,27 +70,19 @@ async function moveTask(
rawData = rawData._rawTaggedData;
}
// Determine the current tag
const currentTag =
options.tag || getCurrentTag(options.projectRoot) || 'master';
// Ensure the tag exists in the raw data
if (
!rawData ||
!rawData[currentTag] ||
!Array.isArray(rawData[currentTag].tasks)
) {
if (!rawData || !rawData[tag] || !Array.isArray(rawData[tag].tasks)) {
throw new Error(
`Invalid tasks file or tag "${currentTag}" not found at ${tasksPath}`
`Invalid tasks file or tag "${tag}" not found at ${tasksPath}`
);
}
// Get the tasks for the current tag
const tasks = rawData[currentTag].tasks;
const tasks = rawData[tag].tasks;
log(
'info',
`Moving task/subtask ${sourceId} to ${destinationId} (tag: ${currentTag})`
`Moving task/subtask ${sourceId} to ${destinationId} (tag: ${tag})`
);
// Parse source and destination IDs
@@ -116,14 +106,17 @@ async function moveTask(
}
// Update the data structure with the modified tasks
rawData[currentTag].tasks = tasks;
rawData[tag].tasks = tasks;
// Always write the data object, never the _rawTaggedData directly
// The writeJSON function will filter out _rawTaggedData automatically
writeJSON(tasksPath, rawData, options.projectRoot, currentTag);
writeJSON(tasksPath, rawData, options.projectRoot, tag);
if (generateFiles) {
await generateTaskFiles(tasksPath, path.dirname(tasksPath));
await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
tag: tag,
projectRoot: projectRoot
});
}
return result;

View File

@@ -19,7 +19,6 @@ import {
import { generateObjectService } from '../ai-services-unified.js';
import { getDebugFlag } from '../config-manager.js';
import { getPromptManager } from '../prompt-manager.js';
import generateTaskFiles from './generate-task-files.js';
import { displayAiUsageSummary } from '../ui.js';
// Define the Zod schema for a SINGLE task object
@@ -76,7 +75,7 @@ async function parsePRD(prdPath, tasksPath, numTasks, options = {}) {
const outputFormat = isMCP ? 'json' : 'text';
// Use the provided tag, or the current active tag, or default to 'master'
const targetTag = tag || getCurrentTag(projectRoot) || 'master';
const targetTag = tag;
const logFn = mcpLog
? mcpLog

View File

@@ -9,6 +9,8 @@ import generateTaskFiles from './generate-task-files.js';
* @param {boolean} convertToTask - Whether to convert the subtask to a standalone task
* @param {boolean} generateFiles - Whether to regenerate task files after removing the subtask
* @param {Object} context - Context object containing projectRoot and tag information
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
* @returns {Object|null} The removed subtask if convertToTask is true, otherwise null
*/
async function removeSubtask(
@@ -18,11 +20,12 @@ async function removeSubtask(
generateFiles = true,
context = {}
) {
const { projectRoot, tag } = context;
try {
log('info', `Removing subtask ${subtaskId}...`);
// Read the existing tasks with proper context
const data = readJSON(tasksPath, context.projectRoot, context.tag);
const data = readJSON(tasksPath, projectRoot, tag);
if (!data || !data.tasks) {
throw new Error(`Invalid or missing tasks file at ${tasksPath}`);
}
@@ -103,7 +106,7 @@ async function removeSubtask(
}
// Write the updated tasks back to the file with proper context
writeJSON(tasksPath, data, context.projectRoot, context.tag);
writeJSON(tasksPath, data, projectRoot, tag);
// Generate task files if requested
if (generateFiles) {

View File

@@ -9,6 +9,8 @@ import taskExists from './task-exists.js';
* @param {string} tasksPath - Path to the tasks file
* @param {string} taskIds - Comma-separated string of task/subtask IDs to remove (e.g., '5,6.1,7')
* @param {Object} context - Context object containing projectRoot and tag information
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
* @returns {Object} Result object with success status, messages, and removed task info
*/
async function removeTask(tasksPath, taskIds, context = {}) {
@@ -32,7 +34,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
try {
// Read the tasks file ONCE before the loop, preserving the full tagged structure
const rawData = readJSON(tasksPath, projectRoot); // Read raw data
const rawData = readJSON(tasksPath, projectRoot, tag); // Read raw data
if (!rawData) {
throw new Error(`Could not read tasks file at ${tasksPath}`);
}
@@ -40,19 +42,18 @@ async function removeTask(tasksPath, taskIds, context = {}) {
// Use the full tagged data if available, otherwise use the data as is
const fullTaggedData = rawData._rawTaggedData || rawData;
const currentTag = tag || rawData.tag || 'master';
if (!fullTaggedData[currentTag] || !fullTaggedData[currentTag].tasks) {
throw new Error(`Tag '${currentTag}' not found or has no tasks.`);
if (!fullTaggedData[tag] || !fullTaggedData[tag].tasks) {
throw new Error(`Tag '${tag}' not found or has no tasks.`);
}
const tasks = fullTaggedData[currentTag].tasks; // Work with tasks from the correct tag
const tasks = fullTaggedData[tag].tasks; // Work with tasks from the correct tag
const tasksToDeleteFiles = []; // Collect IDs of main tasks whose files should be deleted
for (const taskId of taskIdsToRemove) {
// Check if the task ID exists *before* attempting removal
if (!taskExists(tasks, taskId)) {
const errorMsg = `Task with ID ${taskId} in tag '${currentTag}' not found or already removed.`;
const errorMsg = `Task with ID ${taskId} in tag '${tag}' not found or already removed.`;
results.errors.push(errorMsg);
results.success = false; // Mark overall success as false if any error occurs
continue; // Skip to the next ID
@@ -94,7 +95,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
parentTask.subtasks.splice(subtaskIndex, 1);
results.messages.push(
`Successfully removed subtask ${taskId} from tag '${currentTag}'`
`Successfully removed subtask ${taskId} from tag '${tag}'`
);
}
// Handle main task removal
@@ -102,9 +103,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
const taskIdNum = parseInt(taskId, 10);
const taskIndex = tasks.findIndex((t) => t.id === taskIdNum);
if (taskIndex === -1) {
throw new Error(
`Task with ID ${taskId} not found in tag '${currentTag}'`
);
throw new Error(`Task with ID ${taskId} not found in tag '${tag}'`);
}
// Store the task info before removal
@@ -116,7 +115,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
tasks.splice(taskIndex, 1);
results.messages.push(
`Successfully removed task ${taskId} from tag '${currentTag}'`
`Successfully removed task ${taskId} from tag '${tag}'`
);
}
} catch (innerError) {
@@ -139,7 +138,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
);
// Update the tasks in the current tag of the full data structure
fullTaggedData[currentTag].tasks = tasks;
fullTaggedData[tag].tasks = tasks;
// Remove dependencies from all tags
for (const tagName in fullTaggedData) {
@@ -171,7 +170,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
}
// Save the updated raw data structure
writeJSON(tasksPath, fullTaggedData, projectRoot, currentTag);
writeJSON(tasksPath, fullTaggedData, projectRoot, tag);
// Delete task files AFTER saving tasks.json
for (const taskIdNum of tasksToDeleteFiles) {
@@ -196,7 +195,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
try {
await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
projectRoot,
tag: currentTag
tag
});
results.messages.push('Task files regenerated successfully.');
} catch (genError) {

View File

@@ -35,6 +35,7 @@ import {
* @param {boolean} [options.includeProjectTree] - Include project file tree
* @param {string} [options.detailLevel] - Detail level: 'low', 'medium', 'high'
* @param {string} [options.projectRoot] - Project root directory
* @param {string} [options.tag] - Tag for the task
* @param {boolean} [options.saveToFile] - Whether to save results to file (MCP mode)
* @param {Object} [context] - Execution context
* @param {Object} [context.session] - MCP session object
@@ -59,6 +60,7 @@ async function performResearch(
includeProjectTree = false,
detailLevel = 'medium',
projectRoot: providedProjectRoot,
tag,
saveToFile = false
} = options;
@@ -101,7 +103,7 @@ async function performResearch(
try {
// Initialize context gatherer
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
// Auto-discover relevant tasks using fuzzy search to supplement provided tasks
let finalTaskIds = [...taskIds]; // Start with explicitly provided tasks
@@ -114,7 +116,7 @@ async function performResearch(
'tasks',
'tasks.json'
);
const tasksData = await readJSON(tasksPath, projectRoot);
const tasksData = await readJSON(tasksPath, projectRoot, tag);
if (tasksData && tasksData.tasks && tasksData.tasks.length > 0) {
// Flatten tasks to include subtasks for fuzzy search
@@ -769,10 +771,7 @@ async function handleSaveToTask(
return;
}
// Validate ID exists - use tag from context
const { getCurrentTag } = await import('../utils.js');
const tag = context.tag || getCurrentTag(projectRoot) || 'master';
const data = readJSON(tasksPath, projectRoot, tag);
const data = readJSON(tasksPath, projectRoot, context.tag);
if (!data || !data.tasks) {
console.log(chalk.red('❌ No valid tasks found.'));
return;
@@ -806,7 +805,7 @@ async function handleSaveToTask(
trimmedTaskId,
conversationThread,
false, // useResearch = false for simple append
{ ...context, tag },
context,
'text'
);
@@ -833,7 +832,7 @@ async function handleSaveToTask(
taskIdNum,
conversationThread,
false, // useResearch = false for simple append
{ ...context, tag },
context,
'text',
true // appendMode = true
);

View File

@@ -34,7 +34,7 @@ function setResponseLanguage(lang, options = {}) {
error: {
code: 'CONFIG_MISSING',
message:
'The configuration file is missing. Run "task-master models --setup" to create it.'
'The configuration file is missing. Run "task-master init" to create it.'
}
};
}

View File

@@ -7,7 +7,6 @@ import {
readJSON,
writeJSON,
findTaskById,
getCurrentTag,
ensureTagMetadata
} from '../utils.js';
import { displayBanner } from '../ui.js';
@@ -26,16 +25,13 @@ import {
* @param {string} taskIdInput - Task ID(s) to update
* @param {string} newStatus - New status
* @param {Object} options - Additional options (mcpLog for MCP mode, projectRoot for tag resolution)
* @param {string} tag - Optional tag to override current tag resolution
* @param {string} [options.projectRoot] - Project root path
* @param {string} [options.tag] - Optional tag to override current tag resolution
* @param {string} [options.mcpLog] - MCP logger object
* @returns {Object|undefined} Result object in MCP mode, undefined in CLI mode
*/
async function setTaskStatus(
tasksPath,
taskIdInput,
newStatus,
options = {},
tag = null
) {
async function setTaskStatus(tasksPath, taskIdInput, newStatus, options = {}) {
const { projectRoot, tag } = options;
try {
if (!isValidTaskStatus(newStatus)) {
throw new Error(
@@ -59,7 +55,7 @@ async function setTaskStatus(
log('info', `Reading tasks from ${tasksPath}...`);
// Read the raw data without tag resolution to preserve tagged structure
let rawData = readJSON(tasksPath, options.projectRoot); // No tag parameter
let rawData = readJSON(tasksPath, projectRoot, tag); // No tag parameter
// Handle the case where readJSON returns resolved data with _rawTaggedData
if (rawData && rawData._rawTaggedData) {
@@ -67,24 +63,17 @@ async function setTaskStatus(
rawData = rawData._rawTaggedData;
}
// Determine the current tag
const currentTag = tag || getCurrentTag(options.projectRoot) || 'master';
// Ensure the tag exists in the raw data
if (
!rawData ||
!rawData[currentTag] ||
!Array.isArray(rawData[currentTag].tasks)
) {
if (!rawData || !rawData[tag] || !Array.isArray(rawData[tag].tasks)) {
throw new Error(
`Invalid tasks file or tag "${currentTag}" not found at ${tasksPath}`
`Invalid tasks file or tag "${tag}" not found at ${tasksPath}`
);
}
// Get the tasks for the current tag
const data = {
tasks: rawData[currentTag].tasks,
tag: currentTag,
tasks: rawData[tag].tasks,
tag,
_rawTaggedData: rawData
};
@@ -123,16 +112,16 @@ async function setTaskStatus(
}
// Update the raw data structure with the modified tasks
rawData[currentTag].tasks = data.tasks;
rawData[tag].tasks = data.tasks;
// Ensure the tag has proper metadata
ensureTagMetadata(rawData[currentTag], {
description: `Tasks for ${currentTag} context`
ensureTagMetadata(rawData[tag], {
description: `Tasks for ${tag} context`
});
// Write the updated raw data back to the file
// The writeJSON function will automatically filter out _rawTaggedData
writeJSON(tasksPath, rawData, options.projectRoot, currentTag);
writeJSON(tasksPath, rawData, projectRoot, tag);
// Validate dependencies after status update
log('info', 'Validating dependencies after status update...');

View File

@@ -17,8 +17,7 @@ import {
truncate,
isSilentMode,
findProjectRoot,
flattenTasksWithSubtasks,
getCurrentTag
flattenTasksWithSubtasks
} from '../utils.js';
import { generateTextService } from '../ai-services-unified.js';
import { getDebugFlag } from '../config-manager.js';
@@ -37,6 +36,7 @@ import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
* @param {Object} [context.session] - Session object from MCP server.
* @param {Object} [context.mcpLog] - MCP logger object.
* @param {string} [context.projectRoot] - Project root path (needed for AI service key resolution).
* @param {string} [context.tag] - Tag for the task
* @param {string} [outputFormat='text'] - Output format ('text' or 'json'). Automatically 'json' if mcpLog is present.
* @returns {Promise<Object|null>} - The updated subtask or null if update failed.
*/
@@ -92,10 +92,7 @@ async function updateSubtaskById(
throw new Error('Could not determine project root directory');
}
// Determine the tag to use
const currentTag = tag || getCurrentTag(projectRoot) || 'master';
const data = readJSON(tasksPath, projectRoot, currentTag);
const data = readJSON(tasksPath, projectRoot, tag);
if (!data || !data.tasks) {
throw new Error(
`No valid tasks found in ${tasksPath}. The file may be corrupted or have an invalid format.`
@@ -142,7 +139,7 @@ async function updateSubtaskById(
// --- Context Gathering ---
let gatheredContext = '';
try {
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'update-subtask');
const searchQuery = `${parentTask.title} ${subtask.title} ${prompt}`;
@@ -331,13 +328,17 @@ async function updateSubtaskById(
if (outputFormat === 'text' && getDebugFlag(session)) {
console.log('>>> DEBUG: About to call writeJSON with updated data...');
}
writeJSON(tasksPath, data, projectRoot, currentTag);
writeJSON(tasksPath, data, projectRoot, tag);
if (outputFormat === 'text' && getDebugFlag(session)) {
console.log('>>> DEBUG: writeJSON call completed.');
}
report('success', `Successfully updated subtask ${subtaskId}`);
// await generateTaskFiles(tasksPath, path.dirname(tasksPath));
// Updated function call to make sure if uncommented it will generate the task files for the updated subtask based on the tag
// await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
// tag: tag,
// projectRoot: projectRoot
// });
if (outputFormat === 'text') {
if (loadingIndicator) {

View File

@@ -12,8 +12,7 @@ import {
truncate,
isSilentMode,
flattenTasksWithSubtasks,
findProjectRoot,
getCurrentTag
findProjectRoot
} from '../utils.js';
import {
@@ -262,6 +261,7 @@ function parseUpdatedTaskFromText(text, expectedTaskId, logFn, isMCP) {
* @param {Object} [context.session] - Session object from MCP server.
* @param {Object} [context.mcpLog] - MCP logger object.
* @param {string} [context.projectRoot] - Project root path.
* @param {string} [context.tag] - Tag for the task
* @param {string} [outputFormat='text'] - Output format ('text' or 'json').
* @param {boolean} [appendMode=false] - If true, append to details instead of full update.
* @returns {Promise<Object|null>} - The updated task or null if update failed.
@@ -320,11 +320,8 @@ async function updateTaskById(
throw new Error('Could not determine project root directory');
}
// Determine the tag to use
const currentTag = tag || getCurrentTag(projectRoot) || 'master';
// --- Task Loading and Status Check (Keep existing) ---
const data = readJSON(tasksPath, projectRoot, currentTag);
const data = readJSON(tasksPath, projectRoot, tag);
if (!data || !data.tasks)
throw new Error(`No valid tasks found in ${tasksPath}.`);
const taskIndex = data.tasks.findIndex((task) => task.id === taskId);
@@ -364,7 +361,7 @@ async function updateTaskById(
// --- Context Gathering ---
let gatheredContext = '';
try {
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'update-task');
const searchQuery = `${taskToUpdate.title} ${taskToUpdate.description} ${prompt}`;
@@ -559,7 +556,7 @@ async function updateTaskById(
// Write the updated task back to file
data.tasks[taskIndex] = taskToUpdate;
writeJSON(tasksPath, data, projectRoot, currentTag);
writeJSON(tasksPath, data, projectRoot, tag);
report('success', `Successfully appended to task ${taskId}`);
// Display success message for CLI
@@ -704,7 +701,7 @@ async function updateTaskById(
// --- End Update Task Data ---
// --- Write File and Generate (Unchanged) ---
writeJSON(tasksPath, data, projectRoot, currentTag);
writeJSON(tasksPath, data, projectRoot, tag);
report('success', `Successfully updated task ${taskId}`);
// await generateTaskFiles(tasksPath, path.dirname(tasksPath));
// --- End Write File ---

View File

@@ -9,8 +9,7 @@ import {
readJSON,
writeJSON,
truncate,
isSilentMode,
getCurrentTag
isSilentMode
} from '../utils.js';
import {
@@ -43,7 +42,39 @@ const updatedTaskSchema = z
subtasks: z.array(z.any()).nullable() // Keep subtasks flexible for now
})
.strip(); // Allow potential extra fields during parsing if needed, then validate structure
// Preprocessing schema that adds defaults before validation
const preprocessTaskSchema = z.preprocess((task) => {
// Ensure task is an object
if (typeof task !== 'object' || task === null) {
return {};
}
// Return task with defaults for missing fields
return {
...task,
// Add defaults for required fields if missing
id: task.id ?? 0,
title: task.title ?? 'Untitled Task',
description: task.description ?? '',
status: task.status ?? 'pending',
dependencies: Array.isArray(task.dependencies) ? task.dependencies : [],
// Optional fields - preserve undefined/null distinction
priority: task.hasOwnProperty('priority') ? task.priority : null,
details: task.hasOwnProperty('details') ? task.details : null,
testStrategy: task.hasOwnProperty('testStrategy')
? task.testStrategy
: null,
subtasks: Array.isArray(task.subtasks)
? task.subtasks
: task.subtasks === null
? null
: []
};
}, updatedTaskSchema);
const updatedTaskArraySchema = z.array(updatedTaskSchema);
const preprocessedTaskArraySchema = z.array(preprocessTaskSchema);
/**
* Parses an array of task objects from AI's text response.
@@ -196,32 +227,50 @@ function parseUpdatedTasksFromText(text, expectedCount, logFn, isMCP) {
);
}
// Preprocess tasks to ensure required fields have proper defaults
const preprocessedTasks = parsedTasks.map((task) => ({
...task,
// Ensure subtasks is always an array (not null or undefined)
subtasks: Array.isArray(task.subtasks) ? task.subtasks : [],
// Ensure status has a default value if missing
status: task.status || 'pending',
// Ensure dependencies is always an array
dependencies: Array.isArray(task.dependencies) ? task.dependencies : []
}));
// Log missing fields for debugging before preprocessing
let hasWarnings = false;
parsedTasks.forEach((task, index) => {
const missingFields = [];
if (!task.hasOwnProperty('id')) missingFields.push('id');
if (!task.hasOwnProperty('status')) missingFields.push('status');
if (!task.hasOwnProperty('dependencies'))
missingFields.push('dependencies');
const validationResult = updatedTaskArraySchema.safeParse(preprocessedTasks);
if (!validationResult.success) {
report('error', 'Parsed task array failed Zod validation.');
validationResult.error.errors.forEach((err) => {
report('error', ` - Path '${err.path.join('.')}': ${err.message}`);
if (missingFields.length > 0) {
hasWarnings = true;
report(
'warn',
`Task ${index} is missing fields: ${missingFields.join(', ')} - will use defaults`
);
}
});
throw new Error(
`AI response failed task structure validation: ${validationResult.error.message}`
if (hasWarnings) {
report(
'warn',
'Some tasks were missing required fields. Applying defaults...'
);
}
report('info', 'Successfully validated task structure.');
return validationResult.data.slice(
// Use the preprocessing schema to add defaults and validate
const preprocessResult = preprocessedTaskArraySchema.safeParse(parsedTasks);
if (!preprocessResult.success) {
// This should rarely happen now since preprocessing adds defaults
report('error', 'Failed to validate task array even after preprocessing.');
preprocessResult.error.errors.forEach((err) => {
report('error', ` - Path '${err.path.join('.')}': ${err.message}`);
});
throw new Error(
`AI response failed validation: ${preprocessResult.error.message}`
);
}
report('info', 'Successfully validated and transformed task structure.');
return preprocessResult.data.slice(
0,
expectedCount || validationResult.data.length
expectedCount || preprocessResult.data.length
);
}
@@ -234,8 +283,8 @@ function parseUpdatedTasksFromText(text, expectedCount, logFn, isMCP) {
* @param {Object} context - Context object containing session and mcpLog.
* @param {Object} [context.session] - Session object from MCP server.
* @param {Object} [context.mcpLog] - MCP logger object.
* @param {string} [context.tag] - Tag for the task
* @param {string} [outputFormat='text'] - Output format ('text' or 'json').
* @param {string} [tag=null] - Tag associated with the tasks.
*/
async function updateTasks(
tasksPath,
@@ -269,11 +318,8 @@ async function updateTasks(
throw new Error('Could not determine project root directory');
}
// Determine the current tag - prioritize explicit tag, then context.tag, then current tag
const currentTag = tag || getCurrentTag(projectRoot) || 'master';
// --- Task Loading/Filtering (Updated to pass projectRoot and tag) ---
const data = readJSON(tasksPath, projectRoot, currentTag);
const data = readJSON(tasksPath, projectRoot, tag);
if (!data || !data.tasks)
throw new Error(`No valid tasks found in ${tasksPath}`);
const tasksToUpdate = data.tasks.filter(
@@ -292,7 +338,7 @@ async function updateTasks(
// --- Context Gathering ---
let gatheredContext = '';
try {
const contextGatherer = new ContextGatherer(projectRoot);
const contextGatherer = new ContextGatherer(projectRoot, tag);
const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'update');
const searchResults = fuzzySearch.findRelevantTasks(prompt, {
@@ -478,7 +524,7 @@ async function updateTasks(
);
// Fix: Pass projectRoot and currentTag to writeJSON
writeJSON(tasksPath, data, projectRoot, currentTag);
writeJSON(tasksPath, data, projectRoot, tag);
if (isMCP)
logFn.info(
`Successfully updated ${actualUpdateCount} tasks in ${tasksPath}`

View File

@@ -1197,18 +1197,18 @@ async function displayNextTask(
* @param {string|number} taskId - The ID of the task to display
* @param {string} complexityReportPath - Path to the complexity report file
* @param {string} [statusFilter] - Optional status to filter subtasks by
* @param {string} tag - Optional tag to override current tag resolution
* @param {object} context - Context object containing projectRoot and tag
* @param {string} context.projectRoot - Project root path
* @param {string} context.tag - Tag for the task
*/
async function displayTaskById(
tasksPath,
taskId,
complexityReportPath = null,
statusFilter = null,
tag = null,
context = {}
) {
// Extract projectRoot from context
const projectRoot = context.projectRoot || null;
const { projectRoot, tag } = context;
// Read the tasks file with proper projectRoot for tag resolution
const data = readJSON(tasksPath, projectRoot, tag);
@@ -2251,7 +2251,9 @@ function displayAiUsageSummary(telemetryData, outputType = 'cli') {
* @param {Array<string>} taskIds - Array of task IDs to display
* @param {string} complexityReportPath - Path to complexity report
* @param {string} statusFilter - Optional status filter for subtasks
* @param {Object} context - Optional context object containing projectRoot and tag
* @param {Object} context - Context object containing projectRoot and tag
* @param {string} [context.projectRoot] - Project root path
* @param {string} [context.tag] - Tag for the task
*/
async function displayMultipleTasksSummary(
tasksPath,
@@ -2602,7 +2604,6 @@ async function displayMultipleTasksSummary(
choice.trim(),
complexityReportPath,
statusFilter,
tag,
context
);
}

View File

@@ -1190,6 +1190,7 @@ function aggregateTelemetry(telemetryArray, overallCommandName) {
}
/**
* @deprecated Use TaskMaster.getCurrentTag() instead
* Gets the current tag from state.json or falls back to defaultTag from config
* @param {string} projectRoot - The project root directory (required)
* @returns {string} The current tag name

View File

@@ -21,7 +21,7 @@ const { encode } = pkg;
* Context Gatherer class for collecting and formatting context from various sources
*/
export class ContextGatherer {
constructor(projectRoot) {
constructor(projectRoot, tag) {
this.projectRoot = projectRoot;
this.tasksPath = path.join(
projectRoot,
@@ -29,12 +29,13 @@ export class ContextGatherer {
'tasks',
'tasks.json'
);
this.tag = tag;
this.allTasks = this._loadAllTasks();
}
_loadAllTasks() {
try {
const data = readJSON(this.tasksPath, this.projectRoot);
const data = readJSON(this.tasksPath, this.projectRoot, this.tag);
const tasks = data?.tasks || [];
return tasks;
} catch (error) {
@@ -958,10 +959,15 @@ export class ContextGatherer {
/**
* Factory function to create a context gatherer instance
* @param {string} projectRoot - Project root directory
* @param {string} tag - Tag for the task
* @returns {ContextGatherer} Context gatherer instance
* @throws {Error} If tag is not provided
*/
export function createContextGatherer(projectRoot) {
return new ContextGatherer(projectRoot);
export function createContextGatherer(projectRoot, tag) {
if (!tag) {
throw new Error('Tag is required');
}
return new ContextGatherer(projectRoot, tag);
}
export default ContextGatherer;

View File

@@ -1,5 +1,5 @@
/**
* @typedef {'amp' | 'claude' | 'cline' | 'codex' | 'cursor' | 'gemini' | 'opencode' | 'roo' | 'trae' | 'windsurf' | 'vscode' | 'zed'} RulesProfile
* @typedef {'amp' | 'claude' | 'cline' | 'codex' | 'cursor' | 'gemini' | 'kiro' | 'opencode' | 'roo' | 'trae' | 'windsurf' | 'vscode' | 'zed'} RulesProfile
*/
/**
@@ -16,6 +16,7 @@
* - codex: Codex integration
* - cursor: Cursor IDE rules
* - gemini: Gemini integration
* - kiro: Kiro IDE rules
* - opencode: OpenCode integration
* - roo: Roo Code IDE rules
* - trae: Trae IDE rules
@@ -35,6 +36,7 @@ export const RULE_PROFILES = [
'codex',
'cursor',
'gemini',
'kiro',
'opencode',
'roo',
'trae',

View File

@@ -5,6 +5,7 @@ export { clineProfile } from './cline.js';
export { codexProfile } from './codex.js';
export { cursorProfile } from './cursor.js';
export { geminiProfile } from './gemini.js';
export { kiroProfile } from './kiro.js';
export { opencodeProfile } from './opencode.js';
export { rooProfile } from './roo.js';
export { traeProfile } from './trae.js';

42
src/profiles/kiro.js Normal file
View File

@@ -0,0 +1,42 @@
// Kiro profile for rule-transformer
import { createProfile } from './base-profile.js';
// Create and export kiro profile using the base factory
export const kiroProfile = createProfile({
name: 'kiro',
displayName: 'Kiro',
url: 'kiro.dev',
docsUrl: 'kiro.dev/docs',
profileDir: '.kiro',
rulesDir: '.kiro/steering', // Kiro rules location (full path)
mcpConfig: true,
mcpConfigName: 'settings/mcp.json', // Create directly in settings subdirectory
includeDefaultRules: true, // Include default rules to get all the standard files
targetExtension: '.md',
fileMap: {
// Override specific mappings - the base profile will create:
// 'rules/cursor_rules.mdc': 'kiro_rules.md'
// 'rules/dev_workflow.mdc': 'dev_workflow.md'
// 'rules/self_improve.mdc': 'self_improve.md'
// 'rules/taskmaster.mdc': 'taskmaster.md'
// We can add additional custom mappings here if needed
},
customReplacements: [
// Core Kiro directory structure changes
{ from: /\.cursor\/rules/g, to: '.kiro/steering' },
{ from: /\.cursor\/mcp\.json/g, to: '.kiro/settings/mcp.json' },
// Fix any remaining kiro/rules references that might be created during transformation
{ from: /\.kiro\/rules/g, to: '.kiro/steering' },
// Essential markdown link transformations for Kiro structure
{
from: /\[(.+?)\]\(mdc:\.cursor\/rules\/(.+?)\.mdc\)/g,
to: '[$1](.kiro/steering/$2.md)'
},
// Kiro specific terminology
{ from: /rules directory/g, to: 'steering directory' },
{ from: /cursor rules/gi, to: 'Kiro steering files' }
]
});

View File

@@ -1,6 +1,162 @@
// VS Code conversion profile for rule-transformer
import path from 'path';
import fs from 'fs';
import { log } from '../../scripts/modules/utils.js';
import { createProfile, COMMON_TOOL_MAPPINGS } from './base-profile.js';
/**
* Transform standard MCP config format to VS Code format
* @param {Object} mcpConfig - Standard MCP configuration object
* @returns {Object} - Transformed VS Code configuration object
*/
function transformToVSCodeFormat(mcpConfig) {
const vscodeConfig = {};
// Transform mcpServers to servers
if (mcpConfig.mcpServers) {
vscodeConfig.servers = {};
for (const [serverName, serverConfig] of Object.entries(
mcpConfig.mcpServers
)) {
// Transform server configuration
const transformedServer = {
...serverConfig
};
// Add type: "stdio" after the env block
if (transformedServer.env) {
// Reorder properties: keep command, args, env, then add type
const reorderedServer = {};
if (transformedServer.command)
reorderedServer.command = transformedServer.command;
if (transformedServer.args)
reorderedServer.args = transformedServer.args;
if (transformedServer.env) reorderedServer.env = transformedServer.env;
reorderedServer.type = 'stdio';
// Add any other properties that might exist
Object.keys(transformedServer).forEach((key) => {
if (!['command', 'args', 'env', 'type'].includes(key)) {
reorderedServer[key] = transformedServer[key];
}
});
vscodeConfig.servers[serverName] = reorderedServer;
} else {
// If no env block, just add type at the end
transformedServer.type = 'stdio';
vscodeConfig.servers[serverName] = transformedServer;
}
}
}
return vscodeConfig;
}
/**
* Lifecycle function called after MCP config generation to transform to VS Code format
* @param {string} targetDir - Target project directory
* @param {string} assetsDir - Assets directory (unused for VS Code)
*/
function onPostConvertRulesProfile(targetDir, assetsDir) {
const vscodeConfigPath = path.join(targetDir, '.vscode', 'mcp.json');
if (!fs.existsSync(vscodeConfigPath)) {
log('debug', '[VS Code] No .vscode/mcp.json found to transform');
return;
}
try {
// Read the generated standard MCP config
const mcpConfigContent = fs.readFileSync(vscodeConfigPath, 'utf8');
const mcpConfig = JSON.parse(mcpConfigContent);
// Check if it's already in VS Code format (has servers instead of mcpServers)
if (mcpConfig.servers) {
log(
'info',
'[VS Code] mcp.json already in VS Code format, skipping transformation'
);
return;
}
// Transform to VS Code format
const vscodeConfig = transformToVSCodeFormat(mcpConfig);
// Write back the transformed config with proper formatting
fs.writeFileSync(
vscodeConfigPath,
JSON.stringify(vscodeConfig, null, 2) + '\n'
);
log('info', '[VS Code] Transformed mcp.json to VS Code format');
log('debug', `[VS Code] Renamed mcpServers->servers, added type: "stdio"`);
} catch (error) {
log('error', `[VS Code] Failed to transform mcp.json: ${error.message}`);
}
}
/**
* Lifecycle function called when removing VS Code profile
* @param {string} targetDir - Target project directory
*/
function onRemoveRulesProfile(targetDir) {
const vscodeConfigPath = path.join(targetDir, '.vscode', 'mcp.json');
if (!fs.existsSync(vscodeConfigPath)) {
log('debug', '[VS Code] No .vscode/mcp.json found to clean up');
return;
}
try {
// Read the current config
const configContent = fs.readFileSync(vscodeConfigPath, 'utf8');
const config = JSON.parse(configContent);
// Check if it has the servers section and task-master-ai server
if (config.servers && config.servers['task-master-ai']) {
// Remove task-master-ai server
delete config.servers['task-master-ai'];
// Check if there are other MCP servers
const remainingServers = Object.keys(config.servers);
if (remainingServers.length === 0) {
// No other servers, remove entire file
fs.rmSync(vscodeConfigPath, { force: true });
log('info', '[VS Code] Removed empty mcp.json file');
// Also remove .vscode directory if it's empty
const vscodeDir = path.dirname(vscodeConfigPath);
try {
const dirContents = fs.readdirSync(vscodeDir);
if (dirContents.length === 0) {
fs.rmSync(vscodeDir, { recursive: true, force: true });
log('debug', '[VS Code] Removed empty .vscode directory');
}
} catch (err) {
// Directory might not be empty or might not exist, that's fine
}
} else {
// Write back the modified config
fs.writeFileSync(
vscodeConfigPath,
JSON.stringify(config, null, 2) + '\n'
);
log(
'info',
'[VS Code] Removed TaskMaster from mcp.json, preserved other configurations'
);
}
} else {
log('debug', '[VS Code] TaskMaster not found in mcp.json');
}
} catch (error) {
log('error', `[VS Code] Failed to clean up mcp.json: ${error.message}`);
}
}
// Create and export vscode profile using the base factory
export const vscodeProfile = createProfile({
name: 'vscode',
@@ -8,6 +164,8 @@ export const vscodeProfile = createProfile({
url: 'code.visualstudio.com',
docsUrl: 'code.visualstudio.com/docs',
rulesDir: '.github/instructions', // VS Code instructions location
profileDir: '.vscode', // VS Code configuration directory
mcpConfigName: 'mcp.json', // VS Code uses mcp.json in .vscode directory
customReplacements: [
// Core VS Code directory structure changes
{ from: /\.cursor\/rules/g, to: '.github/instructions' },
@@ -28,5 +186,10 @@ export const vscodeProfile = createProfile({
// VS Code specific terminology
{ from: /rules directory/g, to: 'instructions directory' },
{ from: /cursor rules/gi, to: 'VS Code instructions' }
]
],
onPostConvert: onPostConvertRulesProfile,
onRemove: onRemoveRulesProfile
});
// Export lifecycle functions separately to avoid naming conflicts
export { onPostConvertRulesProfile, onRemoveRulesProfile };

View File

@@ -56,17 +56,17 @@
"prompts": {
"complexity-report": {
"condition": "expansionPrompt",
"system": "You are an AI assistant helping with task breakdown. Generate {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks based on the provided prompt and context.\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array of the generated subtask objects.\nEach subtask object in the array must have keys: \"id\", \"title\", \"description\", \"dependencies\", \"details\", \"status\".\nEnsure the 'id' starts from {{nextSubtaskId}} and is sequential.\nEnsure 'dependencies' only reference valid prior subtask IDs generated in this response (starting from {{nextSubtaskId}}).\nEnsure 'status' is 'pending'.\nDo not include any other text or explanation.",
"system": "You are an AI assistant helping with task breakdown. Generate {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks based on the provided prompt and context.\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array of the generated subtask objects.\nEach subtask object in the array must have keys: \"id\", \"title\", \"description\", \"dependencies\", \"details\", \"status\".\nEnsure the 'id' starts from {{nextSubtaskId}} and is sequential.\nFor 'dependencies', use the full subtask ID format: \"{{task.id}}.1\", \"{{task.id}}.2\", etc. Only reference subtasks within this same task.\nEnsure 'status' is 'pending'.\nDo not include any other text or explanation.",
"user": "{{expansionPrompt}}{{#if additionalContext}}\n\n{{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\n\n{{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}"
},
"research": {
"condition": "useResearch === true && !expansionPrompt",
"system": "You are an AI assistant that responds ONLY with valid JSON objects as requested. The object should contain a 'subtasks' array.",
"user": "Analyze the following task and break it down into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks using your research capabilities. Assign sequential IDs starting from {{nextSubtaskId}}.\n\nParent Task:\nID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nConsider this context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nCRITICAL: Respond ONLY with a valid JSON object containing a single key \"subtasks\". The value must be an array of the generated subtasks, strictly matching this structure:\n\n{\n \"subtasks\": [\n {\n \"id\": <number>, // Sequential ID starting from {{nextSubtaskId}}\n \"title\": \"<string>\",\n \"description\": \"<string>\",\n \"dependencies\": [<number>], // e.g., [{{nextSubtaskId}} + 1]. If no dependencies, use an empty array [].\n \"details\": \"<string>\",\n \"testStrategy\": \"<string>\" // Optional\n },\n // ... (repeat for {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}appropriate number of{{/if}} subtasks)\n ]\n}\n\nImportant: For the 'dependencies' field, if a subtask has no dependencies, you MUST use an empty array, for example: \"dependencies\": []. Do not use null or omit the field.\n\nDo not include ANY explanatory text, markdown, or code block markers. Just the JSON object."
"user": "Analyze the following task and break it down into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks using your research capabilities. Assign sequential IDs starting from {{nextSubtaskId}}.\n\nParent Task:\nID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nConsider this context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nCRITICAL: Respond ONLY with a valid JSON object containing a single key \"subtasks\". The value must be an array of the generated subtasks, strictly matching this structure:\n\n{\n \"subtasks\": [\n {\n \"id\": <number>, // Sequential ID starting from {{nextSubtaskId}}\n \"title\": \"<string>\",\n \"description\": \"<string>\",\n \"dependencies\": [\"<string>\"], // Use full subtask IDs like [\"{{task.id}}.1\", \"{{task.id}}.2\"]. If no dependencies, use an empty array [].\n \"details\": \"<string>\",\n \"testStrategy\": \"<string>\" // Optional\n },\n // ... (repeat for {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}appropriate number of{{/if}} subtasks)\n ]\n}\n\nImportant: For the 'dependencies' field, if a subtask has no dependencies, you MUST use an empty array, for example: \"dependencies\": []. Do not use null or omit the field.\n\nDo not include ANY explanatory text, markdown, or code block markers. Just the JSON object."
},
"default": {
"system": "You are an AI assistant helping with task breakdown for software development.\nYou need to break down a high-level task into {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks that can be implemented one by one.\n\nSubtasks should:\n1. Be specific and actionable implementation steps\n2. Follow a logical sequence\n3. Each handle a distinct part of the parent task\n4. Include clear guidance on implementation approach\n5. Have appropriate dependency chains between subtasks (using the new sequential IDs)\n6. Collectively cover all aspects of the parent task\n\nFor each subtask, provide:\n- id: Sequential integer starting from the provided nextSubtaskId\n- title: Clear, specific title\n- description: Detailed description\n- dependencies: Array of prerequisite subtask IDs (use the new sequential IDs)\n- details: Implementation details, the output should be in string\n- testStrategy: Optional testing approach\n\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array matching the structure described. Do not include any explanatory text, markdown formatting, or code block markers.",
"user": "Break down this task into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks:\n\nTask ID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nAdditional context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nReturn ONLY the JSON object containing the \"subtasks\" array, matching this structure:\n\n{\n \"subtasks\": [\n {\n \"id\": {{nextSubtaskId}}, // First subtask ID\n \"title\": \"Specific subtask title\",\n \"description\": \"Detailed description\",\n \"dependencies\": [], // e.g., [{{nextSubtaskId}} + 1] if it depends on the next\n \"details\": \"Implementation guidance\",\n \"testStrategy\": \"Optional testing approach\"\n },\n // ... (repeat for {{#if (gt subtaskCount 0)}}a total of {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks with sequential IDs)\n ]\n}"
"system": "You are an AI assistant helping with task breakdown for software development.\nYou need to break down a high-level task into {{#if (gt subtaskCount 0)}}{{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks that can be implemented one by one.\n\nSubtasks should:\n1. Be specific and actionable implementation steps\n2. Follow a logical sequence\n3. Each handle a distinct part of the parent task\n4. Include clear guidance on implementation approach\n5. Have appropriate dependency chains between subtasks (using full subtask IDs)\n6. Collectively cover all aspects of the parent task\n\nFor each subtask, provide:\n- id: Sequential integer starting from the provided nextSubtaskId\n- title: Clear, specific title\n- description: Detailed description\n- dependencies: Array of prerequisite subtask IDs using full format like [\"{{task.id}}.1\", \"{{task.id}}.2\"]\n- details: Implementation details, the output should be in string\n- testStrategy: Optional testing approach\n\nRespond ONLY with a valid JSON object containing a single key \"subtasks\" whose value is an array matching the structure described. Do not include any explanatory text, markdown formatting, or code block markers.",
"user": "Break down this task into {{#if (gt subtaskCount 0)}}exactly {{subtaskCount}}{{else}}an appropriate number of{{/if}} specific subtasks:\n\nTask ID: {{task.id}}\nTitle: {{task.title}}\nDescription: {{task.description}}\nCurrent details: {{#if task.details}}{{task.details}}{{else}}None{{/if}}{{#if additionalContext}}\nAdditional context: {{additionalContext}}{{/if}}{{#if complexityReasoningContext}}\nComplexity Analysis Reasoning: {{complexityReasoningContext}}{{/if}}{{#if gatheredContext}}\n\n# Project Context\n\n{{gatheredContext}}{{/if}}\n\nReturn ONLY the JSON object containing the \"subtasks\" array, matching this structure:\n\n{\n \"subtasks\": [\n {\n \"id\": {{nextSubtaskId}}, // First subtask ID\n \"title\": \"Specific subtask title\",\n \"description\": \"Detailed description\",\n \"dependencies\": [], // e.g., [\"{{task.id}}.1\", \"{{task.id}}.2\"] for dependencies. Use empty array [] if no dependencies\n \"details\": \"Implementation guidance\",\n \"testStrategy\": \"Optional testing approach\"\n },\n // ... (repeat for {{#if (gt subtaskCount 0)}}a total of {{subtaskCount}}{{else}}an appropriate number of{{/if}} subtasks with sequential IDs)\n ]\n}"
}
}
}

View File

@@ -31,8 +31,8 @@
},
"prompts": {
"default": {
"system": "You are an AI assistant helping to update software development tasks based on new context.\nYou will be given a set of tasks and a prompt describing changes or new implementation details.\nYour job is to update the tasks to reflect these changes, while preserving their basic structure.\n\nGuidelines:\n1. Maintain the same IDs, statuses, and dependencies unless specifically mentioned in the prompt\n2. Update titles, descriptions, details, and test strategies to reflect the new information\n3. Do not change anything unnecessarily - just adapt what needs to change based on the prompt\n4. You should return ALL the tasks in order, not just the modified ones\n5. Return a complete valid JSON object with the updated tasks array\n6. VERY IMPORTANT: Preserve all subtasks marked as \"done\" or \"completed\" - do not modify their content\n7. For tasks with completed subtasks, build upon what has already been done rather than rewriting everything\n8. If an existing completed subtask needs to be changed/undone based on the new context, DO NOT modify it directly\n9. Instead, add a new subtask that clearly indicates what needs to be changed or replaced\n10. Use the existence of completed subtasks as an opportunity to make new subtasks more specific and targeted\n\nThe changes described in the prompt should be applied to ALL tasks in the list.",
"user": "Here are the tasks to update:\n{{{json tasks}}}\n\nPlease update these tasks based on the following new context:\n{{updatePrompt}}\n\nIMPORTANT: In the tasks JSON above, any subtasks with \"status\": \"done\" or \"status\": \"completed\" should be preserved exactly as is. Build your changes around these completed items.{{#if projectContext}}\n\n# Project Context\n\n{{projectContext}}{{/if}}\n\nReturn only the updated tasks as a valid JSON array."
"system": "You are an AI assistant helping to update software development tasks based on new context.\nYou will be given a set of tasks and a prompt describing changes or new implementation details.\nYour job is to update the tasks to reflect these changes, while preserving their basic structure.\n\nCRITICAL RULES:\n1. Return ONLY a JSON array - no explanations, no markdown, no additional text before or after\n2. Each task MUST have ALL fields from the original (do not omit any fields)\n3. Maintain the same IDs, statuses, and dependencies unless specifically mentioned in the prompt\n4. Update titles, descriptions, details, and test strategies to reflect the new information\n5. Do not change anything unnecessarily - just adapt what needs to change based on the prompt\n6. You should return ALL the tasks in order, not just the modified ones\n7. Return a complete valid JSON array with all tasks\n8. VERY IMPORTANT: Preserve all subtasks marked as \"done\" or \"completed\" - do not modify their content\n9. For tasks with completed subtasks, build upon what has already been done rather than rewriting everything\n10. If an existing completed subtask needs to be changed/undone based on the new context, DO NOT modify it directly\n11. Instead, add a new subtask that clearly indicates what needs to be changed or replaced\n12. Use the existence of completed subtasks as an opportunity to make new subtasks more specific and targeted\n\nThe changes described in the prompt should be applied to ALL tasks in the list.",
"user": "Here are the tasks to update:\n{{{json tasks}}}\n\nPlease update these tasks based on the following new context:\n{{updatePrompt}}\n\nIMPORTANT: In the tasks JSON above, any subtasks with \"status\": \"done\" or \"status\": \"completed\" should be preserved exactly as is. Build your changes around these completed items.{{#if projectContext}}\n\n# Project Context\n\n{{projectContext}}{{/if}}\n\nRequired JSON structure for EACH task (ALL fields MUST be present):\n{\n \"id\": <number>,\n \"title\": <string>,\n \"description\": <string>,\n \"status\": <string>,\n \"dependencies\": <array>,\n \"priority\": <string or null>,\n \"details\": <string or null>,\n \"testStrategy\": <string or null>,\n \"subtasks\": <array or null>\n}\n\nReturn a valid JSON array containing ALL the tasks with ALL their fields:\n- id (number) - preserve existing value\n- title (string)\n- description (string)\n- status (string) - preserve existing value unless explicitly changing\n- dependencies (array) - preserve existing value unless explicitly changing\n- priority (string or null)\n- details (string or null)\n- testStrategy (string or null)\n- subtasks (array or null)\n\nReturn ONLY the JSON array now:"
}
}
}

View File

@@ -14,8 +14,10 @@ import {
TASKMASTER_DOCS_DIR,
TASKMASTER_REPORTS_DIR,
TASKMASTER_CONFIG_FILE,
LEGACY_CONFIG_FILE
LEGACY_CONFIG_FILE,
COMPLEXITY_REPORT_FILE
} from './constants/paths.js';
import { findProjectRoot } from './utils/path-utils.js';
/**
* TaskMaster class manages all the paths for the application.
@@ -23,13 +25,16 @@ import {
*/
export class TaskMaster {
#paths;
#tag;
/**
* The constructor is intended to be used only by the initTaskMaster factory function.
* @param {object} paths - A pre-resolved object of all application paths.
* @param {string|undefined} tag - The current tag.
*/
constructor(paths) {
constructor(paths, tag) {
this.#paths = Object.freeze({ ...paths });
this.#tag = tag;
}
/**
@@ -64,9 +69,21 @@ export class TaskMaster {
* @returns {string|null} The absolute path to the complexity report.
*/
getComplexityReportPath() {
if (this.#paths.complexityReportPath) {
return this.#paths.complexityReportPath;
}
const complexityReportFile =
this.getCurrentTag() !== 'master'
? COMPLEXITY_REPORT_FILE.replace(
'.json',
`_${this.getCurrentTag()}.json`
)
: COMPLEXITY_REPORT_FILE;
return path.join(this.#paths.projectRoot, complexityReportFile);
}
/**
* @returns {string|null} The absolute path to the config.json file.
*/
@@ -87,6 +104,45 @@ export class TaskMaster {
getAllPaths() {
return this.#paths;
}
/**
* Gets the current tag from state.json or falls back to defaultTag from config
* @returns {string} The current tag name
*/
getCurrentTag() {
if (this.#tag) {
return this.#tag;
}
try {
// Try to read current tag from state.json using fs directly
if (fs.existsSync(this.#paths.statePath)) {
const rawState = fs.readFileSync(this.#paths.statePath, 'utf8');
const stateData = JSON.parse(rawState);
if (stateData && stateData.currentTag) {
return stateData.currentTag;
}
}
} catch (error) {
// Ignore errors, fall back to default
}
// Fall back to defaultTag from config using fs directly
try {
if (fs.existsSync(this.#paths.configPath)) {
const rawConfig = fs.readFileSync(this.#paths.configPath, 'utf8');
const configData = JSON.parse(rawConfig);
if (configData && configData.global && configData.global.defaultTag) {
return configData.global.defaultTag;
}
}
} catch (error) {
// Ignore errors, use hardcoded default
}
// Final fallback
return 'master';
}
}
/**
@@ -100,41 +156,42 @@ export class TaskMaster {
* @param {string} [overrides.complexityReportPath]
* @param {string} [overrides.configPath]
* @param {string} [overrides.statePath]
* @param {string} [overrides.tag]
* @returns {TaskMaster} An initialized TaskMaster instance.
*/
export function initTaskMaster(overrides = {}) {
const findProjectRoot = (startDir = process.cwd()) => {
const projectMarkers = [TASKMASTER_DIR, LEGACY_CONFIG_FILE];
let currentDir = path.resolve(startDir);
const rootDir = path.parse(currentDir).root;
while (currentDir !== rootDir) {
for (const marker of projectMarkers) {
const markerPath = path.join(currentDir, marker);
if (fs.existsSync(markerPath)) {
return currentDir;
}
}
currentDir = path.dirname(currentDir);
}
return null;
};
const resolvePath = (
pathType,
override,
defaultPaths = [],
basePath = null
basePath = null,
createParentDirs = false
) => {
if (typeof override === 'string') {
const resolvedPath = path.isAbsolute(override)
? override
: path.resolve(basePath || process.cwd(), override);
if (createParentDirs) {
// For output paths, create parent directory if it doesn't exist
const parentDir = path.dirname(resolvedPath);
if (!fs.existsSync(parentDir)) {
try {
fs.mkdirSync(parentDir, { recursive: true });
} catch (error) {
throw new Error(
`Could not create directory for ${pathType}: ${parentDir}. Error: ${error.message}`
);
}
}
} else {
// Original validation logic
if (!fs.existsSync(resolvedPath)) {
throw new Error(
`${pathType} override path does not exist: ${resolvedPath}`
);
}
}
return resolvedPath;
}
@@ -192,13 +249,8 @@ export function initTaskMaster(overrides = {}) {
paths.projectRoot = resolvedOverride;
} else {
const foundRoot = findProjectRoot();
if (!foundRoot) {
throw new Error(
'Unable to find project root. No project markers found. Run "init" command first.'
);
}
paths.projectRoot = foundRoot;
// findProjectRoot now always returns a value (fallback to cwd)
paths.projectRoot = findProjectRoot();
}
// TaskMaster Directory
@@ -289,9 +341,10 @@ export function initTaskMaster(overrides = {}) {
'task-complexity-report.json',
'complexity-report.json'
],
paths.projectRoot
paths.projectRoot,
true // Enable parent directory creation for output paths
);
}
return new TaskMaster(paths);
return new TaskMaster(paths, overrides.tag);
}

View File

@@ -66,8 +66,10 @@ export function findProjectRoot(startDir = process.cwd()) {
let currentDir = path.resolve(startDir);
const rootDir = path.parse(currentDir).root;
const maxDepth = 50; // Reasonable limit to prevent infinite loops
let depth = 0;
while (currentDir !== rootDir) {
while (currentDir !== rootDir && depth < maxDepth) {
// Check if current directory contains any project markers
for (const marker of projectMarkers) {
const markerPath = path.join(currentDir, marker);
@@ -76,9 +78,11 @@ export function findProjectRoot(startDir = process.cwd()) {
}
}
currentDir = path.dirname(currentDir);
depth++;
}
return null;
// Fallback to current working directory if no project root found
return process.cwd();
}
/**
@@ -271,7 +275,12 @@ export function findComplexityReportPath(
'' // Project root
];
const fileNames = ['task-complexity-report.json', 'complexity-report.json'];
const fileNames = ['task-complexity', 'complexity-report'].map((fileName) => {
if (args?.tag && args?.tag !== 'master') {
return `${fileName}_${args.tag}.json`;
}
return `${fileName}.json`;
});
for (const location of locations) {
for (const fileName of fileNames) {
@@ -353,6 +362,7 @@ export function resolveComplexityReportOutputPath(
log = null
) {
const logger = getLoggerOrDefault(log);
const tag = args?.tag;
// 1. If explicit path is provided, use it
if (explicitPath) {
@@ -369,13 +379,19 @@ export function resolveComplexityReportOutputPath(
// 2. Try to get project root from args (MCP) or find it
const rawProjectRoot =
args?.projectRoot || findProjectRoot() || process.cwd();
// 3. Normalize project root to prevent double .taskmaster paths
const projectRoot = normalizeProjectRoot(rawProjectRoot);
// 3. Use tag-aware filename
let filename = 'task-complexity-report.json';
if (tag && tag !== 'master') {
filename = `task-complexity-report_${tag}.json`;
}
// 4. Use new .taskmaster structure by default
const defaultPath = path.join(projectRoot, COMPLEXITY_REPORT_FILE);
logger.info?.(`Using default complexity report output path: ${defaultPath}`);
const defaultPath = path.join(projectRoot, '.taskmaster/reports', filename);
logger.info?.(
`Using tag-aware complexity report output path: ${defaultPath}`
);
// Ensure the directory exists
const outputDir = path.dirname(defaultPath);

View File

@@ -368,7 +368,7 @@ log_step() {
log_success "Formatted complexity report saved to complexity_report_formatted.log"
log_step "Expanding Task 1 (assuming it exists)"
cmd_output_expand1=$(task-master expand --id=1 2>&1)
cmd_output_expand1=$(task-master expand --id=1 --cr complexity_results.json 2>&1)
exit_status_expand1=$?
echo "$cmd_output_expand1"
extract_and_sum_cost "$cmd_output_expand1"

View File

@@ -0,0 +1,142 @@
import { jest } from '@jest/globals';
import fs from 'fs';
import path from 'path';
import os from 'os';
// Mock external modules
jest.mock('child_process', () => ({
execSync: jest.fn()
}));
// Mock console methods
jest.mock('console', () => ({
log: jest.fn(),
info: jest.fn(),
warn: jest.fn(),
error: jest.fn(),
clear: jest.fn()
}));
describe('Kiro Integration', () => {
let tempDir;
beforeEach(() => {
jest.clearAllMocks();
// Create a temporary directory for testing
tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'task-master-test-'));
// Spy on fs methods
jest.spyOn(fs, 'writeFileSync').mockImplementation(() => {});
jest.spyOn(fs, 'readFileSync').mockImplementation((filePath) => {
if (filePath.toString().includes('mcp.json')) {
return JSON.stringify({ mcpServers: {} }, null, 2);
}
return '{}';
});
jest.spyOn(fs, 'existsSync').mockImplementation(() => false);
jest.spyOn(fs, 'mkdirSync').mockImplementation(() => {});
});
afterEach(() => {
// Clean up the temporary directory
try {
fs.rmSync(tempDir, { recursive: true, force: true });
} catch (err) {
console.error(`Error cleaning up: ${err.message}`);
}
});
// Test function that simulates the createProjectStructure behavior for Kiro files
function mockCreateKiroStructure() {
// This function simulates the actual kiro profile creation logic
// It explicitly calls the mocked fs methods to ensure consistency with the test environment
// Simulate directory creation calls - these will call the mocked mkdirSync
fs.mkdirSync(path.join(tempDir, '.kiro'), { recursive: true });
fs.mkdirSync(path.join(tempDir, '.kiro', 'steering'), { recursive: true });
fs.mkdirSync(path.join(tempDir, '.kiro', 'settings'), { recursive: true });
// Create MCP config file at .kiro/settings/mcp.json
// This will call the mocked writeFileSync
fs.writeFileSync(
path.join(tempDir, '.kiro', 'settings', 'mcp.json'),
JSON.stringify({ mcpServers: {} }, null, 2)
);
// Create kiro rule files in steering directory
// All these will call the mocked writeFileSync
fs.writeFileSync(
path.join(tempDir, '.kiro', 'steering', 'kiro_rules.md'),
'# Kiro Rules\n\nKiro-specific rules and instructions.'
);
fs.writeFileSync(
path.join(tempDir, '.kiro', 'steering', 'dev_workflow.md'),
'# Development Workflow\n\nDevelopment workflow instructions.'
);
fs.writeFileSync(
path.join(tempDir, '.kiro', 'steering', 'self_improve.md'),
'# Self Improvement\n\nSelf improvement guidelines.'
);
fs.writeFileSync(
path.join(tempDir, '.kiro', 'steering', 'taskmaster.md'),
'# Task Master\n\nTask Master integration instructions.'
);
}
test('creates all required .kiro directories', () => {
// Act
mockCreateKiroStructure();
// Assert
expect(fs.mkdirSync).toHaveBeenCalledWith(path.join(tempDir, '.kiro'), {
recursive: true
});
expect(fs.mkdirSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'steering'),
{
recursive: true
}
);
expect(fs.mkdirSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'settings'),
{
recursive: true
}
);
});
test('creates Kiro mcp.json with mcpServers format', () => {
// Act
mockCreateKiroStructure();
// Assert
expect(fs.writeFileSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'settings', 'mcp.json'),
JSON.stringify({ mcpServers: {} }, null, 2)
);
});
test('creates rule files in steering directory', () => {
// Act
mockCreateKiroStructure();
// Assert
expect(fs.writeFileSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'steering', 'kiro_rules.md'),
'# Kiro Rules\n\nKiro-specific rules and instructions.'
);
expect(fs.writeFileSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'steering', 'dev_workflow.md'),
'# Development Workflow\n\nDevelopment workflow instructions.'
);
expect(fs.writeFileSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'steering', 'self_improve.md'),
'# Self Improvement\n\nSelf improvement guidelines.'
);
expect(fs.writeFileSync).toHaveBeenCalledWith(
path.join(tempDir, '.kiro', 'steering', 'taskmaster.md'),
'# Task Master\n\nTask Master integration instructions.'
);
});
});

View File

@@ -41,6 +41,12 @@ describe('MCP Configuration Validation', () => {
expectedConfigName: 'settings.json',
expectedPath: '.gemini/settings.json'
},
kiro: {
shouldHaveMcp: true,
expectedDir: '.kiro',
expectedConfigName: 'settings/mcp.json',
expectedPath: '.kiro/settings/mcp.json'
},
opencode: {
shouldHaveMcp: true,
expectedDir: '.',
@@ -128,6 +134,7 @@ describe('MCP Configuration Validation', () => {
test('should ensure all MCP-enabled profiles use proper directory structure', () => {
const rootProfiles = ['opencode', 'claude', 'codex']; // Profiles that use root directory for config
const nestedConfigProfiles = ['kiro']; // Profiles that use nested directories for config
RULE_PROFILES.forEach((profileName) => {
const profile = getRulesProfile(profileName);
@@ -140,6 +147,11 @@ describe('MCP Configuration Validation', () => {
// Other root profiles normalize to just the filename (no ./ prefix)
expect(profile.mcpConfigPath).toMatch(/^[\w_.]+$/);
}
} else if (nestedConfigProfiles.includes(profileName)) {
// Profiles with nested config directories
expect(profile.mcpConfigPath).toMatch(
/^\.[\w-]+\/[\w-]+\/[\w_.]+$/
);
} else {
// Other profiles should have config files in their specific directories
expect(profile.mcpConfigPath).toMatch(/^\.[\w-]+\/[\w_.]+$/);
@@ -347,6 +359,13 @@ describe('MCP Configuration Validation', () => {
// Other root profiles normalize to just the filename
expect(profile.mcpConfigPath).toBe(profile.mcpConfigName);
}
} else if (profileName === 'kiro') {
// Kiro has a nested config structure
const parts = profile.mcpConfigPath.split('/');
expect(parts).toHaveLength(3); // Should be profileDir/settings/mcp.json
expect(parts[0]).toBe(profile.profileDir);
expect(parts[1]).toBe('settings');
expect(parts[2]).toBe('mcp.json');
} else {
// Non-root profiles should have profileDir/configName structure
const parts = profile.mcpConfigPath.split('/');

Some files were not shown because too many files have changed in this diff Show More