ros/claude-task-master
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(expand/all): Implement additive expansion and complexity report integration

Browse Source 
Refactors the `expandTask` and `expandAllTasks` features to complete subtask 61.38 and enhance functionality based on subtask 61.37's refactor.

Key Changes:

- **Additive Expansion (`expandTask`, `expandAllTasks`):**

    - Modified `expandTask` default behavior to append newly generated subtasks to any existing ones.

    - Added a `force` flag (passed down from CLI/MCP via `--force` option/parameter) to `expandTask` and `expandAllTasks`. When `force` is true, existing subtasks are cleared before generating new ones.

    - Updated relevant CLI command (`expand`), MCP tool (`expand_task`, `expand_all`), and direct function wrappers (`expandTaskDirect`, `expandAllTasksDirect`) to handle and pass the `force` flag.

- **Complexity Report Integration (`expandTask`):**

    - `expandTask` now reads `scripts/task-complexity-report.json`.

    - If an analysis entry exists for the target task:

        - `recommendedSubtasks` is used to determine the number of subtasks to generate (unless `--num` is explicitly provided).

        - `expansionPrompt` is used as the primary prompt content for the AI.

        - `reasoning` is appended to any additional context provided.

    - If no report entry exists or the report is missing, it falls back to default subtask count (from config) and standard prompt generation.

- **`expandAllTasks` Orchestration:**

    - Refactored `expandAllTasks` to primarily iterate through eligible tasks (pending/in-progress, considering `force` flag and existing subtasks) and call the updated `expandTask` function for each.

    - Removed redundant logic (like complexity reading or explicit subtask clearing) now handled within `expandTask`.

    - Ensures correct context (`session`, `mcpLog`) and flags (`useResearch`, `force`) are passed down.

- **Configuration & Cleanup:**

    - Updated `.cursor/mcp.json` with new Perplexity/Anthropic API keys (old ones invalidated).

    - Completed refactoring of `expandTask` started in 61.37, confirming usage of `generateTextService` and appropriate prompts.

- **Task Management:**

    - Marked subtask 61.37 as complete.

    - Updated `.changeset/cuddly-zebras-matter.md` to reflect user-facing changes.

These changes finalize the refactoring of the task expansion features, making them more robust, configurable via complexity analysis, and aligned with the unified AI service architecture.
This commit is contained in:
Eyal Toledano
2025-04-25 02:57:08 -04:00
parent f6c5a3b23b
commit 443824a35e
12 changed files with 1068 additions and 542 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
tasks/task_053.txt
View File

@@ -51,3 +51,41 @@ Testing should verify both the functionality and the quality of suggestions:
- Test with a parent task that has no description
- Test with a parent task that already has many subtasks
- Test with a newly created system with minimal task history
# Subtasks:
## 1. Implement parent task validation [pending]
### Dependencies: None
### Description: Create validation logic to ensure subtasks are being added to valid parent tasks
### Details:
Develop functions to verify that the parent task exists in the system before allowing subtask creation. Handle error cases gracefully with informative messages. Include validation for task ID format and existence in the database.
## 2. Build context gathering mechanism [pending]
### Dependencies: 53.1
### Description: Develop a system to collect relevant context from parent task and existing subtasks
### Details:
Create functions to extract information from the parent task including title, description, and metadata. Also gather information about any existing subtasks to provide context for AI suggestions. Format this data appropriately for the AI prompt.
## 3. Develop AI suggestion logic for subtasks [pending]
### Dependencies: 53.2
### Description: Create the core AI integration to generate relevant subtask suggestions
### Details:
Implement the AI prompt engineering and response handling for subtask generation. Ensure the AI provides structured output with appropriate fields for subtasks. Include error handling for API failures and malformed responses.
## 4. Create interactive CLI interface [pending]
### Dependencies: 53.3
### Description: Build a user-friendly command-line interface for the subtask suggestion feature
### Details:
Develop CLI commands and options for requesting subtask suggestions. Include interactive elements for selecting, modifying, or rejecting suggested subtasks. Ensure clear user feedback throughout the process.
## 5. Implement subtask linking functionality [pending]
### Dependencies: 53.4
### Description: Create system to properly link suggested subtasks to their parent task
### Details:
Develop the database operations to save accepted subtasks and link them to the parent task. Include functionality for setting dependencies between subtasks. Ensure proper transaction handling to maintain data integrity.
## 6. Perform comprehensive testing [pending]
### Dependencies: 53.5
### Description: Test the subtask suggestion feature across various scenarios
### Details:
Create unit tests for each component. Develop integration tests for the full feature workflow. Test edge cases including invalid inputs, API failures, and unusual task structures. Document test results and fix any identified issues.