8e3991361e
- Enhanced the function in ℹ️ Initialized Perplexity client with OpenAI compatibility layer _____ _ __ __ _ |_ _|_ _ ___| | __ | \/ | __ _ ___| |_ ___ _ __ | |/ _` / __| |/ / | |\/| |/ _` / __| __/ _ \ '__| | | (_| \__ \ < | | | | (_| \__ \ || __/ | |_|\__,_|___/_|\_\ |_| |_|\__,_|___/\__\___|_| by https://x.com/eyaltoledano ╭────────────────────────────────────────────╮ │ │ │ Version: 0.9.24 Project: Task Master │ │ │ ╰────────────────────────────────────────────╯ ╭─────────────────────╮ │ │ │ Task Master CLI │ │ │ ╰─────────────────────╯ ╭───────────────────╮ │ Task Generation │ ╰───────────────────╯ parse-prd --input=<file.txt> [--tasks=10] Generate tasks from a PRD document generate Create individual task files from tasks… ╭───────────────────╮ │ Task Management │ ╰───────────────────╯ list [--status=<status>] [--with-subtas… List all tasks with their status set-status --id=<id> --status=<status> Update task status (done, pending, etc.) update --from=<id> --prompt="<context>" Update tasks based on new requirements add-task --prompt="<text>" [--dependencies=… Add a new task using AI add-dependency --id=<id> --depends-on=<id> Add a dependency to a task remove-dependency --id=<id> --depends-on=<id> Remove a dependency from a task ╭──────────────────────────╮ │ Task Analysis & Detail │ ╰──────────────────────────╯ analyze-complexity [--research] [--threshold=5] Analyze tasks and generate expansion re… complexity-report [--file=<path>] Display the complexity analysis report expand --id=<id> [--num=5] [--research] [… Break down tasks into detailed subtasks expand --all [--force] [--research] Expand all pending tasks with subtasks clear-subtasks --id=<id> Remove subtasks from specified tasks ╭─────────────────────────────╮ │ Task Navigation & Viewing │ ╰─────────────────────────────╯ next Show the next task to work on based on … show <id> Display detailed information about a sp… ╭─────────────────────────╮ │ Dependency Management │ ╰─────────────────────────╯ validate-dependenci… Identify invalid dependencies without f… fix-dependencies Fix invalid dependencies automatically ╭─────────────────────────╮ │ Environment Variables │ ╰─────────────────────────╯ ANTHROPIC_API_KEY Your Anthropic API key Required MODEL Claude model to use Default: claude-3-7-sonn… MAX_TOKENS Maximum tokens for responses Default: 4000 TEMPERATURE Temperature for model responses Default: 0.7 PERPLEXITY_API_KEY Perplexity API key for research Optional PERPLEXITY_MODEL Perplexity model to use Default: sonar-pro DEBUG Enable debug logging Default: false LOG_LEVEL Console output level (debug,info,warn,error) Default: info DEFAULT_SUBTASKS Default number of subtasks to generate Default: 3 DEFAULT_PRIORITY Default task priority Default: medium PROJECT_NAME Project name displayed in UI Default: Task Master _____ _ __ __ _ |_ _|_ _ ___| | __ | \/ | __ _ ___| |_ ___ _ __ | |/ _` / __| |/ / | |\/| |/ _` / __| __/ _ \ '__| | | (_| \__ \ < | | | | (_| \__ \ || __/ | |_|\__,_|___/_|\_\ |_| |_|\__,_|___/\__\___|_| by https://x.com/eyaltoledano ╭────────────────────────────────────────────╮ │ │ │ Version: 0.9.24 Project: Task Master │ │ │ ╰────────────────────────────────────────────╯ ╭─────────────────────╮ │ │ │ Task Master CLI │ │ │ ╰─────────────────────╯ ╭───────────────────╮ │ Task Generation │ ╰───────────────────╯ parse-prd --input=<file.txt> [--tasks=10] Generate tasks from a PRD document generate Create individual task files from tasks… ╭───────────────────╮ │ Task Management │ ╰───────────────────╯ list [--status=<status>] [--with-subtas… List all tasks with their status set-status --id=<id> --status=<status> Update task status (done, pending, etc.) update --from=<id> --prompt="<context>" Update tasks based on new requirements add-task --prompt="<text>" [--dependencies=… Add a new task using AI add-dependency --id=<id> --depends-on=<id> Add a dependency to a task remove-dependency --id=<id> --depends-on=<id> Remove a dependency from a task ╭──────────────────────────╮ │ Task Analysis & Detail │ ╰──────────────────────────╯ analyze-complexity [--research] [--threshold=5] Analyze tasks and generate expansion re… complexity-report [--file=<path>] Display the complexity analysis report expand --id=<id> [--num=5] [--research] [… Break down tasks into detailed subtasks expand --all [--force] [--research] Expand all pending tasks with subtasks clear-subtasks --id=<id> Remove subtasks from specified tasks ╭─────────────────────────────╮ │ Task Navigation & Viewing │ ╰─────────────────────────────╯ next Show the next task to work on based on … show <id> Display detailed information about a sp… ╭─────────────────────────╮ │ Dependency Management │ ╰─────────────────────────╯ validate-dependenci… Identify invalid dependencies without f… fix-dependencies Fix invalid dependencies automatically ╭─────────────────────────╮ │ Environment Variables │ ╰─────────────────────────╯ ANTHROPIC_API_KEY Your Anthropic API key Required MODEL Claude model to use Default: claude-3-7-sonn… MAX_TOKENS Maximum tokens for responses Default: 4000 TEMPERATURE Temperature for model responses Default: 0.7 PERPLEXITY_API_KEY Perplexity API key for research Optional PERPLEXITY_MODEL Perplexity model to use Default: sonar-pro DEBUG Enable debug logging Default: false LOG_LEVEL Console output level (debug,info,warn,error) Default: info DEFAULT_SUBTASKS Default number of subtasks to generate Default: 3 DEFAULT_PRIORITY Default task priority Default: medium PROJECT_NAME Project name displayed in UI Default: Task Master to correctly handle kebab-case flags by: - Converting camelCase options back to kebab-case for command line arguments. - Checking the original CLI arguments to determine the format used by the user. - Preserving the original flag format when passing it to the underlying script. - Special handling for and flags to ensure they are correctly interpreted. - Updated boolean flag handling to correctly manage negated options and preserve user-specified formats. - Marked task 022 as done and updated the status of its sub-tasks in . - Added tasks 26, 27 and 28 for context improvements related to task generation This commit ensures that all kebab-case flags are handled consistently across the CLI, improving user experience and command reliability.
96 lines
4.4 KiB
Plaintext
96 lines
4.4 KiB
Plaintext
# Task ID: 27
|
|
# Title: Implement Context Enhancements for AI Operations
|
|
# Status: pending
|
|
# Dependencies: 26
|
|
# Priority: high
|
|
# Description: Enhance the basic context integration with more sophisticated code context extraction, task history awareness, and PRD integration to provide richer context for AI operations.
|
|
# Details:
|
|
Building upon the foundational context implementation in Task #26, implement Phase 2 context enhancements:
|
|
|
|
1. Add Code Context Extraction Feature:
|
|
- Create a `--context-code <pattern>` option for all AI commands
|
|
- Implement glob-based file matching to extract code from specified patterns
|
|
- Create intelligent code parsing to extract most relevant sections (function signatures, classes, exports)
|
|
- Implement token usage optimization by selecting key structural elements
|
|
- Add formatting for code context with proper file paths and syntax indicators
|
|
|
|
2. Implement Task History Context:
|
|
- Add a `--context-tasks <ids>` option for AI commands
|
|
- Support comma-separated task IDs and a "similar" option to find related tasks
|
|
- Create functions to extract context from specified tasks or find similar tasks
|
|
- Implement formatting for task context with clear section markers
|
|
- Add validation and error handling for non-existent task IDs
|
|
|
|
3. Add PRD Context Integration:
|
|
- Create a `--context-prd <file>` option for AI commands
|
|
- Implement PRD text extraction and intelligent summarization
|
|
- Add formatting for PRD context with appropriate section markers
|
|
- Integrate with the existing PRD parsing functionality from Task #6
|
|
|
|
4. Improve Context Formatting and Integration:
|
|
- Create a standardized context formatting system
|
|
- Implement type-based sectioning for different context sources
|
|
- Add token estimation for different context types to manage total prompt size
|
|
- Enhance prompt templates to better integrate various context types
|
|
|
|
These enhancements will provide significantly richer context for AI operations, resulting in more accurate and relevant outputs while remaining practical to implement.
|
|
|
|
# Test Strategy:
|
|
Testing should verify the enhanced context functionality:
|
|
|
|
1. Code Context Testing:
|
|
- Verify pattern matching works for different glob patterns
|
|
- Test code extraction with various file types and sizes
|
|
- Verify intelligent parsing correctly identifies important code elements
|
|
- Test token optimization by comparing full file extraction vs. optimized extraction
|
|
- Check code formatting in prompts sent to Claude API
|
|
|
|
2. Task History Testing:
|
|
- Test with different combinations of task IDs
|
|
- Verify "similar" option correctly identifies relevant tasks
|
|
- Test with non-existent task IDs to ensure proper error handling
|
|
- Verify formatting and integration in prompts
|
|
|
|
3. PRD Context Testing:
|
|
- Test with various PRD files of different sizes
|
|
- Verify summarization functions correctly when PRDs are too large
|
|
- Test integration with prompts and formatting
|
|
|
|
4. Performance Testing:
|
|
- Measure the impact of context enrichment on command execution time
|
|
- Test with large code bases to ensure reasonable performance
|
|
- Verify token counting and optimization functions work as expected
|
|
|
|
5. Quality Assessment:
|
|
- Compare AI outputs with Phase 1 vs. Phase 2 context to measure improvements
|
|
- Create test cases that specifically benefit from code context
|
|
- Create test cases that benefit from task history context
|
|
|
|
Focus testing on practical use cases that demonstrate clear improvements in AI-generated outputs.
|
|
|
|
# Subtasks:
|
|
## 1. Implement Code Context Extraction Feature [pending]
|
|
### Dependencies: None
|
|
### Description: Create a --context-code <pattern> option for AI commands and implement glob-based file matching to extract relevant code sections
|
|
### Details:
|
|
|
|
|
|
## 2. Implement Task History Context Integration [pending]
|
|
### Dependencies: None
|
|
### Description: Add a --context-tasks option for AI commands that supports finding and extracting context from specified or similar tasks
|
|
### Details:
|
|
|
|
|
|
## 3. Add PRD Context Integration [pending]
|
|
### Dependencies: None
|
|
### Description: Implement a --context-prd option for AI commands that extracts and formats content from PRD files
|
|
### Details:
|
|
|
|
|
|
## 4. Create Standardized Context Formatting System [pending]
|
|
### Dependencies: None
|
|
### Description: Implement a consistent formatting system for different context types with section markers and token optimization
|
|
### Details:
|
|
|
|
|