mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-03-28 20:01:17 +08:00
Refactor implementation approach structure across task generation files
- Updated implementation_approach in task-generate-tdd.md to use an array format with detailed steps for minimal code implementation and iterative testing. - Enhanced task-generate.md to support CLI execution mode with Codex, including examples for task execution and session management. - Modified test-task-generate.md to incorporate CLI execution mode, allowing Codex to autonomously generate tests and execute iterative test-fix cycles. - Revised task-core.md and workflow-architecture.md to adopt a step-based implementation approach, improving clarity and dependency management in task execution. - Improved documentation in workflow-architecture.md to clarify flow control structure and variable referencing.
This commit is contained in:
catlog22
@@ -142,37 +142,6 @@ mcp__exa__get_code_context_exa(
|
||||
}
|
||||
```
|
||||
|
||||
**Legacy Pre-Execution Analysis** (backward compatibility):
|
||||
- **Multi-step Pre-Analysis**: Execute comprehensive analysis BEFORE implementation begins
|
||||
- **Sequential Processing**: Process each step sequentially, expanding brief actions
|
||||
- **Template Usage**: Use full template paths with $(cat template_path)
|
||||
- **Method Selection**: gemini/codex/manual/auto-detected
|
||||
- **CLI Commands**:
|
||||
- **Gemini**: `bash(~/.claude/scripts/gemini-wrapper -p "$(cat template_path) [action]")`
|
||||
- **Codex**: `bash(codex --full-auto exec "$(cat template_path) [action]" -s danger-full-access)`
|
||||
- **Follow Guidelines**: @~/.claude/workflows/intelligent-tools-strategy.md
|
||||
|
||||
### Pre-Execution Analysis
|
||||
**When [MULTI_STEP_ANALYSIS] marker is present:**
|
||||
|
||||
#### Multi-Step Pre-Analysis Execution
|
||||
1. Process each analysis step sequentially from pre_analysis array
|
||||
2. For each step:
|
||||
- Expand brief action into comprehensive analysis task
|
||||
- Use specified template with $(cat template_path)
|
||||
- Execute with specified method (gemini/codex/manual/auto-detected)
|
||||
3. Accumulate results across all steps for comprehensive context
|
||||
4. Use consolidated analysis to inform implementation stages and task breakdown
|
||||
|
||||
#### Analysis Dimensions Coverage
|
||||
- **Exa Research**: Use `mcp__exa__get_code_context_exa` for technology stack selection and API patterns
|
||||
- Architecture patterns and component relationships
|
||||
- Implementation conventions and coding standards
|
||||
- Module dependencies and integration points
|
||||
- Testing requirements and coverage patterns
|
||||
- Security considerations and performance implications
|
||||
3. Use Codex insights to create self-guided implementation stages
|
||||
|
||||
## Core Functions
|
||||
|
||||
### 1. Stage Design
|
||||
@@ -222,11 +191,26 @@ Generate individual `.task/IMPL-*.json` files with:
|
||||
"output_to": "codebase_structure"
|
||||
}
|
||||
],
|
||||
"implementation_approach": {
|
||||
"task_description": "Implement following synthesis specification",
|
||||
"modification_points": ["Apply requirements"],
|
||||
"logic_flow": ["Load spec", "Analyze", "Implement", "Validate"]
|
||||
},
|
||||
"implementation_approach": [
|
||||
{
|
||||
"step": 1,
|
||||
"title": "Load and analyze synthesis specification",
|
||||
"description": "Load synthesis specification from artifacts and extract requirements",
|
||||
"modification_points": ["Load synthesis specification", "Extract requirements and design patterns"],
|
||||
"logic_flow": ["Read synthesis specification from artifacts", "Parse architecture decisions", "Extract implementation requirements"],
|
||||
"depends_on": [],
|
||||
"output": "synthesis_requirements"
|
||||
},
|
||||
{
|
||||
"step": 2,
|
||||
"title": "Implement following specification",
|
||||
"description": "Implement task requirements following consolidated synthesis specification",
|
||||
"modification_points": ["Apply requirements from [synthesis_requirements]", "Modify target files", "Integrate with existing code"],
|
||||
"logic_flow": ["Apply changes based on [synthesis_requirements]", "Implement core logic", "Validate against acceptance criteria"],
|
||||
"depends_on": [1],
|
||||
"output": "implementation"
|
||||
}
|
||||
],
|
||||
"target_files": ["file:function:lines", "path/to/NewFile.ts"]
|
||||
}
|
||||
}
|
||||
|
||||
@@ -90,6 +90,32 @@ ELIF context insufficient OR task has flow control marker:
|
||||
- Get API examples: `mcp__exa__get_code_context_exa(query="React authentication hooks", tokensNum="dynamic")`
|
||||
- Update after changes: `mcp__code-index__refresh_index()`
|
||||
|
||||
**Implementation Approach Execution**:
|
||||
When task JSON contains `flow_control.implementation_approach` array:
|
||||
1. **Sequential Processing**: Execute steps in order, respecting `depends_on` dependencies
|
||||
2. **Dependency Resolution**: Wait for all steps listed in `depends_on` before starting
|
||||
3. **Variable Substitution**: Use `[variable_name]` to reference outputs from previous steps
|
||||
4. **Step Structure**:
|
||||
- `step`: Unique identifier (1, 2, 3...)
|
||||
- `title`: Step title
|
||||
- `description`: Detailed description with variable references
|
||||
- `modification_points`: Code modification targets
|
||||
- `logic_flow`: Business logic sequence
|
||||
- `command`: Optional CLI command (only when explicitly specified)
|
||||
- `depends_on`: Array of step numbers that must complete first
|
||||
- `output`: Variable name for this step's output
|
||||
5. **Execution Rules**:
|
||||
- Execute step 1 first (typically has `depends_on: []`)
|
||||
- For each subsequent step, verify all `depends_on` steps completed
|
||||
- Substitute `[variable_name]` with actual outputs from previous steps
|
||||
- Store this step's result in the `output` variable for future steps
|
||||
- If `command` field present, execute it; otherwise use agent capabilities
|
||||
|
||||
**CLI Command Execution (CLI Execute Mode)**:
|
||||
When step contains `command` field with Codex CLI, execute via Bash tool. For Codex resume:
|
||||
- First task (`depends_on: []`): `codex -C [path] --full-auto exec "..." --skip-git-repo-check -s danger-full-access`
|
||||
- Subsequent tasks (has `depends_on`): Add `resume --last` flag to maintain session context
|
||||
|
||||
**Test-Driven Development**:
|
||||
- Write tests first (red → green → refactor)
|
||||
- Focus on core functionality and edge cases
|
||||
|
||||
@@ -83,6 +83,54 @@ def handle_brainstorm_assignment(prompt):
|
||||
generate_brainstorm_analysis(role, context_vars, output_location, topic)
|
||||
```
|
||||
|
||||
## Flow Control Format Handling
|
||||
|
||||
This agent processes **simplified inline [FLOW_CONTROL]** format from brainstorm workflows.
|
||||
|
||||
### Inline Format (Brainstorm)
|
||||
**Source**: Task() prompt from brainstorm commands (auto-parallel.md, etc.)
|
||||
|
||||
**Structure**: Markdown list format (3-5 steps)
|
||||
|
||||
**Example**:
|
||||
```markdown
|
||||
[FLOW_CONTROL]
|
||||
|
||||
### Flow Control Steps
|
||||
1. **load_topic_framework**
|
||||
- Action: Load structured topic framework
|
||||
- Command: Read(.workflow/WFS-{session}/.brainstorming/topic-framework.md)
|
||||
- Output: topic_framework
|
||||
|
||||
2. **load_role_template**
|
||||
- Action: Load role-specific planning template
|
||||
- Command: bash($(cat "~/.claude/workflows/cli-templates/planning-roles/{role}.md"))
|
||||
- Output: role_template
|
||||
|
||||
3. **load_session_metadata**
|
||||
- Action: Load session metadata
|
||||
- Command: bash(cat .workflow/WFS-{session}/workflow-session.json)
|
||||
- Output: session_metadata
|
||||
```
|
||||
|
||||
**Characteristics**:
|
||||
- 3-5 simple context loading steps
|
||||
- Written directly in prompt (not persistent)
|
||||
- No dependency management
|
||||
- Used for temporary context preparation
|
||||
|
||||
### NOT Handled by This Agent
|
||||
|
||||
**JSON format** (used by code-developer, test-fix-agent):
|
||||
```json
|
||||
"flow_control": {
|
||||
"pre_analysis": [...],
|
||||
"implementation_approach": [...]
|
||||
}
|
||||
```
|
||||
|
||||
This complete JSON format is stored in `.task/IMPL-*.json` files and handled by implementation agents, not conceptual-planning-agent.
|
||||
|
||||
### Role-Specific Analysis Dimensions
|
||||
|
||||
| Role | Primary Dimensions | Focus Areas | Exa Usage |
|
||||
|
||||
@@ -68,8 +68,17 @@ You are an expert technical documentation specialist. Your responsibility is to
|
||||
|
||||
### 3. Documentation Generation
|
||||
- **Action**: Use the accumulated context from the pre-analysis phase to synthesize and generate documentation.
|
||||
- **Instructions**: Follow the `implementation_approach` defined in the `flow_control` block.
|
||||
- **Templates**: Apply templates as specified in `meta.template` or `implementation_approach`.
|
||||
- **Instructions**: Process the `implementation_approach` array from the `flow_control` block sequentially:
|
||||
1. **Array Structure**: `implementation_approach` is an array of step objects
|
||||
2. **Sequential Execution**: Execute steps in order, respecting `depends_on` dependencies
|
||||
3. **Variable Substitution**: Use `[variable_name]` to reference outputs from previous steps
|
||||
4. **Step Processing**:
|
||||
- Verify all `depends_on` steps completed before starting
|
||||
- Follow `modification_points` and `logic_flow` for each step
|
||||
- Execute `command` if present, otherwise use agent capabilities
|
||||
- Store result in `output` variable for future steps
|
||||
5. **CLI Command Execution**: When step contains `command` field, execute via Bash tool (Codex/Gemini CLI). For Codex with dependencies, use `resume --last` flag.
|
||||
- **Templates**: Apply templates as specified in `meta.template` or step-level templates.
|
||||
- **Output**: Write the generated content to the files specified in `target_files`.
|
||||
|
||||
### 4. Progress Tracking with TodoWrite
|
||||
|
||||
@@ -41,6 +41,30 @@ You will execute tests, analyze failures, and fix code to ensure all tests pass.
|
||||
|
||||
## Execution Process
|
||||
|
||||
### Flow Control Execution
|
||||
When task JSON contains `flow_control` field, execute preparation and implementation steps systematically.
|
||||
|
||||
**Pre-Analysis Steps** (`flow_control.pre_analysis`):
|
||||
1. **Sequential Processing**: Execute steps in order, accumulating context
|
||||
2. **Variable Substitution**: Use `[variable_name]` to reference previous outputs
|
||||
3. **Error Handling**: Follow step-specific strategies (`skip_optional`, `fail`, `retry_once`)
|
||||
|
||||
**Implementation Approach** (`flow_control.implementation_approach`):
|
||||
When task JSON contains implementation_approach array:
|
||||
1. **Sequential Execution**: Process steps in order, respecting `depends_on` dependencies
|
||||
2. **Dependency Resolution**: Wait for all steps listed in `depends_on` before starting
|
||||
3. **Variable References**: Use `[variable_name]` to reference outputs from previous steps
|
||||
4. **Step Structure**:
|
||||
- `step`: Step number (1, 2, 3...)
|
||||
- `title`: Step title
|
||||
- `description`: Detailed description with variable references
|
||||
- `modification_points`: Test and code modification targets
|
||||
- `logic_flow`: Test-fix iteration sequence
|
||||
- `command`: Optional CLI command (only when explicitly specified)
|
||||
- `depends_on`: Array of step numbers that must complete first
|
||||
- `output`: Variable name for this step's output
|
||||
|
||||
|
||||
### 1. Context Assessment & Test Discovery
|
||||
- Analyze task context to identify test files and source code paths
|
||||
- Load test framework configuration (Jest, Pytest, Mocha, etc.)
|
||||
@@ -61,16 +85,34 @@ fi
|
||||
- Parse test results to identify failures
|
||||
|
||||
### 3. Failure Diagnosis & Fixing Loop
|
||||
|
||||
**Execution Modes**:
|
||||
|
||||
**A. Manual Mode (Default, meta.use_codex=false)**:
|
||||
```
|
||||
WHILE tests are failing:
|
||||
1. Analyze failure output
|
||||
2. Identify root cause in source code
|
||||
3. Modify source code to fix issue
|
||||
4. Re-run affected tests
|
||||
WHILE tests are failing AND iterations < max_iterations:
|
||||
1. Use Gemini to diagnose failure (bug-fix template)
|
||||
2. Present fix recommendations to user
|
||||
3. User applies fixes manually
|
||||
4. Re-run test suite
|
||||
5. Verify fix doesn't break other tests
|
||||
END WHILE
|
||||
```
|
||||
|
||||
**B. Codex Mode (meta.use_codex=true)**:
|
||||
```
|
||||
WHILE tests are failing AND iterations < max_iterations:
|
||||
1. Use Gemini to diagnose failure (bug-fix template)
|
||||
2. Use Codex to apply fixes automatically with resume mechanism
|
||||
3. Re-run test suite
|
||||
4. Verify fix doesn't break other tests
|
||||
END WHILE
|
||||
```
|
||||
|
||||
**Codex Resume in Test-Fix Cycle** (when `meta.use_codex=true`):
|
||||
- First iteration: Start new Codex session with full context
|
||||
- Subsequent iterations: Use `resume --last` to maintain fix history and apply consistent strategies
|
||||
|
||||
### 4. Code Quality Certification
|
||||
- All tests pass → Code is APPROVED ✅
|
||||
- Generate summary documenting:
|
||||
|
||||
Reference in New Issue
Block a user