refactor: Optimize document passing strategy in workflow

- **concept-enhanced**: Add explicit priority for source documents
  - PRIMARY: role analysis.md files (complete technical details, ADRs)
  - SECONDARY: synthesis-specification.md (integrated requirements)
  - Framework: topic-framework.md (discussion context)

- **task-generate**: Enhanced artifacts array with usage guidance
  - Add 'usage' field for each artifact type
  - Support dynamic role discovery
  - Reorder priority: synthesis (highest) → role_analysis (high) → framework (low)

- **pre_analysis**: Add explicit artifact loading instructions
  - Note when to consult role analysis (API schemas, caching configs, design tokens)
  - Load system-architect, ui-designer, product-manager analyses

- **implementation_approach**: Add clear priority instructions
  - Primary: Use synthesis-specification.md for requirements
  - Secondary: Refer to artifacts[] for technical details
  - Update logic_flow to include "Consult artifacts when needed"

- **gitignore**: Add .workflow directory to ignore list

🎯 Result: Balanced strategy - 100% fidelity in analysis phase, 78% token efficiency in planning phase, hybrid approach in execution phase

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-10-04 12:44:07 +08:00
parent 237a2867fb
commit e90c9baa13
4 changed files with 47 additions and 17 deletions

View File

@@ -130,6 +130,15 @@ Advanced solution design and feasibility analysis engine with parallel CLI execu
- Tech stack from tech_stack section
- Project structure from statistics section
**ANALYSIS PRIORITY - Use ALL source documents from context-package assets[]**:
1. PRIMARY SOURCES (Highest Priority): Individual role analysis.md files (system-architect, ui-designer, product-manager, etc.)
- These contain complete technical details, design rationale, ADRs, and decision context
- Extract: Technical specs, API schemas, design tokens, caching configs, performance metrics
2. SYNTHESIS REFERENCE (Medium Priority): synthesis-specification.md
- Use for integrated requirements and cross-role alignment
- Validate decisions and identify integration points
3. TOPIC FRAMEWORK (Low Priority): topic-framework.md for discussion context
EXPECTED:
1. CURRENT STATE ANALYSIS: Existing patterns, code structure, integration points, technical debt
2. SOLUTION DESIGN: Core architecture principles, system design, key design decisions with rationale

View File

@@ -169,7 +169,21 @@ Task(
{
"type": "synthesis_specification",
"path": "{synthesis_spec_path}",
"priority": "highest"
"priority": "highest",
"usage": "Primary requirement source - use for consolidated requirements and cross-role alignment"
},
{
"type": "role_analysis",
"path": "{role_analysis_path}",
"priority": "high",
"usage": "Technical/design/business details from specific roles. Common roles: system-architect (ADRs, APIs, caching), ui-designer (design tokens, layouts), product-manager (user stories, metrics)",
"note": "Dynamically discovered - multiple role analysis files included based on brainstorming results"
},
{
"type": "topic_framework",
"path": "{topic_framework_path}",
"priority": "low",
"usage": "Discussion context and framework structure"
}
]
},
@@ -203,12 +217,13 @@ Task(
}
],
"implementation_approach": {
"task_description": "Implement '[title]' following synthesis specification",
"task_description": "Implement '[title]' following synthesis specification. PRIORITY: Use synthesis-specification.md as primary requirement source. When implementation needs technical details (e.g., API schemas, caching configs, design tokens), refer to artifacts[] for detailed specifications from original role analyses.",
"modification_points": ["Apply requirements from synthesis"],
"logic_flow": [
"Load synthesis specification",
"Analyze existing patterns",
"Implement following specification",
"Consult artifacts for technical details when needed",
"Validate against acceptance criteria"
]
},

View File

@@ -84,21 +84,22 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
"source": "brainstorm_synthesis",
"path": ".workflow/WFS-[session]/.brainstorming/synthesis-specification.md",
"priority": "highest",
"contains": "complete_integrated_specification"
"usage": "Primary requirement source - use for consolidated requirements and cross-role alignment"
},
{
"type": "role_analysis",
"source": "brainstorm_roles",
"path": ".workflow/WFS-[session]/.brainstorming/[role-name]/analysis.md",
"priority": "high",
"usage": "Technical/design/business details from specific roles. Common roles: system-architect (ADRs, APIs, caching), ui-designer (design tokens, layouts), product-manager (user stories, metrics)",
"note": "Dynamically discovered - multiple role analysis files may be included based on brainstorming results"
},
{
"type": "topic_framework",
"source": "brainstorm_framework",
"path": ".workflow/WFS-[session]/.brainstorming/topic-framework.md",
"priority": "medium",
"contains": "discussion_framework_structure"
},
{
"type": "individual_role_analysis",
"source": "brainstorm_roles",
"path": ".workflow/WFS-[session]/.brainstorming/[role]/analysis.md",
"priority": "low",
"contains": "role_specific_analysis_fallback"
"usage": "Discussion context and framework structure"
}
]
},
@@ -115,14 +116,16 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
"on_error": "skip_optional"
},
{
"step": "load_individual_role_artifacts",
"action": "Load individual role analyses as fallback",
"step": "load_role_analysis_artifacts",
"action": "Load role-specific analysis documents for technical details",
"note": "These artifacts contain implementation details not in synthesis. Consult when needing: API schemas, caching configs, design tokens, ADRs, performance metrics.",
"commands": [
"bash(find .workflow/WFS-[session]/.brainstorming/ -name 'analysis.md' 2>/dev/null | head -8)",
"Read(.workflow/WFS-[session]/.brainstorming/system-architect/analysis.md)",
"Read(.workflow/WFS-[session]/.brainstorming/ui-designer/analysis.md)",
"Read(.workflow/WFS-[session]/.brainstorming/system-architect/analysis.md)"
"Read(.workflow/WFS-[session]/.brainstorming/product-manager/analysis.md)"
],
"output_to": "individual_artifacts",
"output_to": "role_analysis_artifacts",
"on_error": "skip_optional"
},
{
@@ -152,10 +155,11 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
}
],
"implementation_approach": {
"task_description": "Implement '[title]' following synthesis specification",
"task_description": "Implement '[title]' following synthesis specification. PRIORITY: Use synthesis-specification.md as primary requirement source. When implementation needs technical details (e.g., API schemas, caching configs, design tokens), refer to artifacts[] for detailed specifications from original role analyses.",
"modification_points": [
"Apply consolidated requirements from synthesis-specification.md",
"Follow technical guidelines from synthesis",
"Consult artifacts for implementation details when needed",
"Integrate with existing patterns"
],
"logic_flow": [
@@ -163,6 +167,7 @@ Generate task JSON files and IMPL_PLAN.md from analysis results with automatic a
"Extract requirements and design",
"Analyze existing patterns",
"Implement following specification",
"Consult artifacts for technical details when needed",
"Validate against acceptance criteria"
]
},

3
.gitignore vendored
View File

@@ -17,4 +17,5 @@ yarn-error.log*
Thumbs.db
.env
settings.local.json
settings.local.json
.workflow