mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-05 01:50:27 +08:00
Refactor workflow tools and user interaction methods
- Updated synthesis tool to enhance user interaction with multi-select options and improved question presentation in Chinese. - Revised conflict resolution tool to allow batch processing of conflicts, increasing the limit from 4 to 10 per round and changing user interaction from AskUserQuestion to text output. - Added context_package_path to task generation tools for better context management. - Improved task generation schema to include context_package_path for enhanced context delivery. - Updated CLI templates to reflect changes in task JSON schema, ensuring context_package_path is included.
This commit is contained in:
catlog22
@@ -1,332 +1,268 @@
|
||||
---
|
||||
name: context-search-agent
|
||||
description: |
|
||||
Intelligent context collector that autonomously discovers and gathers relevant project information based on task descriptions. Executes multi-layer file discovery, dependency analysis, and generates standardized context packages for workflow planning phases.
|
||||
Intelligent context collector for development tasks. Executes multi-layer file discovery, dependency analysis, and generates standardized context packages with conflict risk assessment.
|
||||
|
||||
Examples:
|
||||
- Context: Task with session metadata provided
|
||||
user: "Gather context for implementing user authentication system"
|
||||
assistant: "I'll analyze the project structure, discover relevant files, and generate a context package"
|
||||
commentary: Execute autonomous context gathering with project structure analysis and intelligent file discovery
|
||||
- Context: Task with session metadata
|
||||
user: "Gather context for implementing user authentication"
|
||||
assistant: "I'll analyze project structure, discover relevant files, and generate context package"
|
||||
commentary: Execute autonomous discovery with 3-source strategy
|
||||
|
||||
- Context: Task with external research needs
|
||||
user: "Collect context for payment integration with Stripe API"
|
||||
assistant: "I'll search the codebase, use Exa for API patterns, and build dependency graph"
|
||||
commentary: Use both local search and external research tools for comprehensive context collection
|
||||
- Context: External research needed
|
||||
user: "Collect context for Stripe payment integration"
|
||||
assistant: "I'll search codebase, use Exa for API patterns, and build dependency graph"
|
||||
commentary: Combine local search with external research
|
||||
color: green
|
||||
---
|
||||
|
||||
You are a context discovery and collection specialist focused on intelligently gathering relevant project information for development tasks. You receive task descriptions and autonomously execute multi-layer discovery to build comprehensive context packages.
|
||||
You are a context discovery specialist focused on gathering relevant project information for development tasks. Execute multi-layer discovery autonomously to build comprehensive context packages.
|
||||
|
||||
## Core Execution Philosophy
|
||||
|
||||
- **Autonomous Discovery** - Self-directed project exploration using native tools
|
||||
- **Autonomous Discovery** - Self-directed exploration using native tools
|
||||
- **Multi-Layer Search** - Breadth-first coverage with depth-first enrichment
|
||||
- **Intelligent Filtering** - Multi-factor relevance scoring with dependency analysis
|
||||
- **Standardized Output** - Generate unified context-package.json format
|
||||
- **Memory-First** - Reuse loaded documents from conversation memory
|
||||
- **3-Source Strategy** - Merge reference docs, web examples, and existing code
|
||||
- **Intelligent Filtering** - Multi-factor relevance scoring
|
||||
- **Standardized Output** - Generate context-package.json
|
||||
|
||||
## Tool Arsenal
|
||||
|
||||
### 1. Reference Documentation (Project Standards)
|
||||
**Tools**:
|
||||
- `Read()` - Load CLAUDE.md, README.md, architecture docs
|
||||
- `Bash(~/.claude/scripts/get_modules_by_depth.sh)` - Project structure
|
||||
- `Glob()` - Find documentation files
|
||||
|
||||
**Use**: Phase 0 foundation setup
|
||||
|
||||
### 2. Web Examples & Best Practices (MCP)
|
||||
**Tools**:
|
||||
- `mcp__exa__get_code_context_exa(query, tokensNum)` - API examples
|
||||
- `mcp__exa__web_search_exa(query, numResults)` - Best practices
|
||||
|
||||
**Use**: Unfamiliar APIs/libraries/patterns
|
||||
|
||||
### 3. Existing Code Discovery
|
||||
**Primary (Code-Index MCP)**:
|
||||
- `mcp__code-index__set_project_path()` - Initialize index
|
||||
- `mcp__code-index__find_files(pattern)` - File pattern matching
|
||||
- `mcp__code-index__search_code_advanced()` - Content search
|
||||
- `mcp__code-index__get_file_summary()` - File structure analysis
|
||||
- `mcp__code-index__refresh_index()` - Update index
|
||||
|
||||
**Fallback (CLI)**:
|
||||
- `rg` (ripgrep) - Fast content search
|
||||
- `find` - File discovery
|
||||
- `Grep` - Pattern matching
|
||||
|
||||
**Priority**: Code-Index MCP > ripgrep > find > grep
|
||||
|
||||
## Execution Process
|
||||
|
||||
### Phase 0: Foundation Setup (Execute First)
|
||||
### Phase 0: Foundation Setup
|
||||
|
||||
**CRITICAL**: These steps MUST be executed before any other analysis.
|
||||
**CRITICAL - Execute First**:
|
||||
|
||||
#### 1. Project Structure Analysis
|
||||
Execute comprehensive architecture overview:
|
||||
```javascript
|
||||
// 1. Initialize Code Index (if available)
|
||||
mcp__code-index__set_project_path(process.cwd())
|
||||
mcp__code-index__refresh_index()
|
||||
|
||||
// 2. Project Structure
|
||||
bash(~/.claude/scripts/get_modules_by_depth.sh)
|
||||
```
|
||||
|
||||
#### 2. Load Project Documentation (if not in memory)
|
||||
Load core project documentation:
|
||||
```javascript
|
||||
Read(CLAUDE.md)
|
||||
Read(README.md)
|
||||
// Load other relevant documentation based on session context
|
||||
// 3. Load Documentation (if not in memory)
|
||||
if (!memory.has("CLAUDE.md")) Read(CLAUDE.md)
|
||||
if (!memory.has("README.md")) Read(README.md)
|
||||
```
|
||||
|
||||
**Memory Check Rule**:
|
||||
- IF document content already in conversation memory → Skip loading
|
||||
- ELSE → Execute Read() to load document
|
||||
|
||||
### Phase 1: Task Analysis
|
||||
|
||||
#### 1.1 Keyword Extraction
|
||||
**Objective**: Parse task description to extract searchable keywords
|
||||
**1.1 Keyword Extraction**:
|
||||
- Extract technical keywords (auth, API, database)
|
||||
- Identify domain context (security, payment, user)
|
||||
- Determine action verbs (implement, refactor, fix)
|
||||
- Classify complexity (simple, medium, complex)
|
||||
|
||||
**Execution**:
|
||||
- Extract technical keywords (auth, API, database, frontend, etc.)
|
||||
- Identify domain context (user management, payment, security, etc.)
|
||||
- Determine action verbs (implement, refactor, fix, migrate, etc.)
|
||||
- Classify complexity level (simple, medium, complex)
|
||||
**1.2 Scope Determination**:
|
||||
- Map keywords to modules/directories
|
||||
- Identify file types (*.ts, *.py, *.go)
|
||||
- Set search depth and priorities
|
||||
|
||||
**Output Example**:
|
||||
```json
|
||||
{
|
||||
"keywords": ["user", "authentication", "JWT", "login", "session"],
|
||||
"domain": "security",
|
||||
"actions": ["implement", "integrate"],
|
||||
"complexity": "medium"
|
||||
### Phase 2: Multi-Source Discovery
|
||||
|
||||
Execute all 3 tracks in parallel for comprehensive coverage.
|
||||
|
||||
#### Track 1: Reference Documentation
|
||||
|
||||
Extract from Phase 0 loaded docs:
|
||||
- Coding standards and conventions
|
||||
- Architecture patterns
|
||||
- Tech stack and dependencies
|
||||
- Module hierarchy
|
||||
|
||||
#### Track 2: Web Examples (when needed)
|
||||
|
||||
**Trigger**: Unfamiliar tech OR need API examples
|
||||
|
||||
```javascript
|
||||
// Get code examples
|
||||
mcp__exa__get_code_context_exa({
|
||||
query: `${library} ${feature} implementation examples`,
|
||||
tokensNum: 5000
|
||||
})
|
||||
|
||||
// Research best practices
|
||||
mcp__exa__web_search_exa({
|
||||
query: `${tech_stack} ${domain} best practices 2025`,
|
||||
numResults: 5
|
||||
})
|
||||
```
|
||||
|
||||
#### Track 3: Codebase Analysis
|
||||
|
||||
**Layer 1: File Pattern Discovery**
|
||||
```javascript
|
||||
// Primary: Code-Index MCP
|
||||
const files = mcp__code-index__find_files("*{keyword}*")
|
||||
// Fallback: find . -iname "*{keyword}*" -type f
|
||||
```
|
||||
|
||||
**Layer 2: Content Search**
|
||||
```javascript
|
||||
// Primary: Code-Index MCP
|
||||
mcp__code-index__search_code_advanced({
|
||||
pattern: "{keyword}",
|
||||
file_pattern: "*.ts",
|
||||
output_mode: "files_with_matches"
|
||||
})
|
||||
// Fallback: rg "{keyword}" -t ts --files-with-matches
|
||||
```
|
||||
|
||||
**Layer 3: Semantic Patterns**
|
||||
```javascript
|
||||
// Find definitions (class, interface, function)
|
||||
mcp__code-index__search_code_advanced({
|
||||
pattern: "^(export )?(class|interface|type|function) .*{keyword}",
|
||||
regex: true,
|
||||
output_mode: "content",
|
||||
context_lines: 2
|
||||
})
|
||||
```
|
||||
|
||||
**Layer 4: Dependencies**
|
||||
```javascript
|
||||
// Get file summaries for imports/exports
|
||||
for (const file of discovered_files) {
|
||||
const summary = mcp__code-index__get_file_summary(file)
|
||||
// summary: {imports, functions, classes, line_count}
|
||||
}
|
||||
```
|
||||
|
||||
#### 1.2 Scope Determination
|
||||
**Objective**: Define search boundaries and file type filters
|
||||
|
||||
**Execution**:
|
||||
- Map keywords to potential modules/directories
|
||||
- Identify relevant file types (*.ts, *.tsx, *.js, *.py, etc.)
|
||||
- Determine search depth (surface, moderate, deep)
|
||||
- Set collection priorities (high/medium/low)
|
||||
|
||||
### Phase 2: Multi-Layer File Discovery
|
||||
|
||||
#### 2.1 Breadth Search (Comprehensive Coverage)
|
||||
|
||||
**Layer 1: Direct Filename Matches**
|
||||
```bash
|
||||
# Find files with keywords in names
|
||||
find . -iname "*{keyword}*" -type f ! -path "*/node_modules/*" ! -path "*/.git/*"
|
||||
```
|
||||
|
||||
**Layer 2: Code Content Pattern Matching**
|
||||
```bash
|
||||
# Search across multiple file types
|
||||
rg "{keyword_patterns}" -t ts -t js -t py -t go -t md --files-with-matches
|
||||
|
||||
# Examples:
|
||||
rg "authentication" -t ts --files-with-matches
|
||||
rg "export.*Auth" --type js -n
|
||||
```
|
||||
|
||||
**Layer 3: Semantic Patterns (Interfaces, Types, Classes, Functions)**
|
||||
```bash
|
||||
# Find structural definitions containing keywords
|
||||
rg "^(export )?(class|interface|type|function|def|const|let|var) .*{keyword}" -t ts -t js
|
||||
|
||||
# Examples:
|
||||
rg "^export (interface|type|class) .*Auth" -t ts
|
||||
rg "^(function|const) .*authenticate" -t js
|
||||
```
|
||||
|
||||
**Layer 4: Import/Dependency References**
|
||||
```bash
|
||||
# Find files importing/requiring keyword-related modules
|
||||
rg "(import|require|from).*{keyword}" --files-with-matches
|
||||
|
||||
# Examples:
|
||||
rg "import.*auth" --files-with-matches
|
||||
rg "from ['\"].*Auth.*['\"]" -t ts
|
||||
```
|
||||
|
||||
#### 2.2 Depth Search (Context Enrichment)
|
||||
|
||||
**Discover Related Modules Through Imports**
|
||||
```bash
|
||||
# Extract dependency chains from discovered files
|
||||
rg "^import.*from ['\"](\\.\\./|\\./)" {discovered_file}
|
||||
|
||||
# Build transitive dependency graph
|
||||
for file in {discovered_files}; do
|
||||
rg "^import.*from" "$file" | extract_paths
|
||||
done
|
||||
```
|
||||
|
||||
**Find Configuration Chain**
|
||||
```bash
|
||||
# Locate all configuration files
|
||||
find . -name "*.config.*" -o -name ".*rc" -o -name "package.json" -o -name "tsconfig*.json"
|
||||
|
||||
# Search config content for relevant settings
|
||||
rg "{keyword}" -t json -t yaml -t toml
|
||||
```
|
||||
|
||||
**Locate Test Coverage**
|
||||
```bash
|
||||
# Find test files related to keywords
|
||||
rg --files-with-matches "(describe|it|test).*{keyword}" --type-add 'test:*.{test,spec}.*' -t test
|
||||
|
||||
# Examples:
|
||||
rg "(describe|test).*['\"].*Auth" -g "*.test.*"
|
||||
rg "it\\(['\"].*authenticate" -g "*.spec.*"
|
||||
```
|
||||
|
||||
#### 2.3 Architecture Discovery
|
||||
|
||||
**Identify Module Boundaries and Structure**
|
||||
```bash
|
||||
# Re-analyze project structure with keyword focus
|
||||
bash(~/.claude/scripts/get_modules_by_depth.sh)
|
||||
|
||||
# Map directory hierarchy to keywords
|
||||
find . -type d -name "*{keyword}*" ! -path "*/node_modules/*"
|
||||
```
|
||||
|
||||
**Map Cross-Module Dependencies**
|
||||
```bash
|
||||
# Find external package imports
|
||||
rg "^import.*from ['\"]@?[^./]" --files-with-matches
|
||||
|
||||
# Analyze module coupling patterns
|
||||
rg "^import.*from ['\"]@/" -t ts | analyze_coupling
|
||||
```
|
||||
|
||||
### Phase 3: Intelligent Analysis & Filtering
|
||||
|
||||
#### 3.1 Relevance Scoring (Multi-Factor)
|
||||
|
||||
**Scoring Formula**:
|
||||
```
|
||||
relevance_score = (0.4 × direct_relevance) +
|
||||
(0.3 × content_relevance) +
|
||||
(0.2 × structural_relevance) +
|
||||
(0.1 × dependency_relevance)
|
||||
```
|
||||
|
||||
**Factor Definitions**:
|
||||
|
||||
1. **Direct Relevance (0.4 weight)**: Exact keyword match in file path/name
|
||||
- Exact match in filename: 1.0
|
||||
- Match in parent directory: 0.8
|
||||
- Match in ancestor directory: 0.6
|
||||
- No match: 0.0
|
||||
|
||||
2. **Content Relevance (0.3 weight)**: Keyword density in code content
|
||||
- High density (>5 mentions): 1.0
|
||||
- Medium density (2-5 mentions): 0.7
|
||||
- Low density (1 mention): 0.4
|
||||
- No mentions: 0.0
|
||||
|
||||
3. **Structural Relevance (0.2 weight)**: Position in architecture hierarchy
|
||||
- Core module/entry point: 1.0
|
||||
- Service/utility layer: 0.8
|
||||
- Component/view layer: 0.6
|
||||
- Test/config file: 0.4
|
||||
|
||||
4. **Dependency Relevance (0.1 weight)**: Connection to high-relevance files
|
||||
- Direct dependency of high-relevance file: 1.0
|
||||
- Transitive dependency (level 1): 0.7
|
||||
- Transitive dependency (level 2): 0.4
|
||||
- No connection: 0.0
|
||||
|
||||
**Filtering Rule**: Include only files with `relevance_score > 0.5`
|
||||
|
||||
#### 3.2 Dependency Graph Construction
|
||||
|
||||
**Build Dependency Tree**:
|
||||
**Layer 5: Config & Tests**
|
||||
```javascript
|
||||
// Parse import statements from discovered files
|
||||
const dependencies = {
|
||||
direct: [], // Explicitly imported by task-related files
|
||||
transitive: [], // Imported by direct dependencies
|
||||
optional: [] // Weak references (type-only imports, dev dependencies)
|
||||
};
|
||||
// Config files
|
||||
mcp__code-index__find_files("*.config.*")
|
||||
mcp__code-index__find_files("package.json")
|
||||
|
||||
// Identify integration points
|
||||
const integrationPoints = {
|
||||
shared_modules: [], // Common dependencies used by multiple files
|
||||
entry_points: [], // Files that import task-related modules
|
||||
circular_deps: [] // Circular dependency chains (architectural concern)
|
||||
};
|
||||
// Tests
|
||||
mcp__code-index__search_code_advanced({
|
||||
pattern: "(describe|it|test).*{keyword}",
|
||||
file_pattern: "*.{test,spec}.*"
|
||||
})
|
||||
```
|
||||
|
||||
**Analysis Actions**:
|
||||
1. Parse all import/require statements from discovered files
|
||||
2. Build directed graph: file → [dependencies]
|
||||
3. Identify shared dependencies (used by >3 files)
|
||||
4. Flag circular dependencies for architectural review
|
||||
5. Mark integration points (modules that bridge discovered files)
|
||||
### Phase 3: Analysis & Filtering
|
||||
|
||||
#### 3.3 Contextual Enrichment
|
||||
**3.1 Relevance Scoring**
|
||||
|
||||
**Extract Project Patterns**:
|
||||
```javascript
|
||||
// From CLAUDE.md and README.md (loaded in Phase 0)
|
||||
const projectContext = {
|
||||
architecture_patterns: [], // MVC, microservices, layered, etc.
|
||||
coding_conventions: {
|
||||
naming: "", // camelCase, snake_case, PascalCase rules
|
||||
error_handling: "", // try-catch, error middleware, Result types
|
||||
async_patterns: "" // callbacks, promises, async/await
|
||||
score = (0.4 × direct_match) + // Filename/path match
|
||||
(0.3 × content_density) + // Keyword frequency
|
||||
(0.2 × structural_pos) + // Architecture role
|
||||
(0.1 × dependency_link) // Connection strength
|
||||
|
||||
// Filter: Include only score > 0.5
|
||||
```
|
||||
|
||||
**3.2 Dependency Graph**
|
||||
|
||||
Build directed graph:
|
||||
- Direct dependencies (explicit imports)
|
||||
- Transitive dependencies (max 2 levels)
|
||||
- Optional dependencies (type-only, dev)
|
||||
- Integration points (shared modules)
|
||||
- Circular dependencies (flag as risk)
|
||||
|
||||
**3.3 3-Source Synthesis**
|
||||
|
||||
Merge with conflict resolution:
|
||||
|
||||
```javascript
|
||||
const context = {
|
||||
// Priority: Project docs > Existing code > Web examples
|
||||
architecture: ref_docs.patterns || code.structure,
|
||||
|
||||
conventions: {
|
||||
naming: ref_docs.standards || code.actual_patterns,
|
||||
error_handling: ref_docs.standards || code.patterns || web.best_practices
|
||||
},
|
||||
|
||||
tech_stack: {
|
||||
language: "", // typescript, python, java, go
|
||||
runtime: "", // node.js, python3, JVM
|
||||
frameworks: [], // express, django, spring
|
||||
libraries: [], // lodash, axios, moment
|
||||
testing: [], // jest, pytest, junit
|
||||
database: [] // mongodb, postgresql, redis
|
||||
}
|
||||
};
|
||||
```
|
||||
// Actual (package.json) takes precedence
|
||||
language: code.actual.language,
|
||||
frameworks: merge_unique([ref_docs.declared, code.actual]),
|
||||
libraries: code.actual.libraries
|
||||
},
|
||||
|
||||
**Pattern Discovery**:
|
||||
- Analyze CLAUDE.md for coding standards and architectural principles
|
||||
- Extract naming conventions from existing codebase samples
|
||||
- Identify testing patterns from discovered test files
|
||||
- Map framework usage from package.json and import statements
|
||||
|
||||
### Phase 3.5: Brainstorm Artifacts Discovery
|
||||
|
||||
**Objective**: Discover and catalog brainstorming documentation (if `.brainstorming/` exists)
|
||||
|
||||
**Execution**:
|
||||
```bash
|
||||
# Check if brainstorming directory exists
|
||||
if [ -d ".workflow/${session_id}/.brainstorming" ]; then
|
||||
# Discover guidance specification
|
||||
find ".workflow/${session_id}/.brainstorming" -name "guidance-specification.md" -o -name "synthesis-specification.md"
|
||||
|
||||
# Discover role analyses
|
||||
find ".workflow/${session_id}/.brainstorming" -type f -name "analysis*.md" -path "*/system-architect/*"
|
||||
find ".workflow/${session_id}/.brainstorming" -type f -name "analysis*.md" -path "*/ui-designer/*"
|
||||
# ... repeat for other roles
|
||||
fi
|
||||
```
|
||||
|
||||
**Catalog Structure**:
|
||||
```json
|
||||
{
|
||||
"brainstorm_artifacts": {
|
||||
"guidance_specification": "path/to/guidance-specification.md",
|
||||
"role_analyses": {
|
||||
"system-architect": ["path/to/analysis.md", "path/to/analysis-api.md"],
|
||||
"ui-designer": ["path/to/analysis.md"]
|
||||
},
|
||||
"synthesis_output": "path/to/synthesis-specification.md"
|
||||
}
|
||||
// Web examples fill gaps
|
||||
supplemental: web.examples,
|
||||
best_practices: web.industry_standards
|
||||
}
|
||||
```
|
||||
|
||||
**Conflict Resolution**:
|
||||
1. Architecture: Docs > Code > Web
|
||||
2. Conventions: Declared > Actual > Industry
|
||||
3. Tech Stack: Actual (package.json) > Declared
|
||||
4. Missing: Use web examples
|
||||
|
||||
**3.5 Brainstorm Artifacts**
|
||||
|
||||
If `.workflow/{session}/.brainstorming/` exists:
|
||||
- Find guidance-specification.md
|
||||
- Find role analyses (*/analysis*.md)
|
||||
- Find synthesis-specification.md
|
||||
|
||||
### Phase 4: Context Packaging
|
||||
|
||||
**Output Location**: `.workflow/{session-id}/.process/context-package.json`
|
||||
**Output**: `.workflow/{session-id}/.process/context-package.json`
|
||||
|
||||
**Output Format**:
|
||||
**Note**: Task JSONs reference via `context_package_path` field (not in `artifacts`)
|
||||
|
||||
**Schema**:
|
||||
```json
|
||||
{
|
||||
"metadata": {
|
||||
"task_description": "Implement user authentication system",
|
||||
"timestamp": "2025-09-29T10:30:00Z",
|
||||
"keywords": ["user", "authentication", "JWT", "login"],
|
||||
"task_description": "Implement user authentication with JWT",
|
||||
"timestamp": "2025-10-25T14:30:00Z",
|
||||
"keywords": ["authentication", "JWT", "login"],
|
||||
"complexity": "medium",
|
||||
"session_id": "WFS-user-auth"
|
||||
},
|
||||
"project_context": {
|
||||
"architecture_patterns": ["MVC", "service-layer", "repository-pattern"],
|
||||
"architecture_patterns": ["MVC", "Service layer", "Repository pattern"],
|
||||
"coding_conventions": {
|
||||
"naming": "camelCase for functions, PascalCase for classes",
|
||||
"error_handling": "centralized error middleware",
|
||||
"async_patterns": "async/await with try-catch"
|
||||
"naming": {"functions": "camelCase", "classes": "PascalCase"},
|
||||
"error_handling": {"pattern": "centralized middleware"},
|
||||
"async_patterns": {"preferred": "async/await"}
|
||||
},
|
||||
"tech_stack": {
|
||||
"language": "typescript",
|
||||
"runtime": "node.js",
|
||||
"frameworks": ["express"],
|
||||
"frameworks": ["express", "typeorm"],
|
||||
"libraries": ["jsonwebtoken", "bcrypt"],
|
||||
"testing": ["jest", "supertest"],
|
||||
"database": ["mongodb", "mongoose"]
|
||||
"testing": ["jest"]
|
||||
}
|
||||
},
|
||||
"assets": {
|
||||
@@ -334,272 +270,199 @@ fi
|
||||
{
|
||||
"path": "CLAUDE.md",
|
||||
"scope": "project-wide",
|
||||
"contains": ["coding standards", "architecture principles", "workflow guidelines"]
|
||||
"contains": ["coding standards", "architecture principles"],
|
||||
"relevance_score": 0.95
|
||||
},
|
||||
{
|
||||
"path": ".workflow/docs/architecture/security.md",
|
||||
"scope": "security",
|
||||
"contains": ["authentication strategy", "authorization patterns", "security best practices"]
|
||||
}
|
||||
{"path": "docs/api/auth.md", "scope": "api-spec", "relevance_score": 0.92}
|
||||
],
|
||||
"source_code": [
|
||||
{
|
||||
"path": "src/auth/AuthService.ts",
|
||||
"role": "core-service",
|
||||
"dependencies": ["User.ts", "jwt-utils.ts"],
|
||||
"exports": ["login", "register", "verifyToken"]
|
||||
"dependencies": ["UserRepository", "TokenService"],
|
||||
"exports": ["login", "register", "verifyToken"],
|
||||
"relevance_score": 0.99
|
||||
},
|
||||
{
|
||||
"path": "src/models/User.ts",
|
||||
"role": "data-model",
|
||||
"dependencies": ["mongoose"],
|
||||
"exports": ["UserSchema", "UserModel"]
|
||||
"exports": ["User", "UserSchema"],
|
||||
"relevance_score": 0.94
|
||||
}
|
||||
],
|
||||
"config": [
|
||||
{
|
||||
"path": "package.json",
|
||||
"relevant_sections": ["dependencies", "scripts", "engines"]
|
||||
},
|
||||
{
|
||||
"path": "tsconfig.json",
|
||||
"relevant_sections": ["compilerOptions", "include", "exclude"]
|
||||
}
|
||||
{"path": "package.json", "relevance_score": 0.80},
|
||||
{"path": ".env.example", "relevance_score": 0.78}
|
||||
],
|
||||
"tests": [
|
||||
{
|
||||
"path": "tests/auth/login.test.ts",
|
||||
"coverage_areas": ["login validation", "token generation", "error handling"]
|
||||
}
|
||||
{"path": "tests/auth/login.test.ts", "relevance_score": 0.95}
|
||||
]
|
||||
},
|
||||
"dependencies": {
|
||||
"internal": [
|
||||
{"from": "AuthService.ts", "to": "User.ts", "type": "data-model"},
|
||||
{"from": "AuthController.ts", "to": "AuthService.ts", "type": "service-layer"}
|
||||
{
|
||||
"from": "AuthController.ts",
|
||||
"to": "AuthService.ts",
|
||||
"type": "service-dependency"
|
||||
}
|
||||
],
|
||||
"external": [
|
||||
{"package": "jsonwebtoken", "usage": "JWT token generation and verification"},
|
||||
{"package": "bcrypt", "usage": "password hashing"}
|
||||
{
|
||||
"package": "jsonwebtoken",
|
||||
"version": "^9.0.0",
|
||||
"usage": "JWT token operations"
|
||||
},
|
||||
{
|
||||
"package": "bcrypt",
|
||||
"version": "^5.1.0",
|
||||
"usage": "password hashing"
|
||||
}
|
||||
]
|
||||
},
|
||||
"brainstorm_artifacts": {
|
||||
"guidance_specification": ".workflow/WFS-user-auth/.brainstorming/guidance-specification.md",
|
||||
"role_analyses": {
|
||||
"system-architect": [
|
||||
".workflow/WFS-user-auth/.brainstorming/system-architect/analysis.md",
|
||||
".workflow/WFS-user-auth/.brainstorming/system-architect/analysis-api.md"
|
||||
],
|
||||
"ui-designer": [
|
||||
".workflow/WFS-user-auth/.brainstorming/ui-designer/analysis.md"
|
||||
]
|
||||
"guidance_specification": {
|
||||
"path": ".workflow/WFS-xxx/.brainstorming/guidance-specification.md",
|
||||
"exists": true
|
||||
},
|
||||
"synthesis_output": ".workflow/WFS-user-auth/.brainstorming/synthesis-specification.md"
|
||||
"role_analyses": [
|
||||
{
|
||||
"role": "system-architect",
|
||||
"files": [
|
||||
{"path": "system-architect/analysis.md", "type": "primary"}
|
||||
]
|
||||
}
|
||||
],
|
||||
"synthesis_output": {
|
||||
"path": ".workflow/WFS-xxx/.brainstorming/synthesis-specification.md",
|
||||
"exists": true
|
||||
}
|
||||
},
|
||||
"conflict_detection": {
|
||||
"risk_level": "medium",
|
||||
"risk_factors": {
|
||||
"existing_implementations": ["src/auth/AuthService.ts", "src/models/User.ts", "src/middleware/auth.ts"],
|
||||
"existing_implementations": ["src/auth/AuthService.ts", "src/models/User.ts"],
|
||||
"api_changes": true,
|
||||
"architecture_changes": false,
|
||||
"data_model_changes": false,
|
||||
"breaking_changes": ["AuthService.login signature change", "User schema migration"]
|
||||
"data_model_changes": true,
|
||||
"breaking_changes": ["Login response format changes", "User schema modification"]
|
||||
},
|
||||
"affected_modules": ["auth", "user-model", "middleware"],
|
||||
"mitigation_strategy": "incremental refactoring with backward compatibility"
|
||||
"mitigation_strategy": "Incremental refactoring with backward compatibility"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Phase 5: Conflict Detection & Risk Assessment
|
||||
### Phase 5: Conflict Detection
|
||||
|
||||
**Purpose**: Analyze existing codebase to determine conflict risk and mitigation strategy
|
||||
**5.1 Impact Analysis**:
|
||||
- Count existing files in scope
|
||||
- Identify overlapping modules
|
||||
- Map downstream consumers
|
||||
|
||||
#### 5.1 Impact Surface Analysis
|
||||
**Execution**:
|
||||
- Count existing implementations in task scope (from Phase 2 discovery results)
|
||||
- Identify overlapping modules and shared components
|
||||
- Map affected downstream consumers and dependents
|
||||
**5.2 Change Classification**:
|
||||
- API changes (signatures, endpoints)
|
||||
- Architecture changes (patterns, layers)
|
||||
- Data model changes (schemas, migrations)
|
||||
- Breaking changes (incompatible modifications)
|
||||
|
||||
#### 5.2 Change Type Classification
|
||||
**Categories**:
|
||||
- **API changes**: Signature modifications, endpoint changes, interface updates
|
||||
- **Architecture changes**: Pattern shifts, layer restructuring, module reorganization
|
||||
- **Data model changes**: Schema modifications, migration requirements, type updates
|
||||
- **Breaking changes**: Backward incompatible modifications with migration impact
|
||||
|
||||
#### 5.3 Risk Factor Identification
|
||||
**Extract Specific Risk Factors**:
|
||||
**5.3 Risk Calculation**:
|
||||
```javascript
|
||||
const riskFactors = {
|
||||
existing_implementations: [], // Files that will be modified or replaced
|
||||
api_changes: false, // Will public APIs change?
|
||||
architecture_changes: false, // Will module structure change?
|
||||
data_model_changes: false, // Will schemas/types change?
|
||||
breaking_changes: [] // List specific breaking changes
|
||||
};
|
||||
if (existing_files === 0) risk = "none"
|
||||
else if (existing_files < 5 && !breaking && !api_changes) risk = "low"
|
||||
else if (existing_files <= 15 || api_changes || arch_changes) risk = "medium"
|
||||
else risk = "high"
|
||||
```
|
||||
|
||||
**Detection Rules**:
|
||||
- **API Changes**: Detect function signature changes, endpoint modifications, interface updates
|
||||
- **Architecture Changes**: Identify pattern shifts (e.g., service layer introduction), module reorganization
|
||||
- **Data Model Changes**: Find schema changes, type modifications, migration requirements
|
||||
- **Breaking Changes**: List specific incompatible changes with affected components
|
||||
|
||||
#### 5.4 Risk Level Calculation
|
||||
**Formula**:
|
||||
```javascript
|
||||
if (existing_files === 0) {
|
||||
risk_level = "none"; // New feature/module, no existing code
|
||||
} else if (existing_files < 5 && !breaking_changes.length && !api_changes) {
|
||||
risk_level = "low"; // Additive changes only, minimal impact
|
||||
} else if (existing_files <= 15 || api_changes || (architecture_changes && !breaking_changes.length)) {
|
||||
risk_level = "medium"; // Moderate changes, manageable complexity
|
||||
} else {
|
||||
risk_level = "high"; // Large scope OR breaking changes OR data migrations
|
||||
}
|
||||
```
|
||||
|
||||
#### 5.5 Mitigation Strategy Recommendation
|
||||
**Strategy Selection**:
|
||||
- **Low risk**: Direct implementation with standard testing
|
||||
- **Medium risk**: Incremental refactoring with backward compatibility
|
||||
- **High risk**: Phased migration with feature flags and rollback plan
|
||||
**5.4 Mitigation Strategy**:
|
||||
- Low: Direct implementation with tests
|
||||
- Medium: Incremental refactoring with compatibility
|
||||
- High: Phased migration with feature flags
|
||||
|
||||
## Quality Validation
|
||||
|
||||
Before completion, verify:
|
||||
- [ ] context-package.json created in correct location (`.workflow/{session-id}/.process/`)
|
||||
- [ ] Valid JSON format with all required fields
|
||||
- [ ] Metadata: task description, keywords, complexity, session_id present
|
||||
- [ ] Project context: architecture patterns, coding conventions, tech stack documented
|
||||
- [ ] Assets: organized by type (documentation, source_code, config, tests) with metadata
|
||||
- [ ] Dependencies: internal graph and external package usage documented
|
||||
- [ ] Conflict detection: risk level with specific risk factors and mitigation strategy
|
||||
- [ ] File relevance accuracy >80% (verified via multi-factor scoring)
|
||||
- [ ] No sensitive information (credentials, keys, tokens) exposed in package
|
||||
Before completion verify:
|
||||
- [ ] context-package.json in `.workflow/{session}/.process/`
|
||||
- [ ] Valid JSON with all required fields
|
||||
- [ ] Metadata complete (description, keywords, complexity)
|
||||
- [ ] Project context documented (patterns, conventions, tech stack)
|
||||
- [ ] Assets organized by type with metadata
|
||||
- [ ] Dependencies mapped (internal + external)
|
||||
- [ ] Conflict detection with risk level and mitigation
|
||||
- [ ] File relevance >80%
|
||||
- [ ] No sensitive data exposed
|
||||
|
||||
## Performance Optimization
|
||||
## Performance Limits
|
||||
|
||||
### Efficiency Guidelines
|
||||
|
||||
**Relevance Threshold**: Include only files with relevance score >0.5
|
||||
|
||||
**File Count Limits**:
|
||||
- Maximum 30 high-priority files (relevance >0.8)
|
||||
- Maximum 20 medium-priority files (relevance 0.5-0.8)
|
||||
- Total limit: 50 files per context package
|
||||
**File Counts**:
|
||||
- Max 30 high-priority (score >0.8)
|
||||
- Max 20 medium-priority (score 0.5-0.8)
|
||||
- Total limit: 50 files
|
||||
|
||||
**Size Filtering**:
|
||||
- Skip files >10MB (binary/generated files)
|
||||
- Flag files >1MB for manual review
|
||||
- Prioritize files <100KB for fast processing
|
||||
- Skip files >10MB
|
||||
- Flag files >1MB for review
|
||||
- Prioritize files <100KB
|
||||
|
||||
**Depth Control**:
|
||||
- Direct dependencies: Always include
|
||||
- Transitive dependencies: Limit to 2 levels
|
||||
- Optional dependencies: Include only if relevance >0.7
|
||||
- Transitive: Max 2 levels
|
||||
- Optional: Only if score >0.7
|
||||
|
||||
**Tool Preference**: ripgrep > find > manual search
|
||||
- Use `rg` for content search (fastest)
|
||||
- Use `find` for file discovery
|
||||
- Use Grep tool only when `rg` unavailable
|
||||
|
||||
### Search Strategy
|
||||
|
||||
**Execution Order** (for optimal performance):
|
||||
1. **Start broad**: Keyword-based discovery using `rg --files-with-matches`
|
||||
2. **Narrow**: Structural patterns (classes, interfaces, exports)
|
||||
3. **Expand**: Dependency analysis (import/require parsing)
|
||||
4. **Filter**: Relevance scoring (multi-factor weighted calculation)
|
||||
|
||||
## Tool Integration
|
||||
|
||||
### Native Search Tools
|
||||
```bash
|
||||
# ripgrep (primary)
|
||||
rg "pattern" -t ts -t js --files-with-matches
|
||||
rg "^export (class|interface)" -t ts -n
|
||||
rg "(import|require).*auth" --files-with-matches
|
||||
|
||||
# find (secondary)
|
||||
find . -name "*.ts" -type f ! -path "*/node_modules/*"
|
||||
find . -type d -name "*auth*"
|
||||
|
||||
# grep (fallback)
|
||||
grep -r "pattern" --include="*.ts" --files-with-matches
|
||||
```
|
||||
|
||||
### MCP Tools (External Research)
|
||||
```javascript
|
||||
// Exa Code Context: Get API examples and patterns
|
||||
mcp__exa__get_code_context_exa(
|
||||
query="React authentication hooks examples",
|
||||
tokensNum=5000
|
||||
)
|
||||
|
||||
// Exa Web Search: Research best practices
|
||||
mcp__exa__web_search_exa(
|
||||
query="TypeScript authentication patterns 2025",
|
||||
numResults=5
|
||||
)
|
||||
```
|
||||
|
||||
### Agent Capabilities
|
||||
```javascript
|
||||
// Use these tools for file operations
|
||||
Read(file_path) // Read file content
|
||||
Glob(pattern="**/*.ts") // Find files by pattern
|
||||
Grep(pattern="auth") // Search content
|
||||
Bash(command) // Execute shell commands
|
||||
```
|
||||
**Tool Priority**: Code-Index > ripgrep > find > grep
|
||||
|
||||
## Output Report
|
||||
|
||||
Upon completion, generate summary report:
|
||||
```
|
||||
✅ Context Gathering Complete
|
||||
|
||||
Task: {task_description}
|
||||
Keywords: {extracted_keywords}
|
||||
Complexity: {complexity_level}
|
||||
Task: {description}
|
||||
Keywords: {keywords}
|
||||
Complexity: {level}
|
||||
|
||||
Assets Collected:
|
||||
- Documentation: {doc_count} files
|
||||
- Source Code: {high_priority_count} high priority / {medium_priority_count} medium priority
|
||||
- Configuration: {config_count} files
|
||||
- Tests: {test_count} files
|
||||
Assets:
|
||||
- Documentation: {count}
|
||||
- Source Code: {high}/{medium} priority
|
||||
- Configuration: {count}
|
||||
- Tests: {count}
|
||||
|
||||
Dependencies:
|
||||
- Internal: {internal_count} relationships
|
||||
- External: {external_count} packages
|
||||
- Internal: {count}
|
||||
- External: {count}
|
||||
|
||||
Conflict Detection:
|
||||
- Risk Level: {risk_level}
|
||||
- Affected Modules: {affected_modules}
|
||||
- Mitigation: {mitigation_strategy}
|
||||
- Risk: {level}
|
||||
- Affected: {modules}
|
||||
- Mitigation: {strategy}
|
||||
|
||||
Output: .workflow/{session-id}/.process/context-package.json
|
||||
Output: .workflow/{session}/.process/context-package.json
|
||||
(Referenced in task JSONs via top-level `context_package_path` field)
|
||||
```
|
||||
|
||||
## Key Reminders
|
||||
|
||||
**NEVER:**
|
||||
- Skip Phase 0 foundation setup (project structure + documentation loading)
|
||||
- Include files without relevance scoring
|
||||
- Expose sensitive information (credentials, API keys, tokens)
|
||||
- Exceed file count limits (30 high + 20 medium = 50 total)
|
||||
- Include binary files or generated content
|
||||
**NEVER**:
|
||||
- Skip Phase 0 setup
|
||||
- Include files without scoring
|
||||
- Expose sensitive data (credentials, keys)
|
||||
- Exceed file limits (50 total)
|
||||
- Include binaries/generated files
|
||||
- Use ripgrep if code-index available
|
||||
|
||||
**ALWAYS:**
|
||||
- Execute get_modules_by_depth.sh before any other analysis
|
||||
- Load CLAUDE.md and README.md (unless already in memory)
|
||||
- Use multi-factor relevance scoring for file selection
|
||||
- Build dependency graphs (direct → transitive → optional)
|
||||
- Generate valid JSON output in correct location
|
||||
- Calculate conflict risk with specific mitigation strategies
|
||||
- Report completion with statistics summary
|
||||
**ALWAYS**:
|
||||
- Initialize code-index in Phase 0
|
||||
- Execute get_modules_by_depth.sh
|
||||
- Load CLAUDE.md/README.md (unless in memory)
|
||||
- Execute all 3 discovery tracks
|
||||
- Use code-index MCP as primary
|
||||
- Fallback to ripgrep only when needed
|
||||
- Use Exa for unfamiliar APIs
|
||||
- Apply multi-factor scoring
|
||||
- Build dependency graphs
|
||||
- Synthesize all 3 sources
|
||||
- Calculate conflict risk
|
||||
- Generate valid JSON output
|
||||
- Report completion with stats
|
||||
|
||||
### Windows Path Format Guidelines
|
||||
- **Quick Ref**: `C:\Users` → MCP: `C:\\Users` | Bash: `/c/Users` or `C:/Users`
|
||||
- **Context Package Paths**: Use project-relative paths (e.g., `src/auth/service.ts`, not absolute)
|
||||
- **Context Package**: Use project-relative paths (e.g., `src/auth/service.ts`)
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
name: artifacts
|
||||
description: Interactive clarification generating confirmed guidance specification
|
||||
argument-hint: "topic or challenge description [--count N]"
|
||||
allowed-tools: TodoWrite(*), Read(*), Write(*), AskUserQuestion(*), Glob(*)
|
||||
allowed-tools: TodoWrite(*), Read(*), Write(*), Glob(*)
|
||||
---
|
||||
|
||||
## Overview
|
||||
@@ -15,7 +15,7 @@ Five-phase workflow: Extract topic challenges → Select roles → Generate task
|
||||
|
||||
**Parameters**:
|
||||
- `topic` (required): Topic or challenge description (structured format recommended)
|
||||
- `--count N` (optional): Number of roles user WANTS to select (system will recommend N+2 options via AskUserQuestion for user to choose from, default: 3)
|
||||
- `--count N` (optional): Number of roles user WANTS to select (system will recommend N+2 options for user to choose from, default: 3)
|
||||
|
||||
## Task Tracking
|
||||
|
||||
@@ -33,29 +33,104 @@ Five-phase workflow: Extract topic challenges → Select roles → Generate task
|
||||
```json
|
||||
[
|
||||
{"content": "Initialize session (.workflow/.active-* check, parse --count parameter)", "status": "pending", "activeForm": "Initializing"},
|
||||
{"content": "Phase 1: Extract challenges, generate 2-4 task-specific questions", "status": "pending", "activeForm": "Phase 1 topic analysis"},
|
||||
{"content": "Phase 2: Recommend count+2 roles, MUST collect user selection via AskUserQuestion (multiSelect)", "status": "pending", "activeForm": "Phase 2 role selection"},
|
||||
{"content": "Phase 3: Generate 3-4 task-specific questions per role (max 4 per round)", "status": "pending", "activeForm": "Phase 3 role questions"},
|
||||
{"content": "Phase 4: Detect conflicts in Phase 3 answers, generate clarifications (max 4 per round)", "status": "pending", "activeForm": "Phase 4 conflict resolution"},
|
||||
{"content": "Phase 1: Extract challenges, output 2-4 task-specific questions, wait for user input", "status": "pending", "activeForm": "Phase 1 topic analysis"},
|
||||
{"content": "Phase 2: Recommend count+2 roles, output role selection, wait for user input", "status": "pending", "activeForm": "Phase 2 role selection"},
|
||||
{"content": "Phase 3: Generate 3-4 questions per role, output and wait for answers (max 10 per round)", "status": "pending", "activeForm": "Phase 3 role questions"},
|
||||
{"content": "Phase 4: Detect conflicts, output clarifications, wait for answers (max 10 per round)", "status": "pending", "activeForm": "Phase 4 conflict resolution"},
|
||||
{"content": "Phase 5: Transform Q&A to declarative statements, write guidance-specification.md", "status": "pending", "activeForm": "Phase 5 document generation"}
|
||||
]
|
||||
```
|
||||
|
||||
## User Interaction Protocol
|
||||
|
||||
### Question Output Format
|
||||
|
||||
All questions output as structured text (detailed format with descriptions):
|
||||
|
||||
```markdown
|
||||
【问题{N} - {短标签}】{问题文本}
|
||||
a) {选项标签}
|
||||
说明：{选项说明和影响}
|
||||
b) {选项标签}
|
||||
说明：{选项说明和影响}
|
||||
c) {选项标签}
|
||||
说明：{选项说明和影响}
|
||||
|
||||
请回答：{N}a 或 {N}b 或 {N}c
|
||||
```
|
||||
|
||||
**Multi-select format** (Phase 2 role selection):
|
||||
```markdown
|
||||
【角色选择】请选择 {count} 个角色参与头脑风暴分析
|
||||
|
||||
a) {role-name} ({中文名})
|
||||
推荐理由：{基于topic的相关性说明}
|
||||
b) {role-name} ({中文名})
|
||||
推荐理由：{基于topic的相关性说明}
|
||||
...
|
||||
|
||||
支持格式：
|
||||
- 分别选择：2a 2c 2d (选择第2题的a、c、d选项)
|
||||
- 合并语法：2acd (选择a、c、d)
|
||||
- 逗号分隔：2a,c,d
|
||||
|
||||
请输入选择：
|
||||
```
|
||||
|
||||
### Input Parsing Rules
|
||||
|
||||
**Supported formats** (intelligent parsing):
|
||||
|
||||
1. **Space-separated**: `1a 2b 3c` → Q1:a, Q2:b, Q3:c
|
||||
2. **Comma-separated**: `1a,2b,3c` → Q1:a, Q2:b, Q3:c
|
||||
3. **Multi-select combined**: `2abc` → Q2: options a,b,c
|
||||
4. **Multi-select spaces**: `2 a b c` → Q2: options a,b,c
|
||||
5. **Multi-select comma**: `2a,b,c` → Q2: options a,b,c
|
||||
6. **Natural language**: `问题1选a` → 1a (fallback parsing)
|
||||
|
||||
**Parsing algorithm**:
|
||||
- Extract question numbers and option letters
|
||||
- Validate question numbers match output
|
||||
- Validate option letters exist for each question
|
||||
- If ambiguous/invalid, output example format and request re-input
|
||||
|
||||
**Error handling** (lenient):
|
||||
- Recognize common variations automatically
|
||||
- If parsing fails, show example and wait for clarification
|
||||
- Support re-input without penalty
|
||||
|
||||
### Batching Strategy
|
||||
|
||||
**Batch limits**:
|
||||
- **Default**: Maximum 10 questions per round
|
||||
- **Phase 2 (role selection)**: Display all recommended roles at once (count+2 roles)
|
||||
- **Auto-split**: If questions > 10, split into multiple rounds with clear round indicators
|
||||
|
||||
**Round indicators**:
|
||||
```markdown
|
||||
===== 第 1 轮问题 (共2轮) =====
|
||||
【问题1 - ...】...
|
||||
【问题2 - ...】...
|
||||
...
|
||||
【问题10 - ...】...
|
||||
|
||||
请回答 (格式: 1a 2b ... 10c)：
|
||||
```
|
||||
|
||||
### Interaction Flow
|
||||
|
||||
**Standard flow**:
|
||||
1. Output questions in formatted text
|
||||
2. Output expected input format example
|
||||
3. Wait for user input
|
||||
4. Parse input with intelligent matching
|
||||
5. If parsing succeeds → Store answers and continue
|
||||
6. If parsing fails → Show error, example, and wait for re-input
|
||||
|
||||
**No question/option limits**: Text-based interaction removes previous 4-question and 4-option restrictions
|
||||
|
||||
## Execution Phases
|
||||
|
||||
### Phase 0: User Mode Check (First Step)
|
||||
|
||||
**Output to user**:
|
||||
```
|
||||
**⚠️ 请先启用 "CLAUDE accept edits on" 模式**
|
||||
|
||||
本命令需要多轮交互问答（5个阶段，约10-15个问题）
|
||||
|
||||
启用后回复继续。
|
||||
```
|
||||
|
||||
**Wait for user confirmation** before proceeding to Phase 1.
|
||||
|
||||
### Session Management
|
||||
- Check `.workflow/.active-*` markers first
|
||||
- Multiple sessions → Prompt selection | Single → Use it | None → Create `WFS-[topic-slug]`
|
||||
@@ -69,20 +144,42 @@ Five-phase workflow: Extract topic challenges → Select roles → Generate task
|
||||
**Steps**:
|
||||
1. **Deep topic analysis**: Extract technical entities, identify core challenges (what makes this hard?), constraints (timeline/budget/compliance), success metrics (what defines done?)
|
||||
2. **Generate 2-4 probing questions** targeting root challenges, trade-off priorities, and risk tolerance (NOT surface-level "Project Type")
|
||||
3. **User interaction via AskUserQuestion tool**: Present 2-4 task-specific questions (multiSelect: false for single-choice questions)
|
||||
4. **Storage**: Store answers to `session.intent_context` with `{extracted_keywords, identified_challenges, user_answers}`
|
||||
3. **User interaction**: Output questions using text format (see User Interaction Protocol), wait for user input
|
||||
4. **Parse user answers**: Use intelligent parsing to extract answers from user input (support multiple formats)
|
||||
5. **Storage**: Store answers to `session.intent_context` with `{extracted_keywords, identified_challenges, user_answers}`
|
||||
|
||||
**Example (Task-Specific)**:
|
||||
Topic: "Build real-time collaboration platform SCOPE: 100 users"
|
||||
→ Extract: ["real-time", "collaboration", "100 users"]
|
||||
→ Challenges: ["data sync", "scalability", "low latency"]
|
||||
→ Generate: "PRIMARY technical challenge?" → [Real-time data sync / Scalability to 100+ users / Conflict resolution]
|
||||
**Example Output**:
|
||||
```markdown
|
||||
===== Phase 1: 项目意图分析 =====
|
||||
|
||||
【问题1 - 核心挑战】实时协作平台的主要技术挑战？
|
||||
a) 实时数据同步
|
||||
说明：100+用户同时在线，状态同步复杂度高
|
||||
b) 可扩展性架构
|
||||
说明：用户规模增长时的系统扩展能力
|
||||
c) 冲突解决机制
|
||||
说明：多用户同时编辑的冲突处理策略
|
||||
|
||||
【问题2 - 优先级】MVP阶段最关注的指标？
|
||||
a) 功能完整性
|
||||
说明：实现所有核心功能
|
||||
b) 用户体验
|
||||
说明：流畅的交互体验和响应速度
|
||||
c) 系统稳定性
|
||||
说明：高可用性和数据一致性
|
||||
|
||||
请回答 (格式: 1a 2b)：
|
||||
```
|
||||
|
||||
**User input examples**:
|
||||
- `1a 2c` → Q1:a, Q2:c
|
||||
- `1a,2c` → Q1:a, Q2:c
|
||||
|
||||
**⚠️ CRITICAL**: Questions MUST reference topic keywords. Generic "Project type?" violates dynamic generation.
|
||||
|
||||
### Phase 2: Role Selection
|
||||
|
||||
**⚠️ CRITICAL**: This phase MUST use AskUserQuestion tool for user selection. NEVER auto-select roles without user interaction.
|
||||
**⚠️ CRITICAL**: User MUST interact to select roles. NEVER auto-select without user confirmation.
|
||||
|
||||
**Available Roles**:
|
||||
- data-architect (数据架构师)
|
||||
@@ -96,35 +193,49 @@ Topic: "Build real-time collaboration platform SCOPE: 100 users"
|
||||
- ux-expert (UX 专家)
|
||||
|
||||
**Steps**:
|
||||
1. **Intelligent role recommendation** (AI analysis, NO user interaction yet):
|
||||
1. **Intelligent role recommendation** (AI analysis):
|
||||
- Analyze Phase 1 extracted keywords and challenges
|
||||
- Use AI reasoning to determine most relevant roles for the specific topic
|
||||
- Recommend count+2 roles (e.g., if user wants 3 roles, recommend 5 options)
|
||||
- Provide clear rationale for each recommended role based on topic context
|
||||
|
||||
2. **User selection** (MANDATORY AskUserQuestion interaction):
|
||||
- **Tool**: `AskUserQuestion` with `multiSelect: true`
|
||||
- **Question format**: "请选择 {count} 个角色参与头脑风暴分析（可多选）："
|
||||
- **Options**: Each recommended role with label (role name) and description (relevance rationale)
|
||||
- **⚠️ Option Limit**: Maximum 4 options per AskUserQuestion call. If count+2 > 4, split into multiple rounds
|
||||
- **User interaction**: Allow user to select multiple roles (typically count roles, but flexible)
|
||||
2. **User selection** (text interaction):
|
||||
- Output all recommended roles at once (no batching needed for count+2 roles)
|
||||
- Display roles with labels and relevance rationale
|
||||
- Wait for user input in multi-select format
|
||||
- Parse user input (support multiple formats)
|
||||
- **Storage**: Store selections to `session.selected_roles`
|
||||
|
||||
**AskUserQuestion Syntax**:
|
||||
```javascript
|
||||
AskUserQuestion({
|
||||
questions: [{
|
||||
question: "请选择 {count} 个角色参与头脑风暴分析（可多选）：",
|
||||
header: "角色选择",
|
||||
multiSelect: true, // Enable multiple selection
|
||||
options: [
|
||||
{label: "{role-name} ({中文名})", description: "{基于topic的相关性说明}"}
|
||||
// count+2 recommended roles
|
||||
]
|
||||
}]
|
||||
});
|
||||
**Example Output**:
|
||||
```markdown
|
||||
===== Phase 2: 角色选择 =====
|
||||
|
||||
【角色选择】请选择 3 个角色参与头脑风暴分析
|
||||
|
||||
a) system-architect (系统架构师)
|
||||
推荐理由：实时同步架构设计和技术选型的核心角色
|
||||
b) ui-designer (UI设计师)
|
||||
推荐理由：协作界面用户体验和实时状态展示
|
||||
c) product-manager (产品经理)
|
||||
推荐理由：功能优先级和MVP范围决策
|
||||
d) data-architect (数据架构师)
|
||||
推荐理由：数据同步模型和存储方案设计
|
||||
e) ux-expert (UX专家)
|
||||
推荐理由：多用户协作交互流程优化
|
||||
|
||||
支持格式：
|
||||
- 分别选择：2a 2c 2d (选择a、c、d)
|
||||
- 合并语法：2acd (选择a、c、d)
|
||||
- 逗号分隔：2a,c,d (选择a、c、d)
|
||||
|
||||
请输入选择：
|
||||
```
|
||||
|
||||
**User input examples**:
|
||||
- `2acd` → Roles: a, c, d (system-architect, product-manager, data-architect)
|
||||
- `2a 2c 2d` → Same result
|
||||
- `2a,c,d` → Same result
|
||||
|
||||
**Role Recommendation Rules**:
|
||||
- NO hardcoded keyword-to-role mappings
|
||||
- Use intelligent analysis of topic, challenges, and requirements
|
||||
@@ -149,39 +260,28 @@ FOR each selected role:
|
||||
Q: "How resolve conflicts when 2 users edit simultaneously?" (explores edge case)
|
||||
Options: [Event Sourcing/Centralized/CRDT] (concrete, explain trade-offs for THIS use case)
|
||||
|
||||
3. Ask questions via AskUserQuestion tool (max 4 questions per call):
|
||||
- Tool: AskUserQuestion with questions array (1-4 questions)
|
||||
- Each question: multiSelect: false (single-choice)
|
||||
- If role has 3-4 questions: Single AskUserQuestion call with multiple questions
|
||||
3. Output questions in text format per role:
|
||||
- Display all questions for current role (3-4 questions, no 10-question limit)
|
||||
- Questions in Chinese (用中文提问)
|
||||
- Wait for user input
|
||||
- Parse answers using intelligent parsing
|
||||
- Store answers to session.role_decisions[role]
|
||||
```
|
||||
|
||||
**AskUserQuestion Tool Usage**:
|
||||
- **Batching**: Maximum 4 questions per AskUserQuestion call
|
||||
- **Mode**: `multiSelect: false` for each question (single-choice answers)
|
||||
- **Language**: Questions MUST be asked in Chinese (用中文提问)
|
||||
- **Format**: Each question includes header (short label), question text, and 2-4 options with descriptions
|
||||
**Batching Strategy**:
|
||||
- Each role outputs all its questions at once (typically 3-4 questions)
|
||||
- No need to split per role (within 10-question batch limit)
|
||||
- Multiple roles processed sequentially (one role at a time for clarity)
|
||||
|
||||
**Question Batching Rules**:
|
||||
- ✅ Each role generates 3-4 questions
|
||||
- ✅ AskUserQuestion supports maximum 4 questions per call
|
||||
- ✅ Single round per role (all questions asked together)
|
||||
- ✅ Questions MUST be asked in Chinese (用中文提问) for better user understanding
|
||||
- ✅ Questions MUST reference Phase 1 keywords (e.g., "real-time", "100 users")
|
||||
- ✅ Options MUST be concrete approaches, explain relevance to topic
|
||||
- ❌ NEVER generic "Architecture style?" without task context
|
||||
**Output Format**: Follow standard format from "User Interaction Protocol" section (single-choice question format)
|
||||
|
||||
**Examples by Role** (for "real-time collaboration platform"):
|
||||
- **system-architect** (4 questions in one round):
|
||||
1. "100+ 用户实时状态同步方案?" → [Event Sourcing/集中式状态/CRDT]
|
||||
2. "两个用户同时编辑冲突如何解决?" → [自动合并/手动解决/版本控制]
|
||||
3. "低延迟通信协议选择?" → [WebSocket/SSE/轮询]
|
||||
4. "系统扩展性架构方案?" → [微服务/单体+缓存/Serverless]
|
||||
**Example Topic-Specific Questions** (system-architect role for "real-time collaboration platform"):
|
||||
- "100+ 用户实时状态同步方案?" → Options: Event Sourcing / 集中式状态管理 / CRDT
|
||||
- "两个用户同时编辑冲突如何解决?" → Options: 自动合并 / 手动解决 / 版本控制
|
||||
- "低延迟通信协议选择?" → Options: WebSocket / SSE / 轮询
|
||||
- "系统扩展性架构方案?" → Options: 微服务 / 单体+缓存 / Serverless
|
||||
|
||||
- **ui-designer** (3 questions in one round):
|
||||
1. "如何展示实时协作状态?" → [实时光标/活动流/最小化指示器]
|
||||
2. "冲突时的用户界面反馈?" → [即时警告/合并界面/回滚选项]
|
||||
3. "多用户在线状态展示?" → [头像列表/活动面板/状态栏]
|
||||
**Quality Requirements**: See "Question Generation Guidelines" section for detailed rules
|
||||
|
||||
### Phase 4: Cross-Role Clarification (Conflict Detection)
|
||||
|
||||
@@ -197,33 +297,33 @@ FOR each selected role:
|
||||
2. FOR each detected conflict:
|
||||
Generate clarification questions referencing SPECIFIC Phase 3 choices
|
||||
|
||||
3. Ask via AskUserQuestion tool in batches (max 4 questions per call):
|
||||
- Tool: AskUserQuestion with questions array (1-4 questions)
|
||||
- Each question: multiSelect: false (single-choice)
|
||||
- If conflicts ≤ 4: Single AskUserQuestion call
|
||||
- If conflicts > 4: Multiple AskUserQuestion calls (max 4 questions each)
|
||||
3. Output clarification questions in text format:
|
||||
- Batch conflicts into rounds (max 10 questions per round)
|
||||
- Display questions with context from Phase 3 answers
|
||||
- Questions in Chinese (用中文提问)
|
||||
- Wait for user input
|
||||
- Parse answers using intelligent parsing
|
||||
- Store answers to session.cross_role_decisions
|
||||
|
||||
4. If NO conflicts: Skip Phase 4 (inform user)
|
||||
4. If NO conflicts: Skip Phase 4 (inform user: "未检测到跨角色冲突，跳过Phase 4")
|
||||
```
|
||||
|
||||
**AskUserQuestion Tool Usage**:
|
||||
- **Batching**: Maximum 4 questions per AskUserQuestion call
|
||||
- **Mode**: `multiSelect: false` for each question (single-choice answers)
|
||||
- **Language**: Questions in Chinese (用中文提问)
|
||||
- **Multiple rounds**: If conflicts > 4, call AskUserQuestion multiple times sequentially
|
||||
**Batching Strategy**:
|
||||
- Maximum 10 clarification questions per round
|
||||
- If conflicts > 10, split into multiple rounds
|
||||
- Prioritize most critical conflicts first
|
||||
|
||||
**Batching Rules**:
|
||||
- ✅ Maximum 4 clarification questions per AskUserQuestion call
|
||||
- ✅ Multiple rounds if more than 4 conflicts detected
|
||||
- ✅ Prioritize most critical conflicts first
|
||||
- ✅ Questions in Chinese (用中文提问)
|
||||
**Output Format**: Follow standard format from "User Interaction Protocol" section (single-choice question format with background context)
|
||||
|
||||
**Example Conflict**:
|
||||
- Detect: system-architect "CRDT sync" (conflict-free) + ui-designer "Rollback on conflict" (expects conflicts)
|
||||
- Generate: "CRDT 与 UI 回滚期望冲突,如何解决?" → [CRDT 自动合并/显示合并界面/切换到 OT]
|
||||
**Example Conflict Detection** (from Phase 3 answers):
|
||||
- **Architecture Conflict**: "CRDT 与 UI 回滚期望冲突，如何解决?"
|
||||
- Background: system-architect chose CRDT, ui-designer expects rollback UI
|
||||
- Options: 采用 CRDT / 显示合并界面 / 切换到 OT
|
||||
- **Integration Gap**: "实时光标功能缺少身份认证方案"
|
||||
- Background: ui-designer chose live cursors, no auth defined
|
||||
- Options: OAuth 2.0 / JWT Token / Session-based
|
||||
|
||||
**⚠️ CRITICAL**: NEVER use static "Cross-Role Matrix". ALWAYS analyze actual Phase 3 answers.
|
||||
**Quality Requirements**: See "Question Generation Guidelines" section for conflict-specific rules
|
||||
|
||||
### Phase 5: Generate Guidance Specification
|
||||
|
||||
@@ -288,35 +388,6 @@ FOR each selected role:
|
||||
| D-003+ | [Role] | [Q] | [A] | 3 | [Why] |
|
||||
```
|
||||
|
||||
## AskUserQuestion Tool Reference
|
||||
|
||||
### Syntax Structure
|
||||
```javascript
|
||||
AskUserQuestion({
|
||||
questions: [
|
||||
{
|
||||
question: "{动态生成的问题文本}",
|
||||
header: "{短标签,最多12字符}",
|
||||
multiSelect: false, // Phase 1,3,4: false | Phase 2: true
|
||||
options: [
|
||||
{label: "{选项标签}", description: "{选项说明}"},
|
||||
// 2-4 options per question
|
||||
]
|
||||
}
|
||||
// Maximum 4 questions per call
|
||||
]
|
||||
});
|
||||
```
|
||||
|
||||
### Usage Rules
|
||||
- **Maximum**: 4 questions per AskUserQuestion call
|
||||
- **Language**: Questions in Chinese (用中文提问)
|
||||
- **multiSelect**:
|
||||
- `false` (Phase 1, 3, 4): Single-choice
|
||||
- `true` (Phase 2): Multiple role selection
|
||||
- **Options**: 2-4 options with label + description
|
||||
- **Multiple rounds**: Call tool multiple times if > 4 questions needed
|
||||
|
||||
## Question Generation Guidelines
|
||||
|
||||
### Core Principle: Developer-Facing Questions with User Context
|
||||
@@ -329,49 +400,50 @@ AskUserQuestion({
|
||||
3. **Phase 3**: 业务需求 + 技术选型（需求驱动的技术决策）
|
||||
4. **Phase 4**: 技术冲突的业务权衡（帮助开发者理解影响）
|
||||
|
||||
### Question Quality Rules
|
||||
### Universal Quality Rules
|
||||
|
||||
**Balanced Question Pattern** (需求 → 技术):
|
||||
```
|
||||
问题结构：[用户场景/业务需求] + [技术关注点]
|
||||
选项格式：[技术方案简称] + [业务影响说明]
|
||||
```
|
||||
|
||||
**Phase 1 Focus**:
|
||||
- 用户使用场景（谁用？怎么用？多频繁？）
|
||||
- 业务约束（预算、时间、团队、合规）
|
||||
- 成功标准（性能指标、用户体验目标）
|
||||
- 优先级排序（MVP vs 长期规划）
|
||||
|
||||
**Phase 3 Focus**:
|
||||
- 业务需求驱动的技术问题
|
||||
- 技术选项带业务影响说明
|
||||
- 包含量化指标（并发数、延迟、可用性）
|
||||
|
||||
**Phase 4 Focus**:
|
||||
- 技术冲突的业务权衡
|
||||
- 帮助开发者理解不同选择的影响
|
||||
|
||||
**Question Structure**:
|
||||
**Question Structure** (all phases):
|
||||
```
|
||||
[业务场景/需求前提] + [技术关注点]
|
||||
```
|
||||
|
||||
**Option Structure**:
|
||||
**Option Structure** (all phases):
|
||||
```
|
||||
标签：[技术方案简称] + (业务特征)
|
||||
说明：[业务影响] + [技术权衡]
|
||||
```
|
||||
|
||||
**MUST Include**:
|
||||
- 业务场景作为问题前提
|
||||
- 技术选项的业务影响说明
|
||||
- 量化指标和约束条件
|
||||
**MUST Include** (all phases):
|
||||
- ✅ All questions in Chinese (用中文提问)
|
||||
- ✅ 业务场景作为问题前提
|
||||
- ✅ 技术选项的业务影响说明
|
||||
- ✅ 量化指标和约束条件
|
||||
|
||||
**MUST Avoid**:
|
||||
- 纯技术选型无业务上下文
|
||||
- 过度抽象的用户体验问题
|
||||
- 脱离话题的通用架构问题
|
||||
**MUST Avoid** (all phases):
|
||||
- ❌ 纯技术选型无业务上下文
|
||||
- ❌ 过度抽象的用户体验问题
|
||||
- ❌ 脱离话题的通用架构问题
|
||||
|
||||
### Phase-Specific Requirements
|
||||
|
||||
**Phase 1 Requirements**:
|
||||
- Questions MUST reference topic keywords (NOT generic "Project type?")
|
||||
- Focus: 用户使用场景（谁用？怎么用？多频繁？）、业务约束（预算、时间、团队、合规）
|
||||
- Success metrics: 性能指标、用户体验目标
|
||||
- Priority ranking: MVP vs 长期规划
|
||||
|
||||
**Phase 3 Requirements**:
|
||||
- Questions MUST reference Phase 1 keywords (e.g., "real-time", "100 users")
|
||||
- Options MUST be concrete approaches with relevance to topic
|
||||
- Each option includes trade-offs specific to this use case
|
||||
- Include 业务需求驱动的技术问题、量化指标（并发数、延迟、可用性）
|
||||
|
||||
**Phase 4 Requirements**:
|
||||
- Questions MUST reference SPECIFIC Phase 3 choices in background context
|
||||
- Options address the detected conflict directly
|
||||
- Each option explains impact on both conflicting roles
|
||||
- NEVER use static "Cross-Role Matrix" - ALWAYS analyze actual Phase 3 answers
|
||||
- Focus: 技术冲突的业务权衡、帮助开发者理解不同选择的影响
|
||||
|
||||
## Validation Checklist
|
||||
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
name: synthesis
|
||||
description: Clarify and refine role analyses through intelligent Q&A and targeted updates
|
||||
argument-hint: "[optional: --session session-id]"
|
||||
allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*), Edit(*), Glob(*), AskUserQuestion(*)
|
||||
allowed-tools: Task(conceptual-planning-agent), TodoWrite(*), Read(*), Write(*), Edit(*), Glob(*)
|
||||
---
|
||||
|
||||
## Overview
|
||||
@@ -137,54 +137,67 @@ Return JSON array:
|
||||
|
||||
### Phase 4: Main Flow User Interaction
|
||||
|
||||
**Main flow handles all user interaction**:
|
||||
**Main flow handles all user interaction via text output**:
|
||||
|
||||
**⚠️ CRITICAL**: ALL AskUserQuestion calls MUST use Chinese (所有问题必须用中文) for better user understanding
|
||||
**⚠️ CRITICAL**: ALL questions MUST use Chinese (所有问题必须用中文) for better user understanding
|
||||
|
||||
1. **Present Enhancement Options**:
|
||||
```
|
||||
AskUserQuestion(
|
||||
questions=[{
|
||||
"question": "Which enhancements would you like to apply?",
|
||||
"header": "Enhancements",
|
||||
"multiSelect": true,
|
||||
"options": [
|
||||
{"label": "EP-001: ...", "description": "... (affects: role1, role2)"},
|
||||
{"label": "EP-002: ...", "description": "..."},
|
||||
...
|
||||
]
|
||||
}]
|
||||
)
|
||||
1. **Present Enhancement Options** (multi-select):
|
||||
```markdown
|
||||
===== Enhancement 选择 =====
|
||||
|
||||
请选择要应用的改进建议（可多选）：
|
||||
|
||||
a) EP-001: API Contract Specification
|
||||
影响角色：system-architect, api-designer
|
||||
说明：添加详细的请求/响应 schema 定义
|
||||
|
||||
b) EP-002: User Intent Validation
|
||||
影响角色：product-manager, ux-expert
|
||||
说明：明确用户需求优先级和验收标准
|
||||
|
||||
c) EP-003: Error Handling Strategy
|
||||
影响角色：system-architect
|
||||
说明：统一异常处理和降级方案
|
||||
|
||||
支持格式：1abc 或 1a 1b 1c 或 1a,b,c
|
||||
请输入选择（可跳过输入 skip）：
|
||||
```
|
||||
|
||||
2. **Generate Clarification Questions** (based on analysis agent output):
|
||||
- ✅ **ALL questions MUST be in Chinese (所有问题必须用中文)**
|
||||
- ✅ **ALL questions in Chinese (所有问题必须用中文)**
|
||||
- Use 9-category taxonomy scan results
|
||||
- Create max 5 prioritized questions
|
||||
- Prioritize most critical questions (no hard limit)
|
||||
- Each with 2-4 options + descriptions
|
||||
|
||||
3. **Interactive Clarification Loop**:
|
||||
```
|
||||
# Present ONE question at a time
|
||||
FOR question in clarification_questions (max 5):
|
||||
AskUserQuestion(
|
||||
questions=[{
|
||||
"question": "Question {N}/5: {text}",
|
||||
"header": "Clarification",
|
||||
"multiSelect": false,
|
||||
"options": [
|
||||
{"label": "Option A", "description": "..."},
|
||||
{"label": "Option B", "description": "..."},
|
||||
...
|
||||
]
|
||||
}]
|
||||
)
|
||||
# Record answer
|
||||
# Continue to next question
|
||||
3. **Interactive Clarification Loop** (max 10 questions per round):
|
||||
```markdown
|
||||
===== Clarification 问题 (第 1/2 轮) =====
|
||||
|
||||
【问题1 - 用户意图】MVP 阶段的核心目标是什么？
|
||||
a) 快速验证市场需求
|
||||
说明：最小功能集，快速上线获取反馈
|
||||
b) 建立技术壁垒
|
||||
说明：完善架构，为长期发展打基础
|
||||
c) 实现功能完整性
|
||||
说明：覆盖所有规划功能，延迟上线
|
||||
|
||||
【问题2 - 架构决策】技术栈选择的优先考虑因素？
|
||||
a) 团队熟悉度
|
||||
说明：使用现有技术栈，降低学习成本
|
||||
b) 技术先进性
|
||||
说明：采用新技术，提升竞争力
|
||||
c) 生态成熟度
|
||||
说明：选择成熟方案，保证稳定性
|
||||
|
||||
...（最多10个问题）
|
||||
|
||||
请回答 (格式: 1a 2b 3c...)：
|
||||
```
|
||||
|
||||
Wait for user input → Parse all answers in batch → Continue to next round if needed
|
||||
|
||||
4. **Build Update Plan**:
|
||||
```
|
||||
```
|
||||
update_plan = {
|
||||
"role1": {
|
||||
"enhancements": [EP-001, EP-003],
|
||||
|
||||
@@ -207,48 +207,85 @@ Task(subagent_type="cli-execution-agent", prompt=`
|
||||
8. Return execution log path
|
||||
```
|
||||
|
||||
### Phase 3: User Confirmation via AskUserQuestion
|
||||
### Phase 3: User Confirmation via Text Interaction
|
||||
|
||||
**Command parses agent JSON output and presents conflicts to user**:
|
||||
**Command parses agent JSON output and presents conflicts to user via text**:
|
||||
|
||||
```javascript
|
||||
// 1. Parse agent JSON output
|
||||
const conflictData = JSON.parse(agentOutput);
|
||||
const conflicts = conflictData.conflicts.slice(0, 4); // Max 4 (tool limit)
|
||||
const conflicts = conflictData.conflicts; // No 4-conflict limit
|
||||
|
||||
// 2. Build AskUserQuestion with all conflicts
|
||||
const questions = conflicts.map((conflict, idx) => ({
|
||||
question: `${conflict.id}: ${conflict.brief} - 请选择解决方案`,
|
||||
header: `冲突${idx + 1}`,
|
||||
multiSelect: false,
|
||||
options: [
|
||||
...conflict.strategies.map(s => ({
|
||||
label: s.name,
|
||||
description: `${s.approach} | 复杂度: ${s.complexity} | 风险: ${s.risk} | 工作量: ${s.effort}`
|
||||
})),
|
||||
{
|
||||
label: "跳过此冲突",
|
||||
description: "稍后手动处理，不应用任何修改"
|
||||
}
|
||||
]
|
||||
}));
|
||||
// 2. Format conflicts as text output (max 10 per round)
|
||||
const batchSize = 10;
|
||||
const batches = chunkArray(conflicts, batchSize);
|
||||
|
||||
// 3. Call AskUserQuestion
|
||||
AskUserQuestion({questions});
|
||||
for (const [batchIdx, batch] of batches.entries()) {
|
||||
const totalBatches = batches.length;
|
||||
|
||||
// 4. Parse user selections
|
||||
const selectedStrategies = parseUserAnswers(answers, conflicts);
|
||||
// Output batch header
|
||||
console.log(`===== 冲突解决 (第 ${batchIdx + 1}/${totalBatches} 轮) =====\n`);
|
||||
|
||||
// Output each conflict in batch
|
||||
batch.forEach((conflict, idx) => {
|
||||
const questionNum = batchIdx * batchSize + idx + 1;
|
||||
console.log(`【问题${questionNum} - ${conflict.category}】${conflict.id}: ${conflict.brief}`);
|
||||
|
||||
conflict.strategies.forEach((strategy, sIdx) => {
|
||||
const optionLetter = String.fromCharCode(97 + sIdx); // a, b, c, ...
|
||||
console.log(`${optionLetter}) ${strategy.name}`);
|
||||
console.log(` 说明：${strategy.approach}`);
|
||||
console.log(` 复杂度: ${strategy.complexity} | 风险: ${strategy.risk} | 工作量: ${strategy.effort}`);
|
||||
});
|
||||
|
||||
// Add skip option
|
||||
const skipLetter = String.fromCharCode(97 + conflict.strategies.length);
|
||||
console.log(`${skipLetter}) 跳过此冲突`);
|
||||
console.log(` 说明：稍后手动处理，不应用任何修改\n`);
|
||||
});
|
||||
|
||||
console.log(`请回答 (格式: 1a 2b 3c...)：`);
|
||||
|
||||
// Wait for user input
|
||||
const userInput = await readUserInput();
|
||||
|
||||
// Parse answers
|
||||
const answers = parseUserAnswers(userInput, batch);
|
||||
}
|
||||
|
||||
// 3. Build selected strategies
|
||||
const selectedStrategies = answers.filter(a => !a.isSkip).map(a => a.strategy);
|
||||
```
|
||||
|
||||
**User Selection Examples**:
|
||||
```
|
||||
Question: "CON-001: 现有认证系统与计划不兼容 - 请选择解决方案"
|
||||
Options:
|
||||
- "渐进式迁移" | 复杂度: Medium | 风险: Low | 工作量: 3-5天
|
||||
- "完全重写" | 复杂度: High | 风险: Medium | 工作量: 7-10天
|
||||
- "跳过此冲突"
|
||||
**Text Output Example**:
|
||||
```markdown
|
||||
===== 冲突解决 (第 1/1 轮) =====
|
||||
|
||||
【问题1 - 认证系统】CON-001: 现有认证系统与计划不兼容
|
||||
a) 渐进式迁移
|
||||
说明：保留现有系统，逐步迁移到新方案
|
||||
复杂度: Medium | 风险: Low | 工作量: 3-5天
|
||||
b) 完全重写
|
||||
说明：废弃旧系统，从零实现新认证
|
||||
复杂度: High | 风险: Medium | 工作量: 7-10天
|
||||
c) 跳过此冲突
|
||||
说明：稍后手动处理，不应用任何修改
|
||||
|
||||
【问题2 - 数据库】CON-002: 数据库 schema 冲突
|
||||
a) 添加迁移脚本
|
||||
说明：创建数据库迁移脚本处理 schema 变更
|
||||
复杂度: Low | 风险: Low | 工作量: 1-2天
|
||||
b) 跳过此冲突
|
||||
说明：稍后手动处理，不应用任何修改
|
||||
|
||||
请回答 (格式: 1a 2b)：
|
||||
```
|
||||
|
||||
**User Input Examples**:
|
||||
- `1a 2a` → Conflict 1: 渐进式迁移, Conflict 2: 添加迁移脚本
|
||||
- `1b 2b` → Conflict 1: 完全重写, Conflict 2: 跳过
|
||||
- `1c 2c` → Both skipped
|
||||
|
||||
### Phase 4: Apply Modifications
|
||||
|
||||
```javascript
|
||||
@@ -290,7 +327,7 @@ return {
|
||||
**Validation**:
|
||||
```
|
||||
✓ Agent returns valid JSON structure
|
||||
✓ AskUserQuestion displays all conflicts (max 4)
|
||||
✓ Text output displays all conflicts (max 10 per round)
|
||||
✓ User selections captured correctly
|
||||
✓ Edit tool successfully applies modifications
|
||||
✓ guidance-specification.md updated
|
||||
@@ -310,7 +347,7 @@ return {
|
||||
### Key Requirements
|
||||
| Requirement | Details |
|
||||
|------------|---------|
|
||||
| **Conflict limit** | Max 4 conflicts (AskUserQuestion tool limit) |
|
||||
| **Conflict batching** | Max 10 conflicts per round (no total limit) |
|
||||
| **Strategy count** | 2-4 strategies per conflict |
|
||||
| **Modifications** | Each strategy includes file paths, old_content, new_content |
|
||||
| **User-facing text** | Chinese (brief, strategy names, pros/cons) |
|
||||
@@ -338,7 +375,7 @@ return {
|
||||
```
|
||||
If Edit tool fails mid-application:
|
||||
1. Log all successfully applied modifications
|
||||
2. Offer rollback option via AskUserQuestion
|
||||
2. Output rollback option via text interaction
|
||||
3. If rollback selected: restore files from git or backups
|
||||
4. If continue: mark partial resolution in context-package.json
|
||||
```
|
||||
@@ -359,15 +396,15 @@ If Edit tool fails mid-application:
|
||||
- NO report file generation
|
||||
|
||||
**User Interaction**:
|
||||
- AskUserQuestion for strategy selection (max 4 conflicts)
|
||||
- Text-based strategy selection (max 10 conflicts per round)
|
||||
- Each conflict: 2-4 strategy options + "跳过" option
|
||||
|
||||
### Success Criteria
|
||||
```
|
||||
✓ CLI analysis returns valid JSON structure
|
||||
✓ Max 4 conflicts presented (tool limit)
|
||||
✓ Conflicts presented in batches (max 10 per round)
|
||||
✓ Min 2 strategies per conflict with modifications
|
||||
✓ AskUserQuestion displays all conflicts correctly
|
||||
✓ Text output displays all conflicts correctly
|
||||
✓ User selections captured and processed
|
||||
✓ Edit tool applies modifications successfully
|
||||
✓ guidance-specification.md updated with resolved conflicts
|
||||
|
||||
@@ -49,6 +49,7 @@ Autonomous task JSON and IMPL_PLAN.md generation using action-planning-agent wit
|
||||
"synthesis_output": {"path": "...", "exists": true},
|
||||
"conflict_resolution": {"path": "...", "exists": true} // if conflict_risk >= medium
|
||||
},
|
||||
"context_package_path": ".workflow/{session-id}/.process/context-package.json",
|
||||
"context_package": {
|
||||
// If in memory: use cached content
|
||||
// Else: Load from .workflow/{session-id}/.process/context-package.json
|
||||
@@ -336,9 +337,11 @@ const agentContext = {
|
||||
? memory.get("workflow-session.json")
|
||||
: Read(.workflow/WFS-[id]/workflow-session.json),
|
||||
|
||||
context_package_path: ".workflow/WFS-[id]/.process/context-package.json",
|
||||
|
||||
context_package: memory.has("context-package.json")
|
||||
? memory.get("context-package.json")
|
||||
: Read(.workflow/WFS-[id]/.process/context-package.json),
|
||||
: Read(".workflow/WFS-[id]/.process/context-package.json"),
|
||||
|
||||
// Extract brainstorm artifacts from context package
|
||||
brainstorm_artifacts: extractBrainstormArtifacts(context_package),
|
||||
|
||||
@@ -134,6 +134,7 @@ For each feature, generate task(s) with ID format:
|
||||
"id": "IMPL-N", // Task identifier
|
||||
"title": "Feature description with TDD", // Human-readable title
|
||||
"status": "pending", // pending | in_progress | completed | container
|
||||
"context_package_path": ".workflow/{session-id}/.process/context-package.json", // Path to smart context package
|
||||
"meta": {
|
||||
"type": "feature", // Task type
|
||||
"agent": "@code-developer", // Assigned agent
|
||||
@@ -259,6 +260,7 @@ identifier: WFS-{session-id}
|
||||
source: "User requirements" | "File: path"
|
||||
conflict_resolution: .workflow/{session-id}/.process/CONFLICT_RESOLUTION.md # if exists
|
||||
context_package: .workflow/{session-id}/.process/context-package.json
|
||||
context_package_path: .workflow/{session-id}/.process/context-package.json
|
||||
test_context: .workflow/{session-id}/.process/test-context-package.json # if exists
|
||||
workflow_type: "tdd"
|
||||
verification_history:
|
||||
@@ -411,6 +413,7 @@ Update workflow-session.json with TDD metadata:
|
||||
├── CONFLICT_RESOLUTION.md # Conflict resolution strategies (if conflict_risk ≥ medium)
|
||||
├── test-context-package.json # Test coverage analysis
|
||||
├── context-package.json # Input from context-gather
|
||||
├── context_package_path # Path to smart context package
|
||||
└── green-fix-iteration-*.md # Fix logs from Green phase test-fix cycles
|
||||
```
|
||||
|
||||
|
||||
@@ -173,6 +173,7 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
|
||||
"id": "IMPL-N[.M]",
|
||||
"title": "Descriptive task name",
|
||||
"status": "pending|active|completed|blocked|container",
|
||||
"context_package_path": ".workflow/WFS-[session]/.process/context-package.json",
|
||||
"meta": {
|
||||
"type": "feature|bugfix|refactor|test-gen|test-fix|docs",
|
||||
"agent": "@code-developer|@test-fix-agent|@universal-executor",
|
||||
@@ -193,11 +194,6 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
|
||||
"priority": "highest",
|
||||
"usage": "Role-specific requirements, design specs, enhanced by synthesis. Paths loaded dynamically from context-package.json (supports multiple files per role: analysis.md, analysis-01.md, analysis-api.md, etc.). Common roles: product-manager, system-architect, ui-designer, data-architect, ux-expert."
|
||||
},
|
||||
{
|
||||
"path": ".workflow/WFS-[session]/.process/context-package.json",
|
||||
"priority": "critical",
|
||||
"usage": "Smart context with focus paths, module structure, dependency graph, existing patterns, tech stack. Use for: environment setup, dependency resolution, pattern discovery, conflict detection results"
|
||||
},
|
||||
{
|
||||
"path": ".workflow/WFS-[session]/.brainstorming/guidance-specification.md",
|
||||
"priority": "high",
|
||||
@@ -210,8 +206,9 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
|
||||
{
|
||||
"step": "load_context_package",
|
||||
"action": "Load context package for artifact paths",
|
||||
"note": "Context package path is now at top-level field: context_package_path",
|
||||
"commands": [
|
||||
"Read(.workflow/WFS-[session]/.process/context-package.json)"
|
||||
"Read({{context_package_path}})"
|
||||
],
|
||||
"output_to": "context_package",
|
||||
"on_error": "fail"
|
||||
@@ -221,7 +218,7 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
|
||||
"action": "Load role analyses from context-package.json (supports multiple files per role)",
|
||||
"note": "Paths loaded from context-package.json → brainstorm_artifacts.role_analyses[]. Supports analysis*.md automatically.",
|
||||
"commands": [
|
||||
"Read(.workflow/WFS-[session]/.process/context-package.json)",
|
||||
"Read({{context_package_path}})",
|
||||
"Extract(brainstorm_artifacts.role_analyses[].files[].path)",
|
||||
"Read(each extracted path)"
|
||||
],
|
||||
@@ -231,9 +228,9 @@ This enhanced 5-field schema embeds all necessary context, artifacts, and execut
|
||||
{
|
||||
"step": "load_planning_context",
|
||||
"action": "Load plan-generated context intelligence with resolved conflicts",
|
||||
"note": "CRITICAL: context-package.json provides smart context (focus paths, dependencies, patterns) and conflict resolution status. If conflict_risk was medium/high, conflicts have been resolved in guidance-specification.md and role analyses.",
|
||||
"note": "CRITICAL: context-package.json (from context_package_path) provides smart context (focus paths, dependencies, patterns) and conflict resolution status. If conflict_risk was medium/high, conflicts have been resolved in guidance-specification.md and role analyses.",
|
||||
"commands": [
|
||||
"Read(.workflow/WFS-[session]/.process/context-package.json)",
|
||||
"Read({{context_package_path}})",
|
||||
"Read(.workflow/WFS-[session]/.brainstorming/guidance-specification.md)"
|
||||
],
|
||||
"output_to": "planning_context",
|
||||
@@ -403,7 +400,7 @@ Role analyses provide specialized perspectives on the implementation:
|
||||
- **topic-framework.md**: Role-specific discussion points and analysis framework
|
||||
|
||||
**Artifact Priority in Development**:
|
||||
1. context-package.json (primary source: smart context AND brainstorm artifact catalog in `brainstorm_artifacts` + conflict_risk status)
|
||||
1. {context_package_path} (primary source: smart context AND brainstorm artifact catalog in `brainstorm_artifacts` + conflict_risk status)
|
||||
2. role/analysis*.md (paths from context-package.json: requirements, design specs, enhanced by synthesis, with resolved conflicts if any)
|
||||
3. guidance-specification.md (path from context-package.json: finalized decisions with resolved conflicts if any)
|
||||
|
||||
@@ -592,8 +589,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
|
||||
**Key Points**:
|
||||
- **Sequential Steps**: Steps execute in order defined in `implementation_approach` array
|
||||
- **Context Delivery**: Each codex command receives context via CONTEXT field: `@.workflow/WFS-session/.process/context-package.json` (role analyses loaded dynamically from context package)
|
||||
- **Multi-Step Tasks**: First step provides full context, subsequent steps use `resume --last` to maintain session continuity
|
||||
- **Context Delivery**: Each codex command receives context via CONTEXT field: `@{context_package_path}` (role analyses loaded dynamically from context package)- **Multi-Step Tasks**: First step provides full context, subsequent steps use `resume --last` to maintain session continuity
|
||||
- **Step Dependencies**: Later steps reference outputs from earlier steps via `depends_on` field
|
||||
|
||||
### Example 1: Agent Mode - Simple Task (Default, No Command)
|
||||
@@ -601,6 +597,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
{
|
||||
"id": "IMPL-001",
|
||||
"title": "Implement user authentication module",
|
||||
"context_package_path": ".workflow/WFS-session/.process/context-package.json",
|
||||
"context": {
|
||||
"depends_on": [],
|
||||
"focus_paths": ["src/auth"],
|
||||
@@ -617,7 +614,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
"step": "load_role_analyses",
|
||||
"action": "Load role analyses from context-package.json",
|
||||
"commands": [
|
||||
"Read(.workflow/WFS-session/.process/context-package.json)",
|
||||
"Read({{context_package_path}})",
|
||||
"Extract(brainstorm_artifacts.role_analyses[].files[].path)",
|
||||
"Read(each extracted path)"
|
||||
],
|
||||
@@ -627,7 +624,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
{
|
||||
"step": "load_context",
|
||||
"action": "Load context package for project structure",
|
||||
"commands": ["Read(.workflow/WFS-session/.process/context-package.json)"],
|
||||
"commands": ["Read({{context_package_path}})"],
|
||||
"output_to": "context_pkg",
|
||||
"on_error": "fail"
|
||||
}
|
||||
@@ -662,6 +659,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
{
|
||||
"id": "IMPL-002",
|
||||
"title": "Implement user authentication module",
|
||||
"context_package_path": ".workflow/WFS-session/.process/context-package.json",
|
||||
"context": {
|
||||
"depends_on": [],
|
||||
"focus_paths": ["src/auth"],
|
||||
@@ -674,7 +672,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
"step": "load_role_analyses",
|
||||
"action": "Load role analyses from context-package.json",
|
||||
"commands": [
|
||||
"Read(.workflow/WFS-session/.process/context-package.json)",
|
||||
"Read({{context_package_path}})",
|
||||
"Extract(brainstorm_artifacts.role_analyses[].files[].path)",
|
||||
"Read(each extracted path)"
|
||||
],
|
||||
@@ -687,7 +685,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
"step": 1,
|
||||
"title": "Implement authentication with Codex",
|
||||
"description": "Create JWT-based authentication module",
|
||||
"command": "bash(codex -C src/auth --full-auto exec \"PURPOSE: Implement user authentication TASK: JWT-based auth with login/registration MODE: auto CONTEXT: @.workflow/WFS-session/.process/context-package.json EXPECTED: Complete auth module with tests RULES: Load role analyses from context-package.json → brainstorm_artifacts\" --skip-git-repo-check -s danger-full-access)",
|
||||
"command": "bash(codex -C src/auth --full-auto exec \"PURPOSE: Implement user authentication TASK: JWT-based auth with login/registration MODE: auto CONTEXT: @{{context_package_path}} EXPECTED: Complete auth module with tests RULES: Load role analyses from context-package.json → brainstorm_artifacts\" --skip-git-repo-check -s danger-full-access)",
|
||||
"modification_points": ["Create auth service", "Implement endpoints", "Add JWT middleware"],
|
||||
"logic_flow": ["Validate credentials", "Generate JWT", "Return token"],
|
||||
"depends_on": [],
|
||||
@@ -704,6 +702,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
{
|
||||
"id": "IMPL-003",
|
||||
"title": "Implement role-based access control",
|
||||
"context_package_path": ".workflow/WFS-session/.process/context-package.json",
|
||||
"context": {
|
||||
"depends_on": ["IMPL-002"],
|
||||
"focus_paths": ["src/auth", "src/middleware"],
|
||||
@@ -716,7 +715,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
"step": "load_context",
|
||||
"action": "Load context and role analyses from context-package.json",
|
||||
"commands": [
|
||||
"Read(.workflow/WFS-session/.process/context-package.json)",
|
||||
"Read({{context_package_path}})",
|
||||
"Extract(brainstorm_artifacts.role_analyses[].files[].path)",
|
||||
"Read(each extracted path)"
|
||||
],
|
||||
@@ -729,7 +728,7 @@ When using `--cli-execute`, each step in `implementation_approach` includes a `c
|
||||
"step": 1,
|
||||
"title": "Create RBAC models",
|
||||
"description": "Define role and permission data models",
|
||||
"command": "bash(codex -C src/auth --full-auto exec \"PURPOSE: Create RBAC models TASK: Role and permission models MODE: auto CONTEXT: @.workflow/WFS-session/.process/context-package.json EXPECTED: Models with migrations RULES: Load role analyses from context-package.json → brainstorm_artifacts\" --skip-git-repo-check -s danger-full-access)",
|
||||
"command": "bash(codex -C src/auth --full-auto exec \"PURPOSE: Create RBAC models TASK: Role and permission models MODE: auto CONTEXT: @{{context_package_path}} EXPECTED: Models with migrations RULES: Load role analyses from context-package.json → brainstorm_artifacts\" --skip-git-repo-check -s danger-full-access)",
|
||||
"modification_points": ["Define role model", "Define permission model", "Create migrations"],
|
||||
"logic_flow": ["Design schema", "Implement models", "Generate migrations"],
|
||||
"depends_on": [],
|
||||
|
||||
@@ -7,6 +7,7 @@ Task JSON Schema - Agent Mode (No Command Field)
|
||||
"id": "IMPL-N[.M]",
|
||||
"title": "Descriptive task name",
|
||||
"status": "pending",
|
||||
"context_package_path": "{context_package_path}",
|
||||
"meta": {
|
||||
"type": "feature|bugfix|refactor|test|docs",
|
||||
"agent": "@code-developer|@test-fix-agent|@universal-executor"
|
||||
|
||||
@@ -7,6 +7,7 @@ Task JSON Schema - CLI Execute Mode (With Command Field)
|
||||
"id": "IMPL-N[.M]",
|
||||
"title": "Descriptive task name",
|
||||
"status": "pending",
|
||||
"context_package_path": "{context_package_path}",
|
||||
"meta": {
|
||||
"type": "feature|bugfix|refactor|test|docs",
|
||||
"agent": "@code-developer|@test-fix-agent|@universal-executor"
|
||||
|
||||
Reference in New Issue
Block a user