mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-03-06 16:31:12 +08:00
feat: Add role specifications for 三省六部 architecture
- Introduced role specifications for 尚书省 (shangshu), 刑部 (xingbu), and 中书省 (zhongshu) to facilitate task management and execution flow. - Implemented quality gates for each phase of the process to ensure compliance and quality assurance. - Established a coordinator role to manage the overall workflow and task distribution among the departments. - Created a team configuration file to define roles, responsibilities, and routing rules for task execution. - Added localization support for DeepWiki in both English and Chinese, enhancing accessibility for users.
This commit is contained in:
catlog22
File diff suppressed because it is too large
Load Diff
56
.claude/skills/skill-simplify/SKILL.md
Normal file
56
.claude/skills/skill-simplify/SKILL.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
name: skill-simplify
|
||||
description: SKILL.md simplification with functional integrity verification. Analyze redundancy, optimize content, check no functionality lost. Triggers on "simplify skill", "optimize skill", "skill-simplify".
|
||||
allowed-tools: AskUserQuestion, Read, Write, Edit, Bash, Glob, Grep
|
||||
---
|
||||
|
||||
# Skill Simplify
|
||||
|
||||
Three-phase pipeline: analyze functional inventory, apply optimization rules, verify integrity.
|
||||
|
||||
**Phase Reference Documents** (read on-demand):
|
||||
|
||||
| Phase | Document | Purpose |
|
||||
|-------|----------|---------|
|
||||
| 1 | [phases/01-analysis.md](phases/01-analysis.md) | Extract functional inventory, identify redundancy, validate pseudo-code format |
|
||||
| 2 | [phases/02-optimize.md](phases/02-optimize.md) | Apply simplification rules, fix format issues |
|
||||
| 3 | [phases/03-check.md](phases/03-check.md) | Verify functional integrity, validate format |
|
||||
|
||||
## Input Processing
|
||||
|
||||
```javascript
|
||||
const targetPath = input.trim()
|
||||
const targetFile = targetPath.endsWith('.md') ? targetPath : `${targetPath}/SKILL.md`
|
||||
const originalContent = Read(targetFile)
|
||||
const originalLineCount = originalContent.split('\n').length
|
||||
```
|
||||
|
||||
## TodoWrite Pattern
|
||||
|
||||
```javascript
|
||||
TodoWrite({ todos: [
|
||||
{ content: `Phase 1: Analyzing ${targetFile}`, status: "in_progress", activeForm: "Extracting functional inventory" },
|
||||
{ content: "Phase 2: Optimize", status: "pending" },
|
||||
{ content: "Phase 3: Integrity Check", status: "pending" }
|
||||
]})
|
||||
```
|
||||
|
||||
## Core Rules
|
||||
|
||||
1. **Preserve ALL functional elements**: Code blocks with logic, agent calls, data structures, routing, error handling, input/output specs
|
||||
2. **Only reduce descriptive content**: Flowcharts, verbose comments, duplicate sections, examples that repeat logic
|
||||
3. **Never summarize algorithm logic**: If-else branches, function bodies, schemas must remain verbatim
|
||||
4. **Classify code blocks**: Distinguish `functional` (logic, routing, schemas) from `descriptive` (ASCII art, examples, display templates) — only descriptive blocks may be deleted
|
||||
5. **Merge equivalent variants**: Single/multi-perspective templates differing only by a parameter → one template with variant comment
|
||||
6. **Fix format issues**: Nested backtick template literals in code fences → convert to prose; hardcoded option lists → flag for dynamic generation; workflow handoff references → ensure execution steps present
|
||||
7. **Validate pseudo-code**: Check bracket matching, variable consistency, structural completeness
|
||||
8. **Quantitative verification**: Phase 3 counts must match Phase 1 counts for functional categories; descriptive block decreases are expected
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Resolution |
|
||||
|-------|------------|
|
||||
| Target file not found | Report error, stop |
|
||||
| Check FAIL (missing functional elements) | Show delta, revert to original, report which elements lost |
|
||||
| Check WARN (descriptive decrease or merge) | Show delta with justification |
|
||||
| Format issues found | Report in check, fix in Phase 2 |
|
||||
224
.claude/skills/skill-simplify/phases/01-analysis.md
Normal file
224
.claude/skills/skill-simplify/phases/01-analysis.md
Normal file
@@ -0,0 +1,224 @@
|
||||
# Phase 1: Functional Analysis
|
||||
|
||||
Read target file, extract functional inventory with code block classification, identify redundancy, validate pseudo-code format, and produce optimization plan.
|
||||
|
||||
## Objective
|
||||
|
||||
- Build quantitative functional inventory with code block classification (baseline for Phase 3)
|
||||
- Identify redundancy categories with specific line ranges
|
||||
- Detect pseudo-code format issues
|
||||
- Produce optimization plan with estimated line savings
|
||||
|
||||
## Execution
|
||||
|
||||
### Step 1.1: Read & Measure Target
|
||||
|
||||
```javascript
|
||||
const originalContent = Read(targetFile)
|
||||
const lines = originalContent.split('\n')
|
||||
const originalLineCount = lines.length
|
||||
```
|
||||
|
||||
### Step 1.2: Extract Functional Inventory
|
||||
|
||||
Count and catalog every functional element. These counts are the **baseline** for Phase 3 verification.
|
||||
|
||||
```javascript
|
||||
const inventory = {
|
||||
// Code structures — with role classification
|
||||
codeBlocks: [], // { startLine, endLine, language, purpose, role: 'functional'|'descriptive' }
|
||||
agentCalls: [], // { line, agentType, description, mergeGroup?: string }
|
||||
dataStructures: [], // { line, name, type: 'object'|'array'|'schema' }
|
||||
|
||||
// Logic elements
|
||||
routingBranches: [], // { line, condition, outcomes[] }
|
||||
errorHandlers: [], // { line, errorType, resolution }
|
||||
conditionalLogic: [], // { line, condition, trueAction, falseAction }
|
||||
|
||||
// Interface elements
|
||||
askUserQuestions: [], // { line, questionCount, headers[], optionType: 'static'|'dynamic' }
|
||||
inputModes: [], // { line, mode, description }
|
||||
outputArtifacts: [], // { line, artifact, format }
|
||||
|
||||
// Structural elements
|
||||
todoWriteBlocks: [], // { line, phaseCount }
|
||||
phaseHandoffs: [], // { line, fromPhase, toPhase }
|
||||
skillInvocations: [], // { line, skillName, hasExecutionSteps: boolean }
|
||||
|
||||
// Reference elements
|
||||
tables: [], // { startLine, endLine, columns }
|
||||
schemas: [], // { line, schemaName, fields[] }
|
||||
|
||||
// Format issues
|
||||
formatIssues: [], // { line, type, description, severity: 'error'|'warning' }
|
||||
|
||||
// Totals (computed)
|
||||
counts: {}
|
||||
}
|
||||
```
|
||||
|
||||
**Extraction rules**:
|
||||
- **Code blocks**: Match ` ```language ... ``` ` pairs, record start/end/language/first-line-as-purpose
|
||||
- **Agent calls**: Match `Agent(`, `Task(`, `subagent_type=`, record type and prompt summary
|
||||
- **Data structures**: Match `const xxx = {`, `const xxx = [`, JSON schema objects
|
||||
- **Routing branches**: Match `if/else`, `switch/case`, ternary `? :` with meaningful branching
|
||||
- **Error handlers**: Match `catch`, error table rows `| Error |`, fallback patterns
|
||||
- **AskUserQuestion**: Match `AskUserQuestion({`, count questions array length
|
||||
- **Input modes**: Match `Mode 1/2/3`, `--flag`, argument parsing
|
||||
- **Output artifacts**: Match `Write(`, `Output:`, file path patterns in comments
|
||||
- **TodoWrite**: Match `TodoWrite({`, count todo items
|
||||
- **Phase handoffs**: Match `Read("phases/`, `Skill(`, `proceed_to_next_phase`
|
||||
- **Tables**: Match `| header |` markdown table blocks
|
||||
- **Schemas**: Match schema references, JSON structure definitions
|
||||
|
||||
### Step 1.2.1: Code Block Role Classification
|
||||
|
||||
For each code block, determine its role:
|
||||
|
||||
| Role | Criteria | Examples |
|
||||
|------|----------|---------|
|
||||
| `functional` | Contains algorithm logic, routing branches, conditional code, agent calls, schema definitions, data processing, AskUserQuestion, Skill invocations | `if/else`, `Agent({...})`, `const schema = {...}`, `Bash({...})` |
|
||||
| `descriptive` | Contains ASCII art, usage examples, display templates, illustrative good/bad comparisons, folder structure trees | `┌───┐`, `# Example usage`, `❌ Bad / ✅ Good`, `├── file.ts` |
|
||||
|
||||
**Classification rules**:
|
||||
- If block contains ANY of: `Agent(`, `Bash(`, `AskUserQuestion(`, `if (`, `switch`, `Skill(`, `Write(`, `Read(`, `TodoWrite(` → `functional`
|
||||
- If block language is `bash` and content is only example invocations (no logic) → `descriptive`
|
||||
- If block has no language tag and contains only ASCII box-drawing characters → `descriptive`
|
||||
- If block is labeled as "Example" in surrounding markdown heading → `descriptive`
|
||||
- **Default**: `functional` (conservative)
|
||||
|
||||
### Step 1.2.2: Pseudo-Code Format Validation
|
||||
|
||||
Scan all `functional` code blocks for format issues:
|
||||
|
||||
| Check | Detection | Severity |
|
||||
|-------|-----------|----------|
|
||||
| **Nested backticks** | Template literal `` ` `` inside ` ```javascript ``` ` code fence | warning |
|
||||
| **Unclosed brackets** | Unmatched `{`, `(`, `[` in code block | error |
|
||||
| **Undefined references** | `${variable}` where variable is never declared in the block or prior blocks | warning |
|
||||
| **Inconsistent indentation** | Mixed tabs/spaces or inconsistent nesting depth | warning |
|
||||
| **Dead code patterns** | Commented-out code blocks (`// if (`, `/* ... */` spanning 5+ lines) | warning |
|
||||
| **Missing return/output** | Function-like block with no return, Write, or console.log | warning |
|
||||
|
||||
```javascript
|
||||
inventory.formatIssues = validatePseudoCode(inventory.codeBlocks.filter(b => b.role === 'functional'))
|
||||
```
|
||||
|
||||
### Step 1.2.3: Compute Totals
|
||||
|
||||
```javascript
|
||||
inventory.counts = {
|
||||
codeBlocks: inventory.codeBlocks.length,
|
||||
functionalCodeBlocks: inventory.codeBlocks.filter(b => b.role === 'functional').length,
|
||||
descriptiveCodeBlocks: inventory.codeBlocks.filter(b => b.role === 'descriptive').length,
|
||||
agentCalls: inventory.agentCalls.length,
|
||||
dataStructures: inventory.dataStructures.length,
|
||||
routingBranches: inventory.routingBranches.length,
|
||||
errorHandlers: inventory.errorHandlers.length,
|
||||
conditionalLogic: inventory.conditionalLogic.length,
|
||||
askUserQuestions: inventory.askUserQuestions.length,
|
||||
inputModes: inventory.inputModes.length,
|
||||
outputArtifacts: inventory.outputArtifacts.length,
|
||||
todoWriteBlocks: inventory.todoWriteBlocks.length,
|
||||
phaseHandoffs: inventory.phaseHandoffs.length,
|
||||
skillInvocations: inventory.skillInvocations.length,
|
||||
tables: inventory.tables.length,
|
||||
schemas: inventory.schemas.length,
|
||||
formatIssues: inventory.formatIssues.length
|
||||
}
|
||||
```
|
||||
|
||||
### Step 1.3: Identify Redundancy Categories
|
||||
|
||||
Scan for each category, record specific line ranges:
|
||||
|
||||
```javascript
|
||||
const redundancyMap = {
|
||||
deletable: [], // { category, startLine, endLine, reason, estimatedSave }
|
||||
simplifiable: [], // { category, startLine, endLine, strategy, estimatedSave }
|
||||
mergeable: [], // { items: [{startLine, endLine}], mergeStrategy, estimatedSave }
|
||||
formatFixes: [], // { line, type, fix }
|
||||
languageUnify: [] // { line, currentLang, targetLang }
|
||||
}
|
||||
```
|
||||
|
||||
**Deletable** (remove entirely, no functional loss):
|
||||
|
||||
| Pattern | Detection |
|
||||
|---------|-----------|
|
||||
| Duplicate Overview | `## Overview` that restates frontmatter description |
|
||||
| ASCII flowchart | Flowchart that duplicates Phase Summary table or implementation structure |
|
||||
| "When to use" section | Usage guidance not needed for execution |
|
||||
| Best Practices section | Advisory content duplicating Core Rules |
|
||||
| Duplicate examples | Code examples that repeat logic shown elsewhere |
|
||||
| Folder structure duplicate | ASCII tree repeating Output Artifacts table |
|
||||
| "Next Phase" paragraphs | Prose between phases when TodoWrite handles flow |
|
||||
| Descriptive code blocks | Code blocks classified as `descriptive` whose content is covered by surrounding prose or tables |
|
||||
|
||||
**Simplifiable** (compress, preserve meaning):
|
||||
|
||||
| Pattern | Strategy |
|
||||
|---------|----------|
|
||||
| Verbose comments in code blocks | Reduce to single-line; keep only non-obvious logic comments |
|
||||
| Multi-line console.log | Compress to single template literal |
|
||||
| Wordy section intros | Remove "In this phase, we will..." preamble |
|
||||
| Exploration prompt bloat | Trim to essential instructions, remove generic advice |
|
||||
| Display-format code blocks | Convert code blocks that only define output format (console.log with template) to prose description |
|
||||
|
||||
**Mergeable** (combine related structures):
|
||||
|
||||
| Pattern | Strategy |
|
||||
|---------|----------|
|
||||
| Multiple similar AskUserQuestion calls | Extract shared function with mode parameter |
|
||||
| Repeated Option routing | Unify into single dispatch |
|
||||
| Sequential single-line operations | Combine into one code block |
|
||||
| TodoWrite full blocks x N | Template once + delta comments |
|
||||
| Duplicate error handling tables | Merge into single table |
|
||||
| Equivalent template variants | Single/multi-perspective templates → one template with variant comment |
|
||||
| Multiple output artifact tables | Merge into single combined table |
|
||||
|
||||
**Format fixes** (pseudo-code quality):
|
||||
|
||||
| Pattern | Fix |
|
||||
|---------|-----|
|
||||
| Nested backtick template literals | Convert surrounding code block to prose description, or use 4-backtick fence |
|
||||
| Hardcoded option lists | Add comment: `// Generate dynamically from {context source}` |
|
||||
| Workflow handoff without execution steps | Add execution steps referencing the target command's actual interface |
|
||||
| Unclosed brackets | Fix bracket matching |
|
||||
|
||||
**Language unification**:
|
||||
- Detect mixed Chinese/English in functional comments
|
||||
- Recommend consistent language (match majority)
|
||||
|
||||
### Step 1.4: Build Optimization Plan
|
||||
|
||||
```javascript
|
||||
const optimizationPlan = {
|
||||
targetFile,
|
||||
originalLineCount,
|
||||
estimatedReduction: redundancyMap.deletable.reduce((s, d) => s + d.estimatedSave, 0)
|
||||
+ redundancyMap.simplifiable.reduce((s, d) => s + d.estimatedSave, 0)
|
||||
+ redundancyMap.mergeable.reduce((s, d) => s + d.estimatedSave, 0),
|
||||
categories: {
|
||||
deletable: { count: redundancyMap.deletable.length, totalLines: '...' },
|
||||
simplifiable: { count: redundancyMap.simplifiable.length, totalLines: '...' },
|
||||
mergeable: { count: redundancyMap.mergeable.length, totalLines: '...' },
|
||||
formatFixes: { count: redundancyMap.formatFixes.length },
|
||||
languageUnify: { count: redundancyMap.languageUnify.length }
|
||||
},
|
||||
// Ordered: delete → merge → simplify → format
|
||||
operations: [
|
||||
...redundancyMap.deletable.map(d => ({ type: 'delete', ...d, priority: 1 })),
|
||||
...redundancyMap.mergeable.map(m => ({ type: 'merge', ...m, priority: 2 })),
|
||||
...redundancyMap.simplifiable.map(s => ({ type: 'simplify', ...s, priority: 3 })),
|
||||
...redundancyMap.formatFixes.map(f => ({ type: 'format', ...f, priority: 4 }))
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Display plan summary: category counts, estimated reduction percentage, sections NOT changed (functional core).
|
||||
|
||||
## Output
|
||||
|
||||
- **Variable**: `analysisResult = { inventory, redundancyMap, optimizationPlan, originalContent, originalLineCount }`
|
||||
- **TodoWrite**: Mark Phase 1 completed, Phase 2 in_progress
|
||||
107
.claude/skills/skill-simplify/phases/02-optimize.md
Normal file
107
.claude/skills/skill-simplify/phases/02-optimize.md
Normal file
@@ -0,0 +1,107 @@
|
||||
# Phase 2: Optimize
|
||||
|
||||
Apply simplification rules from analysisResult to produce optimized content. Write result to disk.
|
||||
|
||||
## Objective
|
||||
|
||||
- Execute all optimization operations in priority order (delete → merge → simplify → format)
|
||||
- Preserve every functional element identified in Phase 1 inventory
|
||||
- Fix pseudo-code format issues
|
||||
- Write optimized content back to target file
|
||||
|
||||
## Execution
|
||||
|
||||
### Step 2.1: Apply Operations in Order
|
||||
|
||||
Process `analysisResult.optimizationPlan.operations` sorted by priority:
|
||||
|
||||
**Priority 1 — Delete** (safest, highest impact):
|
||||
|
||||
| Target Pattern | Action |
|
||||
|----------------|--------|
|
||||
| Duplicate Overview section | Remove `## Overview` if it restates frontmatter `description` |
|
||||
| ASCII flowchart | Remove if Phase Summary table or implementation structure covers same info |
|
||||
| "When to use" / "Use Cases" section | Remove entirely |
|
||||
| Best Practices section | Remove if content duplicates Core Rules |
|
||||
| Duplicate folder structure | Remove ASCII tree if Output Artifacts table covers same info |
|
||||
| Redundant "Next Phase" prose | Remove when TodoWrite handles flow |
|
||||
| Standalone example sections | Remove if logic already demonstrated inline |
|
||||
| Descriptive code blocks | Remove if content covered by surrounding prose or tables |
|
||||
|
||||
**Priority 2 — Merge** (structural optimization):
|
||||
|
||||
| Target Pattern | Action |
|
||||
|----------------|--------|
|
||||
| Multiple similar AskUserQuestion blocks | Extract shared function with mode parameter |
|
||||
| Repeated Option A/B/C routing | Unify into single dispatch |
|
||||
| Sequential single-line bash commands | Combine into single code block |
|
||||
| TodoWrite full blocks x N | Template ONCE, subsequent as one-line comment |
|
||||
| Duplicate error handling across sections | Merge into single `## Error Handling` table |
|
||||
| Equivalent template variants | Single/multi templates → one template with `// For multi: add Perspective` comment |
|
||||
| Multiple output artifact tables | Merge into single combined table with Phase column |
|
||||
|
||||
**Priority 3 — Simplify** (compress descriptive content):
|
||||
|
||||
| Target Pattern | Action |
|
||||
|----------------|--------|
|
||||
| Verbose inline comments | Reduce to single-line; remove obvious restatements |
|
||||
| Display-format code blocks | Convert `console.log` with template literal to prose describing output format |
|
||||
| Wordy section introductions | Remove preamble sentences |
|
||||
| Exploration/agent prompt padding | Remove generic advice |
|
||||
| Success Criteria lists > 7 items | Trim to essential 5-7, remove obvious/generic |
|
||||
|
||||
**Priority 4 — Format fixes** (pseudo-code quality):
|
||||
|
||||
| Target Pattern | Action |
|
||||
|----------------|--------|
|
||||
| Nested backtick template literals | Convert code block to prose description, or use 4-backtick fence |
|
||||
| Hardcoded option lists | Replace with dynamic generation: describe source of options + generation logic |
|
||||
| Workflow handoff without execution steps | Add concrete steps referencing target command's interface (e.g., pipe to `ccw issue create`) |
|
||||
| Unclosed brackets | Fix bracket matching |
|
||||
| Undefined variable references | Add declaration or link to source |
|
||||
|
||||
### Step 2.2: Language Unification (if applicable)
|
||||
|
||||
```javascript
|
||||
if (analysisResult.redundancyMap.languageUnify.length > 0) {
|
||||
// Detect majority language, unify non-functional text
|
||||
// DO NOT change: variable names, function names, schema fields, error messages in code
|
||||
}
|
||||
```
|
||||
|
||||
### Step 2.3: Write Optimized Content
|
||||
|
||||
```javascript
|
||||
Write(targetFile, optimizedContent)
|
||||
const optimizedLineCount = optimizedContent.split('\n').length
|
||||
const reduction = originalLineCount - optimizedLineCount
|
||||
const reductionPct = Math.round(reduction / originalLineCount * 100)
|
||||
```
|
||||
|
||||
### Step 2.4: Preserve Optimization Record
|
||||
|
||||
```javascript
|
||||
const optimizationRecord = {
|
||||
deletedSections: [], // section names removed
|
||||
mergedGroups: [], // { from: [sections], to: description }
|
||||
simplifiedAreas: [], // { section, strategy }
|
||||
formatFixes: [], // { line, type, fix }
|
||||
linesBefore: originalLineCount,
|
||||
linesAfter: optimizedLineCount
|
||||
}
|
||||
```
|
||||
|
||||
## Key Rules
|
||||
|
||||
1. **Never modify functional code blocks** — only compress comments/whitespace within them
|
||||
2. **Descriptive code blocks may be deleted** if their content is covered by prose or tables
|
||||
3. **Never change function signatures, variable names, or schema fields**
|
||||
4. **Merge preserves all branches** — unified function must handle all original cases
|
||||
5. **When uncertain, keep original** — conservative approach prevents functional loss
|
||||
6. **Format fixes must not alter semantics** — only presentation changes
|
||||
|
||||
## Output
|
||||
|
||||
- **File**: Target file overwritten with optimized content
|
||||
- **Variable**: `optimizationRecord` (changes log for Phase 3)
|
||||
- **TodoWrite**: Mark Phase 2 completed, Phase 3 in_progress
|
||||
224
.claude/skills/skill-simplify/phases/03-check.md
Normal file
224
.claude/skills/skill-simplify/phases/03-check.md
Normal file
@@ -0,0 +1,224 @@
|
||||
# Phase 3: Integrity Check
|
||||
|
||||
Re-extract functional inventory from optimized file, compare against Phase 1 baseline, validate pseudo-code format. Report PASS/FAIL with detailed delta.
|
||||
|
||||
## Objective
|
||||
|
||||
- Re-run the same inventory extraction on optimized content
|
||||
- Compare counts using role-aware classification (functional vs descriptive)
|
||||
- Validate pseudo-code format issues are resolved
|
||||
- Report check result with actionable details
|
||||
- Revert if critical functional elements are missing
|
||||
|
||||
## Execution
|
||||
|
||||
### Step 3.1: Re-Extract Inventory from Optimized File
|
||||
|
||||
```javascript
|
||||
const optimizedContent = Read(targetFile)
|
||||
const optimizedLineCount = optimizedContent.split('\n').length
|
||||
|
||||
// Use SAME extraction logic as Phase 1 (including role classification)
|
||||
const afterInventory = extractFunctionalInventory(optimizedContent)
|
||||
```
|
||||
|
||||
### Step 3.2: Compare Inventories (Role-Aware)
|
||||
|
||||
```javascript
|
||||
const beforeCounts = analysisResult.inventory.counts
|
||||
const afterCounts = afterInventory.counts
|
||||
|
||||
const delta = {}
|
||||
let hasCriticalLoss = false
|
||||
let hasWarning = false
|
||||
|
||||
// CRITICAL: Functional elements that MUST NOT decrease
|
||||
const CRITICAL = ['functionalCodeBlocks', 'dataStructures', 'routingBranches',
|
||||
'errorHandlers', 'conditionalLogic', 'askUserQuestions',
|
||||
'inputModes', 'outputArtifacts', 'skillInvocations']
|
||||
|
||||
// MERGE_AWARE: May decrease due to valid merge operations — verify coverage
|
||||
const MERGE_AWARE = ['agentCalls', 'codeBlocks']
|
||||
|
||||
// EXPECTED_DECREASE: May decrease from merge/consolidation
|
||||
const EXPECTED_DECREASE = ['descriptiveCodeBlocks', 'todoWriteBlocks',
|
||||
'phaseHandoffs', 'tables', 'schemas']
|
||||
|
||||
for (const [key, before] of Object.entries(beforeCounts)) {
|
||||
const after = afterCounts[key] || 0
|
||||
const diff = after - before
|
||||
let category, status
|
||||
|
||||
if (CRITICAL.includes(key)) {
|
||||
category = 'critical'
|
||||
status = diff < 0 ? 'FAIL' : 'OK'
|
||||
if (diff < 0) hasCriticalLoss = true
|
||||
} else if (MERGE_AWARE.includes(key)) {
|
||||
category = 'merge_aware'
|
||||
// Decrease is WARN (needs justification), not FAIL
|
||||
status = diff < 0 ? 'WARN' : 'OK'
|
||||
if (diff < 0) hasWarning = true
|
||||
} else {
|
||||
category = 'expected'
|
||||
status = 'OK' // Descriptive decreases are expected
|
||||
}
|
||||
|
||||
delta[key] = { before, after, diff, category, status }
|
||||
}
|
||||
```
|
||||
|
||||
### Step 3.3: Deep Verification
|
||||
|
||||
**For CRITICAL categories with decrease** — identify exactly what was lost:
|
||||
|
||||
```javascript
|
||||
if (hasCriticalLoss) {
|
||||
const lostElements = {}
|
||||
for (const [key, d] of Object.entries(delta)) {
|
||||
if (d.status === 'FAIL') {
|
||||
const beforeItems = analysisResult.inventory[key]
|
||||
const afterItems = afterInventory[key]
|
||||
lostElements[key] = beforeItems.filter(beforeItem =>
|
||||
!afterItems.some(afterItem => matchesElement(beforeItem, afterItem))
|
||||
)
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**For MERGE_AWARE categories with decrease** — verify merged coverage:
|
||||
|
||||
```javascript
|
||||
if (hasWarning) {
|
||||
for (const [key, d] of Object.entries(delta)) {
|
||||
if (d.category === 'merge_aware' && d.diff < 0) {
|
||||
// Check if merged template covers all original variants
|
||||
// e.g., single Agent template with "// For multi: add Perspective" covers both
|
||||
const beforeItems = analysisResult.inventory[key]
|
||||
const afterItems = afterInventory[key]
|
||||
const unmatched = beforeItems.filter(beforeItem =>
|
||||
!afterItems.some(afterItem => matchesElement(beforeItem, afterItem))
|
||||
)
|
||||
if (unmatched.length > 0) {
|
||||
// Check if unmatched items are covered by merge comments in remaining items
|
||||
const mergeComments = afterItems.flatMap(item => extractMergeComments(item))
|
||||
const trulyLost = unmatched.filter(item =>
|
||||
!mergeComments.some(comment => coversElement(comment, item))
|
||||
)
|
||||
if (trulyLost.length > 0) {
|
||||
delta[key].status = 'FAIL'
|
||||
hasCriticalLoss = true
|
||||
delta[key].trulyLost = trulyLost
|
||||
}
|
||||
// else: merge-covered, WARN is correct
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Step 3.4: Pseudo-Code Format Validation
|
||||
|
||||
```javascript
|
||||
const afterFormatIssues = validatePseudoCode(afterInventory.codeBlocks.filter(b => b.role === 'functional'))
|
||||
const beforeFormatCount = analysisResult.inventory.formatIssues.length
|
||||
const afterFormatCount = afterFormatIssues.length
|
||||
|
||||
const formatDelta = {
|
||||
before: beforeFormatCount,
|
||||
after: afterFormatCount,
|
||||
resolved: beforeFormatCount - afterFormatCount,
|
||||
newIssues: afterFormatIssues.filter(issue =>
|
||||
!analysisResult.inventory.formatIssues.some(orig => orig.line === issue.line && orig.type === issue.type)
|
||||
)
|
||||
}
|
||||
|
||||
// New format issues introduced by optimization = FAIL
|
||||
if (formatDelta.newIssues.length > 0) {
|
||||
hasCriticalLoss = true
|
||||
}
|
||||
```
|
||||
|
||||
**Pseudo-code validation checks**:
|
||||
|
||||
| Check | Detection | Action on Failure |
|
||||
|-------|-----------|-------------------|
|
||||
| Bracket matching | Count `{([` vs `})]` per code block | FAIL — fix or revert |
|
||||
| Variable consistency | `${var}` used but never declared | WARNING — note in report |
|
||||
| Structural completeness | Function body has entry but no exit (return/Write/output) | WARNING |
|
||||
| Nested backtick resolution | Backtick template literals inside code fences | WARNING if pre-existing, FAIL if newly introduced |
|
||||
| Schema field preservation | Schema fields in after match before | FAIL if fields lost |
|
||||
|
||||
### Step 3.5: Generate Check Report
|
||||
|
||||
```javascript
|
||||
const status = hasCriticalLoss ? 'FAIL' : (hasWarning ? 'WARN' : 'PASS')
|
||||
|
||||
const checkReport = {
|
||||
status,
|
||||
linesBefore: analysisResult.originalLineCount,
|
||||
linesAfter: optimizedLineCount,
|
||||
reduction: `${analysisResult.originalLineCount - optimizedLineCount} lines (-${Math.round((analysisResult.originalLineCount - optimizedLineCount) / analysisResult.originalLineCount * 100)}%)`,
|
||||
delta,
|
||||
formatDelta,
|
||||
lostElements: hasCriticalLoss ? lostElements : null
|
||||
}
|
||||
|
||||
// Display report table
|
||||
// | Category | Before | After | Delta | Status |
|
||||
// Show all categories, highlight FAIL/WARN rows
|
||||
// Show format issues summary if any
|
||||
```
|
||||
|
||||
### Step 3.6: Act on Result
|
||||
|
||||
```javascript
|
||||
if (status === 'FAIL') {
|
||||
Write(targetFile, analysisResult.originalContent)
|
||||
// Report: "Critical elements lost / new format issues introduced. Reverted."
|
||||
}
|
||||
|
||||
if (status === 'WARN') {
|
||||
// Report: "Decreases from merge/descriptive removal. Verify coverage."
|
||||
// Show merge justifications for MERGE_AWARE categories
|
||||
}
|
||||
|
||||
if (status === 'PASS') {
|
||||
// Report: "All functional elements preserved. Optimization successful."
|
||||
}
|
||||
```
|
||||
|
||||
## Element Matching Rules
|
||||
|
||||
How `matchesElement()` determines if a before-element exists in after-inventory:
|
||||
|
||||
| Element Type | Match Criteria |
|
||||
|-------------|---------------|
|
||||
| codeBlocks | Same language + first meaningful line (ignore whitespace/comments) |
|
||||
| agentCalls | Same agentType + similar prompt keywords (>60% overlap) |
|
||||
| dataStructures | Same variable name OR same field set |
|
||||
| routingBranches | Same condition expression (normalized) |
|
||||
| errorHandlers | Same error type/pattern |
|
||||
| conditionalLogic | Same condition + same outcome set |
|
||||
| askUserQuestions | Same question count + similar option labels |
|
||||
| inputModes | Same mode identifier |
|
||||
| outputArtifacts | Same file path pattern or artifact name |
|
||||
| skillInvocations | Same skill name |
|
||||
| todoWriteBlocks | Same phase names (order-independent) |
|
||||
| phaseHandoffs | Same target phase reference |
|
||||
| tables | Same column headers |
|
||||
| schemas | Same schema name or field set |
|
||||
|
||||
**Merge coverage check** (`coversElement()`):
|
||||
- Agent calls: Merged template contains `// For multi:` or `// Multi-perspective:` comment referencing the missing variant
|
||||
- Code blocks: Merged block contains comment noting the alternative was folded in
|
||||
|
||||
## Completion
|
||||
|
||||
```javascript
|
||||
TodoWrite({ todos: [
|
||||
{ content: `Phase 1: Analysis [${Object.keys(analysisResult.inventory.counts).length} categories]`, status: "completed" },
|
||||
{ content: `Phase 2: Optimize [${checkReport.reduction}]`, status: "completed" },
|
||||
{ content: `Phase 3: Check [${checkReport.status}] | Format: ${formatDelta.resolved} resolved, ${formatDelta.newIssues.length} new`, status: "completed" }
|
||||
]})
|
||||
```
|
||||
BIN
.claude/skills/team-edict.zip
Normal file
BIN
.claude/skills/team-edict.zip
Normal file
Binary file not shown.
204
.claude/skills/team-edict/SKILL.md
Normal file
204
.claude/skills/team-edict/SKILL.md
Normal file
@@ -0,0 +1,204 @@
|
||||
---
|
||||
name: team-edict
|
||||
description: |
|
||||
三省六部 multi-agent 协作框架，完整复刻 Edict 架构。
|
||||
太子接旨 -> 中书省规划 -> 门下省审议(多CLI并行) -> 尚书省调度 -> 六部并行执行。
|
||||
强制看板状态上报（state/flow/progress），支持 Blocked 一等公民状态，全流程可观测。
|
||||
Triggers on "team edict", "三省六部", "edict team".
|
||||
allowed-tools: TeamCreate(*), TeamDelete(*), SendMessage(*), TaskCreate(*), TaskUpdate(*), TaskList(*), TaskGet(*), Agent(*), AskUserQuestion(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*)
|
||||
---
|
||||
|
||||
# Team Edict — 三省六部
|
||||
|
||||
受古代三省六部制启发的多 agent 协作框架。核心设计：**严格的级联审批流 + 实时看板可观测性 + 多 CLI 并行分析**。
|
||||
|
||||
## Architecture
|
||||
|
||||
```
|
||||
+----------------------------------------------------------+
|
||||
| Skill(skill="team-edict") |
|
||||
| args="任务描述" |
|
||||
+------------------------+---------------------------------+
|
||||
|
|
||||
Coordinator (太子·接旨分拣)
|
||||
Phase 0-5 orchestration
|
||||
|
|
||||
+---------------+--------------+
|
||||
| |
|
||||
[串行审批链] [看板 State Bus]
|
||||
| |
|
||||
中书省(PLAN) ← 所有 agent 强制上报
|
||||
| state/flow/progress
|
||||
门下省(REVIEW) ← 多CLI审议
|
||||
|
|
||||
尚书省(DISPATCH) ← 路由分析
|
||||
|
|
||||
+----+----+----+----+----+----+
|
||||
工部 兵部 户部 礼部 吏部 刑部
|
||||
(IMPL)(OPS)(DATA)(DOC)(HR)(QA)
|
||||
[team-worker × 6, 按需并行]
|
||||
```
|
||||
|
||||
## Role Router
|
||||
|
||||
此 skill 为 **coordinator-only**。所有 worker 直接以 `team-worker` agent 形式 spawn。
|
||||
|
||||
### 输入解析
|
||||
|
||||
直接解析 `$ARGUMENTS` 作为任务描述，始终路由至 coordinator。
|
||||
|
||||
### Role Registry
|
||||
|
||||
| 角色 | 别名 | Spec | Task Prefix | Inner Loop | 职责 |
|
||||
|------|------|------|-------------|------------|------|
|
||||
| coordinator | 太子 | [roles/coordinator/role.md](roles/coordinator/role.md) | (none) | - | 接旨分拣、驱动流程 |
|
||||
| zhongshu | 中书省 | [role-specs/zhongshu.md](role-specs/zhongshu.md) | PLAN-* | false | 分析旨意、起草执行方案 |
|
||||
| menxia | 门下省 | [role-specs/menxia.md](role-specs/menxia.md) | REVIEW-* | false | 多维审议、准奏/封驳 |
|
||||
| shangshu | 尚书省 | [role-specs/shangshu.md](role-specs/shangshu.md) | DISPATCH-* | false | 分析方案、派发六部 |
|
||||
| gongbu | 工部 | [role-specs/gongbu.md](role-specs/gongbu.md) | IMPL-* | true | 功能开发、架构设计、代码实现 |
|
||||
| bingbu | 兵部 | [role-specs/bingbu.md](role-specs/bingbu.md) | OPS-* | true | 基础设施、部署、性能监控 |
|
||||
| hubu | 户部 | [role-specs/hubu.md](role-specs/hubu.md) | DATA-* | true | 数据分析、统计、资源管理 |
|
||||
| libu | 礼部 | [role-specs/libu.md](role-specs/libu.md) | DOC-* | true | 文档、规范、UI/UX、对外沟通 |
|
||||
| libu-hr | 吏部 | [role-specs/libu-hr.md](role-specs/libu-hr.md) | HR-* | false | Agent 管理、培训、考核评估 |
|
||||
| xingbu | 刑部 | [role-specs/xingbu.md](role-specs/xingbu.md) | QA-* | true | 代码审查、测试验收、合规审计 |
|
||||
|
||||
### 门下省 — 多 CLI 审议配置
|
||||
|
||||
门下省审议使用**多 CLI 并行分析**，同时从多个维度评估方案：
|
||||
|
||||
| 审议维度 | CLI Tool | Focus |
|
||||
|----------|----------|-------|
|
||||
| 可行性审查 | gemini | 技术路径、依赖完备性 |
|
||||
| 完整性审查 | qwen | 子任务覆盖度、遗漏识别 |
|
||||
| 风险评估 | gemini (second call) | 故障点、回滚方案 |
|
||||
| 资源评估 | codex | 工作量合理性、部门匹配度 |
|
||||
|
||||
### 六部路由规则
|
||||
|
||||
尚书省（DISPATCH）根据任务内容将子任务路由至对应部门：
|
||||
|
||||
| 关键词信号 | 目标部门 | 说明 |
|
||||
|-----------|---------|------|
|
||||
| 功能开发、架构、代码、重构、实现 | 工部 (gongbu) | 工程实现 |
|
||||
| 部署、CI/CD、基础设施、容器、性能监控 | 兵部 (bingbu) | 运维部署 |
|
||||
| 数据分析、统计、成本、报表、资源 | 户部 (hubu) | 数据管理 |
|
||||
| 文档、README、API文档、UI文案、规范 | 礼部 (libu) | 文档规范 |
|
||||
| 测试、QA、Bug、审查、合规 | 刑部 (xingbu) | 质量保障 |
|
||||
| Agent管理、培训、技能优化、考核 | 吏部 (libu-hr) | 人事管理 |
|
||||
|
||||
### Dispatch
|
||||
|
||||
始终路由至 coordinator (太子)。
|
||||
|
||||
### Orchestration Mode
|
||||
|
||||
用户只提供任务描述。
|
||||
|
||||
**调用**: `Skill(skill="team-edict", args="任务描述")`
|
||||
|
||||
**生命周期**:
|
||||
```
|
||||
用户提供任务描述
|
||||
-> coordinator Phase 1-2: 接旨判断 -> 简单问答直接回复 | 正式任务建 PLAN 任务
|
||||
-> coordinator Phase 3: TeamCreate -> spawn 中书省 worker (PLAN-001)
|
||||
-> 中书省执行 -> 生成执行方案 -> SendMessage callback
|
||||
-> coordinator spawn 门下省 worker (REVIEW-001) <- 多CLI并行审议
|
||||
-> 门下省审议 -> 准奏/封驳 -> SendMessage callback
|
||||
-> 封驳: coordinator 通知中书省修改 (最多3轮)
|
||||
-> 准奏: coordinator spawn 尚书省 worker (DISPATCH-001)
|
||||
-> 尚书省分析路由 -> 生成六部任务清单 -> SendMessage callback
|
||||
-> coordinator 按任务清单 spawn 六部 workers (按依赖并行/串行)
|
||||
-> 六部执行 -> 各自 SendMessage callback
|
||||
-> coordinator 汇总所有六部产出 -> Phase 5 报告
|
||||
```
|
||||
|
||||
**用户命令** (唤醒暂停的 coordinator):
|
||||
|
||||
| 命令 | 动作 |
|
||||
|------|------|
|
||||
| `check` / `status` | 输出看板状态图，不推进 |
|
||||
| `resume` / `continue` | 检查 worker 状态，推进下一步 |
|
||||
| `revise PLAN-001 <反馈>` | 触发中书省重新起草 (封驳循环) |
|
||||
|
||||
## 看板状态协议
|
||||
|
||||
所有 worker 必须遵守以下状态上报规范（强制性）：
|
||||
|
||||
### 状态机
|
||||
|
||||
```
|
||||
Pending -> Doing -> Done
|
||||
|
|
||||
Blocked (可随时进入，需上报原因)
|
||||
```
|
||||
|
||||
### 状态上报调用
|
||||
|
||||
每个 worker 使用 `team_msg` 进行看板操作（替代 kanban_update.py）：
|
||||
|
||||
```javascript
|
||||
// 接任务时
|
||||
team_msg(operation="log", session_id=<session_id>, from=<role>,
|
||||
type="state_update", data={state: "Doing", current_step: "开始执行[任务]"})
|
||||
|
||||
// 进度上报 (每个关键步骤)
|
||||
team_msg(operation="log", session_id=<session_id>, from=<role>,
|
||||
type="impl_progress", data={
|
||||
current: "正在执行步骤2：实现API接口",
|
||||
plan: "步骤1分析✅|步骤2实现🔄|步骤3测试"
|
||||
})
|
||||
|
||||
// 任务交接 (flow)
|
||||
team_msg(operation="log", session_id=<session_id>, from=<role>, to="coordinator",
|
||||
type="task_handoff", data={from_role: <role>, to_role: "coordinator", remark: "✅ 完成：[产出摘要]"})
|
||||
|
||||
// 阻塞上报
|
||||
team_msg(operation="log", session_id=<session_id>, from=<role>, to="coordinator",
|
||||
type="error", data={state: "Blocked", reason: "[阻塞原因]，请求协助"})
|
||||
```
|
||||
|
||||
## Specs Reference
|
||||
|
||||
| 文件 | 内容 | 使用方 |
|
||||
|------|------|--------|
|
||||
| [specs/team-config.json](specs/team-config.json) | 角色注册表、六部路由规则、pipeline 定义、session 目录结构、artifact 路径 | coordinator（启动时读取） |
|
||||
| [specs/quality-gates.md](specs/quality-gates.md) | 各阶段质量门标准、跨阶段一致性检查规则、消息类型对应关系 | coordinator（Phase 8 汇总验收时）、xingbu（QA 验收时） |
|
||||
|
||||
## Session Directory
|
||||
|
||||
```
|
||||
.workflow/.team/<session-id>/
|
||||
├── plan/
|
||||
│ ├── zhongshu-plan.md # 中书省起草的执行方案
|
||||
│ └── dispatch-plan.md # 尚书省生成的六部任务清单
|
||||
├── review/
|
||||
│ └── menxia-review.md # 门下省审议报告（含多CLI结论）
|
||||
├── artifacts/
|
||||
│ ├── gongbu-output.md # 工部产出
|
||||
│ ├── xingbu-report.md # 刑部测试报告
|
||||
│ └── ... # 各部门产出
|
||||
├── kanban/
|
||||
│ └── state.json # 看板状态快照
|
||||
└── wisdom/
|
||||
└── contributions/ # 各 worker 知识沉淀
|
||||
```
|
||||
|
||||
## Spawn Template
|
||||
|
||||
Coordinator 使用以下模板 spawn worker：
|
||||
|
||||
```javascript
|
||||
Agent({
|
||||
subagent_type: "team-worker",
|
||||
name: "<role>",
|
||||
team_name: "<team_name>",
|
||||
prompt: `role: <role>
|
||||
role_spec: .claude/skills/team-edict/role-specs/<role>.md
|
||||
session: <session_path>
|
||||
session_id: <session_id>
|
||||
team_name: <team_name>
|
||||
requirement: <original_requirement>
|
||||
inner_loop: <true|false>`,
|
||||
run_in_background: false
|
||||
})
|
||||
```
|
||||
56
.claude/skills/team-edict/role-specs/bingbu.md
Normal file
56
.claude/skills/team-edict/role-specs/bingbu.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
role: bingbu
|
||||
prefix: OPS
|
||||
inner_loop: true
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: ops_complete
|
||||
progress: ops_progress
|
||||
error: error
|
||||
---
|
||||
|
||||
# 兵部 — 基础设施与运维
|
||||
|
||||
基础设施运维、部署发布、CI/CD、性能监控、安全防御。
|
||||
|
||||
## Phase 2: 任务加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="bingbu",
|
||||
type="state_update", data={state:"Doing", current_step:"兵部开始执行：<运维任务>"})
|
||||
```
|
||||
|
||||
1. 读取当前任务（OPS-* task description）
|
||||
2. 读取 `<session_path>/plan/dispatch-plan.md` 获取任务令
|
||||
|
||||
## Phase 3: 运维执行
|
||||
|
||||
**进度上报（每步必须）**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="bingbu",
|
||||
type="ops_progress", data={current:"正在执行：<步骤>", plan:"<步骤1>✅|<步骤2>🔄|<步骤3>"})
|
||||
```
|
||||
|
||||
**执行策略**:
|
||||
|
||||
| 任务类型 | 方法 | CLI 工具 |
|
||||
|----------|------|---------|
|
||||
| 部署脚本/CI配置 | 直接 Write/Edit | inline |
|
||||
| 复杂基础设施分析 | CLI 分析 | gemini analysis |
|
||||
| 性能问题诊断 | CLI 分析 | gemini --rule analysis-analyze-performance |
|
||||
| 安全配置审查 | CLI 分析 | gemini --rule analysis-assess-security-risks |
|
||||
|
||||
## Phase 4: 产出上报
|
||||
|
||||
**写入** `<session_path>/artifacts/bingbu-output.md`
|
||||
|
||||
**看板流转 + SendMessage**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="bingbu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"bingbu", to_role:"coordinator",
|
||||
remark:"✅ 完成：<运维产出摘要>"})
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`ops_complete: task=<task_id>, artifact=artifacts/bingbu-output.md`,
|
||||
summary:"兵部运维任务完成"})
|
||||
```
|
||||
86
.claude/skills/team-edict/role-specs/gongbu.md
Normal file
86
.claude/skills/team-edict/role-specs/gongbu.md
Normal file
@@ -0,0 +1,86 @@
|
||||
---
|
||||
role: gongbu
|
||||
prefix: IMPL
|
||||
inner_loop: true
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: impl_complete
|
||||
progress: impl_progress
|
||||
error: error
|
||||
---
|
||||
|
||||
# 工部 — 工程实现
|
||||
|
||||
负责功能开发、架构设计、代码实现、重构优化。
|
||||
|
||||
## Phase 2: 任务加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="gongbu",
|
||||
type="state_update", data={state:"Doing", current_step:"工部开始执行：<任务内容>"})
|
||||
```
|
||||
|
||||
1. 读取当前任务（IMPL-* task description）
|
||||
2. 读取 `<session_path>/plan/dispatch-plan.md` 获取任务令详情
|
||||
3. 读取 `<session_path>/plan/zhongshu-plan.md` 获取验收标准
|
||||
|
||||
**后端选择**:
|
||||
|
||||
| 条件 | 后端 | 调用方式 |
|
||||
|------|------|---------|
|
||||
| 复杂多文件变更 / 架构级改动 | gemini | `ccw cli --tool gemini --mode write` |
|
||||
| 中等复杂度 | codex | `ccw cli --tool codex --mode write` |
|
||||
| 简单单文件修改 | 直接 Edit/Write | inline |
|
||||
|
||||
## Phase 3: 代码实现
|
||||
|
||||
**进度上报（每步必须）**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="gongbu",
|
||||
type="impl_progress", data={current:"正在执行：<当前步骤>",
|
||||
plan:"<步骤1>✅|<步骤2>🔄|<步骤3>"})
|
||||
```
|
||||
|
||||
**实现流程**:
|
||||
1. 探索代码库，理解现有架构:
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 理解与任务相关的现有代码模式
|
||||
TASK: • 找出相关模块 • 理解接口约定 • 识别可复用组件
|
||||
CONTEXT: @**/*
|
||||
MODE: analysis" --tool gemini --mode analysis
|
||||
```
|
||||
2. 按任务令实现功能（CLI write 或 inline）
|
||||
3. 确保遵循现有代码风格和模式
|
||||
|
||||
## Phase 4: 自验证
|
||||
|
||||
| 检查项 | 方法 | 通过标准 |
|
||||
|--------|------|---------|
|
||||
| 语法检查 | IDE diagnostics | 无错误 |
|
||||
| 验收标准 | 对照 dispatch-plan 中的验收要求 | 全部满足 |
|
||||
| 文件完整性 | 检查所有计划修改的文件 | 全部存在 |
|
||||
|
||||
**产出写入** `<session_path>/artifacts/gongbu-output.md`:
|
||||
```
|
||||
# 工部产出报告
|
||||
## 实现概述 / 修改文件 / 关键决策 / 验收自查
|
||||
```
|
||||
|
||||
**看板流转 + SendMessage**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="gongbu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"gongbu", to_role:"coordinator",
|
||||
remark:"✅ 完成：<实现摘要>"})
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`impl_complete: task=<task_id>, artifact=artifacts/gongbu-output.md`,
|
||||
summary:"工部实现完成"})
|
||||
```
|
||||
|
||||
## 阻塞处理
|
||||
|
||||
```javascript
|
||||
// 遇到无法解决的问题时
|
||||
team_msg(operation="log", session_id=<session_id>, from="gongbu", to="coordinator",
|
||||
type="error", data={state:"Blocked", reason:"<具体阻塞原因>，请求协助"})
|
||||
```
|
||||
57
.claude/skills/team-edict/role-specs/hubu.md
Normal file
57
.claude/skills/team-edict/role-specs/hubu.md
Normal file
@@ -0,0 +1,57 @@
|
||||
---
|
||||
role: hubu
|
||||
prefix: DATA
|
||||
inner_loop: true
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: data_complete
|
||||
progress: data_progress
|
||||
error: error
|
||||
---
|
||||
|
||||
# 户部 — 数据与资源管理
|
||||
|
||||
数据分析、统计汇总、成本分析、资源管理、报表生成。
|
||||
|
||||
## Phase 2: 任务加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="hubu",
|
||||
type="state_update", data={state:"Doing", current_step:"户部开始执行：<数据任务>"})
|
||||
```
|
||||
|
||||
1. 读取当前任务（DATA-* task description）
|
||||
2. 读取 `<session_path>/plan/dispatch-plan.md` 获取任务令
|
||||
|
||||
## Phase 3: 数据分析执行
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="hubu",
|
||||
type="data_progress", data={current:"正在执行：<步骤>", plan:"<步骤1>✅|<步骤2>🔄|<步骤3>"})
|
||||
```
|
||||
|
||||
**执行策略**:
|
||||
```bash
|
||||
# 数据探索和分析
|
||||
ccw cli -p "PURPOSE: <具体数据分析目标>
|
||||
TASK: • 数据采集 • 清洗处理 • 统计分析 • 可视化/报表
|
||||
CONTEXT: @**/*
|
||||
MODE: analysis
|
||||
EXPECTED: 结构化分析报告 + 关键指标" --tool gemini --mode analysis
|
||||
```
|
||||
|
||||
## Phase 4: 产出上报
|
||||
|
||||
**写入** `<session_path>/artifacts/hubu-output.md`
|
||||
|
||||
**看板流转 + SendMessage**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="hubu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"hubu", to_role:"coordinator",
|
||||
remark:"✅ 完成：<数据产出摘要>"})
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`data_complete: task=<task_id>, artifact=artifacts/hubu-output.md`,
|
||||
summary:"户部数据任务完成"})
|
||||
```
|
||||
64
.claude/skills/team-edict/role-specs/libu-hr.md
Normal file
64
.claude/skills/team-edict/role-specs/libu-hr.md
Normal file
@@ -0,0 +1,64 @@
|
||||
---
|
||||
role: libu-hr
|
||||
prefix: HR
|
||||
inner_loop: false
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: hr_complete
|
||||
progress: hr_progress
|
||||
error: error
|
||||
---
|
||||
|
||||
# 吏部 — 人事与能力管理
|
||||
|
||||
Agent管理、技能培训、考核评估、协作规范制定。
|
||||
|
||||
## Phase 2: 任务加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="libu-hr",
|
||||
type="state_update", data={state:"Doing", current_step:"吏部开始执行：<人事任务>"})
|
||||
```
|
||||
|
||||
1. 读取当前任务（HR-* task description）
|
||||
2. 读取 `<session_path>/plan/dispatch-plan.md` 获取任务令
|
||||
|
||||
## Phase 3: 人事任务执行
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="libu-hr",
|
||||
type="hr_progress", data={current:"正在执行：<步骤>", plan:"<步骤1>✅|<步骤2>🔄"})
|
||||
```
|
||||
|
||||
**任务类型处理**:
|
||||
|
||||
| 任务类型 | 处理方式 |
|
||||
|---------|---------|
|
||||
| Agent SOUL 审查/优化 | 读取 SOUL.md，分析后提供改进建议 |
|
||||
| Skill 编写/优化 | 分析现有 skill 模式，生成优化版本 |
|
||||
| 能力基线评估 | CLI 分析，生成评估报告 |
|
||||
| 协作规范制定 | 基于现有模式生成规范文档 |
|
||||
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: <具体人事任务目标>
|
||||
TASK: <具体步骤>
|
||||
CONTEXT: @.claude/agents/**/* @.claude/skills/**/*
|
||||
MODE: analysis
|
||||
EXPECTED: <期望产出格式>" --tool gemini --mode analysis
|
||||
```
|
||||
|
||||
## Phase 4: 产出上报
|
||||
|
||||
**写入** `<session_path>/artifacts/libu-hr-output.md`
|
||||
|
||||
**看板流转 + SendMessage**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="libu-hr", to="coordinator",
|
||||
type="task_handoff", data={from_role:"libu-hr", to_role:"coordinator",
|
||||
remark:"✅ 完成：<人事产出摘要>"})
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`hr_complete: task=<task_id>, artifact=artifacts/libu-hr-output.md`,
|
||||
summary:"吏部人事任务完成"})
|
||||
```
|
||||
56
.claude/skills/team-edict/role-specs/libu.md
Normal file
56
.claude/skills/team-edict/role-specs/libu.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
role: libu
|
||||
prefix: DOC
|
||||
inner_loop: true
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: doc_complete
|
||||
progress: doc_progress
|
||||
error: error
|
||||
---
|
||||
|
||||
# 礼部 — 文档与规范
|
||||
|
||||
文档撰写、规范制定、UI/UX文案、对外沟通、API文档、Release Notes。
|
||||
|
||||
## Phase 2: 任务加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="libu",
|
||||
type="state_update", data={state:"Doing", current_step:"礼部开始执行：<文档任务>"})
|
||||
```
|
||||
|
||||
1. 读取当前任务（DOC-* task description）
|
||||
2. 读取相关代码/实现产出（通常依赖工部产出）
|
||||
3. 读取 `<session_path>/plan/dispatch-plan.md` 获取输出要求
|
||||
|
||||
## Phase 3: 文档生成
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="libu",
|
||||
type="doc_progress", data={current:"正在撰写：<文档章节>", plan:"<章节1>✅|<章节2>🔄|<章节3>"})
|
||||
```
|
||||
|
||||
**执行策略**:
|
||||
|
||||
| 文档类型 | 方法 |
|
||||
|---------|------|
|
||||
| README / API文档 | 读取代码后直接 Write |
|
||||
| 复杂规范/指南 | `ccw cli --tool gemini --mode write` |
|
||||
| 多语言翻译 | `ccw cli --tool qwen --mode write` |
|
||||
|
||||
## Phase 4: 产出上报
|
||||
|
||||
**写入** `<session_path>/artifacts/libu-output.md`
|
||||
|
||||
**看板流转 + SendMessage**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="libu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"libu", to_role:"coordinator",
|
||||
remark:"✅ 完成：<文档产出摘要>"})
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`doc_complete: task=<task_id>, artifact=artifacts/libu-output.md`,
|
||||
summary:"礼部文档任务完成"})
|
||||
```
|
||||
139
.claude/skills/team-edict/role-specs/menxia.md
Normal file
139
.claude/skills/team-edict/role-specs/menxia.md
Normal file
@@ -0,0 +1,139 @@
|
||||
---
|
||||
role: menxia
|
||||
prefix: REVIEW
|
||||
inner_loop: false
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: review_result
|
||||
error: error
|
||||
---
|
||||
|
||||
# 门下省 — 多维审议
|
||||
|
||||
从四个维度并行审议中书省方案，输出准奏/封驳结论。**核心特性：多 CLI 并行分析**。
|
||||
|
||||
## Phase 2: 接旨 + 方案加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="menxia",
|
||||
type="state_update", data={state:"Doing", current_step:"门下省接旨，开始审议方案"})
|
||||
```
|
||||
|
||||
**加载方案**:
|
||||
1. 从 prompt 中提取 `plan_file` 路径（由 coordinator 传入）
|
||||
2. `Read(plan_file)` 获取中书省方案全文
|
||||
3. 若 plan_file 未指定，默认读取 `<session_path>/plan/zhongshu-plan.md`
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="menxia",
|
||||
type="impl_progress", data={current:"方案加载完成，启动多维并行审议",
|
||||
plan:"方案加载✅|可行性审查🔄|完整性审查🔄|风险评估🔄|资源评估🔄|综合结论"})
|
||||
```
|
||||
|
||||
## Phase 3: 多 CLI 并行审议
|
||||
|
||||
**四维并行分析**（同时启动，不等待单个完成）:
|
||||
|
||||
### 维度1 — 可行性审查 (gemini)
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 审查以下方案的技术可行性；成功标准=每个技术路径均有可实现依据
|
||||
TASK: • 验证技术路径是否可实现 • 检查所需依赖是否已具备 • 评估技术风险
|
||||
MODE: analysis
|
||||
CONTEXT: @**/*
|
||||
EXPECTED: 可行性结论（通过/有条件通过/不可行）+ 具体问题列表
|
||||
CONSTRAINTS: 只关注技术可行性，不评估工作量
|
||||
---
|
||||
方案内容：
|
||||
<plan_content>" --tool gemini --mode analysis --rule analysis-review-architecture
|
||||
```
|
||||
|
||||
### 维度2 — 完整性审查 (qwen)
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 审查方案是否覆盖所有需求，识别遗漏；成功标准=每个需求点有对应子任务
|
||||
TASK: • 逐条对比原始需求与子任务清单 • 识别未覆盖的需求 • 检查验收标准是否可量化
|
||||
MODE: analysis
|
||||
CONTEXT: @**/*
|
||||
EXPECTED: 完整性结论（完整/有缺失）+ 遗漏清单
|
||||
CONSTRAINTS: 只关注需求覆盖度，不评估实现方式
|
||||
---
|
||||
原始需求：<requirement>
|
||||
方案子任务：<subtasks_section>" --tool qwen --mode analysis
|
||||
```
|
||||
|
||||
### 维度3 — 风险评估 (gemini, 第二次调用)
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 识别方案中的潜在故障点和风险；成功标准=每个高风险点有对应缓解措施
|
||||
TASK: • 识别技术风险点 • 检查是否有回滚方案 • 评估依赖失败的影响
|
||||
MODE: analysis
|
||||
EXPECTED: 风险矩阵（风险项/概率/影响/缓解措施）
|
||||
---
|
||||
方案内容：
|
||||
<plan_content>" --tool gemini --mode analysis --rule analysis-assess-security-risks
|
||||
```
|
||||
|
||||
### 维度4 — 资源评估 (codex)
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 评估各部门工作量分配是否合理；成功标准=工作量与各部门专长匹配
|
||||
TASK: • 检查子任务与部门专长的匹配度 • 评估工作量是否均衡 • 识别超负荷或空置部门
|
||||
MODE: analysis
|
||||
EXPECTED: 资源分配评估表 + 调整建议
|
||||
CONSTRAINTS: 只关注工作量合理性和部门匹配度
|
||||
---
|
||||
方案子任务：<subtasks_section>" --tool codex --mode analysis
|
||||
```
|
||||
|
||||
**执行策略**: 四个 CLI 调用顺序执行，每个同步等待结果后再启动下一个。
|
||||
|
||||
## Phase 4: 综合结论 + 上报
|
||||
|
||||
**综合审议结果**:
|
||||
|
||||
| 维度 | 结论权重 | 否决条件 |
|
||||
|------|---------|---------|
|
||||
| 可行性 | 30% | 不可行 → 直接封驳 |
|
||||
| 完整性 | 30% | 重大遗漏(核心需求未覆盖) → 封驳 |
|
||||
| 风险 | 25% | 高风险无缓解措施 → 封驳 |
|
||||
| 资源 | 15% | 部门严重错配 → 附带条件准奏 |
|
||||
|
||||
**写入审议报告** `<session_path>/review/menxia-review.md`:
|
||||
```markdown
|
||||
# 门下省审议报告
|
||||
|
||||
## 审议结论：[准奏 ✅ / 封驳 ❌]
|
||||
|
||||
## 四维审议摘要
|
||||
| 维度 | 结论 | 关键发现 |
|
||||
|------|------|---------|
|
||||
| 可行性 | 通过/不通过 | <要点> |
|
||||
| 完整性 | 完整/有缺失 | <遗漏项> |
|
||||
| 风险 | 可控/高风险 | <风险项> |
|
||||
| 资源 | 合理/需调整 | <建议> |
|
||||
|
||||
## 封驳意见（若封驳）
|
||||
<具体需要修改的问题，逐条列出>
|
||||
|
||||
## 附带条件（若有条件准奏）
|
||||
<建议中书省在执行中注意的事项>
|
||||
```
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="menxia",
|
||||
type="impl_progress", data={current:"审议完成，结论：<准奏/封驳>",
|
||||
plan:"方案加载✅|可行性审查✅|完整性审查✅|风险评估✅|资源评估✅|综合结论✅"})
|
||||
```
|
||||
|
||||
**看板流转 + SendMessage 回调**:
|
||||
```javascript
|
||||
// 流转上报
|
||||
team_msg(operation="log", session_id=<session_id>, from="menxia", to="coordinator",
|
||||
type="task_handoff", data={from_role:"menxia", to_role:"coordinator",
|
||||
remark:"<准奏✅/封驳❌>：审议报告见 review/menxia-review.md"})
|
||||
|
||||
// SendMessage 回调
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`review_result: approved=<true/false>, round=<N>, report=review/menxia-review.md`,
|
||||
summary:"门下省审议完成"})
|
||||
```
|
||||
105
.claude/skills/team-edict/role-specs/shangshu.md
Normal file
105
.claude/skills/team-edict/role-specs/shangshu.md
Normal file
@@ -0,0 +1,105 @@
|
||||
---
|
||||
role: shangshu
|
||||
prefix: DISPATCH
|
||||
inner_loop: false
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: dispatch_ready
|
||||
error: error
|
||||
---
|
||||
|
||||
# 尚书省 — 执行调度
|
||||
|
||||
分析准奏方案，按部门职责拆解子任务，生成六部执行调度清单。
|
||||
|
||||
## Phase 2: 接旨 + 方案加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="shangshu",
|
||||
type="state_update", data={state:"Doing", current_step:"尚书省接令，分析准奏方案，准备调度六部"})
|
||||
```
|
||||
|
||||
**加载方案**:
|
||||
1. 读取 `<session_path>/plan/zhongshu-plan.md`（准奏方案）
|
||||
2. 读取 `<session_path>/review/menxia-review.md`（审议报告，含附带条件）
|
||||
3. 解析子任务清单和验收标准
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="shangshu",
|
||||
type="impl_progress", data={current:"方案解析完成，开始路由分析",
|
||||
plan:"方案加载✅|路由分析🔄|任务分解|生成调度令|输出清单"})
|
||||
```
|
||||
|
||||
## Phase 3: 路由分析 + 任务分解
|
||||
|
||||
**六部路由规则**:
|
||||
|
||||
| 关键词信号 | 目标部门 | agent role |
|
||||
|-----------|---------|------------|
|
||||
| 功能开发、架构设计、代码实现、重构、API、接口 | 工部 | gongbu |
|
||||
| 部署、CI/CD、基础设施、容器、性能监控、安全防御 | 兵部 | bingbu |
|
||||
| 数据分析、统计、成本、报表、资源管理、度量 | 户部 | hubu |
|
||||
| 文档、README、UI文案、规范、对外沟通、翻译 | 礼部 | libu |
|
||||
| 测试、QA、Bug定位、代码审查、合规审计 | 刑部 | xingbu |
|
||||
| Agent管理、培训、技能优化、考核、知识库 | 吏部 | libu-hr |
|
||||
|
||||
**对每个子任务**:
|
||||
1. 提取关键词，匹配目标部门
|
||||
2. 若跨部门（如"实现+测试"），拆分为独立子任务
|
||||
3. 分析依赖关系（哪些必须串行，哪些可并行）
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="shangshu",
|
||||
type="impl_progress", data={current:"路由分析完成，生成六部调度令",
|
||||
plan:"方案加载✅|路由分析✅|任务分解✅|生成调度令🔄|输出清单"})
|
||||
```
|
||||
|
||||
## Phase 4: 生成调度清单 + 上报
|
||||
|
||||
**写入调度清单** `<session_path>/plan/dispatch-plan.md`:
|
||||
```markdown
|
||||
# 尚书省调度清单
|
||||
|
||||
## 调度概览
|
||||
- 总子任务数: N
|
||||
- 涉及部门: <部门列表>
|
||||
- 预计并行批次: M 批
|
||||
|
||||
## 调度令
|
||||
|
||||
### 第1批（无依赖，并行执行）
|
||||
#### 工部任务令 (IMPL-001)
|
||||
- **任务**: <具体任务描述>
|
||||
- **输出要求**: <格式/验收标准>
|
||||
- **参考文件**: <如有>
|
||||
|
||||
#### 礼部任务令 (DOC-001)
|
||||
- **任务**: <具体任务描述>
|
||||
- **输出要求**: <格式/验收标准>
|
||||
|
||||
### 第2批（依赖第1批，串行）
|
||||
#### 刑部任务令 (QA-001)
|
||||
- **任务**: 验收工部产出，执行测试
|
||||
- **输出要求**: 测试报告 + 通过/不通过结论
|
||||
- **前置条件**: IMPL-001 完成
|
||||
|
||||
## 汇总验收标准
|
||||
<综合所有部门产出的最终验收指标>
|
||||
|
||||
## 附带条件（来自门下省审议）
|
||||
<门下省要求注意的事项>
|
||||
```
|
||||
|
||||
**看板流转 + SendMessage 回调**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="shangshu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"shangshu", to_role:"coordinator",
|
||||
remark:"✅ 调度清单生成完毕，共<N>个子任务分配给<M>个部门"})
|
||||
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`dispatch_ready: plan=plan/dispatch-plan.md, departments=[<dept_list>], batches=<N>`,
|
||||
summary:"尚书省调度清单就绪"})
|
||||
```
|
||||
85
.claude/skills/team-edict/role-specs/xingbu.md
Normal file
85
.claude/skills/team-edict/role-specs/xingbu.md
Normal file
@@ -0,0 +1,85 @@
|
||||
---
|
||||
role: xingbu
|
||||
prefix: QA
|
||||
inner_loop: true
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: qa_complete
|
||||
progress: qa_progress
|
||||
error: error
|
||||
fix: fix_required
|
||||
---
|
||||
|
||||
# 刑部 — 质量保障
|
||||
|
||||
代码审查、测试验收、Bug定位、合规审计。
|
||||
|
||||
## Phase 2: 任务加载
|
||||
|
||||
**看板上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="xingbu",
|
||||
type="state_update", data={state:"Doing", current_step:"刑部开始执行：<QA任务>"})
|
||||
```
|
||||
|
||||
1. 读取当前任务（QA-* task description）
|
||||
2. 读取 `<session_path>/plan/dispatch-plan.md` 获取验收标准
|
||||
3. 读取 `.claude/skills/team-edict/specs/quality-gates.md` 获取质量门标准
|
||||
4. 读取被测部门（通常为工部）的产出报告
|
||||
|
||||
## Phase 3: 质量审查
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="xingbu",
|
||||
type="qa_progress", data={current:"正在执行：<审查步骤>",
|
||||
plan:"<步骤1>✅|<步骤2>🔄|<步骤3>"})
|
||||
```
|
||||
|
||||
**多 CLI 并行审查**（按任务类型选择）:
|
||||
|
||||
代码审查:
|
||||
```bash
|
||||
ccw cli --tool codex --mode review
|
||||
```
|
||||
|
||||
测试执行:
|
||||
```bash
|
||||
# 检测测试框架并运行
|
||||
ccw cli -p "PURPOSE: 执行测试套件并分析结果
|
||||
TASK: • 识别测试框架 • 运行所有相关测试 • 分析失败原因
|
||||
CONTEXT: @**/*.test.* @**/*.spec.*
|
||||
MODE: analysis" --tool gemini --mode analysis
|
||||
```
|
||||
|
||||
合规审计（如需）:
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 审查代码合规性
|
||||
TASK: • 检查敏感信息暴露 • 权限控制审查 • 日志规范
|
||||
CONTEXT: @**/*
|
||||
MODE: analysis" --tool gemini --mode analysis --rule analysis-assess-security-risks
|
||||
```
|
||||
|
||||
**Test-Fix 循环**（最多3轮）:
|
||||
1. 运行测试 -> 分析结果
|
||||
2. 通过率 >= 95% -> 退出（成功）
|
||||
3. 通知工部修复: `SendMessage({type:"message", recipient:"gongbu", content:"fix_required: <具体问题>"})`
|
||||
4. 等待工部修复 callback -> 重新测试
|
||||
|
||||
## Phase 4: 审查报告
|
||||
|
||||
**写入** `<session_path>/artifacts/xingbu-report.md`:
|
||||
```
|
||||
# 刑部质量报告
|
||||
## 审查结论 (通过/不通过) / 测试结果 / Bug清单 / 合规状态
|
||||
```
|
||||
|
||||
**看板流转 + SendMessage**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="xingbu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"xingbu", to_role:"coordinator",
|
||||
remark:"✅ 完成：质量审查<通过/不通过>，见 xingbu-report.md"})
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:`qa_complete: task=<task_id>, passed=<true/false>, artifact=artifacts/xingbu-report.md`,
|
||||
summary:"刑部质量审查完成"})
|
||||
```
|
||||
116
.claude/skills/team-edict/role-specs/zhongshu.md
Normal file
116
.claude/skills/team-edict/role-specs/zhongshu.md
Normal file
@@ -0,0 +1,116 @@
|
||||
---
|
||||
role: zhongshu
|
||||
prefix: PLAN
|
||||
inner_loop: false
|
||||
discuss_rounds: []
|
||||
message_types:
|
||||
success: plan_ready
|
||||
error: error
|
||||
---
|
||||
|
||||
# 中书省 — 规划起草
|
||||
|
||||
分析旨意，起草结构化执行方案，提交门下省审议。
|
||||
|
||||
## Phase 2: 接旨 + 上下文加载
|
||||
|
||||
**看板上报（必须立即执行）**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="zhongshu",
|
||||
type="state_update", data={state:"Doing", current_step:"中书省接旨，开始分析任务"})
|
||||
```
|
||||
|
||||
**加载上下文**:
|
||||
1. 从 task description 提取 `session_path` 和 `requirement`
|
||||
2. 若存在历史方案（封驳重来）：读取 `<session_path>/review/menxia-review.md` 获取封驳意见
|
||||
3. 执行代码库探索（如涉及代码任务）:
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: 理解当前代码库结构，为任务规划提供上下文
|
||||
TASK: • 识别相关模块 • 理解现有架构 • 找出关键文件
|
||||
CONTEXT: @**/*
|
||||
EXPECTED: 关键文件列表 + 架构概述 + 依赖关系
|
||||
MODE: analysis" --tool gemini --mode analysis
|
||||
```
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="zhongshu",
|
||||
type="impl_progress", data={current:"完成上下文分析，开始起草方案",
|
||||
plan:"上下文分析✅|方案起草🔄|子任务分解|输出方案"})
|
||||
```
|
||||
|
||||
## Phase 3: 起草执行方案
|
||||
|
||||
**方案结构**（写入 `<session_path>/plan/zhongshu-plan.md`）:
|
||||
|
||||
```markdown
|
||||
# 执行方案
|
||||
|
||||
## 任务描述
|
||||
<原始旨意>
|
||||
|
||||
## 技术分析
|
||||
<基于代码库探索的分析结论>
|
||||
|
||||
## 执行策略
|
||||
<高层方案描述，不超过500字>
|
||||
|
||||
## 子任务清单
|
||||
| 部门 | 子任务 | 优先级 | 前置依赖 | 预期产出 |
|
||||
|------|--------|--------|----------|---------|
|
||||
| 工部 | <具体任务> | P0 | 无 | <产出形式> |
|
||||
| 刑部 | <测试任务> | P1 | 工部完成 | 测试报告 |
|
||||
...
|
||||
|
||||
## 验收标准
|
||||
<可量化的成功指标>
|
||||
|
||||
## 风险点
|
||||
<潜在问题和建议回滚方案>
|
||||
```
|
||||
|
||||
**起草原则**:
|
||||
|
||||
| 维度 | 要求 |
|
||||
|------|------|
|
||||
| 技术可行性 | 方案必须基于实际代码库现状 |
|
||||
| 完整性 | 覆盖所有需求点，无遗漏 |
|
||||
| 颗粒度 | 子任务可被具体部门直接执行 |
|
||||
| 风险 | 每个高风险点有回滚方案 |
|
||||
|
||||
**进度上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="zhongshu",
|
||||
type="impl_progress", data={current:"方案起草完成，准备提交审议",
|
||||
plan:"上下文分析✅|方案起草✅|子任务分解✅|输出方案🔄"})
|
||||
```
|
||||
|
||||
## Phase 4: 输出 + 上报
|
||||
|
||||
1. 确认方案文件已写入 `<session_path>/plan/zhongshu-plan.md`
|
||||
2. **看板流转上报**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="zhongshu", to="coordinator",
|
||||
type="task_handoff", data={from_role:"zhongshu", to_role:"coordinator",
|
||||
remark:"✅ 完成：执行方案已起草，含<N>个子任务，提交门下省审议"})
|
||||
```
|
||||
3. **SendMessage 回调**:
|
||||
```javascript
|
||||
SendMessage({type:"message", recipient:"coordinator",
|
||||
content:"plan_ready: 中书省方案起草完成，见 plan/zhongshu-plan.md",
|
||||
summary:"中书省规划完成"})
|
||||
```
|
||||
|
||||
## 错误处理
|
||||
|
||||
| 情况 | 处理 |
|
||||
|------|------|
|
||||
| 任务描述不清晰 | 在方案中列出假设，继续起草 |
|
||||
| 代码库探索超时 | 基于旨意直接起草，标注"待验证" |
|
||||
| 封驳重来（含封驳意见） | 针对封驳意见逐条修改，在方案头部列出修改点 |
|
||||
|
||||
**阻塞上报**（当无法继续时）:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="zhongshu", to="coordinator",
|
||||
type="error", data={state:"Blocked", reason:"<阻塞原因>，请求协助"})
|
||||
```
|
||||
254
.claude/skills/team-edict/roles/coordinator/role.md
Normal file
254
.claude/skills/team-edict/roles/coordinator/role.md
Normal file
@@ -0,0 +1,254 @@
|
||||
# Coordinator — 太子·接旨分拣
|
||||
|
||||
接收用户旨意，判断消息类型，驱动三省六部全流程。
|
||||
|
||||
## Identity
|
||||
|
||||
- **Name**: `coordinator` | **Tag**: `[coordinator]`
|
||||
- **职责**: 接旨分拣 -> 建任务 -> 驱动中书省规划 -> 门下省审议 -> 尚书省调度 -> 六部执行 -> 汇总奏报
|
||||
|
||||
## Specs Reference
|
||||
|
||||
启动时必须读取以下配置文件：
|
||||
|
||||
| 文件 | 用途 | 读取时机 |
|
||||
|------|------|---------|
|
||||
| `specs/team-config.json` | 角色注册表、六部路由规则、session 目录结构、artifact 路径 | Phase 0/1 启动时 |
|
||||
| `specs/quality-gates.md` | 各阶段质量门标准，用于验收判断 | Phase 8 汇总奏报时 |
|
||||
|
||||
```javascript
|
||||
// Phase 0/1 启动时执行
|
||||
Read(".claude/skills/team-edict/specs/team-config.json") // 加载路由规则和artifact路径
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
- 判断用户消息：简单问答直接回复，正式任务建 PLAN-001 走全流程
|
||||
- 创建团队、按依赖链 spawn worker agents
|
||||
- 每个关键节点更新看板状态（team_msg state_update）
|
||||
- 等待 worker callback 后再推进下一阶段
|
||||
- 最终汇总所有六部产出，回奏用户
|
||||
|
||||
### MUST NOT
|
||||
- 自己执行规划、开发、测试工作（委托给三省六部）
|
||||
- 跳过门下省审议直接派发执行
|
||||
- 封驳超过3轮仍强行推进
|
||||
|
||||
---
|
||||
|
||||
## Entry Router
|
||||
|
||||
| 检测条件 | 处理路径 |
|
||||
|---------|---------|
|
||||
| 消息含已知 worker role tag | -> handleCallback |
|
||||
| 参数含 "check" / "status" | -> handleCheck |
|
||||
| 参数含 "resume" / "continue" | -> handleResume |
|
||||
| 存在 active/paused 会话 | -> Phase 0 Resume |
|
||||
| 以上都不满足 | -> Phase 1 新任务 |
|
||||
|
||||
---
|
||||
|
||||
## Phase 0: 会话恢复检查
|
||||
|
||||
1. 扫描 `.workflow/.team/EDT-*/team-session.json` 中 status=active/paused 的会话
|
||||
2. 若找到：展示会话摘要，询问是否恢复
|
||||
3. 恢复：加载会话上下文，跳转到上次中断的阶段
|
||||
4. 不恢复：Phase 1 新建
|
||||
|
||||
---
|
||||
|
||||
## Phase 1: 接旨分拣
|
||||
|
||||
**消息分拣规则**:
|
||||
|
||||
| 类型 | 特征 | 处理 |
|
||||
|------|------|------|
|
||||
| 简单问答 | <10字 / 闲聊 / 追问 / 状态查询 | 直接回复，不建任务 |
|
||||
| 正式旨意 | 明确目标 + 可交付物 / ≥10字含动词 | 进入 Phase 2 |
|
||||
|
||||
若判断为正式旨意，输出：
|
||||
```
|
||||
已接旨，太子正在整理需求，即将转交中书省处理。
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Phase 2: 建队 + 初始化看板
|
||||
|
||||
1. **TeamCreate**: `team_name = "edict"` (或加时间戳区分)
|
||||
2. **创建会话目录**: `.workflow/.team/EDT-<timestamp>/`
|
||||
3. **创建初始看板状态**:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="coordinator",
|
||||
type="state_update", data={
|
||||
state: "Planning",
|
||||
task_title: <提炼的任务标题>,
|
||||
pipeline: "PLAN -> REVIEW -> DISPATCH -> 六部执行"
|
||||
})
|
||||
```
|
||||
4. **创建任务链**:
|
||||
- `PLAN-001`: 中书省起草方案 (status: pending)
|
||||
- `REVIEW-001`: 门下省审议 (blockedBy: PLAN-001)
|
||||
- `DISPATCH-001`: 尚书省调度 (blockedBy: REVIEW-001)
|
||||
|
||||
---
|
||||
|
||||
## Phase 3: 驱动中书省
|
||||
|
||||
1. 更新 PLAN-001 -> in_progress
|
||||
2. **Spawn 中书省 worker**:
|
||||
```javascript
|
||||
Agent({
|
||||
subagent_type: "team-worker",
|
||||
name: "zhongshu",
|
||||
team_name: <team_name>,
|
||||
prompt: `role: zhongshu
|
||||
role_spec: .claude/skills/team-edict/role-specs/zhongshu.md
|
||||
session: <session_path>
|
||||
session_id: <session_id>
|
||||
team_name: <team_name>
|
||||
requirement: <original_requirement>
|
||||
inner_loop: false`,
|
||||
run_in_background: false
|
||||
})
|
||||
```
|
||||
3. 等待 SendMessage callback (type: plan_ready)
|
||||
4. STOP — 等待中书省回调
|
||||
|
||||
---
|
||||
|
||||
## Phase 4: 接收规划 -> 驱动门下省审议
|
||||
|
||||
**当收到 zhongshu 的 plan_ready callback**:
|
||||
|
||||
1. 更新 PLAN-001 -> completed
|
||||
2. 更新 REVIEW-001 -> in_progress
|
||||
3. 记录流转:
|
||||
```javascript
|
||||
team_msg(operation="log", session_id=<session_id>, from="coordinator",
|
||||
type="task_handoff", data={from_role:"zhongshu", to_role:"menxia", remark:"方案提交审议"})
|
||||
```
|
||||
4. **Spawn 门下省 worker** (参数含方案路径):
|
||||
```javascript
|
||||
Agent({
|
||||
subagent_type: "team-worker",
|
||||
name: "menxia",
|
||||
team_name: <team_name>,
|
||||
prompt: `role: menxia
|
||||
role_spec: .claude/skills/team-edict/role-specs/menxia.md
|
||||
session: <session_path>
|
||||
session_id: <session_id>
|
||||
team_name: <team_name>
|
||||
requirement: <original_requirement>
|
||||
plan_file: <session_path>/plan/zhongshu-plan.md
|
||||
inner_loop: false`,
|
||||
run_in_background: false
|
||||
})
|
||||
```
|
||||
5. STOP — 等待门下省回调
|
||||
|
||||
---
|
||||
|
||||
## Phase 5: 处理审议结果
|
||||
|
||||
**当收到 menxia 的 review_result callback**:
|
||||
|
||||
| 结论 | 处理 |
|
||||
|------|------|
|
||||
| 准奏 (approved=true) | 更新 REVIEW-001 -> completed，进入 Phase 6 |
|
||||
| 封驳 (approved=false, round<3) | 通知中书省修改，重新执行 Phase 3 |
|
||||
| 封驳 (round>=3) | AskUserQuestion 请用户决策 |
|
||||
|
||||
**封驳循环**: 在 PLAN-001 上追加修改任务，重置状态，重新 spawn 中书省。
|
||||
|
||||
---
|
||||
|
||||
## Phase 6: 驱动尚书省调度
|
||||
|
||||
1. 更新 DISPATCH-001 -> in_progress
|
||||
2. 记录流转 (menxia -> shangshu)
|
||||
3. **Spawn 尚书省 worker**:
|
||||
```javascript
|
||||
Agent({
|
||||
subagent_type: "team-worker",
|
||||
name: "shangshu",
|
||||
team_name: <team_name>,
|
||||
prompt: `role: shangshu
|
||||
role_spec: .claude/skills/team-edict/role-specs/shangshu.md
|
||||
session: <session_path>
|
||||
session_id: <session_id>
|
||||
team_name: <team_name>
|
||||
requirement: <original_requirement>
|
||||
plan_file: <session_path>/plan/zhongshu-plan.md
|
||||
inner_loop: false`,
|
||||
run_in_background: false
|
||||
})
|
||||
```
|
||||
4. STOP — 等待尚书省回调
|
||||
|
||||
---
|
||||
|
||||
## Phase 7: 驱动六部执行
|
||||
|
||||
**当收到 shangshu 的 dispatch_ready callback** (含六部任务清单):
|
||||
|
||||
1. 更新 DISPATCH-001 -> completed
|
||||
2. 读取尚书省生成的 `<session_path>/plan/dispatch-plan.md`
|
||||
3. 解析六部任务清单，按依赖关系建任务
|
||||
4. **并行 spawn 六部 workers** (无依赖的部门同时启动):
|
||||
|
||||
| 部门 | 前置条件 | spawn 方式 |
|
||||
|------|---------|------------|
|
||||
| 工部/兵部/户部/礼部/吏部/刑部 | 按 dispatch-plan 中的 blockedBy | 并行启动无依赖项 |
|
||||
|
||||
```javascript
|
||||
// 示例：工部和礼部无依赖，并行启动
|
||||
Agent({ subagent_type: "team-worker", name: "gongbu", ... })
|
||||
Agent({ subagent_type: "team-worker", name: "xingbu", ... })
|
||||
```
|
||||
5. 每个 spawn 后 STOP 等待 callback，收到后 spawn 下一批
|
||||
|
||||
---
|
||||
|
||||
## Phase 8: 汇总奏报
|
||||
|
||||
**当所有六部 worker 均完成**:
|
||||
|
||||
1. 收集 `<session_path>/artifacts/` 下所有产出
|
||||
2. 生成汇总奏报 (最终回复):
|
||||
```
|
||||
## 奏报·任务完成
|
||||
|
||||
**任务**: <task_title>
|
||||
**执行路径**: 中书省规划 -> 门下省准奏 -> 尚书省调度 -> 六部执行
|
||||
|
||||
### 各部产出
|
||||
- 工部: <gongbu 产出摘要>
|
||||
- 刑部: <xingbu 测试报告>
|
||||
- ...
|
||||
|
||||
### 质量验收
|
||||
<合并刑部的 QA 报告>
|
||||
```
|
||||
3. TeamDelete
|
||||
4. 回复用户
|
||||
|
||||
---
|
||||
|
||||
## Callback 处理协议
|
||||
|
||||
| Sender | Message Type | 处理 |
|
||||
|--------|-------------|------|
|
||||
| zhongshu | plan_ready | -> Phase 5 (驱动门下省) |
|
||||
| menxia | review_result | -> Phase 5 (处理审议) |
|
||||
| shangshu | dispatch_ready | -> Phase 7 (驱动六部) |
|
||||
| gongbu | impl_complete | -> 标记完成，检查是否全部完成 |
|
||||
| bingbu | ops_complete | -> 标记完成，检查是否全部完成 |
|
||||
| hubu | data_complete | -> 标记完成，检查是否全部完成 |
|
||||
| libu | doc_complete | -> 标记完成，检查是否全部完成 |
|
||||
| libu-hr | hr_complete | -> 标记完成，检查是否全部完成 |
|
||||
| xingbu | qa_complete | -> 标记完成，检查是否全部完成 |
|
||||
| 任意 | error (Blocked) | -> 记录阻塞，AskUserQuestion 或自动协调 |
|
||||
133
.claude/skills/team-edict/specs/quality-gates.md
Normal file
133
.claude/skills/team-edict/specs/quality-gates.md
Normal file
@@ -0,0 +1,133 @@
|
||||
# Quality Gates — team-edict
|
||||
|
||||
看板强制上报、审议质量、执行验收的分级质量门控标准。
|
||||
|
||||
## 质量阈值
|
||||
|
||||
| 门控 | 分数 | 动作 |
|
||||
|------|------|------|
|
||||
| **通过** | >= 80% | 继续下一阶段 |
|
||||
| **警告** | 60-79% | 记录警告，谨慎推进 |
|
||||
| **失败** | < 60% | 必须解决后才能继续 |
|
||||
|
||||
---
|
||||
|
||||
## 各阶段质量门
|
||||
|
||||
### Phase 1: 接旨分拣 (coordinator)
|
||||
|
||||
| 检查项 | 标准 | 严重性 |
|
||||
|--------|------|--------|
|
||||
| 任务分类正确 | 正式旨意/简单问答判断符合规则 | Error |
|
||||
| 任务标题合规 | 10-30字中文概括，无路径/URL/系统元数据 | Error |
|
||||
| Session 创建 | EDT-{slug}-{date} 格式，目录结构完整 | Error |
|
||||
| 初始任务链 | PLAN/REVIEW/DISPATCH 任务创建，依赖正确 | Error |
|
||||
|
||||
### Phase 2: 中书省规划 (zhongshu)
|
||||
|
||||
| 检查项 | 标准 | 严重性 |
|
||||
|--------|------|--------|
|
||||
| 看板上报 | 接任务/进度/完成 三个时机均已上报 | Error |
|
||||
| 方案文件存在 | `plan/zhongshu-plan.md` 已写入 | Error |
|
||||
| 子任务清单完整 | 覆盖所有旨意要点，含部门分配 | Error |
|
||||
| 验收标准可量化 | >= 2 条可验证的成功指标 | Warning |
|
||||
| 风险点识别 | >= 1 条风险及回滚方案 | Warning |
|
||||
|
||||
### Phase 3: 门下省审议 (menxia)
|
||||
|
||||
| 检查项 | 标准 | 严重性 |
|
||||
|--------|------|--------|
|
||||
| 四维分析均完成 | 可行性/完整性/风险/资源均有结论 | Error |
|
||||
| 多CLI全部执行 | gemini×2 + qwen + codex 均调用 | Error |
|
||||
| 审议报告存在 | `review/menxia-review.md` 已写入 | Error |
|
||||
| 结论明确 | 准奏✅ 或 封驳❌ + 具体理由 | Error |
|
||||
| 封驳意见具体 | 逐条列出需修改问题（封驳时必须）| Error（封驳时）|
|
||||
| 看板上报 | 接任务/进度/完成 三个时机均已上报 | Error |
|
||||
|
||||
### Phase 4: 尚书省调度 (shangshu)
|
||||
|
||||
| 检查项 | 标准 | 严重性 |
|
||||
|--------|------|--------|
|
||||
| 调度清单存在 | `plan/dispatch-plan.md` 已写入 | Error |
|
||||
| 每个子任务有部门归属 | 100% 覆盖，无遗漏子任务 | Error |
|
||||
| 依赖关系正确 | 串行依赖标注清晰，并行任务识别正确 | Error |
|
||||
| 看板上报 | 接任务/进度/完成 三个时机均已上报 | Error |
|
||||
|
||||
### Phase 5: 六部执行 (gongbu/bingbu/hubu/libu/libu-hr/xingbu)
|
||||
|
||||
| 检查项 | 标准 | 严重性 |
|
||||
|--------|------|--------|
|
||||
| 看板上报完整 | 接任务/每步进度/完成/阻塞 均正确上报 | Error |
|
||||
| 产出文件存在 | `artifacts/<dept>-output.md` 已写入 | Error |
|
||||
| 验收标准满足 | 对照 dispatch-plan 中的要求逐条验证 | Error |
|
||||
| 阻塞主动上报 | 无法继续时 state=Blocked + reason | Error（阻塞时）|
|
||||
|
||||
### 刑部专项: 质量验收
|
||||
|
||||
| 检查项 | 标准 | 严重性 |
|
||||
|--------|------|--------|
|
||||
| 测试通过率 | >= 95% | Error |
|
||||
| code review | codex review 无 Critical 问题 | Error |
|
||||
| test-fix 循环 | <= 3 轮 | Warning |
|
||||
| QA 报告完整 | 通过/不通过结论 + 问题清单 | Error |
|
||||
|
||||
---
|
||||
|
||||
## 跨阶段一致性检查
|
||||
|
||||
### 封驳循环约束
|
||||
|
||||
| 检查 | 规则 |
|
||||
|------|------|
|
||||
| 封驳轮数 | coordinator 跟踪，超过3轮必须 AskUserQuestion |
|
||||
| 修改覆盖度 | 每轮中书省修改必须回应门下省的所有封驳意见 |
|
||||
| 方案版本 | zhongshu-plan.md 每轮包含"本轮修改点"摘要 |
|
||||
|
||||
### 消息类型一致性
|
||||
|
||||
| Sender | message_type | Coordinator 处理 |
|
||||
|--------|-------------|-----------------|
|
||||
| zhongshu | plan_ready | -> spawn menxia |
|
||||
| menxia | review_result (approved=true) | -> spawn shangshu |
|
||||
| menxia | review_result (approved=false) | -> respawn zhongshu (round++) |
|
||||
| shangshu | dispatch_ready | -> spawn 六部 workers |
|
||||
| 六部 | *_complete | -> 标记完成，检查全部完成 |
|
||||
| 任意 | error (Blocked) | -> 记录，AskUserQuestion 或协调 |
|
||||
|
||||
### Task Prefix 唯一性
|
||||
|
||||
| Role | Prefix | 冲突检查 |
|
||||
|------|--------|---------|
|
||||
| zhongshu | PLAN | ✅ 唯一 |
|
||||
| menxia | REVIEW | ✅ 唯一 |
|
||||
| shangshu | DISPATCH | ✅ 唯一 |
|
||||
| gongbu | IMPL | ✅ 唯一 |
|
||||
| bingbu | OPS | ✅ 唯一 |
|
||||
| hubu | DATA | ✅ 唯一 |
|
||||
| libu | DOC | ✅ 唯一 |
|
||||
| libu-hr | HR | ✅ 唯一 |
|
||||
| xingbu | QA | ✅ 唯一 |
|
||||
|
||||
---
|
||||
|
||||
## 问题分级
|
||||
|
||||
### Error（必须修复）
|
||||
|
||||
- 看板上报缺失（任一强制时机未上报）
|
||||
- 产出文件未写入
|
||||
- 封驳超过3轮未询问用户
|
||||
- 阻塞状态未上报
|
||||
- task prefix 冲突
|
||||
|
||||
### Warning（应当修复）
|
||||
|
||||
- 进度上报粒度不足（步骤描述过于笼统）
|
||||
- 验收标准不可量化
|
||||
- 风险点无回滚方案
|
||||
|
||||
### Info（建议改进）
|
||||
|
||||
- 产出报告缺乏详细摘要
|
||||
- wisdom contributions 未记录
|
||||
- 调度批次可进一步优化并行度
|
||||
180
.claude/skills/team-edict/specs/team-config.json
Normal file
180
.claude/skills/team-edict/specs/team-config.json
Normal file
@@ -0,0 +1,180 @@
|
||||
{
|
||||
"version": "5.0.0",
|
||||
"team_name": "team-edict",
|
||||
"team_display_name": "Team Edict — 三省六部",
|
||||
"description": "完整复刻 Edict 三省六部架构：太子接旨 -> 中书省规划 -> 门下省多CLI审议 -> 尚书省调度 -> 六部并行执行。强制看板状态上报，支持 Blocked 一等公民状态，全流程可观测。",
|
||||
"architecture": "team-worker agent + role-specs + 串行审批链 + 多CLI并行审议",
|
||||
"worker_agent": "team-worker",
|
||||
"session_prefix": "EDT",
|
||||
|
||||
"roles": {
|
||||
"coordinator": {
|
||||
"alias": "太子",
|
||||
"task_prefix": null,
|
||||
"responsibility": "接旨分拣、驱动八阶段流程、封驳循环控制、六部并行调度、最终汇总奏报",
|
||||
"message_types": ["plan_ready", "review_result", "dispatch_ready", "impl_complete", "ops_complete", "data_complete", "doc_complete", "hr_complete", "qa_complete", "error"]
|
||||
},
|
||||
"zhongshu": {
|
||||
"alias": "中书省",
|
||||
"task_prefix": "PLAN",
|
||||
"role_spec": "role-specs/zhongshu.md",
|
||||
"responsibility": "分析旨意、代码库探索（gemini CLI）、起草结构化执行方案",
|
||||
"inner_loop": false,
|
||||
"message_types": ["plan_ready", "error"]
|
||||
},
|
||||
"menxia": {
|
||||
"alias": "门下省",
|
||||
"task_prefix": "REVIEW",
|
||||
"role_spec": "role-specs/menxia.md",
|
||||
"responsibility": "四维并行审议（gemini×2 + qwen + codex）、输出准奏/封驳结论",
|
||||
"inner_loop": false,
|
||||
"multi_cli": {
|
||||
"enabled": true,
|
||||
"dimensions": [
|
||||
{"name": "可行性", "tool": "gemini", "rule": "analysis-review-architecture"},
|
||||
{"name": "完整性", "tool": "qwen"},
|
||||
{"name": "风险评估", "tool": "gemini", "rule": "analysis-assess-security-risks"},
|
||||
{"name": "资源评估", "tool": "codex"}
|
||||
]
|
||||
},
|
||||
"message_types": ["review_result", "error"]
|
||||
},
|
||||
"shangshu": {
|
||||
"alias": "尚书省",
|
||||
"task_prefix": "DISPATCH",
|
||||
"role_spec": "role-specs/shangshu.md",
|
||||
"responsibility": "解析准奏方案、按六部路由规则拆解子任务、生成调度令清单",
|
||||
"inner_loop": false,
|
||||
"message_types": ["dispatch_ready", "error"]
|
||||
},
|
||||
"gongbu": {
|
||||
"alias": "工部",
|
||||
"task_prefix": "IMPL",
|
||||
"role_spec": "role-specs/gongbu.md",
|
||||
"responsibility": "功能开发、架构设计、代码实现、重构优化",
|
||||
"inner_loop": true,
|
||||
"message_types": ["impl_complete", "impl_progress", "error"]
|
||||
},
|
||||
"bingbu": {
|
||||
"alias": "兵部",
|
||||
"task_prefix": "OPS",
|
||||
"role_spec": "role-specs/bingbu.md",
|
||||
"responsibility": "基础设施运维、部署发布、CI/CD、性能监控、安全防御",
|
||||
"inner_loop": true,
|
||||
"message_types": ["ops_complete", "ops_progress", "error"]
|
||||
},
|
||||
"hubu": {
|
||||
"alias": "户部",
|
||||
"task_prefix": "DATA",
|
||||
"role_spec": "role-specs/hubu.md",
|
||||
"responsibility": "数据分析、统计汇总、成本分析、资源管理、报表生成",
|
||||
"inner_loop": true,
|
||||
"message_types": ["data_complete", "data_progress", "error"]
|
||||
},
|
||||
"libu": {
|
||||
"alias": "礼部",
|
||||
"task_prefix": "DOC",
|
||||
"role_spec": "role-specs/libu.md",
|
||||
"responsibility": "文档撰写、规范制定、UI/UX文案、API文档、对外沟通",
|
||||
"inner_loop": true,
|
||||
"message_types": ["doc_complete", "doc_progress", "error"]
|
||||
},
|
||||
"libu-hr": {
|
||||
"alias": "吏部",
|
||||
"task_prefix": "HR",
|
||||
"role_spec": "role-specs/libu-hr.md",
|
||||
"responsibility": "Agent管理、技能培训与优化、考核评估、协作规范制定",
|
||||
"inner_loop": false,
|
||||
"message_types": ["hr_complete", "error"]
|
||||
},
|
||||
"xingbu": {
|
||||
"alias": "刑部",
|
||||
"task_prefix": "QA",
|
||||
"role_spec": "role-specs/xingbu.md",
|
||||
"responsibility": "代码审查、测试验收、Bug定位修复、合规审计（test-fix循环最多3轮）",
|
||||
"inner_loop": true,
|
||||
"message_types": ["qa_complete", "qa_progress", "fix_required", "error"]
|
||||
}
|
||||
},
|
||||
|
||||
"pipeline": {
|
||||
"type": "cascade_with_parallel_execution",
|
||||
"description": "串行审批链 + 六部按依赖并行执行",
|
||||
"stages": [
|
||||
{
|
||||
"stage": 1,
|
||||
"name": "规划",
|
||||
"roles": ["zhongshu"],
|
||||
"blockedBy": []
|
||||
},
|
||||
{
|
||||
"stage": 2,
|
||||
"name": "审议",
|
||||
"roles": ["menxia"],
|
||||
"blockedBy": ["zhongshu"],
|
||||
"retry": {"max_rounds": 3, "on_reject": "respawn zhongshu with feedback"}
|
||||
},
|
||||
{
|
||||
"stage": 3,
|
||||
"name": "调度",
|
||||
"roles": ["shangshu"],
|
||||
"blockedBy": ["menxia"]
|
||||
},
|
||||
{
|
||||
"stage": 4,
|
||||
"name": "执行",
|
||||
"roles": ["gongbu", "bingbu", "hubu", "libu", "libu-hr", "xingbu"],
|
||||
"blockedBy": ["shangshu"],
|
||||
"parallel": true,
|
||||
"note": "实际并行度由 dispatch-plan.md 中的 blockedBy 决定"
|
||||
}
|
||||
],
|
||||
"diagram": "PLAN-001 -> REVIEW-001 -> DISPATCH-001 -> [IMPL/OPS/DATA/DOC/HR/QA 按需并行]"
|
||||
},
|
||||
|
||||
"kanban_protocol": {
|
||||
"description": "所有 worker 强制遵守的看板状态上报规范",
|
||||
"state_machine": ["Pending", "Doing", "Blocked", "Done"],
|
||||
"mandatory_events": [
|
||||
{"event": "接任务时", "type": "state_update", "data": "state=Doing + current_step"},
|
||||
{"event": "每个关键步骤", "type": "impl_progress", "data": "current + plan(步骤1✅|步骤2🔄|步骤3)"},
|
||||
{"event": "完成时", "type": "task_handoff", "data": "from_role -> coordinator + remark"},
|
||||
{"event": "阻塞时", "type": "error", "data": "state=Blocked + reason"}
|
||||
],
|
||||
"implementation": "team_msg(operation='log', session_id=<session_id>, from=<role>, ...)"
|
||||
},
|
||||
|
||||
"routing_rules": {
|
||||
"description": "尚书省六部路由规则",
|
||||
"rules": [
|
||||
{"keywords": ["功能开发", "架构", "代码", "重构", "API", "接口", "实现"], "department": "gongbu"},
|
||||
{"keywords": ["部署", "CI/CD", "基础设施", "容器", "性能监控", "安全防御"], "department": "bingbu"},
|
||||
{"keywords": ["数据分析", "统计", "成本", "报表", "资源管理"], "department": "hubu"},
|
||||
{"keywords": ["文档", "README", "UI文案", "规范", "API文档", "对外沟通"], "department": "libu"},
|
||||
{"keywords": ["测试", "QA", "Bug", "审查", "合规审计"], "department": "xingbu"},
|
||||
{"keywords": ["Agent管理", "培训", "技能优化", "考核"], "department": "libu-hr"}
|
||||
]
|
||||
},
|
||||
|
||||
"session_dirs": {
|
||||
"base": ".workflow/.team/EDT-{slug}-{YYYY-MM-DD}/",
|
||||
"plan": "plan/",
|
||||
"review": "review/",
|
||||
"artifacts": "artifacts/",
|
||||
"kanban": "kanban/",
|
||||
"wisdom": "wisdom/contributions/",
|
||||
"messages": ".msg/"
|
||||
},
|
||||
|
||||
"artifacts": {
|
||||
"zhongshu": "plan/zhongshu-plan.md",
|
||||
"menxia": "review/menxia-review.md",
|
||||
"shangshu": "plan/dispatch-plan.md",
|
||||
"gongbu": "artifacts/gongbu-output.md",
|
||||
"bingbu": "artifacts/bingbu-output.md",
|
||||
"hubu": "artifacts/hubu-output.md",
|
||||
"libu": "artifacts/libu-output.md",
|
||||
"libu-hr": "artifacts/libu-hr-output.md",
|
||||
"xingbu": "artifacts/xingbu-report.md"
|
||||
}
|
||||
}
|
||||
@@ -6,83 +6,78 @@ allowed-tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash
|
||||
|
||||
# Workflow-Lite-Execute
|
||||
|
||||
Complete execution engine: multi-mode input, task grouping, batch execution, code review, and development index update.
|
||||
Execution engine for workflow-lite-plan handoff and standalone task execution.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Flexible task execution command supporting three input modes: in-memory plan (from lite-plan), direct prompt description, or file content. Handles execution orchestration, progress tracking, and optional code review.
|
||||
|
||||
**Core capabilities:**
|
||||
- Multi-mode input (in-memory plan, prompt description, or file path)
|
||||
- Execution orchestration (Agent or Codex) with full context
|
||||
- Live progress tracking via TodoWrite at execution call level
|
||||
- Optional code review with selected tool (Gemini, Agent, or custom)
|
||||
- Context continuity across multiple executions
|
||||
- Intelligent format detection (Enhanced Task JSON vs plain text)
|
||||
|
||||
## Usage
|
||||
|
||||
### Input
|
||||
```
|
||||
<input> Task description string, or path to file (required)
|
||||
```
|
||||
|
||||
### Flags
|
||||
| Flag | Description |
|
||||
|------|-------------|
|
||||
| `--in-memory` | Mode 1: Use executionContext from workflow-lite-plan handoff (via Skill({ skill: "workflow-lite-execute", args: "--in-memory" }) |
|
||||
|
||||
Mode 1 (In-Memory) is triggered by `--in-memory` flag or when `executionContext` global variable is available.
|
||||
|
||||
## Input Modes
|
||||
|
||||
### Mode 1: In-Memory Plan
|
||||
|
||||
**Trigger**: Called by workflow-lite-plan direct handoff after Phase 4 approval (executionContext available)
|
||||
**Trigger**: `--in-memory` flag or `executionContext` global variable available
|
||||
|
||||
**Input Source**: `executionContext` global variable set by workflow-lite-plan
|
||||
|
||||
**Content**: Complete execution context (see Data Structures section)
|
||||
**Behavior**: Skip execution method/code review selection (already chosen in LP-Phase 4), directly proceed with full context (exploration, clarifications, plan artifacts all available)
|
||||
|
||||
**Behavior**:
|
||||
- Skip execution method selection (already set by lite-plan)
|
||||
- Directly proceed to execution with full context
|
||||
- All planning artifacts available (exploration, clarifications, plan)
|
||||
> **Note**: LP-Phase 4 is the single confirmation gate. Mode 1 invocation means user already approved — no further prompts.
|
||||
|
||||
### Mode 2: Prompt Description
|
||||
|
||||
**Trigger**: User calls with task description string
|
||||
**Trigger**: User calls with task description string (e.g., "Add unit tests for auth module")
|
||||
|
||||
**Input**: Simple task description (e.g., "Add unit tests for auth module")
|
||||
**Behavior**: Store prompt as `originalUserInput` → create simple execution plan → run `selectExecutionOptions()` → proceed
|
||||
|
||||
**Behavior**:
|
||||
- Store prompt as `originalUserInput`
|
||||
- Create simple execution plan from prompt
|
||||
- AskUserQuestion: Select execution method (Agent/Codex/Auto)
|
||||
- AskUserQuestion: Select code review tool (Skip/Gemini/Agent/Other)
|
||||
- Proceed to execution with `originalUserInput` included
|
||||
### Mode 3: File Content
|
||||
|
||||
**Trigger**: User calls with file path (ends with .md/.json/.txt)
|
||||
|
||||
**User Interaction**:
|
||||
```javascript
|
||||
const autoYes = workflowPreferences.autoYes
|
||||
|
||||
let userSelection
|
||||
|
||||
if (autoYes) {
|
||||
// Auto mode: Use defaults
|
||||
console.log(`[Auto] Auto-confirming execution:`)
|
||||
console.log(` - Execution method: Auto`)
|
||||
console.log(` - Code review: Skip`)
|
||||
|
||||
userSelection = {
|
||||
execution_method: "Auto",
|
||||
code_review_tool: "Skip"
|
||||
fileContent = Read(filePath)
|
||||
try {
|
||||
jsonData = JSON.parse(fileContent)
|
||||
// plan.json detection: two-layer format with task_ids[]
|
||||
if (jsonData.summary && jsonData.approach && jsonData.task_ids) {
|
||||
planObject = jsonData
|
||||
originalUserInput = jsonData.summary
|
||||
isPlanJson = true
|
||||
const planDir = filePath.replace(/[/\\][^/\\]+$/, '')
|
||||
planObject._loadedTasks = loadTaskFiles(planDir, jsonData.task_ids)
|
||||
} else {
|
||||
originalUserInput = fileContent
|
||||
isPlanJson = false
|
||||
}
|
||||
} else {
|
||||
// Interactive mode: Ask user
|
||||
userSelection = AskUserQuestion({
|
||||
} catch {
|
||||
originalUserInput = fileContent
|
||||
isPlanJson = false
|
||||
}
|
||||
```
|
||||
|
||||
- `isPlanJson === true`: Use `planObject` directly → run `selectExecutionOptions()`
|
||||
- `isPlanJson === false`: Treat as prompt (same as Mode 2)
|
||||
|
||||
### User Selection (Mode 2/3 shared)
|
||||
|
||||
```javascript
|
||||
function selectExecutionOptions() {
|
||||
// autoYes: set by -y flag (standalone only; Mode 1 never reaches here)
|
||||
const autoYes = workflowPreferences?.autoYes ?? false
|
||||
|
||||
if (autoYes) {
|
||||
return { execution_method: "Auto", code_review_tool: "Skip" }
|
||||
}
|
||||
|
||||
return AskUserQuestion({
|
||||
questions: [
|
||||
{
|
||||
question: "Select execution method:",
|
||||
@@ -110,120 +105,17 @@ if (autoYes) {
|
||||
}
|
||||
```
|
||||
|
||||
### Mode 3: File Content
|
||||
## Execution Steps
|
||||
|
||||
**Trigger**: User calls with file path
|
||||
|
||||
**Input**: Path to file containing task description or plan.json
|
||||
|
||||
**Step 1: Read and Detect Format**
|
||||
### Step 1: Initialize & Echo Strategy
|
||||
|
||||
```javascript
|
||||
fileContent = Read(filePath)
|
||||
|
||||
// Attempt JSON parsing
|
||||
try {
|
||||
jsonData = JSON.parse(fileContent)
|
||||
|
||||
// Check if plan.json from workflow-lite-plan session (two-layer format: task_ids[])
|
||||
if (jsonData.summary && jsonData.approach && jsonData.task_ids) {
|
||||
planObject = jsonData
|
||||
originalUserInput = jsonData.summary
|
||||
isPlanJson = true
|
||||
|
||||
// Load tasks from .task/*.json files
|
||||
const planDir = filePath.replace(/[/\\][^/\\]+$/, '') // parent directory
|
||||
planObject._loadedTasks = loadTaskFiles(planDir, jsonData.task_ids)
|
||||
} else {
|
||||
// Valid JSON but not plan.json - treat as plain text
|
||||
originalUserInput = fileContent
|
||||
isPlanJson = false
|
||||
}
|
||||
} catch {
|
||||
// Not valid JSON - treat as plain text prompt
|
||||
originalUserInput = fileContent
|
||||
isPlanJson = false
|
||||
}
|
||||
```
|
||||
|
||||
**Step 2: Create Execution Plan**
|
||||
|
||||
If `isPlanJson === true`:
|
||||
- Use `planObject` directly
|
||||
- User selects execution method and code review
|
||||
|
||||
If `isPlanJson === false`:
|
||||
- Treat file content as prompt (same behavior as Mode 2)
|
||||
- Create simple execution plan from content
|
||||
|
||||
**Step 3: User Interaction**
|
||||
|
||||
- AskUserQuestion: Select execution method (Agent/Codex/Auto)
|
||||
- AskUserQuestion: Select code review tool
|
||||
- Proceed to execution with full context
|
||||
|
||||
## Helper Functions
|
||||
|
||||
```javascript
|
||||
// Load task files from .task/ directory (two-layer format)
|
||||
function loadTaskFiles(planDir, taskIds) {
|
||||
return taskIds.map(id => {
|
||||
const taskPath = `${planDir}/.task/${id}.json`
|
||||
return JSON.parse(Read(taskPath))
|
||||
})
|
||||
}
|
||||
|
||||
// Get tasks array from loaded .task/*.json files
|
||||
function getTasks(planObject) {
|
||||
return planObject._loadedTasks || []
|
||||
}
|
||||
```
|
||||
|
||||
## Execution Process
|
||||
|
||||
```
|
||||
Input Parsing:
|
||||
└─ Decision (mode detection):
|
||||
├─ executionContext exists → Mode 1: Load executionContext → Skip user selection
|
||||
├─ Ends with .md/.json/.txt → Mode 3: Read file → Detect format
|
||||
│ ├─ Valid plan.json → Use planObject → User selects method + review
|
||||
│ └─ Not plan.json → Treat as prompt → User selects method + review
|
||||
└─ Other → Mode 2: Prompt description → User selects method + review
|
||||
|
||||
Execution:
|
||||
├─ Step 1: Initialize result tracking (previousExecutionResults = [])
|
||||
├─ Step 2: Task grouping & batch creation
|
||||
│ ├─ Extract explicit depends_on (no file/keyword inference)
|
||||
│ ├─ Group: independent tasks → per-executor parallel batches (one CLI per batch)
|
||||
│ ├─ Group: dependent tasks → sequential phases (respect dependencies)
|
||||
│ └─ Create TodoWrite list for batches
|
||||
├─ Step 3: Launch execution
|
||||
│ ├─ Phase 1: Independent tasks (⚡ per-executor batches, multi-CLI concurrent)
|
||||
│ └─ Phase 2+: Dependent tasks by dependency order
|
||||
├─ Step 4: Track progress (TodoWrite updates per batch)
|
||||
└─ Step 5: Code review (if codeReviewTool ≠ "Skip")
|
||||
|
||||
Output:
|
||||
└─ Execution complete with results in previousExecutionResults[]
|
||||
```
|
||||
|
||||
## Detailed Execution Steps
|
||||
|
||||
### Step 1: Initialize Execution Tracking
|
||||
|
||||
**Operations**:
|
||||
- Initialize result tracking for multi-execution scenarios
|
||||
- Set up `previousExecutionResults` array for context continuity
|
||||
- **In-Memory Mode**: Echo execution strategy from workflow-lite-plan for transparency
|
||||
|
||||
```javascript
|
||||
// Initialize result tracking
|
||||
previousExecutionResults = []
|
||||
|
||||
// In-Memory Mode: Echo execution strategy (transparency before execution)
|
||||
// Mode 1: echo strategy for transparency
|
||||
if (executionContext) {
|
||||
console.log(`
|
||||
📋 Execution Strategy (from lite-plan):
|
||||
Execution Strategy (from lite-plan):
|
||||
Method: ${executionContext.executionMethod}
|
||||
Review: ${executionContext.codeReviewTool}
|
||||
Tasks: ${getTasks(executionContext.planObject).length}
|
||||
@@ -231,19 +123,24 @@ if (executionContext) {
|
||||
${executionContext.executorAssignments ? ` Assignments: ${JSON.stringify(executionContext.executorAssignments)}` : ''}
|
||||
`)
|
||||
}
|
||||
|
||||
// Helper: load .task/*.json files (two-layer format)
|
||||
function loadTaskFiles(planDir, taskIds) {
|
||||
return taskIds.map(id => JSON.parse(Read(`${planDir}/.task/${id}.json`)))
|
||||
}
|
||||
function getTasks(planObject) {
|
||||
return planObject._loadedTasks || []
|
||||
}
|
||||
```
|
||||
|
||||
### Step 2: Task Grouping & Batch Creation
|
||||
|
||||
**Dependency Analysis & Grouping Algorithm**:
|
||||
```javascript
|
||||
// Use explicit depends_on from plan.json (no inference from file/keywords)
|
||||
// Dependency extraction: explicit depends_on only (no file/keyword inference)
|
||||
function extractDependencies(tasks) {
|
||||
const taskIdToIndex = {}
|
||||
tasks.forEach((t, i) => { taskIdToIndex[t.id] = i })
|
||||
|
||||
return tasks.map((task, i) => {
|
||||
// Only use explicit depends_on from plan.json
|
||||
const deps = (task.depends_on || [])
|
||||
.map(depId => taskIdToIndex[depId])
|
||||
.filter(idx => idx !== undefined && idx < i)
|
||||
@@ -251,184 +148,170 @@ function extractDependencies(tasks) {
|
||||
})
|
||||
}
|
||||
|
||||
// Executor Resolution (used by task grouping below)
|
||||
// 获取任务的 executor（优先使用 executorAssignments，fallback 到全局 executionMethod）
|
||||
// Executor resolution: executorAssignments[taskId] > executionMethod > Auto fallback
|
||||
function getTaskExecutor(task) {
|
||||
const assignments = executionContext?.executorAssignments || {}
|
||||
if (assignments[task.id]) {
|
||||
return assignments[task.id].executor // 'gemini' | 'codex' | 'agent'
|
||||
}
|
||||
// Fallback: 全局 executionMethod 映射
|
||||
if (assignments[task.id]) return assignments[task.id].executor // 'gemini' | 'codex' | 'agent'
|
||||
const method = executionContext?.executionMethod || 'Auto'
|
||||
if (method === 'Agent') return 'agent'
|
||||
if (method === 'Codex') return 'codex'
|
||||
// Auto: 根据复杂度
|
||||
return planObject.complexity === 'Low' ? 'agent' : 'codex'
|
||||
return planObject.complexity === 'Low' ? 'agent' : 'codex' // Auto fallback
|
||||
}
|
||||
|
||||
// 按 executor 分组任务（核心分组组件）
|
||||
function groupTasksByExecutor(tasks) {
|
||||
const groups = { gemini: [], codex: [], agent: [] }
|
||||
tasks.forEach(task => {
|
||||
const executor = getTaskExecutor(task)
|
||||
groups[executor].push(task)
|
||||
})
|
||||
tasks.forEach(task => { groups[getTaskExecutor(task)].push(task) })
|
||||
return groups
|
||||
}
|
||||
|
||||
// Group into batches: per-executor parallel batches (one CLI per batch)
|
||||
// Batch creation: independent → per-executor parallel, dependent → sequential phases
|
||||
function createExecutionCalls(tasks, executionMethod) {
|
||||
const tasksWithDeps = extractDependencies(tasks)
|
||||
const processed = new Set()
|
||||
const calls = []
|
||||
|
||||
// Phase 1: Independent tasks → per-executor batches (multi-CLI concurrent)
|
||||
// Phase 1: Independent tasks → per-executor parallel batches
|
||||
const independentTasks = tasksWithDeps.filter(t => t.dependencies.length === 0)
|
||||
if (independentTasks.length > 0) {
|
||||
const executorGroups = groupTasksByExecutor(independentTasks)
|
||||
let parallelIndex = 1
|
||||
|
||||
for (const [executor, tasks] of Object.entries(executorGroups)) {
|
||||
if (tasks.length === 0) continue
|
||||
tasks.forEach(t => processed.add(t.taskIndex))
|
||||
calls.push({
|
||||
method: executionMethod,
|
||||
executor: executor, // 明确指定 executor
|
||||
executionType: "parallel",
|
||||
method: executionMethod, executor, executionType: "parallel",
|
||||
groupId: `P${parallelIndex++}`,
|
||||
taskSummary: tasks.map(t => t.title).join(' | '),
|
||||
tasks: tasks
|
||||
taskSummary: tasks.map(t => t.title).join(' | '), tasks
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Phase 2: Dependent tasks → sequential/parallel batches (respect dependencies)
|
||||
// Phase 2+: Dependent tasks → respect dependency order
|
||||
let sequentialIndex = 1
|
||||
let remaining = tasksWithDeps.filter(t => !processed.has(t.taskIndex))
|
||||
|
||||
while (remaining.length > 0) {
|
||||
// Find tasks whose dependencies are all satisfied
|
||||
const ready = remaining.filter(t =>
|
||||
t.dependencies.every(d => processed.has(d))
|
||||
)
|
||||
|
||||
if (ready.length === 0) {
|
||||
console.warn('Circular dependency detected, forcing remaining tasks')
|
||||
ready.push(...remaining)
|
||||
}
|
||||
let ready = remaining.filter(t => t.dependencies.every(d => processed.has(d)))
|
||||
if (ready.length === 0) { console.warn('Circular dependency detected, forcing remaining'); ready = [...remaining] }
|
||||
|
||||
if (ready.length > 1) {
|
||||
// Multiple ready tasks → per-executor batches (parallel within this phase)
|
||||
const executorGroups = groupTasksByExecutor(ready)
|
||||
for (const [executor, tasks] of Object.entries(executorGroups)) {
|
||||
if (tasks.length === 0) continue
|
||||
tasks.forEach(t => processed.add(t.taskIndex))
|
||||
calls.push({
|
||||
method: executionMethod,
|
||||
executor: executor,
|
||||
executionType: "parallel",
|
||||
method: executionMethod, executor, executionType: "parallel",
|
||||
groupId: `P${calls.length + 1}`,
|
||||
taskSummary: tasks.map(t => t.title).join(' | '),
|
||||
tasks: tasks
|
||||
taskSummary: tasks.map(t => t.title).join(' | '), tasks
|
||||
})
|
||||
}
|
||||
} else {
|
||||
// Single ready task → sequential batch
|
||||
ready.forEach(t => processed.add(t.taskIndex))
|
||||
calls.push({
|
||||
method: executionMethod,
|
||||
executor: getTaskExecutor(ready[0]),
|
||||
executionType: "sequential",
|
||||
groupId: `S${sequentialIndex++}`,
|
||||
taskSummary: ready[0].title,
|
||||
tasks: ready
|
||||
method: executionMethod, executor: getTaskExecutor(ready[0]),
|
||||
executionType: "sequential", groupId: `S${sequentialIndex++}`,
|
||||
taskSummary: ready[0].title, tasks: ready
|
||||
})
|
||||
}
|
||||
|
||||
remaining = remaining.filter(t => !processed.has(t.taskIndex))
|
||||
}
|
||||
|
||||
return calls
|
||||
}
|
||||
|
||||
executionCalls = createExecutionCalls(getTasks(planObject), executionMethod).map(c => ({ ...c, id: `[${c.groupId}]` }))
|
||||
|
||||
TodoWrite({
|
||||
todos: executionCalls.map(c => ({
|
||||
content: `${c.executionType === "parallel" ? "⚡" : "→"} ${c.id} [${c.executor}] (${c.tasks.length} tasks)`,
|
||||
todos: executionCalls.map((c, i) => ({
|
||||
content: `${c.executionType === "parallel" ? "⚡" : `→ [${i+1}/${executionCalls.filter(x=>x.executionType==="sequential").length}]`} ${c.id} [${c.executor}] ${c.tasks.map(t=>t.id).join(', ')}`,
|
||||
status: "pending",
|
||||
activeForm: `Executing ${c.id} [${c.executor}]`
|
||||
activeForm: `Waiting: ${c.tasks.length} task(s) via ${c.executor}`
|
||||
}))
|
||||
})
|
||||
```
|
||||
|
||||
### Step 3: Launch Execution
|
||||
### Step 3: Launch Execution & Track Progress
|
||||
|
||||
> **⚠️ CHECKPOINT**: Before proceeding, verify Phase 2 execution protocol (Step 3-5) is in active memory. If only a summary remains, re-read `phases/02-lite-execute.md` now.
|
||||
> **CHECKPOINT**: Verify Phase 2 execution protocol (Step 3-5) is in active memory. If only a summary remains, re-read `phases/02-lite-execute.md` now.
|
||||
|
||||
**Executor Resolution**: `getTaskExecutor()` and `groupTasksByExecutor()` defined in Step 2 (Task Grouping).
|
||||
|
||||
**Batch Execution Routing** (根据 batch.executor 字段路由):
|
||||
**Batch Routing** (by `batch.executor` field):
|
||||
```javascript
|
||||
// executeBatch 根据 batch 自身的 executor 字段决定调用哪个 CLI
|
||||
function executeBatch(batch) {
|
||||
const executor = batch.executor || getTaskExecutor(batch.tasks[0])
|
||||
const sessionId = executionContext?.session?.id || 'standalone'
|
||||
const fixedId = `${sessionId}-${batch.groupId}`
|
||||
|
||||
if (executor === 'agent') {
|
||||
// Agent execution (synchronous)
|
||||
return Agent({
|
||||
subagent_type: "code-developer",
|
||||
run_in_background: false,
|
||||
description: batch.taskSummary,
|
||||
prompt: buildExecutionPrompt(batch)
|
||||
})
|
||||
} else if (executor === 'codex') {
|
||||
// Codex CLI (background)
|
||||
return Bash(`ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write --id ${fixedId}`, { run_in_background: true })
|
||||
} else if (executor === 'gemini') {
|
||||
// Gemini CLI (background)
|
||||
return Bash(`ccw cli -p "${buildExecutionPrompt(batch)}" --tool gemini --mode write --id ${fixedId}`, { run_in_background: true })
|
||||
return Agent({ subagent_type: "code-developer", run_in_background: false,
|
||||
description: batch.taskSummary, prompt: buildExecutionPrompt(batch) })
|
||||
} else {
|
||||
// CLI execution (codex/gemini): background with fixed ID
|
||||
const tool = executor // 'codex' | 'gemini'
|
||||
const mode = executor === 'gemini' ? 'analysis' : 'write'
|
||||
const previousCliId = batch.resumeFromCliId || null
|
||||
const cmd = previousCliId
|
||||
? `ccw cli -p "${buildExecutionPrompt(batch)}" --tool ${tool} --mode ${mode} --id ${fixedId} --resume ${previousCliId}`
|
||||
: `ccw cli -p "${buildExecutionPrompt(batch)}" --tool ${tool} --mode ${mode} --id ${fixedId}`
|
||||
return Bash(cmd, { run_in_background: true })
|
||||
// STOP - wait for task hook callback
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**并行执行原则**:
|
||||
- 每个 batch 对应一个独立的 CLI 实例或 Agent 调用
|
||||
- 并行 = 多个 Bash(run_in_background=true) 或多个 Task() 同时发出
|
||||
- 绝不将多个独立任务合并到同一个 CLI prompt 中
|
||||
- Agent 任务不可后台执行（run_in_background=false），但多个 Agent 任务可通过单条消息中的多个 Task() 调用并发
|
||||
**Parallel execution rules**:
|
||||
- Each batch = one independent CLI instance or Agent call
|
||||
- Parallel = multiple Bash(run_in_background=true) or multiple Agent() in single message
|
||||
- Never merge independent tasks into one CLI prompt
|
||||
- Agent: run_in_background=false, but multiple Agent() calls can be concurrent in single message
|
||||
|
||||
**Execution Flow**: Parallel batches concurrently → Sequential batches in order
|
||||
```javascript
|
||||
const parallel = executionCalls.filter(c => c.executionType === "parallel")
|
||||
const sequential = executionCalls.filter(c => c.executionType === "sequential")
|
||||
|
||||
// Phase 1: Launch all parallel batches (single message with multiple tool calls)
|
||||
// Phase 1: All parallel batches (single message, multiple tool calls)
|
||||
if (parallel.length > 0) {
|
||||
TodoWrite({ todos: executionCalls.map(c => ({ status: c.executionType === "parallel" ? "in_progress" : "pending" })) })
|
||||
TodoWrite({ todos: executionCalls.map(c => ({
|
||||
status: c.executionType === "parallel" ? "in_progress" : "pending",
|
||||
activeForm: c.executionType === "parallel" ? `Running [${c.executor}]: ${c.tasks.map(t=>t.id).join(', ')}` : `Blocked by parallel phase`
|
||||
})) })
|
||||
parallelResults = await Promise.all(parallel.map(c => executeBatch(c)))
|
||||
previousExecutionResults.push(...parallelResults)
|
||||
TodoWrite({ todos: executionCalls.map(c => ({ status: parallel.includes(c) ? "completed" : "pending" })) })
|
||||
TodoWrite({ todos: executionCalls.map(c => ({
|
||||
status: parallel.includes(c) ? "completed" : "pending",
|
||||
activeForm: parallel.includes(c) ? `Done [${c.executor}]` : `Ready`
|
||||
})) })
|
||||
}
|
||||
|
||||
// Phase 2: Execute sequential batches one by one
|
||||
// Phase 2: Sequential batches one by one
|
||||
for (const call of sequential) {
|
||||
TodoWrite({ todos: executionCalls.map(c => ({ status: c === call ? "in_progress" : "..." })) })
|
||||
TodoWrite({ todos: executionCalls.map(c => ({
|
||||
status: c === call ? "in_progress" : (c.status === "completed" ? "completed" : "pending"),
|
||||
activeForm: c === call ? `Running [${c.executor}]: ${c.tasks.map(t=>t.id).join(', ')}` : undefined
|
||||
})) })
|
||||
result = await executeBatch(call)
|
||||
previousExecutionResults.push(result)
|
||||
TodoWrite({ todos: executionCalls.map(c => ({ status: "completed" or "pending" })) })
|
||||
TodoWrite({ todos: executionCalls.map(c => ({
|
||||
status: sequential.indexOf(c) <= sequential.indexOf(call) ? "completed" : "pending"
|
||||
})) })
|
||||
}
|
||||
```
|
||||
|
||||
**Resume on Failure**:
|
||||
```javascript
|
||||
if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
|
||||
// fixedId = `${sessionId}-${groupId}` (predictable, no auto-generated timestamps)
|
||||
console.log(`Execution incomplete. Resume: ccw cli -p "Continue" --resume ${fixedId} --tool codex --mode write --id ${fixedId}-retry`)
|
||||
batch.resumeFromCliId = fixedId
|
||||
}
|
||||
```
|
||||
|
||||
Progress tracked at batch level. Icons: ⚡ parallel (concurrent), → sequential (one-by-one).
|
||||
|
||||
### Unified Task Prompt Builder
|
||||
|
||||
**Task Formatting Principle**: Each task is a self-contained checklist. The executor only needs to know what THIS task requires. Same template for Agent and CLI.
|
||||
Each task is a self-contained checklist. Same template for Agent and CLI.
|
||||
|
||||
```javascript
|
||||
function buildExecutionPrompt(batch) {
|
||||
// Task template (6 parts: Files → Why → How → Reference → Risks → Done)
|
||||
const formatTask = (t) => `
|
||||
## ${t.title}
|
||||
|
||||
@@ -437,355 +320,174 @@ function buildExecutionPrompt(batch) {
|
||||
### Files
|
||||
${(t.files || []).map(f => `- **${f.path}** → \`${f.target || ''}\`: ${f.change || (f.changes || []).join(', ') || ''}`).join('\n')}
|
||||
|
||||
${t.rationale ? `
|
||||
### Why this approach (Medium/High)
|
||||
${t.rationale ? `### Why this approach (Medium/High)
|
||||
${t.rationale.chosen_approach}
|
||||
${t.rationale.decision_factors?.length > 0 ? `\nKey factors: ${t.rationale.decision_factors.join(', ')}` : ''}
|
||||
${t.rationale.tradeoffs ? `\nTradeoffs: ${t.rationale.tradeoffs}` : ''}
|
||||
` : ''}
|
||||
${t.rationale.decision_factors?.length > 0 ? `Key factors: ${t.rationale.decision_factors.join(', ')}` : ''}
|
||||
${t.rationale.tradeoffs ? `Tradeoffs: ${t.rationale.tradeoffs}` : ''}` : ''}
|
||||
|
||||
### How to do it
|
||||
${t.description}
|
||||
|
||||
${t.implementation.map(step => `- ${step}`).join('\n')}
|
||||
|
||||
${t.code_skeleton ? `
|
||||
### Code skeleton (High)
|
||||
${t.code_skeleton ? `### Code skeleton (High)
|
||||
${t.code_skeleton.interfaces?.length > 0 ? `**Interfaces**: ${t.code_skeleton.interfaces.map(i => `\`${i.name}\` - ${i.purpose}`).join(', ')}` : ''}
|
||||
${t.code_skeleton.key_functions?.length > 0 ? `\n**Functions**: ${t.code_skeleton.key_functions.map(f => `\`${f.signature}\` - ${f.purpose}`).join(', ')}` : ''}
|
||||
${t.code_skeleton.classes?.length > 0 ? `\n**Classes**: ${t.code_skeleton.classes.map(c => `\`${c.name}\` - ${c.purpose}`).join(', ')}` : ''}
|
||||
` : ''}
|
||||
${t.code_skeleton.key_functions?.length > 0 ? `**Functions**: ${t.code_skeleton.key_functions.map(f => `\`${f.signature}\` - ${f.purpose}`).join(', ')}` : ''}
|
||||
${t.code_skeleton.classes?.length > 0 ? `**Classes**: ${t.code_skeleton.classes.map(c => `\`${c.name}\` - ${c.purpose}`).join(', ')}` : ''}` : ''}
|
||||
|
||||
### Reference
|
||||
- Pattern: ${t.reference?.pattern || 'N/A'}
|
||||
- Files: ${t.reference?.files?.join(', ') || 'N/A'}
|
||||
${t.reference?.examples ? `- Notes: ${t.reference.examples}` : ''}
|
||||
|
||||
${t.risks?.length > 0 ? `
|
||||
### Risk mitigations (High)
|
||||
${t.risks.map(r => `- ${r.description} → **${r.mitigation}**`).join('\n')}
|
||||
` : ''}
|
||||
${t.risks?.length > 0 ? `### Risk mitigations (High)
|
||||
${t.risks.map(r => `- ${r.description} → **${r.mitigation}**`).join('\n')}` : ''}
|
||||
|
||||
### Done when
|
||||
${(t.convergence?.criteria || []).map(c => `- [ ] ${c}`).join('\n')}
|
||||
${(t.test?.success_metrics || []).length > 0 ? `\n**Success metrics**: ${t.test.success_metrics.join(', ')}` : ''}`
|
||||
${(t.test?.success_metrics || []).length > 0 ? `**Success metrics**: ${t.test.success_metrics.join(', ')}` : ''}`
|
||||
|
||||
// Build prompt
|
||||
const sections = []
|
||||
|
||||
if (originalUserInput) sections.push(`## Goal\n${originalUserInput}`)
|
||||
|
||||
sections.push(`## Tasks\n${batch.tasks.map(formatTask).join('\n\n---\n')}`)
|
||||
|
||||
// Context (reference only)
|
||||
const context = []
|
||||
if (previousExecutionResults.length > 0) {
|
||||
if (previousExecutionResults.length > 0)
|
||||
context.push(`### Previous Work\n${previousExecutionResults.map(r => `- ${r.tasksSummary}: ${r.status}`).join('\n')}`)
|
||||
}
|
||||
if (clarificationContext) {
|
||||
if (clarificationContext)
|
||||
context.push(`### Clarifications\n${Object.entries(clarificationContext).map(([q, a]) => `- ${q}: ${a}`).join('\n')}`)
|
||||
}
|
||||
if (executionContext?.planObject?.data_flow?.diagram) {
|
||||
if (executionContext?.planObject?.data_flow?.diagram)
|
||||
context.push(`### Data Flow\n${executionContext.planObject.data_flow.diagram}`)
|
||||
}
|
||||
if (executionContext?.session?.artifacts?.plan) {
|
||||
if (executionContext?.session?.artifacts?.plan)
|
||||
context.push(`### Artifacts\nPlan: ${executionContext.session.artifacts.plan}`)
|
||||
}
|
||||
// Project guidelines (user-defined constraints from /workflow:session:solidify)
|
||||
// Loaded via: ccw spec load --category planning
|
||||
context.push(`### Project Guidelines\n(Loaded via ccw spec load --category planning)`)
|
||||
if (context.length > 0) sections.push(`## Context\n${context.join('\n\n')}`)
|
||||
|
||||
sections.push(`Complete each task according to its "Done when" checklist.`)
|
||||
|
||||
return sections.join('\n\n')
|
||||
}
|
||||
```
|
||||
|
||||
**Option A: Agent Execution**
|
||||
### Step 4: Code Review (Optional)
|
||||
|
||||
When to use:
|
||||
- `getTaskExecutor(task) === "agent"`
|
||||
- 或 `executionMethod = "Agent"` (全局 fallback)
|
||||
- 或 `executionMethod = "Auto" AND complexity = "Low"` (全局 fallback)
|
||||
> **CHECKPOINT**: Verify Phase 2 review protocol is in active memory. If only a summary remains, re-read `phases/02-lite-execute.md` now.
|
||||
|
||||
```javascript
|
||||
Task(
|
||||
subagent_type="code-developer",
|
||||
run_in_background=false,
|
||||
description=batch.taskSummary,
|
||||
prompt=buildExecutionPrompt(batch)
|
||||
)
|
||||
```
|
||||
**Skip Condition**: Only run if `codeReviewTool !== "Skip"`
|
||||
|
||||
**Result Collection**: After completion, collect result following `executionResult` structure (see Data Structures section)
|
||||
|
||||
**Option B: CLI Execution (Codex)**
|
||||
|
||||
When to use:
|
||||
- `getTaskExecutor(task) === "codex"`
|
||||
- 或 `executionMethod = "Codex"` (全局 fallback)
|
||||
- 或 `executionMethod = "Auto" AND complexity = "Medium/High"` (全局 fallback)
|
||||
|
||||
```bash
|
||||
ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write
|
||||
```
|
||||
|
||||
**Execution with fixed IDs** (predictable ID pattern):
|
||||
```javascript
|
||||
// Launch CLI in background, wait for task hook callback
|
||||
// Generate fixed execution ID: ${sessionId}-${groupId}
|
||||
const sessionId = executionContext?.session?.id || 'standalone'
|
||||
const fixedExecutionId = `${sessionId}-${batch.groupId}` // e.g., "implement-auth-2025-12-13-P1"
|
||||
|
||||
// Check if resuming from previous failed execution
|
||||
const previousCliId = batch.resumeFromCliId || null
|
||||
|
||||
// Build command with fixed ID (and optional resume for continuation)
|
||||
const cli_command = previousCliId
|
||||
? `ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId} --resume ${previousCliId}`
|
||||
: `ccw cli -p "${buildExecutionPrompt(batch)}" --tool codex --mode write --id ${fixedExecutionId}`
|
||||
|
||||
// Execute in background, stop output and wait for task hook callback
|
||||
Bash(
|
||||
command=cli_command,
|
||||
run_in_background=true
|
||||
)
|
||||
// STOP HERE - CLI executes in background, task hook will notify on completion
|
||||
```
|
||||
|
||||
**Resume on Failure** (with fixed ID):
|
||||
```javascript
|
||||
// If execution failed or timed out, offer resume option
|
||||
if (bash_result.status === 'failed' || bash_result.status === 'timeout') {
|
||||
console.log(`
|
||||
⚠️ Execution incomplete. Resume available:
|
||||
Fixed ID: ${fixedExecutionId}
|
||||
Lookup: ccw cli detail ${fixedExecutionId}
|
||||
Resume: ccw cli -p "Continue tasks" --resume ${fixedExecutionId} --tool codex --mode write --id ${fixedExecutionId}-retry
|
||||
`)
|
||||
|
||||
// Store for potential retry in same session
|
||||
batch.resumeFromCliId = fixedExecutionId
|
||||
}
|
||||
```
|
||||
|
||||
**Result Collection**: After completion, analyze output and collect result following `executionResult` structure (include `cliExecutionId` for resume capability)
|
||||
|
||||
**Option C: CLI Execution (Gemini)**
|
||||
|
||||
When to use: `getTaskExecutor(task) === "gemini"` (分析类任务)
|
||||
|
||||
```bash
|
||||
# 使用统一的 buildExecutionPrompt，切换 tool 和 mode
|
||||
ccw cli -p "${buildExecutionPrompt(batch)}" --tool gemini --mode analysis --id ${sessionId}-${batch.groupId}
|
||||
```
|
||||
|
||||
### Step 4: Progress Tracking
|
||||
|
||||
Progress tracked at batch level (not individual task level). Icons: ⚡ (parallel, concurrent), → (sequential, one-by-one)
|
||||
|
||||
### Step 5: Code Review (Optional)
|
||||
|
||||
> **⚠️ CHECKPOINT**: Before proceeding, verify Phase 2 review protocol is in active memory. If only a summary remains, re-read `phases/02-lite-execute.md` now.
|
||||
|
||||
**Skip Condition**: Only run if `codeReviewTool ≠ "Skip"`
|
||||
|
||||
**Review Focus**: Verify implementation against plan convergence criteria and test requirements
|
||||
- Read plan.json + .task/*.json for task convergence criteria and test checklist
|
||||
- Check each convergence criterion is fulfilled
|
||||
- Verify success metrics from test field (Medium/High complexity)
|
||||
- Run unit/integration tests specified in test field
|
||||
- Validate code quality and identify issues
|
||||
- Ensure alignment with planned approach and risk mitigations
|
||||
|
||||
**Operations**:
|
||||
- Agent Review: Current agent performs direct review
|
||||
- Gemini Review: Execute gemini CLI with review prompt
|
||||
- Codex Review: Two options - (A) with prompt for complex reviews, (B) `--uncommitted` flag only for quick reviews
|
||||
- Custom tool: Execute specified CLI tool (qwen, etc.)
|
||||
|
||||
**Unified Review Template** (All tools use same standard):
|
||||
|
||||
**Review Criteria**:
|
||||
**Review Criteria** (all tools use same standard):
|
||||
- **Convergence Criteria**: Verify each criterion from task convergence.criteria
|
||||
- **Test Checklist** (Medium/High): Check unit, integration, success_metrics from task test
|
||||
- **Code Quality**: Analyze quality, identify issues, suggest improvements
|
||||
- **Plan Alignment**: Validate implementation matches planned approach and risk mitigations
|
||||
|
||||
**Shared Prompt Template** (used by all CLI tools):
|
||||
**Shared Prompt Template**:
|
||||
```
|
||||
PURPOSE: Code review for implemented changes against plan convergence criteria and test requirements
|
||||
TASK: • Verify plan convergence criteria fulfillment • Check test requirements (unit, integration, success_metrics) • Analyze code quality • Identify issues • Suggest improvements • Validate plan adherence and risk mitigations
|
||||
MODE: analysis
|
||||
CONTEXT: @**/* @{plan.json} @{.task/*.json} [@{exploration.json}] | Memory: Review lite-execute changes against plan requirements including test checklist
|
||||
EXPECTED: Quality assessment with:
|
||||
- Convergence criteria verification (all tasks from .task/*.json)
|
||||
- Test checklist validation (Medium/High: unit, integration, success_metrics)
|
||||
- Issue identification
|
||||
- Recommendations
|
||||
Explicitly check each convergence criterion and test item from .task/*.json files.
|
||||
EXPECTED: Quality assessment with: convergence criteria verification, test checklist validation, issue identification, recommendations. Explicitly check each convergence criterion and test item from .task/*.json.
|
||||
CONSTRAINTS: Focus on plan convergence criteria, test requirements, and plan adherence | analysis=READ-ONLY
|
||||
```
|
||||
|
||||
**Tool-Specific Execution** (Apply shared prompt template above):
|
||||
**Tool-Specific Execution** (apply shared prompt template above):
|
||||
|
||||
```bash
|
||||
# Method 1: Agent Review (current agent)
|
||||
# - Read plan.json: ${executionContext.session.artifacts.plan}
|
||||
# - Apply unified review criteria (see Shared Prompt Template)
|
||||
# - Report findings directly
|
||||
| Tool | Command | Notes |
|
||||
|------|---------|-------|
|
||||
| Agent Review | Current agent reads plan.json + applies review criteria directly | No CLI call |
|
||||
| Gemini Review | `ccw cli -p "[template]" --tool gemini --mode analysis` | Recommended |
|
||||
| Qwen Review | `ccw cli -p "[template]" --tool qwen --mode analysis` | Alternative |
|
||||
| Codex Review (A) | `ccw cli -p "[template]" --tool codex --mode review` | With prompt, for complex reviews |
|
||||
| Codex Review (B) | `ccw cli --tool codex --mode review --uncommitted` | No prompt, quick review |
|
||||
|
||||
# Method 2: Gemini Review (recommended)
|
||||
ccw cli -p "[Shared Prompt Template with artifacts]" --tool gemini --mode analysis
|
||||
# CONTEXT includes: @**/* @${plan.json} [@${exploration.json}]
|
||||
> Codex: `-p` prompt and target flags (`--uncommitted`/`--base`/`--commit`) are **mutually exclusive**.
|
||||
|
||||
# Method 3: Qwen Review (alternative)
|
||||
ccw cli -p "[Shared Prompt Template with artifacts]" --tool qwen --mode analysis
|
||||
# Same prompt as Gemini, different execution engine
|
||||
|
||||
# Method 4: Codex Review (git-aware) - Two mutually exclusive options:
|
||||
|
||||
# Option A: With custom prompt (reviews uncommitted by default)
|
||||
ccw cli -p "[Shared Prompt Template with artifacts]" --tool codex --mode review
|
||||
# Use for complex reviews with specific focus areas
|
||||
|
||||
# Option B: Target flag only (no prompt allowed)
|
||||
ccw cli --tool codex --mode review --uncommitted
|
||||
# Quick review of uncommitted changes without custom instructions
|
||||
|
||||
# ⚠️ IMPORTANT: -p prompt and target flags (--uncommitted/--base/--commit) are MUTUALLY EXCLUSIVE
|
||||
```
|
||||
|
||||
**Multi-Round Review with Fixed IDs**:
|
||||
**Multi-Round Review**:
|
||||
```javascript
|
||||
// Generate fixed review ID
|
||||
const reviewId = `${sessionId}-review`
|
||||
|
||||
// First review pass with fixed ID
|
||||
const reviewResult = Bash(`ccw cli -p "[Review prompt]" --tool gemini --mode analysis --id ${reviewId}`)
|
||||
|
||||
// If issues found, continue review dialog with fixed ID chain
|
||||
const reviewResult = Bash(`ccw cli -p "[template]" --tool gemini --mode analysis --id ${reviewId}`)
|
||||
if (hasUnresolvedIssues(reviewResult)) {
|
||||
// Resume with follow-up questions
|
||||
Bash(`ccw cli -p "Clarify the security concerns you mentioned" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
|
||||
Bash(`ccw cli -p "Clarify concerns" --resume ${reviewId} --tool gemini --mode analysis --id ${reviewId}-followup`)
|
||||
}
|
||||
```
|
||||
|
||||
**Implementation Note**: Replace `[Shared Prompt Template with artifacts]` placeholder with actual template content, substituting:
|
||||
- `@{plan.json}` → `@${executionContext.session.artifacts.plan}`
|
||||
- `[@{exploration.json}]` → exploration files from artifacts (if exists)
|
||||
**Artifact Substitution**: Replace `@{plan.json}` → `@${executionContext.session.artifacts.plan}`, `[@{exploration.json}]` → exploration files from artifacts (if exists).
|
||||
|
||||
### Step 6: Auto-Sync Project State
|
||||
### Step 5: Auto-Sync Project State
|
||||
|
||||
**Trigger**: After all executions complete (regardless of code review)
|
||||
|
||||
**Operation**: Execute `/workflow:session:sync -y "{summary}"` to update both `specs/*.md` and `project-tech.json` in one shot.
|
||||
**Operation**: `/workflow:session:sync -y "{summary}"`
|
||||
|
||||
Summary 取值优先级：`originalUserInput` → `planObject.summary` → git log 自动推断。
|
||||
Summary priority: `originalUserInput` → `planObject.summary` → git log auto-infer.
|
||||
|
||||
## Best Practices
|
||||
### Step 6: Post-Completion Expansion
|
||||
|
||||
**Input Modes**: In-memory (workflow-lite-plan), prompt (standalone), file (JSON/text)
|
||||
**Task Grouping**: Based on explicit depends_on only; independent tasks split by executor, each batch runs as separate CLI instance
|
||||
**Execution**: Independent task batches launch concurrently via single Claude message with multiple tool calls (one tool call per batch)
|
||||
Ask user whether to expand into issues (test/enhance/refactor/doc). Selected items call `/issue:new "{summary} - {dimension}"`.
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Cause | Resolution |
|
||||
|-------|-------|------------|
|
||||
| Missing executionContext | In-memory mode without context | Error: "No execution context found. Only available when called by lite-plan." |
|
||||
| File not found | File path doesn't exist | Error: "File not found: {path}. Check file path." |
|
||||
| Empty file | File exists but no content | Error: "File is empty: {path}. Provide task description." |
|
||||
| Invalid Enhanced Task JSON | JSON missing required fields | Warning: "Missing required fields. Treating as plain text." |
|
||||
| Malformed JSON | JSON parsing fails | Treat as plain text (expected for non-JSON files) |
|
||||
| Execution failure | Agent/Codex crashes | Display error, use fixed ID `${sessionId}-${groupId}` for resume: `ccw cli -p "Continue" --resume <fixed-id> --id <fixed-id>-retry` |
|
||||
| Execution timeout | CLI exceeded timeout | Use fixed ID for resume with extended timeout |
|
||||
| Codex unavailable | Codex not installed | Show installation instructions, offer Agent execution |
|
||||
| Fixed ID not found | Custom ID lookup failed | Check `ccw cli history`, verify date directories |
|
||||
| Error | Resolution |
|
||||
|-------|------------|
|
||||
| Missing executionContext | "No execution context found. Only available when called by lite-plan." |
|
||||
| File not found | "File not found: {path}. Check file path." |
|
||||
| Empty file | "File is empty: {path}. Provide task description." |
|
||||
| Invalid plan JSON | Warning: "Missing required fields. Treating as plain text." |
|
||||
| Malformed JSON | Treat as plain text (expected for non-JSON files) |
|
||||
| Execution failure | Use fixed ID `${sessionId}-${groupId}` for resume |
|
||||
| Execution timeout | Use fixed ID for resume with extended timeout |
|
||||
| Codex unavailable | Show installation instructions, offer Agent execution |
|
||||
| Fixed ID not found | Check `ccw cli history`, verify date directories |
|
||||
|
||||
## Data Structures
|
||||
|
||||
### executionContext (Input - Mode 1)
|
||||
|
||||
Passed from lite-plan via global variable:
|
||||
|
||||
```javascript
|
||||
{
|
||||
planObject: {
|
||||
summary: string,
|
||||
approach: string,
|
||||
task_ids: string[], // Task IDs referencing .task/*.json files
|
||||
task_count: number, // Number of tasks
|
||||
_loadedTasks: [...], // Populated at runtime from .task/*.json files
|
||||
task_ids: string[],
|
||||
task_count: number,
|
||||
_loadedTasks: [...], // populated at runtime from .task/*.json
|
||||
estimated_time: string,
|
||||
recommended_execution: string,
|
||||
complexity: string
|
||||
},
|
||||
// Task file paths (populated for two-layer format)
|
||||
taskFiles: [{id: string, path: string}] | null,
|
||||
explorationsContext: {...} | null, // Multi-angle explorations
|
||||
explorationAngles: string[], // List of exploration angles
|
||||
explorationManifest: {...} | null, // Exploration manifest
|
||||
explorationsContext: {...} | null,
|
||||
explorationAngles: string[],
|
||||
explorationManifest: {...} | null,
|
||||
clarificationContext: {...} | null,
|
||||
executionMethod: "Agent" | "Codex" | "Auto", // 全局默认
|
||||
executionMethod: "Agent" | "Codex" | "Auto",
|
||||
codeReviewTool: "Skip" | "Gemini Review" | "Agent Review" | string,
|
||||
originalUserInput: string,
|
||||
|
||||
// 任务级 executor 分配（优先于 executionMethod）
|
||||
executorAssignments: {
|
||||
executorAssignments: { // per-task override, priority over executionMethod
|
||||
[taskId]: { executor: "gemini" | "codex" | "agent", reason: string }
|
||||
},
|
||||
|
||||
// Session artifacts location (saved by lite-plan)
|
||||
session: {
|
||||
id: string, // Session identifier: {taskSlug}-{shortTimestamp}
|
||||
folder: string, // Session folder path: .workflow/.lite-plan/{session-id}
|
||||
id: string, // {taskSlug}-{shortTimestamp}
|
||||
folder: string, // .workflow/.lite-plan/{session-id}
|
||||
artifacts: {
|
||||
explorations: [{angle, path}], // exploration-{angle}.json paths
|
||||
explorations_manifest: string, // explorations-manifest.json path
|
||||
plan: string // plan.json path (always present)
|
||||
explorations: [{angle, path}],
|
||||
explorations_manifest: string,
|
||||
plan: string // always present
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Artifact Usage**:
|
||||
- Artifact files contain detailed planning context
|
||||
- Pass artifact paths to CLI tools and agents for enhanced context
|
||||
- See execution options below for usage examples
|
||||
|
||||
### executionResult (Output)
|
||||
|
||||
Collected after each execution call completes:
|
||||
|
||||
```javascript
|
||||
{
|
||||
executionId: string, // e.g., "[Agent-1]", "[Codex-1]"
|
||||
executionId: string, // e.g., "[Agent-1]", "[Codex-1]"
|
||||
status: "completed" | "partial" | "failed",
|
||||
tasksSummary: string, // Brief description of tasks handled
|
||||
completionSummary: string, // What was completed
|
||||
keyOutputs: string, // Files created/modified, key changes
|
||||
notes: string, // Important context for next execution
|
||||
fixedCliId: string | null // Fixed CLI execution ID (e.g., "implement-auth-2025-12-13-P1")
|
||||
tasksSummary: string,
|
||||
completionSummary: string,
|
||||
keyOutputs: string,
|
||||
notes: string,
|
||||
fixedCliId: string | null // for resume: ccw cli detail ${fixedCliId}
|
||||
}
|
||||
```
|
||||
|
||||
Appended to `previousExecutionResults` array for context continuity in multi-execution scenarios.
|
||||
|
||||
## Post-Completion Expansion
|
||||
|
||||
**Auto-sync**: 执行 `/workflow:session:sync -y "{summary}"` 更新 specs/*.md + project-tech（Step 6 已触发，此处不重复）。
|
||||
|
||||
完成后询问用户是否扩展为issue(test/enhance/refactor/doc)，选中项调用 `/issue:new "{summary} - {dimension}"`
|
||||
|
||||
**Fixed ID Pattern**: `${sessionId}-${groupId}` enables predictable lookup without auto-generated timestamps.
|
||||
|
||||
**Resume Usage**: If `status` is "partial" or "failed", use `fixedCliId` to resume:
|
||||
```bash
|
||||
# Lookup previous execution
|
||||
ccw cli detail ${fixedCliId}
|
||||
|
||||
# Resume with new fixed ID for retry
|
||||
ccw cli -p "Continue from where we left off" --resume ${fixedCliId} --tool codex --mode write --id ${fixedCliId}-retry
|
||||
// Appended to previousExecutionResults[] for context continuity
|
||||
```
|
||||
|
||||
@@ -6,29 +6,13 @@ allowed-tools: Skill, Agent, AskUserQuestion, TodoWrite, Read, Write, Edit, Bash
|
||||
|
||||
# Workflow-Lite-Plan
|
||||
|
||||
Complete planning pipeline: task analysis, multi-angle exploration, clarification, adaptive planning, confirmation, and execution handoff.
|
||||
Planning pipeline: explore → clarify → plan → confirm → handoff to lite-execute.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Intelligent lightweight planning command with dynamic workflow adaptation based on task complexity. Focuses on planning phases (exploration, clarification, planning, confirmation) and delegates execution to workflow-lite-execute skill.
|
||||
|
||||
**Core capabilities:**
|
||||
- Intelligent task analysis with automatic exploration detection
|
||||
- Dynamic code exploration (cli-explore-agent) when codebase understanding needed
|
||||
- Interactive clarification after exploration to gather missing information
|
||||
- Adaptive planning: Low complexity → Direct Claude; Medium/High → cli-lite-planning-agent
|
||||
- Two-step confirmation: plan display → multi-dimensional input collection
|
||||
- Execution handoff with complete context to workflow-lite-execute
|
||||
|
||||
## Context Isolation
|
||||
|
||||
> **⚠️ CRITICAL**: If this phase was invoked from analyze-with-file (via "执行任务"),
|
||||
> the analyze-with-file session is **COMPLETE** and all its phase instructions
|
||||
> are FINISHED and MUST NOT be referenced.
|
||||
> Only follow the LP-Phase 1-5 defined in THIS document (01-lite-plan.md).
|
||||
> Phase numbers in this document are INDEPENDENT of any prior workflow.
|
||||
> **CRITICAL**: If invoked from analyze-with-file (via "执行任务"), the analyze-with-file session is **COMPLETE** and all its phase instructions are FINISHED and MUST NOT be referenced. Only follow LP-Phase 1-5 defined in THIS document. Phase numbers are INDEPENDENT of any prior workflow.
|
||||
|
||||
## Input
|
||||
|
||||
@@ -36,14 +20,12 @@ Intelligent lightweight planning command with dynamic workflow adaptation based
|
||||
<task-description> Task description or path to .md file (required)
|
||||
```
|
||||
|
||||
### Flags
|
||||
|
||||
| Flag | Description |
|
||||
|------|-------------|
|
||||
| `-y`, `--yes` | Auto mode: Skip clarification, auto-confirm plan, auto-select execution, skip review |
|
||||
| `-y`, `--yes` | Auto mode: Skip clarification, auto-confirm plan, auto-select execution, skip review (entire plan+execute workflow) |
|
||||
| `--force-explore` | Force code exploration even when task has prior analysis |
|
||||
|
||||
Workflow preferences (`autoYes`, `forceExplore`) are collected by SKILL.md via AskUserQuestion and passed as `workflowPreferences` context variable.
|
||||
**Note**: Workflow preferences (`autoYes`, `forceExplore`) must be initialized at skill start. If not provided by caller, skill will prompt user for workflow mode selection.
|
||||
|
||||
## Output Artifacts
|
||||
|
||||
@@ -57,88 +39,68 @@ Workflow preferences (`autoYes`, `forceExplore`) are collected by SKILL.md via A
|
||||
|
||||
**Output Directory**: `.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/`
|
||||
|
||||
**Agent Usage**:
|
||||
- Low complexity → Direct Claude planning (no agent)
|
||||
- Medium/High complexity → `cli-lite-planning-agent` generates `plan.json`
|
||||
**Agent Usage**: Low → Direct Claude planning (no agent) | Medium/High → `cli-lite-planning-agent`
|
||||
|
||||
**Schema Reference**: `~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json`
|
||||
|
||||
## Auto Mode Defaults
|
||||
|
||||
When `workflowPreferences.autoYes === true`:
|
||||
- **Clarification Questions**: Skipped (no clarification phase)
|
||||
- **Plan Confirmation**: Auto-selected "Allow"
|
||||
- **Execution Method**: Auto-selected "Auto"
|
||||
- **Code Review**: Auto-selected "Skip"
|
||||
When `workflowPreferences.autoYes === true` (entire plan+execute workflow):
|
||||
- **Clarification**: Skipped | **Plan Confirmation**: Allow & Execute | **Execution**: Auto | **Review**: Skip
|
||||
|
||||
## Execution Process
|
||||
Auto mode authorizes the complete plan-and-execute workflow with a single confirmation. No further prompts.
|
||||
|
||||
```
|
||||
LP-Phase 1: Task Analysis & Exploration
|
||||
├─ Parse input (description or .md file)
|
||||
├─ intelligent complexity assessment (Low/Medium/High)
|
||||
├─ Exploration decision (auto-detect or workflowPreferences.forceExplore)
|
||||
├─ Context protection: If file reading ≥50k chars → force cli-explore-agent
|
||||
└─ Decision:
|
||||
├─ needsExploration=true → Launch parallel cli-explore-agents (1-4 based on complexity)
|
||||
└─ needsExploration=false → Skip to LP-Phase 2/3
|
||||
## Phase Summary
|
||||
|
||||
LP-Phase 2: Clarification (optional, multi-round)
|
||||
├─ Aggregate clarification_needs from all exploration angles
|
||||
├─ Deduplicate similar questions
|
||||
└─ Decision:
|
||||
├─ Has clarifications → AskUserQuestion (max 4 questions per round, multiple rounds allowed)
|
||||
└─ No clarifications → Skip to LP-Phase 3
|
||||
|
||||
LP-Phase 3: Planning (NO CODE EXECUTION - planning only)
|
||||
└─ Decision (based on LP-Phase 1 complexity):
|
||||
├─ Low → Load schema: cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json → Direct Claude planning (following schema) → plan.json
|
||||
└─ Medium/High → cli-lite-planning-agent → plan.json (agent internally executes quality check)
|
||||
|
||||
LP-Phase 4: Confirmation & Selection
|
||||
├─ Display plan summary (tasks, complexity, estimated time)
|
||||
└─ AskUserQuestion:
|
||||
├─ Confirm: Allow / Modify / Cancel
|
||||
├─ Execution: Agent / Codex / Auto
|
||||
└─ Review: Gemini / Agent / Skip
|
||||
|
||||
LP-Phase 5: Execute
|
||||
├─ Build executionContext (plan + explorations + clarifications + selections)
|
||||
└─ Direct handoff: Skill("lite-execute") → Execute with executionContext (Mode 1)
|
||||
```
|
||||
| Phase | Core Action | Output |
|
||||
|-------|-------------|--------|
|
||||
| LP-0 | Initialize workflowPreferences | autoYes, forceExplore |
|
||||
| LP-1 | Complexity assessment → parallel cli-explore-agents (1-4) | exploration-*.json + manifest |
|
||||
| LP-2 | Aggregate + dedup clarification_needs → multi-round AskUserQuestion | clarificationContext (in-memory) |
|
||||
| LP-3 | Low: Direct Claude planning / Medium+High: cli-lite-planning-agent | plan.json + .task/TASK-*.json |
|
||||
| LP-4 | Display plan → AskUserQuestion (Confirm + Execution + Review) | userSelection |
|
||||
| LP-5 | Build executionContext → Skill("lite-execute") | handoff (Mode 1) |
|
||||
|
||||
## Implementation
|
||||
|
||||
### LP-Phase 0: Workflow Preferences Initialization
|
||||
|
||||
```javascript
|
||||
if (typeof workflowPreferences === 'undefined' || workflowPreferences === null) {
|
||||
workflowPreferences = {
|
||||
autoYes: false, // false: show LP-Phase 2/4 prompts | true (-y): skip all prompts
|
||||
forceExplore: false
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### LP-Phase 1: Intelligent Multi-Angle Exploration
|
||||
|
||||
**Session Setup** (MANDATORY - follow exactly):
|
||||
**Session Setup** (MANDATORY):
|
||||
```javascript
|
||||
// Helper: Get UTC+8 (China Standard Time) ISO string
|
||||
const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
|
||||
|
||||
const taskSlug = task_description.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
|
||||
const dateStr = getUtc8ISOString().substring(0, 10) // Format: 2025-11-29
|
||||
|
||||
const sessionId = `${taskSlug}-${dateStr}` // e.g., "implement-jwt-refresh-2025-11-29"
|
||||
const dateStr = getUtc8ISOString().substring(0, 10)
|
||||
const sessionId = `${taskSlug}-${dateStr}`
|
||||
const sessionFolder = `.workflow/.lite-plan/${sessionId}`
|
||||
|
||||
bash(`mkdir -p ${sessionFolder} && test -d ${sessionFolder} && echo "SUCCESS: ${sessionFolder}" || echo "FAILED: ${sessionFolder}"`)
|
||||
```
|
||||
|
||||
**TodoWrite (LP-Phase 1 start)**:
|
||||
**TodoWrite Template** (initial state — subsequent phases update status progressively):
|
||||
```javascript
|
||||
// Pattern: set phases[0..N-1].status="completed", phases[N].status="in_progress"
|
||||
// Only full block shown here; subsequent updates follow same structure with status changes
|
||||
TodoWrite({ todos: [
|
||||
{ content: "LP-Phase 1: Exploration", status: "in_progress", activeForm: "Exploring codebase" },
|
||||
{ content: "LP-Phase 2: Clarification", status: "pending", activeForm: "Collecting clarifications" },
|
||||
{ content: "LP-Phase 3: Planning", status: "pending", activeForm: "Generating plan" },
|
||||
{ content: "LP-Phase 4: Confirmation", status: "pending", activeForm: "Awaiting confirmation" },
|
||||
{ content: "LP-Phase 5: Execution", status: "pending", activeForm: "Executing tasks" }
|
||||
{ content: `LP-Phase 1: Exploration [${complexity}] ${selectedAngles.length} angles`, status: "in_progress", activeForm: `Exploring: ${selectedAngles.join(', ')}` },
|
||||
{ content: "LP-Phase 2: Clarification", status: "pending" },
|
||||
{ content: `LP-Phase 3: Planning [${planningStrategy}]`, status: "pending" },
|
||||
{ content: "LP-Phase 4: Confirmation", status: "pending" },
|
||||
{ content: "LP-Phase 5: Execution", status: "pending" }
|
||||
]})
|
||||
```
|
||||
|
||||
**Exploration Decision Logic**:
|
||||
```javascript
|
||||
// Check if task description already contains prior analysis context (from analyze-with-file)
|
||||
const hasPriorAnalysis = /##\s*Prior Analysis/i.test(task_description)
|
||||
|
||||
needsExploration = workflowPreferences.forceExplore ? true
|
||||
@@ -149,33 +111,21 @@ needsExploration = workflowPreferences.forceExplore ? true
|
||||
task.modifies_existing_code)
|
||||
|
||||
if (!needsExploration) {
|
||||
// Skip exploration — analysis context already in task description (or not needed)
|
||||
// manifest is absent; LP-Phase 3 loads it with safe fallback
|
||||
// manifest absent; LP-Phase 3 loads with safe fallback
|
||||
proceed_to_next_phase()
|
||||
}
|
||||
```
|
||||
|
||||
**⚠️ Context Protection**: File reading ≥50k chars → force `needsExploration=true` (delegate to cli-explore-agent)
|
||||
**Context Protection**: File reading >=50k chars → force `needsExploration=true` (delegate to cli-explore-agent)
|
||||
|
||||
**Complexity Assessment** (Intelligent Analysis):
|
||||
**Complexity Assessment**:
|
||||
```javascript
|
||||
// analyzes task complexity based on:
|
||||
// - Scope: How many systems/modules are affected?
|
||||
// - Depth: Surface change vs architectural impact?
|
||||
// - Risk: Potential for breaking existing functionality?
|
||||
// - Dependencies: How interconnected is the change?
|
||||
|
||||
const complexity = analyzeTaskComplexity(task_description)
|
||||
// Returns: 'Low' | 'Medium' | 'High'
|
||||
// Low: ONLY truly trivial — single file, single function, zero cross-module impact, no new patterns
|
||||
// Examples: fix typo, rename variable, add log line, adjust constant value
|
||||
// Medium: Multiple files OR any integration point OR new pattern introduction OR moderate risk
|
||||
// Examples: add endpoint, implement feature, refactor module, fix bug spanning files
|
||||
// High: Cross-module, architectural, or systemic change
|
||||
// Examples: new subsystem, migration, security overhaul, API redesign
|
||||
// ⚠️ Default bias: When uncertain between Low and Medium, choose Medium
|
||||
// 'Low': single file, single function, zero cross-module impact (fix typo, rename var, adjust constant)
|
||||
// 'Medium': multiple files OR integration point OR new pattern (add endpoint, implement feature, refactor)
|
||||
// 'High': cross-module, architectural, systemic (new subsystem, migration, security overhaul)
|
||||
// Default bias: uncertain between Low/Medium → choose Medium
|
||||
|
||||
// Angle assignment based on task type (orchestrator decides, not agent)
|
||||
const ANGLE_PRESETS = {
|
||||
architecture: ['architecture', 'dependencies', 'modularity', 'integration-points'],
|
||||
security: ['security', 'auth-patterns', 'dataflow', 'validation'],
|
||||
@@ -186,59 +136,39 @@ const ANGLE_PRESETS = {
|
||||
|
||||
function selectAngles(taskDescription, count) {
|
||||
const text = taskDescription.toLowerCase()
|
||||
let preset = 'feature' // default
|
||||
|
||||
let preset = 'feature'
|
||||
if (/refactor|architect|restructure|modular/.test(text)) preset = 'architecture'
|
||||
else if (/security|auth|permission|access/.test(text)) preset = 'security'
|
||||
else if (/performance|slow|optimi|cache/.test(text)) preset = 'performance'
|
||||
else if (/fix|bug|error|issue|broken/.test(text)) preset = 'bugfix'
|
||||
|
||||
return ANGLE_PRESETS[preset].slice(0, count)
|
||||
}
|
||||
|
||||
const selectedAngles = selectAngles(task_description, complexity === 'High' ? 4 : (complexity === 'Medium' ? 3 : 1))
|
||||
|
||||
// Planning strategy determination
|
||||
// Agent trigger: anything beyond trivial single-file change
|
||||
// - hasPriorAnalysis → always agent (analysis validated non-trivial task)
|
||||
// - multi-angle exploration → agent (complexity warranted multiple angles)
|
||||
// - Medium/High complexity → agent
|
||||
// Direct Claude planning ONLY for truly trivial Low + no analysis + single angle
|
||||
// Direct Claude planning ONLY for: Low + no prior analysis + single angle
|
||||
const planningStrategy = (
|
||||
complexity === 'Low' && !hasPriorAnalysis && selectedAngles.length <= 1
|
||||
) ? 'Direct Claude Planning'
|
||||
: 'cli-lite-planning-agent'
|
||||
) ? 'Direct Claude Planning' : 'cli-lite-planning-agent'
|
||||
|
||||
console.log(`
|
||||
## Exploration Plan
|
||||
|
||||
Task Complexity: ${complexity}
|
||||
Selected Angles: ${selectedAngles.join(', ')}
|
||||
Planning Strategy: ${planningStrategy}
|
||||
|
||||
Launching ${selectedAngles.length} parallel explorations...
|
||||
`)
|
||||
console.log(`Exploration Plan: ${complexity} | ${selectedAngles.join(', ')} | ${planningStrategy}`)
|
||||
```
|
||||
|
||||
**Launch Parallel Explorations** - Orchestrator assigns angle to each agent:
|
||||
|
||||
**⚠️ CRITICAL - NO BACKGROUND EXECUTION**:
|
||||
- **MUST NOT use `run_in_background: true`** - exploration results are REQUIRED before planning
|
||||
**Launch Parallel Explorations**:
|
||||
|
||||
**CRITICAL**: MUST NOT use `run_in_background: true` — exploration results are REQUIRED before planning.
|
||||
|
||||
```javascript
|
||||
// Launch agents with pre-assigned angles
|
||||
const explorationTasks = selectedAngles.map((angle, index) =>
|
||||
Task(
|
||||
subagent_type="cli-explore-agent",
|
||||
run_in_background=false, // ⚠️ MANDATORY: Must wait for results
|
||||
run_in_background=false,
|
||||
description=`Explore: ${angle}`,
|
||||
prompt=`
|
||||
## Task Objective
|
||||
Execute **${angle}** exploration for task planning context. Analyze codebase from this specific angle to discover relevant structure, patterns, and constraints.
|
||||
Execute **${angle}** exploration for task planning context.
|
||||
|
||||
## Output Location
|
||||
|
||||
**Session Folder**: ${sessionFolder}
|
||||
**Output File**: ${sessionFolder}/exploration-${angle}.json
|
||||
|
||||
@@ -247,9 +177,6 @@ Execute **${angle}** exploration for task planning context. Analyze codebase fro
|
||||
- **Task Description**: ${task_description}
|
||||
- **Exploration Index**: ${index + 1} of ${selectedAngles.length}
|
||||
|
||||
## Agent Initialization
|
||||
cli-explore-agent autonomously handles: project structure discovery, schema loading, project context loading (project-tech.json, specs/*.md), and keyword search. These steps execute automatically.
|
||||
|
||||
## Exploration Strategy (${angle} focus)
|
||||
|
||||
**Step 1: Structural Scan** (Bash)
|
||||
@@ -267,11 +194,7 @@ cli-explore-agent autonomously handles: project structure discovery, schema load
|
||||
- Identify ${angle}-specific clarification needs
|
||||
|
||||
## Expected Output
|
||||
|
||||
**Schema Reference**: explore-json-schema.json (auto-loaded by agent during initialization)
|
||||
|
||||
**Required Fields** (all ${angle} focused):
|
||||
- Follow explore-json-schema.json exactly (auto-loaded by agent)
|
||||
**Schema**: explore-json-schema.json (auto-loaded by agent)
|
||||
- All fields scoped to ${angle} perspective
|
||||
- Ensure rationale is specific and >10 chars (not generic)
|
||||
- Include file:line locations in integration_points
|
||||
@@ -279,16 +202,12 @@ cli-explore-agent autonomously handles: project structure discovery, schema load
|
||||
|
||||
## Success Criteria
|
||||
- [ ] get_modules_by_depth.sh executed
|
||||
- [ ] At least 3 relevant files identified with specific rationale + role
|
||||
- [ ] Every file has rationale >10 chars (not generic like "Related to ${angle}")
|
||||
- [ ] Every file has role classification (modify_target/dependency/etc.)
|
||||
- [ ] At least 3 relevant files with specific rationale (>10 chars) + role classification
|
||||
- [ ] Patterns are actionable (code examples, not generic advice)
|
||||
- [ ] Integration points include file:line locations
|
||||
- [ ] Constraints are project-specific to ${angle}
|
||||
- [ ] JSON output follows schema exactly
|
||||
- [ ] clarification_needs includes options + recommended
|
||||
- [ ] Files with relevance >= 0.7 have key_code array describing key symbols
|
||||
- [ ] Files with relevance >= 0.7 have topic_relation explaining connection to ${angle}
|
||||
- [ ] JSON follows schema; clarification_needs includes options + recommended
|
||||
- [ ] Files with relevance >= 0.7 have key_code array + topic_relation
|
||||
|
||||
## Execution
|
||||
**Write**: \`${sessionFolder}/exploration-${angle}.json\`
|
||||
@@ -296,30 +215,25 @@ cli-explore-agent autonomously handles: project structure discovery, schema load
|
||||
`
|
||||
)
|
||||
)
|
||||
|
||||
// Execute all exploration tasks in parallel
|
||||
```
|
||||
|
||||
**Auto-discover Generated Exploration Files**:
|
||||
**Auto-discover & Build Manifest**:
|
||||
```javascript
|
||||
// After explorations complete, auto-discover all exploration-*.json files
|
||||
const explorationFiles = bash(`find ${sessionFolder} -name "exploration-*.json" -type f`)
|
||||
.split('\n')
|
||||
.filter(f => f.trim())
|
||||
.split('\n').filter(f => f.trim())
|
||||
|
||||
// Read metadata to build manifest
|
||||
const explorationManifest = {
|
||||
session_id: sessionId,
|
||||
task_description: task_description,
|
||||
timestamp: getUtc8ISOString(),
|
||||
complexity: complexity,
|
||||
exploration_count: explorationCount,
|
||||
exploration_count: explorationFiles.length,
|
||||
explorations: explorationFiles.map(file => {
|
||||
const data = JSON.parse(Read(file))
|
||||
const filename = path.basename(file)
|
||||
return {
|
||||
angle: data._metadata.exploration_angle,
|
||||
file: filename,
|
||||
file: path.basename(file),
|
||||
path: file,
|
||||
index: data._metadata.exploration_index
|
||||
}
|
||||
@@ -327,34 +241,12 @@ const explorationManifest = {
|
||||
}
|
||||
|
||||
Write(`${sessionFolder}/explorations-manifest.json`, JSON.stringify(explorationManifest, null, 2))
|
||||
|
||||
console.log(`
|
||||
## Exploration Complete
|
||||
|
||||
Generated exploration files in ${sessionFolder}:
|
||||
${explorationManifest.explorations.map(e => `- exploration-${e.angle}.json (angle: ${e.angle})`).join('\n')}
|
||||
|
||||
Manifest: explorations-manifest.json
|
||||
Angles explored: ${explorationManifest.explorations.map(e => e.angle).join(', ')}
|
||||
`)
|
||||
console.log(`Exploration complete: ${explorationManifest.explorations.map(e => e.angle).join(', ')}`)
|
||||
```
|
||||
|
||||
**TodoWrite (LP-Phase 1 complete)**:
|
||||
```javascript
|
||||
TodoWrite({ todos: [
|
||||
{ content: "LP-Phase 1: Exploration", status: "completed", activeForm: "Exploring codebase" },
|
||||
{ content: "LP-Phase 2: Clarification", status: "in_progress", activeForm: "Collecting clarifications" },
|
||||
{ content: "LP-Phase 3: Planning", status: "pending", activeForm: "Generating plan" },
|
||||
{ content: "LP-Phase 4: Confirmation", status: "pending", activeForm: "Awaiting confirmation" },
|
||||
{ content: "LP-Phase 5: Execution", status: "pending", activeForm: "Executing tasks" }
|
||||
]})
|
||||
```
|
||||
// TodoWrite: Phase 1 → completed, Phase 2 → in_progress
|
||||
|
||||
**Output**:
|
||||
- `${sessionFolder}/exploration-{angle1}.json`
|
||||
- `${sessionFolder}/exploration-{angle2}.json`
|
||||
- ... (1-4 files based on complexity)
|
||||
- `${sessionFolder}/explorations-manifest.json`
|
||||
**Output**: `exploration-{angle}.json` (1-4 files) + `explorations-manifest.json`
|
||||
|
||||
---
|
||||
|
||||
@@ -362,11 +254,9 @@ TodoWrite({ todos: [
|
||||
|
||||
**Skip if**: No exploration or `clarification_needs` is empty across all explorations
|
||||
|
||||
**⚠️ CRITICAL**: AskUserQuestion tool limits max 4 questions per call. **MUST execute multiple rounds** to exhaust all clarification needs - do NOT stop at round 1.
|
||||
**CRITICAL**: AskUserQuestion limits max 4 questions per call. **MUST execute multiple rounds** to exhaust all clarification needs.
|
||||
|
||||
**Aggregate clarification needs from all exploration angles**:
|
||||
```javascript
|
||||
// Load manifest and all exploration files (may not exist if exploration was skipped)
|
||||
const manifest = file_exists(`${sessionFolder}/explorations-manifest.json`)
|
||||
? JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
|
||||
: { exploration_count: 0, explorations: [] }
|
||||
@@ -375,41 +265,28 @@ const explorations = manifest.explorations.map(exp => ({
|
||||
data: JSON.parse(Read(exp.path))
|
||||
}))
|
||||
|
||||
// Aggregate clarification needs from all explorations
|
||||
// Aggregate from all explorations
|
||||
const allClarifications = []
|
||||
explorations.forEach(exp => {
|
||||
if (exp.data.clarification_needs?.length > 0) {
|
||||
exp.data.clarification_needs.forEach(need => {
|
||||
allClarifications.push({
|
||||
...need,
|
||||
source_angle: exp.angle
|
||||
})
|
||||
allClarifications.push({ ...need, source_angle: exp.angle })
|
||||
})
|
||||
}
|
||||
})
|
||||
|
||||
// Intelligent deduplication: analyze allClarifications by intent
|
||||
// - Identify questions with similar intent across different angles
|
||||
// - Merge similar questions: combine options, consolidate context
|
||||
// - Produce dedupedClarifications with unique intents only
|
||||
// Intelligent dedup: merge similar intent across angles, combine options
|
||||
const dedupedClarifications = intelligentMerge(allClarifications)
|
||||
|
||||
const autoYes = workflowPreferences.autoYes
|
||||
|
||||
if (autoYes) {
|
||||
// Auto mode: Skip clarification phase
|
||||
if (workflowPreferences.autoYes) {
|
||||
console.log(`[Auto] Skipping ${dedupedClarifications.length} clarification questions`)
|
||||
console.log(`Proceeding to planning with exploration results...`)
|
||||
// Continue to LP-Phase 3
|
||||
} else if (dedupedClarifications.length > 0) {
|
||||
// Interactive mode: Multi-round clarification
|
||||
const BATCH_SIZE = 4
|
||||
const totalRounds = Math.ceil(dedupedClarifications.length / BATCH_SIZE)
|
||||
|
||||
for (let i = 0; i < dedupedClarifications.length; i += BATCH_SIZE) {
|
||||
const batch = dedupedClarifications.slice(i, i + BATCH_SIZE)
|
||||
const currentRound = Math.floor(i / BATCH_SIZE) + 1
|
||||
|
||||
console.log(`### Clarification Round ${currentRound}/${totalRounds}`)
|
||||
|
||||
AskUserQuestion({
|
||||
@@ -423,7 +300,6 @@ if (autoYes) {
|
||||
}))
|
||||
}))
|
||||
})
|
||||
|
||||
// Store batch responses in clarificationContext before next round
|
||||
}
|
||||
}
|
||||
@@ -435,90 +311,56 @@ if (autoYes) {
|
||||
|
||||
### LP-Phase 3: Planning
|
||||
|
||||
**Planning Strategy Selection** (based on LP-Phase 1 complexity):
|
||||
|
||||
**IMPORTANT**: LP-Phase 3 is **planning only** - NO code execution. All execution happens in LP-Phase 5 via lite-execute.
|
||||
|
||||
**Executor Assignment** (Claude 智能分配，plan 生成后执行):
|
||||
**IMPORTANT**: LP-Phase 3 is **planning only** — NO code execution. All execution happens in LP-Phase 5 via lite-execute.
|
||||
|
||||
**Executor Assignment** (after plan generation):
|
||||
```javascript
|
||||
// 分配规则（优先级从高到低）：
|
||||
// 1. 用户明确指定："用 gemini 分析..." → gemini, "codex 实现..." → codex
|
||||
// 2. 默认 → agent
|
||||
|
||||
const executorAssignments = {} // { taskId: { executor: 'gemini'|'codex'|'agent', reason: string } }
|
||||
|
||||
// Load tasks from .task/ directory for executor assignment
|
||||
// Priority: 1. User explicit ("用 gemini 分析..." → gemini) | 2. Default → agent
|
||||
const executorAssignments = {} // { taskId: { executor: 'gemini'|'codex'|'agent', reason } }
|
||||
const taskFiles = Glob(`${sessionFolder}/.task/TASK-*.json`)
|
||||
taskFiles.forEach(taskPath => {
|
||||
const task = JSON.parse(Read(taskPath))
|
||||
// Claude 根据上述规则语义分析，为每个 task 分配 executor
|
||||
executorAssignments[task.id] = { executor: '...', reason: '...' }
|
||||
})
|
||||
```
|
||||
|
||||
**Low Complexity** - Direct planning by Claude:
|
||||
**Low Complexity** — Direct planning by Claude:
|
||||
```javascript
|
||||
// Step 1: Read schema
|
||||
const schema = Bash(`cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json`)
|
||||
|
||||
// Step 2: Read exploration files if available
|
||||
const manifest = file_exists(`${sessionFolder}/explorations-manifest.json`)
|
||||
? JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
|
||||
: { explorations: [] }
|
||||
manifest.explorations.forEach(exp => {
|
||||
const explorationData = Read(exp.path)
|
||||
console.log(`\n### Exploration: ${exp.angle}\n${explorationData}`)
|
||||
console.log(`\n### Exploration: ${exp.angle}\n${Read(exp.path)}`)
|
||||
})
|
||||
|
||||
// Step 3: Generate task objects (Claude directly, no agent)
|
||||
// ⚠️ Tasks MUST incorporate insights from exploration files read in Step 2
|
||||
// Task fields use NEW names: convergence.criteria (not acceptance), files[].change (not modification_points), test (not verification)
|
||||
// Generate tasks — MUST incorporate exploration insights
|
||||
// Field names: convergence.criteria (not acceptance), files[].change (not modification_points), test (not verification)
|
||||
const tasks = [
|
||||
{
|
||||
id: "TASK-001",
|
||||
title: "...",
|
||||
description: "...",
|
||||
depends_on: [],
|
||||
id: "TASK-001", title: "...", description: "...", depends_on: [],
|
||||
convergence: { criteria: ["..."] },
|
||||
files: [{ path: "...", change: "..." }],
|
||||
implementation: ["..."],
|
||||
test: "..."
|
||||
},
|
||||
// ... more tasks
|
||||
implementation: ["..."], test: "..."
|
||||
}
|
||||
]
|
||||
|
||||
// Step 4: Write task files to .task/ directory
|
||||
const taskDir = `${sessionFolder}/.task`
|
||||
Bash(`mkdir -p "${taskDir}"`)
|
||||
tasks.forEach(task => {
|
||||
Write(`${taskDir}/${task.id}.json`, JSON.stringify(task, null, 2))
|
||||
})
|
||||
tasks.forEach(task => Write(`${taskDir}/${task.id}.json`, JSON.stringify(task, null, 2)))
|
||||
|
||||
// Step 5: Generate plan overview (NO embedded tasks[])
|
||||
const plan = {
|
||||
summary: "...",
|
||||
approach: "...",
|
||||
task_ids: tasks.map(t => t.id),
|
||||
task_count: tasks.length,
|
||||
complexity: "Low",
|
||||
estimated_time: "...",
|
||||
recommended_execution: "Agent",
|
||||
_metadata: {
|
||||
timestamp: getUtc8ISOString(),
|
||||
source: "direct-planning",
|
||||
planning_mode: "direct",
|
||||
plan_type: "feature"
|
||||
}
|
||||
summary: "...", approach: "...",
|
||||
task_ids: tasks.map(t => t.id), task_count: tasks.length,
|
||||
complexity: "Low", estimated_time: "...", recommended_execution: "Agent",
|
||||
_metadata: { timestamp: getUtc8ISOString(), source: "direct-planning", planning_mode: "direct", plan_type: "feature" }
|
||||
}
|
||||
|
||||
// Step 6: Write plan overview to session folder
|
||||
Write(`${sessionFolder}/plan.json`, JSON.stringify(plan, null, 2))
|
||||
|
||||
// Step 7: MUST continue to LP-Phase 4 (Confirmation) - DO NOT execute code here
|
||||
// MUST continue to LP-Phase 4 — DO NOT execute code here
|
||||
```
|
||||
|
||||
**Medium/High Complexity** - Invoke cli-lite-planning-agent:
|
||||
**Medium/High Complexity** — Invoke cli-lite-planning-agent:
|
||||
|
||||
```javascript
|
||||
Task(
|
||||
@@ -529,20 +371,17 @@ Task(
|
||||
Generate implementation plan and write plan.json.
|
||||
|
||||
## Output Location
|
||||
|
||||
**Session Folder**: ${sessionFolder}
|
||||
**Output Files**:
|
||||
- ${sessionFolder}/planning-context.md (evidence + understanding)
|
||||
- ${sessionFolder}/plan.json (plan overview -- NO embedded tasks[])
|
||||
- ${sessionFolder}/plan.json (plan overview — NO embedded tasks[])
|
||||
- ${sessionFolder}/.task/TASK-*.json (independent task files, one per task)
|
||||
|
||||
## Output Schema Reference
|
||||
Execute: cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json (get schema reference before generating plan)
|
||||
## Schema Reference
|
||||
Execute: cat ~/.ccw/workflows/cli-templates/schemas/plan-overview-base-schema.json
|
||||
|
||||
## Project Context (MANDATORY - Load via ccw spec)
|
||||
## Project Context (MANDATORY)
|
||||
Execute: ccw spec load --category planning
|
||||
This loads technology stack, architecture, key components, and user-defined constraints/conventions.
|
||||
|
||||
**CRITICAL**: All generated tasks MUST comply with constraints in specs/*.md
|
||||
|
||||
## Task Description
|
||||
@@ -553,14 +392,11 @@ ${task_description}
|
||||
${manifest.explorations.length > 0
|
||||
? manifest.explorations.map(exp => `### Exploration: ${exp.angle} (${exp.file})
|
||||
Path: ${exp.path}
|
||||
|
||||
Read this file for detailed ${exp.angle} analysis.`).join('\n\n') + `
|
||||
|
||||
Total explorations: ${manifest.exploration_count}
|
||||
Angles covered: ${manifest.explorations.map(e => e.angle).join(', ')}
|
||||
|
||||
Total: ${manifest.exploration_count} | Angles: ${manifest.explorations.map(e => e.angle).join(', ')}
|
||||
Manifest: ${sessionFolder}/explorations-manifest.json`
|
||||
: `No exploration files. Task Description above contains "## Prior Analysis" with analysis summary, key files, and findings — use it as primary planning context.`}
|
||||
: `No exploration files. Task Description contains "## Prior Analysis" — use as primary planning context.`}
|
||||
|
||||
## User Clarifications
|
||||
${JSON.stringify(clarificationContext) || "None"}
|
||||
@@ -569,112 +405,68 @@ ${JSON.stringify(clarificationContext) || "None"}
|
||||
${complexity}
|
||||
|
||||
## Requirements
|
||||
Generate plan.json and .task/*.json following the schema obtained above. Key constraints:
|
||||
- _metadata.exploration_angles: ${JSON.stringify(manifest.explorations.map(e => e.angle))}
|
||||
|
||||
**Output Format**: Two-layer structure:
|
||||
- plan.json: Overview with task_ids[] referencing .task/ files (NO tasks[] array)
|
||||
- .task/TASK-*.json: Independent task files following task-schema.json
|
||||
|
||||
Follow plan-overview-base-schema.json (loaded via cat command above) for plan.json structure.
|
||||
Follow task-schema.json for .task/TASK-*.json structure.
|
||||
Note: Use files[].change (not modification_points), convergence.criteria (not acceptance).
|
||||
- Two-layer output: plan.json (task_ids[], NO tasks[]) + .task/TASK-*.json
|
||||
- Follow plan-overview-base-schema.json for plan.json, task-schema.json for .task/*.json
|
||||
- Field names: files[].change (not modification_points), convergence.criteria (not acceptance)
|
||||
|
||||
## Task Grouping Rules
|
||||
1. **Group by feature**: All changes for one feature = one task (even if 3-5 files)
|
||||
2. **Group by context**: Tasks with similar context or related functional changes can be grouped together
|
||||
3. **Minimize agent count**: Simple, unrelated tasks can also be grouped to reduce agent execution overhead
|
||||
2. **Group by context**: Related functional changes can be grouped together
|
||||
3. **Minimize agent count**: Group simple unrelated tasks to reduce overhead
|
||||
4. **Avoid file-per-task**: Do NOT create separate tasks for each file
|
||||
5. **Substantial tasks**: Each task should represent 15-60 minutes of work
|
||||
6. **True dependencies only**: Only use depends_on when Task B cannot start without Task A's output
|
||||
7. **Prefer parallel**: Most tasks should be independent (no depends_on)
|
||||
5. **Substantial tasks**: Each task = 15-60 minutes of work
|
||||
6. **True dependencies only**: depends_on only when Task B needs Task A's output
|
||||
7. **Prefer parallel**: Most tasks should be independent
|
||||
|
||||
## Execution
|
||||
1. Read schema file (cat command above)
|
||||
2. Execute CLI planning using Gemini (Qwen fallback)
|
||||
3. Read ALL exploration files for comprehensive context
|
||||
4. Synthesize findings and generate tasks + plan overview
|
||||
5. **Write**: \`${sessionFolder}/planning-context.md\` (evidence paths + understanding)
|
||||
6. **Create**: \`${sessionFolder}/.task/\` directory (mkdir -p)
|
||||
7. **Write**: \`${sessionFolder}/.task/TASK-001.json\`, \`TASK-002.json\`, etc. (one per task)
|
||||
8. **Write**: \`${sessionFolder}/plan.json\` (overview with task_ids[], NO tasks[])
|
||||
9. Return brief completion summary
|
||||
1. Read schema → 2. ccw spec load → 3. Read ALL exploration files → 4. Synthesize + generate
|
||||
5. Write: planning-context.md, .task/TASK-*.json, plan.json (task_ids[], NO tasks[])
|
||||
6. Return brief completion summary
|
||||
`
|
||||
)
|
||||
```
|
||||
|
||||
**Output**: `${sessionFolder}/plan.json`
|
||||
|
||||
**TodoWrite (LP-Phase 3 complete)**:
|
||||
```javascript
|
||||
TodoWrite({ todos: [
|
||||
{ content: "LP-Phase 1: Exploration", status: "completed", activeForm: "Exploring codebase" },
|
||||
{ content: "LP-Phase 2: Clarification", status: "completed", activeForm: "Collecting clarifications" },
|
||||
{ content: "LP-Phase 3: Planning", status: "completed", activeForm: "Generating plan" },
|
||||
{ content: "LP-Phase 4: Confirmation", status: "in_progress", activeForm: "Awaiting confirmation" },
|
||||
{ content: "LP-Phase 5: Execution", status: "pending", activeForm: "Executing tasks" }
|
||||
]})
|
||||
```
|
||||
// TodoWrite: Phase 3 → completed, Phase 4 → in_progress
|
||||
|
||||
---
|
||||
|
||||
### LP-Phase 4: Task Confirmation & Execution Selection
|
||||
|
||||
**Step 4.1: Display Plan**
|
||||
**Display Plan**:
|
||||
```javascript
|
||||
const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
|
||||
|
||||
// Load tasks from .task/ directory
|
||||
const tasks = (plan.task_ids || []).map(id => {
|
||||
const taskPath = `${sessionFolder}/.task/${id}.json`
|
||||
return JSON.parse(Read(taskPath))
|
||||
})
|
||||
const taskList = tasks
|
||||
const tasks = (plan.task_ids || []).map(id => JSON.parse(Read(`${sessionFolder}/.task/${id}.json`)))
|
||||
|
||||
console.log(`
|
||||
## Implementation Plan
|
||||
|
||||
**Summary**: ${plan.summary}
|
||||
**Approach**: ${plan.approach}
|
||||
|
||||
**Tasks** (${taskList.length}):
|
||||
${taskList.map((t, i) => `${i+1}. ${t.title} (${t.scope || t.files?.[0]?.path || ''})`).join('\n')}
|
||||
|
||||
**Complexity**: ${plan.complexity}
|
||||
**Estimated Time**: ${plan.estimated_time}
|
||||
**Recommended**: ${plan.recommended_execution}
|
||||
**Tasks** (${tasks.length}):
|
||||
${tasks.map((t, i) => `${i+1}. ${t.title} (${t.scope || t.files?.[0]?.path || ''})`).join('\n')}
|
||||
**Complexity**: ${plan.complexity} | **Time**: ${plan.estimated_time} | **Recommended**: ${plan.recommended_execution}
|
||||
`)
|
||||
```
|
||||
|
||||
**Step 4.2: Collect Confirmation**
|
||||
**Collect Confirmation**:
|
||||
```javascript
|
||||
const autoYes = workflowPreferences.autoYes
|
||||
|
||||
let userSelection
|
||||
|
||||
if (autoYes) {
|
||||
// Auto mode: Use defaults
|
||||
console.log(`[Auto] Auto-confirming plan:`)
|
||||
console.log(` - Confirmation: Allow`)
|
||||
console.log(` - Execution: Auto`)
|
||||
console.log(` - Review: Skip`)
|
||||
|
||||
userSelection = {
|
||||
confirmation: "Allow",
|
||||
execution_method: "Auto",
|
||||
code_review_tool: "Skip"
|
||||
}
|
||||
if (workflowPreferences.autoYes) {
|
||||
console.log(`[Auto] Allow & Execute | Auto | Skip`)
|
||||
userSelection = { confirmation: "Allow", execution_method: "Auto", code_review_tool: "Skip" }
|
||||
} else {
|
||||
// Interactive mode: Ask user
|
||||
// Note: Execution "Other" option allows specifying CLI tools from ~/.claude/cli-tools.json
|
||||
// "Other" in Execution allows specifying CLI tools from ~/.claude/cli-tools.json
|
||||
userSelection = AskUserQuestion({
|
||||
questions: [
|
||||
{
|
||||
question: `Confirm plan? (${taskList.length} tasks, ${plan.complexity})`,
|
||||
question: `Confirm plan and authorize execution? (${tasks.length} tasks, ${plan.complexity})`,
|
||||
header: "Confirm",
|
||||
multiSelect: false,
|
||||
options: [
|
||||
{ label: "Allow", description: "Proceed as-is" },
|
||||
{ label: "Allow & Execute", description: "Approve plan and begin execution immediately (no further prompts)" },
|
||||
{ label: "Modify", description: "Adjust before execution" },
|
||||
{ label: "Cancel", description: "Abort workflow" }
|
||||
]
|
||||
@@ -705,67 +497,42 @@ if (autoYes) {
|
||||
}
|
||||
```
|
||||
|
||||
**TodoWrite (LP-Phase 4 confirmed)**:
|
||||
```javascript
|
||||
const executionLabel = userSelection.execution_method
|
||||
|
||||
TodoWrite({ todos: [
|
||||
{ content: "LP-Phase 1: Exploration", status: "completed", activeForm: "Exploring codebase" },
|
||||
{ content: "LP-Phase 2: Clarification", status: "completed", activeForm: "Collecting clarifications" },
|
||||
{ content: "LP-Phase 3: Planning", status: "completed", activeForm: "Generating plan" },
|
||||
{ content: `LP-Phase 4: Confirmed [${executionLabel}]`, status: "completed", activeForm: "Confirmed" },
|
||||
{ content: `LP-Phase 5: Execution [${executionLabel}]`, status: "in_progress", activeForm: `Executing [${executionLabel}]` }
|
||||
]})
|
||||
```
|
||||
// TodoWrite: Phase 4 → completed `[${userSelection.execution_method} + ${userSelection.code_review_tool}]`, Phase 5 → in_progress
|
||||
|
||||
---
|
||||
|
||||
### LP-Phase 5: Handoff to Execution
|
||||
|
||||
**CRITICAL**: lite-plan NEVER executes code directly. ALL execution MUST go through lite-execute.
|
||||
|
||||
**Step 5.1: Build executionContext**
|
||||
**CRITICAL**: lite-plan NEVER executes code directly. ALL execution goes through lite-execute.
|
||||
|
||||
**Build executionContext**:
|
||||
```javascript
|
||||
// Load manifest and all exploration files (may not exist if exploration was skipped)
|
||||
const manifest = file_exists(`${sessionFolder}/explorations-manifest.json`)
|
||||
? JSON.parse(Read(`${sessionFolder}/explorations-manifest.json`))
|
||||
: { exploration_count: 0, explorations: [] }
|
||||
const explorations = {}
|
||||
|
||||
manifest.explorations.forEach(exp => {
|
||||
if (file_exists(exp.path)) {
|
||||
explorations[exp.angle] = JSON.parse(Read(exp.path))
|
||||
}
|
||||
if (file_exists(exp.path)) explorations[exp.angle] = JSON.parse(Read(exp.path))
|
||||
})
|
||||
|
||||
const plan = JSON.parse(Read(`${sessionFolder}/plan.json`))
|
||||
|
||||
executionContext = {
|
||||
planObject: plan, // plan overview (no tasks[])
|
||||
taskFiles: (plan.task_ids || []).map(id => ({
|
||||
id,
|
||||
path: `${sessionFolder}/.task/${id}.json`
|
||||
})),
|
||||
planObject: plan,
|
||||
taskFiles: (plan.task_ids || []).map(id => ({ id, path: `${sessionFolder}/.task/${id}.json` })),
|
||||
explorationsContext: explorations,
|
||||
explorationAngles: manifest.explorations.map(e => e.angle),
|
||||
explorationManifest: manifest,
|
||||
clarificationContext: clarificationContext || null,
|
||||
executionMethod: userSelection.execution_method, // 全局默认，可被 executorAssignments 覆盖
|
||||
executionMethod: userSelection.execution_method,
|
||||
codeReviewTool: userSelection.code_review_tool,
|
||||
originalUserInput: task_description,
|
||||
|
||||
// 任务级 executor 分配（优先于全局 executionMethod）
|
||||
executorAssignments: executorAssignments, // { taskId: { executor, reason } }
|
||||
|
||||
executorAssignments: executorAssignments, // { taskId: { executor, reason } } — overrides executionMethod
|
||||
session: {
|
||||
id: sessionId,
|
||||
folder: sessionFolder,
|
||||
artifacts: {
|
||||
explorations: manifest.explorations.map(exp => ({
|
||||
angle: exp.angle,
|
||||
path: exp.path
|
||||
})),
|
||||
explorations: manifest.explorations.map(exp => ({ angle: exp.angle, path: exp.path })),
|
||||
explorations_manifest: `${sessionFolder}/explorations-manifest.json`,
|
||||
plan: `${sessionFolder}/plan.json`,
|
||||
task_dir: `${sessionFolder}/.task`
|
||||
@@ -774,56 +541,39 @@ executionContext = {
|
||||
}
|
||||
```
|
||||
|
||||
**Step 5.2: Handoff with Tracking**
|
||||
|
||||
**Handoff**:
|
||||
```javascript
|
||||
// Update TodoWrite to show handoff to lite-execute
|
||||
if (!workflowPreferences.autoYes) {
|
||||
console.log(`Handing off to execution engine. No further prompts.`)
|
||||
}
|
||||
|
||||
// TodoWrite: Phase 5 → completed, add LE-Phase 1 → in_progress
|
||||
const taskCount = (plan.task_ids || []).length
|
||||
TodoWrite({ todos: [
|
||||
{ content: "LP-Phase 1: Exploration", status: "completed", activeForm: "Exploring codebase" },
|
||||
{ content: "LP-Phase 2: Clarification", status: "completed", activeForm: "Collecting clarifications" },
|
||||
{ content: "LP-Phase 3: Planning", status: "completed", activeForm: "Generating plan" },
|
||||
{ content: `LP-Phase 4: Confirmed [${executionLabel}]`, status: "completed", activeForm: "Confirmed" },
|
||||
{ content: `LP-Phase 5: Handoff → lite-execute`, status: "completed", activeForm: "Handoff to execution" },
|
||||
{ content: "LP-Phase 1: Exploration", status: "completed" },
|
||||
{ content: "LP-Phase 2: Clarification", status: "completed" },
|
||||
{ content: "LP-Phase 3: Planning", status: "completed" },
|
||||
{ content: `LP-Phase 4: Confirmed [${userSelection.execution_method}]`, status: "completed" },
|
||||
{ content: `LP-Phase 5: Handoff → lite-execute`, status: "completed" },
|
||||
{ content: `LE-Phase 1: Task Loading [${taskCount} tasks]`, status: "in_progress", activeForm: "Loading tasks" }
|
||||
]})
|
||||
|
||||
// Invoke lite-execute skill with executionContext
|
||||
Skill("lite-execute")
|
||||
// executionContext is passed as global variable (Mode 1: In-Memory Plan)
|
||||
// lite-execute will continue TodoWrite tracking with LE-Phase prefix
|
||||
// executionContext passed as global variable (Mode 1: In-Memory Plan)
|
||||
```
|
||||
|
||||
## Session Folder Structure
|
||||
|
||||
```
|
||||
.workflow/.lite-plan/{task-slug}-{YYYY-MM-DD}/
|
||||
├── exploration-{angle1}.json # Exploration angle 1
|
||||
├── exploration-{angle2}.json # Exploration angle 2
|
||||
├── exploration-{angle3}.json # Exploration angle 3 (if applicable)
|
||||
├── exploration-{angle4}.json # Exploration angle 4 (if applicable)
|
||||
├── explorations-manifest.json # Exploration index
|
||||
├── planning-context.md # Evidence paths + understanding
|
||||
├── plan.json # Plan overview (task_ids[])
|
||||
└── .task/ # Task files directory
|
||||
├── TASK-001.json
|
||||
├── TASK-002.json
|
||||
└── ...
|
||||
```
|
||||
|
||||
**Example**:
|
||||
```
|
||||
.workflow/.lite-plan/implement-jwt-refresh-2025-11-25-14-30-25/
|
||||
├── exploration-architecture.json
|
||||
├── exploration-auth-patterns.json
|
||||
├── exploration-security.json
|
||||
├── explorations-manifest.json
|
||||
├── planning-context.md
|
||||
├── plan.json
|
||||
├── exploration-{angle}.json (1-4) # Per-angle exploration
|
||||
├── explorations-manifest.json # Exploration index
|
||||
├── planning-context.md # Evidence paths + understanding
|
||||
├── plan.json # Plan overview (task_ids[])
|
||||
└── .task/
|
||||
├── TASK-001.json
|
||||
├── TASK-002.json
|
||||
└── TASK-003.json
|
||||
└── ...
|
||||
```
|
||||
|
||||
## Error Handling
|
||||
@@ -835,7 +585,3 @@ Skill("lite-execute")
|
||||
| Clarification timeout | Use exploration findings as-is |
|
||||
| Confirmation timeout | Save context, display resume instructions |
|
||||
| Modify loop > 3 times | Suggest breaking task or using /workflow-plan |
|
||||
|
||||
## Next Phase
|
||||
|
||||
After LP-Phase 5 handoff, execution continues in the workflow-lite-execute skill.
|
||||
|
||||
Reference in New Issue
Block a user