catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-12 02:37:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: Update review commands to require active sessions and unify output directory structure for improved organization and clarity

Browse Source
This commit is contained in:
catlog22
2025-11-25 23:02:20 +08:00
parent c3e87db5be
commit 8f2126677f
5 changed files with 485 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

85
.claude/commands/workflow/review-module-cycle.md
View File

@@ -26,8 +26,9 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Task(*)
/workflow:review-module-cycle --resume
```
**Review Scope**: Specified modules/files only (independent of git history or sessions)
**Output Directory**: `.workflow/.reviews/module-{pattern-hash}/` (fixed location)
**Review Scope**: Specified modules/files only (independent of git history)
**Session Requirement**: Requires active workflow session (or creates review-only session)
**Output Directory**: `.workflow/active/WFS-{session-id}/.review/` (session-based)
**Default Dimensions**: Security, Architecture, Quality, Action-Items, Performance, Maintainability, Best-Practices
**Max Iterations**: 3 (default, adjustable)
**CLI Tools**: Gemini → Qwen → Codex (fallback chain)
@@ -39,19 +40,21 @@ Independent multi-dimensional code review orchestrator with **hybrid parallel-it
**Review Scope**:
- **Module-based**: Reviews specified file patterns (e.g., `src/auth/**`, `*.ts`)
- **No session dependency**: Works independently of workflow sessions
- **For session-based review**: Use `/workflow:review-session-cycle` command instead
- **Session-integrated**: Runs within workflow session context for unified tracking
- **Output location**: `.review/` subdirectory within active session
**vs Session Review**:
- **Session Review** (`review-session-cycle`): Reviews git changes within a workflow session
- **Module Review** (`review-module-cycle`): Reviews any specified code paths, regardless of git history
- **Common output**: Both use same `.review/` directory structure within session
### Value Proposition
1. **Ad-hoc Review**: Review any code without requiring a workflow session
2. **Module-focused**: Target specific areas of codebase for deep analysis
1. **Module-Focused Review**: Target specific code areas independent of git history
2. **Session-Integrated**: Review results tracked within workflow session for unified management
3. **Comprehensive Coverage**: Same 7 specialized dimensions as session review
4. **Intelligent Prioritization**: Automatic identification of critical issues and cross-cutting concerns
5. **Real-time Visibility**: JSON-based progress tracking with interactive HTML dashboard
6. **Unified Archive**: Review results archived with session for historical reference
### Orchestrator Boundary (CRITICAL)
- **ONLY command** for independent multi-dimensional module review
@@ -60,7 +63,7 @@ Independent multi-dimensional code review orchestrator with **hybrid parallel-it
## How It Works
### Execution Flow (Simplified)
### Execution Flow
```
1. Discovery & Initialization
@@ -175,13 +178,45 @@ const CATEGORIES = {
### Orchestrator
**Phase 1: Discovery & Initialization**
- Path resolution: Parse and expand file patterns (glob support)
**Step 1: Session Discovery**
```javascript
// Auto-discover or create session
SlashCommand(command="/workflow:session:start --auto \"Code review for [target_pattern]\"")
// Parse output
const sessionId = output.match(/SESSION_ID: (WFS-[^\s]+)/)[1];
// Validate session exists
Bash(`test -d .workflow/active/${sessionId} && echo "EXISTS"`);
```
**Step 2: Path Resolution & Validation**
- Parse and expand file patterns (glob support): `src/auth/**` → actual file list
- Validation: Ensure all specified files exist and are readable
- Output directory: Set to `.workflow/.reviews/module-{pattern-hash}/` (fixed location, hash based on target pattern)
- State initialization: Create review-state.json with dimensions, max_iterations, resolved_files
- Directory structure: Create {dimensions,iterations,reports}/ subdirectories
- Dashboard generation: Generate dashboard.html from template (see Dashboard Generation below)
- TodoWrite initialization: Set up progress tracking
- Store resolved files as absolute paths (e.g., `D:\\project\\src\\auth\\service.ts`)
**Step 3: Output Directory Setup**
- Output directory: `.workflow/active/${sessionId}/.review/`
- Create directory structure:
```bash
mkdir -p ${sessionDir}/.review/{dimensions,iterations,reports}
```
**Step 4: Initialize Review State**
- Metadata creation: Create `review-metadata.json` with scope, dimensions, and configuration
- State initialization: Create `review-state.json` with dimensions, max_iterations, resolved_files
- Progress tracking: Create `review-progress.json` for dashboard polling
**Step 5: Dashboard Generation**
- Read template: `~/.claude/templates/review-cycle-dashboard.html`
- Replace placeholders: `{{SESSION_ID}}`, `{{REVIEW_TYPE}}`, `{{REVIEW_DIR}}`
- Write to: `${sessionDir}/.review/dashboard.html`
- Output path to user: `file://${absolutePath}/dashboard.html`
**Step 6: TodoWrite Initialization**
- Set up progress tracking with hierarchical structure
- Mark Phase 1 completed, Phase 2 in_progress
**Phase 2: Parallel Review Coordination**
- Launch 7 @cli-explore-agent instances simultaneously (Deep Scan mode)
@@ -315,7 +350,8 @@ Dashboard uses **static HTML + JSON polling**: reads template from `~/.claude/te
### Output File Structure
```
.workflow/.reviews/module-{pattern-hash}/
.workflow/active/WFS-{session-id}/.review/
├── review-metadata.json # Review configuration and scope
├── review-state.json # Orchestrator state machine
├── review-progress.json # Real-time progress for dashboard
├── dimensions/ # Per-dimension results
@@ -338,6 +374,18 @@ Dashboard uses **static HTML + JSON polling**: reads template from `~/.claude/te
└── dashboard.html # Interactive dashboard
```
**Session Context**:
```
.workflow/active/WFS-{session-id}/
├── workflow-session.json
├── IMPL_PLAN.md
├── TODO_LIST.md
├── .task/
├── .summaries/
└── .review/ # Review results (this command)
└── (structure above)
```
### Review State JSON
**Purpose**: Persisted state machine for phase transitions and iteration control - enables Resume
@@ -346,11 +394,12 @@ Dashboard uses **static HTML + JSON polling**: reads template from `~/.claude/te
{
"review_id": "review-20250125-143022",
"review_type": "module",
"session_id": "WFS-auth-system",
"target_pattern": "src/auth/**",
"resolved_files": [
"src/auth/service.ts",
"src/auth/validator.ts",
"src/auth/middleware.ts"
"D:\\project\\src\\auth\\service.ts",
"D:\\project\\src\\auth\\validator.ts",
"D:\\project\\src\\auth\\middleware.ts"
],
"phase": "parallel|aggregate|iterate|complete",
"current_iteration": 1,
@@ -801,7 +850,7 @@ After completing a module review, use the dashboard to select findings and expor
# Dashboard generates: fix-export-{timestamp}.json
# Step 3: Run automated fixes
/workflow:review-fix .workflow/.reviews/module-{hash}/fix-export-{timestamp}.json
/workflow:review-fix .workflow/active/WFS-{session-id}/.review/fix-export-{timestamp}.json
```
See `/workflow:review-fix` for automated fixing with smart grouping, parallel execution, and test verification.

82
.claude/commands/workflow/review-session-cycle.md
View File

@@ -24,7 +24,8 @@ allowed-tools: SlashCommand(*), TodoWrite(*), Read(*), Bash(*), Task(*)
```
**Review Scope**: Git changes from session creation to present (via `git log --since`)
**Output Directory**: `.workflow/.reviews/session-{session-id}/` (fixed location)
**Session Requirement**: Requires active or completed workflow session
**Output Directory**: `.workflow/active/WFS-{session-id}/.review/` (session-based)
**Default Dimensions**: Security, Architecture, Quality, Action-Items, Performance, Maintainability, Best-Practices
**Max Iterations**: 3 (default, adjustable)
**CLI Tools**: Gemini → Qwen → Codex (fallback chain)
@@ -156,13 +157,61 @@ const CATEGORIES = {
### Orchestrator
**Phase 1: Discovery & Initialization**
- Session discovery: Auto-detect active session if not specified
- Validation: Ensure session has completed implementation (check .summaries/)
- Output directory: Set to `.workflow/.reviews/session-{session-id}/` (fixed location)
- State initialization: Create review-state.json with dimensions, max_iterations
- Directory structure: Create {dimensions,iterations,reports}/ subdirectories
- Dashboard generation: Generate dashboard.html from template (see Dashboard Generation below)
- TodoWrite initialization: Set up progress tracking
**Step 1: Session Discovery**
```javascript
// If session ID not provided, auto-detect
if (!providedSessionId) {
// Check for active sessions
const activeSessions = Glob('.workflow/active/WFS-*');
if (activeSessions.length === 1) {
sessionId = activeSessions[0].match(/WFS-[^/]+/)[0];
} else if (activeSessions.length > 1) {
// List sessions and prompt user
error("Multiple active sessions found. Please specify session ID.");
} else {
error("No active session found. Create session first with /workflow:session:start");
}
} else {
sessionId = providedSessionId;
}
// Validate session exists
Bash(`test -d .workflow/active/${sessionId} && echo "EXISTS"`);
```
**Step 2: Session Validation**
- Ensure session has implementation artifacts (check `.summaries/` or `.task/` directory)
- Extract session creation timestamp from `workflow-session.json`
- Use timestamp for git log filtering: `git log --since="${sessionCreatedAt}"`
**Step 3: Changed Files Detection**
```bash
# Get files changed since session creation
git log --since="${sessionCreatedAt}" --name-only --pretty=format: | sort -u
```
**Step 4: Output Directory Setup**
- Output directory: `.workflow/active/${sessionId}/.review/`
- Create directory structure:
```bash
mkdir -p ${sessionDir}/.review/{dimensions,iterations,reports}
```
**Step 5: Initialize Review State**
- Metadata creation: Create `review-metadata.json` with scope, dimensions, and configuration
- State initialization: Create `review-state.json` with dimensions, max_iterations
- Progress tracking: Create `review-progress.json` for dashboard polling
**Step 6: Dashboard Generation**
- Read template: `~/.claude/templates/review-cycle-dashboard.html`
- Replace placeholders: `{{SESSION_ID}}`, `{{REVIEW_TYPE}}`, `{{REVIEW_DIR}}`
- Write to: `${sessionDir}/.review/dashboard.html`
- Output path to user: `file://${absolutePath}/dashboard.html`
**Step 7: TodoWrite Initialization**
- Set up progress tracking with hierarchical structure
- Mark Phase 1 completed, Phase 2 in_progress
**Phase 2: Parallel Review Coordination**
- Launch 7 @cli-explore-agent instances simultaneously (Deep Scan mode)
@@ -304,7 +353,8 @@ Dashboard uses **static HTML + JSON polling**: reads template from `~/.claude/te
### Session File Structure
```
.workflow/.reviews/session-{session-id}/
.workflow/active/WFS-{session-id}/.review/
├── review-metadata.json # Review configuration and scope
├── review-state.json # Orchestrator state machine
├── review-progress.json # Real-time progress for dashboard
├── dimensions/ # Per-dimension results
@@ -327,6 +377,18 @@ Dashboard uses **static HTML + JSON polling**: reads template from `~/.claude/te
└── dashboard.html # Interactive dashboard
```
**Session Context**:
```
.workflow/active/WFS-{session-id}/
├── workflow-session.json
├── IMPL_PLAN.md
├── TODO_LIST.md
├── .task/
├── .summaries/
└── .review/ # Review results (this command)
└── (structure above)
```
### Review State JSON
**Purpose**: Persisted state machine for phase transitions and iteration control - enables Resume
@@ -834,7 +896,7 @@ After completing a review, use the dashboard to select findings and export them
# Dashboard generates: fix-export-{timestamp}.json
# Step 3: Run automated fixes
/workflow:review-fix .workflow/.reviews/session-{session-id}/fix-export-{timestamp}.json
/workflow:review-fix .workflow/active/WFS-{session-id}/.review/fix-export-{timestamp}.json
```
See `/workflow:review-fix` for automated fixing with smart grouping, parallel execution, and test verification.

19
.claude/commands/workflow/session/start.md
View File

@@ -168,25 +168,6 @@ DECISION: Reusing existing session
SESSION_ID: WFS-promptmaster-platform
```
## Command Integration
### For /workflow:plan (Use Auto Mode)
```bash
SlashCommand(command="/workflow:session:start --auto \"implement OAuth2 authentication\"")
# Parse session ID from output
grep "^SESSION_ID:" | awk '{print $2}'
```
### For Interactive Workflows (Use Discovery Mode)
```bash
SlashCommand(command="/workflow:session:start")
```
### For New Isolated Work (Use Force New Mode)
```bash
SlashCommand(command="/workflow:session:start --new \"experimental feature\"")
```
## Session ID Format
- Pattern: `WFS-[lowercase-slug]`