mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-03-28 20:01:17 +08:00
feat: migrate all codex team skills from spawn_agents_on_csv to spawn_agent + wait_agent architecture
- Delete 21 old team skill directories using CSV-wave pipeline pattern (~100+ files) - Delete old team-lifecycle (v3) and team-planex-v2 - Create generic team-worker.toml and team-supervisor.toml (replacing tlv4-specific TOMLs) - Convert 19 team skills from Claude Code format (Agent/SendMessage/TaskCreate) to Codex format (spawn_agent/wait_agent/tasks.json/request_user_input) - Update team-lifecycle-v4 to use generic agent types (team_worker/team_supervisor) - Convert all coordinator role files: dispatch.md, monitor.md, role.md - Convert all worker role files: remove run_in_background, fix Bash syntax - Convert all specs/pipelines.md references - Final state: 20 team skills, 217 .md files, zero Claude Code API residuals Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
catlog22
@@ -1,825 +1,134 @@
|
||||
---
|
||||
name: team-iterdev
|
||||
description: Iterative development team with Generator-Critic loop, dynamic pipeline selection (patch/sprint/multi-sprint), task ledger for progress tracking, and shared wisdom for cross-sprint learning.
|
||||
argument-hint: "[-y|--yes] [-c|--concurrency N] [--continue] \"task description\""
|
||||
allowed-tools: spawn_agents_on_csv, spawn_agent, wait, send_input, close_agent, Read, Write, Edit, Bash, Glob, Grep, request_user_input
|
||||
description: Unified team skill for iterative development team. Pure router — all roles read this file. Beat model is coordinator-only in monitor.md. Generator-Critic loops (developer<->reviewer, max 3 rounds). Triggers on "team iterdev".
|
||||
allowed-tools: spawn_agent(*), wait_agent(*), send_input(*), close_agent(*), report_agent_job_result(*), request_user_input(*), Read(*), Write(*), Edit(*), Bash(*), Glob(*), Grep(*)
|
||||
---
|
||||
|
||||
## Auto Mode
|
||||
|
||||
When `--yes` or `-y`: Auto-confirm task decomposition, skip interactive validation, use defaults.
|
||||
|
||||
# Team IterDev
|
||||
|
||||
## Usage
|
||||
Iterative development team skill. Generator-Critic loops (developer<->reviewer, max 3 rounds), task ledger (task-ledger.json) for real-time progress, shared memory (cross-sprint learning), and dynamic pipeline selection for incremental delivery.
|
||||
|
||||
```bash
|
||||
$team-iterdev "Implement user authentication with JWT"
|
||||
$team-iterdev -c 4 "Refactor payment module to support multiple gateways"
|
||||
$team-iterdev -y "Fix login button not responding on mobile"
|
||||
$team-iterdev --continue "ids-auth-jwt-20260308"
|
||||
```
|
||||
|
||||
**Flags**:
|
||||
- `-y, --yes`: Skip all confirmations (auto mode)
|
||||
- `-c, --concurrency N`: Max concurrent agents within each wave (default: 3)
|
||||
- `--continue`: Resume existing session
|
||||
|
||||
**Output Directory**: `.workflow/.csv-wave/{session-id}/`
|
||||
**Core Output**: `tasks.csv` (master state) + `results.csv` (final) + `discoveries.ndjson` (shared exploration) + `context.md` (human-readable report)
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Iterative development team skill with Generator-Critic (GC) loops between developer and reviewer roles (max 3 rounds). Automatically selects pipeline complexity (patch/sprint/multi-sprint) based on task signals. Tracks progress via task ledger. Accumulates cross-sprint wisdom in shared discovery board.
|
||||
|
||||
**Execution Model**: Hybrid -- CSV wave pipeline (primary) + individual agent spawn (secondary for GC loop control and requirement analysis)
|
||||
## Architecture
|
||||
|
||||
```
|
||||
+-------------------------------------------------------------------------+
|
||||
| TEAM ITERDEV WORKFLOW |
|
||||
+-------------------------------------------------------------------------+
|
||||
| |
|
||||
| Phase 0: Pre-Wave Interactive |
|
||||
| +-- Analyze task complexity and select pipeline mode |
|
||||
| +-- Explore codebase for patterns and dependencies |
|
||||
| +-- Output: pipeline mode, task analysis, session artifacts |
|
||||
| |
|
||||
| Phase 1: Requirement -> CSV + Classification |
|
||||
| +-- Parse task into pipeline-specific task chain |
|
||||
| +-- Assign roles: architect, developer, tester, reviewer |
|
||||
| +-- Classify tasks: csv-wave | interactive (exec_mode) |
|
||||
| +-- Compute dependency waves (topological sort -> depth grouping) |
|
||||
| +-- Generate tasks.csv with wave + exec_mode columns |
|
||||
| +-- User validates task breakdown (skip if -y) |
|
||||
| |
|
||||
| Phase 2: Wave Execution Engine (Extended) |
|
||||
| +-- For each wave (1..N): |
|
||||
| | +-- Execute pre-wave interactive tasks (if any) |
|
||||
| | +-- Build wave CSV (filter csv-wave tasks for this wave) |
|
||||
| | +-- Inject previous findings into prev_context column |
|
||||
| | +-- spawn_agents_on_csv(wave CSV) |
|
||||
| | +-- Execute post-wave interactive tasks (if any) |
|
||||
| | +-- Merge all results into master tasks.csv |
|
||||
| | +-- Check: any failed? -> skip dependents |
|
||||
| +-- discoveries.ndjson shared across all modes (append-only) |
|
||||
| |
|
||||
| Phase 3: Post-Wave Interactive |
|
||||
| +-- Generator-Critic (GC) loop control |
|
||||
| +-- If review has critical issues: trigger DEV-fix -> re-REVIEW |
|
||||
| +-- Max 3 GC rounds, then force convergence |
|
||||
| |
|
||||
| Phase 4: Results Aggregation |
|
||||
| +-- Export final results.csv |
|
||||
| +-- Generate context.md with all findings |
|
||||
| +-- Display summary: completed/failed/skipped per wave |
|
||||
| +-- Offer: view results | retry failed | done |
|
||||
| |
|
||||
+-------------------------------------------------------------------------+
|
||||
Skill(skill="team-iterdev", args="task description")
|
||||
|
|
||||
SKILL.md (this file) = Router
|
||||
|
|
||||
+--------------+--------------+
|
||||
| |
|
||||
no --role flag --role <name>
|
||||
| |
|
||||
Coordinator Worker
|
||||
roles/coordinator/role.md roles/<name>/role.md
|
||||
|
|
||||
+-- analyze -> dispatch -> spawn workers -> STOP
|
||||
|
|
||||
+-------+-------+-------+
|
||||
v v v v
|
||||
[architect] [developer] [tester] [reviewer]
|
||||
(team-worker agents, each loads roles/<role>/role.md)
|
||||
```
|
||||
|
||||
---
|
||||
## Role Registry
|
||||
|
||||
## Task Classification Rules
|
||||
| Role | Path | Prefix | Inner Loop |
|
||||
|------|------|--------|------------|
|
||||
| coordinator | [roles/coordinator/role.md](roles/coordinator/role.md) | — | — |
|
||||
| architect | [roles/architect/role.md](roles/architect/role.md) | DESIGN-* | false |
|
||||
| developer | [roles/developer/role.md](roles/developer/role.md) | DEV-* | true |
|
||||
| tester | [roles/tester/role.md](roles/tester/role.md) | VERIFY-* | false |
|
||||
| reviewer | [roles/reviewer/role.md](roles/reviewer/role.md) | REVIEW-* | false |
|
||||
|
||||
Each task is classified by `exec_mode`:
|
||||
## Role Router
|
||||
|
||||
| exec_mode | Mechanism | Criteria |
|
||||
|-----------|-----------|----------|
|
||||
| `csv-wave` | `spawn_agents_on_csv` | One-shot, structured I/O, no multi-round interaction |
|
||||
| `interactive` | `spawn_agent`/`wait`/`send_input`/`close_agent` | Multi-round, clarification, inline utility |
|
||||
Parse `$ARGUMENTS`:
|
||||
- Has `--role <name>` → Read `roles/<name>/role.md`, execute Phase 2-4
|
||||
- No `--role` → `roles/coordinator/role.md`, execute entry router
|
||||
|
||||
**Classification Decision**:
|
||||
## Shared Constants
|
||||
|
||||
| Task Property | Classification |
|
||||
|---------------|---------------|
|
||||
| Architecture design (DESIGN-*) | `csv-wave` |
|
||||
| Code implementation (DEV-*) | `csv-wave` |
|
||||
| Test execution and fix cycle (VERIFY-*) | `csv-wave` |
|
||||
| Code review (REVIEW-*) | `csv-wave` |
|
||||
| Fix task from review feedback (DEV-fix-*) | `csv-wave` |
|
||||
| GC loop control (decide revision vs convergence) | `interactive` |
|
||||
| Task analysis and pipeline selection (Phase 0) | `interactive` |
|
||||
- **Session prefix**: `IDS`
|
||||
- **Session path**: `.workflow/.team/IDS-<slug>-<date>/`
|
||||
- **CLI tools**: `ccw cli --mode analysis` (read-only), `ccw cli --mode write` (modifications)
|
||||
- **Message bus**: `mcp__ccw-tools__team_msg(session_id=<session-id>, ...)`
|
||||
|
||||
---
|
||||
## Worker Spawn Template
|
||||
|
||||
## Pipeline Selection Logic
|
||||
|
||||
| Signal | Score |
|
||||
|--------|-------|
|
||||
| Changed files > 10 | +3 |
|
||||
| Changed files 3-10 | +2 |
|
||||
| Structural change (refactor, architect, restructure) | +3 |
|
||||
| Cross-cutting concern (multiple, across, cross) | +2 |
|
||||
| Simple fix (fix, bug, typo, patch) | -2 |
|
||||
|
||||
| Score | Pipeline |
|
||||
|-------|----------|
|
||||
| >= 5 | multi-sprint |
|
||||
| 2-4 | sprint |
|
||||
| 0-1 | patch |
|
||||
|
||||
### Pipeline Definitions
|
||||
|
||||
**Patch** (2 tasks, serial):
|
||||
```
|
||||
DEV-001 -> VERIFY-001
|
||||
```
|
||||
|
||||
**Sprint** (4 tasks, with parallel window):
|
||||
```
|
||||
DESIGN-001 -> DEV-001 -> [VERIFY-001 + REVIEW-001] (parallel)
|
||||
```
|
||||
|
||||
**Multi-Sprint** (5+ tasks, iterative with GC loop):
|
||||
```
|
||||
Sprint 1: DESIGN-001 -> DEV-001 -> [VERIFY-001 + REVIEW-001] -> DEV-fix (if needed) -> REVIEW-002
|
||||
Sprint 2+ created dynamically
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## CSV Schema
|
||||
|
||||
### tasks.csv (Master State)
|
||||
|
||||
```csv
|
||||
id,title,description,role,pipeline,sprint_num,gc_round,deps,context_from,exec_mode,wave,status,findings,review_score,gc_signal,error
|
||||
"DESIGN-001","Technical design and task breakdown","Explore codebase, create component design, break into implementable tasks with acceptance criteria","architect","sprint","1","0","","","csv-wave","1","pending","","","",""
|
||||
"DEV-001","Implement design","Load design and task breakdown, implement tasks in execution order, validate syntax","developer","sprint","1","0","DESIGN-001","DESIGN-001","csv-wave","2","pending","","","",""
|
||||
"VERIFY-001","Verify implementation","Detect test framework, run targeted tests, run regression suite","tester","sprint","1","0","DEV-001","DEV-001","csv-wave","3","pending","","","",""
|
||||
```
|
||||
|
||||
**Columns**:
|
||||
|
||||
| Column | Phase | Description |
|
||||
|--------|-------|-------------|
|
||||
| `id` | Input | Unique task identifier (string) |
|
||||
| `title` | Input | Short task title |
|
||||
| `description` | Input | Detailed task description |
|
||||
| `role` | Input | Worker role: architect, developer, tester, reviewer |
|
||||
| `pipeline` | Input | Pipeline mode: patch, sprint, multi-sprint |
|
||||
| `sprint_num` | Input | Sprint number (1-based, for multi-sprint) |
|
||||
| `gc_round` | Input | Generator-Critic round number (0 = initial, 1+ = fix round) |
|
||||
| `deps` | Input | Semicolon-separated dependency task IDs |
|
||||
| `context_from` | Input | Semicolon-separated task IDs whose findings this task needs |
|
||||
| `exec_mode` | Input | `csv-wave` or `interactive` |
|
||||
| `wave` | Computed | Wave number (computed by topological sort, 1-based) |
|
||||
| `status` | Output | `pending` -> `completed` / `failed` / `skipped` |
|
||||
| `findings` | Output | Key discoveries or implementation notes (max 500 chars) |
|
||||
| `review_score` | Output | Quality score 1-10 (reviewer only) |
|
||||
| `gc_signal` | Output | `REVISION_NEEDED` or `CONVERGED` (reviewer only) |
|
||||
| `error` | Output | Error message if failed (empty if success) |
|
||||
|
||||
### Per-Wave CSV (Temporary)
|
||||
|
||||
Each wave generates a temporary `wave-{N}.csv` with extra `prev_context` column (csv-wave tasks only).
|
||||
|
||||
---
|
||||
|
||||
## Agent Registry (Interactive Agents)
|
||||
|
||||
| Agent | Role File | Pattern | Responsibility | Position |
|
||||
|-------|-----------|---------|----------------|----------|
|
||||
| task-analyzer | agents/task-analyzer.md | 2.3 (wait-respond) | Analyze task complexity, select pipeline mode, detect capabilities | standalone (Phase 0) |
|
||||
| gc-controller | agents/gc-controller.md | 2.3 (wait-respond) | Evaluate review severity, decide DEV-fix vs convergence | post-wave (after REVIEW wave) |
|
||||
|
||||
> **COMPACT PROTECTION**: Agent files are execution documents. When context compression occurs, **you MUST immediately `Read` the corresponding agent.md** to reload.
|
||||
|
||||
---
|
||||
|
||||
## Output Artifacts
|
||||
|
||||
| File | Purpose | Lifecycle |
|
||||
|------|---------|-----------|
|
||||
| `tasks.csv` | Master state -- all tasks with status/findings | Updated after each wave |
|
||||
| `wave-{N}.csv` | Per-wave input (temporary, csv-wave tasks only) | Created before wave, deleted after |
|
||||
| `results.csv` | Final export of all task results | Created in Phase 4 |
|
||||
| `discoveries.ndjson` | Shared exploration board (all agents, both modes) | Append-only, carries across waves |
|
||||
| `context.md` | Human-readable execution report | Created in Phase 4 |
|
||||
| `interactive/{id}-result.json` | Results from interactive tasks | Created per interactive task |
|
||||
| `wisdom/` | Cross-sprint knowledge accumulation | Updated by agents via discoveries |
|
||||
|
||||
---
|
||||
|
||||
## Session Structure
|
||||
Coordinator spawns workers using this template:
|
||||
|
||||
```
|
||||
.workflow/.csv-wave/{session-id}/
|
||||
+-- tasks.csv # Master state (all tasks, both modes)
|
||||
+-- results.csv # Final results export
|
||||
+-- discoveries.ndjson # Shared discovery board (all agents)
|
||||
+-- context.md # Human-readable report
|
||||
+-- wave-{N}.csv # Temporary per-wave input (csv-wave only)
|
||||
+-- interactive/ # Interactive task artifacts
|
||||
| +-- {id}-result.json # Per-task results
|
||||
+-- wisdom/ # Cross-sprint knowledge
|
||||
| +-- learnings.md
|
||||
| +-- decisions.md
|
||||
| +-- conventions.md
|
||||
| +-- issues.md
|
||||
+-- design/ # Architect output
|
||||
| +-- design-001.md
|
||||
| +-- task-breakdown.json
|
||||
+-- code/ # Developer tracking
|
||||
| +-- dev-log.md
|
||||
+-- verify/ # Tester output
|
||||
| +-- verify-001.json
|
||||
+-- review/ # Reviewer output
|
||||
+-- review-001.md
|
||||
```
|
||||
spawn_agent({
|
||||
agent_type: "team_worker",
|
||||
items: [
|
||||
{ type: "text", text: `## Role Assignment
|
||||
role: <role>
|
||||
role_spec: <skill_root>/roles/<role>/role.md
|
||||
session: <session-folder>
|
||||
session_id: <session-id>
|
||||
requirement: <task-description>
|
||||
inner_loop: <true|false>
|
||||
|
||||
---
|
||||
Read role_spec file (<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.` },
|
||||
|
||||
## Implementation
|
||||
{ type: "text", text: `## Task Context
|
||||
task_id: <task-id>
|
||||
title: <task-title>
|
||||
description: <task-description>
|
||||
pipeline_phase: <pipeline-phase>` },
|
||||
|
||||
### Session Initialization
|
||||
|
||||
```javascript
|
||||
const getUtc8ISOString = () => new Date(Date.now() + 8 * 60 * 60 * 1000).toISOString()
|
||||
|
||||
// Parse flags
|
||||
const AUTO_YES = $ARGUMENTS.includes('--yes') || $ARGUMENTS.includes('-y')
|
||||
const continueMode = $ARGUMENTS.includes('--continue')
|
||||
const concurrencyMatch = $ARGUMENTS.match(/(?:--concurrency|-c)\s+(\d+)/)
|
||||
const maxConcurrency = concurrencyMatch ? parseInt(concurrencyMatch[1]) : 3
|
||||
|
||||
// Clean requirement text (remove flags)
|
||||
const requirement = $ARGUMENTS
|
||||
.replace(/--yes|-y|--continue|--concurrency\s+\d+|-c\s+\d+/g, '')
|
||||
.trim()
|
||||
|
||||
const slug = requirement.toLowerCase()
|
||||
.replace(/[^a-z0-9\u4e00-\u9fa5]+/g, '-')
|
||||
.substring(0, 40)
|
||||
const dateStr = getUtc8ISOString().substring(0, 10).replace(/-/g, '')
|
||||
let sessionId = `ids-${slug}-${dateStr}`
|
||||
let sessionFolder = `.workflow/.csv-wave/${sessionId}`
|
||||
|
||||
// Continue mode: find existing session
|
||||
if (continueMode) {
|
||||
const existing = Bash(`ls -t .workflow/.csv-wave/ids-* 2>/dev/null | head -1`).trim()
|
||||
if (existing) {
|
||||
sessionId = existing.split('/').pop()
|
||||
sessionFolder = existing
|
||||
// Read existing tasks.csv, find incomplete waves, resume from Phase 2
|
||||
}
|
||||
}
|
||||
|
||||
Bash(`mkdir -p ${sessionFolder}/{interactive,wisdom,design,code,verify,review}`)
|
||||
|
||||
// Initialize wisdom files
|
||||
Write(`${sessionFolder}/wisdom/learnings.md`, `# Learnings\n\n`)
|
||||
Write(`${sessionFolder}/wisdom/decisions.md`, `# Decisions\n\n`)
|
||||
Write(`${sessionFolder}/wisdom/conventions.md`, `# Conventions\n\n`)
|
||||
Write(`${sessionFolder}/wisdom/issues.md`, `# Issues\n\n`)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Phase 0: Pre-Wave Interactive
|
||||
|
||||
**Objective**: Analyze task complexity, explore codebase, and select pipeline mode.
|
||||
|
||||
**Execution**:
|
||||
|
||||
```javascript
|
||||
const analyzer = spawn_agent({
|
||||
message: `
|
||||
## TASK ASSIGNMENT
|
||||
|
||||
### MANDATORY FIRST STEPS (Agent Execute)
|
||||
1. **Read role definition**: ~ or <project>/.codex/skills/team-iterdev/agents/task-analyzer.md (MUST read first)
|
||||
2. Read: .workflow/project-tech.json (if exists)
|
||||
|
||||
---
|
||||
|
||||
Goal: Analyze iterative development task and select pipeline mode
|
||||
Requirement: ${requirement}
|
||||
|
||||
### Task
|
||||
1. Detect capabilities from keywords:
|
||||
- design/architect/restructure -> architect role needed
|
||||
- implement/build/code/fix -> developer role needed
|
||||
- test/verify/validate -> tester role needed
|
||||
- review/audit/quality -> reviewer role needed
|
||||
2. Score complexity for pipeline selection:
|
||||
- Changed files > 10: +3, 3-10: +2
|
||||
- Structural change: +3
|
||||
- Cross-cutting: +2
|
||||
- Simple fix: -2
|
||||
3. Score >= 5 -> multi-sprint, 2-4 -> sprint, 0-1 -> patch
|
||||
4. Return structured analysis result
|
||||
`
|
||||
{ type: "text", text: `## Upstream Context
|
||||
<prev_context>` }
|
||||
]
|
||||
})
|
||||
|
||||
const analyzerResult = wait({ ids: [analyzer], timeout_ms: 120000 })
|
||||
|
||||
if (analyzerResult.timed_out) {
|
||||
send_input({ id: analyzer, message: "Please finalize and output current findings." })
|
||||
const retry = wait({ ids: [analyzer], timeout_ms: 60000 })
|
||||
}
|
||||
|
||||
close_agent({ id: analyzer })
|
||||
|
||||
// Store analysis result
|
||||
Write(`${sessionFolder}/interactive/task-analyzer-result.json`, JSON.stringify({
|
||||
task_id: "task-analysis",
|
||||
status: "completed",
|
||||
pipeline_mode: parsedMode, // "patch" | "sprint" | "multi-sprint"
|
||||
capabilities: parsedCapabilities,
|
||||
complexity_score: parsedScore,
|
||||
roles_needed: parsedRoles,
|
||||
timestamp: getUtc8ISOString()
|
||||
}))
|
||||
```
|
||||
|
||||
If not AUTO_YES, present pipeline mode selection for confirmation:
|
||||
After spawning, use `wait_agent({ ids: [...], timeout_ms: 900000 })` to collect results, then `close_agent({ id })` each worker.
|
||||
|
||||
```javascript
|
||||
if (!AUTO_YES) {
|
||||
const answer = request_user_input({
|
||||
questions: [{
|
||||
question: `Task: "${requirement}" — Recommended: ${pipeline_mode}. Approve or override?`,
|
||||
header: "Pipeline",
|
||||
id: "pipeline_select",
|
||||
options: [
|
||||
{ label: "Approve (Recommended)", description: `Use ${pipeline_mode} pipeline (complexity: ${complexity_score})` },
|
||||
{ label: "Patch", description: "Simple fix: DEV -> VERIFY (2 tasks)" },
|
||||
{ label: "Sprint/Multi", description: "Standard or complex: DESIGN -> DEV -> VERIFY + REVIEW" }
|
||||
]
|
||||
}]
|
||||
})
|
||||
}
|
||||
## User Commands
|
||||
|
||||
| Command | Action |
|
||||
|---------|--------|
|
||||
| `check` / `status` | View execution status graph |
|
||||
| `resume` / `continue` | Advance to next step |
|
||||
|
||||
## Session Directory
|
||||
|
||||
```
|
||||
.workflow/.team/IDS-<slug>-<YYYY-MM-DD>/
|
||||
├── .msg/
|
||||
│ ├── messages.jsonl # Team message bus
|
||||
│ └── meta.json # Session state
|
||||
├── task-analysis.json # Coordinator analyze output
|
||||
├── task-ledger.json # Real-time task progress ledger
|
||||
├── wisdom/ # Cross-task knowledge accumulation
|
||||
│ ├── learnings.md
|
||||
│ ├── decisions.md
|
||||
│ ├── conventions.md
|
||||
│ └── issues.md
|
||||
├── design/ # Architect output
|
||||
│ ├── design-001.md
|
||||
│ └── task-breakdown.json
|
||||
├── code/ # Developer tracking
|
||||
│ └── dev-log.md
|
||||
├── verify/ # Tester output
|
||||
│ └── verify-001.json
|
||||
└── review/ # Reviewer output
|
||||
└── review-001.md
|
||||
```
|
||||
|
||||
**Success Criteria**:
|
||||
- Pipeline mode selected and confirmed
|
||||
- Task analysis stored in session
|
||||
- Interactive agents closed, results stored
|
||||
## Specs Reference
|
||||
|
||||
---
|
||||
|
||||
### Phase 1: Requirement -> CSV + Classification
|
||||
|
||||
**Objective**: Build tasks.csv from selected pipeline mode with proper wave assignments.
|
||||
|
||||
**Decomposition Rules**:
|
||||
|
||||
| Pipeline | Tasks | Wave Structure |
|
||||
|----------|-------|---------------|
|
||||
| patch | DEV-001 -> VERIFY-001 | 2 waves, serial |
|
||||
| sprint | DESIGN-001 -> DEV-001 -> VERIFY-001 + REVIEW-001 | 3 waves (VERIFY and REVIEW parallel in wave 3) |
|
||||
| multi-sprint | DESIGN-001 -> DEV-001 -> VERIFY-001 + REVIEW-001 -> DEV-fix + REVIEW-002 | 4+ waves, with GC loop |
|
||||
|
||||
**Pipeline Task Definitions**:
|
||||
|
||||
#### Patch Pipeline (2 csv-wave tasks)
|
||||
|
||||
| Task ID | Role | Wave | Deps | Description |
|
||||
|---------|------|------|------|-------------|
|
||||
| DEV-001 | developer | 1 | (none) | Implement fix: load target files, apply changes, validate syntax |
|
||||
| VERIFY-001 | tester | 2 | DEV-001 | Verify fix: detect test framework, run targeted tests, check for regressions |
|
||||
|
||||
#### Sprint Pipeline (4 csv-wave tasks)
|
||||
|
||||
| Task ID | Role | Wave | Deps | Description |
|
||||
|---------|------|------|------|-------------|
|
||||
| DESIGN-001 | architect | 1 | (none) | Technical design: explore codebase, create component design, task breakdown |
|
||||
| DEV-001 | developer | 2 | DESIGN-001 | Implement design: load design and task breakdown, implement in order, validate syntax |
|
||||
| VERIFY-001 | tester | 3 | DEV-001 | Verify implementation: detect framework, run targeted tests, run regression suite |
|
||||
| REVIEW-001 | reviewer | 3 | DEV-001 | Code review: load changes and design, review across correctness/completeness/maintainability/security, score quality |
|
||||
|
||||
#### Multi-Sprint Pipeline (5+ csv-wave tasks + GC control)
|
||||
|
||||
| Task ID | Role | Wave | Deps | Description |
|
||||
|---------|------|------|------|-------------|
|
||||
| DESIGN-001 | architect | 1 | (none) | Technical design and task breakdown for sprint 1 |
|
||||
| DEV-001 | developer | 2 | DESIGN-001 | First implementation batch |
|
||||
| VERIFY-001 | tester | 3 | DEV-001 | Test execution and fix cycle |
|
||||
| REVIEW-001 | reviewer | 3 | DEV-001 | Code review with GC signal |
|
||||
| GC-CHECK-001 | gc-controller | 4 | REVIEW-001 | GC decision: revision or convergence |
|
||||
|
||||
Additional DEV-fix and REVIEW tasks created dynamically when GC controller decides REVISION.
|
||||
|
||||
**Classification Rules**:
|
||||
|
||||
All work tasks (design, development, testing, review) are `csv-wave`. GC loop control between reviewer and next dev-fix is `interactive` (post-wave, spawned by orchestrator to decide the GC outcome).
|
||||
|
||||
**Wave Computation**: Kahn's BFS topological sort with depth tracking (csv-wave tasks only).
|
||||
|
||||
**User Validation**: Display task breakdown with wave + exec_mode assignment (skip if AUTO_YES).
|
||||
|
||||
**Success Criteria**:
|
||||
- tasks.csv created with valid schema, wave, and exec_mode assignments
|
||||
- No circular dependencies
|
||||
- User approved (or AUTO_YES)
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Wave Execution Engine (Extended)
|
||||
|
||||
**Objective**: Execute tasks wave-by-wave with hybrid mechanism support and cross-wave context propagation.
|
||||
|
||||
```javascript
|
||||
const failedIds = new Set()
|
||||
const skippedIds = new Set()
|
||||
const MAX_GC_ROUNDS = 3
|
||||
let gcRound = 0
|
||||
|
||||
for (let wave = 1; wave <= maxWave; wave++) {
|
||||
console.log(`\n## Wave ${wave}/${maxWave}\n`)
|
||||
|
||||
// 1. Read current master CSV
|
||||
const masterCsv = parseCsv(Read(`${sessionFolder}/tasks.csv`))
|
||||
|
||||
// 2. Separate csv-wave and interactive tasks for this wave
|
||||
const waveTasks = masterCsv.filter(row => parseInt(row.wave) === wave)
|
||||
const csvTasks = waveTasks.filter(t => t.exec_mode === 'csv-wave')
|
||||
const interactiveTasks = waveTasks.filter(t => t.exec_mode === 'interactive')
|
||||
|
||||
// 3. Skip tasks whose deps failed
|
||||
const executableCsvTasks = []
|
||||
for (const task of csvTasks) {
|
||||
const deps = task.deps.split(';').filter(Boolean)
|
||||
if (deps.some(d => failedIds.has(d) || skippedIds.has(d))) {
|
||||
skippedIds.add(task.id)
|
||||
updateMasterCsvRow(sessionFolder, task.id, {
|
||||
status: 'skipped',
|
||||
error: 'Dependency failed or skipped'
|
||||
})
|
||||
continue
|
||||
}
|
||||
executableCsvTasks.push(task)
|
||||
}
|
||||
|
||||
// 4. Build prev_context for each csv-wave task
|
||||
for (const task of executableCsvTasks) {
|
||||
const contextIds = task.context_from.split(';').filter(Boolean)
|
||||
const prevFindings = contextIds
|
||||
.map(id => {
|
||||
const prevRow = masterCsv.find(r => r.id === id)
|
||||
if (prevRow && prevRow.status === 'completed' && prevRow.findings) {
|
||||
return `[Task ${id}: ${prevRow.title}] ${prevRow.findings}`
|
||||
}
|
||||
return null
|
||||
})
|
||||
.filter(Boolean)
|
||||
.join('\n')
|
||||
task.prev_context = prevFindings || 'No previous context available'
|
||||
}
|
||||
|
||||
// 5. Write wave CSV and execute csv-wave tasks
|
||||
if (executableCsvTasks.length > 0) {
|
||||
const waveHeader = 'id,title,description,role,pipeline,sprint_num,gc_round,deps,context_from,exec_mode,wave,prev_context'
|
||||
const waveRows = executableCsvTasks.map(t =>
|
||||
[t.id, t.title, t.description, t.role, t.pipeline, t.sprint_num, t.gc_round, t.deps, t.context_from, t.exec_mode, t.wave, t.prev_context]
|
||||
.map(cell => `"${String(cell).replace(/"/g, '""')}"`)
|
||||
.join(',')
|
||||
)
|
||||
Write(`${sessionFolder}/wave-${wave}.csv`, [waveHeader, ...waveRows].join('\n'))
|
||||
|
||||
const waveResult = spawn_agents_on_csv({
|
||||
csv_path: `${sessionFolder}/wave-${wave}.csv`,
|
||||
id_column: "id",
|
||||
instruction: Read(`~ or <project>/.codex/skills/team-iterdev/instructions/agent-instruction.md`),
|
||||
max_concurrency: maxConcurrency,
|
||||
max_runtime_seconds: 900,
|
||||
output_csv_path: `${sessionFolder}/wave-${wave}-results.csv`,
|
||||
output_schema: {
|
||||
type: "object",
|
||||
properties: {
|
||||
id: { type: "string" },
|
||||
status: { type: "string", enum: ["completed", "failed"] },
|
||||
findings: { type: "string" },
|
||||
review_score: { type: "string" },
|
||||
gc_signal: { type: "string" },
|
||||
error: { type: "string" }
|
||||
},
|
||||
required: ["id", "status", "findings"]
|
||||
}
|
||||
})
|
||||
|
||||
// Merge results into master CSV
|
||||
const waveResults = parseCsv(Read(`${sessionFolder}/wave-${wave}-results.csv`))
|
||||
for (const result of waveResults) {
|
||||
updateMasterCsvRow(sessionFolder, result.id, {
|
||||
status: result.status,
|
||||
findings: result.findings || '',
|
||||
review_score: result.review_score || '',
|
||||
gc_signal: result.gc_signal || '',
|
||||
error: result.error || ''
|
||||
})
|
||||
if (result.status === 'failed') failedIds.add(result.id)
|
||||
}
|
||||
|
||||
Bash(`rm -f "${sessionFolder}/wave-${wave}.csv"`)
|
||||
}
|
||||
|
||||
// 6. Execute post-wave interactive tasks (GC controller)
|
||||
for (const task of interactiveTasks) {
|
||||
if (task.status !== 'pending') continue
|
||||
const deps = task.deps.split(';').filter(Boolean)
|
||||
if (deps.some(d => failedIds.has(d) || skippedIds.has(d))) {
|
||||
skippedIds.add(task.id)
|
||||
continue
|
||||
}
|
||||
|
||||
// Spawn GC controller agent
|
||||
const gcAgent = spawn_agent({
|
||||
message: `
|
||||
## TASK ASSIGNMENT
|
||||
|
||||
### MANDATORY FIRST STEPS (Agent Execute)
|
||||
1. **Read role definition**: ~ or <project>/.codex/skills/team-iterdev/agents/gc-controller.md (MUST read first)
|
||||
2. Read: ${sessionFolder}/discoveries.ndjson (shared discoveries)
|
||||
|
||||
---
|
||||
|
||||
Goal: Evaluate review severity and decide DEV-fix vs convergence
|
||||
Session: ${sessionFolder}
|
||||
GC Round: ${gcRound}
|
||||
Max GC Rounds: ${MAX_GC_ROUNDS}
|
||||
|
||||
### Context
|
||||
Read the latest review file in ${sessionFolder}/review/ and check:
|
||||
- review.critical_count > 0 OR review.score < 7 -> REVISION
|
||||
- review.critical_count == 0 AND review.score >= 7 -> CONVERGE
|
||||
If gcRound >= maxRounds -> CONVERGE (force convergence)
|
||||
`
|
||||
})
|
||||
|
||||
const gcResult = wait({ ids: [gcAgent], timeout_ms: 120000 })
|
||||
if (gcResult.timed_out) {
|
||||
send_input({ id: gcAgent, message: "Please finalize your decision now." })
|
||||
wait({ ids: [gcAgent], timeout_ms: 60000 })
|
||||
}
|
||||
close_agent({ id: gcAgent })
|
||||
|
||||
Write(`${sessionFolder}/interactive/${task.id}-result.json`, JSON.stringify({
|
||||
task_id: task.id, status: "completed",
|
||||
gc_decision: gcDecision, gc_round: gcRound,
|
||||
timestamp: getUtc8ISOString()
|
||||
}))
|
||||
|
||||
if (gcDecision === "CONVERGE") {
|
||||
// Skip remaining GC tasks, mark fix tasks as skipped
|
||||
} else {
|
||||
gcRound++
|
||||
// Dynamically add DEV-fix and REVIEW tasks to master CSV for next waves
|
||||
const fixWave = wave + 1
|
||||
const reviewWave = wave + 2
|
||||
appendMasterCsvRow(sessionFolder, {
|
||||
id: `DEV-fix-${gcRound}`, title: `Fix review issues (round ${gcRound})`,
|
||||
description: `Fix critical/high issues from REVIEW. Focus on review feedback only.`,
|
||||
role: 'developer', pipeline: pipeline_mode, sprint_num: '1',
|
||||
gc_round: String(gcRound), deps: task.id, context_from: `REVIEW-001`,
|
||||
exec_mode: 'csv-wave', wave: String(fixWave),
|
||||
status: 'pending', findings: '', review_score: '', gc_signal: '', error: ''
|
||||
})
|
||||
appendMasterCsvRow(sessionFolder, {
|
||||
id: `REVIEW-${gcRound + 1}`, title: `Re-review (round ${gcRound})`,
|
||||
description: `Review fixes from DEV-fix-${gcRound}. Re-evaluate quality.`,
|
||||
role: 'reviewer', pipeline: pipeline_mode, sprint_num: '1',
|
||||
gc_round: String(gcRound), deps: `DEV-fix-${gcRound}`, context_from: `DEV-fix-${gcRound}`,
|
||||
exec_mode: 'csv-wave', wave: String(reviewWave),
|
||||
status: 'pending', findings: '', review_score: '', gc_signal: '', error: ''
|
||||
})
|
||||
maxWave = Math.max(maxWave, reviewWave)
|
||||
}
|
||||
|
||||
updateMasterCsvRow(sessionFolder, task.id, { status: 'completed', findings: `GC decision: ${gcDecision}` })
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Success Criteria**:
|
||||
- All waves executed in order
|
||||
- Both csv-wave and interactive tasks handled per wave
|
||||
- Each wave's results merged into master CSV before next wave starts
|
||||
- Dependent tasks skipped when predecessor failed
|
||||
- discoveries.ndjson accumulated across all waves and mechanisms
|
||||
- GC loop controlled with max 3 rounds
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Post-Wave Interactive
|
||||
|
||||
**Objective**: Handle any final GC loop convergence and multi-sprint transitions.
|
||||
|
||||
If the pipeline is multi-sprint and the current sprint completed successfully:
|
||||
1. Evaluate sprint metrics (velocity, review scores)
|
||||
2. If more sprints needed, dynamically create next sprint tasks in master CSV
|
||||
3. If sprint metrics are strong (review avg >= 8), consider downgrading next sprint to simpler pipeline
|
||||
|
||||
If max GC rounds reached and issues remain, log to wisdom/issues.md and proceed.
|
||||
|
||||
**Success Criteria**:
|
||||
- Post-wave interactive processing complete
|
||||
- Interactive agents closed, results stored
|
||||
|
||||
---
|
||||
|
||||
### Phase 4: Results Aggregation
|
||||
|
||||
**Objective**: Generate final results and human-readable report.
|
||||
|
||||
```javascript
|
||||
const masterCsv = Read(`${sessionFolder}/tasks.csv`)
|
||||
Write(`${sessionFolder}/results.csv`, masterCsv)
|
||||
|
||||
const tasks = parseCsv(masterCsv)
|
||||
const completed = tasks.filter(t => t.status === 'completed')
|
||||
const failed = tasks.filter(t => t.status === 'failed')
|
||||
const skipped = tasks.filter(t => t.status === 'skipped')
|
||||
|
||||
const contextContent = `# Team IterDev Report
|
||||
|
||||
**Session**: ${sessionId}
|
||||
**Requirement**: ${requirement}
|
||||
**Pipeline**: ${pipeline_mode}
|
||||
**Completed**: ${getUtc8ISOString()}
|
||||
|
||||
---
|
||||
|
||||
## Summary
|
||||
|
||||
| Metric | Count |
|
||||
|--------|-------|
|
||||
| Total Tasks | ${tasks.length} |
|
||||
| Completed | ${completed.length} |
|
||||
| Failed | ${failed.length} |
|
||||
| Skipped | ${skipped.length} |
|
||||
| GC Rounds | ${gcRound} |
|
||||
|
||||
---
|
||||
|
||||
## Pipeline Execution
|
||||
|
||||
${waveDetails}
|
||||
|
||||
---
|
||||
|
||||
## Task Details
|
||||
|
||||
${taskDetails}
|
||||
|
||||
---
|
||||
|
||||
## Deliverables
|
||||
|
||||
| Artifact | Path |
|
||||
|----------|------|
|
||||
| Design Document | ${sessionFolder}/design/design-001.md |
|
||||
| Task Breakdown | ${sessionFolder}/design/task-breakdown.json |
|
||||
| Dev Log | ${sessionFolder}/code/dev-log.md |
|
||||
| Verification | ${sessionFolder}/verify/verify-001.json |
|
||||
| Review Report | ${sessionFolder}/review/review-001.md |
|
||||
| Wisdom | ${sessionFolder}/wisdom/ |
|
||||
`
|
||||
|
||||
Write(`${sessionFolder}/context.md`, contextContent)
|
||||
```
|
||||
|
||||
If not AUTO_YES, offer completion actions:
|
||||
|
||||
```javascript
|
||||
if (!AUTO_YES) {
|
||||
request_user_input({
|
||||
questions: [{
|
||||
question: "IterDev pipeline complete. Choose next action.",
|
||||
header: "Done",
|
||||
id: "completion",
|
||||
options: [
|
||||
{ label: "Archive (Recommended)", description: "Archive session, generate final report" },
|
||||
{ label: "Keep Active", description: "Keep session for follow-up or inspection" },
|
||||
{ label: "Retry Failed", description: "Re-run failed tasks" }
|
||||
]
|
||||
}]
|
||||
})
|
||||
}
|
||||
```
|
||||
|
||||
**Success Criteria**:
|
||||
- results.csv exported (all tasks, both modes)
|
||||
- context.md generated
|
||||
- All interactive agents closed
|
||||
- Summary displayed to user
|
||||
|
||||
---
|
||||
|
||||
## Shared Discovery Board Protocol
|
||||
|
||||
All agents across all waves share `discoveries.ndjson`. This enables cross-role knowledge sharing.
|
||||
|
||||
**Discovery Types**:
|
||||
|
||||
| Type | Dedup Key | Data Schema | Description |
|
||||
|------|-----------|-------------|-------------|
|
||||
| `design_decision` | `data.component` | `{component, approach, rationale, alternatives}` | Architecture decision |
|
||||
| `implementation` | `data.file` | `{file, changes, pattern_used, notes}` | Code implementation detail |
|
||||
| `test_result` | `data.test_suite` | `{test_suite, pass_rate, failures[], regressions}` | Test execution result |
|
||||
| `review_finding` | `data.file_line` | `{file_line, severity, dimension, description, suggestion}` | Review finding |
|
||||
| `convention` | `data.name` | `{name, description, example}` | Discovered project convention |
|
||||
| `gc_decision` | `data.round` | `{round, signal, critical_count, score}` | GC loop decision |
|
||||
|
||||
**Format**: NDJSON, each line is self-contained JSON:
|
||||
|
||||
```jsonl
|
||||
{"ts":"2026-03-08T10:00:00+08:00","worker":"DESIGN-001","type":"design_decision","data":{"component":"AuthModule","approach":"JWT with refresh tokens","rationale":"Stateless auth for microservices","alternatives":"Session-based, OAuth2"}}
|
||||
{"ts":"2026-03-08T10:05:00+08:00","worker":"DEV-001","type":"implementation","data":{"file":"src/auth/jwt.ts","changes":"Added JWT middleware","pattern_used":"Express middleware pattern","notes":"Uses existing bcrypt dependency"}}
|
||||
{"ts":"2026-03-08T10:10:00+08:00","worker":"REVIEW-001","type":"review_finding","data":{"file_line":"src/auth/jwt.ts:42","severity":"HIGH","dimension":"security","description":"Token expiry not validated","suggestion":"Add exp claim check"}}
|
||||
```
|
||||
|
||||
**Protocol Rules**:
|
||||
1. Read board before own work -- leverage existing context
|
||||
2. Write discoveries immediately via `echo >>` -- don't batch
|
||||
3. Deduplicate -- check existing entries by type + dedup key
|
||||
4. Append-only -- never modify or delete existing lines
|
||||
|
||||
---
|
||||
|
||||
## Consensus Severity Routing
|
||||
|
||||
When the reviewer returns review results with severity-graded verdicts:
|
||||
|
||||
| Severity | Action |
|
||||
|----------|--------|
|
||||
| HIGH | Trigger DEV-fix round (GC loop), max 3 rounds total |
|
||||
| MEDIUM | Log warning, continue pipeline |
|
||||
| LOW | Treat as review passed |
|
||||
|
||||
**Constraints**: Max 3 GC rounds (fix cycles). If still HIGH after 3 rounds, force convergence and record in wisdom/issues.md.
|
||||
|
||||
---
|
||||
- [specs/pipelines.md](specs/pipelines.md) — Pipeline definitions and task registry
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Resolution |
|
||||
|-------|------------|
|
||||
| Circular dependency | Detect in wave computation, abort with error message |
|
||||
| CSV agent timeout | Mark as failed in results, continue with wave |
|
||||
| CSV agent failed | Mark as failed, skip dependent tasks in later waves |
|
||||
| Interactive agent timeout | Urge convergence via send_input, then close if still timed out |
|
||||
| Interactive agent failed | Mark as failed, skip dependents |
|
||||
| All agents in wave failed | Log error, offer retry or abort |
|
||||
| CSV parse error | Validate CSV format before execution, show line number |
|
||||
| discoveries.ndjson corrupt | Ignore malformed lines, continue with valid entries |
|
||||
| GC loop exceeds 3 rounds | Force convergence, record in wisdom/issues.md |
|
||||
| Sprint velocity drops below 50% | Report to user, suggest scope reduction |
|
||||
| Task ledger corrupted | Rebuild from tasks.csv state |
|
||||
| Continue mode: no session found | List available sessions, prompt user to select |
|
||||
|
||||
---
|
||||
|
||||
## Core Rules
|
||||
|
||||
1. **Start Immediately**: First action is session initialization, then Phase 0/1
|
||||
2. **Wave Order is Sacred**: Never execute wave N before wave N-1 completes and results are merged
|
||||
3. **CSV is Source of Truth**: Master tasks.csv holds all state (both csv-wave and interactive)
|
||||
4. **CSV First**: Default to csv-wave for tasks; only use interactive when interaction pattern requires it
|
||||
5. **Context Propagation**: prev_context built from master CSV, not from memory
|
||||
6. **Discovery Board is Append-Only**: Never clear, modify, or recreate discoveries.ndjson -- both mechanisms share it
|
||||
7. **Skip on Failure**: If a dependency failed, skip the dependent task (regardless of mechanism)
|
||||
8. **Lifecycle Balance**: Every spawn_agent MUST have a matching close_agent
|
||||
9. **Cleanup Temp Files**: Remove wave-{N}.csv after results are merged
|
||||
10. **DO NOT STOP**: Continuous execution until all waves complete or all remaining tasks are skipped
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Coordinator Role Constraints (Main Agent)
|
||||
|
||||
**CRITICAL**: The coordinator (main agent executing this skill) is responsible for **orchestration only**, NOT implementation.
|
||||
|
||||
15. **Coordinator Does NOT Execute Code**: The main agent MUST NOT write, modify, or implement any code directly. All implementation work is delegated to spawned team agents. The coordinator only:
|
||||
- Spawns agents with task assignments
|
||||
- Waits for agent callbacks
|
||||
- Merges results and coordinates workflow
|
||||
- Manages workflow transitions between phases
|
||||
|
||||
16. **Patient Waiting is Mandatory**: Agent execution takes significant time (typically 10-30 minutes per phase, sometimes longer). The coordinator MUST:
|
||||
- Wait patiently for `wait()` calls to complete
|
||||
- NOT skip workflow steps due to perceived delays
|
||||
- NOT assume agents have failed just because they're taking time
|
||||
- Trust the timeout mechanisms defined in the skill
|
||||
|
||||
17. **Use send_input for Clarification**: When agents need guidance or appear stuck, the coordinator MUST:
|
||||
- Use `send_input()` to ask questions or provide clarification
|
||||
- NOT skip the agent or move to next phase prematurely
|
||||
- Give agents opportunity to respond before escalating
|
||||
- Example: `send_input({ id: agent_id, message: "Please provide status update or clarify blockers" })`
|
||||
|
||||
18. **No Workflow Shortcuts**: The coordinator MUST NOT:
|
||||
- Skip phases or stages defined in the workflow
|
||||
- Bypass required approval or review steps
|
||||
- Execute dependent tasks before prerequisites complete
|
||||
- Assume task completion without explicit agent callback
|
||||
- Make up or fabricate agent results
|
||||
|
||||
19. **Respect Long-Running Processes**: This is a complex multi-agent workflow that requires patience:
|
||||
- Total execution time may range from 30-90 minutes or longer
|
||||
- Each phase may take 10-30 minutes depending on complexity
|
||||
- The coordinator must remain active and attentive throughout the entire process
|
||||
- Do not terminate or skip steps due to time concerns
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| Unknown command | Error with available command list |
|
||||
| Role not found | Error with role registry |
|
||||
| GC loop exceeds 3 rounds | Accept with warning, record in shared memory |
|
||||
| Sprint velocity drops below 50% | Coordinator alerts user, suggests scope reduction |
|
||||
| Task ledger corrupted | Rebuild from TaskList state |
|
||||
| Conflict detected | Update conflict_info, notify coordinator, create DEV-fix task |
|
||||
| Pipeline deadlock | Check blockedBy chain, report blocking point |
|
||||
|
||||
@@ -1,193 +0,0 @@
|
||||
# GC Controller Agent
|
||||
|
||||
Evaluate review severity after REVIEW wave and decide whether to trigger a DEV-fix iteration or converge the pipeline.
|
||||
|
||||
## Identity
|
||||
|
||||
- **Type**: `interactive`
|
||||
- **Role File**: `agents/gc-controller.md`
|
||||
- **Responsibility**: Evaluate review severity, decide DEV-fix vs convergence
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
- Load role definition via MANDATORY FIRST STEPS pattern
|
||||
- Load review results from completed REVIEW tasks
|
||||
- Evaluate gc_signal and review_score to determine decision
|
||||
- Respect max iteration count to prevent infinite loops
|
||||
- Produce structured output with clear CONVERGE/FIX/ESCALATE decision
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Skip the MANDATORY FIRST STEPS role loading
|
||||
- Modify source code directly
|
||||
- Produce unstructured output
|
||||
- Exceed max iteration count without escalating
|
||||
- Ignore Critical findings in review results
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Tools
|
||||
|
||||
| Tool | Type | Purpose |
|
||||
|------|------|---------|
|
||||
| `Read` | builtin | Load review results and session state |
|
||||
| `Write` | builtin | Create FIX task definitions for next wave |
|
||||
| `Bash` | builtin | Query session state, count iterations |
|
||||
|
||||
### Tool Usage Patterns
|
||||
|
||||
**Read Pattern**: Load review results
|
||||
```
|
||||
Read("{session_folder}/artifacts/review-results.json")
|
||||
Read("{session_folder}/session-state.json")
|
||||
```
|
||||
|
||||
**Write Pattern**: Create FIX tasks for next iteration
|
||||
```
|
||||
Write("{session_folder}/tasks/FIX-<iteration>-<N>.json", <task>)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
|
||||
### Phase 1: Review Loading
|
||||
|
||||
**Objective**: Load review results from completed REVIEW tasks.
|
||||
|
||||
**Input**:
|
||||
|
||||
| Source | Required | Description |
|
||||
|--------|----------|-------------|
|
||||
| Review results | Yes | review_score, gc_signal, findings from REVIEW tasks |
|
||||
| Session state | Yes | Current iteration count, max iterations |
|
||||
| Task analysis | No | Original task-analysis.json for context |
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Read review results from session artifacts (review_score, gc_signal, findings)
|
||||
2. Read session state to determine current iteration number
|
||||
3. Read max_iterations from task-analysis.json or default to 3
|
||||
|
||||
**Output**: Loaded review context with iteration state
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Severity Evaluation
|
||||
|
||||
**Objective**: Evaluate review severity and determine pipeline decision.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. **Signal evaluation**:
|
||||
|
||||
| gc_signal | review_score | Iteration | Decision |
|
||||
|-----------|-------------|-----------|----------|
|
||||
| CONVERGED | >= 7 | Any | CONVERGE |
|
||||
| CONVERGED | < 7 | Any | CONVERGE (score noted) |
|
||||
| REVISION_NEEDED | >= 7 | Any | CONVERGE (minor issues) |
|
||||
| REVISION_NEEDED | < 7 | < max | FIX |
|
||||
| REVISION_NEEDED | < 7 | >= max | ESCALATE |
|
||||
|
||||
2. **Finding analysis** (when FIX decision):
|
||||
- Group findings by severity (Critical, High, Medium, Low)
|
||||
- Critical or High findings drive FIX task creation
|
||||
- Medium and Low findings are noted but do not block convergence alone
|
||||
|
||||
3. **Iteration guard**:
|
||||
- Track current iteration count
|
||||
- If iteration >= max_iterations (default 3): force ESCALATE regardless of score
|
||||
- Include iteration history in decision reasoning
|
||||
|
||||
**Output**: GC decision with reasoning
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Decision Execution
|
||||
|
||||
**Objective**: Execute the GC decision.
|
||||
|
||||
| Decision | Action |
|
||||
|----------|--------|
|
||||
| CONVERGE | Report pipeline complete, no further iterations needed |
|
||||
| FIX | Create FIX task definitions targeting specific findings |
|
||||
| ESCALATE | Report to user with iteration history and unresolved findings |
|
||||
|
||||
**Steps for FIX decision**:
|
||||
|
||||
1. Extract actionable findings (Critical and High severity)
|
||||
2. Group findings by target file or module
|
||||
3. Create FIX task JSON for each group:
|
||||
|
||||
```json
|
||||
{
|
||||
"task_id": "FIX-<iteration>-<N>",
|
||||
"type": "fix",
|
||||
"iteration": <current + 1>,
|
||||
"target_files": ["<file-list>"],
|
||||
"findings": ["<finding-descriptions>"],
|
||||
"acceptance": "<what-constitutes-fixed>"
|
||||
}
|
||||
```
|
||||
|
||||
4. Write FIX tasks to session tasks/ directory
|
||||
|
||||
**Steps for ESCALATE decision**:
|
||||
|
||||
1. Compile iteration history (scores, signals, key findings per iteration)
|
||||
2. List unresolved Critical/High findings
|
||||
3. Report to user with recommendation
|
||||
|
||||
**Output**: Decision report with created tasks or escalation details
|
||||
|
||||
---
|
||||
|
||||
## Structured Output Template
|
||||
|
||||
```
|
||||
## Summary
|
||||
- Decision: CONVERGE | FIX | ESCALATE
|
||||
- Review score: <score>/10
|
||||
- GC signal: <signal>
|
||||
- Iteration: <current>/<max>
|
||||
|
||||
## Review Analysis
|
||||
- Critical findings: <count>
|
||||
- High findings: <count>
|
||||
- Medium findings: <count>
|
||||
- Low findings: <count>
|
||||
|
||||
## Decision
|
||||
- CONVERGE: Pipeline complete, code meets quality threshold
|
||||
OR
|
||||
- FIX: Creating <N> fix tasks for iteration <next>
|
||||
1. FIX-<id>: <description> targeting <files>
|
||||
2. FIX-<id>: <description> targeting <files>
|
||||
OR
|
||||
- ESCALATE: Max iterations reached, unresolved issues require user input
|
||||
1. Unresolved: <finding-description>
|
||||
2. Unresolved: <finding-description>
|
||||
|
||||
## Iteration History
|
||||
- Iteration 1: score=<N>, signal=<signal>, findings=<count>
|
||||
- Iteration 2: score=<N>, signal=<signal>, findings=<count>
|
||||
|
||||
## Reasoning
|
||||
- <Why this decision was made>
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| Review results not found | Report as error, cannot make GC decision |
|
||||
| Missing gc_signal field | Infer from review_score: >= 7 treat as CONVERGED, < 7 as REVISION_NEEDED |
|
||||
| Missing review_score field | Infer from gc_signal and findings count |
|
||||
| Session state corrupted | Default to iteration 1, note uncertainty |
|
||||
| Timeout approaching | Output current decision with "PARTIAL" status |
|
||||
@@ -1,206 +0,0 @@
|
||||
# Task Analyzer Agent
|
||||
|
||||
Analyze task complexity, detect required capabilities, and select the appropriate pipeline mode for iterative development.
|
||||
|
||||
## Identity
|
||||
|
||||
- **Type**: `interactive`
|
||||
- **Role File**: `agents/task-analyzer.md`
|
||||
- **Responsibility**: Analyze task complexity, detect required capabilities, select pipeline mode
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
- Load role definition via MANDATORY FIRST STEPS pattern
|
||||
- Parse user requirement to detect project type
|
||||
- Analyze complexity by file count and dependency depth
|
||||
- Select appropriate pipeline mode based on analysis
|
||||
- Produce structured output with task-analysis JSON
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Skip the MANDATORY FIRST STEPS role loading
|
||||
- Modify source code or project files
|
||||
- Produce unstructured output
|
||||
- Select pipeline mode without analyzing the codebase
|
||||
- Begin implementation work
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Tools
|
||||
|
||||
| Tool | Type | Purpose |
|
||||
|------|------|---------|
|
||||
| `Read` | builtin | Load project files, configs, package manifests |
|
||||
| `Glob` | builtin | Discover project files and estimate scope |
|
||||
| `Grep` | builtin | Detect frameworks, dependencies, patterns |
|
||||
| `Bash` | builtin | Run detection commands, count files |
|
||||
|
||||
### Tool Usage Patterns
|
||||
|
||||
**Glob Pattern**: Estimate scope by file discovery
|
||||
```
|
||||
Glob("src/**/*.ts")
|
||||
Glob("**/*.test.*")
|
||||
Glob("**/package.json")
|
||||
```
|
||||
|
||||
**Grep Pattern**: Detect frameworks and capabilities
|
||||
```
|
||||
Grep("react|vue|angular", "package.json")
|
||||
Grep("jest|vitest|mocha", "package.json")
|
||||
```
|
||||
|
||||
**Read Pattern**: Load project configuration
|
||||
```
|
||||
Read("package.json")
|
||||
Read("tsconfig.json")
|
||||
Read("pyproject.toml")
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Execution
|
||||
|
||||
### Phase 1: Requirement Parsing
|
||||
|
||||
**Objective**: Parse user requirement and detect project type.
|
||||
|
||||
**Input**:
|
||||
|
||||
| Source | Required | Description |
|
||||
|--------|----------|-------------|
|
||||
| User requirement | Yes | Task description from $ARGUMENTS |
|
||||
| Project root | Yes | Working directory for codebase analysis |
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Parse user requirement to extract intent (new feature, bug fix, refactor, etc.)
|
||||
2. Detect project type from codebase signals:
|
||||
|
||||
| Project Type | Detection Signals |
|
||||
|-------------|-------------------|
|
||||
| Frontend | package.json with react/vue/angular, src/**/*.tsx |
|
||||
| Backend | server.ts, app.py, go.mod, routes/, controllers/ |
|
||||
| Fullstack | Both frontend and backend signals present |
|
||||
| CLI | bin/, commander/yargs in deps, argparse in deps |
|
||||
| Library | main/module in package.json, src/lib/, no app entry |
|
||||
|
||||
3. Identify primary language and framework from project files
|
||||
|
||||
**Output**: Project type classification and requirement intent
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Complexity Analysis
|
||||
|
||||
**Objective**: Estimate scope, detect capabilities, and assess dependency depth.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. **Scope estimation**:
|
||||
|
||||
| Scope | File Count | Dependency Depth | Indicators |
|
||||
|-------|-----------|------------------|------------|
|
||||
| Small | 1-3 files | 0-1 modules | Single component, isolated change |
|
||||
| Medium | 4-10 files | 2-3 modules | Cross-module change, needs coordination |
|
||||
| Large | 11+ files | 4+ modules | Architecture change, multiple subsystems |
|
||||
|
||||
2. **Capability detection**:
|
||||
- Language: TypeScript, Python, Go, Java, etc.
|
||||
- Testing framework: jest, vitest, pytest, go test, etc.
|
||||
- Build system: webpack, vite, esbuild, setuptools, etc.
|
||||
- Linting: eslint, prettier, ruff, etc.
|
||||
- Type checking: tsc, mypy, etc.
|
||||
|
||||
3. **Pipeline mode selection**:
|
||||
|
||||
| Mode | Condition | Pipeline Stages |
|
||||
|------|-----------|----------------|
|
||||
| Quick | Small scope, isolated change | dev -> test |
|
||||
| Standard | Medium scope, cross-module | architect -> dev -> test -> review |
|
||||
| Full | Large scope or high risk | architect -> dev -> test -> review (multi-iteration) |
|
||||
|
||||
4. **Risk assessment**:
|
||||
- Breaking change potential (public API modifications)
|
||||
- Test coverage gaps (areas without existing tests)
|
||||
- Dependency complexity (shared modules, circular refs)
|
||||
|
||||
**Output**: Scope, capabilities, pipeline mode, and risk assessment
|
||||
|
||||
---
|
||||
|
||||
### Phase 3: Analysis Report
|
||||
|
||||
**Objective**: Write task-analysis result as structured JSON.
|
||||
|
||||
**Steps**:
|
||||
|
||||
1. Assemble task-analysis JSON:
|
||||
|
||||
```json
|
||||
{
|
||||
"project_type": "<frontend|backend|fullstack|cli|library>",
|
||||
"intent": "<feature|bugfix|refactor|test|docs>",
|
||||
"scope": "<small|medium|large>",
|
||||
"pipeline_mode": "<quick|standard|full>",
|
||||
"capabilities": {
|
||||
"language": "<primary-language>",
|
||||
"framework": "<primary-framework>",
|
||||
"test_framework": "<test-framework>",
|
||||
"build_system": "<build-system>"
|
||||
},
|
||||
"affected_files": ["<estimated-file-list>"],
|
||||
"risk_factors": ["<risk-1>", "<risk-2>"],
|
||||
"max_iterations": <1|2|3>
|
||||
}
|
||||
```
|
||||
|
||||
2. Report analysis summary to user
|
||||
|
||||
**Output**: task-analysis.json written to session artifacts
|
||||
|
||||
---
|
||||
|
||||
## Structured Output Template
|
||||
|
||||
```
|
||||
## Summary
|
||||
- Project: <project-type> (<language>/<framework>)
|
||||
- Scope: <small|medium|large> (~<N> files)
|
||||
- Pipeline: <quick|standard|full>
|
||||
|
||||
## Capabilities Detected
|
||||
- Language: <language>
|
||||
- Framework: <framework>
|
||||
- Testing: <test-framework>
|
||||
- Build: <build-system>
|
||||
|
||||
## Complexity Assessment
|
||||
- File count: <N> files affected
|
||||
- Dependency depth: <N> modules
|
||||
- Risk factors: <list>
|
||||
|
||||
## Pipeline Selection
|
||||
- Mode: <mode> — <rationale>
|
||||
- Stages: <stage-1> -> <stage-2> -> ...
|
||||
- Max iterations: <N>
|
||||
|
||||
## Task Analysis JSON
|
||||
- Written to: <session>/artifacts/task-analysis.json
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| Empty project directory | Report as unknown project type, default to standard pipeline |
|
||||
| No package manifest found | Infer from file extensions, note reduced confidence |
|
||||
| Ambiguous project type | Report both candidates, select most likely |
|
||||
| Cannot determine scope | Default to medium, note uncertainty |
|
||||
| Timeout approaching | Output current analysis with "PARTIAL" status |
|
||||
@@ -1,118 +0,0 @@
|
||||
## TASK ASSIGNMENT
|
||||
|
||||
### MANDATORY FIRST STEPS
|
||||
1. Read shared discoveries: .workflow/.csv-wave/{session-id}/discoveries.ndjson (if exists, skip if not)
|
||||
2. Read project context: .workflow/project-tech.json (if exists)
|
||||
|
||||
---
|
||||
|
||||
## Your Task
|
||||
|
||||
**Task ID**: {id}
|
||||
**Title**: {title}
|
||||
**Role**: {role}
|
||||
**Description**: {description}
|
||||
**Pipeline**: {pipeline}
|
||||
**Sprint**: {sprint_num}
|
||||
**GC Round**: {gc_round}
|
||||
|
||||
### Previous Tasks' Findings (Context)
|
||||
{prev_context}
|
||||
|
||||
---
|
||||
|
||||
## Execution Protocol
|
||||
|
||||
1. **Read discoveries**: Load shared discoveries from the session's discoveries.ndjson for cross-task context
|
||||
2. **Use context**: Apply previous tasks' findings from prev_context above
|
||||
3. **Execute by role**:
|
||||
|
||||
### Role: architect (DESIGN-* tasks)
|
||||
- Explore codebase for existing patterns, module structure, and dependencies
|
||||
- Use mcp__ace-tool__search_context for semantic discovery when available
|
||||
- Create design document covering:
|
||||
- Architecture decision: approach, rationale, alternatives considered
|
||||
- Component design: responsibility, dependencies, files to modify, complexity
|
||||
- Task breakdown: file changes, estimated complexity, dependencies, acceptance criteria
|
||||
- Integration points and risks with mitigations
|
||||
- Write design document to session design/ directory
|
||||
- Write task breakdown JSON (array of tasks with id, title, files, complexity, dependencies, acceptance_criteria)
|
||||
- Record architecture decisions in wisdom/decisions.md via discovery board
|
||||
|
||||
### Role: developer (DEV-* tasks)
|
||||
- **Normal task** (gc_round = 0):
|
||||
- Read design document and task breakdown from context
|
||||
- Implement tasks following the execution order from breakdown
|
||||
- Use Edit or Write for file modifications
|
||||
- Validate syntax after each major change (tsc --noEmit or equivalent)
|
||||
- Auto-fix if validation fails (max 2 attempts)
|
||||
- **Fix task** (gc_round > 0):
|
||||
- Read review feedback from prev_context
|
||||
- Focus on critical/high severity issues ONLY
|
||||
- Do NOT change code that was not flagged in review
|
||||
- Fix critical issues first, then high, then medium
|
||||
- Maintain existing code style and patterns
|
||||
- Write dev log to session code/ directory
|
||||
- Record implementation details via discovery board
|
||||
|
||||
### Role: tester (VERIFY-* tasks)
|
||||
- Detect test framework from project files (package.json, pytest.ini, etc.)
|
||||
- Get list of changed files from dev log in prev_context
|
||||
- Run targeted tests for changed files
|
||||
- Run regression test suite
|
||||
- If tests fail: attempt fix (max 3 iterations using available tools)
|
||||
- Write verification results JSON to session verify/ directory
|
||||
- Record test results via discovery board
|
||||
- Report pass rate in findings
|
||||
|
||||
### Role: reviewer (REVIEW-* tasks)
|
||||
- Read changed files from dev log in prev_context
|
||||
- Read design document for requirements alignment
|
||||
- Review across 4 weighted dimensions:
|
||||
- Correctness (30%): Logic correctness, boundary handling, edge cases
|
||||
- Completeness (25%): Coverage of design requirements
|
||||
- Maintainability (25%): Readability, code style, DRY, naming
|
||||
- Security (20%): Vulnerabilities, input validation, auth issues
|
||||
- Assign severity per finding: CRITICAL / HIGH / MEDIUM / LOW
|
||||
- Include file:line references for each finding
|
||||
- Calculate weighted quality score (1-10)
|
||||
- Determine GC signal:
|
||||
- critical_count > 0 OR score < 7 -> `REVISION_NEEDED`
|
||||
- critical_count == 0 AND score >= 7 -> `CONVERGED`
|
||||
- Write review report to session review/ directory
|
||||
- Record review findings via discovery board
|
||||
|
||||
4. **Share discoveries**: Append exploration findings to shared board:
|
||||
```bash
|
||||
echo '{"ts":"<ISO8601>","worker":"{id}","type":"<type>","data":{...}}' >> .workflow/.csv-wave/{session-id}/discoveries.ndjson
|
||||
```
|
||||
|
||||
Discovery types to share:
|
||||
- `design_decision`: {component, approach, rationale, alternatives} -- architecture decision
|
||||
- `implementation`: {file, changes, pattern_used, notes} -- code implementation detail
|
||||
- `test_result`: {test_suite, pass_rate, failures[], regressions} -- test execution result
|
||||
- `review_finding`: {file_line, severity, dimension, description, suggestion} -- review finding
|
||||
- `convention`: {name, description, example} -- discovered project convention
|
||||
|
||||
5. **Report result**: Return JSON via report_agent_job_result
|
||||
|
||||
---
|
||||
|
||||
## Output (report_agent_job_result)
|
||||
|
||||
Return JSON:
|
||||
{
|
||||
"id": "{id}",
|
||||
"status": "completed" | "failed",
|
||||
"findings": "Key discoveries and implementation notes (max 500 chars)",
|
||||
"review_score": "Quality score 1-10 (reviewer only, empty for others)",
|
||||
"gc_signal": "REVISION_NEEDED | CONVERGED (reviewer only, empty for others)",
|
||||
"error": ""
|
||||
}
|
||||
|
||||
**Role-specific findings guidance**:
|
||||
- **architect**: List component count, task count, key decisions. Example: "Designed 3 components (AuthModule, TokenService, Middleware). Created 5 implementation tasks. Key decision: JWT with refresh token rotation."
|
||||
- **developer**: List changed file count, syntax status, key changes. Example: "Modified 5 files. All syntax clean. Key changes: JWT middleware, token validation, auth routes."
|
||||
- **developer (fix)**: List fixed issue count, remaining issues. Example: "Fixed 2 HIGH issues (token expiry, input validation). 0 remaining critical/high issues."
|
||||
- **tester**: List pass rate, test count, regression status. Example: "Pass rate: 96% (24/25 tests). 1 edge case failure (token-expiry). No regressions detected."
|
||||
- **reviewer**: List score, issue counts, verdict. Example: "Score: 7.5/10. Findings: 0 CRITICAL, 1 HIGH, 3 MEDIUM, 2 LOW. GC signal: REVISION_NEEDED."
|
||||
65
.codex/skills/team-iterdev/roles/architect/role.md
Normal file
65
.codex/skills/team-iterdev/roles/architect/role.md
Normal file
@@ -0,0 +1,65 @@
|
||||
---
|
||||
role: architect
|
||||
prefix: DESIGN
|
||||
inner_loop: false
|
||||
message_types:
|
||||
success: design_ready
|
||||
revision: design_revision
|
||||
error: error
|
||||
---
|
||||
|
||||
# Architect
|
||||
|
||||
Technical design, task decomposition, and architecture decision records for iterative development.
|
||||
|
||||
## Phase 2: Context Loading + Codebase Exploration
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Task description | From task subject/description | Yes |
|
||||
| Session path | Extracted from task description | Yes |
|
||||
| .msg/meta.json | <session>/.msg/meta.json | No |
|
||||
| Wisdom files | <session>/wisdom/ | No |
|
||||
|
||||
1. Extract session path and requirement from task description
|
||||
2. Read .msg/meta.json for shared context (architecture_decisions, implementation_context)
|
||||
3. Read wisdom files if available (learnings.md, decisions.md, conventions.md)
|
||||
4. Explore codebase for existing patterns, module structure, dependencies:
|
||||
- Use mcp__ace-tool__search_context for semantic discovery
|
||||
- Identify similar implementations and integration points
|
||||
|
||||
## Phase 3: Technical Design + Task Decomposition
|
||||
|
||||
**Design strategy selection**:
|
||||
|
||||
| Condition | Strategy |
|
||||
|-----------|----------|
|
||||
| Single module change | Direct inline design |
|
||||
| Cross-module change | Multi-component design with integration points |
|
||||
| Large refactoring | Phased approach with milestones |
|
||||
|
||||
**Outputs**:
|
||||
|
||||
1. **Design Document** (`<session>/design/design-<num>.md`):
|
||||
- Architecture decision: approach, rationale, alternatives
|
||||
- Component design: responsibility, dependencies, files, complexity
|
||||
- Task breakdown: files, estimated complexity, dependencies, acceptance criteria
|
||||
- Integration points and risks with mitigations
|
||||
|
||||
2. **Task Breakdown JSON** (`<session>/design/task-breakdown.json`):
|
||||
- Array of tasks with id, title, files, complexity, dependencies, acceptance_criteria
|
||||
- Execution order for developer to follow
|
||||
|
||||
## Phase 4: Design Validation
|
||||
|
||||
| Check | Method | Pass Criteria |
|
||||
|-------|--------|---------------|
|
||||
| Components defined | Verify component list | At least 1 component |
|
||||
| Task breakdown exists | Verify task list | At least 1 task |
|
||||
| Dependencies mapped | All components have dependencies field | All present (can be empty) |
|
||||
| Integration points | Verify integration section | Key integrations documented |
|
||||
|
||||
1. Run validation checks above
|
||||
2. Write architecture_decisions entry to .msg/meta.json:
|
||||
- design_id, approach, rationale, components, task_count
|
||||
3. Write discoveries to wisdom/decisions.md and wisdom/conventions.md
|
||||
@@ -0,0 +1,62 @@
|
||||
# Analyze Task
|
||||
|
||||
Parse iterative development task -> detect capabilities -> assess pipeline complexity -> design roles.
|
||||
|
||||
**CONSTRAINT**: Text-level analysis only. NO source code reading, NO codebase exploration.
|
||||
|
||||
## Signal Detection
|
||||
|
||||
| Keywords | Capability | Role |
|
||||
|----------|------------|------|
|
||||
| design, architect, restructure, refactor plan | architect | architect |
|
||||
| implement, build, code, fix, develop | developer | developer |
|
||||
| test, verify, validate, coverage | tester | tester |
|
||||
| review, audit, quality, check | reviewer | reviewer |
|
||||
|
||||
## Pipeline Selection
|
||||
|
||||
| Signal | Score |
|
||||
|--------|-------|
|
||||
| Changed files > 10 | +3 |
|
||||
| Changed files 3-10 | +2 |
|
||||
| Structural change (refactor, architect, restructure) | +3 |
|
||||
| Cross-cutting (multiple, across, cross) | +2 |
|
||||
| Simple fix (fix, bug, typo, patch) | -2 |
|
||||
|
||||
| Score | Pipeline |
|
||||
|-------|----------|
|
||||
| >= 5 | multi-sprint |
|
||||
| 2-4 | sprint |
|
||||
| 0-1 | patch |
|
||||
|
||||
## Dependency Graph
|
||||
|
||||
Natural ordering tiers:
|
||||
- Tier 0: architect (design must come first)
|
||||
- Tier 1: developer (implementation requires design)
|
||||
- Tier 2: tester, reviewer (validation requires artifacts, can run parallel)
|
||||
|
||||
## Complexity Assessment
|
||||
|
||||
| Factor | Points |
|
||||
|--------|--------|
|
||||
| Cross-module changes | +2 |
|
||||
| Serial depth > 3 | +1 |
|
||||
| Multiple developers needed | +2 |
|
||||
| GC loop likely needed | +1 |
|
||||
|
||||
## Output
|
||||
|
||||
Write <session>/task-analysis.json:
|
||||
```json
|
||||
{
|
||||
"task_description": "<original>",
|
||||
"pipeline_type": "<patch|sprint|multi-sprint>",
|
||||
"capabilities": [{ "name": "<cap>", "role": "<role>", "keywords": ["..."] }],
|
||||
"roles": [{ "name": "<role>", "prefix": "<PREFIX>", "inner_loop": false }],
|
||||
"complexity": { "score": 0, "level": "Low|Medium|High" },
|
||||
"needs_architecture": true,
|
||||
"needs_testing": true,
|
||||
"needs_review": true
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,187 @@
|
||||
# Command: Dispatch
|
||||
|
||||
Create the iterative development task chain with correct dependencies and structured task descriptions.
|
||||
|
||||
## Phase 2: Context Loading
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| User requirement | From coordinator Phase 1 | Yes |
|
||||
| Session folder | From coordinator Phase 2 | Yes |
|
||||
| Pipeline definition | From SKILL.md Pipeline Definitions | Yes |
|
||||
| Pipeline mode | From tasks.json `pipeline_mode` | Yes |
|
||||
|
||||
1. Load user requirement and scope from tasks.json
|
||||
2. Load pipeline stage definitions from SKILL.md Task Metadata Registry
|
||||
3. Read `pipeline_mode` from tasks.json (patch / sprint / multi-sprint)
|
||||
|
||||
## Phase 3: Task Chain Creation
|
||||
|
||||
### Task Entry Template
|
||||
|
||||
Each task in tasks.json `tasks` object:
|
||||
```json
|
||||
{
|
||||
"<TASK-ID>": {
|
||||
"title": "<concise title>",
|
||||
"description": "PURPOSE: <what this task achieves> | Success: <measurable completion criteria>\nTASK:\n - <step 1: specific action>\n - <step 2: specific action>\n - <step 3: specific action>\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Upstream artifacts: <artifact-1>, <artifact-2>\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: <deliverable path> + <quality criteria>\nCONSTRAINTS: <scope limits, focus areas>\n---\nInnerLoop: <true|false>",
|
||||
"role": "<role-name>",
|
||||
"prefix": "<PREFIX>",
|
||||
"deps": ["<dependency-list>"],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Mode Router
|
||||
|
||||
| Mode | Action |
|
||||
|------|--------|
|
||||
| `patch` | Create DEV-001 + VERIFY-001 |
|
||||
| `sprint` | Create DESIGN-001 + DEV-001 + VERIFY-001 + REVIEW-001 |
|
||||
| `multi-sprint` | Create Sprint 1 chain, subsequent sprints created dynamically |
|
||||
|
||||
---
|
||||
|
||||
### Patch Pipeline
|
||||
|
||||
**DEV-001** (developer):
|
||||
```json
|
||||
{
|
||||
"DEV-001": {
|
||||
"title": "Implement fix",
|
||||
"description": "PURPOSE: Implement fix | Success: Fix applied, syntax clean\nTASK:\n - Load target files and understand context\n - Apply fix changes\n - Validate syntax\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: Modified source files + <session>/code/dev-log.md | Syntax clean\nCONSTRAINTS: Minimal changes | Preserve existing behavior\n---\nInnerLoop: true",
|
||||
"role": "developer",
|
||||
"prefix": "DEV",
|
||||
"deps": [],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**VERIFY-001** (tester):
|
||||
```json
|
||||
{
|
||||
"VERIFY-001": {
|
||||
"title": "Verify fix correctness",
|
||||
"description": "PURPOSE: Verify fix correctness | Success: Tests pass, no regressions\nTASK:\n - Detect test framework\n - Run targeted tests for changed files\n - Run regression test suite\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Upstream artifacts: code/dev-log.md\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: <session>/verify/verify-001.json | Pass rate >= 95%\nCONSTRAINTS: Focus on changed files | Report any regressions\n---\nInnerLoop: false",
|
||||
"role": "tester",
|
||||
"prefix": "VERIFY",
|
||||
"deps": ["DEV-001"],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Sprint Pipeline
|
||||
|
||||
**DESIGN-001** (architect):
|
||||
```json
|
||||
{
|
||||
"DESIGN-001": {
|
||||
"title": "Technical design and task breakdown",
|
||||
"description": "PURPOSE: Technical design and task breakdown | Success: Design document + task breakdown ready\nTASK:\n - Explore codebase for patterns and dependencies\n - Create component design with integration points\n - Break down into implementable tasks with acceptance criteria\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: <session>/design/design-001.md + <session>/design/task-breakdown.json | Components defined, tasks actionable\nCONSTRAINTS: Focus on <task-scope> | Risk assessment required\n---\nInnerLoop: false",
|
||||
"role": "architect",
|
||||
"prefix": "DESIGN",
|
||||
"deps": [],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**DEV-001** (developer):
|
||||
```json
|
||||
{
|
||||
"DEV-001": {
|
||||
"title": "Implement design",
|
||||
"description": "PURPOSE: Implement design | Success: All design tasks implemented, syntax clean\nTASK:\n - Load design and task breakdown\n - Implement tasks in execution order\n - Validate syntax after changes\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Upstream artifacts: design/design-001.md, design/task-breakdown.json\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: Modified source files + <session>/code/dev-log.md | Syntax clean, all tasks done\nCONSTRAINTS: Follow design | Preserve existing behavior | Follow code conventions\n---\nInnerLoop: true",
|
||||
"role": "developer",
|
||||
"prefix": "DEV",
|
||||
"deps": ["DESIGN-001"],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**VERIFY-001** (tester, parallel with REVIEW-001):
|
||||
```json
|
||||
{
|
||||
"VERIFY-001": {
|
||||
"title": "Verify implementation",
|
||||
"description": "PURPOSE: Verify implementation | Success: Tests pass, no regressions\nTASK:\n - Detect test framework\n - Run tests for changed files\n - Run regression test suite\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Upstream artifacts: code/dev-log.md\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: <session>/verify/verify-001.json | Pass rate >= 95%\nCONSTRAINTS: Focus on changed files | Report regressions\n---\nInnerLoop: false",
|
||||
"role": "tester",
|
||||
"prefix": "VERIFY",
|
||||
"deps": ["DEV-001"],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**REVIEW-001** (reviewer, parallel with VERIFY-001):
|
||||
```json
|
||||
{
|
||||
"REVIEW-001": {
|
||||
"title": "Code review for correctness and quality",
|
||||
"description": "PURPOSE: Code review for correctness and quality | Success: All dimensions reviewed, verdict issued\nTASK:\n - Load changed files and design document\n - Review across 4 dimensions: correctness, completeness, maintainability, security\n - Score quality (1-10) and issue verdict\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Upstream artifacts: design/design-001.md, code/dev-log.md\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: <session>/review/review-001.md | Per-dimension findings with severity\nCONSTRAINTS: Focus on implementation changes | Provide file:line references\n---\nInnerLoop: false",
|
||||
"role": "reviewer",
|
||||
"prefix": "REVIEW",
|
||||
"deps": ["DEV-001"],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Multi-Sprint Pipeline
|
||||
|
||||
Sprint 1: DESIGN-001 -> DEV-001 -> DEV-002(incremental) -> VERIFY-001 -> DEV-fix -> REVIEW-001
|
||||
|
||||
Create Sprint 1 tasks using sprint templates above, plus:
|
||||
|
||||
**DEV-002** (developer, incremental):
|
||||
```json
|
||||
{
|
||||
"DEV-002": {
|
||||
"title": "Incremental implementation",
|
||||
"description": "PURPOSE: Incremental implementation | Success: Remaining tasks implemented\nTASK:\n - Load remaining tasks from breakdown\n - Implement incrementally\n - Validate syntax\nCONTEXT:\n - Session: <session-folder>\n - Scope: <task-scope>\n - Upstream artifacts: design/task-breakdown.json, code/dev-log.md\n - Shared memory: <session>/.msg/meta.json\nEXPECTED: Modified source files + updated dev-log.md\nCONSTRAINTS: Incremental delivery | Follow existing patterns\n---\nInnerLoop: true",
|
||||
"role": "developer",
|
||||
"prefix": "DEV",
|
||||
"deps": ["DEV-001"],
|
||||
"status": "pending",
|
||||
"findings": "",
|
||||
"error": ""
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Subsequent sprints created dynamically after Sprint N completes.
|
||||
|
||||
## Phase 4: Validation
|
||||
|
||||
Verify task chain integrity:
|
||||
|
||||
| Check | Method | Expected |
|
||||
|-------|--------|----------|
|
||||
| Task count correct | tasks.json count | patch: 2, sprint: 4, multi: 5+ |
|
||||
| Dependencies correct | Trace deps graph | Acyclic, correct ordering |
|
||||
| No circular dependencies | Trace full graph | Acyclic |
|
||||
| Structured descriptions | Each has PURPOSE/TASK/CONTEXT/EXPECTED | All present |
|
||||
|
||||
If validation fails, fix the specific task and re-validate.
|
||||
186
.codex/skills/team-iterdev/roles/coordinator/commands/monitor.md
Normal file
186
.codex/skills/team-iterdev/roles/coordinator/commands/monitor.md
Normal file
@@ -0,0 +1,186 @@
|
||||
# Command: Monitor
|
||||
|
||||
Synchronous pipeline coordination using spawn_agent + wait_agent.
|
||||
|
||||
## Constants
|
||||
|
||||
- WORKER_AGENT: team_worker
|
||||
- MAX_GC_ROUNDS: 3
|
||||
|
||||
## Handler Router
|
||||
|
||||
| Source | Handler |
|
||||
|--------|---------|
|
||||
| "capability_gap" | handleAdapt |
|
||||
| "check" or "status" | handleCheck |
|
||||
| "resume" or "continue" | handleResume |
|
||||
| All tasks completed | handleComplete |
|
||||
| Default | handleSpawnNext |
|
||||
|
||||
## Phase 2: Context Loading
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Session state | tasks.json | Yes |
|
||||
| Trigger event | From Entry Router detection | Yes |
|
||||
| Meta state | <session>/.msg/meta.json | Yes |
|
||||
|
||||
1. Load tasks.json for current state, pipeline_mode, gc_round, max_gc_rounds
|
||||
2. Read tasks from tasks.json to get current task statuses
|
||||
3. Identify trigger event type from Entry Router
|
||||
|
||||
## Phase 3: Event Handlers
|
||||
|
||||
### handleCallback
|
||||
|
||||
Triggered when a worker completes (wait_agent returns).
|
||||
|
||||
1. Determine role from completed task prefix:
|
||||
|
||||
| Task Prefix | Role Detection |
|
||||
|-------------|---------------|
|
||||
| `DESIGN-*` | architect |
|
||||
| `DEV-*` | developer |
|
||||
| `VERIFY-*` | tester |
|
||||
| `REVIEW-*` | reviewer |
|
||||
|
||||
2. Mark task as completed in tasks.json:
|
||||
|
||||
```
|
||||
state.tasks[taskId].status = 'completed'
|
||||
```
|
||||
|
||||
3. Record completion in session state and update metrics
|
||||
|
||||
4. **Generator-Critic check** (when reviewer completes):
|
||||
- If completed task is REVIEW-* AND pipeline is sprint or multi-sprint:
|
||||
- Read review report for GC signal (critical_count, score)
|
||||
- Read tasks.json for gc_round
|
||||
|
||||
| GC Signal | gc_round < max | Action |
|
||||
|-----------|----------------|--------|
|
||||
| review.critical_count > 0 OR review.score < 7 | Yes | Increment gc_round, create DEV-fix task in tasks.json with deps on this REVIEW, log `gc_loop_trigger` |
|
||||
| review.critical_count > 0 OR review.score < 7 | No (>= max) | Force convergence, accept with warning, log to wisdom/issues.md |
|
||||
| review.critical_count == 0 AND review.score >= 7 | - | Review passed, proceed to handleComplete check |
|
||||
|
||||
- Log team_msg with type "gc_loop_trigger" or "task_unblocked"
|
||||
|
||||
5. Proceed to handleSpawnNext
|
||||
|
||||
### handleSpawnNext
|
||||
|
||||
Find and spawn the next ready tasks.
|
||||
|
||||
1. Read tasks.json, find tasks where:
|
||||
- Status is "pending"
|
||||
- All deps tasks have status "completed"
|
||||
|
||||
2. For each ready task, determine role from task prefix:
|
||||
|
||||
| Task Prefix | Role | Inner Loop |
|
||||
|-------------|------|------------|
|
||||
| DESIGN-* | architect | false |
|
||||
| DEV-* | developer | true |
|
||||
| VERIFY-* | tester | false |
|
||||
| REVIEW-* | reviewer | false |
|
||||
|
||||
3. Spawn team_worker:
|
||||
|
||||
```javascript
|
||||
// 1) Update status in tasks.json
|
||||
state.tasks[taskId].status = 'in_progress'
|
||||
|
||||
// 2) Spawn worker
|
||||
const agentId = spawn_agent({
|
||||
agent_type: "team_worker",
|
||||
items: [
|
||||
{ type: "text", text: `## Role Assignment
|
||||
role: ${role}
|
||||
role_spec: ${skillRoot}/roles/${role}/role.md
|
||||
session: ${sessionFolder}
|
||||
session_id: ${sessionId}
|
||||
requirement: ${taskDescription}
|
||||
inner_loop: ${innerLoop}` },
|
||||
|
||||
{ type: "text", text: `Read role_spec file to load Phase 2-4 domain instructions.
|
||||
Execute built-in Phase 1 -> role-spec Phase 2-4 -> built-in Phase 5.` }
|
||||
]
|
||||
})
|
||||
|
||||
// 3) Track agent
|
||||
state.active_agents[taskId] = { agentId, role, started_at: now }
|
||||
|
||||
// 4) Wait for completion
|
||||
wait_agent({ ids: [agentId] })
|
||||
|
||||
// 5) Collect results and update tasks.json
|
||||
state.tasks[taskId].status = 'completed'
|
||||
delete state.active_agents[taskId]
|
||||
```
|
||||
|
||||
4. **Parallel spawn rules**:
|
||||
|
||||
| Pipeline | Scenario | Spawn Behavior |
|
||||
|----------|----------|---------------|
|
||||
| Patch | DEV -> VERIFY | One worker at a time |
|
||||
| Sprint | VERIFY + REVIEW both unblocked | Spawn BOTH in parallel, wait_agent for both |
|
||||
| Sprint | Other stages | One worker at a time |
|
||||
| Multi-Sprint | VERIFY + DEV-fix both unblocked | Spawn BOTH in parallel, wait_agent for both |
|
||||
| Multi-Sprint | Other stages | One worker at a time |
|
||||
|
||||
5. STOP after processing -- wait for next event
|
||||
|
||||
### handleCheck
|
||||
|
||||
Output current pipeline status from tasks.json. Do NOT advance pipeline.
|
||||
|
||||
```
|
||||
Pipeline Status (<pipeline-mode>):
|
||||
[DONE] DESIGN-001 (architect) -> design/design-001.md
|
||||
[DONE] DEV-001 (developer) -> code/dev-log.md
|
||||
[RUN] VERIFY-001 (tester) -> verifying...
|
||||
[RUN] REVIEW-001 (reviewer) -> reviewing...
|
||||
[WAIT] DEV-fix (developer) -> blocked by REVIEW-001
|
||||
|
||||
GC Rounds: <gc_round>/<max_gc_rounds>
|
||||
Sprint: <sprint_id>
|
||||
Session: <session-id>
|
||||
```
|
||||
|
||||
### handleResume
|
||||
|
||||
Resume pipeline after user pause or interruption.
|
||||
|
||||
1. Audit tasks.json for inconsistencies:
|
||||
- Tasks stuck in "in_progress" -> reset to "pending"
|
||||
- Tasks with completed deps but still "pending" -> include in spawn list
|
||||
2. Proceed to handleSpawnNext
|
||||
|
||||
### handleComplete
|
||||
|
||||
Triggered when all pipeline tasks are completed.
|
||||
|
||||
**Completion check by mode**:
|
||||
|
||||
| Mode | Completion Condition |
|
||||
|------|---------------------|
|
||||
| patch | DEV-001 + VERIFY-001 completed |
|
||||
| sprint | DESIGN-001 + DEV-001 + VERIFY-001 + REVIEW-001 (+ any GC tasks) completed |
|
||||
| multi-sprint | All sprint tasks (+ any GC tasks) completed |
|
||||
|
||||
1. Verify all tasks completed in tasks.json
|
||||
2. If any tasks not completed, return to handleSpawnNext
|
||||
3. **Multi-sprint check**: If multi-sprint AND more sprints planned:
|
||||
- Record sprint metrics to .msg/meta.json sprint_history
|
||||
- Evaluate downgrade eligibility (velocity >= expected, review avg >= 8)
|
||||
- Pause for user confirmation before Sprint N+1
|
||||
4. If all completed, transition to coordinator Phase 5 (Report + Completion Action)
|
||||
|
||||
## Phase 4: State Persistence
|
||||
|
||||
After every handler execution:
|
||||
|
||||
1. Update tasks.json with current state (gc_round, last event, active tasks)
|
||||
2. Update .msg/meta.json gc_round if changed
|
||||
3. Verify task list consistency
|
||||
4. STOP and wait for next event
|
||||
161
.codex/skills/team-iterdev/roles/coordinator/role.md
Normal file
161
.codex/skills/team-iterdev/roles/coordinator/role.md
Normal file
@@ -0,0 +1,161 @@
|
||||
# Coordinator Role
|
||||
|
||||
Orchestrate team-iterdev: analyze -> dispatch -> spawn -> monitor -> report.
|
||||
|
||||
## Identity
|
||||
- Name: coordinator | Tag: [coordinator]
|
||||
- Responsibility: Analyze task -> Create session -> Dispatch tasks -> Monitor progress -> Report results
|
||||
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
- Use `team_worker` agent type for all worker spawns (NOT `general-purpose`)
|
||||
- Follow Command Execution Protocol for dispatch and monitor commands
|
||||
- Respect pipeline stage dependencies (deps)
|
||||
- Stop after spawning workers -- wait for results via wait_agent
|
||||
- Handle developer<->reviewer GC loop (max 3 rounds)
|
||||
- Maintain tasks.json for real-time progress
|
||||
- Execute completion action in Phase 5
|
||||
|
||||
### MUST NOT
|
||||
- Implement domain logic (designing, coding, testing, reviewing) -- workers handle this
|
||||
- Spawn workers without creating tasks first
|
||||
- Write source code directly
|
||||
- Force-advance pipeline past failed review/validation
|
||||
- Modify task outputs (workers own their deliverables)
|
||||
|
||||
## Command Execution Protocol
|
||||
|
||||
When coordinator needs to execute a command:
|
||||
1. Read `commands/<command>.md`
|
||||
2. Follow the workflow defined in the command
|
||||
3. Commands are inline execution guides, NOT separate agents
|
||||
4. Execute synchronously, complete before proceeding
|
||||
|
||||
## Entry Router
|
||||
|
||||
| Detection | Condition | Handler |
|
||||
|-----------|-----------|---------|
|
||||
| Status check | Args contain "check" or "status" | -> handleCheck (monitor.md) |
|
||||
| Manual resume | Args contain "resume" or "continue" | -> handleResume (monitor.md) |
|
||||
| Pipeline complete | All tasks completed | -> handleComplete (monitor.md) |
|
||||
| Interrupted session | Active/paused session in .workflow/.team/IDS-* | -> Phase 0 |
|
||||
| New session | None of above | -> Phase 1 |
|
||||
|
||||
For check/resume/complete: load @commands/monitor.md, execute handler, STOP.
|
||||
|
||||
## Phase 0: Session Resume Check
|
||||
|
||||
1. Scan `.workflow/.team/IDS-*/tasks.json` for active/paused sessions
|
||||
2. No sessions -> Phase 1
|
||||
3. Single session -> reconcile (read tasks.json, reset in_progress->pending, kick first ready task)
|
||||
4. Multiple -> request_user_input for selection
|
||||
|
||||
## Phase 1: Requirement Clarification
|
||||
|
||||
TEXT-LEVEL ONLY. No source code reading.
|
||||
|
||||
1. Parse user task description from $ARGUMENTS
|
||||
2. Delegate to @commands/analyze.md
|
||||
3. Assess complexity for pipeline selection:
|
||||
|
||||
| Signal | Weight |
|
||||
|--------|--------|
|
||||
| Changed files > 10 | +3 |
|
||||
| Changed files 3-10 | +2 |
|
||||
| Structural change (refactor, architect, restructure) | +3 |
|
||||
| Cross-cutting (multiple, across, cross) | +2 |
|
||||
| Simple fix (fix, bug, typo, patch) | -2 |
|
||||
|
||||
| Score | Pipeline |
|
||||
|-------|----------|
|
||||
| >= 5 | multi-sprint |
|
||||
| 2-4 | sprint |
|
||||
| 0-1 | patch |
|
||||
|
||||
4. Ask for missing parameters via request_user_input (mode selection)
|
||||
5. Record requirement with scope, pipeline mode
|
||||
6. CRITICAL: Always proceed to Phase 2, never skip team workflow
|
||||
|
||||
## Phase 2: Session & Team Setup
|
||||
|
||||
1. Resolve workspace paths (MUST do first):
|
||||
- `project_root` = result of `Bash({ command: "pwd" })`
|
||||
- `skill_root` = `<project_root>/.codex/skills/team-iterdev`
|
||||
2. Generate session ID: `IDS-<slug>-<YYYY-MM-DD>`
|
||||
3. Create session folder structure:
|
||||
```
|
||||
mkdir -p .workflow/.team/<session-id>/{design,code,verify,review,wisdom}
|
||||
```
|
||||
4. Read specs/pipelines.md -> select pipeline based on complexity
|
||||
5. Initialize wisdom directory (learnings.md, decisions.md, conventions.md, issues.md)
|
||||
6. Write initial tasks.json:
|
||||
```json
|
||||
{
|
||||
"session_id": "<id>",
|
||||
"pipeline_mode": "<patch|sprint|multi-sprint>",
|
||||
"requirement": "<original requirement>",
|
||||
"created_at": "<ISO timestamp>",
|
||||
"gc_round": 0,
|
||||
"max_gc_rounds": 3,
|
||||
"active_agents": {},
|
||||
"tasks": {}
|
||||
}
|
||||
```
|
||||
7. Initialize meta.json with pipeline metadata:
|
||||
```typescript
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", session_id: "<id>", from: "coordinator",
|
||||
type: "state_update", summary: "Session initialized",
|
||||
data: {
|
||||
pipeline_mode: "<patch|sprint|multi-sprint>",
|
||||
pipeline_stages: ["architect", "developer", "tester", "reviewer"],
|
||||
roles: ["coordinator", "architect", "developer", "tester", "reviewer"]
|
||||
}
|
||||
})
|
||||
```
|
||||
|
||||
## Phase 3: Task Chain Creation
|
||||
|
||||
Delegate to @commands/dispatch.md:
|
||||
1. Read specs/pipelines.md for selected pipeline task registry
|
||||
2. Add task entries to tasks.json `tasks` object with deps
|
||||
3. Update tasks.json metadata
|
||||
|
||||
## Phase 4: Spawn-and-Wait
|
||||
|
||||
Delegate to @commands/monitor.md#handleSpawnNext:
|
||||
1. Find ready tasks (pending + all deps resolved)
|
||||
2. Spawn team_worker agents via spawn_agent, wait_agent for results
|
||||
3. Output status summary
|
||||
4. STOP
|
||||
|
||||
## Phase 5: Report + Completion Action
|
||||
|
||||
1. Load session state -> count completed tasks, calculate duration
|
||||
2. Record sprint learning to .msg/meta.json sprint_history
|
||||
3. List deliverables:
|
||||
|
||||
| Deliverable | Path |
|
||||
|-------------|------|
|
||||
| Design Document | <session>/design/design-001.md |
|
||||
| Task Breakdown | <session>/design/task-breakdown.json |
|
||||
| Dev Log | <session>/code/dev-log.md |
|
||||
| Verification Results | <session>/verify/verify-001.json |
|
||||
| Review Report | <session>/review/review-001.md |
|
||||
|
||||
4. Execute completion action per session.completion_action:
|
||||
- interactive -> request_user_input (Archive/Keep/Export)
|
||||
- auto_archive -> Archive & Clean (status=completed)
|
||||
- auto_keep -> Keep Active (status=paused)
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Resolution |
|
||||
|-------|------------|
|
||||
| Task too vague | request_user_input for clarification |
|
||||
| Session corruption | Attempt recovery, fallback to manual |
|
||||
| Worker crash | Reset task to pending, respawn |
|
||||
| GC loop exceeds 3 rounds | Accept with warning, record in shared memory |
|
||||
| Sprint velocity drops below 50% | Alert user, suggest scope reduction |
|
||||
| Task ledger corrupted | Rebuild from tasks.json state |
|
||||
74
.codex/skills/team-iterdev/roles/developer/role.md
Normal file
74
.codex/skills/team-iterdev/roles/developer/role.md
Normal file
@@ -0,0 +1,74 @@
|
||||
---
|
||||
role: developer
|
||||
prefix: DEV
|
||||
inner_loop: true
|
||||
message_types:
|
||||
success: dev_complete
|
||||
progress: dev_progress
|
||||
error: error
|
||||
---
|
||||
|
||||
# Developer
|
||||
|
||||
Code implementer. Implements code according to design, incremental delivery. Acts as Generator in Generator-Critic loop (paired with reviewer).
|
||||
|
||||
## Phase 2: Context Loading
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Task description | From task subject/description | Yes |
|
||||
| Session path | Extracted from task description | Yes |
|
||||
| .msg/meta.json | <session>/.msg/meta.json | Yes |
|
||||
| Design document | <session>/design/design-001.md | For non-fix tasks |
|
||||
| Task breakdown | <session>/design/task-breakdown.json | For non-fix tasks |
|
||||
| Review feedback | <session>/review/*.md | For fix tasks |
|
||||
| Wisdom files | <session>/wisdom/ | No |
|
||||
|
||||
1. Extract session path from task description
|
||||
2. Read .msg/meta.json for shared context
|
||||
3. Detect task type:
|
||||
|
||||
| Task Type | Detection | Loading |
|
||||
|-----------|-----------|---------|
|
||||
| Fix task | Subject contains "fix" | Read latest review file for feedback |
|
||||
| Normal task | No "fix" in subject | Read design document + task breakdown |
|
||||
|
||||
4. Load previous implementation_context from .msg/meta.json
|
||||
5. Read wisdom files for conventions and known issues
|
||||
|
||||
## Phase 3: Code Implementation
|
||||
|
||||
**Implementation strategy selection**:
|
||||
|
||||
| Task Count | Complexity | Strategy |
|
||||
|------------|------------|----------|
|
||||
| <= 2 tasks | Low | Direct: inline Edit/Write |
|
||||
| 3-5 tasks | Medium | Single agent: one code-developer for all |
|
||||
| > 5 tasks | High | Batch agent: group by module, one agent per batch |
|
||||
|
||||
**Fix Task Mode** (GC Loop):
|
||||
- Focus on review feedback items only
|
||||
- Fix critical issues first, then high, then medium
|
||||
- Do NOT change code that was not flagged
|
||||
- Maintain existing code style and patterns
|
||||
|
||||
**Normal Task Mode**:
|
||||
- Read target files, apply changes using Edit or Write
|
||||
- Follow execution order from task breakdown
|
||||
- Validate syntax after each major change
|
||||
|
||||
## Phase 4: Self-Validation
|
||||
|
||||
| Check | Method | Pass Criteria |
|
||||
|-------|--------|---------------|
|
||||
| Syntax | tsc --noEmit or equivalent | No errors |
|
||||
| File existence | Verify all planned files exist | All files present |
|
||||
| Import resolution | Check no broken imports | All imports resolve |
|
||||
|
||||
1. Run syntax check: `tsc --noEmit` / `python -m py_compile` / equivalent
|
||||
2. Auto-fix if validation fails (max 2 attempts)
|
||||
3. Write dev log to `<session>/code/dev-log.md`:
|
||||
- Changed files count, syntax status, fix task flag, file list
|
||||
4. Update implementation_context in .msg/meta.json:
|
||||
- task, changed_files, is_fix, syntax_clean
|
||||
5. Write discoveries to wisdom/learnings.md
|
||||
66
.codex/skills/team-iterdev/roles/reviewer/role.md
Normal file
66
.codex/skills/team-iterdev/roles/reviewer/role.md
Normal file
@@ -0,0 +1,66 @@
|
||||
---
|
||||
role: reviewer
|
||||
prefix: REVIEW
|
||||
inner_loop: false
|
||||
message_types:
|
||||
success: review_passed
|
||||
revision: review_revision
|
||||
critical: review_critical
|
||||
error: error
|
||||
---
|
||||
|
||||
# Reviewer
|
||||
|
||||
Code reviewer. Multi-dimensional review, quality scoring, improvement suggestions. Acts as Critic in Generator-Critic loop (paired with developer).
|
||||
|
||||
## Phase 2: Context Loading
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Task description | From task subject/description | Yes |
|
||||
| Session path | Extracted from task description | Yes |
|
||||
| .msg/meta.json | <session>/.msg/meta.json | Yes |
|
||||
| Design document | <session>/design/design-001.md | For requirements alignment |
|
||||
| Changed files | Git diff | Yes |
|
||||
|
||||
1. Extract session path from task description
|
||||
2. Read .msg/meta.json for shared context and previous review_feedback_trends
|
||||
3. Read design document for requirements alignment
|
||||
4. Get changed files via git diff, read file contents (limit 20 files)
|
||||
|
||||
## Phase 3: Multi-Dimensional Review
|
||||
|
||||
**Review dimensions**:
|
||||
|
||||
| Dimension | Weight | Focus Areas |
|
||||
|-----------|--------|-------------|
|
||||
| Correctness | 30% | Logic correctness, boundary handling |
|
||||
| Completeness | 25% | Coverage of design requirements |
|
||||
| Maintainability | 25% | Readability, code style, DRY |
|
||||
| Security | 20% | Vulnerabilities, input validation |
|
||||
|
||||
Per-dimension: scan modified files, record findings with severity (CRITICAL/HIGH/MEDIUM/LOW), include file:line references and suggestions.
|
||||
|
||||
**Scoring**: Weighted average of dimension scores (1-10 each).
|
||||
|
||||
**Output review report** (`<session>/review/review-<num>.md`):
|
||||
- Files reviewed count, quality score, issue counts by severity
|
||||
- Per-finding: severity, file:line, dimension, description, suggestion
|
||||
- Scoring breakdown by dimension
|
||||
- Signal: CRITICAL / REVISION_NEEDED / APPROVED
|
||||
- Design alignment notes
|
||||
|
||||
## Phase 4: Trend Analysis + Verdict
|
||||
|
||||
1. Compare with previous review_feedback_trends from .msg/meta.json
|
||||
2. Identify recurring issues, improvement areas, new issues
|
||||
|
||||
| Verdict Condition | Message Type |
|
||||
|-------------------|--------------|
|
||||
| criticalCount > 0 | review_critical |
|
||||
| score < 7 | review_revision |
|
||||
| else | review_passed |
|
||||
|
||||
3. Update review_feedback_trends in .msg/meta.json:
|
||||
- review_id, score, critical count, high count, dimensions, gc_round
|
||||
4. Write discoveries to wisdom/learnings.md
|
||||
88
.codex/skills/team-iterdev/roles/tester/role.md
Normal file
88
.codex/skills/team-iterdev/roles/tester/role.md
Normal file
@@ -0,0 +1,88 @@
|
||||
---
|
||||
role: tester
|
||||
prefix: VERIFY
|
||||
inner_loop: false
|
||||
message_types:
|
||||
success: verify_passed
|
||||
failure: verify_failed
|
||||
fix: fix_required
|
||||
error: error
|
||||
---
|
||||
|
||||
# Tester
|
||||
|
||||
Test validator. Test execution, fix cycles, and regression detection.
|
||||
|
||||
## Phase 2: Environment Detection
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Task description | From task subject/description | Yes |
|
||||
| Session path | Extracted from task description | Yes |
|
||||
| .msg/meta.json | <session>/.msg/meta.json | Yes |
|
||||
| Changed files | Git diff | Yes |
|
||||
|
||||
1. Extract session path from task description
|
||||
2. Read .msg/meta.json for shared context
|
||||
3. Get changed files via git diff
|
||||
4. Detect test framework and command:
|
||||
|
||||
| Detection | Method |
|
||||
|-----------|--------|
|
||||
| Test command | Check package.json scripts, pytest.ini, Makefile |
|
||||
| Coverage tool | Check for nyc, coverage.py, jest --coverage config |
|
||||
|
||||
Common commands: npm test, pytest, go test ./..., cargo test
|
||||
|
||||
## Phase 3: Execution + Fix Cycle
|
||||
|
||||
**Iterative test-fix cycle** (max 5 iterations):
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Run test command |
|
||||
| 2 | Parse results, check pass rate |
|
||||
| 3 | Pass rate >= 95% -> exit loop (success) |
|
||||
| 4 | Extract failing test details |
|
||||
| 5 | Apply fix using CLI tool |
|
||||
| 6 | Increment iteration counter |
|
||||
| 7 | iteration >= MAX (5) -> exit loop (report failures) |
|
||||
| 8 | Go to Step 1 |
|
||||
|
||||
**Fix delegation**: Use CLI tool to fix failing tests:
|
||||
|
||||
```bash
|
||||
ccw cli -p "PURPOSE: Fix failing tests; success = all listed tests pass
|
||||
TASK: • Analyze test failure output • Identify root cause in changed files • Apply minimal fix
|
||||
MODE: write
|
||||
CONTEXT: @<changed-files> | Memory: Test output from current iteration
|
||||
EXPECTED: Code fixes that make failing tests pass without breaking other tests
|
||||
CONSTRAINTS: Only modify files in changed list | Minimal changes
|
||||
Test output: <test-failure-details>
|
||||
Changed files: <file-list>" --tool gemini --mode write --rule development-debug-runtime-issues
|
||||
```
|
||||
|
||||
Wait for CLI completion before re-running tests.
|
||||
|
||||
## Phase 4: Regression Check + Report
|
||||
|
||||
1. Run full test suite for regression: `<test-command> --all`
|
||||
|
||||
| Check | Method | Pass Criteria |
|
||||
|-------|--------|---------------|
|
||||
| Regression | Run full test suite | No FAIL in output |
|
||||
| Coverage | Run coverage tool | >= 80% (if configured) |
|
||||
|
||||
2. Write verification results to `<session>/verify/verify-<num>.json`:
|
||||
- verify_id, pass_rate, iterations, passed, timestamp, regression_passed
|
||||
|
||||
3. Determine message type:
|
||||
|
||||
| Condition | Message Type |
|
||||
|-----------|--------------|
|
||||
| passRate >= 0.95 | verify_passed |
|
||||
| passRate < 0.95 && iterations >= MAX | fix_required |
|
||||
| passRate < 0.95 | verify_failed |
|
||||
|
||||
4. Update .msg/meta.json with test_patterns entry
|
||||
5. Write discoveries to wisdom/issues.md
|
||||
@@ -1,174 +0,0 @@
|
||||
# Team IterDev -- CSV Schema
|
||||
|
||||
## Master CSV: tasks.csv
|
||||
|
||||
### Column Definitions
|
||||
|
||||
#### Input Columns (Set by Decomposer)
|
||||
|
||||
| Column | Type | Required | Description | Example |
|
||||
|--------|------|----------|-------------|---------|
|
||||
| `id` | string | Yes | Unique task identifier | `"DEV-001"` |
|
||||
| `title` | string | Yes | Short task title | `"Implement design"` |
|
||||
| `description` | string | Yes | Detailed task description (self-contained) | `"Load design document, implement tasks in execution order..."` |
|
||||
| `role` | string | Yes | Worker role: architect, developer, tester, reviewer | `"developer"` |
|
||||
| `pipeline` | string | Yes | Pipeline mode: patch, sprint, multi-sprint | `"sprint"` |
|
||||
| `sprint_num` | integer | Yes | Sprint number (1-based, for multi-sprint tracking) | `"1"` |
|
||||
| `gc_round` | integer | Yes | Generator-Critic round number (0 = initial, 1+ = fix round) | `"0"` |
|
||||
| `deps` | string | No | Semicolon-separated dependency task IDs | `"DESIGN-001"` |
|
||||
| `context_from` | string | No | Semicolon-separated task IDs for context | `"DESIGN-001"` |
|
||||
| `exec_mode` | enum | Yes | Execution mechanism: `csv-wave` or `interactive` | `"csv-wave"` |
|
||||
|
||||
#### Computed Columns (Set by Wave Engine)
|
||||
|
||||
| Column | Type | Description | Example |
|
||||
|--------|------|-------------|---------|
|
||||
| `wave` | integer | Wave number (1-based, from topological sort) | `2` |
|
||||
| `prev_context` | string | Aggregated findings from context_from tasks (per-wave CSV only) | `"[Task DESIGN-001] Created design with 3 components..."` |
|
||||
|
||||
#### Output Columns (Set by Agent)
|
||||
|
||||
| Column | Type | Description | Example |
|
||||
|--------|------|-------------|---------|
|
||||
| `status` | enum | `pending` -> `completed` / `failed` / `skipped` | `"completed"` |
|
||||
| `findings` | string | Key discoveries (max 500 chars) | `"Implemented 5 files, all syntax clean..."` |
|
||||
| `review_score` | string | Quality score 1-10 (reviewer only, empty for others) | `"8"` |
|
||||
| `gc_signal` | string | `REVISION_NEEDED` or `CONVERGED` (reviewer only) | `"CONVERGED"` |
|
||||
| `error` | string | Error message if failed | `""` |
|
||||
|
||||
---
|
||||
|
||||
### exec_mode Values
|
||||
|
||||
| Value | Mechanism | Description |
|
||||
|-------|-----------|-------------|
|
||||
| `csv-wave` | `spawn_agents_on_csv` | One-shot batch execution within wave |
|
||||
| `interactive` | `spawn_agent`/`wait`/`send_input`/`close_agent` | Multi-round individual execution |
|
||||
|
||||
Interactive tasks appear in master CSV for dependency tracking but are NOT included in wave-{N}.csv files.
|
||||
|
||||
---
|
||||
|
||||
### Example Data
|
||||
|
||||
```csv
|
||||
id,title,description,role,pipeline,sprint_num,gc_round,deps,context_from,exec_mode,wave,status,findings,review_score,gc_signal,error
|
||||
"DESIGN-001","Technical design and task breakdown","Explore codebase for patterns and dependencies. Create component design with integration points. Break into implementable tasks with acceptance criteria.","architect","sprint","1","0","","","csv-wave","1","pending","","","",""
|
||||
"DEV-001","Implement design","Load design document and task breakdown. Implement tasks in execution order. Validate syntax after each change. Write dev log.","developer","sprint","1","0","DESIGN-001","DESIGN-001","csv-wave","2","pending","","","",""
|
||||
"VERIFY-001","Verify implementation","Detect test framework. Run targeted tests for changed files. Run regression test suite. Report pass rate.","tester","sprint","1","0","DEV-001","DEV-001","csv-wave","3","pending","","","",""
|
||||
"REVIEW-001","Code review","Load changed files and design. Review across correctness, completeness, maintainability, security. Score quality 1-10. Issue verdict.","reviewer","sprint","1","0","DEV-001","DEV-001","csv-wave","3","pending","","","",""
|
||||
"GC-CHECK-001","GC loop decision","Evaluate review severity. If critical_count > 0 or score < 7: REVISION. Else: CONVERGE.","gc-controller","sprint","1","1","REVIEW-001","REVIEW-001","interactive","4","pending","","","",""
|
||||
"DEV-fix-1","Fix review issues (round 1)","Fix critical and high issues from REVIEW-001. Focus on review feedback only. Do NOT change unflagged code.","developer","sprint","1","1","GC-CHECK-001","REVIEW-001","csv-wave","5","pending","","","",""
|
||||
"REVIEW-002","Re-review (round 1)","Review fixes from DEV-fix-1. Re-evaluate quality. Check if critical issues are resolved.","reviewer","sprint","1","1","DEV-fix-1","DEV-fix-1","csv-wave","6","pending","","","",""
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
### Column Lifecycle
|
||||
|
||||
```
|
||||
Decomposer (Phase 1) Wave Engine (Phase 2) Agent (Execution)
|
||||
--------------------- -------------------- -----------------
|
||||
id -----------> id ----------> id
|
||||
title -----------> title ----------> (reads)
|
||||
description -----------> description ----------> (reads)
|
||||
role -----------> role ----------> (reads)
|
||||
pipeline -----------> pipeline ----------> (reads)
|
||||
sprint_num -----------> sprint_num ----------> (reads)
|
||||
gc_round -----------> gc_round ----------> (reads)
|
||||
deps -----------> deps ----------> (reads)
|
||||
context_from-----------> context_from----------> (reads)
|
||||
exec_mode -----------> exec_mode ----------> (reads)
|
||||
wave ----------> (reads)
|
||||
prev_context ----------> (reads)
|
||||
status
|
||||
findings
|
||||
review_score
|
||||
gc_signal
|
||||
error
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Output Schema (JSON)
|
||||
|
||||
Agent output via `report_agent_job_result` (csv-wave tasks):
|
||||
|
||||
```json
|
||||
{
|
||||
"id": "DEV-001",
|
||||
"status": "completed",
|
||||
"findings": "Implemented 5 files following design. All syntax checks pass. Key changes: src/auth/jwt.ts, src/middleware/auth.ts.",
|
||||
"review_score": "",
|
||||
"gc_signal": "",
|
||||
"error": ""
|
||||
}
|
||||
```
|
||||
|
||||
Reviewer-specific output:
|
||||
|
||||
```json
|
||||
{
|
||||
"id": "REVIEW-001",
|
||||
"status": "completed",
|
||||
"findings": "Reviewed 5 files. Correctness: 8/10, Completeness: 9/10, Maintainability: 7/10, Security: 6/10. 1 HIGH issue (missing token expiry check).",
|
||||
"review_score": "7.5",
|
||||
"gc_signal": "REVISION_NEEDED",
|
||||
"error": ""
|
||||
}
|
||||
```
|
||||
|
||||
Interactive tasks output via structured text or JSON written to `interactive/{id}-result.json`.
|
||||
|
||||
---
|
||||
|
||||
## Discovery Types
|
||||
|
||||
| Type | Dedup Key | Data Schema | Description |
|
||||
|------|-----------|-------------|-------------|
|
||||
| `design_decision` | `data.component` | `{component, approach, rationale, alternatives}` | Architecture decision |
|
||||
| `implementation` | `data.file` | `{file, changes, pattern_used, notes}` | Code implementation detail |
|
||||
| `test_result` | `data.test_suite` | `{test_suite, pass_rate, failures[], regressions}` | Test execution result |
|
||||
| `review_finding` | `data.file_line` | `{file_line, severity, dimension, description, suggestion}` | Review finding |
|
||||
| `convention` | `data.name` | `{name, description, example}` | Discovered project convention |
|
||||
| `gc_decision` | `data.round` | `{round, signal, critical_count, score}` | GC loop decision record |
|
||||
|
||||
### Discovery NDJSON Format
|
||||
|
||||
```jsonl
|
||||
{"ts":"2026-03-08T10:00:00+08:00","worker":"DESIGN-001","type":"design_decision","data":{"component":"AuthModule","approach":"JWT with refresh tokens","rationale":"Stateless auth","alternatives":"Session-based, OAuth2"}}
|
||||
{"ts":"2026-03-08T10:05:00+08:00","worker":"DEV-001","type":"implementation","data":{"file":"src/auth/jwt.ts","changes":"Added JWT middleware with token validation","pattern_used":"Express middleware","notes":"Reuses existing bcrypt"}}
|
||||
{"ts":"2026-03-08T10:10:00+08:00","worker":"VERIFY-001","type":"test_result","data":{"test_suite":"auth","pass_rate":0.96,"failures":["token-expiry-edge-case"],"regressions":false}}
|
||||
{"ts":"2026-03-08T10:15:00+08:00","worker":"REVIEW-001","type":"review_finding","data":{"file_line":"src/auth/jwt.ts:42","severity":"HIGH","dimension":"security","description":"Token expiry not validated","suggestion":"Add exp claim check in validateToken()"}}
|
||||
```
|
||||
|
||||
> Both csv-wave and interactive agents read/write the same discoveries.ndjson file.
|
||||
|
||||
---
|
||||
|
||||
## Cross-Mechanism Context Flow
|
||||
|
||||
| Source | Target | Mechanism |
|
||||
|--------|--------|-----------|
|
||||
| CSV task findings | Interactive task | Injected via spawn message or send_input |
|
||||
| Interactive task result | CSV task prev_context | Read from interactive/{id}-result.json |
|
||||
| Any agent discovery | Any agent | Shared via discoveries.ndjson |
|
||||
|
||||
---
|
||||
|
||||
## Validation Rules
|
||||
|
||||
| Rule | Check | Error |
|
||||
|------|-------|-------|
|
||||
| Unique IDs | No duplicate `id` values | "Duplicate task ID: {id}" |
|
||||
| Valid deps | All dep IDs exist in tasks | "Unknown dependency: {dep_id}" |
|
||||
| No self-deps | Task cannot depend on itself | "Self-dependency: {id}" |
|
||||
| No circular deps | Topological sort completes | "Circular dependency detected involving: {ids}" |
|
||||
| context_from valid | All context IDs exist and in earlier waves | "Invalid context_from: {id}" |
|
||||
| exec_mode valid | Value is `csv-wave` or `interactive` | "Invalid exec_mode: {value}" |
|
||||
| Description non-empty | Every task has description | "Empty description for task: {id}" |
|
||||
| Status enum | status in {pending, completed, failed, skipped} | "Invalid status: {status}" |
|
||||
| Valid role | role in {architect, developer, tester, reviewer, gc-controller} | "Invalid role: {role}" |
|
||||
| GC round non-negative | gc_round >= 0 | "Invalid gc_round: {value}" |
|
||||
| Valid pipeline | pipeline in {patch, sprint, multi-sprint} | "Invalid pipeline: {value}" |
|
||||
| Cross-mechanism deps | Interactive<->CSV deps resolve correctly | "Cross-mechanism dependency unresolvable: {id}" |
|
||||
94
.codex/skills/team-iterdev/specs/pipelines.md
Normal file
94
.codex/skills/team-iterdev/specs/pipelines.md
Normal file
@@ -0,0 +1,94 @@
|
||||
# IterDev Pipeline Definitions
|
||||
|
||||
## Three-Pipeline Architecture
|
||||
|
||||
### Patch Pipeline (2 beats, serial)
|
||||
|
||||
```
|
||||
DEV-001 -> VERIFY-001
|
||||
[developer] [tester]
|
||||
```
|
||||
|
||||
### Sprint Pipeline (4 beats, with parallel window)
|
||||
|
||||
```
|
||||
DESIGN-001 -> DEV-001 -> [VERIFY-001 + REVIEW-001] (parallel)
|
||||
[architect] [developer] [tester] [reviewer]
|
||||
```
|
||||
|
||||
### Multi-Sprint Pipeline (N beats, iterative)
|
||||
|
||||
```
|
||||
Sprint 1: DESIGN-001 -> DEV-001 -> DEV-002(incremental) -> VERIFY-001 -> DEV-fix -> REVIEW-001
|
||||
Sprint 2: DESIGN-002(refined) -> DEV-003 -> VERIFY-002 -> REVIEW-002
|
||||
...
|
||||
```
|
||||
|
||||
## Generator-Critic Loop (developer <-> reviewer)
|
||||
|
||||
```
|
||||
DEV -> REVIEW -> (if review.critical_count > 0 || review.score < 7)
|
||||
-> DEV-fix -> REVIEW-2 -> (if still issues) -> DEV-fix-2 -> REVIEW-3
|
||||
-> (max 3 rounds, then accept with warning)
|
||||
```
|
||||
|
||||
## Pipeline Selection Logic
|
||||
|
||||
| Signal | Score |
|
||||
|--------|-------|
|
||||
| Changed files > 10 | +3 |
|
||||
| Changed files 3-10 | +2 |
|
||||
| Structural change | +3 |
|
||||
| Cross-cutting concern | +2 |
|
||||
| Simple fix | -2 |
|
||||
|
||||
| Score | Pipeline |
|
||||
|-------|----------|
|
||||
| >= 5 | multi-sprint |
|
||||
| 2-4 | sprint |
|
||||
| 0-1 | patch |
|
||||
|
||||
## Task Metadata Registry
|
||||
|
||||
| Task ID | Role | Pipeline | Dependencies | Description |
|
||||
|---------|------|----------|-------------|-------------|
|
||||
| DESIGN-001 | architect | sprint/multi | (none) | Technical design and task breakdown |
|
||||
| DEV-001 | developer | all | DESIGN-001 (sprint/multi) or (none for patch) | Code implementation |
|
||||
| DEV-002 | developer | multi | DEV-001 | Incremental implementation |
|
||||
| DEV-fix | developer | sprint/multi | REVIEW-* (GC loop trigger) | Fix issues from review |
|
||||
| VERIFY-001 | tester | all | DEV-001 (or last DEV) | Test execution and fix cycles |
|
||||
| REVIEW-001 | reviewer | sprint/multi | DEV-001 (or last DEV) | Code review and quality scoring |
|
||||
|
||||
## Checkpoints
|
||||
|
||||
| Trigger Condition | Location | Behavior |
|
||||
|-------------------|----------|----------|
|
||||
| GC loop exceeds max rounds | After REVIEW-3 | Stop iteration, accept with warning, record in wisdom |
|
||||
| Sprint transition | End of Sprint N | Pause, retrospective, user confirms `resume` for Sprint N+1 |
|
||||
| Pipeline stall | No ready + no running tasks | Check missing tasks, report blockedBy chain to user |
|
||||
|
||||
## Multi-Sprint Dynamic Downgrade
|
||||
|
||||
If Sprint N metrics are strong (velocity >= expected, review avg >= 8), coordinator may downgrade Sprint N+1 from multi-sprint to sprint pipeline for efficiency.
|
||||
|
||||
## Task Ledger Schema
|
||||
|
||||
| Field | Description |
|
||||
|-------|-------------|
|
||||
| `sprint_id` | Current sprint identifier |
|
||||
| `sprint_goal` | Sprint objective |
|
||||
| `tasks[]` | Array of task entries |
|
||||
| `metrics` | Aggregated metrics: total, completed, in_progress, blocked, velocity |
|
||||
|
||||
**Task Entry Fields**:
|
||||
|
||||
| Field | Description |
|
||||
|-------|-------------|
|
||||
| `id` | Task identifier |
|
||||
| `title` | Task title |
|
||||
| `owner` | Assigned role |
|
||||
| `status` | pending / in_progress / completed / blocked |
|
||||
| `started_at` / `completed_at` | Timestamps |
|
||||
| `gc_rounds` | Generator-Critic iteration count |
|
||||
| `review_score` | Reviewer score (null until reviewed) |
|
||||
| `test_pass_rate` | Tester pass rate (null until tested) |
|
||||
172
.codex/skills/team-iterdev/specs/team-config.json
Normal file
172
.codex/skills/team-iterdev/specs/team-config.json
Normal file
@@ -0,0 +1,172 @@
|
||||
{
|
||||
"team_name": "team-iterdev",
|
||||
"team_display_name": "Team IterDev",
|
||||
"description": "Iterative development team with Generator-Critic loop, task ledger, sprint learning, dynamic pipeline, conflict handling, concurrency control, rollback strategy, user feedback loop, and tech debt tracking",
|
||||
"version": "1.2.0",
|
||||
|
||||
"roles": {
|
||||
"coordinator": {
|
||||
"task_prefix": null,
|
||||
"responsibility": "Sprint planning, backlog management, task ledger maintenance, GC loop control, Phase 1: conflict handling, concurrency control, rollback strategy, Phase 3: user feedback loop, tech debt tracking",
|
||||
"message_types": [
|
||||
"sprint_started", "gc_loop_trigger", "sprint_complete", "task_unblocked", "error", "shutdown",
|
||||
"conflict_detected", "conflict_resolved", "resource_locked", "resource_unlocked", "resource_contention",
|
||||
"rollback_initiated", "rollback_completed", "rollback_failed",
|
||||
"user_feedback_received", "tech_debt_identified"
|
||||
]
|
||||
},
|
||||
"architect": {
|
||||
"task_prefix": "DESIGN",
|
||||
"responsibility": "Technical design, task decomposition, architecture decisions",
|
||||
"message_types": ["design_ready", "design_revision", "error"]
|
||||
},
|
||||
"developer": {
|
||||
"task_prefix": "DEV",
|
||||
"responsibility": "Code implementation, incremental delivery",
|
||||
"message_types": ["dev_complete", "dev_progress", "error"]
|
||||
},
|
||||
"tester": {
|
||||
"task_prefix": "VERIFY",
|
||||
"responsibility": "Test execution, fix cycle, regression detection",
|
||||
"message_types": ["verify_passed", "verify_failed", "fix_required", "error"]
|
||||
},
|
||||
"reviewer": {
|
||||
"task_prefix": "REVIEW",
|
||||
"responsibility": "Code review, quality scoring, improvement suggestions",
|
||||
"message_types": ["review_passed", "review_revision", "review_critical", "error"]
|
||||
}
|
||||
},
|
||||
|
||||
"pipelines": {
|
||||
"patch": {
|
||||
"description": "Simple fix: implement → verify",
|
||||
"task_chain": ["DEV-001", "VERIFY-001"],
|
||||
"gc_loops": 0
|
||||
},
|
||||
"sprint": {
|
||||
"description": "Standard feature: design → implement → verify + review (parallel)",
|
||||
"task_chain": ["DESIGN-001", "DEV-001", "VERIFY-001", "REVIEW-001"],
|
||||
"gc_loops": 3,
|
||||
"parallel_groups": [["VERIFY-001", "REVIEW-001"]]
|
||||
},
|
||||
"multi-sprint": {
|
||||
"description": "Large feature: multiple sprint cycles with incremental delivery",
|
||||
"task_chain": "dynamic — coordinator creates per-sprint chains",
|
||||
"gc_loops": 3,
|
||||
"sprint_count": "dynamic"
|
||||
}
|
||||
},
|
||||
|
||||
"innovation_patterns": {
|
||||
"generator_critic": {
|
||||
"generator": "developer",
|
||||
"critic": "reviewer",
|
||||
"max_rounds": 3,
|
||||
"convergence_trigger": "review.critical_count === 0 && review.score >= 7"
|
||||
},
|
||||
"task_ledger": {
|
||||
"file": "task-ledger.json",
|
||||
"updated_by": "coordinator",
|
||||
"tracks": ["status", "gc_rounds", "review_score", "test_pass_rate", "velocity"],
|
||||
"phase1_extensions": {
|
||||
"conflict_info": {
|
||||
"fields": ["status", "conflicting_files", "resolution_strategy", "resolved_by_task_id"],
|
||||
"default": { "status": "none", "conflicting_files": [], "resolution_strategy": null, "resolved_by_task_id": null }
|
||||
},
|
||||
"rollback_info": {
|
||||
"fields": ["snapshot_id", "rollback_procedure", "last_successful_state_id"],
|
||||
"default": { "snapshot_id": null, "rollback_procedure": null, "last_successful_state_id": null }
|
||||
}
|
||||
}
|
||||
},
|
||||
"shared_memory": {
|
||||
"file": "shared-memory.json",
|
||||
"fields": {
|
||||
"architect": "architecture_decisions",
|
||||
"developer": "implementation_context",
|
||||
"tester": "test_patterns",
|
||||
"reviewer": "review_feedback_trends"
|
||||
},
|
||||
"persistent_fields": ["sprint_history", "what_worked", "what_failed", "patterns_learned"],
|
||||
"phase1_extensions": {
|
||||
"resource_locks": {
|
||||
"description": "Concurrency control: resource locking state",
|
||||
"lock_timeout_ms": 300000,
|
||||
"deadlock_detection": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"dynamic_pipeline": {
|
||||
"selector": "coordinator",
|
||||
"criteria": "file_count + module_count + complexity_assessment",
|
||||
"downgrade_rule": "velocity >= expected && review_avg >= 8 → simplify next sprint"
|
||||
}
|
||||
},
|
||||
|
||||
"phase1_features": {
|
||||
"conflict_handling": {
|
||||
"enabled": true,
|
||||
"detection_strategy": "file_overlap",
|
||||
"resolution_strategies": ["manual", "auto_merge", "abort"]
|
||||
},
|
||||
"concurrency_control": {
|
||||
"enabled": true,
|
||||
"lock_timeout_minutes": 5,
|
||||
"deadlock_detection": true,
|
||||
"resources": ["task-ledger.json", "shared-memory.json"]
|
||||
},
|
||||
"rollback_strategy": {
|
||||
"enabled": true,
|
||||
"snapshot_trigger": "task_complete",
|
||||
"default_procedure": "git revert HEAD"
|
||||
}
|
||||
},
|
||||
|
||||
"phase2_features": {
|
||||
"external_dependency_management": {
|
||||
"enabled": true,
|
||||
"validation_trigger": "task_start",
|
||||
"supported_sources": ["npm", "maven", "pip", "git"],
|
||||
"version_check_command": {
|
||||
"npm": "npm list {name}",
|
||||
"pip": "pip show {name}",
|
||||
"maven": "mvn dependency:tree"
|
||||
}
|
||||
},
|
||||
"state_recovery": {
|
||||
"enabled": true,
|
||||
"checkpoint_trigger": "phase_complete",
|
||||
"max_checkpoints_per_task": 5,
|
||||
"checkpoint_dir": "checkpoints/"
|
||||
}
|
||||
},
|
||||
|
||||
"phase3_features": {
|
||||
"user_feedback_loop": {
|
||||
"enabled": true,
|
||||
"collection_trigger": "sprint_complete",
|
||||
"max_feedback_items": 50,
|
||||
"severity_levels": ["low", "medium", "high", "critical"],
|
||||
"status_flow": ["new", "reviewed", "addressed", "closed"]
|
||||
},
|
||||
"tech_debt_tracking": {
|
||||
"enabled": true,
|
||||
"detection_sources": ["review", "test", "architect"],
|
||||
"categories": ["code", "design", "test", "documentation"],
|
||||
"severity_levels": ["low", "medium", "high", "critical"],
|
||||
"status_flow": ["open", "in_progress", "resolved", "deferred"],
|
||||
"report_trigger": "sprint_retrospective"
|
||||
}
|
||||
},
|
||||
|
||||
"collaboration_patterns": ["CP-1", "CP-3", "CP-5", "CP-6"],
|
||||
|
||||
"session_dirs": {
|
||||
"base": ".workflow/.team/IDS-{slug}-{YYYY-MM-DD}/",
|
||||
"design": "design/",
|
||||
"code": "code/",
|
||||
"verify": "verify/",
|
||||
"review": "review/",
|
||||
"messages": ".workflow/.team-msg/{team-name}/"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user