Team Testing

Unified team skill: progressive test coverage through Generator-Critic loops (generator<->executor), shared memory (defect pattern tracking), and dynamic layer selection. All team members invoke with --role=xxx to route to role-specific execution.

Architecture

┌───────────────────────────────────────────────────┐
│  Skill(skill="team-testing")                       │
│  args="<task>" or args="--role=xxx"                │
└───────────────────┬───────────────────────────────┘
                    │ Role Router
         ┌──── --role present? ────┐
         │ NO                      │ YES
         ↓                         ↓
  Orchestration Mode         Role Dispatch
  (auto → coordinator)      (route to role.md)
         │
    ┌────┴────┬───────────┬───────────┬───────────┐
    ↓         ↓           ↓           ↓           ↓
┌──────────┐┌──────────┐┌──────────┐┌──────────┐┌─────────┐
│coordinator││strategist││generator ││ executor ││ analyst │
│          ││STRATEGY-*││TESTGEN-* ││TESTRUN-* ││TESTANA-*│
└──────────┘└──────────┘└──────────┘└──────────┘└─────────┘

Role Router

Input Parsing

Parse $ARGUMENTS to extract --role. If absent → Orchestration Mode (auto route to coordinator).

Role Registry

⚠️ COMPACT PROTECTION: 角色文件是执行文档，不是参考资料。当 context compression 发生后，角色指令仅剩摘要时，必须立即 Read 对应 role.md 重新加载后再继续执行。不得基于摘要执行任何 Phase。

Dispatch

1. Extract --role from arguments
2. If no --role → route to coordinator (Orchestration Mode)
3. Look up role in registry → Read the role file → Execute its phases

Orchestration Mode

When invoked without --role, coordinator auto-starts. User just provides task description.

Invocation: Skill(skill="team-testing", args="<task-description>")

Lifecycle:

User provides task description
  → coordinator Phase 1-3: Change scope analysis → TeamCreate → Create task chain
  → coordinator Phase 4: spawn first batch workers (background) → STOP
  → Worker executes → SendMessage callback → coordinator advances next step
  → Loop until pipeline complete → Phase 5 report

User Commands (wake paused coordinator):

Shared Infrastructure

The following templates apply to all worker roles. Each role.md only needs to write Phase 2-4 role-specific logic.

Worker Phase 1: Task Discovery (shared by all workers)

Every worker executes the same task discovery flow on startup:

1. Call TaskList() to get all tasks
2. Filter: subject matches this role’s prefix + owner is this role + status is pending + blockedBy is empty
3. No tasks → idle wait
4. Has tasks → TaskGet for details → TaskUpdate mark in_progress

Resume Artifact Check (prevent duplicate output after resume):

• Check whether this task’s output artifact already exists
• Artifact complete → skip to Phase 5 report completion
• Artifact incomplete or missing → normal Phase 2-4 execution

Worker Phase 5: Report (shared by all workers)

Standard reporting flow after task completion:

1. Message Bus: Call mcp__ccw-tools__team_msg to log message
   • Parameters: operation=”log”, team=”testing”, from=, to=”coordinator”, type=, summary=”[] “, ref=
   • CLI fallback: When MCP unavailable → ccw team log --team <session-id> --from <role> --to coordinator --type <type> --summary "[<role>] ..." --json // team must be session ID
2. SendMessage: Send result to coordinator (content and summary both prefixed with [<role>])
3. TaskUpdate: Mark task completed
4. Loop: Return to Phase 1 to check next task

Wisdom Accumulation (all roles)

Cross-task knowledge accumulation. Coordinator creates wisdom/ directory at session initialization.

Directory:

<session-folder>/wisdom/
├── learnings.md      # Patterns and insights
├── decisions.md      # Architecture and design decisions
├── conventions.md    # Codebase conventions
└── issues.md         # Known risks and issues

Worker Load (Phase 2): Extract Session: <path> from task description, read wisdom directory files. Worker Contribute (Phase 4/5): Write this task’s discoveries to corresponding wisdom files.

Role Isolation Rules

Coordinator additional restrictions: Do not write tests directly, do not execute tests, do not analyze coverage, do not bypass workers.

Output Tagging

All outputs must carry [role_name] prefix in both SendMessage content/summary and team_msg summary.

Message Bus (All Roles)

Every SendMessage before, must call mcp__ccw-tools__team_msg to log:

Parameters: operation=”log”, team=, from=, to=”coordinator”, type=, summary=”[] “, ref=

CRITICAL: team must be session ID (e.g., TST-xxx-date), NOT team name. Extract from Session: field in task description.

CLI fallback: When MCP unavailable → ccw team log --team <session-id> --from <role> --to coordinator --type <type> --summary "[<role>] ..." --json

Message types by role:

Shared Memory

All roles read in Phase 2 and write in Phase 5 to shared-memory.json:

Team Configuration

Three-Pipeline Architecture

Targeted (small-scope changes):
  STRATEGY-001 → TESTGEN-001(L1 unit) → TESTRUN-001

Standard (progressive):
  STRATEGY-001 → TESTGEN-001(L1) → TESTRUN-001(L1) → TESTGEN-002(L2) → TESTRUN-002(L2) → TESTANA-001

Comprehensive (full coverage):
  STRATEGY-001 → [TESTGEN-001(L1) + TESTGEN-002(L2)](parallel) → [TESTRUN-001(L1) + TESTRUN-002(L2)](parallel) → TESTGEN-003(L3) → TESTRUN-003(L3) → TESTANA-001

Generator-Critic Loop

generator <-> executor loop (revise tests when coverage below target):

TESTGEN → TESTRUN → (if coverage < target) → TESTGEN-fix → TESTRUN-2
                     (if coverage >= target) → next layer or TESTANA

Cadence Control

Beat model: Event-driven, each beat = coordinator wake → process → spawn → STOP. Testing beat: strategy → generate → execute → analyze.

Beat Cycle (single beat)
═══════════════════════════════════════════════════════════
  Event                   Coordinator              Workers
───────────────────────────────────────────────────────────
  callback/resume ──→ ┌─ handleCallback ─┐
                      │  mark completed   │
                      │  check pipeline   │
                      ├─ handleSpawnNext ─┤
                      │  find ready tasks │
                      │  spawn workers ───┼──→ [Worker A] Phase 1-5
                      │  (parallel OK)  ──┼──→ [Worker B] Phase 1-5
                      └─ STOP (idle) ─────┘         │
                                                     │
  callback ←─────────────────────────────────────────┘
  (next beat)              SendMessage + TaskUpdate(completed)
═══════════════════════════════════════════════════════════

Pipeline beat views:

Targeted (3 beats, strictly serial)
──────────────────────────────────────────────────────────
Beat  1            2              3
      │            │              │
      STRATEGY → TESTGEN ──→ TESTRUN
      ▲                           ▲
   pipeline                   pipeline
    start                      done

STRATEGY=strategist  TESTGEN=generator  TESTRUN=executor

Standard (6 beats, progressive layers)
──────────────────────────────────────────────────────────
Beat  1            2           3           4           5           6
      │            │           │           │           │           │
      STRATEGY → TESTGEN-L1 → TESTRUN-L1 → TESTGEN-L2 → TESTRUN-L2 → TESTANA
                                    │
                              coverage check
                        (< target → GC loop)

Comprehensive (5+ beats, parallel windows)
──────────────────────────────────────────────────────────
Beat  1                  2                       3              4         5
      │            ┌─────┴─────┐          ┌──────┴──────┐       │         │
      STRATEGY → TESTGEN-L1 ∥ TESTGEN-L2 → TESTRUN-L1 ∥ TESTRUN-L2 → TESTGEN-L3 → TESTRUN-L3 → TESTANA
                 ▲                          ▲                                                       ▲
            parallel                   parallel                                                  pipeline
            window                     window                                                     done

Checkpoints:

Stall Detection (coordinator handleCheck executes):

Task Metadata Registry

Coordinator Spawn Template

When coordinator spawns workers, use background mode (Spawn-and-Stop):

Task({
  subagent_type: "general-purpose",
  description: "Spawn <role> worker",
  team_name: "testing",
  name: "<role>",
  run_in_background: true,
  prompt: `You are team "testing" <ROLE>.

## Primary Directive
All your work must be executed through Skill to load role definition:
Skill(skill="team-testing", args="--role=<role>")

Current task: <task-description>
Session: <session-folder>

## Role Guidelines
- Only process <PREFIX>-* tasks, do not execute other role work
- All output prefixed with [<role>] identifier
- Only communicate with coordinator
- Do not use TaskCreate for other roles
- Call mcp__ccw-tools__team_msg before every SendMessage

## Workflow
1. Call Skill -> load role definition and execution logic
2. Follow role.md 5-Phase flow
3. team_msg + SendMessage results to coordinator
4. TaskUpdate completed -> check next task`
})

Unified Session Directory

.workflow/.team/TST-<slug>-<YYYY-MM-DD>/
├── team-session.json           # Session state
├── shared-memory.json          # Defect patterns / effective test patterns / coverage history
├── wisdom/                     # Cross-task knowledge
│   ├── learnings.md
│   ├── decisions.md
│   ├── conventions.md
│   └── issues.md
├── strategy/                   # Strategist output
│   └── test-strategy.md
├── tests/                      # Generator output
│   ├── L1-unit/
│   ├── L2-integration/
│   └── L3-e2e/
├── results/                    # Executor output
│   ├── run-001.json
│   └── coverage-001.json
└── analysis/                   # Analyst output
    └── quality-report.md

Error Handling