mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-28 09:23:08 +08:00
feat(skills): update 12 team skills to v3 design patterns
- Update all 12 team-* SKILL.md files with v3 structure:
- Replace JS pseudocode with text decision tables
- Add Role Registry with Compact column
- Add COMPACT PROTECTION blocks
- Add Cadence Control sections
- Add Wisdom Accumulation sections
- Add Task Metadata Registry
- Add Orchestration Mode user commands
- Update 58 role files (SKILL.md + roles/*):
- Flat-file skills: team-brainstorm, team-issue, team-testing,
team-uidesign, team-planex, team-iterdev
- Folder-based skills: team-review, team-roadmap-dev, team-frontend,
team-quality-assurance, team-tech-debt, team-ultra-analyze
- Preserve special architectures:
- team-planex: 2-member (planner + executor only)
- team-tech-debt: Stop-Wait strategy (run_in_background:false)
- team-iterdev: 7 behavior protocol tables in coordinator
- All 12 teams reviewed for content completeness (PASS)
This commit is contained in:
catlog22
@@ -4,7 +4,7 @@ Interactive roadmap discussion with the user. This is the KEY coordinator comman
|
||||
|
||||
## Purpose
|
||||
|
||||
Discuss project roadmap with the user using project-tech.json + project-guidelines.json as context. Elicit phases, requirements, success criteria, and execution preferences. Produces `roadmap.md` and `config.json` as session artifacts.
|
||||
Discuss project roadmap with the user using project-tech.json + specs/*.md as context. Elicit phases, requirements, success criteria, and execution preferences. Produces `roadmap.md` and `config.json` as session artifacts.
|
||||
|
||||
## When to Use
|
||||
|
||||
@@ -22,7 +22,7 @@ Direct interaction via AskUserQuestion. No delegation to workers or subagents. C
|
||||
| `sessionFolder` | From coordinator Phase 1 | Session artifact directory |
|
||||
| `taskDescription` | From coordinator Phase 1 | User's original task description |
|
||||
| `projectTech` | Loaded in Phase 1 | Parsed project-tech.json |
|
||||
| `projectGuidelines` | Loaded in Phase 1 | Parsed project-guidelines.json (nullable) |
|
||||
| `projectGuidelines` | Loaded in Phase 1 | Parsed specs/*.md (nullable) |
|
||||
| `autoYes` | From -y/--yes flag | Skip interactive prompts, use defaults |
|
||||
|
||||
## Execution Steps
|
||||
@@ -34,7 +34,7 @@ Direct interaction via AskUserQuestion. No delegation to workers or subagents. C
|
||||
const projectTech = JSON.parse(Read('.workflow/project-tech.json'))
|
||||
let projectGuidelines = null
|
||||
try {
|
||||
projectGuidelines = JSON.parse(Read('.workflow/project-guidelines.json'))
|
||||
projectGuidelines = JSON.parse(Read('.workflow/specs/*.md'))
|
||||
} catch {}
|
||||
```
|
||||
|
||||
|
||||
@@ -1,63 +1,54 @@
|
||||
# Role: coordinator
|
||||
# Coordinator Role
|
||||
|
||||
Team coordinator. Manages the full project lifecycle: init prerequisites → roadmap discussion with user → phase dispatch → monitoring → transitions → completion.
|
||||
Orchestrate the roadmap-driven development workflow: init prerequisites -> roadmap discussion with user -> phase dispatch -> monitoring -> transitions -> completion. Coordinator is the ONLY role that interacts with humans.
|
||||
|
||||
**Key innovation**: Roadmap is discussed with the user via `commands/roadmap-discuss.md` before any work begins. Coordinator is the ONLY role that interacts with humans.
|
||||
## Identity
|
||||
|
||||
## Role Identity
|
||||
- **Name**: `coordinator` | **Tag**: `[coordinator]`
|
||||
- **Responsibility**: Orchestration (parse requirements -> discuss roadmap -> create team -> dispatch tasks -> monitor progress -> report results)
|
||||
|
||||
- **Name**: `coordinator`
|
||||
- **Task Prefix**: N/A (coordinator creates tasks, doesn't receive them)
|
||||
- **Responsibility**: Orchestration
|
||||
- **Communication**: SendMessage to all teammates + AskUserQuestion to user
|
||||
- **Output Tag**: `[coordinator]`
|
||||
|
||||
## Role Boundaries
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
- All outputs must carry `[coordinator]` prefix
|
||||
- Handle ALL human interaction (AskUserQuestion) — workers never interact with user
|
||||
- Handle ALL human interaction (AskUserQuestion) -- workers never interact with user
|
||||
- Ensure init prerequisites before starting (project-tech.json)
|
||||
- Discuss roadmap with user before dispatching work
|
||||
- Manage state.md updates at every phase transition
|
||||
- Route verifier gap results to planner for closure
|
||||
- Parse user requirements and clarify ambiguous inputs via AskUserQuestion
|
||||
- Create team and spawn worker subagents in background
|
||||
- Dispatch tasks with proper dependency chains
|
||||
- Monitor progress via worker callbacks and route messages
|
||||
- Maintain session state persistence
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- ❌ Execute any business tasks (code, analysis, testing, verification)
|
||||
- ❌ Call code-developer, cli-explore-agent, or other implementation subagents
|
||||
- ❌ Modify source code or generate implementation artifacts
|
||||
- ❌ Bypass worker roles to do work directly
|
||||
- ❌ Skip roadmap discussion phase
|
||||
- Execute any business tasks (code, analysis, testing, verification)
|
||||
- Call code-developer, cli-explore-agent, or other implementation subagents
|
||||
- Modify source code or generate implementation artifacts
|
||||
- Bypass worker roles to do work directly
|
||||
- Skip roadmap discussion phase
|
||||
- Modify task outputs (workers own their deliverables)
|
||||
- Skip dependency validation when creating task chains
|
||||
|
||||
## Message Types
|
||||
> **Core principle**: coordinator is the orchestrator, not the executor. All actual work must be delegated to worker roles via TaskCreate.
|
||||
|
||||
| Type | Direction | Trigger | Description |
|
||||
|------|-----------|---------|-------------|
|
||||
| `phase_started` | coordinator → workers | Phase dispatch | New phase initiated |
|
||||
| `phase_complete` | coordinator → user | All phase tasks done | Phase results summary |
|
||||
| `gap_closure` | coordinator → planner | Verifier found gaps | Trigger re-plan for gaps |
|
||||
| `project_complete` | coordinator → user | All phases done | Final report |
|
||||
| `error` | coordinator → user | Critical failure | Error report |
|
||||
---
|
||||
|
||||
## Message Bus
|
||||
## Entry Router
|
||||
|
||||
```javascript
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "coordinator", to: targetRole,
|
||||
type: messageType,
|
||||
summary: `[coordinator] ${messageSummary}`,
|
||||
ref: artifactPath
|
||||
})
|
||||
```
|
||||
When coordinator is invoked, first detect the invocation type:
|
||||
|
||||
### CLI Fallback
|
||||
| Detection | Condition | Handler |
|
||||
|-----------|-----------|---------|
|
||||
| Resume mode | Arguments contain `--resume` | -> commands/resume.md: load session, re-enter monitor |
|
||||
| Status check | Arguments contain "check" or "status" | -> handleCheck: output execution graph, no advancement |
|
||||
| Manual continue | Arguments contain "resume" or "continue" | -> handleContinue: check worker states, advance pipeline |
|
||||
| New session | None of the above | -> Phase 1 (Init Prerequisites) |
|
||||
|
||||
```javascript
|
||||
Bash(`ccw team log --team "roadmap-dev" --from "coordinator" --to "${targetRole}" --type "${type}" --summary "[coordinator] ${summary}" --json`)
|
||||
```
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
@@ -65,129 +56,168 @@ Bash(`ccw team log --team "roadmap-dev" --from "coordinator" --to "${targetRole}
|
||||
|
||||
| Command | File | Phase | Description |
|
||||
|---------|------|-------|-------------|
|
||||
| `roadmap-discuss` | [commands/roadmap-discuss.md](commands/roadmap-discuss.md) | Phase 1-2 | Discuss roadmap with user, generate session artifacts |
|
||||
| `roadmap-discuss` | [commands/roadmap-discuss.md](commands/roadmap-discuss.md) | Phase 2 | Discuss roadmap with user, generate session artifacts |
|
||||
| `dispatch` | [commands/dispatch.md](commands/dispatch.md) | Phase 3 | Create task chain per phase |
|
||||
| `monitor` | [commands/monitor.md](commands/monitor.md) | Phase 4 | Stop-Wait phase execution loop |
|
||||
| `pause` | [commands/pause.md](commands/pause.md) | Any | Save state and exit cleanly |
|
||||
| `resume` | [commands/resume.md](commands/resume.md) | Any | Resume from paused session |
|
||||
|
||||
## Execution
|
||||
### Tool Capabilities
|
||||
|
||||
| Tool | Type | Used By | Purpose |
|
||||
|------|------|---------|---------|
|
||||
| `AskUserQuestion` | Human interaction | coordinator | Clarify requirements, roadmap discussion |
|
||||
| `TeamCreate` | Team management | coordinator | Create roadmap-dev team |
|
||||
| `TaskCreate` | Task dispatch | coordinator | Create PLAN-*, EXEC-*, VERIFY-* tasks |
|
||||
| `SendMessage` | Worker communication | coordinator | Receive worker callbacks |
|
||||
| `mcp__ccw-tools__team_msg` | Message bus | coordinator | Log all communications |
|
||||
| `Read/Write` | File operations | coordinator | Session state management |
|
||||
|
||||
---
|
||||
|
||||
## Message Types
|
||||
|
||||
| Type | Direction | Trigger | Description |
|
||||
|------|-----------|---------|-------------|
|
||||
| `phase_started` | coordinator -> workers | Phase dispatch | New phase initiated |
|
||||
| `phase_complete` | coordinator -> user | All phase tasks done | Phase results summary |
|
||||
| `gap_closure` | coordinator -> planner | Verifier found gaps | Trigger re-plan for gaps |
|
||||
| `project_complete` | coordinator -> user | All phases done | Final report |
|
||||
| `error` | coordinator -> user | Critical failure | Error report |
|
||||
|
||||
## Message Bus
|
||||
|
||||
Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
|
||||
|
||||
```
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log",
|
||||
team: "roadmap-dev",
|
||||
from: "coordinator",
|
||||
to: <target-role>,
|
||||
type: <message-type>,
|
||||
summary: "[coordinator] <summary>",
|
||||
ref: <artifact-path>
|
||||
})
|
||||
```
|
||||
|
||||
**CLI fallback** (when MCP unavailable):
|
||||
|
||||
```
|
||||
Bash("ccw team log --team roadmap-dev --from coordinator --to <target> --type <type> --summary \"[coordinator] <summary>\" --json")
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Execution (5-Phase)
|
||||
|
||||
### Phase 1: Init Prerequisites + Requirement Parsing
|
||||
|
||||
```javascript
|
||||
const args = "$ARGUMENTS"
|
||||
const taskDescription = args.replace(/--\w+[=\s]+\S+/g, '').trim()
|
||||
const autoYes = /\b(-y|--yes)\b/.test(args)
|
||||
const resumeMatch = args.match(/--resume[=\s]+(.+?)(?:\s|$)/)
|
||||
**Objective**: Ensure prerequisites and parse user requirements.
|
||||
|
||||
// Resume mode: skip init, load existing session
|
||||
if (resumeMatch) {
|
||||
const sessionFolder = resumeMatch[1].trim()
|
||||
Read("commands/resume.md")
|
||||
// Resume handles: validate state → load context → re-enter monitor
|
||||
return
|
||||
}
|
||||
**Workflow**:
|
||||
|
||||
// 1. Ensure project-tech.json exists
|
||||
const techExists = Bash(`test -f .workflow/project-tech.json && echo "EXISTS" || echo "NOT_FOUND"`).trim()
|
||||
if (techExists === "NOT_FOUND") {
|
||||
// Invoke workflow:init
|
||||
Skill(skill="workflow:init")
|
||||
}
|
||||
1. Parse arguments for flags: `--resume`, `--yes`, task description
|
||||
2. If `--resume` present -> load commands/resume.md and execute resume flow
|
||||
3. Ensure project-tech.json exists:
|
||||
|
||||
// 2. Load project context
|
||||
const projectTech = JSON.parse(Read('.workflow/project-tech.json'))
|
||||
let projectGuidelines = null
|
||||
try {
|
||||
projectGuidelines = JSON.parse(Read('.workflow/project-guidelines.json'))
|
||||
} catch {}
|
||||
| Condition | Action |
|
||||
|-----------|--------|
|
||||
| `.workflow/project-tech.json` exists | Continue to step 4 |
|
||||
| File not found | Invoke `Skill(skill="workflow:init")` |
|
||||
|
||||
// 3. Create session directory
|
||||
const slug = taskDescription.replace(/[^a-zA-Z0-9\u4e00-\u9fff]+/g, '-').slice(0, 30).toLowerCase()
|
||||
const date = new Date().toISOString().slice(0, 10)
|
||||
const sessionFolder = `.workflow/.team/RD-${slug}-${date}`
|
||||
Bash(`mkdir -p "${sessionFolder}"`)
|
||||
4. Load project context from project-tech.json
|
||||
5. Create session directory: `.workflow/.team/RD-<slug>-<date>/`
|
||||
6. Initialize state.md with project reference, current position, task description
|
||||
|
||||
// 4. Initialize state.md
|
||||
Write(`${sessionFolder}/state.md`, `# Roadmap Dev Session State
|
||||
|
||||
## Project Reference
|
||||
- Name: ${projectTech.project_name}
|
||||
- Session: RD-${slug}-${date}
|
||||
- Started: ${date}
|
||||
|
||||
## Current Position
|
||||
- Phase: 0 (Roadmap Discussion)
|
||||
- Status: initializing
|
||||
|
||||
## Accumulated Context
|
||||
- Task: ${taskDescription}
|
||||
`)
|
||||
```
|
||||
**Success**: Session directory created, state.md initialized.
|
||||
|
||||
### Phase 2: Roadmap Discussion (via command)
|
||||
|
||||
```javascript
|
||||
// Delegate to roadmap-discuss command
|
||||
Read("commands/roadmap-discuss.md")
|
||||
// Execute roadmap discussion with user
|
||||
// Produces: {sessionFolder}/roadmap.md, {sessionFolder}/config.json
|
||||
// Updates: {sessionFolder}/state.md
|
||||
```
|
||||
**Objective**: Discuss roadmap with user and generate phase plan.
|
||||
|
||||
Delegate to `commands/roadmap-discuss.md`:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Load commands/roadmap-discuss.md |
|
||||
| 2 | Execute interactive discussion with user |
|
||||
| 3 | Produce roadmap.md with phase requirements |
|
||||
| 4 | Produce config.json with session settings |
|
||||
| 5 | Update state.md with roadmap reference |
|
||||
|
||||
**Produces**: `<session>/roadmap.md`, `<session>/config.json`
|
||||
|
||||
**Command**: [commands/roadmap-discuss.md](commands/roadmap-discuss.md)
|
||||
|
||||
### Phase 3: Create Team + Dispatch First Phase
|
||||
|
||||
```javascript
|
||||
// 1. Create team and spawn workers
|
||||
TeamCreate({ team_name: "roadmap-dev" })
|
||||
// Spawn planner, executor, verifier (see SKILL.md Coordinator Spawn Template)
|
||||
**Objective**: Initialize team and dispatch first phase task.
|
||||
|
||||
// 2. Dispatch first phase
|
||||
Read("commands/dispatch.md")
|
||||
// Creates: PLAN-101 (phase 1 planning task)
|
||||
```
|
||||
**Workflow**:
|
||||
|
||||
1. Call `TeamCreate({ team_name: "roadmap-dev" })`
|
||||
2. Spawn worker roles (see SKILL.md Coordinator Spawn Template)
|
||||
3. Load `commands/dispatch.md` for task chain creation
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Read roadmap.md for phase definitions |
|
||||
| 2 | Create PLAN-101 task for first phase |
|
||||
| 3 | Set proper owner and dependencies |
|
||||
| 4 | Include `Session: <session-folder>` in task description |
|
||||
|
||||
**Produces**: PLAN-101 task created, workers spawned
|
||||
|
||||
**Command**: [commands/dispatch.md](commands/dispatch.md)
|
||||
|
||||
### Phase 4: Coordination Loop (Stop-Wait per phase)
|
||||
|
||||
```javascript
|
||||
Read("commands/monitor.md")
|
||||
// Executes: phase-by-phase Stop-Wait loop
|
||||
// Handles: phase transitions, gap closure, next phase dispatch
|
||||
// Continues until all roadmap phases complete
|
||||
```
|
||||
**Objective**: Monitor phase execution, handle callbacks, advance pipeline.
|
||||
|
||||
**Design**: Spawn-and-Stop + Callback pattern.
|
||||
- Spawn workers with `Task(run_in_background: true)` -> immediately return
|
||||
- Worker completes -> SendMessage callback -> auto-advance
|
||||
- User can use "check" / "resume" to manually advance
|
||||
- Coordinator does one operation per invocation, then STOPS
|
||||
|
||||
Delegate to `commands/monitor.md`:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Load commands/monitor.md |
|
||||
| 2 | Find tasks with: status=pending, blockedBy all resolved |
|
||||
| 3 | For each ready task -> spawn worker (see SKILL.md Spawn Template) |
|
||||
| 4 | Handle worker callbacks -> advance pipeline |
|
||||
| 5 | Phase complete -> transition to next phase or gap closure |
|
||||
| 6 | STOP after each operation |
|
||||
|
||||
**Pipeline advancement** driven by three wake sources:
|
||||
- Worker callback (automatic) -> handleCallback
|
||||
- User "check" -> handleCheck (status only)
|
||||
- User "resume" -> handleContinue (advance)
|
||||
|
||||
**Command**: [commands/monitor.md](commands/monitor.md)
|
||||
|
||||
### Phase 5: Report + Persist
|
||||
|
||||
```javascript
|
||||
// 1. Update state.md with final status
|
||||
const finalState = Read(`${sessionFolder}/state.md`)
|
||||
// Update status to "completed"
|
||||
**Objective**: Completion report and follow-up options.
|
||||
|
||||
// 2. Summary report to user
|
||||
const roadmap = Read(`${sessionFolder}/roadmap.md`)
|
||||
// Compile results from all phase summaries and verifications
|
||||
**Workflow**:
|
||||
|
||||
// 3. Post-completion options
|
||||
AskUserQuestion({
|
||||
questions: [{
|
||||
question: "项目执行完成。下一步？",
|
||||
header: "Next",
|
||||
multiSelect: false,
|
||||
options: [
|
||||
{ label: "提交代码", description: "git add + commit 所有变更" },
|
||||
{ label: "继续下一个里程碑", description: "开始新的 roadmap discussion" },
|
||||
{ label: "完成", description: "结束 session" }
|
||||
]
|
||||
}]
|
||||
})
|
||||
```
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Load session state -> count completed tasks, duration |
|
||||
| 2 | List deliverables with output paths |
|
||||
| 3 | Update state.md status -> "completed" |
|
||||
| 4 | Offer next steps via AskUserQuestion |
|
||||
|
||||
**Next step options**:
|
||||
- Submit code (git add + commit)
|
||||
- Continue next milestone (new roadmap discussion)
|
||||
- Complete (end session)
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
@@ -197,6 +227,11 @@ AskUserQuestion({
|
||||
| User cancels roadmap discussion | Save session state, exit gracefully |
|
||||
| Planner fails | Retry once, then ask user for guidance |
|
||||
| Executor fails on plan | Mark plan as failed, continue with next |
|
||||
| Verifier finds gaps (≤3 iterations) | Trigger gap closure: re-plan → re-execute → re-verify |
|
||||
| Verifier finds gaps (<=3 iterations) | Trigger gap closure: re-plan -> re-execute -> re-verify |
|
||||
| Verifier gaps persist (>3 iterations) | Report to user, ask for manual intervention |
|
||||
| Worker timeout | Kill worker, report partial results |
|
||||
| Task timeout | Log, mark failed, ask user to retry or skip |
|
||||
| Worker crash | Respawn worker, reassign task |
|
||||
| Dependency cycle | Detect, report to user, halt |
|
||||
| Invalid mode | Reject with error, ask to clarify |
|
||||
| Session corruption | Attempt recovery, fallback to manual reconciliation |
|
||||
|
||||
@@ -1,16 +1,14 @@
|
||||
# Role: executor
|
||||
# Executor Role
|
||||
|
||||
Code implementation per phase. Reads IMPL-*.json task files from the phase's .task/ directory, computes execution waves from the dependency graph, and executes sequentially by wave with parallel tasks within each wave. Each task is delegated to a code-developer subagent. Produces summary-{IMPL-ID}.md files for verifier consumption.
|
||||
|
||||
## Role Identity
|
||||
## Identity
|
||||
|
||||
- **Name**: `executor`
|
||||
- **Name**: `executor` | **Tag**: `[executor]`
|
||||
- **Task Prefix**: `EXEC-*`
|
||||
- **Responsibility**: Code generation
|
||||
- **Communication**: SendMessage to coordinator only
|
||||
- **Output Tag**: `[executor]`
|
||||
|
||||
## Role Boundaries
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
@@ -21,15 +19,40 @@ Code implementation per phase. Reads IMPL-*.json task files from the phase's .ta
|
||||
- Execute tasks in dependency order (sequential waves, parallel within wave)
|
||||
- Write summary-{IMPL-ID}.md per task after execution
|
||||
- Report wave progress to coordinator
|
||||
- Work strictly within Code generation responsibility scope
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Execute work outside this role's responsibility scope
|
||||
- Create plans or modify IMPL-*.json task files
|
||||
- Verify implementation against must_haves (that is verifier's job)
|
||||
- Create tasks for other roles (TaskCreate)
|
||||
- Interact with user (AskUserQuestion)
|
||||
- Process PLAN-* or VERIFY-* tasks
|
||||
- Skip loading prior summaries for cross-plan context
|
||||
- Communicate directly with other worker roles (must go through coordinator)
|
||||
- Omit `[executor]` identifier in any output
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Commands
|
||||
|
||||
| Command | File | Phase | Description |
|
||||
|---------|------|-------|-------------|
|
||||
| `implement` | [commands/implement.md](commands/implement.md) | Phase 3 | Wave-based plan execution via code-developer subagent |
|
||||
|
||||
### Tool Capabilities
|
||||
|
||||
| Tool | Type | Used By | Purpose |
|
||||
|------|------|---------|---------|
|
||||
| `code-developer` | Subagent | executor | Code implementation per plan |
|
||||
| `Read/Write` | File operations | executor | Task JSON and summary management |
|
||||
| `Glob` | Search | executor | Find task files and summaries |
|
||||
| `Bash` | Shell | executor | Syntax validation, lint checks |
|
||||
|
||||
---
|
||||
|
||||
## Message Types
|
||||
|
||||
@@ -41,232 +64,157 @@ Code implementation per phase. Reads IMPL-*.json task files from the phase's .ta
|
||||
|
||||
## Message Bus
|
||||
|
||||
```javascript
|
||||
Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
|
||||
|
||||
```
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "executor", to: "coordinator",
|
||||
type: messageType,
|
||||
summary: `[executor] ${messageSummary}`,
|
||||
ref: artifactPath
|
||||
operation: "log",
|
||||
team: "roadmap-dev",
|
||||
from: "executor",
|
||||
to: "coordinator",
|
||||
type: <message-type>,
|
||||
summary: "[executor] <task-prefix> complete: <task-subject>",
|
||||
ref: <artifact-path>
|
||||
})
|
||||
```
|
||||
|
||||
### CLI Fallback
|
||||
**CLI fallback** (when MCP unavailable):
|
||||
|
||||
```javascript
|
||||
Bash(`ccw team log --team "roadmap-dev" --from "executor" --to "coordinator" --type "${type}" --summary "[executor] ${summary}" --json`)
|
||||
```
|
||||
Bash("ccw team log --team roadmap-dev --from executor --to coordinator --type <type> --summary \"[executor] <summary>\" --ref <artifact-path> --json")
|
||||
```
|
||||
|
||||
## Toolbox
|
||||
---
|
||||
|
||||
### Available Commands
|
||||
|
||||
| Command | File | Phase | Description |
|
||||
|---------|------|-------|-------------|
|
||||
| `implement` | [commands/implement.md](commands/implement.md) | Phase 3 | Wave-based plan execution via code-developer subagent |
|
||||
|
||||
### Available Subagents
|
||||
|
||||
| Subagent | Purpose | When |
|
||||
|----------|---------|------|
|
||||
| `code-developer` | Code implementation per plan | Phase 3: delegate each plan |
|
||||
|
||||
### CLI Tools
|
||||
|
||||
None. Executor delegates all implementation work to code-developer subagent.
|
||||
|
||||
## Execution
|
||||
## Execution (5-Phase)
|
||||
|
||||
### Phase 1: Task Discovery
|
||||
|
||||
```javascript
|
||||
// Find assigned EXEC-* task
|
||||
const tasks = TaskList()
|
||||
const execTask = tasks.find(t =>
|
||||
t.subject.startsWith('EXEC-') &&
|
||||
t.status === 'pending' &&
|
||||
(!t.blockedBy || t.blockedBy.length === 0)
|
||||
)
|
||||
> See SKILL.md Shared Infrastructure -> Worker Phase 1: Task Discovery
|
||||
|
||||
if (!execTask) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "executor", to: "coordinator",
|
||||
type: "error",
|
||||
summary: "[executor] No available EXEC-* task found"
|
||||
})
|
||||
return
|
||||
}
|
||||
Standard task discovery flow: TaskList -> filter by prefix `EXEC-*` + owner match + pending + unblocked -> TaskGet -> TaskUpdate in_progress.
|
||||
|
||||
TaskUpdate({ taskId: execTask.id, status: "in_progress" })
|
||||
|
||||
// Parse task description for session context
|
||||
const taskDetails = TaskGet({ taskId: execTask.id })
|
||||
const sessionFolder = parseSessionFolder(taskDetails.description)
|
||||
const phaseNumber = parsePhaseNumber(taskDetails.description)
|
||||
```
|
||||
**Resume Artifact Check**: Check whether this task's output artifact already exists:
|
||||
- All summaries exist for phase tasks -> skip to Phase 5
|
||||
- Artifact incomplete or missing -> normal Phase 2-4 execution
|
||||
|
||||
### Phase 2: Load Tasks
|
||||
|
||||
```javascript
|
||||
// Read all task JSON files for this phase
|
||||
const taskFiles = Glob(`${sessionFolder}/phase-${phaseNumber}/.task/IMPL-*.json`)
|
||||
**Objective**: Load task JSONs and compute execution waves.
|
||||
|
||||
if (!taskFiles || taskFiles.length === 0) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "executor", to: "coordinator",
|
||||
type: "error",
|
||||
summary: `[executor] No task JSONs found in ${sessionFolder}/phase-${phaseNumber}/.task/`
|
||||
})
|
||||
return
|
||||
}
|
||||
**Loading steps**:
|
||||
|
||||
// Parse all task JSONs
|
||||
const tasks = []
|
||||
for (const taskFile of taskFiles) {
|
||||
const taskJson = JSON.parse(Read(taskFile))
|
||||
tasks.push({
|
||||
...taskJson,
|
||||
file: taskFile
|
||||
})
|
||||
}
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Task JSONs | <session-folder>/phase-{N}/.task/IMPL-*.json | Yes |
|
||||
| Prior summaries | <session-folder>/phase-{1..N-1}/summary-*.md | No |
|
||||
| Wisdom | <session-folder>/wisdom/ | No |
|
||||
|
||||
// Compute waves from dependency graph
|
||||
function computeWaves(tasks) {
|
||||
const waveMap = {}
|
||||
const assigned = new Set()
|
||||
let currentWave = 1
|
||||
while (assigned.size < tasks.length) {
|
||||
const ready = tasks.filter(t =>
|
||||
!assigned.has(t.id) &&
|
||||
(t.depends_on || []).every(d => assigned.has(d))
|
||||
)
|
||||
if (ready.length === 0 && assigned.size < tasks.length) {
|
||||
const unassigned = tasks.find(t => !assigned.has(t.id))
|
||||
ready.push(unassigned)
|
||||
}
|
||||
for (const task of ready) { waveMap[task.id] = currentWave; assigned.add(task.id) }
|
||||
currentWave++
|
||||
}
|
||||
const waves = {}
|
||||
for (const task of tasks) {
|
||||
const w = waveMap[task.id]
|
||||
if (!waves[w]) waves[w] = []
|
||||
waves[w].push(task)
|
||||
}
|
||||
return { waves, waveNumbers: Object.keys(waves).map(Number).sort((a, b) => a - b) }
|
||||
}
|
||||
1. **Find task files**:
|
||||
- Glob `{sessionFolder}/phase-{phaseNumber}/.task/IMPL-*.json`
|
||||
- If no files found -> error to coordinator
|
||||
|
||||
const { waves, waveNumbers } = computeWaves(tasks)
|
||||
2. **Parse all task JSONs**:
|
||||
- Read each task file
|
||||
- Extract: id, description, depends_on, files, convergence
|
||||
|
||||
// Load prior summaries for cross-task context
|
||||
const priorSummaries = []
|
||||
for (let p = 1; p < phaseNumber; p++) {
|
||||
try {
|
||||
const summaryFiles = Glob(`${sessionFolder}/phase-${p}/summary-*.md`)
|
||||
for (const sf of summaryFiles) {
|
||||
priorSummaries.push({ phase: p, content: Read(sf) })
|
||||
}
|
||||
} catch {}
|
||||
}
|
||||
```
|
||||
3. **Compute waves from dependency graph**:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Start with wave=1, assigned=set(), waveMap={} |
|
||||
| 2 | Find tasks with all dependencies in assigned |
|
||||
| 3 | If none found but tasks remain -> force-assign first unassigned |
|
||||
| 4 | Assign ready tasks to current wave, add to assigned |
|
||||
| 5 | Increment wave, repeat until all tasks assigned |
|
||||
| 6 | Group tasks by wave number |
|
||||
|
||||
4. **Load prior summaries for cross-task context**:
|
||||
- For each prior phase, read summary files
|
||||
- Store for reference during implementation
|
||||
|
||||
### Phase 3: Implement (via command)
|
||||
|
||||
```javascript
|
||||
// Delegate to implement command
|
||||
Read("commands/implement.md")
|
||||
// Execute wave-based implementation:
|
||||
// 1. Compute waves from depends_on graph
|
||||
// 2. For each wave (sequential): execute all tasks in the wave
|
||||
// 3. For each task in wave: delegate to code-developer subagent
|
||||
// 4. Write summary-{IMPL-ID}.md per task
|
||||
// 5. Report wave progress
|
||||
//
|
||||
// Produces: {sessionFolder}/phase-{N}/summary-IMPL-*.md
|
||||
```
|
||||
**Objective**: Execute wave-based implementation.
|
||||
|
||||
Delegate to `commands/implement.md`:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | For each wave (sequential): |
|
||||
| 2 | For each task in wave: delegate to code-developer subagent |
|
||||
| 3 | Write summary-{IMPL-ID}.md per task |
|
||||
| 4 | Report wave progress |
|
||||
| 5 | Continue to next wave |
|
||||
|
||||
**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 |
|
||||
|
||||
**Produces**: `{sessionFolder}/phase-{N}/summary-IMPL-*.md`
|
||||
|
||||
**Command**: [commands/implement.md](commands/implement.md)
|
||||
|
||||
### Phase 4: Self-Validation
|
||||
|
||||
```javascript
|
||||
// Basic validation after implementation — NOT full verification (that is verifier's job)
|
||||
const summaryFiles = Glob(`${sessionFolder}/phase-${phaseNumber}/summary-*.md`)
|
||||
**Objective**: Basic validation after implementation (NOT full verification).
|
||||
|
||||
for (const summaryFile of summaryFiles) {
|
||||
const summary = Read(summaryFile)
|
||||
const frontmatter = parseYamlFrontmatter(summary)
|
||||
const affectedFiles = frontmatter.affects || frontmatter['key-files'] || []
|
||||
**Validation checks**:
|
||||
|
||||
for (const filePath of affectedFiles) {
|
||||
// 4a. Check file exists
|
||||
const exists = Bash(`test -f "${filePath}" && echo "EXISTS" || echo "NOT_FOUND"`).trim()
|
||||
if (exists === "NOT_FOUND") {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "executor", to: "coordinator",
|
||||
type: "error",
|
||||
summary: `[executor] Expected file not found after implementation: ${filePath}`,
|
||||
ref: summaryFile
|
||||
})
|
||||
}
|
||||
| Check | Method | Pass Criteria |
|
||||
|-------|--------|---------------|
|
||||
| File existence | `test -f <path>` | All affected files exist |
|
||||
| TypeScript syntax | `npx tsc --noEmit` | No TS errors |
|
||||
| Lint | `npm run lint` | No critical errors |
|
||||
|
||||
// 4b. Syntax check (basic — language-aware)
|
||||
if (filePath.endsWith('.ts') || filePath.endsWith('.tsx')) {
|
||||
const syntaxCheck = Bash(`npx tsc --noEmit "${filePath}" 2>&1 || true`)
|
||||
if (syntaxCheck.includes('error TS')) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "executor", to: "coordinator",
|
||||
type: "error",
|
||||
summary: `[executor] TypeScript syntax errors in ${filePath}`,
|
||||
ref: summaryFile
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
**Validation steps**:
|
||||
|
||||
// 4c. Run lint once for all changes (best-effort)
|
||||
Bash(`npm run lint 2>&1 || yarn lint 2>&1 || true`)
|
||||
```
|
||||
1. **Find summary files**: Glob `{sessionFolder}/phase-{phaseNumber}/summary-*.md`
|
||||
|
||||
2. **For each summary**:
|
||||
- Parse frontmatter for affected files
|
||||
- Check each file exists
|
||||
- Run syntax check for TypeScript files
|
||||
- Log errors via team_msg
|
||||
|
||||
3. **Run lint once for all changes** (best-effort)
|
||||
|
||||
### Phase 5: Report to Coordinator
|
||||
|
||||
```javascript
|
||||
const taskCount = tasks.length
|
||||
const waveCount = waveNumbers.length
|
||||
const writtenSummaries = Glob(`${sessionFolder}/phase-${phaseNumber}/summary-*.md`)
|
||||
> See SKILL.md Shared Infrastructure -> Worker Phase 5: Report
|
||||
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "executor", to: "coordinator",
|
||||
type: "exec_complete",
|
||||
summary: `[executor] Phase ${phaseNumber} executed: ${taskCount} tasks across ${waveCount} waves. ${writtenSummaries.length} summaries written.`,
|
||||
ref: `${sessionFolder}/phase-${phaseNumber}/`
|
||||
})
|
||||
Standard report flow: team_msg log -> SendMessage with `[executor]` prefix -> TaskUpdate completed -> Loop to Phase 1 for next task.
|
||||
|
||||
**Report message**:
|
||||
```
|
||||
SendMessage({
|
||||
to: "coordinator",
|
||||
message: `[executor] Phase ${phaseNumber} execution complete.
|
||||
- Tasks executed: ${taskCount}
|
||||
- Waves: ${waveCount}
|
||||
- Summaries: ${writtenSummaries.map(f => f).join(', ')}
|
||||
message: "[executor] Phase <N> execution complete.
|
||||
- Tasks executed: <count>
|
||||
- Waves: <wave-count>
|
||||
- Summaries: <file-list>
|
||||
|
||||
Ready for verification.`
|
||||
Ready for verification."
|
||||
})
|
||||
|
||||
TaskUpdate({ taskId: execTask.id, status: "completed" })
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| No EXEC-* tasks available | Idle, wait for coordinator assignment |
|
||||
| Context/Plan file not found | Notify coordinator, request location |
|
||||
| Command file not found | Fall back to inline execution |
|
||||
| No task JSON files found | Error to coordinator -- planner may have failed |
|
||||
| code-developer subagent fails | Retry once. If still fails, log error in summary, continue with next plan |
|
||||
| Syntax errors after implementation | Log in summary, continue -- verifier will catch remaining issues |
|
||||
| Missing dependency from earlier wave | Error to coordinator -- dependency graph may be incorrect |
|
||||
| File conflict between parallel plans | Log warning, last write wins -- verifier will validate correctness |
|
||||
| Critical issue beyond scope | SendMessage fix_required to coordinator |
|
||||
| Unexpected error | Log error via team_msg, report to coordinator |
|
||||
|
||||
@@ -1,16 +1,14 @@
|
||||
# Role: planner
|
||||
# Planner Role
|
||||
|
||||
Research and plan creation per phase. Gathers codebase context via cli-explore-agent and Gemini CLI, then generates wave-based execution plans with must_haves verification criteria. Each plan is a self-contained unit of work that an executor can implement autonomously.
|
||||
Research and plan creation per phase. Gathers codebase context via cli-explore-agent and Gemini CLI, then generates wave-based execution plans with convergence criteria. Each plan is a self-contained unit of work that an executor can implement autonomously.
|
||||
|
||||
## Role Identity
|
||||
## Identity
|
||||
|
||||
- **Name**: `planner`
|
||||
- **Name**: `planner` | **Tag**: `[planner]`
|
||||
- **Task Prefix**: `PLAN-*`
|
||||
- **Responsibility**: Orchestration (research + plan generation)
|
||||
- **Communication**: SendMessage to coordinator only
|
||||
- **Output Tag**: `[planner]`
|
||||
|
||||
## Role Boundaries
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
@@ -21,15 +19,42 @@ Research and plan creation per phase. Gathers codebase context via cli-explore-a
|
||||
- Delegate plan creation to commands/create-plans.md
|
||||
- Reference real files discovered during research (never fabricate paths)
|
||||
- Verify plans have no dependency cycles before reporting
|
||||
- Work strictly within Orchestration responsibility scope
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Execute work outside this role's responsibility scope
|
||||
- Direct code writing or modification
|
||||
- Call code-developer or other implementation subagents
|
||||
- Create tasks for other roles (TaskCreate)
|
||||
- Interact with user (AskUserQuestion)
|
||||
- Process EXEC-* or VERIFY-* tasks
|
||||
- Skip the research phase
|
||||
- Communicate directly with other worker roles (must go through coordinator)
|
||||
- Omit `[planner]` identifier in any output
|
||||
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
### Available Commands
|
||||
|
||||
| Command | File | Phase | Description |
|
||||
|---------|------|-------|-------------|
|
||||
| `research` | [commands/research.md](commands/research.md) | Phase 2 | Context gathering via codebase exploration |
|
||||
| `create-plans` | [commands/create-plans.md](commands/create-plans.md) | Phase 3 | Wave-based plan file generation |
|
||||
|
||||
### Tool Capabilities
|
||||
|
||||
| Tool | Type | Used By | Purpose |
|
||||
|------|------|---------|---------|
|
||||
| `cli-explore-agent` | Subagent | planner | Codebase exploration, pattern analysis |
|
||||
| `action-planning-agent` | Subagent | planner | Task JSON + IMPL_PLAN.md generation |
|
||||
| `gemini` | CLI tool | planner | Deep analysis for complex phases (optional) |
|
||||
| `Read/Write` | File operations | planner | Context and plan file management |
|
||||
| `Glob/Grep` | Search | planner | File discovery and pattern matching |
|
||||
|
||||
---
|
||||
|
||||
## Message Types
|
||||
|
||||
@@ -41,241 +66,171 @@ Research and plan creation per phase. Gathers codebase context via cli-explore-a
|
||||
|
||||
## Message Bus
|
||||
|
||||
```javascript
|
||||
Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
|
||||
|
||||
```
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: messageType,
|
||||
summary: `[planner] ${messageSummary}`,
|
||||
ref: artifactPath
|
||||
operation: "log",
|
||||
team: "roadmap-dev",
|
||||
from: "planner",
|
||||
to: "coordinator",
|
||||
type: <message-type>,
|
||||
summary: "[planner] <task-prefix> complete: <task-subject>",
|
||||
ref: <artifact-path>
|
||||
})
|
||||
```
|
||||
|
||||
### CLI Fallback
|
||||
**CLI fallback** (when MCP unavailable):
|
||||
|
||||
```javascript
|
||||
Bash(`ccw team log --team "roadmap-dev" --from "planner" --to "coordinator" --type "${type}" --summary "[planner] ${summary}" --json`)
|
||||
```
|
||||
Bash("ccw team log --team roadmap-dev --from planner --to coordinator --type <type> --summary \"[planner] <summary>\" --ref <artifact-path> --json")
|
||||
```
|
||||
|
||||
## Toolbox
|
||||
---
|
||||
|
||||
### Available Commands
|
||||
|
||||
| Command | File | Phase | Description |
|
||||
|---------|------|-------|-------------|
|
||||
| `research` | [commands/research.md](commands/research.md) | Phase 2 | Context gathering via codebase exploration |
|
||||
| `create-plans` | [commands/create-plans.md](commands/create-plans.md) | Phase 3 | Wave-based plan file generation |
|
||||
|
||||
### Available Subagents
|
||||
|
||||
| Subagent | Purpose | When |
|
||||
|----------|---------|------|
|
||||
| `cli-explore-agent` | Codebase exploration (file discovery, pattern analysis) | Phase 2: Research |
|
||||
| `action-planning-agent` | Task JSON + IMPL_PLAN.md generation | Phase 3: Create Plans |
|
||||
|
||||
### CLI Tools
|
||||
|
||||
| Tool | Mode | When |
|
||||
|------|------|------|
|
||||
| `gemini` | analysis | Deep analysis for complex phases (optional, depth=comprehensive) |
|
||||
|
||||
## Execution
|
||||
## Execution (5-Phase)
|
||||
|
||||
### Phase 1: Task Discovery
|
||||
|
||||
```javascript
|
||||
// Find assigned PLAN-* task
|
||||
const tasks = TaskList()
|
||||
const planTask = tasks.find(t =>
|
||||
t.subject.startsWith('PLAN-') &&
|
||||
t.status === 'pending' &&
|
||||
(!t.blockedBy || t.blockedBy.length === 0)
|
||||
)
|
||||
> See SKILL.md Shared Infrastructure -> Worker Phase 1: Task Discovery
|
||||
|
||||
if (!planTask) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "error",
|
||||
summary: "[planner] No available PLAN-* task found"
|
||||
})
|
||||
return
|
||||
}
|
||||
Standard task discovery flow: TaskList -> filter by prefix `PLAN-*` + owner match + pending + unblocked -> TaskGet -> TaskUpdate in_progress.
|
||||
|
||||
TaskUpdate({ taskId: planTask.id, status: "in_progress" })
|
||||
|
||||
// Parse task description for session context
|
||||
const taskDetails = TaskGet({ taskId: planTask.id })
|
||||
const sessionFolder = parseSessionFolder(taskDetails.description)
|
||||
const phaseNumber = parsePhaseNumber(taskDetails.description)
|
||||
const depth = parseDepth(taskDetails.description) || "standard"
|
||||
```
|
||||
**Resume Artifact Check**: Check whether this task's output artifact already exists:
|
||||
- `<session>/phase-N/context.md` exists -> skip to Phase 3
|
||||
- Artifact incomplete or missing -> normal Phase 2-4 execution
|
||||
|
||||
### Phase 2: Research (via command)
|
||||
|
||||
```javascript
|
||||
// Delegate to research command
|
||||
Read("commands/research.md")
|
||||
// Execute research steps:
|
||||
// 1. Read roadmap.md for phase goal and requirements
|
||||
// 2. Read prior phase summaries (if any)
|
||||
// 3. Launch cli-explore-agent for codebase exploration
|
||||
// 4. Optional: Gemini CLI for deeper analysis (if depth=comprehensive)
|
||||
// 5. Write context.md to {sessionFolder}/phase-{N}/context.md
|
||||
//
|
||||
// Produces: {sessionFolder}/phase-{N}/context.md
|
||||
```
|
||||
**Objective**: Gather codebase context for plan generation.
|
||||
|
||||
**Loading steps**:
|
||||
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| roadmap.md | <session-folder>/roadmap.md | Yes |
|
||||
| Prior phase summaries | <session-folder>/phase-*/summary-*.md | No |
|
||||
| Wisdom | <session-folder>/wisdom/ | No |
|
||||
|
||||
Delegate to `commands/research.md`:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Read roadmap.md for phase goal and requirements |
|
||||
| 2 | Read prior phase summaries (if any) |
|
||||
| 3 | Launch cli-explore-agent for codebase exploration |
|
||||
| 4 | Optional: Gemini CLI for deeper analysis (if depth=comprehensive) |
|
||||
| 5 | Write context.md to {sessionFolder}/phase-{N}/context.md |
|
||||
|
||||
**Produces**: `{sessionFolder}/phase-{N}/context.md`
|
||||
|
||||
**Command**: [commands/research.md](commands/research.md)
|
||||
|
||||
```javascript
|
||||
// Report research progress
|
||||
**Report progress via team_msg**:
|
||||
```
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "plan_progress",
|
||||
summary: `[planner] Research complete for phase ${phaseNumber}. Context written.`,
|
||||
ref: `${sessionFolder}/phase-${phaseNumber}/context.md`
|
||||
summary: "[planner] Research complete for phase <N>. Context written.",
|
||||
ref: "<session>/phase-<N>/context.md"
|
||||
})
|
||||
```
|
||||
|
||||
### Phase 3: Create Plans (via command)
|
||||
|
||||
```javascript
|
||||
// Delegate to create-plans command
|
||||
Read("commands/create-plans.md")
|
||||
// Execute plan creation steps:
|
||||
// 1. Load context.md for phase
|
||||
// 2. Prepare output directories (.task/)
|
||||
// 3. Delegate to action-planning-agent
|
||||
// 4. Agent produces IMPL_PLAN.md + .task/IMPL-*.json + TODO_LIST.md
|
||||
// 5. Validate generated artifacts
|
||||
// 6. Return task count and dependency structure
|
||||
//
|
||||
// Produces: {sessionFolder}/phase-{N}/IMPL_PLAN.md
|
||||
// {sessionFolder}/phase-{N}/.task/IMPL-*.json
|
||||
// {sessionFolder}/phase-{N}/TODO_LIST.md
|
||||
```
|
||||
**Objective**: Generate wave-based execution plans.
|
||||
|
||||
Delegate to `commands/create-plans.md`:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Load context.md for phase |
|
||||
| 2 | Prepare output directories (.task/) |
|
||||
| 3 | Delegate to action-planning-agent |
|
||||
| 4 | Agent produces IMPL_PLAN.md + .task/IMPL-*.json + TODO_LIST.md |
|
||||
| 5 | Validate generated artifacts |
|
||||
| 6 | Return task count and dependency structure |
|
||||
|
||||
**Produces**:
|
||||
- `{sessionFolder}/phase-{N}/IMPL_PLAN.md`
|
||||
- `{sessionFolder}/phase-{N}/.task/IMPL-*.json`
|
||||
- `{sessionFolder}/phase-{N}/TODO_LIST.md`
|
||||
|
||||
**Command**: [commands/create-plans.md](commands/create-plans.md)
|
||||
|
||||
### Phase 4: Self-Validation
|
||||
|
||||
```javascript
|
||||
// Verify task JSONs before reporting
|
||||
const taskFiles = Glob(`${sessionFolder}/phase-${phaseNumber}/.task/IMPL-*.json`)
|
||||
**Objective**: Verify task JSONs before reporting.
|
||||
|
||||
for (const taskFile of taskFiles) {
|
||||
const taskJson = JSON.parse(Read(taskFile))
|
||||
**Validation checks**:
|
||||
|
||||
// 4a. Verify referenced files exist (for modify actions only)
|
||||
for (const fileEntry of (taskJson.files || [])) {
|
||||
if (fileEntry.action === 'modify') {
|
||||
const exists = Bash(`test -f "${fileEntry.path}" && echo "EXISTS" || echo "NOT_FOUND"`).trim()
|
||||
if (exists === "NOT_FOUND") {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "plan_progress",
|
||||
summary: `[planner] Warning: ${taskJson.id} references ${fileEntry.path} for modify but file not found`,
|
||||
ref: taskFile
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
| Check | Method | Pass Criteria |
|
||||
|-------|--------|---------------|
|
||||
| Referenced files exist | `test -f <path>` for modify actions | All files found or warning logged |
|
||||
| Self-dependency | Check if depends_on includes own ID | No self-dependencies |
|
||||
| Convergence criteria | Check convergence.criteria exists | Each task has criteria |
|
||||
| Cross-dependency | Verify all depends_on IDs exist | All dependencies valid |
|
||||
|
||||
// 4b. Self-dependency check
|
||||
if ((taskJson.depends_on || []).includes(taskJson.id)) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "error",
|
||||
summary: `[planner] Self-dependency detected: ${taskJson.id}`,
|
||||
ref: taskFile
|
||||
})
|
||||
}
|
||||
**Validation steps**:
|
||||
|
||||
// 4c. Convergence criteria check
|
||||
if (!taskJson.convergence?.criteria?.length) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "plan_progress",
|
||||
summary: `[planner] Warning: ${taskJson.id} has no convergence criteria`,
|
||||
ref: taskFile
|
||||
})
|
||||
}
|
||||
}
|
||||
1. **File existence check** (for modify actions):
|
||||
- For each task file with action="modify"
|
||||
- Check file exists
|
||||
- Log warning if not found
|
||||
|
||||
// 4d. Cross-dependency validation
|
||||
const allTasks = taskFiles.map(f => JSON.parse(Read(f)))
|
||||
const taskIds = new Set(allTasks.map(t => t.id))
|
||||
for (const task of allTasks) {
|
||||
for (const dep of (task.depends_on || [])) {
|
||||
if (!taskIds.has(dep)) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "plan_progress",
|
||||
summary: `[planner] Warning: ${task.id} depends on unknown task ${dep}`
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
2. **Self-dependency check**:
|
||||
- For each task, verify task.id not in task.depends_on
|
||||
- Log error if self-dependency detected
|
||||
|
||||
3. **Convergence criteria check**:
|
||||
- Verify each task has convergence.criteria array
|
||||
- Log warning if missing
|
||||
|
||||
4. **Cross-dependency validation**:
|
||||
- Collect all task IDs
|
||||
- Verify each depends_on reference exists
|
||||
- Log warning if unknown dependency
|
||||
|
||||
### Phase 5: Report to Coordinator
|
||||
|
||||
```javascript
|
||||
const taskCount = allTasks.length
|
||||
> See SKILL.md Shared Infrastructure -> Worker Phase 5: Report
|
||||
|
||||
// Compute wave count from dependency graph
|
||||
function computeWaveCount(tasks) {
|
||||
const waves = {}
|
||||
const assigned = new Set()
|
||||
let wave = 1
|
||||
while (assigned.size < tasks.length) {
|
||||
const ready = tasks.filter(t =>
|
||||
!assigned.has(t.id) &&
|
||||
(t.depends_on || []).every(d => assigned.has(d))
|
||||
)
|
||||
if (ready.length === 0) break
|
||||
for (const t of ready) { waves[t.id] = wave; assigned.add(t.id) }
|
||||
wave++
|
||||
}
|
||||
return wave - 1
|
||||
}
|
||||
const waveCount = computeWaveCount(allTasks)
|
||||
Standard report flow: team_msg log -> SendMessage with `[planner]` prefix -> TaskUpdate completed -> Loop to Phase 1 for next task.
|
||||
|
||||
// Log plan_ready message
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "planner", to: "coordinator",
|
||||
type: "plan_ready",
|
||||
summary: `[planner] Phase ${phaseNumber} planned: ${taskCount} tasks across ${waveCount} waves`,
|
||||
ref: `${sessionFolder}/phase-${phaseNumber}/`
|
||||
})
|
||||
**Wave count computation**:
|
||||
|
||||
// Send message to coordinator
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | Start with wave=1, assigned=set() |
|
||||
| 2 | Find tasks with all dependencies in assigned |
|
||||
| 3 | Assign those tasks to current wave, add to assigned |
|
||||
| 4 | Increment wave, repeat until all tasks assigned |
|
||||
| 5 | Return wave count |
|
||||
|
||||
**Report message**:
|
||||
```
|
||||
SendMessage({
|
||||
to: "coordinator",
|
||||
message: `[planner] Phase ${phaseNumber} planning complete.
|
||||
- Tasks: ${taskCount}
|
||||
- Waves: ${waveCount}
|
||||
- IMPL_PLAN: ${sessionFolder}/phase-${phaseNumber}/IMPL_PLAN.md
|
||||
- Task JSONs: ${taskFiles.map(f => f).join(', ')}
|
||||
message: "[planner] Phase <N> planning complete.
|
||||
- Tasks: <count>
|
||||
- Waves: <wave-count>
|
||||
- IMPL_PLAN: <session>/phase-<N>/IMPL_PLAN.md
|
||||
- Task JSONs: <file-list>
|
||||
|
||||
All tasks validated. Ready for execution.`
|
||||
All tasks validated. Ready for execution."
|
||||
})
|
||||
|
||||
// Mark task complete
|
||||
TaskUpdate({ taskId: planTask.id, status: "completed" })
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| No PLAN-* tasks available | Idle, wait for coordinator assignment |
|
||||
| Context/Plan file not found | Notify coordinator, request location |
|
||||
| Command file not found | Fall back to inline execution |
|
||||
| roadmap.md not found | Error to coordinator -- dispatch may have failed |
|
||||
| cli-explore-agent fails | Retry once. If still fails, use direct ACE search as fallback |
|
||||
| Gemini CLI fails | Skip deep analysis, proceed with basic context |
|
||||
@@ -284,3 +239,5 @@ TaskUpdate({ taskId: planTask.id, status: "completed" })
|
||||
| No requirements found for phase | Error to coordinator -- roadmap may be malformed |
|
||||
| Dependency cycle detected | Log warning, break cycle |
|
||||
| Referenced file not found | Log warning. If file is from prior wave, acceptable |
|
||||
| Critical issue beyond scope | SendMessage fix_required to coordinator |
|
||||
| Unexpected error | Log error via team_msg, report to coordinator |
|
||||
|
||||
@@ -1,16 +1,14 @@
|
||||
# Role: verifier
|
||||
# Verifier Role
|
||||
|
||||
Goal-backward verification per phase. Reads convergence criteria from IMPL-*.json task files and checks them against the actual codebase state after execution. Does NOT modify code — read-only validation. Produces verification.md with pass/fail results and structured gap lists.
|
||||
Goal-backward verification per phase. Reads convergence criteria from IMPL-*.json task files and checks them against the actual codebase state after execution. Does NOT modify code -- read-only validation. Produces verification.md with pass/fail results and structured gap lists.
|
||||
|
||||
## Role Identity
|
||||
## Identity
|
||||
|
||||
- **Name**: `verifier`
|
||||
- **Name**: `verifier` | **Tag**: `[verifier]`
|
||||
- **Task Prefix**: `VERIFY-*`
|
||||
- **Responsibility**: Validation
|
||||
- **Communication**: SendMessage to coordinator only
|
||||
- **Output Tag**: `[verifier]`
|
||||
|
||||
## Role Boundaries
|
||||
## Boundaries
|
||||
|
||||
### MUST
|
||||
|
||||
@@ -21,41 +19,21 @@ Goal-backward verification per phase. Reads convergence criteria from IMPL-*.jso
|
||||
- Check goals (what should exist), NOT tasks (what was done)
|
||||
- Produce structured gap lists for failed items
|
||||
- Remain read-only -- never modify source code
|
||||
- Work strictly within Validation responsibility scope
|
||||
|
||||
### MUST NOT
|
||||
|
||||
- Execute work outside this role's responsibility scope
|
||||
- Modify any source code or project files
|
||||
- Create plans or execute implementations
|
||||
- Create tasks for other roles (TaskCreate)
|
||||
- Interact with user (AskUserQuestion)
|
||||
- Process PLAN-* or EXEC-* tasks
|
||||
- Auto-fix issues (report them, let planner/executor handle fixes)
|
||||
- Communicate directly with other worker roles (must go through coordinator)
|
||||
- Omit `[verifier]` identifier in any output
|
||||
|
||||
## Message Types
|
||||
|
||||
| Type | Direction | Trigger | Description |
|
||||
|------|-----------|---------|-------------|
|
||||
| `verify_passed` | verifier -> coordinator | All must_haves met | Phase verification passed |
|
||||
| `gaps_found` | verifier -> coordinator | Some must_haves failed | Structured gap list for re-planning |
|
||||
| `error` | verifier -> coordinator | Failure | Verification process failed |
|
||||
|
||||
## Message Bus
|
||||
|
||||
```javascript
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "verifier", to: "coordinator",
|
||||
type: messageType,
|
||||
summary: `[verifier] ${messageSummary}`,
|
||||
ref: artifactPath
|
||||
})
|
||||
```
|
||||
|
||||
### CLI Fallback
|
||||
|
||||
```javascript
|
||||
Bash(`ccw team log --team "roadmap-dev" --from "verifier" --to "coordinator" --type "${type}" --summary "[verifier] ${summary}" --json`)
|
||||
```
|
||||
---
|
||||
|
||||
## Toolbox
|
||||
|
||||
@@ -63,205 +41,207 @@ Bash(`ccw team log --team "roadmap-dev" --from "verifier" --to "coordinator" --t
|
||||
|
||||
| Command | File | Phase | Description |
|
||||
|---------|------|-------|-------------|
|
||||
| `verify` | [commands/verify.md](commands/verify.md) | Phase 3 | Goal-backward must_haves checking |
|
||||
| `verify` | [commands/verify.md](commands/verify.md) | Phase 3 | Goal-backward convergence criteria checking |
|
||||
|
||||
### Available Subagents
|
||||
### Tool Capabilities
|
||||
|
||||
None. Verifier executes checks directly using built-in tools (Read, Grep, Bash).
|
||||
| Tool | Type | Used By | Purpose |
|
||||
|------|------|---------|---------|
|
||||
| `gemini` | CLI tool | verifier | Deep semantic checks for complex truths (optional) |
|
||||
| `Read` | File operations | verifier | Task JSON and summary reading |
|
||||
| `Glob` | Search | verifier | Find task and summary files |
|
||||
| `Bash` | Shell | verifier | Execute verification commands |
|
||||
| `Grep` | Search | verifier | Pattern matching in codebase |
|
||||
|
||||
### CLI Tools
|
||||
---
|
||||
|
||||
| Tool | Mode | When |
|
||||
|------|------|------|
|
||||
| `gemini` | analysis | Deep semantic checks for complex truths (optional) |
|
||||
## Message Types
|
||||
|
||||
## Execution
|
||||
| Type | Direction | Trigger | Description |
|
||||
|------|-----------|---------|-------------|
|
||||
| `verify_passed` | verifier -> coordinator | All convergence criteria met | Phase verification passed |
|
||||
| `gaps_found` | verifier -> coordinator | Some criteria failed | Structured gap list for re-planning |
|
||||
| `error` | verifier -> coordinator | Failure | Verification process failed |
|
||||
|
||||
## Message Bus
|
||||
|
||||
Before every SendMessage, log via `mcp__ccw-tools__team_msg`:
|
||||
|
||||
```
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log",
|
||||
team: "roadmap-dev",
|
||||
from: "verifier",
|
||||
to: "coordinator",
|
||||
type: <message-type>,
|
||||
summary: "[verifier] <task-prefix> complete: <task-subject>",
|
||||
ref: <artifact-path>
|
||||
})
|
||||
```
|
||||
|
||||
**CLI fallback** (when MCP unavailable):
|
||||
|
||||
```
|
||||
Bash("ccw team log --team roadmap-dev --from verifier --to coordinator --type <type> --summary \"[verifier] <summary>\" --ref <artifact-path> --json")
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Execution (5-Phase)
|
||||
|
||||
### Phase 1: Task Discovery
|
||||
|
||||
```javascript
|
||||
// Find assigned VERIFY-* task
|
||||
const tasks = TaskList()
|
||||
const verifyTask = tasks.find(t =>
|
||||
t.subject.startsWith('VERIFY-') &&
|
||||
t.status === 'pending' &&
|
||||
(!t.blockedBy || t.blockedBy.length === 0)
|
||||
)
|
||||
> See SKILL.md Shared Infrastructure -> Worker Phase 1: Task Discovery
|
||||
|
||||
if (!verifyTask) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "verifier", to: "coordinator",
|
||||
type: "error",
|
||||
summary: "[verifier] No available VERIFY-* task found"
|
||||
})
|
||||
return
|
||||
}
|
||||
Standard task discovery flow: TaskList -> filter by prefix `VERIFY-*` + owner match + pending + unblocked -> TaskGet -> TaskUpdate in_progress.
|
||||
|
||||
TaskUpdate({ taskId: verifyTask.id, status: "in_progress" })
|
||||
|
||||
// Parse task description for session context
|
||||
const taskDetails = TaskGet({ taskId: verifyTask.id })
|
||||
const sessionFolder = parseSessionFolder(taskDetails.description)
|
||||
const phaseNumber = parsePhaseNumber(taskDetails.description)
|
||||
```
|
||||
**Resume Artifact Check**: Check whether this task's output artifact already exists:
|
||||
- `<session>/phase-N/verification.md` exists -> skip to Phase 5
|
||||
- Artifact incomplete or missing -> normal Phase 2-4 execution
|
||||
|
||||
### Phase 2: Load Verification Targets
|
||||
|
||||
```javascript
|
||||
// Read all task JSON files for convergence criteria
|
||||
const taskFiles = Glob(`${sessionFolder}/phase-${phaseNumber}/.task/IMPL-*.json`)
|
||||
const tasks = []
|
||||
**Objective**: Load task JSONs and summaries for verification.
|
||||
|
||||
for (const taskFile of taskFiles) {
|
||||
const taskJson = JSON.parse(Read(taskFile))
|
||||
tasks.push({
|
||||
...taskJson,
|
||||
file: taskFile
|
||||
})
|
||||
}
|
||||
**Detection steps**:
|
||||
|
||||
// Read all summary files for what was done
|
||||
const summaryFiles = Glob(`${sessionFolder}/phase-${phaseNumber}/summary-*.md`)
|
||||
const summaries = []
|
||||
| Input | Source | Required |
|
||||
|-------|--------|----------|
|
||||
| Task JSONs | <session-folder>/phase-{N}/.task/IMPL-*.json | Yes |
|
||||
| Summaries | <session-folder>/phase-{N}/summary-*.md | Yes |
|
||||
| Wisdom | <session-folder>/wisdom/ | No |
|
||||
|
||||
for (const summaryFile of summaryFiles) {
|
||||
const content = Read(summaryFile)
|
||||
const frontmatter = parseYamlFrontmatter(content)
|
||||
summaries.push({
|
||||
file: summaryFile,
|
||||
task: frontmatter.task,
|
||||
affects: frontmatter.affects || frontmatter['key-files'] || [],
|
||||
provides: frontmatter.provides || []
|
||||
})
|
||||
}
|
||||
1. **Read task JSON files**:
|
||||
- Find all IMPL-*.json files
|
||||
- Extract convergence criteria from each task
|
||||
- If no files found -> error to coordinator
|
||||
|
||||
if (tasks.length === 0) {
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "verifier", to: "coordinator",
|
||||
type: "error",
|
||||
summary: `[verifier] No task JSON files found in ${sessionFolder}/phase-${phaseNumber}/.task/`
|
||||
})
|
||||
return
|
||||
}
|
||||
```
|
||||
2. **Read summary files**:
|
||||
- Find all summary-*.md files
|
||||
- Parse frontmatter for: task, affects, provides
|
||||
- If no files found -> error to coordinator
|
||||
|
||||
### Phase 3: Goal-Backward Verification (via command)
|
||||
|
||||
```javascript
|
||||
// Delegate to verify command
|
||||
Read("commands/verify.md")
|
||||
// Execute goal-backward verification:
|
||||
// 1. For each task's convergence criteria: check criteria, files, verification command
|
||||
// 2. Score each task: pass / partial / fail
|
||||
// 3. Compile gap list
|
||||
//
|
||||
// Produces: verificationResults (structured data)
|
||||
```
|
||||
**Objective**: Execute convergence criteria checks.
|
||||
|
||||
Delegate to `commands/verify.md`:
|
||||
|
||||
| Step | Action |
|
||||
|------|--------|
|
||||
| 1 | For each task's convergence criteria |
|
||||
| 2 | Check criteria type: files, command, pattern |
|
||||
| 3 | Execute appropriate verification method |
|
||||
| 4 | Score each task: pass / partial / fail |
|
||||
| 5 | Compile gap list for failed items |
|
||||
|
||||
**Verification strategy selection**:
|
||||
|
||||
| Criteria Type | Method |
|
||||
|---------------|--------|
|
||||
| File existence | `test -f <path>` |
|
||||
| Command execution | Run specified command, check exit code |
|
||||
| Pattern match | Grep for pattern in specified files |
|
||||
| Semantic check | Optional: Gemini CLI for deep analysis |
|
||||
|
||||
**Produces**: verificationResults (structured data)
|
||||
|
||||
**Command**: [commands/verify.md](commands/verify.md)
|
||||
|
||||
### Phase 4: Compile Results
|
||||
|
||||
```javascript
|
||||
// Aggregate pass/fail per task
|
||||
const results = {
|
||||
totalTasks: tasks.length,
|
||||
passed: 0,
|
||||
partial: 0,
|
||||
failed: 0,
|
||||
gaps: []
|
||||
}
|
||||
**Objective**: Aggregate pass/fail and generate verification.md.
|
||||
|
||||
for (const taskResult of verificationResults) {
|
||||
if (taskResult.status === 'pass') {
|
||||
results.passed++
|
||||
} else if (taskResult.status === 'partial') {
|
||||
results.partial++
|
||||
results.gaps.push(...taskResult.gaps)
|
||||
} else {
|
||||
results.failed++
|
||||
results.gaps.push(...taskResult.gaps)
|
||||
}
|
||||
}
|
||||
**Result aggregation**:
|
||||
|
||||
const overallStatus = results.gaps.length === 0 ? 'passed' : 'gaps_found'
|
||||
```
|
||||
| Metric | Source | Threshold |
|
||||
|--------|--------|-----------|
|
||||
| Pass rate | Task results | >= 100% for passed |
|
||||
| Gaps count | Failed criteria | 0 for passed |
|
||||
|
||||
### Phase 5: Write verification.md + Report
|
||||
**Compile steps**:
|
||||
|
||||
```javascript
|
||||
const verificationPath = `${sessionFolder}/phase-${phaseNumber}/verification.md`
|
||||
1. **Aggregate results per task**:
|
||||
- Count passed, partial, failed
|
||||
- Collect all gaps from partial/failed tasks
|
||||
|
||||
Write(verificationPath, `---
|
||||
phase: ${phaseNumber}
|
||||
status: ${overallStatus}
|
||||
tasks_checked: ${results.totalTasks}
|
||||
tasks_passed: ${results.passed}
|
||||
2. **Determine overall status**:
|
||||
- `passed` if gaps.length === 0
|
||||
- `gaps_found` otherwise
|
||||
|
||||
3. **Write verification.md**:
|
||||
- YAML frontmatter with status, counts, gaps
|
||||
- Summary section
|
||||
- Task results section
|
||||
- Gaps section (if any)
|
||||
|
||||
**Verification.md structure**:
|
||||
```yaml
|
||||
---
|
||||
phase: <N>
|
||||
status: passed | gaps_found
|
||||
tasks_checked: <count>
|
||||
tasks_passed: <count>
|
||||
gaps:
|
||||
${results.gaps.map(g => ` - task: "${g.task}"
|
||||
type: "${g.type}"
|
||||
item: "${g.item}"
|
||||
expected: "${g.expected}"
|
||||
actual: "${g.actual}"`).join('\n')}
|
||||
- task: "<task-id>"
|
||||
type: "<criteria-type>"
|
||||
item: "<description>"
|
||||
expected: "<expected-value>"
|
||||
actual: "<actual-value>"
|
||||
---
|
||||
|
||||
# Phase ${phaseNumber} Verification
|
||||
# Phase <N> Verification
|
||||
|
||||
## Summary
|
||||
|
||||
- **Status**: ${overallStatus}
|
||||
- **Tasks Checked**: ${results.totalTasks}
|
||||
- **Passed**: ${results.passed}
|
||||
- **Partial**: ${results.partial}
|
||||
- **Failed**: ${results.failed}
|
||||
- **Total Gaps**: ${results.gaps.length}
|
||||
- Status: <status>
|
||||
- Tasks Checked: <count>
|
||||
- Passed: <count>
|
||||
- Total Gaps: <count>
|
||||
|
||||
## Task Results
|
||||
### TASK-ID: Title - STATUS
|
||||
- [x] (type) description
|
||||
- [ ] (type) description
|
||||
|
||||
${verificationResults.map(r => `### ${r.task}: ${r.title} — ${r.status.toUpperCase()}
|
||||
${r.details.map(d => `- [${d.passed ? 'x' : ' '}] (${d.type}) ${d.description}`).join('\n')}`).join('\n\n')}
|
||||
## Gaps (if any)
|
||||
### Gap 1: Task - Type
|
||||
- Expected: ...
|
||||
- Actual: ...
|
||||
```
|
||||
|
||||
${results.gaps.length > 0 ? `## Gaps
|
||||
### Phase 5: Report to Coordinator
|
||||
|
||||
${results.gaps.map((g, i) => `### Gap ${i + 1}: ${g.task} - ${g.type}
|
||||
- **Expected**: ${g.expected}
|
||||
- **Actual**: ${g.actual}
|
||||
- **Item**: ${g.item}`).join('\n\n')}` : '## No Gaps Found'}
|
||||
`)
|
||||
> See SKILL.md Shared Infrastructure -> Worker Phase 5: Report
|
||||
|
||||
const messageType = overallStatus === 'passed' ? 'verify_passed' : 'gaps_found'
|
||||
|
||||
mcp__ccw-tools__team_msg({
|
||||
operation: "log", team: "roadmap-dev",
|
||||
from: "verifier", to: "coordinator",
|
||||
type: messageType,
|
||||
summary: `[verifier] Phase ${phaseNumber} verification: ${overallStatus}. ${results.passed}/${results.totalTasks} tasks passed. ${results.gaps.length} gaps.`,
|
||||
ref: verificationPath
|
||||
})
|
||||
Standard report flow: team_msg log -> SendMessage with `[verifier]` prefix -> TaskUpdate completed -> Loop to Phase 1 for next task.
|
||||
|
||||
**Report message**:
|
||||
```
|
||||
SendMessage({
|
||||
to: "coordinator",
|
||||
message: `[verifier] Phase ${phaseNumber} verification complete.
|
||||
- Status: ${overallStatus}
|
||||
- Tasks: ${results.passed}/${results.totalTasks} passed
|
||||
- Gaps: ${results.gaps.length}
|
||||
${results.gaps.length > 0 ? `\nGap summary:\n${results.gaps.map(g => `- ${g.task}, ${g.type}: ${g.item}`).join('\n')}` : ''}
|
||||
message: "[verifier] Phase <N> verification complete.
|
||||
- Status: <status>
|
||||
- Tasks: <passed>/<total> passed
|
||||
- Gaps: <gap-count>
|
||||
|
||||
Verification written to: ${verificationPath}`
|
||||
Verification written to: <verification-path>"
|
||||
})
|
||||
|
||||
TaskUpdate({ taskId: verifyTask.id, status: "completed" })
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Scenario | Resolution |
|
||||
|----------|------------|
|
||||
| No VERIFY-* tasks available | Idle, wait for coordinator assignment |
|
||||
| Context/Plan file not found | Notify coordinator, request location |
|
||||
| Command file not found | Fall back to inline execution |
|
||||
| No task JSON files found | Error to coordinator -- planner may have failed |
|
||||
| No summary files found | Error to coordinator -- executor may have failed |
|
||||
| File referenced in task missing | Record as gap (file type) |
|
||||
| Bash command fails during check | Record as gap with error message |
|
||||
| Verification command fails | Record as gap with exit code |
|
||||
| Gemini CLI fails | Fallback to direct checks, skip semantic analysis |
|
||||
| Critical issue beyond scope | SendMessage fix_required to coordinator |
|
||||
| Unexpected error | Log error via team_msg, report to coordinator |
|
||||
|
||||
Reference in New Issue
Block a user