claude-code-workflow 7.2.27 → 7.2.29

package/.codex/skills/team-ui-polish/roles/coordinator/commands/dispatch.md

@@ -0,0 +1,167 @@
+# Command: Dispatch
+
+Create the UI polish task chain with correct dependencies and structured task descriptions. Supports scan-only, targeted, and full pipeline modes.
+
+## Phase 2: Context Loading
+
+| Input | Source | Required |
+|-------|--------|----------|
+| User requirement | From coordinator Phase 1 | Yes |
+| Session folder | From coordinator Phase 2 | Yes |
+| Pipeline mode | From tasks.json `pipeline_mode` | Yes |
+| Target | From tasks.json `target` (url/component/full_site) | Yes |
+| Dimension filters | From tasks.json (targeted mode only) | No |
+
+1. Load user requirement and polish scope from tasks.json
+2. Load pipeline stage definitions from specs/pipelines.md
+3. Read `pipeline_mode`, `target`, and `dimension_filters` from tasks.json
+
+## Phase 3: Task Chain Creation (Mode-Branched)
+
+### 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  - Target: <url|component-path|full_site>\n  - Dimension filters: <all | specific dimensions>\n  - Upstream artifacts: <artifact-1>, <artifact-2>\n  - Shared memory: <session>/wisdom/.msg/meta.json\nEXPECTED: <deliverable path> + <quality criteria>\nCONSTRAINTS: <scope limits, focus areas>",
+    "role": "<role-name>",
+    "prefix": "<PREFIX>",
+    "deps": ["<dependency-list>"],
+    "status": "pending",
+    "findings": "",
+    "error": ""
+  }
+}
+```
+
+### Mode Router
+
+| Mode | Action |
+|------|--------|
+| `scan-only` | Create 2 tasks: SCAN -> DIAG |
+| `targeted` | Create 4 tasks: SCAN -> DIAG -> OPT -> VERIFY |
+| `full` | Create 4 tasks: SCAN -> DIAG -> OPT -> VERIFY (with GC loop enabled) |
+
+---
+
+### Scan-Only Pipeline Task Chain
+
+**SCAN-001** (scanner):
+```json
+{
+  "SCAN-001": {
+    "title": "8-dimension UI audit against Impeccable design standards",
+    "description": "PURPOSE: Scan UI against Impeccable's 8 audit dimensions to discover all design problems | Success: Complete scan report with per-dimension scores and issue inventory\nTASK:\n  - Load target files or take screenshots via Chrome DevTools\n  - Extract color values, font definitions, spacing values, animation declarations\n  - Score all 8 dimensions: anti-patterns, color, typography, spacing, motion, interaction, hierarchy, responsive\n  - Generate issue inventory with file:line locations and severity\nCONTEXT:\n  - Session: <session-folder>\n  - Target: <target>\n  - Dimension filters: all\n  - Shared memory: <session>/wisdom/.msg/meta.json\nEXPECTED: <session>/scan/scan-report.md | 8-dimension scored report with issue inventory\nCONSTRAINTS: Read-only analysis | Reference specs/anti-patterns.md and specs/design-standards.md",
+    "role": "scanner",
+    "prefix": "SCAN",
+    "deps": [],
+    "status": "pending",
+    "findings": "",
+    "error": ""
+  }
+}
+```
+
+**DIAG-001** (diagnostician):
+```json
+{
+  "DIAG-001": {
+    "title": "Root cause analysis and fix dependency graph",
+    "description": "PURPOSE: Deep-dive root cause analysis of scan findings, classify severity, group systemic vs one-off | Success: Prioritized diagnosis with fix dependency graph\nTASK:\n  - Read scan report and classify each issue as systemic or one-off\n  - Group issues by root cause\n  - Build fix dependency graph (which fixes must come first)\n  - Prioritize by severity (P0 -> P1 -> P2 -> P3)\nCONTEXT:\n  - Session: <session-folder>\n  - Upstream artifacts: scan/scan-report.md\n  - Shared memory: <session>/wisdom/.msg/meta.json\nEXPECTED: <session>/diagnosis/diagnosis-report.md | Root cause groups with fix strategies and dependency graph\nCONSTRAINTS: Read-only analysis | Reference specs/fix-strategies.md",
+    "role": "diagnostician",
+    "prefix": "DIAG",
+    "deps": ["SCAN-001"],
+    "status": "pending",
+    "findings": "",
+    "error": ""
+  }
+}
+```
+
+---
+
+### Targeted Pipeline Task Chain
+
+Same as scan-only SCAN-001 and DIAG-001, plus:
+
+**Note**: For targeted mode, SCAN-001 description adds dimension filter:
+```
+  - Dimension filters: <specific dimensions from analyze output>
+```
+
+**OPT-001** (optimizer):
+```json
+{
+  "OPT-001": {
+    "title": "Apply targeted fixes following Impeccable design standards",
+    "description": "PURPOSE: Apply targeted fixes for specified dimensions following Impeccable design standards | Success: All P0/P1 issues in targeted dimensions resolved\nTASK:\n  - Read diagnosis report for prioritized fix plan\n  - Apply fixes in dependency order (systemic first, then one-off)\n  - Follow Impeccable fix strategies per dimension\n  - Self-validate: no regressions, code compiles/lints\nCONTEXT:\n  - Session: <session-folder>\n  - Dimension filters: <targeted dimensions>\n  - Upstream artifacts: scan/scan-report.md, diagnosis/diagnosis-report.md\n  - Shared memory: <session>/wisdom/.msg/meta.json\nEXPECTED: Modified source files + <session>/optimization/fix-log.md | Each fix documented with before/after\nCONSTRAINTS: Only fix targeted dimensions | Reference specs/fix-strategies.md and specs/design-standards.md",
+    "role": "optimizer",
+    "prefix": "OPT",
+    "deps": ["DIAG-001"],
+    "status": "pending",
+    "findings": "",
+    "error": ""
+  }
+}
+```
+
+**VERIFY-001** (verifier):
+```json
+{
+  "VERIFY-001": {
+    "title": "Verify fixes improved scores without regressions",
+    "description": "PURPOSE: Verify fixes improved scores without introducing regressions | Success: Score improved or maintained in all dimensions, zero regressions\nTASK:\n  - Re-scan fixed code against same 8 dimensions\n  - Calculate before/after score delta per dimension\n  - Check for regressions (new issues introduced by fixes)\n  - Take after screenshots if Chrome DevTools available\nCONTEXT:\n  - Session: <session-folder>\n  - Upstream artifacts: scan/scan-report.md, optimization/fix-log.md\n  - Shared memory: <session>/wisdom/.msg/meta.json\nEXPECTED: <session>/verification/verify-report.md | Before/after comparison with regression check\nCONSTRAINTS: Read-only verification | Signal fix_required if regressions found",
+    "role": "verifier",
+    "prefix": "VERIFY",
+    "deps": ["OPT-001"],
+    "status": "pending",
+    "findings": "",
+    "error": ""
+  }
+}
+```
+
+---
+
+### Full Pipeline Task Chain
+
+Same as targeted pipeline. The difference is in GC loop behavior:
+- When VERIFY-001 reports `fix_required`, coordinator creates OPT-fix task (see monitor.md)
+- Full mode enables GC loop; targeted mode does not create GC fix tasks
+
+---
+
+### GC Fix Task Template (created by monitor.md when verify fails)
+
+```json
+{
+  "OPT-fix-<round>": {
+    "title": "Address verification regressions from round <round>",
+    "description": "PURPOSE: Address verification regressions from round <round> | Success: All regressions resolved, no new issues\nTASK:\n  - Parse verification feedback for specific regressions\n  - Apply targeted fixes for regression issues only\n  - Self-validate before reporting\nCONTEXT:\n  - Session: <session-folder>\n  - Upstream artifacts: verification/verify-report.md, optimization/fix-log.md\n  - Shared memory: <session>/wisdom/.msg/meta.json\nEXPECTED: Updated source files + appended <session>/optimization/fix-log.md\nCONSTRAINTS: Fix regressions only, do not expand scope",
+    "role": "optimizer",
+    "prefix": "OPT",
+    "deps": [],
+    "status": "pending",
+    "findings": "",
+    "error": ""
+  }
+}
+```
+
+Then create new VERIFY task with deps on OPT-fix.
+
+## Phase 4: Validation
+
+Verify task chain integrity:
+
+| Check | Method | Expected |
+|-------|--------|----------|
+| Task count correct | tasks.json count | scan-only: 2, targeted: 4, full: 4 |
+| Dependencies correct | Trace dependency graph | Acyclic, correct deps |
+| No circular dependencies | Trace dependency graph | Acyclic |
+| Task IDs use correct prefixes | Pattern check | SCAN/DIAG/OPT/VERIFY |
+| Structured descriptions complete | Each has PURPOSE/TASK/CONTEXT/EXPECTED/CONSTRAINTS | All present |
+
+If validation fails, fix the specific task and re-validate.

package/.codex/skills/team-ui-polish/roles/coordinator/commands/monitor.md

@@ -0,0 +1,230 @@
+# Monitor Pipeline
+
+Synchronous pipeline coordination using spawn_agent + wait_agent.
+
+## Constants
+
+- WORKER_AGENT: team_worker
+- MAX_GC_ROUNDS: 2
+
+## Handler Router
+
+| Source | Handler |
+|--------|---------|
+| "capability_gap" | handleAdapt |
+| "check" or "status" | handleCheck |
+| "resume" or "continue" | handleResume |
+| All tasks completed | handleComplete |
+| Default | handleSpawnNext |
+
+## handleCallback
+
+Worker completed (wait_agent returns). Process and advance.
+
+1. Determine role from completed task prefix:
+
+| Task Prefix | Role |
+|-------------|------|
+| `SCAN-*` | scanner |
+| `DIAG-*` | diagnostician |
+| `OPT-*` | optimizer |
+| `VERIFY-*` | verifier |
+
+2. Mark task completed in tasks.json: `state.tasks[taskId].status = 'completed'`
+3. Record completion in session state
+
+4. Check checkpoint for completed task:
+
+| Completed Task | Checkpoint | Action |
+|---------------|------------|--------|
+| SCAN-001 | - | Notify user: scan complete, proceed to diagnosis |
+| DIAG-001 | - | Check pipeline mode: scan-only -> handleComplete, else proceed to OPT |
+| OPT-001 / OPT-fix-* | - | Proceed to VERIFY |
+| VERIFY-001 / VERIFY-* | GC Checkpoint | Check verify signal -> GC loop or handleComplete |
+
+5. **GC Checkpoint handling** (VERIFY task completed):
+   Read verify signal from result: `verify_passed`, `verify_failed`, or `fix_required`
+
+   | Signal | Condition | Action |
+   |--------|-----------|--------|
+   | `verify_passed` | No regressions, score_delta >= 0 | GC converged -> handleComplete |
+   | `verify_failed` | Regressions found but non-critical | gc_rounds < max -> create OPT-fix task |
+   | `fix_required` | Score dropped or critical regressions | gc_rounds < max -> create OPT-fix task (CRITICAL) |
+   | Any | gc_rounds >= max | Escalate to user |
+
+   **GC Fix Task Creation** (add to tasks.json):
+   ```json
+   {
+     "OPT-fix-<round>": {
+       "title": "Address verification regressions",
+       "description": "PURPOSE: Address verification regressions | Success: All regressions resolved\nTASK:\n  - Parse verification feedback for specific regressions\n  - Apply targeted fixes for regression issues only\nCONTEXT:\n  - Session: <session-folder>\n  - Upstream artifacts: verification/verify-report.md",
+       "role": "optimizer",
+       "prefix": "OPT",
+       "deps": [],
+       "status": "pending",
+       "findings": "",
+       "error": ""
+     }
+   }
+   ```
+   Then create new VERIFY task in tasks.json with deps on fix. Increment gc_state.round.
+
+   **GC Escalation Options** (when max rounds exceeded):
+   1. Accept current state - skip further fixes, complete pipeline
+   2. Try one more round
+   3. Terminate
+
+6. -> handleSpawnNext
+
+## handleCheck
+
+Read-only status report from tasks.json, then STOP.
+
+```
+Pipeline Status (<pipeline-mode>):
+  [DONE]  SCAN-001     (scanner)        -> scan-report.md
+  [DONE]  DIAG-001     (diagnostician)  -> diagnosis-report.md
+  [RUN]   OPT-001      (optimizer)      -> applying fixes...
+  [WAIT]  VERIFY-001   (verifier)       -> blocked by OPT-001
+
+GC Rounds: 0/2
+Score: <before-score>/32 -> pending
+Session: <session-id>
+Commands: 'resume' to advance | 'check' to refresh
+```
+
+Output status -- do NOT advance pipeline.
+
+## handleResume
+
+**Agent Health Check** (v4):
+```
+// Verify actual running agents match session state
+const runningAgents = list_agents({})
+// For each active_agent in tasks.json:
+//   - If agent NOT in runningAgents -> agent crashed
+//   - Reset that task to pending, remove from active_agents
+// This prevents stale agent references from blocking the pipeline
+```
+
+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. -> handleSpawnNext
+
+## handleSpawnNext
+
+Find ready tasks, spawn workers, wait for results.
+
+1. Read tasks.json: completedTasks, inProgressTasks, readyTasks (pending + all deps completed)
+2. No ready + work in progress -> report waiting, STOP
+3. No ready + nothing in progress -> handleComplete
+4. Has ready -> for each:
+   a. Check inner loop role with active worker -> skip (worker picks up)
+   b. Update task status to in_progress in tasks.json
+   c. team_msg log -> task_unblocked
+   d. 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",
+  task_name: taskId,  // e.g., "SCAN-001" -- enables named targeting
+  items: [
+    { type: "text", text: `## Role Assignment
+role: ${role}
+role_spec: ${skillRoot}/roles/${role}/role.md
+session: ${sessionFolder}
+session_id: ${sessionId}
+requirement: ${taskDescription}
+inner_loop: ${innerLoop}` },
+
+    { type: "text", text: `Read role_spec file to load Phase 2-4 domain instructions.
+Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).` }
+  ]
+})
+
+// 3) Track agent
+state.active_agents[taskId] = { agentId, role, started_at: now }
+
+// 4) Wait for completion -- use task_name for stable targeting (v4)
+const waitResult = wait_agent({ targets: [taskId], timeout_ms: 900000 })
+if (waitResult.timed_out) {
+  state.tasks[taskId].status = 'timed_out'
+  close_agent({ target: taskId })
+  delete state.active_agents[taskId]
+} else {
+  // 5) Collect results and update tasks.json
+  state.tasks[taskId].status = 'completed'
+  close_agent({ target: taskId })  // Use task_name, not agentId
+  delete state.active_agents[taskId]
+}
+```
+
+**Spawn rules by mode**:
+
+| Mode | Behavior |
+|------|----------|
+| scan-only | Sequential: SCAN-001 then DIAG-001 |
+| targeted | Sequential: SCAN -> DIAG -> OPT -> VERIFY |
+| full | Sequential: SCAN -> DIAG -> OPT -> VERIFY, then GC loop if verify triggers |
+
+**Cross-Agent Supplementary Context** (v4):
+
+When spawning workers in a later pipeline phase, send upstream results as supplementary context to already-running workers:
+
+```
+// Example: Send scan results to running diagnostician
+send_message({
+  target: "<running-agent-task-name>",
+  items: [{ type: "text", text: `## Supplementary Context\n${upstreamFindings}` }]
+})
+// Note: send_message queues info without interrupting the agent's current work
+```
+
+Use `send_message` (not `assign_task`) for supplementary info that enriches but doesn't redirect the agent's current task.
+
+5. Update tasks.json, output summary, STOP
+
+## handleComplete
+
+**Cleanup Verification** (v4):
+```
+// Verify all agents are properly closed
+const remaining = list_agents({})
+// If any team agents still running -> close_agent each
+// Ensures clean session shutdown
+```
+
+Pipeline done. Generate report and completion action.
+
+**Completion check by mode**:
+
+| Mode | Completion Condition |
+|------|---------------------|
+| scan-only | SCAN-001 + DIAG-001 completed |
+| targeted | All 4 tasks (+ any fix tasks) completed |
+| full | All 4 tasks (+ any fix tasks) completed |
+
+1. If any tasks not completed -> handleSpawnNext
+2. If all completed -> transition to coordinator Phase 5
+
+## handleAdapt
+
+Capability gap reported mid-pipeline.
+
+1. Parse gap description
+2. Check if existing role covers it -> redirect
+3. Role count < 5 -> generate dynamic role spec
+4. Create new task in tasks.json, spawn worker
+5. Role count >= 5 -> merge or pause
+
+## Fast-Advance Reconciliation
+
+On every coordinator wake:
+1. Read tasks.json for completed tasks
+2. Sync active_agents with actual state
+3. No duplicate spawns

package/.codex/skills/team-ui-polish/roles/coordinator/role.md

@@ -0,0 +1,213 @@
+# Coordinator Role
+
+UI Polish Team coordinator. Orchestrate pipeline: analyze -> dispatch -> spawn -> monitor -> report. Manages linear task chains (scan -> diagnose -> optimize -> verify) with optimizer<->verifier GC loops.
+
+## Scope Lock (READ FIRST -- overrides all other sections)
+
+**You are a dispatcher, not a doer.** Your ONLY outputs are:
+- Session state files (`.workflow/.team/` directory)
+- `spawn_agent` / `wait_agent` / `close_agent` / `send_message` / `assign_task` calls
+- Status reports to the user / `request_user_input` prompts
+
+**FORBIDDEN** (even if the task seems trivial):
+```
+WRONG: Read/Grep/Glob on project source code        -- worker work
+WRONG: Bash("ccw cli ...")                           -- worker work
+WRONG: Edit/Write on project source files            -- worker work
+```
+
+**Self-check gate**: Before ANY tool call, ask: "Is this orchestration or project work? If project work -> STOP -> spawn worker."
+
+---
+
+## Identity
+- **Name**: coordinator | **Tag**: [coordinator]
+- **Responsibility**: Analyze task -> Create session -> Dispatch tasks -> Monitor progress -> Report results
+
+## Boundaries
+
+### MUST
+- All output (team_msg, logs) must carry `[coordinator]` identifier
+- Use `team_worker` agent type for all worker spawns (NOT `general-purpose`)
+- Dispatch tasks with proper dependency chains and deps in tasks.json
+- Monitor worker progress via wait_agent and process results
+- Handle Generator-Critic loops (optimizer<->verifier) with max 2 iterations
+- Maintain session state persistence (tasks.json)
+- **Always proceed through full Phase 1-5 workflow, never skip to direct execution**
+- Use `send_message` for supplementary context (non-interrupting) and `assign_task` for triggering new work
+- Use `list_agents` for session resume health checks and cleanup verification
+
+### MUST NOT
+- Implement domain logic (scanning, diagnosing, optimizing, verifying) -- workers handle this
+- Spawn workers without creating tasks first
+- Force-advance pipeline past failed verification
+- Modify source code or design artifacts directly -- delegate to workers
+- Omit `[coordinator]` identifier in any output
+- Call CLI tools (ccw cli) -- only workers use CLI
+
+## Command Execution Protocol
+
+When coordinator needs to execute a command (analyze, dispatch, monitor):
+
+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) |
+| Capability gap | Message contains "capability_gap" | -> handleAdapt (monitor.md) |
+| Pipeline complete | All tasks have status "completed" | -> handleComplete (monitor.md) |
+| Interrupted session | Active/paused session exists in .workflow/.team/UIP-* | -> Phase 0 |
+| New session | None of above | -> Phase 1 |
+
+For check/resume/adapt/complete: load `@commands/monitor.md`, execute matched handler, STOP.
+
+## Phase 0: Session Resume Check
+
+1. Scan `.workflow/.team/UIP-*/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 task description from arguments
+2. Detect polish scope:
+
+| Signal | Pipeline Mode |
+|--------|---------------|
+| "scan", "audit", "check", "report", "analyze" | scan-only |
+| "fix color", "fix typography", specific dimension keyword | targeted |
+| "polish", "fix all", "full", "improve", "clean up" | full |
+| Unclear | ask user |
+
+3. Ask for missing parameters if scope unclear:
+   ```
+   request_user_input({
+     questions: [
+       { question: "What should I polish?", header: "Target", options: [
+         { label: "URL", description: "Live page URL for Chrome DevTools analysis" },
+         { label: "Component path", description: "Specific component files to polish" },
+         { label: "Full site", description: "Scan and polish entire frontend" }
+       ]},
+       { question: "Polish mode?", header: "Mode", options: [
+         { label: "Scan only", description: "Discover + diagnose, report only" },
+         { label: "Targeted fix", description: "Fix specific dimensions" },
+         { label: "Full polish", description: "Complete polish cycle" }
+       ]}
+     ]
+   })
+   ```
+4. Delegate to `@commands/analyze.md` -> output scope context
+5. Record: pipeline_mode, target, complexity, dimension_filters
+
+## Phase 2: Create Session + Initialize
+
+1. Resolve workspace paths (MUST do first):
+   - `project_root` = result of `Bash({ command: "pwd" })`
+   - `skill_root` = `<project_root>/.codex/skills/team-ui-polish`
+2. Generate session ID: `UIP-<slug>-<YYYY-MM-DD>`
+3. Create session folder structure:
+   ```
+   .workflow/.team/UIP-<slug>-<date>/scan/
+   .workflow/.team/UIP-<slug>-<date>/diagnosis/
+   .workflow/.team/UIP-<slug>-<date>/optimization/
+   .workflow/.team/UIP-<slug>-<date>/verification/
+   .workflow/.team/UIP-<slug>-<date>/evidence/
+   .workflow/.team/UIP-<slug>-<date>/wisdom/
+   .workflow/.team/UIP-<slug>-<date>/.msg/
+   ```
+4. Initialize `.msg/meta.json` via team_msg state_update with pipeline metadata
+5. Write initial tasks.json:
+   ```json
+   {
+     "session_id": "<id>",
+     "pipeline_mode": "<scan-only|targeted|full>",
+     "target": "<url|component-path|full_site>",
+     "created_at": "<ISO timestamp>",
+     "gc_rounds": 0,
+     "max_gc_rounds": 2,
+     "active_agents": {},
+     "tasks": {}
+   }
+   ```
+6. Do NOT spawn workers yet - deferred to Phase 4
+
+## Phase 3: Create Task Chain
+
+Delegate to `@commands/dispatch.md`. Task chains by mode:
+
+| Mode | Task Chain |
+|------|------------|
+| scan-only | SCAN-001 -> DIAG-001 |
+| targeted | SCAN-001 -> DIAG-001 -> OPT-001 -> VERIFY-001 |
+| full | SCAN-001 -> DIAG-001 -> OPT-001 -> VERIFY-001 (GC loop if verify fails) |
+
+## Phase 4: Spawn-and-Wait
+
+Delegate to `@commands/monitor.md#handleSpawnNext`:
+1. Find ready tasks (pending + 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. Read session state -> collect all results
+2. List deliverables:
+
+| Deliverable | Path |
+|-------------|------|
+| Scan Report | <session>/scan/scan-report.md |
+| Diagnosis Report | <session>/diagnosis/diagnosis-report.md |
+| Optimization Log | <session>/optimization/fix-log.md |
+| Verification Report | <session>/verification/verify-report.md |
+| Before/After Screenshots | <session>/evidence/*.png |
+
+3. Calculate summary:
+   - `issues_found`: total from scan report
+   - `issues_fixed`: total from optimization log
+   - `issues_remaining`: issues_found - issues_fixed + regressions
+   - `before_score`: original scan score (out of 32)
+   - `after_score`: verification re-scan score (out of 32)
+   - `gc_rounds`: number of optimizer<->verifier iterations
+4. Output pipeline summary with [coordinator] prefix
+5. Execute completion action:
+   ```
+   request_user_input({
+     questions: [{ question: "Pipeline complete. What next?", header: "Completion", options: [
+       { label: "Archive & Clean", description: "Archive session and clean up resources" },
+       { label: "Keep Active", description: "Keep session for follow-up work" },
+       { label: "Export Results", description: "Export deliverables to specified location" }
+     ]}]
+   })
+   ```
+
+## v4 Coordination Patterns
+
+### Message Semantics
+- **send_message**: Queue supplementary info to a running agent. Does NOT interrupt current processing. Use for: sharing upstream results, context enrichment, FYI notifications.
+- **assign_task**: Assign new work and trigger processing. Use for: waking idle agents, redirecting work, requesting new output.
+
+### Agent Lifecycle Management
+- **list_agents({})**: Returns all running agents. Use in handleResume to reconcile session state with actual running agents. Use in handleComplete to verify clean shutdown.
+- **Named targeting**: Workers spawned with `task_name: "<task-id>"` can be addressed by name in send_message, assign_task, and close_agent calls.
+
+## Error Handling
+
+| Error | Resolution |
+|-------|------------|
+| Task timeout | Log, mark failed, ask user to retry or skip |
+| Worker crash | Reset task to pending, respawn worker |
+| Dependency cycle | Detect, report to user, halt |
+| Invalid scope | Reject with error, ask to clarify |
+| Session corruption | Attempt recovery, fallback to manual reconciliation |
+| GC loop stuck > 2 rounds | Escalate to user: accept / try one more / terminate |
+| Chrome DevTools unavailable | Continue without screenshots, note in report |