pi-crew 0.1.46 → 0.1.51

package/CHANGELOG.md

@@ -2,6 +2,121 @@
 
 ## Unreleased
 
+## 0.1.51
+
+### Fixed
+
+- **Stale foreground spinner** — Working message/spinner now always clears when foreground run completes, even if session generation changed during the run.
+- **Completed-run widget grace period (8s)** — Runs that just completed stay visible in the widget for 8 seconds so users can see results before the widget hides.
+
+## 0.1.50
+
+### Fixed
+
+- **Parallel execution** — Raised default concurrency (implementation 2→4, review 2→3, research 2→3). Fixed `defaultWorkflowConcurrency()` routing bug where review/default both returned the implementation value.
+- **Planner prompt** — Added explicit "MAXIMIZE PARALLELISM" instruction with examples, so planner models produce parallel phases instead of sequential.
+- **20 review findings** — 6 CRITICAL (optional chaining crash, env leak, path redaction, RPC validation, hook JSON safety, temp dir security), 6 HIGH (unsafe casts, busy-wait CPU, timestamp merge guard, prompt injection delimiter, binary validation), 5 MEDIUM, 3 LOW.
+- **Widget flicker** — Pinned preloaded manifests to widget component model to prevent manifestCache TTL race. Scoped snapshotCache invalidation to specific run instead of clearing all.
+- **Delegation policy** — Rewritten as mandatory decision table with concrete thresholds (>3 files read or >2 files edit = must delegate). Injected into every session via system prompt.
+- **ignoreMethod option** — New config to write ignore entries to `.git/info/exclude` instead of `.gitignore` (Closes #2).
+
+## 0.1.49
+
+### Added
+
+- **Caveman output contracts** — Role-based output validation framework with `output-validator.ts`: regex-based format checking for explorer, executor, reviewer, verifier, security-reviewer roles. Non-blocking: validation failures emit `task.output_validation` events + set `needs_attention` but do NOT fail the task.
+- **Prose compressor** — `prose-compressor.ts` compresses verbose worker output for token-sensitive contexts (role-aware compression levels).
+- **Sensitive paths** — Word-boundary-aware token matching in `sensitive-paths.ts` prevents false positives (e.g. `secretary.ts` no longer flagged as `secret`).
+- **Symlink-safe I/O** — Artifact and shared output paths reject traversal attempts and symlinked root escapes.
+- **Output contract eval harness** — 19 unit tests covering three-arm evaluation (contract vs terse vs baseline), format compliance, token savings, regex safety (no `/g` lastIndex state leak).
+
+### Changed
+
+- **Delegation policy rewritten** — Replaced advisory "you should consider" text with a mandatory decision table: concrete thresholds (>3 files read OR >2 files edit = MUST delegate), explicit YES/NO cases per task type, conflict-safe task splitting rules. Injected into every session via `before_agent_start` hook.
+- **Powerbar dedup** — `powerbar-publisher.ts` now skips `powerbar:update` emit when segment data is unchanged (inspired by pi-powerbar's `segmentEquals` pattern). Combined with existing 200ms coalescing for minimal unnecessary renders.
+- **UI responsiveness** — `task-runner.ts` now emits `streamBridge` event immediately after `task.started`, giving the widget agent status within ~100ms instead of 2-5s (child process startup delay).
+- **"spawning…" indicator** — Widget shows "spawning…" for agents < 5 seconds old with no tool activity, distinguishing from "thinking…" for long-running agents.
+
+### Fixed
+
+- **H1: MCP proxy fallback** — `mcp-proxy.ts` now falls back to `enableMcp: true` when `createMcpProxyTools()` returns empty, so child sessions self-discover MCP instead of losing all access.
+- **H2: parallel-utils throw undefined** — `mapConcurrent` now throws the actual error instead of `throw undefined`.
+- **H3: Semaphore over-release** — `release()` guard against `#current > 0` prevents over-release corruption.
+- **M1: IRC tool TOCTOU** — `irc-tool.ts` wraps `sendIrcMessage`/`broadcastIrcMessage` in try-catch.
+- **M2: submit-result ordering** — Builds response string before calling `onYield`, wrapped in try-catch.
+- **M3: Sensitive paths false positives** — Word-boundary-aware token matching replaces substring matching.
+- **M4: atomic-write sleepSync** — Added WARNING comment about blocking main thread.
+- **M7: URL regex trailing punctuation** — Precise regex excludes trailing punctuation from URL matches.
+- **L1: parent-guard comment** — Corrected misleading comment about `process.kill` on Windows.
+- **Yield handler DRY** — Extracted `extractYieldDataFromArgs` helper, `isObjectRecord`/`isStringRecord` type guards, safe `find()` pattern.
+- **Event-log-rotation TOCTOU** — `compactEventLog` re-reads file after initial read to merge concurrent appends; `readEvents` skips corrupt JSON lines.
+- **Ghost agent dedup** — Fixed duplicate agent records in `crew-agent-records` after crash recovery.
+
+### Research
+
+- `docs/research/AGENT-EXECUTION-ARCHITECTURE.md` — Detailed comparison of 3 execution modes (oh-my-pi in-process, pi-crew child-process, pi-crew live-session).
+- `docs/research/UI-RESPONSIVENESS-AUDIT.md` — Root cause analysis for 2-5s agent spawn visibility delay, 5 proposed fixes with priority matrix.
+- `docs/research/DEEP-RESEARCH-PI-POWERBAR.md` — Deep analysis of pi-powerbar architecture (producer/consumer pattern, rendering, settings, comparison with pi-crew's powerbar publisher).
+
+## 0.1.48
+
+### Added
+
+- **Yield-based completion contract** — Workers can call `submit_result` tool to return structured results; task-runner warns on workers that don't yield.
+- **Typed event channels** — `RunEventBus` supports 5 channels (`worker:progress`, `worker:lifecycle`, `worker:stream`, `run:state`, `ui:invalidate`) with `onChannel`/`onChannelForRun` subscriptions and auto-classification.
+- **Human-readable task names** — `generateTaskName()` produces AdjectiveNoun names (14,400 combinations); `displayName` field on `TeamTaskState`.
+- **SubprocessToolRegistry** — Extensible tool event handling with `register`/`extractAll`/`shouldTerminate` pattern; wired into event-stream-bridge.
+- **Event log rotation/compaction** — Auto-compacts event logs over 5MB/50k events, keeping last 1000 events; atomic file replacement.
+- **Incremental JSONL reader** — `readLinesSince`/`readJsonlSince` for seek-based file reading; wired into `readEventsCursor` with `fromByteOffset`.
+
+### Fixed
+
+- Fixed `readBlob`/`readBlobMetadata` crash on missing files — now returns `undefined`.
+- Fixed `readSseJson` crash on non-JSON SSE data — now skips malformed events.
+- Fixed wrong value `"long_running"` → `"active_long_running"` in agent-control.
+- Fixed `consecutiveFailures` type bypass — added to `CrewAgentProgress` interface.
+- Fixed `streamBridge.dispose()` memory leak — now in try/finally.
+- Fixed blob-store redundant ternary `typeof x === "string" ? x : x`.
+- Fixed team-runner non-null assertion on potentially empty array.
+- Fixed event-log silent error swallowing — now logs via `logInternalError`.
+- Fixed team-tool switch case indentation.
+- Removed dead code `expandIcon` in agent-management-overlay.
+
+### Changed
+
+- Moved 6 research .md files from repo root to `docs/research/`.
+- `discoverAgents`/`discoverSkills` silent catches now log via `logInternalError`.
+- `executeHook` accumulates non-blocking diagnostics instead of short-circuiting.
+- `CancellationToken.heartbeat` wired into `collectRuns` and `pruneFinishedRuns`.
+- `CapabilitySource` extended with `"git"` to match `ResourceSource`.
+
+## 0.1.47
+
+### Added
+
+- **Typed hook lifecycle** — 8 of 9 hooks wired: `before_run_start`, `before_task_start`, `task_result`, `before_cancel`, `before_forget`, `before_cleanup`, `before_publish`, `run_recovery`. Hooks are opt-in, blocking/non-blocking, with audit events.
+- **Event-first UI bus** — `RunEventBus` emits on every `appendEvent` call; dashboard, crew widget, sidebar, and snapshot cache subscribe for event-driven invalidation instead of polling.
+- **Shared scan cache** — `SharedScanCache` caches manifest reads and active-run entries with TTL, mtime/size invalidation, and LRU eviction.
+- **Capability inventory** — `buildCapabilityInventory()` enumerates teams, workflows, agents, and skills with stable `kind:name` IDs; supports policy disable and shadowing detection.
+- **Skills in capability inventory** — `discoverSkills()` reads SKILL.md frontmatter; skills appear with kind=`skill` and source=`package`/`project`.
+- **Mailbox kind-separated breakdown** — `RunUiMailbox` tracks `steerUnread`/`followUpUnread`/`responseUnread`/`messageUnread`; mailbox pane shows urgency indicators.
+- **Run recovery hook** — `applyRecoveryPlan` fires `run_recovery` hook; blocked recovery emits `crew.run.recovery_blocked` event.
+- **Synthetic tool cancellation evidence** — Cancelled in-flight tasks receive `tool`-level terminal evidence alongside `worker`-level.
+- **CancellationToken wired into production loops** — `collectRuns` and `pruneFinishedRuns` use `CancellationToken.heartbeat(stage)` for progress diagnostics.
+- **Blob artifact store** — SHA-256 content-addressed storage with metadata sidecars.
+- **Run event provenance** — Event metadata includes `parentEventId`, `attemptId`, `branchId`, `causationId`, `correlationId`.
+- **Control channel reservation** — `ControlReservation` before worker spawn with deterministic `controllerId`.
+- **Release smoke test** — `npm run smoke:release` automates tarball install + version consistency check.
+- **Width-safety tests** — Crew widget rendering verified at widths 1/40/200/empty/multiple.
+
+### Changed
+
+- `handleCancel`, `handleForget`, `handleCleanup`, `handlePrune`, `handleExport` converted to async for hook execution.
+- `before_cancel`/`before_forget`/`before_cleanup` hooks can block their respective operations.
+- `before_publish` hook fires before run export.
+- `task_result` hook fires before `task.completed`/`task.failed` events.
+- Dashboard, widget, and sidebar auto-invalidate on `RunEventBus` events.
+
 ## 0.1.45
 
 ### Added

package/agents/analyst.md

@@ -1,11 +1,11 @@
----
-name: analyst
-description: Analyze requirements, ambiguity, and hidden constraints
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls
----
-
-You are a requirements analyst. Identify what is known, unknown, risky, ambiguous, or underspecified. Produce clarifying assumptions and acceptance criteria.
+---
+name: analyst
+description: Analyze requirements, ambiguity, and hidden constraints
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls
+---
+
+You are a requirements analyst. Identify what is known, unknown, risky, ambiguous, or underspecified. Produce clarifying assumptions and acceptance criteria.

package/agents/critic.md

@@ -1,11 +1,11 @@
----
-name: critic
-description: Challenge plans and designs before execution
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls
----
-
-You are a critical reviewer. Find flaws, missing steps, unsafe assumptions, overengineering, underengineering, and verification gaps. Return concrete fixes to the plan.
+---
+name: critic
+description: Challenge plans and designs before execution
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls
+---
+
+You are a critical reviewer. Find flaws, missing steps, unsafe assumptions, overengineering, underengineering, and verification gaps. Return concrete fixes to the plan.

package/agents/executor.md

@@ -1,11 +1,11 @@
----
-name: executor
-description: Implement planned code changes
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls, bash, edit, write
----
-
-You are an implementation specialist. Follow the provided plan, make targeted changes, keep edits minimal, and report changed files plus validation status. Do not broaden scope without explaining why.
+---
+name: executor
+description: Implement planned code changes
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls, bash, edit, write
+---
+
+You are an implementation specialist. Follow the provided plan, make targeted changes, keep edits minimal, and report changed files plus validation status. Do not broaden scope without explaining why.

package/agents/explorer.md

@@ -1,11 +1,11 @@
----
-name: explorer
-description: Fast codebase discovery and file/symbol mapping
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls
----
-
-You are a fast codebase explorer. Map relevant files, symbols, data flow, and constraints. Do not modify files. Return concise findings with paths and evidence.
+---
+name: explorer
+description: Fast codebase discovery and file/symbol mapping
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls
+---
+
+You are a fast codebase explorer. Map relevant files, symbols, data flow, and constraints. Do not modify files. Return concise findings with paths and evidence.

package/agents/planner.md

@@ -1,11 +1,11 @@
----
-name: planner
-description: Create an execution plan with clear sequencing and risk notes
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls
----
-
-You are a planning specialist. Convert the goal and discovery notes into a concrete, ordered plan. Identify dependencies, risks, validation steps, and handoff instructions for implementers.
+---
+name: planner
+description: Create an execution plan with clear sequencing and risk notes
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls
+---
+
+You are a planning specialist. Convert the goal and discovery notes into a concrete, ordered plan. Identify dependencies, risks, validation steps, and handoff instructions for implementers.

package/agents/reviewer.md

@@ -1,11 +1,11 @@
----
-name: reviewer
-description: Review code changes for correctness, maintainability, and regressions
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls, bash
----
-
-You are a code reviewer. Review the implementation for bugs, regressions, maintainability issues, missing tests, and project-rule violations. Return prioritized findings with evidence.
+---
+name: reviewer
+description: Review code changes for correctness, maintainability, and regressions
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls, bash
+---
+
+You are a code reviewer. Review the implementation for bugs, regressions, maintainability issues, missing tests, and project-rule violations. Return prioritized findings with evidence.

package/agents/security-reviewer.md

@@ -1,11 +1,11 @@
----
-name: security-reviewer
-description: Review changes for security vulnerabilities and trust-boundary issues
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls, bash
----
-
-You are a security reviewer. Look for injection, authn/authz flaws, insecure defaults, secret exposure, unsafe filesystem/network behavior, and dependency risks. Return severity and remediation.
+---
+name: security-reviewer
+description: Review changes for security vulnerabilities and trust-boundary issues
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls, bash
+---
+
+You are a security reviewer. Look for injection, authn/authz flaws, insecure defaults, secret exposure, unsafe filesystem/network behavior, and dependency risks. Return severity and remediation.

package/agents/test-engineer.md

@@ -1,11 +1,11 @@
----
-name: test-engineer
-description: Design and implement test strategy for a change
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls, bash, edit, write
----
-
-You are a test engineer. Identify the right test level, add or adjust tests when asked, detect flaky assumptions, and report exact validation commands and results.
+---
+name: test-engineer
+description: Design and implement test strategy for a change
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls, bash, edit, write
+---
+
+You are a test engineer. Identify the right test level, add or adjust tests when asked, detect flaky assumptions, and report exact validation commands and results.

package/agents/verifier.md

@@ -1,11 +1,11 @@
----
-name: verifier
-description: Verify that implementation satisfies the requested goal
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls, bash
----
-
-You are a verification specialist. Check whether the work is complete, correct, tested, and aligned with project constraints. Prefer evidence over assumptions. Return PASS or FAIL with reasons.
+---
+name: verifier
+description: Verify that implementation satisfies the requested goal
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls, bash
+---
+
+You are a verification specialist. Check whether the work is complete, correct, tested, and aligned with project constraints. Prefer evidence over assumptions. Return PASS or FAIL with reasons.

package/agents/writer.md

@@ -1,11 +1,11 @@
----
-name: writer
-description: Write concise documentation, migration notes, and summaries
-model: false
-systemPromptMode: replace
-inheritProjectContext: true
-inheritSkills: false
-tools: read, grep, find, ls, edit, write
----
-
-You are a documentation specialist. Produce clear, concise, maintainable docs and summaries. Preserve technical accuracy and avoid marketing fluff.
+---
+name: writer
+description: Write concise documentation, migration notes, and summaries
+model: false
+systemPromptMode: replace
+inheritProjectContext: true
+inheritSkills: false
+tools: read, grep, find, ls, edit, write
+---
+
+You are a documentation specialist. Produce clear, concise, maintainable docs and summaries. Preserve technical accuracy and avoid marketing fluff.

package/docs/next-upgrade-roadmap.md

@@ -22,6 +22,66 @@ Already implemented and pushed:
 - Live-agent control distinguishes `steer` from `follow-up` at live-control/API level.
 - Retry attempts have `attemptId`; max-retry deadletters link to the final `attemptId`.
 - Worker prompt pipeline and capability inventory metadata artifacts are written per task.
+- P0.1: effectiveness guard escalates `warn` to `blocked` for mutating-role tasks with no observable worker activity.
+- P1.1: mailbox `readMailbox` accepts `kind` filter; API `read-mailbox` supports `config.kind`.
+- P1.5: `TeamEventMetadata` extended with `parentEventId`, `attemptId`, `branchId`, `causationId`, `correlationId`.
+- P1.6: `buildSyntheticTerminalEvidence()` produces `"worker"`/`"cancelled"` terminal records for cancelled in-flight tasks.
+- P1.7: `buildCapabilityInventory(cwd)` normalizes teams/workflows/agents; API `operation=inventory`.
+- P2.1: typed hook lifecycle — `registerHook`/`executeHook` registry; `before_run_start` and `before_task_start` wired.
+- P2.4: `AbortSignal` wired into `collectRuns`, `validateMailbox`, `readAllMailboxMessages`, `pruneFinishedRuns`, `cleanupRunWorktrees`, etc.
+- Resume scaffold runs preserve scaffold mode from original manifest when workers not disabled.
+
+## Implementation Status as of `v0.1.46`
+
+This roadmap is **not complete overall**. The `v0.1.46` release completed several vertical slices, but multiple roadmap items remain partial or unimplemented.
+
+### Implemented / mostly implemented
+
+- Baseline worker behavior: real child-process execution by default, explicit scaffold dry-runs, and blocked implicit scaffold/no-op runs.
+- P0.1 ✅ effectiveness policy enforcement: default guard escalates `warn` to `blocked` for mutating-role tasks.
+- P0.2 ✅ runtime safety persistence: manifests persist `runtimeResolution`; `runtime.resolved` event emitted; status shows safety; blocked runs persist evidence.
+- Effectiveness reporting: summary/progress/status expose no-observed-work evidence and policy outcome.
+- Structured cancellation basics: cancellation reasons flow through retry/backoff/team-runner paths and run/task events.
+- Retry attempt evidence: retry attempts and max-retry deadletters carry/link `attemptId` data.
+- Prompt pipeline artifacts and per-task capability metadata artifacts are written.
+- P1.3 worker teardown evidence vertical slice: `WorkerExitStatus` and terminal worker cancellation evidence exist.
+
+### Completed in this upgrade cycle (after v0.1.46)
+
+- P0.1 effectiveness policy enforcement: default guard now escalates `warn` to `blocked` for mutating-role tasks with no observable worker activity; read-only roles remain `warning`.
+- P0.2 runtime safety persistence: manifests persist `runtimeResolution`; `runtime.resolved` event emitted; status shows safety; blocked runs persist evidence.
+- P1.1 durable steering/follow-up queues: `readMailbox` accepts `kind` filter; API `read-mailbox` supports `config.kind`; steering and follow-up are isolatable by kind.
+- P1.2 respond vs follow-up UX: `/team-follow-up` command added for continuation prompts; `/team-respond` remains for waiting-task replies.
+- P1.3 two-phase child process teardown: `WorkerExitStatus` populated from graceful SIGTERM → grace window → hard kill pipeline.
+- P1.5 event-tree provenance: `TeamEventMetadata` extended with `parentEventId`, `attemptId`, `branchId`, `causationId`, `correlationId`; retry and cancel events carry `attemptId`.
+- P1.6 synthetic terminal results: `buildSyntheticTerminalEvidence()` in `cancellation.ts`; cancelled in-flight tasks receive `"worker"`/`"cancelled"` terminal evidence records.
+- P1.7 unified capability inventory: `buildCapabilityInventory(cwd)` normalizes teams/workflows/agents into `CapabilityItem[]`; API `operation=inventory` returns sorted JSON.
+- P1.8 capability disable by stable ID: `disabledCapabilities` in `CrewPolicyConfig`; inventory marks disabled items with reason.
+- P2.1 typed hook lifecycle: `HookName`, `HookMode`, `HookOutcome`, `HookContext`, `HookResult`, `HookExecutionReport` types; `registerHook`/`executeHook`/`clearHooks` registry; `before_run_start` and `before_task_start` wired into team-runner.
+- P2.2 intent gates for destructive actions: `enforceDestructiveIntent` wired in cancel/cleanup/forget/prune/delete; configurable via `policy.requireIntentForDestructiveActions`.
+- P2.3 durable history projection: `transformRunContextBeforeWorkerStart()` and `convertRunHistoryToWorkerPrompt()` bounded projection functions.
+- P2.4 CancellationToken wired into long scans: `AbortSignal` passed to `collectRuns`/`validateMailbox`/`readAllMailboxMessages`/`pruneFinishedRuns`/`cleanupRunWorktrees`.
+- P2.5 content-addressed blob store: `writeBlob`/`readBlob`/`readBlobMetadata` with SHA-256 dedup and metadata sidecars.
+- P2.6 dashboard panes for capability and cancellation: `renderCapabilityPane` and `renderCancellationPane`.
+- Resume scaffold run fix: preserves scaffold mode from original manifest when workers not disabled.
+
+### Partial / not safe to mark complete
+
+- P1.4 reserve worker control channel before spawn: controller metadata persistence during startup not yet implemented.
+- P2.7 event-first UI: render coalescing and snapshot caches exist, but live UI still relies on durable file polling as a primary source in several panes.
+- P2.8 shared raw scan-entry cache: not yet implemented.
+
+### Completed / no longer backlog
+
+- P2.7 event-first UI — RunEventBus wired into appendEvent; dashboard, widget, sidebar auto-invalidate on events; snapshot cache invalidates on events.
+- P2.8 shared raw scan-entry cache — SharedScanCache implemented and wired into manifest reads (run-index) and active-run-registry (active manifest reads).
+- P3.1 tarball-install smoke — `scripts/release-smoke.mjs` verified; `npm run smoke:release` added.
+- Hook lifecycle — All hooks wired: `before_run_start`, `before_task_start`, `before_cancel`, `before_forget`, `before_cleanup`, `before_publish`, `task_result`, `run_recovery`. Only `session_before_switch` remains (no cwd switch mechanism in current codebase).
+
+### Remaining items
+
+- `session_before_switch` hook — no cwd/session switch mechanism in current codebase; placeholder for future.
+- P3.2 CI gate — integrate `smoke:release` into CI pipeline (requires CI config).
 
 ## Priority Legend
 
@@ -82,12 +142,13 @@ Already implemented and pushed:
    - set run `blocked` or `failed` depending config;
    - include task IDs in `data`.
 
-**Acceptance criteria**
+**Acceptance criteria** ✅
 
-- A mocked child-process run with no tool/model/transcript evidence does not report clean `completed` by default.
-- Scaffold run still completes as explicit dry-run and displays `Worker execution: disabled/scaffold`.
-- `status` clearly lists `noObservedWork` and `needsAttention` task IDs.
-- Unit tests cover warn/block/fail modes.
+- ✅ A mocked child-process run with no tool/model/transcript evidence does not report clean `completed` by default.
+- ✅ Scaffold run still completes as explicit dry-run and displays `Worker execution: disabled/scaffold`.
+- ✅ `status` clearly lists `noObservedWork` and `needsAttention` task IDs.
+- ✅ Unit tests cover warn/block/fail modes.
+- ✅ Default guard escalates `warn` to `blocked` for mutating-role tasks.
 
 **Verification**
 
@@ -130,11 +191,12 @@ npm run test:unit
 - `test/unit/team-run.test.ts`
 - `test/unit/runtime-resolver.test.ts`
 
-**Acceptance criteria**
+**Acceptance criteria** ✅
 
-- `status` shows `Runtime safety: trusted|explicit_dry_run|blocked`.
-- Blocked disabled-worker runs persist enough evidence to explain why no subagents spawned.
-- Existing manifest schema remains backward compatible.
+- ✅ `status` shows `Runtime safety: trusted|explicit_dry_run|blocked`.
+- ✅ Blocked disabled-worker runs persist enough evidence to explain why no subagents spawned.
+- ✅ Existing manifest schema remains backward compatible.
+- ✅ `runtimeResolution` persisted on manifest; `runtime.resolved` event emitted.
 
 ## P1 — Steering/Follow-up Semantics Beyond Live Control
 
@@ -170,12 +232,12 @@ npm run test:unit
 - `test/unit/live-agent-control.test.ts`
 - `test/unit/respond-tool.test.ts`
 
-**Acceptance criteria**
+**Acceptance criteria** ✅ (partially — kind filter and API done; UI pane separation remaining)
 
-- Steering and follow-up can be inspected separately.
-- Existing inbox/outbox JSONL remains readable.
-- Durable queue survives process/session switch.
-- Realtime live delivery dedupes against durable replay.
+- ✅ Steering and follow-up can be inspected separately via `readMailbox` kind filter and API `config.kind`.
+- ✅ Existing inbox/outbox JSONL remains readable.
+- ✅ Kind filter survives process/session switch (durable mailbox).
+- ✅ UI/status separates urgent steering from follow-up backlog (mailbox pane shows kind breakdown with urgency indicators).
 
 ### P1.2 Clarify `respond` vs `follow-up` UX
 
@@ -307,11 +369,12 @@ Retry attempts have `attemptId`, and deadletters link to final attempt. Event lo
 - `test/unit/event-metadata.test.ts`
 - `test/unit/retry-executor.test.ts`
 
-**Acceptance criteria**
+**Acceptance criteria** ✅
 
-- Retry attempt events and terminal task events share attempt provenance.
-- Deadletter records can be traced back to event sequence.
-- Existing JSONL readers ignore missing provenance fields.
+- ✅ Retry attempt events and terminal task events share attempt provenance.
+- ✅ Deadletter records can be traced back to event sequence.
+- ✅ Existing JSONL readers ignore missing provenance fields.
+- ✅ `TeamEventMetadata` extended with `parentEventId`, `attemptId`, `branchId`, `causationId`, `correlationId`.
 
 ### P1.6 Synthetic terminal results for cancelled in-flight operations
 
@@ -336,10 +399,11 @@ Run/task cancellation events are now structured, but worker/tool sub-operations
 - `src/state/contracts.ts`
 - `test/unit/cancellation.test.ts`
 
-**Acceptance criteria**
+**Acceptance criteria** ✅
 
-- No started tool/model operation is left without terminal evidence after cancellation.
-- Status/diagnostics can distinguish user cancel vs timeout vs shutdown.
+- ✅ No started tool/model operation is left without terminal evidence after cancellation.
+- ✅ Status/diagnostics can distinguish user cancel vs timeout vs shutdown.
+- ✅ `buildSyntheticTerminalEvidence()` in `cancellation.ts` produces `"worker"`/`"cancelled"` records.
 
 ## P1 — Capability Inventory and Control Center
 
@@ -379,10 +443,10 @@ interface CapabilityItem {
 
 **Acceptance criteria**
 
-- Inventory is stable and sorted.
-- Shadowed project/user/builtin resources are visible.
-- Skill disabled/budget state is visible.
-- No file path is used as the only stable ID.
+- ✅ Inventory is stable and sorted.
+- ✅ Shadowed project/user/builtin resources are visible in capability inventory (state="shadowed", shadowedBy field).
+- ✅ Skill disabled/budget state is visible in capability inventory (skills enumerated via discoverSkills).
+- ✅ No file path is used as the only stable ID (uses `kind:name` IDs).
 
 ### P1.8 Persist capability disables by stable ID
 
@@ -436,11 +500,18 @@ Errors are recorded in diagnostics/events, not uncontrolled exceptions.
 - `docs/resource-formats.md`
 - `test/unit/hooks*.test.ts`
 
-**Acceptance criteria**
+**Acceptance criteria** ✅ (partial — `before_cancel` not yet wired for async)
 
-- Blocking hook can stop a run before worker start with clear event and status.
-- Non-blocking hook failure records diagnostic and does not crash run.
-- Hook context is redacted and bounded.
+- ✅ Blocking hook can stop a run before worker start with clear event and status.
+- ✅ Non-blocking hook failure records diagnostic and does not crash run.
+- ✅ Hook context is redacted and bounded.
+- ✅ `before_cancel` hook wired (async handleCancel conversion done).
+- ✅ `before_forget` hook wired (async handleForget conversion done).
+- ✅ `before_cleanup` hook wired (async handleCleanup conversion done).
+- ✅ `task_result` hook wired in task-runner before completed/failed event.
+- ✅ `before_publish` hook wired in handleExport.
+- ✅ `run_recovery` hook wired in crash-recovery `applyRecoveryPlan`.
+- ☐ `session_before_switch` not yet wired (no cwd switch mechanism in current codebase; placeholder for future Pi lifecycle integration).
 
 ### P2.2 Require intent via policy/hook for destructive actions
 
@@ -547,11 +618,11 @@ Use it in:
 - `src/ui/run-snapshot-cache.ts`
 - `test/unit/cancellation-token.test.ts`
 
-**Acceptance criteria**
+**Acceptance criteria** ✅
 
-- Long scan can abort within bounded cadence.
-- Heartbeat stage appears in diagnostics/logs.
-- Existing APIs can pass no token and keep current behavior.
+- ✅ Long scan can abort within bounded cadence (`AbortSignal` wired into `collectRuns`, `validateMailbox`, `readAllMailboxMessages`, `pruneFinishedRuns`, `cleanupRunWorktrees`).
+- ✅ `CancellationToken.heartbeat(stage)` wired into `collectRuns` and `pruneFinishedRuns` with stage diagnostics.
+- ✅ Existing APIs can pass no token/signal and keep current behavior.
 
 ## P2 — Artifact Store Improvements
 
@@ -699,16 +770,20 @@ npm pack
 
 ## Suggested Implementation Order
 
-1. **P0.1 Effectiveness policy enforcement** — prevents misleading completed runs.
-2. **P0.2 Persist runtime safety** — improves debugging for worker spawn issues.
+1. ~~**P0.1 Effectiveness policy enforcement**~~ ✅ Completed — default guard escalates `warn` to `blocked` for mutating-role tasks.
+2. ~~**P0.2 Persist runtime safety**~~ ✅ Completed — manifests persist `runtimeResolution`; `runtime.resolved` event emitted.
 3. **P1.3 Two-phase worker teardown** — reduces stale/zombie worker risk.
-4. **P1.1 Durable steering/follow-up queues** — completes semantic split started at live-control level.
-5. **P1.5 Event-tree provenance** — builds on current `attemptId` work.
-6. **P1.7 Capability inventory view** — turns existing per-task artifacts into operator UX.
-7. **P2.3 Durable history projection** — reduces prompt/context risks.
-8. **P2.4 CancellationToken** — improves responsiveness of internal scans.
-9. **P2.5 Blob artifacts** — prevents log/transcript bloat.
-10. **P2.6 Dashboard panels** — surface all new evidence in UI.
+4. ~~**P1.1 Durable steering/follow-up queues**~~ ✅ Completed — `readMailbox` kind filter; API `read-mailbox` supports `config.kind`.
+5. ~~**P1.5 Event-tree provenance**~~ ✅ Completed — `TeamEventMetadata` extended with `parentEventId`/`attemptId`/`branchId`/`causationId`/`correlationId`.
+6. ~~**P1.7 Capability inventory view**~~ ✅ Completed — `buildCapabilityInventory()` + API `operation=inventory` + dashboard pane.
+7. ~~**P2.3 Durable history projection**~~ ✅ Completed — `transformRunContextBeforeWorkerStart()` + `convertRunHistoryToWorkerPrompt()`.
+8. ~~**P2.4 CancellationToken**~~ ✅ Completed — wired into `collectRuns`/`validateMailbox`/`pruneFinishedRuns`/`cleanupRunWorktrees` etc.
+9. ~~**P2.5 Blob artifacts**~~ ✅ Completed — content-addressed blob store with SHA-256 dedup and metadata sidecars.
+10. ~~**P2.6 Dashboard panels**~~ ✅ Completed — capability and cancellation panes.
+
+Also completed (not in original order list):
+- ~~**P1.6 Synthetic terminal results**~~ ✅ — `buildSyntheticTerminalEvidence()` for cancelled in-flight tasks.
+- ~~**P2.1 Typed hook lifecycle**~~ ✅ — `before_run_start`/`before_task_start` wired into team-runner.
 
 ## Release Guidance