pi-crew 0.1.40 → 0.1.43

package/CHANGELOG.md

@@ -2,6 +2,67 @@
 
 ## Unreleased
 
+## 0.1.43
+
+### Added
+
+- `/team-settings` command: view and manage all pi-crew config from Pi CLI (`list`, `get`, `set`, `unset`, `path`, `scope`).
+- `addTranslations(locale, bundle)` and `listLocales()` for runtime-extensible i18n.
+
+### Fixed
+
+- **UI freeze crash**: replaced `setInterval` with recursive `setTimeout` in `RenderScheduler` and `HeartbeatWatcher` to prevent timer storms when renders exceed the interval.
+- **Growing-file I/O bottleneck**: `safeRecentEvents`, `readMailboxCounts`, `readGroupJoinMailbox` now use tail-reading (last 32 KB) instead of reading entire `.jsonl` files that grow unbounded over long runs.
+- **Snapshot cache TTL** increased from 250 ms to 500 ms, halving unnecessary I/O.
+- **Heartbeat watcher memory leak**: stale keys are now cleaned after 10 minutes of inactivity instead of being held forever.
+- **Dashboard crash guard**: `render()` is wrapped in `try/catch` with a fallback error display.
+- **Dashboard selected-index mismatch**: reset `selected` to 0 when the selected run disappears from the manifest cache.
+- **`live-run-sidebar.ts` crash**: fixed missing optional chaining on `agent.progress?.recentOutput?.at(-1)`.
+- **`signatureFor` crash**: `JSON.stringify` in snapshot cache wrapped in `try/catch` with a timestamp fallback.
+- **Render scheduler timer leak**: added a `disposed` guard after `schedule()` to prevent orphaned timers.
+- **Render scheduler loop guard**: capped at 5 iterations per `flush()` to prevent infinite loops when `render()` re-enters `flush()`.
+- **`powerbar-publisher.ts`**: replaced `.filter().length` with `.reduce()` counting to avoid temporary array allocations.
+
+### Changed
+
+- **i18n module hardened**: locale validated at runtime (not hardcoded union type), `currentLocale` reset on dispose, missing-key guard (`fallback[key] ?? key`), `__test__resetI18n()` helper.
+
+## 0.1.42
+
+### Fixed
+
+- Reduced atomic-write rename retries from 20 to 5 and added busy-wait fallback for `Atomics.wait` to avoid event-loop stalls on Windows with aggressive file-locking.
+- Applied the same `sleepSync` fallback pattern to `locks.ts` for consistent lock-acquisition resilience.
+- Removed dead `findReadyTask` function in team-runner.
+- Eliminated a redundant `refreshTaskGraphQueues` O(n) call per batch iteration by reusing the already-computed `taskGraphSnapshot` for ready-task selection.
+- Expanded `appendTaskAttentionEvent` dedup window from 100 to 200 events and switched to a computed dedup key.
+
+### Changed
+
+- Extended `MUTATING_TOOLS` set in completion guard with `replace_in_file`, `insert`, `delete_files`, `create_file`, `overwrite`, and `patch`.
+- Extended `MUTATING_COMMANDS` regex with `sed -i`, `tee`, `wget -O`, and `curl -o` patterns.
+- Reordered bash-command mutation check so mutating patterns (`sed -i`) take priority over read-only patterns (`sed`).
+- Unknown bash commands that don't match the read-only list are now treated as potentially mutating (conservative default).
+
+### Hardened
+
+- Replaced `timer.unref?.()` with `timer.unref()` in `SubagentManager` blocked-poll and stuck-notify timers.
+- Added session-liveness guard to `notifyOperator` fallback so it won't attempt `sendFollowUp` after extension cleanup.
+
+## 0.1.41
+
+### Added
+
+- Added strict-provider-friendly team tool schema shapes and config schema coverage for result delivery controls.
+- Added resilient result watcher fallback polling for resource-limit watch failures and partial JSON retry handling.
+- Added `runtime.completionMutationGuard` (`off`/`warn`/`fail`) with structured `task.attention` events when implementation-style workers complete without observed mutations.
+- Added group-join mailbox delivery metadata, request-id dedupe, ack observability, timeout events, and dashboard/status visibility.
+- Expanded `team doctor` and `team status` with schema, async/result delivery, worktree/readiness, attention, transcript, and group-join diagnostics.
+
+### Fixed
+
+- Recovered adaptive implementation planner output when compaction truncates the end marker but complete phase objects are still present.
+
 ## 0.1.40
 
 ### Added

package/README.md

@@ -60,6 +60,8 @@ Current highlights:
 - reliability hardening: heartbeat gradient watcher, opt-in retry executor with attempt trace, crash-recovery detection, deadletter queue
 - background `Agent`/`crew_agent` completion wake-up so parent sessions can automatically join completed subagent results
 - optional `runtime.requirePlanApproval` gate for planner-first approval before mutating adaptive implementation workers run
+- optional `runtime.completionMutationGuard` to warn or fail implementation-style workers that complete without observed mutation tool calls
+- grouped result delivery is correlated through mailbox metadata, deduped by request id, and acknowledged via existing `ack-message`
 - shared redaction for common secrets before durable event/log/mailbox/artifact/metric/diagnostic persistence
 - package polish: `schema.json`, TypeScript semantic check, strip-types import smoke, cross-platform CI workflow, dry-run package verification
 
@@ -176,7 +178,10 @@ Supported config:
   },
   "runtime": {
     "mode": "auto",
-    "requirePlanApproval": false
+    "groupJoin": "smart",
+    "groupJoinAckTimeoutMs": 300000,
+    "requirePlanApproval": false,
+    "completionMutationGuard": "warn"
   },
   "limits": {
     "maxConcurrentWorkers": 3,
@@ -237,6 +242,8 @@ Safety notes:
 - Background `Agent`/`crew_agent` runs notify the parent session when they reach a terminal state; the parent can then call `get_subagent_result`/`crew_agent_result` and continue the original task.
 - `tools.terminateOnForeground` is an opt-in power-user setting. When true, foreground `Agent`/`crew_agent` calls return with `terminate: true` after the child result is available, saving one follow-up LLM turn. Default is false so the assistant can still summarize raw worker output.
 - Runtime state paths are treated as untrusted data: run ids, import bundles, artifact/transcript paths, mailbox files, and agent control/log files are validated with containment checks before reads or writes.
+- `runtime.completionMutationGuard` defaults to `warn`; set `off` to disable or `fail` to fail implementation-style tasks that report success without observed mutation tool calls.
+- Group-join result messages use normal mailbox delivery and normal `ack-message`; missing acknowledgements never block run completion, and duplicate delivery attempts reuse the same request id/message instead of appending spam.
 - Common secret patterns (`token=`, `apiKey=`, `Authorization: Bearer ...`, private keys, etc.) are redacted before durable logs/events/mailbox/artifacts/metrics/diagnostics are written.
 - `observability.enabled` defaults to true for in-memory metrics and heartbeat watching. Metric JSONL snapshots are gated by `telemetry.enabled`; set `telemetry.enabled=false` to opt out of local telemetry files.
 - `reliability.autoRetry` and `reliability.autoRecover` default to false. Enabling retry may execute an idempotent task more than once; each attempt is recorded in `task.attempts`, and exhausted retries append a deadletter entry.
@@ -450,6 +457,7 @@ Manual slash commands are ops/debug controls. Autonomous tool use via policy/rec
 /team-dashboard
 /team-init [--copy-builtins] [--overwrite]
 /team-config [key=value] [--unset=key.path] [--project]
+/team-settings [list|get <key>|set <key> <value>|unset <key>|path|scope]
 /team-autonomy [status|on|off|manual|suggested|assisted|aggressive] [--prefer-async] [--no-worktree-suggest]
 /team-validate
 /team-help
@@ -472,7 +480,7 @@ Manual slash commands are ops/debug controls. Autonomous tool use via policy/rec
 /team-api team_... send-message taskId=task_... direction=inbox to=worker body="task scoped message"
 /team-api team_... read-mailbox direction=outbox
 /team-api team_... read-mailbox taskId=task_... direction=inbox
-/team-api team_... ack-message messageId=msg_...
+/team-api team_... ack-message messageId=msg_...   # also acknowledges group-join result messages
 /team-api team_... read-delivery
 /team-api team_... validate-mailbox repair=true
 /team-api team_... approve-plan
@@ -486,6 +494,56 @@ Use `/team-metrics` for a current metrics snapshot. The optional argument is a g
 /team-metrics crew.task.*
 ```
 
+### `/team-settings` — view & manage config
+
+List all settings, get/set individual keys, or unset (reset to default).
+
+```text
+/team-settings                          # list all known config keys
+/team-settings get limits.maxTurns      # read one key
+/team-settings set limits.maxTurns 20   # update a key
+/team-settings unset runtime.maxTurns   # reset to default
+/team-settings path                     # show config file path
+/team-settings scope                    # show current scope (user/project)
+```
+
+**Supported config keys:**
+
+| Key | Type | Description |
+|-----|------|-------------|
+| `asyncByDefault` | boolean | Run workflows async by default |
+| `executeWorkers` | boolean | Enable real child Pi workers |
+| `notifierIntervalMs` | number | Polling interval for async notifications |
+| `runtime.mode` | `"auto"\|"scaffold"\|"child-process"\|"live-session"` | Crew runtime selection |
+| `runtime.maxTurns` | number | Max turns per worker |
+| `runtime.graceTurns` | number | Grace turns after max |
+| `runtime.inheritContext` | boolean | Workers inherit parent context |
+| `runtime.promptMode` | `"replace"\|"append"` | Prompt merge strategy |
+| `runtime.groupJoin` | `"off"\|"group"\|"smart"` | Group join strategy |
+| `runtime.groupJoinAckTimeoutMs` | number | Group join ack timeout (ms) |
+| `runtime.requirePlanApproval` | boolean | Require plan approval before execution |
+| `runtime.completionMutationGuard` | `"off"\|"warn"\|"fail"` | Mutation guard on completion |
+| `limits.maxConcurrentWorkers` | number | Max concurrent workers |
+| `limits.maxTaskDepth` | number | Max task tree depth |
+| `limits.maxChildrenPerTask` | number | Max children per task |
+| `limits.maxRunMinutes` | number | Max run duration (minutes) |
+| `limits.maxRetriesPerTask` | number | Max retries per task |
+| `limits.maxTasksPerRun` | number | Max tasks per run |
+| `limits.heartbeatStaleMs` | number | Heartbeat stale threshold (ms) |
+| `control.enabled` | boolean | Enable agent control-plane |
+| `control.needsAttentionAfterMs` | number | Attention trigger after inactivity (ms) |
+| `autonomous.profile` | `"manual"\|"suggested"\|"assisted"\|"aggressive"` | Autonomy profile |
+| `autonomous.injectPolicy` | boolean | Inject autonomy policy into prompt |
+| `autonomous.preferAsyncForLongTasks` | boolean | Auto-async for long tasks |
+| `autonomous.allowWorktreeSuggestion` | boolean | Suggest worktree mode |
+| `tools.enableClaudeStyleAliases` | boolean | Enable Claude-style tool aliases |
+| `tools.enableSteer` | boolean | Enable steer tool |
+| `tools.terminateOnForeground` | boolean | Return terminate:true from foreground Agent |
+| `agents.disableBuiltins` | boolean | Disable all builtin agents |
+| `observability.prometheus.enabled` | boolean | Enable Prometheus exporter |
+| `observability.otlp.enabled` | boolean | Enable OTLP exporter |
+| `worktree.enabled` | boolean | Enable worktree isolation |
+
 ## Dashboard
 
 Open:

package/agents/analyst.md

@@ -1,11 +1,11 @@
----
-name: analyst
-description: Analyze requirements, ambiguity, and hidden constraints
-model: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-haiku-4-5
-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: claude-haiku-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-sonnet-4-5
-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: claude-sonnet-4-5
+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: claude-haiku-4-5
-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: claude-haiku-4-5
+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.