pi-crew 0.9.57 → 0.9.58

package/CHANGELOG.md

@@ -3,6 +3,38 @@
 > **Note:** `atomic-write-v2.ts` / `AtomicWriter` mentioned in historical entries below was consolidated into `atomic-write.ts` as of v0.9.42. This changelog is preserved as historical record — the migration was completed (the v2 class was never adopted; v1 won on simplicity + symlink-safety + link+unlink atomicity). See `docs/migration/atomic-write-v2-migration.md` for the decision rationale.
 
 
+## [0.9.58] — fix load crash on stale hoisted typebox: defensive guard + bundle vendoring (survives `pi update`) + round-1/round-2 fixes (2026-08-04)
+
+### Bug fixes
+
+- **CRITICAL — extension failed to load after 0.9.57 update (`Cannot read properties of undefined (reading 'Set')`)**. `src/schema/team-tool-schema.ts` called `TypeRegistry.Set("StringEnum", …)` at module top-level. `TypeRegistry` only exists in `@sinclair/typebox@0.34.50+`, but pi-crew declared `^0.34.50`. Pi installs **all** extensions into **one** shared npm store with hoisted deps, and on update it only re-checks the extension's own `package.json` version — if pi-crew is already latest, it does **not** re-resolve transitive deps. So an install could land pi-crew@0.9.57 (needs `TypeRegistry`) over a stale hoisted `@sinclair/typebox@0.34.49` (no `TypeRegistry`). Under ESM↔CJS interop, `import { TypeRegistry }` then resolved to `undefined`, and the unguarded top-level `TypeRegistry.Set(…)` crashed extension load (the bundle path swallowed it and fell through to strip-types, where it was uncaught). `--force` only applies to self-update, not extensions, so the dirty dep tree was never healed.
+  - **Fix 1 — defensive guard (src / strip-types path)**: feature-detect `TypeRegistry` (`HAS_TYPE_REGISTRY`) and skip registration when absent. `buildStringEnum()` (renamed from the internal `stringEnum`, now exported) takes an injectable `hasRegistry` flag and falls back to a verbose-but-validating `Type.Union` of `Type.Literal`s when `TypeRegistry` is missing — so the extension **always loads** regardless of the store's typebox version. `Value.Check` works natively in both branches.
+  - **Fix 2 — vendor `@sinclair/typebox` into the bundle (`scripts/build-bundle.mjs`, removed from `external`)**: this is what makes pi-crew **run the correct/optimal version after `pi update --all|--extensions`**. The bundle now ships its own typebox (built-in ≥0.34.50) with **zero external `@sinclair/typebox` imports**, so pi-crew is fully immune to whatever stale typebox the shared store holds — under ANY update mechanism. The compact `StringEnum` path (not the verbose fallback) is always active. SAFE to bundle: host pi/pi-ai validate tools with the *unscoped* `typebox` package (not `@sinclair/typebox`), so pi-crew's vendored copy never overlaps pi-ai's instance — they were already separate. (Fix 1 stays as a safety net for the strip-types dev fallback.)
+  - Verified: `test/unit/schema/stringenum-typebox-guard.test.ts` exercises both `buildStringEnum` branches against real typebox `Value.Check`; all 95 `test/unit/schema/**` + 245 blast-radius tests green; `tsc --noEmit` clean; bundle-load 2/2; bundle has **zero external `@sinclair/typebox` imports** (self-contained); bundle 2.99 MB (budget 3.5 MB).
+  - User remedy: once 0.9.58 is published, just `pi update --extensions` (or `pi update --all`). The 0.9.57→0.9.58 version bump forces a reinstall, and the new bundle carries its own typebox — no manual store cleanup needed. (On an already-broken machine: start once with `pi -ne`, run the update, then restart normally.)
+
+### Also bundled in 0.9.58 (already on main, unreleased)
+
+- **Round-1 security hardening** (`ea03dd88`): strip `runtime.agentExtensions` from untrusted project config, harden untrusted-data fence injection (no `</untrusted-…>` escape), filter `PI_CREW_*` secrets from child-Pi env.
+- **Round-2 locking fixes** (`6a5d8d16`): PID-guarded `releaseOwnLock` (LOCK-1 — no longer deletes a stolen lock in the `finally`), and `handleResume` releases the resume `withRunLock` before the minutes-long `executeTeamRun` (LOCK-2).
+- **Round-3 correctness** (`ae36cd2a`): `taskTimeoutMs` no longer capped at 10s by the wrong `runtimeMaxTurns` ceiling (RT-NEW-1 — 5-minute timeouts silently disabled before); worktree dirty-snapshots pass `-c core.quotePath=false` so non-ASCII filenames are no longer silently dropped before `git clean -fd` (STATE-8 data-loss fix).
+- **Round-4 state recovery** (`7b7968d5`): corrupt `manifest.json`/`tasks.json` are now quarantined (`.corrupt-<ts>`) + logged instead of silently making a run invisible (STATE-3); the stale-reconciler and health-monitor use the recovery loaders instead of bare `JSON.parse` that silently skipped corrupt runs (NEW-R1/R2).
+- **Round-5 batch** (`59505265`, `26d07b76`, `a0fa1cb2`, `135dfc8b`): state/atomic (async `mode` option, compact `tasks.json`, hash-on-memory, atomic mailbox/subagent/gitignore writes, async-twin manifest quarantine), defense-in-depth (DI-1..DI-4, lazy yaml, bundle-mode warmup skip), TOCTOU `existsSync`+`readFileSync` fixes (NEW-P4), budget-abort drains in-flight units via shared `terminaliseRunWithDrain` (RT-NEW-2), benign signals no longer write terminal `async.failed` (RT-NEW-3), event-log tail-read for notifier/status (STATE-5), lazy `cli-highlight` + lazy `npm root -g` probe + provider-extension cache (PERF-1/2/3), themes mtime fast-path (PERF-7), `userPiRoot` cache keyed on home (NEW-P2 isolation fix).
+- **Bundle rebuild note**: `dist/index.mjs` was rebuilt after R3–R5 — the earlier 13:35 build contained only R1/R2 + the typebox vendoring. Verify the shipped bundle includes the R3+ markers before publishing.
+
+### Note on postinstall "bundle build FAILED" message
+
+- Harmless and expected on published installs: `scripts/build-bundle.mjs` is intentionally omitted from the npm tarball (`files` list) so the committed `dist/index.mjs` is used as-is. `postinstall.mjs` reports the script's absence as a red FAILED line; the install succeeds via the committed bundle. (No code change — documenting so the red line is not mistaken for the load crash.)
+
+### Late-0.9.58 additions — schema validation repair, prune dryRun, cleanup (post round-6)
+
+- **Schema — empty-string unset markers** (`9173c6c4`, `bb47191e`): `replyDeadline`, `interval`, `budgetWarning`, `budgetAbort`, `tokenBudget` now accept `""`. Calling models emit `""` for unset optional fields, and pi-ai `validateToolArguments` runs BEFORE the pi-crew handler — a bare `Type.Integer`/`Type.Number` rejected `""` → every team action returned `Validation failed for tool team` and the model looped. Added `Type.Literal("")` to each union.
+- **Schema — stringified numbers** (`9064343b`): pi-ai's tool-argument coercion stringifies a numeric value when the schema `Union` has a string-literal branch (e.g. `interval:0` arrived as `"0"`). Broadened the 5 numeric-union fields to also accept a numeric-string pattern branch, and added `normalizeLooseNumericFields()` in `handleTeamTool` to coerce the string form back to a real number (and treat `""` as unset) before domain routers read params. Without this, `team prune` and any call sending these optional numeric fields with value `0` failed validation.
+- **prune dryRun now a true non-destructive preview** (`85f657c6`, `d5d42032`): `handlePrune` ignored `params.dryRun` entirely — it only checked `confirm`, then deleted. A caller requesting a preview (`dryRun:true`) with `confirm:true` got runs DELETED instead of listed (data-safety bug). `pruneFinishedRuns` now takes a `dryRun` option (stops after the read-only safety check — no deletion, no worktree cleanup, no audit); `handlePrune` lets `dryRun` bypass `confirm`; the `tool_call` destructive gate now allows `prune dryRun=true` (previously only `cleanup` was exempt).
+- **forget resurrect fix** (`672a3d4d`): a still-alive background runner could land one final heartbeat write after the first `rmSync` in `handleForget` — `atomicWriteFile`'s `mkdirSync(recursive)` re-created the state dir, resurrecting `heartbeat.json` in a dir we just forgot. Now drains briefly (250ms) and re-removes any resurrected residue.
+- **Round-6 resource cleanup** (`9f81a081`): `stopAllWatchdogs()` exported + called in `cleanupRuntime`; `RunDeadline.timer` cleared in all 4 run paths (dwf/async/fg/inline); foreground-abort `removeEventListener`.
+- **CI green**: lint + format:check + full `npm test` pass on ubuntu/windows/macos (3 OSes). `2db4c6bc` fixed biome lint/format gaps; `9808f3b0` fixed a macOS-only path-divergence bug in the corrupt-index test.
+
 ## [0.9.57] — provider-extension auto-discovery + team-tool schema repair + whole-project reorganization (2026-08-03)
 
 ### New: provider extensions work in subagents (no hardcoding)