@zhixuan92/multi-model-agent 3.8.1 → 3.9.0

package/README.md

@@ -82,7 +82,7 @@ Two ways — pick one:
 
 ```bash
 mmagent serve                          # 127.0.0.1:7337 by default
-curl -s http://localhost:7337/health   # → {"ok":true,"version":"3.8.1",...}
+curl -s http://localhost:7337/health   # → {"ok":true,"version":"3.9.0",...}
 ```
 
 For an always-on background install (survives reboots): [launchd / systemd templates](./scripts/README.md).
@@ -187,8 +187,8 @@ Every `defaults` knob has a built-in. Override only when you need to.
 
 | Field | Default | What it does |
 |---|---|---|
-| `defaults.timeoutMs` | `1800000` (30 min) | Hard task-level wall-clock cap |
-| `defaults.stallTimeoutMs` | `600000` (10 min) | Aborts in-flight runs idle for this long |
+| `defaults.timeoutMs` | `3600000` (60 min) | Hard task-level wall-clock cap (bumped from 30 min in 3.9.0) |
+| `defaults.stallTimeoutMs` | `1200000` (20 min) | Aborts in-flight runs idle for this long (bumped from 10 min in 3.9.0) |
 | `defaults.maxCostUSD` | `10` | Hard per-task cost ceiling; returns `cost_exceeded` when hit |
 | `defaults.tools` | `"full"` | Tool surface: `none` / `readonly` / `no-shell` / `full` |
 | `defaults.sandboxPolicy` | `"cwd-only"` | Path-traversal + symlink confinement to the request's `cwd` |
@@ -285,7 +285,7 @@ Full design rationale: [DIRECTION.md](https://github.com/zhixuan312/multi-model-
 
 ## What's new
 
-Latest: **3.8.1** — read-only review becomes annotation, not gating. The 5 read-only routes (audit, review, verify, investigate, debug) now run a single reviewer pass that annotates each worker finding with `reviewerConfidence` (0-100) and an optional `reviewerSeverity` correction — no rework loop, restoring 3.7.0-comparable wall-clock. `Finding` schema simplified (drop `file`/`line`/`sourceQuote`; required `evidence`; rename `suggestedFix` → `suggestion`). Full history: [CHANGELOG](https://github.com/zhixuan312/multi-model-agent/blob/master/CHANGELOG.md).
+Latest: **3.9.0** — watchdog hardening + per-stage idle telemetry. The reviewer entry points (`runSpecReview` / `runQualityReview` / `runDiffReview`) now thread `taskDeadlineMs` + `abortSignal` + `onProgress`, closing the leak that allowed reviewer hangs to run past the documented cap. Total wall-clock cap bumped 30 → 60 min, stall watchdog 10 → 20 min, both via named constants. New `StageIdleTracker` records `maxIdleMs`/`totalIdleMs`/`activityEvents` per stage and surfaces them on `task_completed` + the heartbeat (`stage_idle_ms`). Full history: [CHANGELOG](https://github.com/zhixuan312/multi-model-agent/blob/master/CHANGELOG.md).
 
 ## Full documentation
 

package/dist/skills/mma-audit/SKILL.md

@@ -8,7 +8,7 @@ when_to_use: >-
   User asks for a doc/spec/config audit OR a methodology skill
   (superpowers:dispatching-parallel-agents, /security-review) points at one AND
   mmagent is running. Audit on PROSE/SPEC docs — use mma-review for source code.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-audit

package/dist/skills/mma-clarifications/SKILL.md

@@ -12,7 +12,7 @@ when_to_use: >-
   `proposedInterpretation` is a hard gate — the batch is paused, not
   informational. The batch will not complete until the caller responds. Treating
   it as advisory is the clarification-as-info anti-pattern (AP5).
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-clarifications

package/dist/skills/mma-context-blocks/SKILL.md

@@ -12,7 +12,7 @@ when_to_use: >-
   Register once here, then pass the ID via `contextBlockIds` on mma-delegate /
   mma-execute-plan / mma-audit / mma-review / mma-verify / mma-debug /
   mma-investigate. Cheaper and faster than inlining the same content N times.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-context-blocks

package/dist/skills/mma-debug/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   read files, reproduce, trace — OR a methodology skill
   (superpowers:systematic-debugging) points at the investigation step. Delegate
   the read/reproduce/trace; the main agent stays on the hypothesis and the fix.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-debug

package/dist/skills/mma-delegate/SKILL.md

@@ -11,7 +11,7 @@ when_to_use: >-
   and keep main context free. If a plan file exists → use mma-execute-plan. If
   the task is audit / review / verify / debug / investigate → use the matching
   specialized skill.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-delegate

package/dist/skills/mma-execute-plan/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   superpowers:subagent-driven-development / superpowers:executing-plans —
   workers are cheaper and don't pollute main context. Task descriptors must
   match plan headings verbatim.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-execute-plan

package/dist/skills/mma-investigate/SKILL.md

@@ -12,7 +12,7 @@ when_to_use: >-
   git-history queries. OR you are about to read 3+ files / run any grep in main
   context — that's the inline-labor-leakage anti-pattern (AP2); delegate to this
   skill instead.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-investigate

package/dist/skills/mma-retry/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   you want to re-try the failed indices only. Prefer this over re-dispatching
   the whole batch or inline-retrying — it's idempotent and preserves the
   original batch's diagnostics.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-retry

package/dist/skills/mma-review/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   AND mmagent is running. Delegate so each file reviews on its own worker; the
   main agent only decides what to merge. Review on SOURCE CODE — use mma-audit
   for prose specs / configs.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-review

package/dist/skills/mma-verify/SKILL.md

@@ -10,7 +10,7 @@ when_to_use: >-
   against implemented work BEFORE claiming success. Delegate so each checklist
   item gets independent evidence-gathering on a worker. Use this BEFORE saying
   "done" — never after.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # mma-verify

package/dist/skills/multi-model-agent/SKILL.md

@@ -11,7 +11,7 @@ when_to_use: >-
   tasks — AND mmagent is running. Read this once, pick the matching mma-* skill,
   and delegate there. Applies equally whether the user invoked a superpowers
   methodology skill or asked directly.
-version: 3.8.1
+version: 3.9.0
 ---
 
 # multi-model-agent (router)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "3.8.1",
+  "version": "3.9.0",
   "type": "module",
   "license": "MIT",
   "description": "Standalone HTTP server for multi-model-agent. Routes tool-invocation work to Claude, Codex, or OpenAI-compatible sub-agents with async-polling REST dispatch and installable skills for Claude Code, Gemini CLI, Codex CLI, and Cursor.",
@@ -52,7 +52,7 @@
   },
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^8.5.0",
-    "@zhixuan92/multi-model-agent-core": "^3.8.1",
+    "@zhixuan92/multi-model-agent-core": "^3.9.0",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "proper-lockfile": "^4.1.2",