@zhixuan92/multi-model-agent 4.4.0 → 4.5.0

package/README.md

@@ -88,7 +88,7 @@ Two ways — pick one:
 
 ```bash
 mmagent serve                          # 127.0.0.1:7337 by default
-curl -s http://localhost:7337/health   # → {"ok":true,"version":"4.4.0",...}
+curl -s http://localhost:7337/health   # → {"ok":true,"version":"4.5.0",...}
 ```
 
 For an always-on background install (survives reboots): [launchd / systemd templates](./scripts/README.md).
@@ -287,14 +287,12 @@ Full design rationale: [DIRECTION.md](https://github.com/zhixuan312/multi-model-
 | TLS `handshake_failure` to a known-good telemetry endpoint | Local DNS cache is stale. `sudo dscacheutil -flushcache && sudo killall -HUP mDNSResponder` (macOS); restart the daemon so its Node process re-resolves |
 | Local telemetry queue stops draining | Daemon's flusher is in exponential backoff after a transport failure (capped at 1 hr). Restart the daemon to force an immediate boot-flush |
 
-## What's new in 4.4.0
+## What's new in 4.5.0
 
-- **Session-based provider boundary.** `Provider.openSession() → Session.send() → TurnResult` replaces the 1,559-line `RunnerShell` chain. All providers (claude-agent-sdk, codex CLI, `@openai/agents`) now expose only `openSession`; cost / termination-reason mapping cannot diverge.
-- **Five-stage lifecycle.** Stages collapse to `implementing → review → rework → annotating → committing`. Single `HUMAN_LABEL` source of truth for headline labels.
-- **Codex token accounting fixed (≈4× cost over-report on cached turns).** OpenAI/codex emit `input_tokens` as GROSS including `cached_input_tokens`; Anthropic emits NET. The codex adapter now subtracts the cached subset before pricing.
-- **`X-MMA-Main-Model` required again.** Auto-detect was reading JSONL files written by our own claude-tier workers and returning the worker's model as "main". The calling client is the only reliable source. Returns `400 main_model_required` if missing.
-- **LLM `verify` tool removed.** Verification is `verifyCommand` only (deterministic shell command run after the worker).
-- **Telemetry clamp ceilings raised** for 2026-era usage: per-stage input/cached `5M → 100M`, output `500K → 2M`, per-stage cost `$100 → $500`, per-task cost `$800 → $5000`.
+- **Commit from real git diff, not worker self-report.** The commit gate now reads `filesChanged` from `git diff --name-only <preTaskHeadSha>` + filtered untracked files (snapshot-diffed against a `preTaskUntrackedFiles` set captured at task entry), not from the worker's JSON. Three source values surface in telemetry: `git_diff` (authoritative), `self_report` (non-git cwd, count-only), `git_error` (degraded, no commit). Eliminates the "files written but `filesChanged: []` so commit skipped" failure mode.
+- **Progress-watchdog with three signals.** Arms an interval poller around `delegateWithEscalation()` and `rework` `session.send()`. (1) Wall-clock thrash → `controller.abort()` when `wallClockMs > thrashWallClockMs` AND `git diff` empty (default 20 min). (2) Turn-count thrash → `turnsUsed > thrashTurns` AND diff empty (default 25 turns). (3) Scope-violation → any file in the real diff outside the brief's declared scope. Skip gates: read-only tools, non-git cwd, `defaults.progressWatchdogEnabled: false`. A thrashing worker can no longer burn the full budget producing nothing.
+- **Telemetry envelope fixes.** `subtype` reaches the wire (4.4.0 landed it on the HTTP envelope only); `annotating` stage emits a deterministic `stageStats` entry so per-stage dashboards stop showing a gap; per-stage `mainEquivalentCostUSD` attached for the Lite-page per-model savings slice.
+- **Seven new observability events** for diff resolution + watchdog signals: `real_diff_resolved`, `real_diff_self_report_fallback`, `real_diff_git_error`, `progress_watchdog_armed` / `_warn` / `_fired_thrash` / `_scope_violation` / `_disarmed`.
 
 Full history: [CHANGELOG](https://github.com/zhixuan312/multi-model-agent/blob/master/CHANGELOG.md).
 

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

@@ -12,7 +12,7 @@ when_to_use: >-
   (superpowers:dispatching-parallel-agents, /security-review) points at one AND
   mmagent is running. Audit on PROSE/SPEC docs — use mma-review for source code.
   Audit a CODE-EXECUTION PLAN against the codebase — use subtype=plan.
-version: 4.4.0
+version: 4.5.0
 ---
 
 # mma-audit

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-debug / mma-investigate.
   Cheaper and faster than inlining the same content N times.
-version: 4.4.0
+version: 4.5.0
 ---
 
 # 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: 4.4.0
+version: 4.5.0
 ---
 
 # 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: 4.4.0
+version: 4.5.0
 ---
 
 # 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: 4.4.0
+version: 4.5.0
 ---
 
 # mma-execute-plan

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

@@ -12,7 +12,7 @@ when_to_use: >-
   out mma-investigate (internal) + mma-research (external) in parallel and
   synthesise the results yourself. DO NOT use for convergent single-answer
   questions — those are mma-investigate.
-version: 4.4.0
+version: 4.5.0
 ---
 
 # mma-explore

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: 4.4.0
+version: 4.5.0
 ---
 
 # mma-investigate

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

@@ -10,7 +10,7 @@ when_to_use: >-
   others do, what published methods exist) AND mmagent is running. Delegate the
   multi-source web/adapter research to a worker so the main context stays on
   judgment. NOT for codebase questions — those are mma-investigate.
-version: 4.4.0
+version: 4.5.0
 ---
 
 # mma-research

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

@@ -10,7 +10,7 @@ when_to_use: >-
   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: 4.4.0
+version: 4.5.0
 ---
 
 # 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: 4.4.0
+version: 4.5.0
 ---
 
 # mma-review

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: 4.4.0
+version: 4.5.0
 ---
 
 # multi-model-agent (router)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "4.4.0",
+  "version": "4.5.0",
   "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.",
@@ -53,7 +53,7 @@
   },
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^8.5.0",
-    "@zhixuan92/multi-model-agent-core": "^4.4.0",
+    "@zhixuan92/multi-model-agent-core": "^4.5.0",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "proper-lockfile": "^4.1.2",