@zhixuan92/multi-model-agent 4.5.2 → 4.5.3

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":"4.5.2",...}
+curl -s http://localhost:7337/health   # → {"ok":true,"version":"4.5.3",...}
 ```
 
 For an always-on background install (survives reboots): [launchd / systemd templates](./scripts/README.md).
@@ -287,11 +287,9 @@ 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 4.5.2
+## What's new in 4.5.3
 
-- **Telemetry concernCount fix.** Every wire event since 4.4.0 silently emitted `concernCount: 0` and `findingsBySeverity: {0,0,0,0}` because the event-builder projected from the pre-v4.4 `runResult.concerns` field that the v4.4 lifecycle stopped populating. Now derives from `structuredReport.findings[]` (read-only routes — per-finding severity) and `structuredReport.reviewConcerns[]` (reviewed-write routes — defaults to medium). Live-verified: a real audit producing 21 findings now emits `concernCount: 21` on the wire.
-- **Removed pre-v4.4 LLM-annotator machinery (902 LOC).** The dead `AnnotatorEngine`, its parser, its prompt builder, the factory, the lifecycle plumbing, and the `runResult.annotatedFindings` / `parsedFindings` fields are gone. The pure-transform `lifecycle/handlers/annotator.ts` (already the live path since v4.4) stays; rubric templates the quality reviewer consumes also stay.
-- **BREAKING:** `AnnotatorEngine` and `AnnotatorRoute` public re-exports dropped from `@zhixuan92/multi-model-agent-core`. They were never wired into the run result in v4.4+, so external consumers would have produced no observable effect.
+- **Per-severity warehouse columns now populate on read-only routes.** Audit / review / debug / investigate hardcode `reviewPolicy: 'none'` and don't run an LLM reviewer, so the backend's `findings_critical / high / medium / low` columns (extracted from `stages[?name=review].findingsBySeverity`) stayed zero even when the worker produced dozens of findings. The event-builder now synthesizes a zero-metric v5 review stage entry with `verdict: 'annotated'` for these routes, carrying `findingsBySeverity` derived from `structuredReport.findings`. No schema change — uses existing v5 review-stage fields and the existing `'annotated'` enum value designed for this case. Backend extractor (`transformer.ts:115`) flows the buckets without any backend code change.
 
 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # 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: 4.5.2
+version: 4.5.3
 ---
 
 # multi-model-agent (router)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "4.5.2",
+  "version": "4.5.3",
   "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": "^4.5.2",
+    "@zhixuan92/multi-model-agent-core": "^4.5.3",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "proper-lockfile": "^4.1.2",