@zhixuan92/multi-model-agent 3.1.3 → 3.1.5

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

@@ -10,7 +10,7 @@ when_to_use: >-
   (superpowers:dispatching-parallel-agents, /security-review) points at an audit
   task. Delegate via mmagent so the audit runs on independent workers — your
   main context stays free to synthesize findings.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-audit

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

@@ -9,7 +9,7 @@ when_to_use: >-
   terminal envelope has `proposedInterpretation` as a string (not a
   NotApplicable sentinel). Read the proposal and call this skill to accept or
   correct it. The batch resumes after the POST returns.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-clarifications

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

@@ -10,7 +10,7 @@ when_to_use: >-
   field on mma-delegate / mma-execute-plan / mma-audit / mma-review / mma-verify
   / mma-debug. Cheaper and faster than inlining the same content in every
   request body.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-context-blocks

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

@@ -10,7 +10,7 @@ when_to_use: >-
   (superpowers:systematic-debugging) points at the investigation step. Delegate
   the read/reproduce/trace work to a mmagent worker so your main context stays
   focused on the hypothesis and the fix.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-debug

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

@@ -11,7 +11,7 @@ when_to_use: >-
   parallel-safe, and keep main context free. If a plan file exists, use
   mma-execute-plan; if the task is an audit/review/verify/debug, prefer the
   matching mma-* skill instead.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-delegate

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

@@ -11,7 +11,7 @@ when_to_use: >-
   or superpowers:subagent-driven-development / superpowers:executing-plans when
   mmagent is running — delegated workers are cheaper and don't pollute main
   context. Task descriptors must match the plan headings verbatim.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-execute-plan

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

@@ -9,7 +9,7 @@ when_to_use: >-
   you want to re-try the failed indices only. Prefer this over redispatching the
   whole batch or inline-retrying — it's idempotent and keeps the original
   batch's diagnostics intact.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-retry

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

@@ -9,7 +9,7 @@ when_to_use: >-
   more files OR a methodology skill (superpowers:requesting-code-review,
   /review, /security-review) points at a review task. Delegate the reviewer pass
   to mmagent workers — your main context stays free to decide what to merge.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-review

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

@@ -8,7 +8,7 @@ when_to_use: >-
   superpowers:verification-before-completion) wants acceptance-criteria checked
   against implemented work. Delegate the evidence-gathering to mmagent workers —
   each checklist item is verified independently and in parallel.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## mma-verify

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

@@ -11,7 +11,7 @@ when_to_use: >-
   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 just asked directly.
-version: 3.1.3
+version: 3.1.5
 ---
 
 ## multi-model-agent overview
@@ -19,18 +19,24 @@ version: 3.1.3
 multi-model-agent is a local HTTP service that fans out tool-using work to
 sub-agents running on different LLM providers (Claude, OpenAI-compatible, Codex).
 
-### Setup check
+### Preflight: auto-start the daemon if it is not running
 
-```bash
-curl -s http://localhost:$PORT/health
-# expects: { "ok": true }
-```
+Before any mma-* call, check the server. If it is not up, start it in the background — do NOT run `mmagent serve` synchronously, it blocks forever.
 
-If this fails, start the server:
 ```bash
-mmagent serve
+PORT=7337
+if ! curl -sf "http://127.0.0.1:$PORT/health" >/dev/null 2>&1; then
+  mmagent serve >/dev/null 2>&1 &
+  disown
+  for _ in 1 2 3 4 5 6 7 8 9 10; do
+    sleep 0.5
+    curl -sf "http://127.0.0.1:$PORT/health" >/dev/null 2>&1 && break
+  done
+fi
 ```
 
+Idempotent: already-running daemon → curl succeeds → no-op.
+
 ### Auth token
 
 Set the token in your environment:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "3.1.3",
+  "version": "3.1.5",
   "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": "^3.1.0",
+    "@zhixuan92/multi-model-agent-core": "^3.1.5",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "zod": "^4.0.0"