@zhixuan92/multi-model-agent 4.8.0 → 4.9.0

package/README.md

@@ -291,9 +291,9 @@ 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 4.7.20
+## What's new in 4.9.0
 
-- **`contextBlockId` on read-route results.** `GET /batch` per-task results from read routes (`audit` / `review` / `debug` / `investigate` / `research`) now carry a non-null `contextBlockId` — the sealed report auto-registered as a reusable context block. Pass it into a later call's `contextBlockIds` for delta follow-ups; write routes (`delegate` / `execute-plan` / `retry`) return `null`.
+- **Delegate skill passthrough.** `POST /delegate` tasks accept an optional `skills: string[]`. Each name is resolved from the caller's skill store (by `X-MMA-Client`), staged into an ephemeral per-task directory, and delivered natively — Claude workers via a local SDK plugin, Codex workers via an ephemeral `CODEX_HOME`. Unknown names hard-fail just that task; omitting `skills` is byte-for-byte the previous behavior.
 
 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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # mma-execute-plan

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

@@ -14,7 +14,7 @@ when_to_use: >-
   mma-journal-recall (prior learnings/decisions) in parallel and synthesise the
   results yourself. DO NOT use for convergent single-answer questions — those
   are mma-investigate.
-version: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # mma-investigate

package/dist/skills/mma-journal-recall/SKILL.md

@@ -12,7 +12,7 @@ when_to_use: >-
   A question about THIS project's learnings, before attempting or designing
   something — ask a vague conceptual question; skip if recording a new learning,
   asking the codebase, or researching external docs.
-version: 4.8.0
+version: 4.9.0
 ---
 
 # mma-journal-recall

package/dist/skills/mma-journal-record/SKILL.md

@@ -9,7 +9,7 @@ when_to_use: >-
   hit a blocking constraint, or reached a conclusion worth remembering. NOT for
   recall/investigate/delegate; those are read routes. Journal stores conclusions
   for cross-session reference.
-version: 4.8.0
+version: 4.9.0
 ---
 
 # mma-journal-record

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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # 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: 4.8.0
+version: 4.9.0
 ---
 
 # multi-model-agent (router)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "4.8.0",
+  "version": "4.9.0",
   "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.",
@@ -53,7 +53,7 @@
   },
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^8.5.0",
-    "@zhixuan92/multi-model-agent-core": "^4.8.0",
+    "@zhixuan92/multi-model-agent-core": "^4.9.0",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "proper-lockfile": "^4.1.2",