@zhixuan92/multi-model-agent 4.0.6 → 4.2.0

package/README.md

@@ -121,7 +121,7 @@ Skills are the surface your AI client sees. `mmagent sync-skills` writes them to
 | `mma-research` | `POST /research` | External multi-source research with citations — arxiv, semantic_scholar, github_search, rss, brave-with-`site:`-filters — for a focused question. |
 | `mma-debug` | `POST /debug` | A test fails, a build breaks, or behavior is unexpected — delegate the reproduce/trace, keep the hypothesis on the main agent. |
 | `mma-review` | `POST /review` | Source-code review (pre-merge, post-implementation, security-focused). One worker per file, in parallel. |
-| `mma-audit` | `POST /audit` | Audit a prose document — spec, config, PR description — for correctness, security, or style. |
+| `mma-audit` | `POST /audit` | Audit a spec / plan / design doc / recommendation doc for executability blockers (contradictions, ambiguity, recommendation-coherence gaps). Default is the comprehensive sweep; `security` and `performance` are narrow opt-in lenses. |
 | `mma-verify` | `POST /verify` | Check acceptance criteria against finished work *before* claiming done. One worker per checklist item. |
 
 ### Plumbing skills

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

@@ -1,29 +1,31 @@
 ---
 name: mma-audit
 description: >-
-  Use when the user asks to audit a document, spec, config, or PR description
-  for security, correctness, performance, or style issues — and 2+ files need
-  independent audit passes
+  Use when the user asks to audit a spec, plan, design doc, recommendation doc,
+  or config — the audit checks whether a literal-following worker could execute
+  the artifact without ambiguity, contradiction, or missing context. Default is
+  the comprehensive sweep; narrow lenses (security/performance) exist for cases
+  that want only one dimension.
 when_to_use: >-
-  User asks for a doc/spec/config audit OR a methodology skill
+  User asks for a doc/spec/plan/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: 4.0.6
+version: 4.2.0
 ---
 
 # mma-audit
 
 ## Overview
 
-Send a document or set of files to workers for structured auditing. Each file is audited independently in parallel; per-file results are indexed by path in the terminal envelope.
+Send a spec, plan, design doc, or recommendation doc to a worker for structured auditing. The audit's purpose is to make the artifact **executable by a low-judgment worker** — meaning a sub-agent that follows instructions literally and cannot disambiguate. Findings target executability blockers: ambiguity, internal contradictions, unspecified branches, missing verification, overloaded terms, out-of-order steps.
 
 **Core principle:** One worker per file = no cross-file context pollution. The aggregator (you) decides what to do with the findings.
 
 ## When to Use
 
 **Use when:**
-- A spec / design doc / API contract / config file needs a critical read
-- The audit type is `security`, `performance`, `correctness`, or `style` (or a combination)
+- A spec, plan, design doc, recommendation doc, or post-mortem needs a critical read
+- The artifact will subsequently be executed by a worker (or any reader who follows it literally)
 - 2+ files would benefit from parallel audit
 
 **Don't use when:**
@@ -42,7 +44,7 @@ Send a document or set of files to workers for structured auditing. Each file is
 ```json
 {
   "document": "inline content to audit (optional if filePaths given)",
-  "auditType": "correctness",
+  "auditType": "default",
   "filePaths": ["/project/docs/spec.md"],
   "contextBlockIds": []
 }
@@ -51,7 +53,7 @@ Send a document or set of files to workers for structured auditing. Each file is
 | Field | Type | Required | Notes |
 |---|---|---|---|
 | `document` | string | no | Inline document content |
-| `auditType` | string \| string[] | yes | `security`, `performance`, `correctness`, `style`, or `general`; or an array of the first four |
+| `auditType` | `'default' \| 'security' \| 'performance'` | no (defaults to `'default'`) | See "Picking auditType" below — `default` is right for ~90% of audits |
 | `filePaths` | string[] | no | Files to audit (one worker per file, parallel) |
 | `contextBlockIds` | string[] | no | IDs from `mma-context-blocks` |
 
@@ -59,6 +61,16 @@ Either `document` or `filePaths` (or both) must be provided.
 
 > Worker tier for `mma-audit` is hardcoded to `complex` and is not caller-configurable. Sending `agentType` is rejected with HTTP 400.
 
+### Picking auditType
+
+| Value | When to use |
+|---|---|
+| `default` (or omit the field) | **Right answer for ~90% of audits.** Spec, plan, design doc, recommendation doc, post-mortem, audit, brief, README — any prose artifact. Sweeps the full executability + correctness + clarity taxonomy with security and performance lenses applied. |
+| `security` | Narrow opt-in. Use ONLY when you specifically want security findings and not general audit findings (e.g., a threat model where stylistic noise is unwanted). |
+| `performance` | Narrow opt-in. Use ONLY when you specifically want performance findings (e.g., a scaling design where you want hot-path / latency / unbounded-loop findings only). |
+
+The legacy values `correctness`, `style`, and `general` no longer exist — they were a false dichotomy. Sending any of them returns `400 invalid_request` with a hint to use `default`.
+
 ## Full example
 
 ```bash
@@ -67,7 +79,7 @@ BATCH=$(curl -f --show-error -s -X POST \
   -H "X-MMA-Client: $MMA_CLIENT" \
   -H "Authorization: Bearer $TOKEN" \
   -H "Content-Type: application/json" \
-  -d '{"auditType":"correctness","filePaths":["/project/docs/api-spec.md"]}' \
+  -d '{"auditType":"default","filePaths":["/project/docs/api-spec.md"]}' \
   "http://localhost:$PORT/audit?cwd=/project")
 BATCH_ID=$(echo "$BATCH" | jq -r '.batchId')
 ```
@@ -130,8 +142,8 @@ The auditor lacks codebase context (no type info, no call-site lookup, no test a
 ❌ **Single huge `document` string instead of `filePaths`**
 Inline docs lose the file boundary, so the per-file parallel split degenerates to one worker. **Fix:** save to disk first, pass `filePaths`.
 
-❌ **Asking for `auditType: "general"` when you mean something specific**
-`"general"` is a catch-all that produces watery findings. **Fix:** pick the dimension you actually care about (`"correctness"` for spec gaps, `"security"` for threat models, etc.).
+❌ **Sending legacy auditType values (`correctness`, `style`, `general`)**
+These were removed — they were a false dichotomy that biased workers toward stylistic proofreading on prose artifacts. **Fix:** use `default` (or omit the field). Use `security` or `performance` only when you specifically want a narrow lens.
 
 ❌ **Re-auditing the same files round after round without delta context**
 Round 2 worker has no idea what round 1 found. **Fix:** register the round 1 findings as a context block (`mma-context-blocks`) and pass `contextBlockIds` to round 2.

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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # mma-research

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: 4.0.6
+version: 4.2.0
 ---
 
 # mma-retry

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

@@ -10,16 +10,18 @@ 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: 4.0.6
+version: 4.2.0
 ---
 
 # mma-review
 
 ## Overview
 
-Send code files to workers for structured review. Each file is reviewed independently in parallel; results are index-aligned with `filePaths`.
+mma-review is the **pre-merge gate**. Send code files (or a diff) to a worker for structured review against an executability bar: would a maintainer who reads only the verdict and the diff understand which changes are required, why each is required, and where each lives — well enough to apply the fix and re-merge without re-investigating?
 
-**Core principle:** Reviewer is a different model from the implementer — different training, different blind spots. Cross-model review catches what self-review misses.
+Each file is reviewed independently in parallel; results are index-aligned with `filePaths`.
+
+**Core principle:** Reviewer is a different model from the implementer — different training, different blind spots. Cross-model review catches what self-review misses. The reviewer runs against a 10-category failure-mode taxonomy (test gap, cross-file ripple, missing edge case, race, resource leak, backward-compat break, security/performance regression, implicit-contract assumption, pre-existing-bug-vs-new-regression separation) and weighs every change through the security, performance, and correctness lenses regardless of `focus`.
 
 ## When to Use
 
@@ -34,6 +36,13 @@ Send code files to workers for structured review. Each file is reviewed independ
 - You want to know whether a complete branch is mergeable → run `/ultrareview` (multi-model branch review) instead
 - The diff is one-line / one-character → reading inline is faster than dispatch
 
+## How to invoke for cross-file ripple detection
+
+The cross-file ripple pass (changed-symbol → broken caller) only fires when the worker can identify what changed. Two patterns:
+
+- **Diff-as-input (preferred for cross-file ripple)**: pass the diff via the `code` field, plus the named files via `filePaths`. The worker treats the diff as the change-set and greps for callers of changed public symbols.
+- **Files-only (static review)**: pass only `filePaths`. The worker reviews the files in their current state without a change-set, so cross-file ripple is degenerate. Test gap, missing edge case, race, leak, and security/performance findings still fire.
+
 ## Endpoint
 
 `POST /review?cwd=<abs-path>`

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: 4.0.6
+version: 4.2.0
 ---
 
 # 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: 4.0.6
+version: 4.2.0
 ---
 
 # multi-model-agent (router)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zhixuan92/multi-model-agent",
-  "version": "4.0.6",
+  "version": "4.2.0",
   "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": "^4.0.6",
+    "@zhixuan92/multi-model-agent-core": "^4.2.0",
     "gray-matter": "^4.0.3",
     "minimist": "^1.2.8",
     "proper-lockfile": "^4.1.2",