@mushi-mushi/mcp 0.20.1 → 0.21.0

package/README.md

@@ -123,7 +123,7 @@ The server speaks stdio MCP transport by default; your client launches it as a s
 
 ### 5. Hosted Streamable HTTP (no subprocess)
 
-The Mushi backend now exposes the same tool catalog over the **Streamable HTTP** transport from the MCP 2025-03-26 spec at `/functions/v1/mcp`. Use this when you want to skip the local subprocess; typical for OpenAI Agents SDK, ChatGPT Agent, hosted CrewAI, or any orchestrator that talks remote MCP:
+The Mushi backend now exposes the same tool catalog over the **Streamable HTTP** transport (dual-era: MCP 2024-11-05 … 2025-11-25 legacy and the current 2026-07-28 revision) at `/functions/v1/mcp`. Use this when you want to skip the local subprocess; typical for OpenAI Agents SDK, ChatGPT Agent, hosted CrewAI, or any orchestrator that talks remote MCP:
 
 ```jsonc
 // .cursor/mcp.json — example (hosted HTTP)
@@ -146,7 +146,7 @@ The Mushi backend now exposes the same tool catalog over the **Streamable HTTP**
 
 ### Feature groups (`?features=` / `MUSHI_FEATURES`)
 
-Full catalog is **71 tools** (stdio / `MUSHI_FEATURES=all`). The hosted HTTP
+Full catalog is **73 tools** (stdio / `MUSHI_FEATURES=all`). The hosted HTTP
 endpoint exposes a leaner subset filtered by feature groups (see
 `mcp-hosted-tool-manifest.json`). New installs now default to the lean
 `triage,fixes,inventory,setup,docs` set automatically (stdio: when
@@ -212,6 +212,7 @@ The endpoint accepts JSON-RPC 2.0 over POST (returns `application/json` or `text
 | `get_blast_radius` | Graph traversal showing other components a bug group touches |
 | `get_knowledge_graph` | Traverse the knowledge graph from a seed component or page |
 | `diagnose_setup` | Setup health in one call: `mode=full` (default) runs ingest + dispatch preflight, `mode=ingest` / `mode=dispatch` narrow it. Returns the single best next action. Run first when a user says setup is broken |
+| `check_sdk_version` | Compare a published `@mushi-mushi/*` pin to `GET /v1/sdk/latest-version`. Returns `{ package, current, latest, outdated }` and, when outdated, Sentry-style `suggestedActions` (max 1). Does not bump the pin. |
 | `activation_status` | Unified activation posture for the active project: required steps, SDK heartbeat, dispatch preflight, and the next best action |
 | `get_report_timeline` | Ordered report timeline: the reporter/admin comment thread (including verify/reopen signals) plus fix, QA, and status lanes. Use when triaging whether an end user still sees a bug as unfixed |
 | `list_projects` | Discover all Mushi projects accessible to this API key. Returns project id, name, and created date |
@@ -390,7 +391,7 @@ Spawns `dist/index.js` with a dummy unreachable endpoint and confirms it adverti
 pnpm --filter @mushi-mushi/mcp build
 pnpm --filter @mushi-mushi/mcp test:smoke
 # OK; prints live tool/resource/prompt counts from the catalog
-# (see packages/mcp/src/catalog.ts — currently 71 tools / 8 resources / 4 prompts)
+# (see packages/mcp/src/catalog.ts — currently 73 tools / 8 resources / 4 prompts)
 ```
 
 ### Layer 3; Full localhost E2E (real binary + real backend behaviour)
@@ -480,8 +481,24 @@ Both are complementary; use Sentry for exception noise, Mushi for "the user says
 
 MIT
 
+## More from KENSAURUS
+
+| | App | What it is |
+|---|---|---|
+| <img src="https://kensaur.us/glot-it/icon-512.png" width="28" height="28" alt=""> | [Glot It](https://kensaur.us/glot-it/?utm_source=github&utm_medium=readme) | Learn Thai — bite-size lessons, smart flashcards, and an AI tutor |
+| <img src="https://kensaur.us/yen-yen/icon.svg" width="28" height="28" alt=""> | [yen-yen](https://kensaur.us/yen-yen/?utm_source=github&utm_medium=readme) | Where did the money go? Now you'll know. A kakeibo for households |
+| <img src="https://kensaur.us/the-wanting-mind/pwa-512x512.png" width="28" height="28" alt=""> | [The Wanting Mind](https://kensaur.us/the-wanting-mind/?utm_source=github&utm_medium=readme) | How the Battle Between Extraction and Generation Is Reshaping Our World — a 147,000-word interactive webbook with 268 concepts, 242 citations, and original illustrations |
+| <img src="https://kensaur.us/help-her-take-photo/assets/apple-touch-icon.png" width="28" height="28" alt=""> | [Help Her Take Photo](https://kensaur.us/help-her-take-photo/?utm_source=github&utm_medium=readme) | Pair phones, direct the pose, nail the photo |
+| <img src="https://talk.kensaur.us/pwa-192.png" width="28" height="28" alt=""> | [How to Talk to Girls](https://talk.kensaur.us/?utm_source=github&utm_medium=readme) | BYOK Claude practice coach for sticky chats |
+| <img src="https://solo-boss.kensaur.us/apple-touch-icon.png" width="28" height="28" alt=""> | [一人社長 Solo Boss](https://solo-boss.kensaur.us/?utm_source=github&utm_medium=readme) | Bookkeeping and tax-filing co-pilot for one-person companies in Japan |
+| <img src="https://tsumagoi.kensaur.us/apple-touch-icon.png" width="28" height="28" alt=""> | [Tsumagoi Work&Camp 嬬恋牧場](https://tsumagoi.kensaur.us/?utm_source=github&utm_medium=readme) | Coworking camp at 1,444 m — [Instagram](https://www.instagram.com/tsumagoicamp/) · [Facebook](https://www.facebook.com/profile.php?id=61592113053042) · [Maps](https://maps.app.goo.gl/JCNnTfsdQVHCS1FA7) |
+| <img src="https://github.com/kensaurus.png" width="28" height="28" alt=""> | [cursor-kenji](https://github.com/kensaurus/cursor-kenji) | Ready-made playbooks for your AI coding editor |
+| <img src="https://kensaur.us/favicon.svg" width="28" height="28" alt=""> | [KENSAURUS](https://kensaur.us/?view=portfolio&utm_source=github&utm_medium=readme) | Everything else built under the same roof |
+
+All apps live under [kensaur.us](https://kensaur.us).
+
 
 <!-- mushi-readme-stats-footer -->
 ---
 
-<sub>Monorepo scale (July 2026): 55 edge functions · 331 SQL migrations · 13 outbound plugins · 11 inbound adapters · 19 pipeline agents. Canonical counts: <a href="https://github.com/kensaurus/mushi-mushi/blob/master/docs/stats.md">docs/stats.md</a> · <code>pnpm docs-stats</code></sub>
+<sub>Monorepo scale (July 2026): 58 edge functions · 347 SQL migrations · 13 outbound plugins · 11 inbound adapters · 19 pipeline agents. Canonical counts: <a href="https://github.com/kensaurus/mushi-mushi/blob/master/docs/stats.md">docs/stats.md</a> · <code>pnpm docs-stats</code></sub>

package/dist/catalog.js

@@ -6,7 +6,7 @@ import {
   TDD_TOOL_CATALOG,
   TOOL_CATALOG,
   USE_MUSHI_INTENTS
-} from "./chunk-TP2QQWDJ.js";
+} from "./chunk-FNDGCFSJ.js";
 export {
   ALL_SCOPES,
   CODEBASE_TOOL_CATALOG,

package/dist/{chunk-TP2QQWDJ.js → chunk-FNDGCFSJ.js}

@@ -139,6 +139,14 @@ var TOOL_CATALOG = [
     hints: { readOnly: true, idempotent: true, openWorld: true },
     useCase: "Why is Mushi setup broken \u2014 one call, clear next step."
   },
+  {
+    name: "check_sdk_version",
+    title: "Check SDK freshness",
+    description: "Compare a published @mushi-mushi/* package version against the catalog (GET /v1/sdk/latest-version). Returns { package, current, latest, outdated } and, when outdated, suggestedActions (Sentry-style, max 1) pointing at search_mushi_docs plus the mushi-sdk-upgrade skill. Read-only. Use when Dependabot or mushi upgrade --check reports a drift, or before dispatching a fix that assumes a current SDK. Does not bump the pin \u2014 that stays a human/Dependabot change.",
+    scope: "mcp:read",
+    hints: { readOnly: true, idempotent: true, openWorld: true },
+    useCase: "Is this project on the current Mushi SDK?"
+  },
   {
     name: "search_mushi_docs",
     title: "Search Mushi documentation",
@@ -160,7 +168,7 @@ var TOOL_CATALOG = [
   {
     name: "dispatch_fix",
     title: "Dispatch Mushi fix agent",
-    description: 'Start a Mushi fix agent for a classified report; it writes a branch and opens a signed draft PR. Set agent="cursor_cloud" to dispatch a Cursor Cloud Agent (default uses the in-repo worker). Requires GitHub connected + an LLM key (run diagnose_setup mode=dispatch first). Returns { fixAttemptId }; poll get_fix_timeline for progress and merge_fix when CI is green. Write; NOT idempotent \u2014 each call starts a new attempt. Report must be classified \u2014 run triage_issue if not.',
+    description: 'Start a Mushi fix agent for a classified report; it writes a branch and opens a signed draft PR. Set agent="cursor_cloud" to dispatch a Cursor Cloud Agent (default uses the in-repo worker). Requires GitHub connected + an LLM key (run diagnose_setup mode=dispatch first). Returns { fixId, status } (fixId is the dispatch id; get_fix_timeline accepts it immediately); poll get_fix_timeline for progress and merge_fix when CI is green. Write; pass the same idempotencyKey to retry safely \u2014 without it each call starts a new attempt. Report must be classified \u2014 run triage_issue if not.',
     scope: "mcp:write",
     hints: { readOnly: false, destructive: false, idempotent: false, openWorld: true },
     useCase: "Let the in-repo agent attempt this fix for me (or: dispatch a Cursor Cloud Agent)."
@@ -295,6 +303,14 @@ var TOOL_CATALOG = [
     hints: { readOnly: true, idempotent: true, openWorld: true },
     useCase: "Analyze this bug report end-to-end and tell me what to do."
   },
+  {
+    name: "triage_next_steps",
+    title: "What should I work on now?",
+    description: 'Prioritised "do this next" list for the project: blocked auto-fixes first (with the unblock action), then in-flight fixes to shepherd to merge, then user-felt classified reports by severity, with robot/cron chores (dependency bumps) last. Returns { steps: [{ priority, action, reason, tool, args }], summary }. Read-only. Call this first when the user asks "what needs my attention / what should I triage or fix".',
+    scope: "mcp:read",
+    hints: { readOnly: true, idempotent: true, openWorld: true },
+    useCase: "What should I triage or fix right now?"
+  },
   // ── Lessons / evolution loop ─────────────────────────────────────────────
   {
     name: "query_lessons",
@@ -620,24 +636,29 @@ var TDD_TOOL_CATALOG = [
   }
 ];
 var USE_MUSHI_INTENTS = {
+  // NOTE: every name below MUST be a registered TOOL (scopes.test.ts guards
+  // this). 2026-08-16 audit P0-3 found phantom names (get_report,
+  // get_dashboard, list_qa_stories) and prompts listed as tools
+  // (summarize_report_for_fix, mushi_setup) — agents routed here then
+  // failed the call and gave up.
   fix: {
     label: "Fix a bug",
     tools: [
       "get_recent_reports",
-      "get_report",
-      "summarize_report_for_fix",
+      "get_report_detail",
+      "triage_issue",
       "dispatch_fix",
       "start_skill_pipeline",
       "checkin_pipeline_step",
       "get_pipeline_run"
     ],
-    hint: "Call get_recent_reports to find the top unresolved bug, then summarize_report_for_fix before dispatching."
+    hint: "Call get_recent_reports to find the top unresolved bug, then triage_issue before dispatching."
   },
   status: {
     label: "Check project status",
     tools: [
-      "get_dashboard",
       "triage_next_steps",
+      "get_account_overview",
       "get_usage",
       "get_backend_health",
       "activation_status"
@@ -647,7 +668,8 @@ var USE_MUSHI_INTENTS = {
   setup: {
     label: "Set up Mushi",
     tools: [
-      "mushi_setup",
+      "diagnose_setup",
+      "check_sdk_version",
       "activation_status",
       "get_backend_health",
       "list_byok_keys",
@@ -655,12 +677,11 @@ var USE_MUSHI_INTENTS = {
       "test_byok_key",
       "remove_byok_key"
     ],
-    hint: "Call mushi_setup first \u2014 it diagnoses setup gaps and returns the next command to run."
+    hint: "Call diagnose_setup first \u2014 it diagnoses setup gaps and returns the next action to take."
   },
   qa: {
     label: "Run / review QA tests",
     tools: [
-      "list_qa_stories",
       "run_qa_story",
       "list_qa_story_runs",
       "get_qa_story_run",
@@ -668,7 +689,7 @@ var USE_MUSHI_INTENTS = {
       "approve_qa_story",
       "improve_qa_story"
     ],
-    hint: "Call list_qa_stories to see what test coverage exists; run_qa_story to trigger a run."
+    hint: "Call list_qa_story_runs to see recent coverage and outcomes; run_qa_story to trigger a run."
   },
   pipeline: {
     label: "Run an agent pipeline / skill",
@@ -683,7 +704,7 @@ var USE_MUSHI_INTENTS = {
   },
   audit: {
     label: "Audit / health check",
-    tools: ["run_fullstack_audit", "get_backend_health", "get_dashboard", "get_usage"],
+    tools: ["run_fullstack_audit", "get_backend_health", "get_account_overview", "get_usage"],
     hint: "Call run_fullstack_audit for a full-stack health scorecard."
   }
 };

package/dist/{chunk-ZSVRLSW5.js → chunk-XSL2FPLV.js}

@@ -51,6 +51,7 @@ var TOOL_FEATURE_MAP = {
   inventory_current: "admin",
   // setup
   diagnose_setup: "setup",
+  check_sdk_version: "setup",
   activation_status: "setup",
   project_integration_health: "setup",
   setup_repo_for_mushi: "setup",

package/dist/clients.d.ts

@@ -46,7 +46,7 @@ import { FeatureGroup } from './feature-groups.js';
  * editor launch. Synced to package.json by `scripts/sync-mcp-pin.mjs` — never
  * hand-edit the version.
  */
-declare const MCP_PIN_SPEC = "@mushi-mushi/mcp@0.20.1";
+declare const MCP_PIN_SPEC = "@mushi-mushi/mcp@0.21.0";
 interface StdioConfig {
     command: string;
     args: string[];

package/dist/clients.js

@@ -5,10 +5,10 @@ import {
   DEFAULT_FEATURE_GROUPS,
   appendFeaturesToUrl,
   featuresQueryString
-} from "./chunk-ZSVRLSW5.js";
+} from "./chunk-XSL2FPLV.js";
 
 // src/clients.ts
-var MCP_PIN_SPEC = "@mushi-mushi/mcp@0.20.1";
+var MCP_PIN_SPEC = "@mushi-mushi/mcp@0.21.0";
 function projectServerName(projectId, projectName) {
   const nameSlug = projectName.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-|-$/g, "").slice(0, 22);
   const idSuffix = projectId.replace(/-/g, "").slice(0, 6);

package/dist/feature-groups.js

@@ -9,7 +9,7 @@ import {
   parseFeaturesCsv,
   parseFeaturesParam,
   toolMatchesFeatures
-} from "./chunk-ZSVRLSW5.js";
+} from "./chunk-XSL2FPLV.js";
 export {
   ALL_FEATURE_GROUPS,
   DEFAULT_FEATURE_GROUPS,