@mmerterden/multi-agent-toolkit-mcp 3.1.1 → 3.2.0

package/CHANGELOG.md

@@ -15,6 +15,20 @@ Releases before this file exists are recorded in the git tags and commit history
 
 ---
 
+## 3.2.0
+
+### Added
+
+- `ios_xcresult` gains `mode: "metrics"`: XCTMetric performance results straight
+  out of the `.xcresult` as JSON, via `xcresulttool get test-results metrics`.
+  The tool already shelled out to `xcresulttool` for `mode: "tests"`, so this is
+  a mode on an existing tool rather than a new integration, and Apple ships the
+  output's JSON Schema behind `--schema`, so the shape is documented rather than
+  inferred. Optional `test_id` scopes it to one case or suite.
+  Metrics exist only inside the bundle - there is no line in the build log to
+  fall back to - so a missing `.xcresult` returns an error instead of an empty
+  result that would read as "measured, nothing to report".
+
 ## 3.1.1
 
 ### Fixed

package/index.js

@@ -337,7 +337,7 @@ const IOS_TOOLS = [
   { name: "ios_testflight_validate", description: "Run Apple's own pre-submission validation on an .ipa via `xcrun altool --validate-app`, then map returned ITMS error codes onto the App Store rule each one implies. This is the authoritative gate: unlike the static ios_app_store_audit it can catch an unregistered bundle ID, a profile that does not match the App Store Connect app record, a version+build pair already used, and entitlements not provisioned for the app ID. Auth is a 3-tier chain: ASC API key (api_key_id + api_issuer_id), else Apple ID + app-specific password referenced indirectly through a keychain item or env var (never passed by value), else the gate returns verdict SKIPPED with a reason. SKIPPED is not a pass - it means Apple was never asked. Set list_providers=true for a pre-flight that reports which teams the credentials can deliver for (needed when a corporate Apple ID belongs to several).", inputSchema: { type: "object", properties: { ipa_path: { type: "string", description: "Absolute path to the .ipa" }, platform: { type: "string", description: "ios (default) | appletvos | visionos | macos" }, api_key_id: { type: "string", description: "App Store Connect API key ID (tier 1)" }, api_issuer_id: { type: "string", description: "App Store Connect issuer ID (tier 1)" }, p8_path: { type: "string", description: "Explicit path to AuthKey_<id>.p8; otherwise altool's search dirs are used" }, apple_id: { type: "string", description: "Apple ID (tier 2)" }, keychain_item: { type: "string", description: "Keychain item holding the app-specific password (tier 2, preferred)" }, password_env_var: { type: "string", description: "Env var holding the app-specific password (tier 2 fallback)" }, provider_public_id: { type: "string", description: "Required when the account belongs to multiple providers" }, list_providers: { type: "boolean", description: "Pre-flight only: list deliverable providers and return" }, timeout_sec: { type: "number", description: "Default 900" } }, required: [] } },
   { name: "ios_app_store_audit", description: "Deep App Store Review compliance audit for .xcarchive bundles. 18-rule catalog covering privacy manifest, code signing, embedded SDKs, entitlements, asset hygiene, IPv6 compliance, debug-tool leak detection, Swift ABI compatibility, SDK floor (ITMS-90725), and more. Returns structured JSON with severity-ranked violations and ITMS error code mappings. Replaces ios_archive_audit (deprecated). Pass rules='core' for the 6 baseline checks (code-signing, entitlements, info-plist, privacy-manifest, binary-size, sdk-floor); 'all'|'deep' for the full 18-rule scan; CSV like 'binary-size,ipv6-compliance' for an explicit subset.", inputSchema: { type: "object", properties: { archive_path: { type: "string", description: "Absolute path to the .xcarchive bundle" }, rules: { type: "string", description: "'all' (default) | 'core' | 'deep' | comma-separated ruleIDs" } }, required: ["archive_path"] } },
   { name: "ios_xcodebuild", description: "Build / test / clean an Xcode project with progressive disclosure. Returns one-line summary plus xcresult ID; drill in via ios_xcresult. Token-efficient - full log stays out of context unless requested.", inputSchema: { type: "object", properties: { project: { type: "string", description: "Path to .xcodeproj (mutually exclusive with workspace)" }, workspace: { type: "string", description: "Path to .xcworkspace (mutually exclusive with project)" }, scheme: { type: "string" }, configuration: { type: "string", description: "Debug / Release (default: Release)" }, destination: { type: "string", description: "Xcode destination string. Default: generic iOS Simulator" }, action: { type: "string", enum: ["build", "test", "clean", "archive", "clean-build"], description: "Default: build" }, derived_data_path: { type: "string" }, extra_args: { type: "string", description: "Additional raw xcodebuild args appended verbatim" }, timeout_sec: { type: "number", description: "Build timeout in seconds (default 600)" } }, required: ["scheme"] } },
-  { name: "ios_xcresult", description: "Drill into a previous ios_xcodebuild result by xcresult ID. Modes: summary (counts), errors (file:line + message), warnings, log (last N lines), tests (failed). Use this instead of dumping the whole build log into context.", inputSchema: { type: "object", properties: { id: { type: "string", description: "xcresult ID returned by ios_xcodebuild" }, mode: { type: "string", enum: ["summary", "errors", "warnings", "log", "tests"], description: "Default: summary" }, log_lines: { type: "number", description: "Lines of raw log to return when mode=log (default 200)" } }, required: ["id"] } },
+  { name: "ios_xcresult", description: "Drill into a previous ios_xcodebuild result by xcresult ID. Modes: summary (counts), errors (file:line + message), warnings, log (last N lines), tests (failed), metrics (XCTMetric performance results as JSON). Use this instead of dumping the whole build log into context.", inputSchema: { type: "object", properties: { id: { type: "string", description: "xcresult ID returned by ios_xcodebuild" }, mode: { type: "string", enum: ["summary", "errors", "warnings", "log", "tests", "metrics"], description: "Default: summary" }, log_lines: { type: "number", description: "Lines of raw log to return when mode=log (default 200)" }, test_id: { type: "string", description: "mode=metrics only: scope to one test case or suite instead of every measured test" } }, required: ["id"] } },
   { name: "ios_visual_diff", description: "Compare two PNG screenshots. Returns JSON with diff_pct, pass/fail vs threshold, and an optional diff image. Use for snapshot regression checks across light/dark, locale, dynamic type variants.", inputSchema: { type: "object", properties: { baseline: { type: "string", description: "Path to baseline PNG" }, current: { type: "string", description: "Path to current PNG" }, threshold: { type: "number", description: "Per-pixel color threshold 0..1 (default 0.1, lower = stricter)" }, max_diff_pct: { type: "number", description: "Fail if diff exceeds this percent (default 1.0)" }, output: { type: "string", description: "Path to write diff PNG (optional)" } }, required: ["baseline", "current"] } },
   { name: "ios_list_crashes", description: "List recent crash reports from the host's ~/Library/Logs/DiagnosticReports - where simulator app crashes land. Filter by process name, bound by age and count.", inputSchema: { type: "object", properties: { app: { type: "string", description: "Only reports whose file name (the crashed process) contains this substring" }, since_min: { type: "number", description: "Only reports newer than this many minutes" }, limit: { type: "number", description: "Max reports returned, newest first (default 20)" } } } },
 ];
@@ -731,6 +731,22 @@ async function handleIOS(name, args, ctx = {}) {
         const warns = (raw.match(/^.*warning:.*$/gim) || []).map(l => l.trim());
         return JSON.stringify({ id, count: warns.length, warnings: warns }, null, 2);
       }
+      if (mode === "metrics") {
+        // Performance results live only inside the .xcresult - there is no line
+        // in the text log to fall back to - so a missing bundle is an error, not
+        // an empty measurement. XCTMetric results land here only when the tests
+        // were built with performance diagnostics enabled.
+        if (!existsSync(xcresultPath)) {
+          return `ERROR: no .xcresult bundle for ${id} at ${xcresultPath}; performance metrics exist only in the bundle, not in the build log`;
+        }
+        const scope = args.test_id ? ` --test-id ${shq(args.test_id)}` : "";
+        const out = run(
+          `xcrun xcresulttool get test-results metrics --path ${shq(xcresultPath)}${scope} --compact 2>&1`,
+          { timeout: 20000 },
+        );
+        if (!out || out.startsWith("ERROR")) return out || `ERROR: xcresulttool returned nothing for ${id}`;
+        return out;
+      }
       if (mode === "tests") {
         if (existsSync(xcresultPath)) {
           const out = run(`xcrun xcresulttool get test-results tests --path ${shq(xcresultPath)} --format json 2>/dev/null`, { timeout: 20000 });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mmerterden/multi-agent-toolkit-mcp",
-  "version": "3.1.1",
+  "version": "3.2.0",
   "description": "MCP server for iOS Simulator, Android Emulator and headless web control. 84 tools: device automation (tap/swipe/type), accessibility audits, visual diff, crash logs, App Store / Play Store pre-submission compliance. Runs standalone over stdio with any MCP client.",
   "type": "module",
   "main": "index.js",