ur-agent 1.13.8 → 1.13.9

package/CHANGELOG.md

@@ -1,5 +1,40 @@
 # Changelog
 
+## 1.13.9
+
+### Added
+- **Spec-driven development (`ur spec`).** Scaffolds `requirements.md ->
+  design.md -> tasks.md` plus a phase/approval `spec.json` under `.ur/specs/`,
+  then drives execution task-by-task through a headless agent, checking off each
+  task on a PASS verdict. Tasks use the GitHub Spec Kit / Kiro `- [ ] T1: ...`
+  checkbox format, so lists are drop-in portable. `generate` can model-fill a
+  phase; scaffolding and task parsing stay pure and offline.
+- **In-loop model escalation / local Oracle (`ur escalate`).** Picks a fast tier
+  and a strong "oracle" tier from `ur model-doctor`, starts routine work on the
+  fast model, and auto-escalates hard reasoning/debug/review (or a failed cheap
+  attempt) to the oracle. `escalate oracle` gets a one-shot second opinion;
+  `escalate policy` pins tiers. Tier selection and difficulty scoring are
+  deterministic and testable.
+- **Multi-agent best-of-N judging (`ur arena`).** Runs N agents on the same task
+  in isolated git worktrees, judges the resulting diffs with the deterministic
+  self-review gate plus verdict/diff-shape heuristics, surfaces the winner, and
+  can `--apply` it. Local-first take on parallel-agent judging.
+- **Self-healing CI loop (`ur ci-loop`).** Runs a build/test command and, on
+  failure, summarizes the error, hands it to a fix agent, and re-runs with a
+  bounded retry budget; `--commit`/`--push` are gated by the self-review check so
+  a fix can never push secrets. `--from-log` seeds the first failure from a log.
+- **Verifiable artifacts surface (`ur artifacts`).** Records reviewable
+  deliverables (plans, diffs, test runs, screenshots) under `.ur/artifacts/`
+  with pending/approved/rejected status and threaded feedback; `capture-diff`
+  and `capture-tests` snapshot the working tree and test output for audit.
+
+### Verified
+- Added focused unit suites for escalation, arena judging, the spec workflow,
+  the CI loop, and artifacts (26 tests); rebuilt `dist/cli.js` and verified
+  typecheck, the full test suite, release check, package check, secret scan,
+  version output, npm publish dry-run, and direct CLI smoke tests for
+  `ur spec`, `ur arena`, and `ur escalate`.
+
 ## 1.13.8
 
 ### Fixed

package/README.md

@@ -99,6 +99,17 @@ ur mcp --help
 ur plugin --help
 ```
 
+Agent platform examples:
+
+```sh
+ur spec init demo --goal "1. add a utils.add function 2. add a test"
+ur spec run demo --all --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-diff
+```
+
 ## Documentation
 
 - [Usage Guide](docs/USAGE.md)

package/dist/cli.js

@@ -12685,7 +12685,7 @@ function formatAgentTrendReport(report = buildAgentTrendReport()) {
 function formatA2AAgentCard(options = {}, pretty = true) {
   return JSON.stringify(buildA2AAgentCard(options), null, pretty ? 2 : 0);
 }
-var urVersion = "1.13.8", coverage, priorityRoadmap;
+var urVersion = "1.13.9", coverage, priorityRoadmap;
 var init_trends = __esm(() => {
   coverage = [
     {
@@ -70342,7 +70342,7 @@ var init_auth = __esm(() => {
 
 // src/utils/userAgent.ts
 function getURCodeUserAgent() {
-  return `ur/${"1.13.8"}`;
+  return `ur/${"1.13.9"}`;
 }
 
 // src/utils/workloadContext.ts
@@ -70364,7 +70364,7 @@ function getUserAgent() {
   const clientApp = process.env.UR_AGENT_SDK_CLIENT_APP ? `, client-app/${process.env.UR_AGENT_SDK_CLIENT_APP}` : "";
   const workload = getWorkload();
   const workloadSuffix = workload ? `, workload/${workload}` : "";
-  return `ur-cli/${"1.13.8"} (${process.env.USER_TYPE}, ${process.env.UR_CODE_ENTRYPOINT ?? "cli"}${agentSdkVersion}${clientApp}${workloadSuffix})`;
+  return `ur-cli/${"1.13.9"} (${process.env.USER_TYPE}, ${process.env.UR_CODE_ENTRYPOINT ?? "cli"}${agentSdkVersion}${clientApp}${workloadSuffix})`;
 }
 function getMCPUserAgent() {
   const parts = [];
@@ -70378,7 +70378,7 @@ function getMCPUserAgent() {
     parts.push(`client-app/${process.env.UR_AGENT_SDK_CLIENT_APP}`);
   }
   const suffix = parts.length > 0 ? ` (${parts.join(", ")})` : "";
-  return `ur/${"1.13.8"}${suffix}`;
+  return `ur/${"1.13.9"}${suffix}`;
 }
 function getWebFetchUserAgent() {
   return `UR-User (${getURCodeUserAgent()})`;
@@ -70516,7 +70516,7 @@ var init_user = __esm(() => {
       deviceId,
       sessionId: getSessionId(),
       email: getEmail(),
-      appVersion: "1.13.8",
+      appVersion: "1.13.9",
       platform: getHostPlatformForAnalytics(),
       organizationUuid,
       accountUuid,
@@ -76293,7 +76293,7 @@ var init_metadata = __esm(() => {
   COMPOUND_OPERATOR_REGEX = /\s*(?:&&|\|\||[;|])\s*/;
   WHITESPACE_REGEX = /\s+/;
   getVersionBase = memoize_default(() => {
-    const match = "1.13.8".match(/^\d+\.\d+\.\d+(?:-[a-z]+)?/);
+    const match = "1.13.9".match(/^\d+\.\d+\.\d+(?:-[a-z]+)?/);
     return match ? match[0] : undefined;
   });
   buildEnvContext = memoize_default(async () => {
@@ -76333,7 +76333,7 @@ var init_metadata = __esm(() => {
       isGithubAction: isEnvTruthy(process.env.GITHUB_ACTIONS),
       isURCodeAction: isEnvTruthy(process.env.UR_CODE_ACTION),
       isURAiAuth: isURAISubscriber2(),
-      version: "1.13.8",
+      version: "1.13.9",
       versionBase: getVersionBase(),
       buildTime: "",
       deploymentEnvironment: env3.detectDeploymentEnvironment(),
@@ -77003,7 +77003,7 @@ function initialize1PEventLogging() {
   const platform2 = getPlatform();
   const attributes = {
     [import_semantic_conventions4.ATTR_SERVICE_NAME]: "ur",
-    [import_semantic_conventions4.ATTR_SERVICE_VERSION]: "1.13.8"
+    [import_semantic_conventions4.ATTR_SERVICE_VERSION]: "1.13.9"
   };
   if (platform2 === "wsl") {
     const wslVersion = getWslVersion();
@@ -77030,7 +77030,7 @@ function initialize1PEventLogging() {
       })
     ]
   });
-  firstPartyEventLogger = firstPartyEventLoggerProvider.getLogger("com.urhq.ur.events", "1.13.8");
+  firstPartyEventLogger = firstPartyEventLoggerProvider.getLogger("com.urhq.ur.events", "1.13.9");
 }
 async function reinitialize1PEventLoggingIfConfigChanged() {
   if (!is1PEventLoggingEnabled() || !firstPartyEventLoggerProvider) {
@@ -78894,7 +78894,7 @@ function getAttributionHeader(fingerprint) {
   if (!isAttributionHeaderEnabled()) {
     return "";
   }
-  const version2 = `${"1.13.8"}.${fingerprint}`;
+  const version2 = `${"1.13.9"}.${fingerprint}`;
   const entrypoint = process.env.UR_CODE_ENTRYPOINT ?? "unknown";
   const cch = "";
   const workload = getWorkload();
@@ -185523,7 +185523,7 @@ function getTelemetryAttributes() {
     attributes["session.id"] = sessionId;
   }
   if (shouldIncludeAttribute("OTEL_METRICS_INCLUDE_VERSION")) {
-    attributes["app.version"] = "1.13.8";
+    attributes["app.version"] = "1.13.9";
   }
   const oauthAccount = getOauthAccountInfo();
   if (oauthAccount) {
@@ -221312,7 +221312,7 @@ function getInstallationEnv() {
   return;
 }
 function getURCodeVersion() {
-  return "1.13.8";
+  return "1.13.9";
 }
 async function getInstalledVSCodeExtensionVersion(command) {
   const { stdout } = await execFileNoThrow(command, ["--list-extensions", "--show-versions"], {
@@ -224040,7 +224040,7 @@ async function setupSdkMcpClients(sdkMcpConfigs, sendMcpMessage) {
     const client2 = new Client({
       name: "ur",
       title: "UR",
-      version: "1.13.8",
+      version: "1.13.9",
       description: "URHQ's agentic coding tool",
       websiteUrl: PRODUCT_URL
     }, {
@@ -224394,7 +224394,7 @@ var init_client5 = __esm(() => {
       const client2 = new Client({
         name: "ur",
         title: "UR",
-        version: "1.13.8",
+        version: "1.13.9",
         description: "URHQ's agentic coding tool",
         websiteUrl: PRODUCT_URL
       }, {
@@ -234207,9 +234207,9 @@ async function assertMinVersion() {
   if (false) {}
   try {
     const versionConfig = await getDynamicConfig_BLOCKS_ON_INIT("tengu_version_config", { minVersion: "0.0.0" });
-    if (versionConfig.minVersion && lt("1.13.8", versionConfig.minVersion)) {
+    if (versionConfig.minVersion && lt("1.13.9", versionConfig.minVersion)) {
       console.error(`
-It looks like your version of UR (${"1.13.8"}) needs an update.
+It looks like your version of UR (${"1.13.9"}) needs an update.
 A newer version (${versionConfig.minVersion} or higher) is required to continue.
 
 To update, please run:
@@ -234425,7 +234425,7 @@ async function installGlobalPackage(specificVersion) {
     logError2(new AutoUpdaterError("Another process is currently installing an update"));
     logEvent("tengu_auto_updater_lock_contention", {
       pid: process.pid,
-      currentVersion: "1.13.8"
+      currentVersion: "1.13.9"
     });
     return "in_progress";
   }
@@ -234434,7 +234434,7 @@ async function installGlobalPackage(specificVersion) {
     if (!env3.isRunningWithBun() && env3.isNpmFromWindowsPath()) {
       logError2(new Error("Windows NPM detected in WSL environment"));
       logEvent("tengu_auto_updater_windows_npm_in_wsl", {
-        currentVersion: "1.13.8"
+        currentVersion: "1.13.9"
       });
       console.error(`
 Error: Windows NPM detected in WSL
@@ -234969,7 +234969,7 @@ function detectLinuxGlobPatternWarnings() {
 }
 async function getDoctorDiagnostic() {
   const installationType = await getCurrentInstallationType();
-  const version2 = typeof MACRO !== "undefined" ? "1.13.8" : "unknown";
+  const version2 = typeof MACRO !== "undefined" ? "1.13.9" : "unknown";
   const installationPath = await getInstallationPath();
   const invokedBinary = getInvokedBinary();
   const multipleInstallations = await detectMultipleInstallations();
@@ -235904,8 +235904,8 @@ async function updateLatest(channelOrVersion, forceReinstall = false) {
     const maxVersion = await getMaxVersion();
     if (maxVersion && gt(version2, maxVersion)) {
       logForDebugging(`Native installer: maxVersion ${maxVersion} is set, capping update from ${version2} to ${maxVersion}`);
-      if (gte("1.13.8", maxVersion)) {
-        logForDebugging(`Native installer: current version ${"1.13.8"} is already at or above maxVersion ${maxVersion}, skipping update`);
+      if (gte("1.13.9", maxVersion)) {
+        logForDebugging(`Native installer: current version ${"1.13.9"} is already at or above maxVersion ${maxVersion}, skipping update`);
         logEvent("tengu_native_update_skipped_max_version", {
           latency_ms: Date.now() - startTime,
           max_version: maxVersion,
@@ -235916,7 +235916,7 @@ async function updateLatest(channelOrVersion, forceReinstall = false) {
       version2 = maxVersion;
     }
   }
-  if (!forceReinstall && version2 === "1.13.8" && await versionIsAvailable(version2) && await isPossibleURBinary(executablePath)) {
+  if (!forceReinstall && version2 === "1.13.9" && await versionIsAvailable(version2) && await isPossibleURBinary(executablePath)) {
     logForDebugging(`Found ${version2} at ${executablePath}, skipping install`);
     logEvent("tengu_native_update_complete", {
       latency_ms: Date.now() - startTime,
@@ -330587,7 +330587,7 @@ function Feedback({
       platform: env3.platform,
       gitRepo: envInfo.isGit,
       terminal: env3.terminal,
-      version: "1.13.8",
+      version: "1.13.9",
       transcript: normalizeMessagesForAPI(messages),
       errors: sanitizedErrors,
       lastApiRequest: getLastAPIRequest(),
@@ -330779,7 +330779,7 @@ function Feedback({
                       ", ",
                       env3.terminal,
                       ", v",
-                      "1.13.8"
+                      "1.13.9"
                     ]
                   }, undefined, true, undefined, this)
                 ]
@@ -330885,7 +330885,7 @@ ${sanitizedDescription}
 ` + `**Environment Info**
 ` + `- Platform: ${env3.platform}
 ` + `- Terminal: ${env3.terminal}
-` + `- Version: ${"1.13.8"}
+` + `- Version: ${"1.13.9"}
 ` + `- Feedback ID: ${feedbackId}
 ` + `
 **Errors**
@@ -333995,7 +333995,7 @@ function buildPrimarySection() {
   }, undefined, false, undefined, this);
   return [{
     label: "Version",
-    value: "1.13.8"
+    value: "1.13.9"
   }, {
     label: "Session name",
     value: nameValue
@@ -337273,7 +337273,7 @@ function Config({
         }
       }, undefined, false, undefined, this)
     }, undefined, false, undefined, this) : showSubmenu === "ChannelDowngrade" ? /* @__PURE__ */ jsx_dev_runtime177.jsxDEV(ChannelDowngradeDialog, {
-      currentVersion: "1.13.8",
+      currentVersion: "1.13.9",
       onChoice: (choice) => {
         setShowSubmenu(null);
         setTabsHidden(false);
@@ -337285,7 +337285,7 @@ function Config({
           autoUpdatesChannel: "stable"
         };
         if (choice === "stay") {
-          newSettings.minimumVersion = "1.13.8";
+          newSettings.minimumVersion = "1.13.9";
         }
         updateSettingsForSource("userSettings", newSettings);
         setSettingsData((prev_27) => ({
@@ -345355,7 +345355,7 @@ function HelpV2(t0) {
   let t6;
   if ($3[31] !== tabs) {
     t6 = /* @__PURE__ */ jsx_dev_runtime204.jsxDEV(Tabs, {
-      title: `UR v${"1.13.8"}`,
+      title: `UR v${"1.13.9"}`,
       color: "professionalBlue",
       defaultTab: "general",
       children: tabs
@@ -364958,7 +364958,7 @@ function getAllReleaseNotes(changelogContent = getStoredChangelogFromMemory()) {
     return [];
   }
 }
-async function checkForReleaseNotes(lastSeenVersion, currentVersion = "1.13.8") {
+async function checkForReleaseNotes(lastSeenVersion, currentVersion = "1.13.9") {
   if (process.env.USER_TYPE === "ant") {
     const changelog = "";
     if (changelog) {
@@ -364985,7 +364985,7 @@ async function checkForReleaseNotes(lastSeenVersion, currentVersion = "1.13.8")
     releaseNotes
   };
 }
-function checkForReleaseNotesSync(lastSeenVersion, currentVersion = "1.13.8") {
+function checkForReleaseNotesSync(lastSeenVersion, currentVersion = "1.13.9") {
   if (process.env.USER_TYPE === "ant") {
     const changelog = "";
     if (changelog) {
@@ -366155,7 +366155,7 @@ function getRecentActivitySync() {
   return cachedActivity;
 }
 function getLogoDisplayData() {
-  const version2 = process.env.DEMO_VERSION ?? "1.13.8";
+  const version2 = process.env.DEMO_VERSION ?? "1.13.9";
   const serverUrl = getDirectConnectServerUrl();
   const displayPath = process.env.DEMO_VERSION ? "/code/ur" : getDisplayPath(getCwd());
   const cwd2 = serverUrl ? `${displayPath} in ${serverUrl.replace(/^https?:\/\//, "")}` : displayPath;
@@ -366944,7 +366944,7 @@ function LogoV2() {
   if ($3[2] === Symbol.for("react.memo_cache_sentinel")) {
     t2 = () => {
       const currentConfig = getGlobalConfig();
-      if (currentConfig.lastReleaseNotesSeen === "1.13.8") {
+      if (currentConfig.lastReleaseNotesSeen === "1.13.9") {
         return;
       }
       saveGlobalConfig(_temp326);
@@ -367629,12 +367629,12 @@ function LogoV2() {
   return t41;
 }
 function _temp326(current) {
-  if (current.lastReleaseNotesSeen === "1.13.8") {
+  if (current.lastReleaseNotesSeen === "1.13.9") {
     return current;
   }
   return {
     ...current,
-    lastReleaseNotesSeen: "1.13.8"
+    lastReleaseNotesSeen: "1.13.9"
   };
 }
 function _temp243(s_0) {
@@ -388944,7 +388944,7 @@ function assessDifficulty(task) {
     signals2.push(`${route2.category} task`);
   }
   if (HARD_KEYWORDS.test(task)) {
-    score += 4;
+    score += 5;
     signals2.push("hard-reasoning keywords");
   }
   if (task.length > 600) {
@@ -388957,7 +388957,16 @@ function planEscalation(task, models, policy = {}) {
   const tiers = selectTiers(models, policy);
   const difficulty = assessDifficulty(task);
   const startTier = difficulty.hard && tiers.oracle ? "oracle" : "fast";
-  const rationale = difficulty.hard ? `Hard task (${difficulty.signals.join(", ") || "flagged"}): start on the oracle.` : `Routine task: start on the fast model${tiers.sameModel ? "" : "; escalate to the oracle only if it fails"}.`;
+  let rationale;
+  if (!tiers.fast && !tiers.oracle) {
+    rationale = "No local models available; start Ollama or pull a model.";
+  } else if (startTier === "oracle") {
+    rationale = `Hard task (${difficulty.signals.join(", ") || "flagged"}): start on the oracle.`;
+  } else if (difficulty.hard) {
+    rationale = `Hard task, but no separate oracle is available: running on ${tiers.fast}.`;
+  } else {
+    rationale = `Routine task: start on the fast model${tiers.sameModel ? "" : "; escalate to the oracle only if it fails"}.`;
+  }
   return { task: task.trim(), tiers, difficulty, startTier, rationale };
 }
 function needsEscalation(output) {
@@ -389204,7 +389213,6 @@ var init_escalate2 = __esm(() => {
   escalate = {
     type: "local",
     name: "escalate",
-    aliases: ["oracle"],
     description: 'Capability-aware local model escalation: run on a fast model and auto-escalate hard work to a strong "oracle" model',
     argumentHint: 'plan|run|oracle|policy "<task>" [--dry-run] [--force-oracle] [--fast m] [--oracle m] [--json]',
     supportsNonInteractive: true,
@@ -389771,8 +389779,8 @@ async function captureDiff2(cwd2, title = "Working tree diff", exec5 = defaultEx
   });
 }
 async function captureTestRun(cwd2, command5, exec5 = defaultExec2) {
-  const parts = command5.trim().split(/\s+/);
-  const run = await exec5(parts[0], parts.slice(1), cwd2);
+  const parts = (command5.trim().match(/(?:[^\s"']+|"[^"]*"|'[^']*')+/g) ?? []).map((p2) => p2.replace(/^["']|["']$/g, ""));
+  const run = await exec5(parts[0] ?? "", parts.slice(1), cwd2);
   return recordArtifact(cwd2, {
     kind: "test-run",
     title: `Test run: ${command5}`,
@@ -406101,7 +406109,7 @@ async function captureMemoryDiagnostics(trigger2, dumpNumber = 0) {
     smapsRollup,
     platform: process.platform,
     nodeVersion: process.version,
-    ccVersion: "1.13.8"
+    ccVersion: "1.13.9"
   };
 }
 async function performHeapDump(trigger2 = "manual", dumpNumber = 0) {
@@ -406687,7 +406695,7 @@ var init_bridge_kick = __esm(() => {
 var call121 = async () => {
   return {
     type: "text",
-    value: "1.13.8"
+    value: "1.13.9"
   };
 }, version2, version_default;
 var init_version = __esm(() => {
@@ -415742,7 +415750,7 @@ function generateHtmlReport(data, insights) {
 </html>`;
 }
 function buildExportData(data, insights, facets, remoteStats) {
-  const version3 = typeof MACRO !== "undefined" ? "1.13.8" : "unknown";
+  const version3 = typeof MACRO !== "undefined" ? "1.13.9" : "unknown";
   const remote_hosts_collected = remoteStats?.hosts.filter((h2) => h2.sessionCount > 0).map((h2) => h2.name);
   const facets_summary = {
     total: facets.size,
@@ -419985,7 +419993,7 @@ var init_sessionStorage = __esm(() => {
   init_settings2();
   init_slowOperations();
   init_uuid();
-  VERSION5 = typeof MACRO !== "undefined" ? "1.13.8" : "unknown";
+  VERSION5 = typeof MACRO !== "undefined" ? "1.13.9" : "unknown";
   MAX_TOMBSTONE_REWRITE_BYTES = 50 * 1024 * 1024;
   SKIP_FIRST_PROMPT_PATTERN = /^(?:\s*<[a-z][\w-]*[\s>]|\[Request interrupted by user[^\]]*\])/;
   EPHEMERAL_PROGRESS_TYPES = new Set([
@@ -421190,7 +421198,7 @@ var init_filesystem = __esm(() => {
   });
   getBundledSkillsRoot = memoize_default(function getBundledSkillsRoot2() {
     const nonce = randomBytes18(16).toString("hex");
-    return join170(getURTempDir(), "bundled-skills", "1.13.8", nonce);
+    return join170(getURTempDir(), "bundled-skills", "1.13.9", nonce);
   });
   getResolvedWorkingDirPaths = memoize_default(getPathsForPermissionCheck);
 });
@@ -427221,7 +427229,7 @@ function computeFingerprint(messageText, version3) {
 }
 function computeFingerprintFromMessages(messages) {
   const firstMessageText = extractFirstMessageText(messages);
-  return computeFingerprint(firstMessageText, "1.13.8");
+  return computeFingerprint(firstMessageText, "1.13.9");
 }
 var FINGERPRINT_SALT = "59cf53e54c78";
 var init_fingerprint = () => {};
@@ -429087,7 +429095,7 @@ async function sideQuery(opts) {
     betas.push(STRUCTURED_OUTPUTS_BETA_HEADER);
   }
   const messageText = extractFirstUserMessageText(messages);
-  const fingerprint = computeFingerprint(messageText, "1.13.8");
+  const fingerprint = computeFingerprint(messageText, "1.13.9");
   const attributionHeader = getAttributionHeader(fingerprint);
   const systemBlocks = [
     attributionHeader ? { type: "text", text: attributionHeader } : null,
@@ -433824,7 +433832,7 @@ function buildSystemInitMessage(inputs) {
     slash_commands: inputs.commands.filter((c4) => c4.userInvocable !== false).map((c4) => c4.name),
     apiKeySource: getURHQApiKeyWithSource().source,
     betas: getSdkBetas(),
-    ur_version: "1.13.8",
+    ur_version: "1.13.9",
     output_style: outputStyle2,
     agents: inputs.agents.map((agent) => agent.agentType),
     skills: inputs.skills.filter((s) => s.userInvocable !== false).map((skill) => skill.name),
@@ -448452,7 +448460,7 @@ var init_useVoiceEnabled = __esm(() => {
 function getSemverPart(version3) {
   return `${import_semver13.major(version3, { loose: true })}.${import_semver13.minor(version3, { loose: true })}.${import_semver13.patch(version3, { loose: true })}`;
 }
-function useUpdateNotification(updatedVersion, initialVersion = "1.13.8") {
+function useUpdateNotification(updatedVersion, initialVersion = "1.13.9") {
   const [lastNotifiedSemver, setLastNotifiedSemver] = import_react224.useState(() => getSemverPart(initialVersion));
   if (!updatedVersion) {
     return null;
@@ -448501,7 +448509,7 @@ function AutoUpdater({
       return;
     }
     if (false) {}
-    const currentVersion = "1.13.8";
+    const currentVersion = "1.13.9";
     const channel = getInitialSettings()?.autoUpdatesChannel ?? "latest";
     let latestVersion = await getLatestVersion(channel);
     const isDisabled = isAutoUpdaterDisabled();
@@ -448730,12 +448738,12 @@ function NativeAutoUpdater({
     logEvent("tengu_native_auto_updater_start", {});
     try {
       const maxVersion = await getMaxVersion();
-      if (maxVersion && gt("1.13.8", maxVersion)) {
+      if (maxVersion && gt("1.13.9", maxVersion)) {
         const msg = await getMaxVersionMessage();
         setMaxVersionIssue(msg ?? "affects your version");
       }
       const result = await installLatest(channel);
-      const currentVersion = "1.13.8";
+      const currentVersion = "1.13.9";
       const latencyMs = Date.now() - startTime;
       if (result.lockFailed) {
         logEvent("tengu_native_auto_updater_lock_contention", {
@@ -448872,17 +448880,17 @@ function PackageManagerAutoUpdater(t0) {
       const maxVersion = await getMaxVersion();
       if (maxVersion && latest && gt(latest, maxVersion)) {
         logForDebugging(`PackageManagerAutoUpdater: maxVersion ${maxVersion} is set, capping update from ${latest} to ${maxVersion}`);
-        if (gte("1.13.8", maxVersion)) {
-          logForDebugging(`PackageManagerAutoUpdater: current version ${"1.13.8"} is already at or above maxVersion ${maxVersion}, skipping update`);
+        if (gte("1.13.9", maxVersion)) {
+          logForDebugging(`PackageManagerAutoUpdater: current version ${"1.13.9"} is already at or above maxVersion ${maxVersion}, skipping update`);
           setUpdateAvailable(false);
           return;
         }
         latest = maxVersion;
       }
-      const hasUpdate = latest && !gte("1.13.8", latest) && !shouldSkipVersion(latest);
+      const hasUpdate = latest && !gte("1.13.9", latest) && !shouldSkipVersion(latest);
       setUpdateAvailable(!!hasUpdate);
       if (hasUpdate) {
-        logForDebugging(`PackageManagerAutoUpdater: Update available ${"1.13.8"} -> ${latest}`);
+        logForDebugging(`PackageManagerAutoUpdater: Update available ${"1.13.9"} -> ${latest}`);
       }
     };
     $3[0] = t1;
@@ -448916,7 +448924,7 @@ function PackageManagerAutoUpdater(t0) {
       wrap: "truncate",
       children: [
         "currentVersion: ",
-        "1.13.8"
+        "1.13.9"
       ]
     }, undefined, true, undefined, this);
     $3[3] = verbose;
@@ -461278,7 +461286,7 @@ function buildStatusLineCommandInput(permissionMode, exceeds200kTokens, settings
       project_dir: getOriginalCwd(),
       added_dirs: addedDirs
     },
-    version: "1.13.8",
+    version: "1.13.9",
     output_style: {
       name: outputStyleName
     },
@@ -472774,7 +472782,7 @@ async function submitTranscriptShare(messages, trigger2, appearanceId) {
     } catch {}
     const data = {
       trigger: trigger2,
-      version: "1.13.8",
+      version: "1.13.9",
       platform: process.platform,
       transcript,
       subagentTranscripts: Object.keys(subagentTranscripts).length > 0 ? subagentTranscripts : undefined,
@@ -484689,7 +484697,7 @@ function WelcomeV2() {
             dimColor: true,
             children: [
               "v",
-              "1.13.8"
+              "1.13.9"
             ]
           }, undefined, true, undefined, this)
         ]
@@ -485949,7 +485957,7 @@ function completeOnboarding() {
   saveGlobalConfig((current) => ({
     ...current,
     hasCompletedOnboarding: true,
-    lastOnboardingVersion: "1.13.8"
+    lastOnboardingVersion: "1.13.9"
   }));
 }
 function showDialog(root2, renderer) {
@@ -490409,7 +490417,7 @@ function appendToLog(path24, message) {
     cwd: getFsImplementation().cwd(),
     userType: process.env.USER_TYPE,
     sessionId: getSessionId(),
-    version: "1.13.8"
+    version: "1.13.9"
   };
   getLogWriter(path24).write(messageWithTimestamp);
 }
@@ -494435,8 +494443,8 @@ async function getEnvLessBridgeConfig() {
 }
 async function checkEnvLessBridgeMinVersion() {
   const cfg = await getEnvLessBridgeConfig();
-  if (cfg.min_version && lt("1.13.8", cfg.min_version)) {
-    return `Your version of UR (${"1.13.8"}) is too old for Remote Control.
+  if (cfg.min_version && lt("1.13.9", cfg.min_version)) {
+    return `Your version of UR (${"1.13.9"}) is too old for Remote Control.
 Version ${cfg.min_version} or higher is required. Run \`ur update\` to update.`;
   }
   return null;
@@ -494910,7 +494918,7 @@ async function initBridgeCore(params) {
   const rawApi = createBridgeApiClient({
     baseUrl,
     getAccessToken,
-    runnerVersion: "1.13.8",
+    runnerVersion: "1.13.9",
     onDebug: logForDebugging,
     onAuth401,
     getTrustedDeviceToken
@@ -500575,7 +500583,7 @@ async function startMCPServer(cwd3, debug2, verbose) {
   setCwd(cwd3);
   const server = new Server({
     name: "ur/tengu",
-    version: "1.13.8"
+    version: "1.13.9"
   }, {
     capabilities: {
       tools: {}
@@ -502186,7 +502194,7 @@ __export(exports_update, {
 });
 async function update() {
   logEvent("tengu_update_check", {});
-  writeToStdout(`Current version: ${"1.13.8"}
+  writeToStdout(`Current version: ${"1.13.9"}
 `);
   const channel = getInitialSettings()?.autoUpdatesChannel ?? "latest";
   writeToStdout(`Checking for updates to ${channel} version...
@@ -502261,8 +502269,8 @@ async function update() {
       writeToStdout(`UR is managed by Homebrew.
 `);
       const latest = await getLatestVersion(channel);
-      if (latest && !gte("1.13.8", latest)) {
-        writeToStdout(`${formatUpdateAvailableMessage("1.13.8", latest)}
+      if (latest && !gte("1.13.9", latest)) {
+        writeToStdout(`${formatUpdateAvailableMessage("1.13.9", latest)}
 `);
         writeToStdout(`
 `);
@@ -502278,8 +502286,8 @@ async function update() {
       writeToStdout(`UR is managed by winget.
 `);
       const latest = await getLatestVersion(channel);
-      if (latest && !gte("1.13.8", latest)) {
-        writeToStdout(`${formatUpdateAvailableMessage("1.13.8", latest)}
+      if (latest && !gte("1.13.9", latest)) {
+        writeToStdout(`${formatUpdateAvailableMessage("1.13.9", latest)}
 `);
         writeToStdout(`
 `);
@@ -502295,8 +502303,8 @@ async function update() {
       writeToStdout(`UR is managed by apk.
 `);
       const latest = await getLatestVersion(channel);
-      if (latest && !gte("1.13.8", latest)) {
-        writeToStdout(`${formatUpdateAvailableMessage("1.13.8", latest)}
+      if (latest && !gte("1.13.9", latest)) {
+        writeToStdout(`${formatUpdateAvailableMessage("1.13.9", latest)}
 `);
         writeToStdout(`
 `);
@@ -502361,11 +502369,11 @@ async function update() {
 `);
         await gracefulShutdown(1);
       }
-      if (result.latestVersion === "1.13.8") {
-        writeToStdout(source_default.green(`UR is up to date (${"1.13.8"})`) + `
+      if (result.latestVersion === "1.13.9") {
+        writeToStdout(source_default.green(`UR is up to date (${"1.13.9"})`) + `
 `);
       } else {
-        writeToStdout(source_default.green(`Successfully updated from ${"1.13.8"} to version ${result.latestVersion}`) + `
+        writeToStdout(source_default.green(`Successfully updated from ${"1.13.9"} to version ${result.latestVersion}`) + `
 `);
         await regenerateCompletionCache();
       }
@@ -502425,12 +502433,12 @@ async function update() {
 `);
     await gracefulShutdown(1);
   }
-  if (latestVersion === "1.13.8") {
-    writeToStdout(source_default.green(`UR is up to date (${"1.13.8"})`) + `
+  if (latestVersion === "1.13.9") {
+    writeToStdout(source_default.green(`UR is up to date (${"1.13.9"})`) + `
 `);
     await gracefulShutdown(0);
   }
-  writeToStdout(`${formatUpdateAvailableMessage("1.13.8", latestVersion)}
+  writeToStdout(`${formatUpdateAvailableMessage("1.13.9", latestVersion)}
 `);
   writeToStdout(`Installing update...
 `);
@@ -502475,7 +502483,7 @@ async function update() {
   logForDebugging(`update: Installation status: ${status2}`);
   switch (status2) {
     case "success":
-      writeToStdout(source_default.green(`Successfully updated from ${"1.13.8"} to version ${latestVersion}`) + `
+      writeToStdout(source_default.green(`Successfully updated from ${"1.13.9"} to version ${latestVersion}`) + `
 `);
       await regenerateCompletionCache();
       break;
@@ -503726,7 +503734,7 @@ ${customInstructions}` : customInstructions;
       }
     }
     logForDiagnosticsNoPII("info", "started", {
-      version: "1.13.8",
+      version: "1.13.9",
       is_native_binary: isInBundledMode()
     });
     registerCleanup(async () => {
@@ -504510,7 +504518,7 @@ Usage: ur --remote "your task description"`, () => gracefulShutdown(1));
         pendingHookMessages
       }, renderAndRun);
     }
-  }).version("1.13.8 (Ur)", "-v, --version", "Output the version number");
+  }).version("1.13.9 (Ur)", "-v, --version", "Output the version number");
   program2.option("-w, --worktree [name]", "Create a new git worktree for this session (optionally specify a name)");
   program2.option("--tmux", "Create a tmux session for the worktree (requires --worktree). Uses iTerm2 native panes when available; use --tmux=classic for traditional tmux.");
   if (canUserConfigureAdvisor()) {
@@ -504799,6 +504807,26 @@ Usage: ur --remote "your task description"`, () => gracefulShutdown(1));
     const args = [action2, name, opts.objective ? `--objective ${quoteLocalCommandArg(opts.objective)}` : undefined, opts.workflow ? `--workflow ${quoteLocalCommandArg(opts.workflow)}` : undefined, opts.pattern ? `--pattern ${quoteLocalCommandArg(opts.pattern)}` : undefined, opts.note ? `--note ${quoteLocalCommandArg(opts.note)}` : undefined, opts.maxTurns ? `--max-turns ${opts.maxTurns}` : undefined, opts.dryRun ? "--dry-run" : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
     await runLocalTextCommand(() => Promise.resolve().then(() => (init_goal(), exports_goal)), args);
   });
+  program2.command("spec [action] [name] [phase]").alias("specs").description("Spec-driven development: scaffold requirements/design/tasks in .ur/specs and drive execution task-by-task").option("--goal <text>", "Goal text for init").option("--all", "Run all open tasks, not just the next one").option("--dry-run", "Run offline without calling any model").option("--max-turns <n>", "Max agentic turns per task when running").option("--skip-permissions", "Pass --dangerously-skip-permissions to each task (sandboxes only)").option("--json", "Output as JSON").action(async (action2, name, phase, opts) => {
+    const args = [action2, name, phase, opts.goal ? `--goal ${quoteLocalCommandArg(opts.goal)}` : undefined, opts.all ? "--all" : undefined, opts.dryRun ? "--dry-run" : undefined, opts.maxTurns ? `--max-turns ${opts.maxTurns}` : undefined, opts.skipPermissions ? "--skip-permissions" : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
+    await runLocalTextCommand(() => Promise.resolve().then(() => (init_spec2(), exports_spec)), args);
+  });
+  program2.command("escalate [action] [task...]").description("Capability-aware local model escalation: run on a fast model and auto-escalate hard work to the oracle").option("--dry-run", "Run offline without calling any model").option("--force-oracle", "Start on the oracle regardless of difficulty").option("--fast <model>", "Pin the fast-tier model (policy)").option("--oracle <model>", "Pin the oracle-tier model (policy)").option("--auto <onoff>", "Enable/disable auto-escalation (policy): on|off").option("--max-turns <n>", "Max agentic turns when running").option("--skip-permissions", "Pass --dangerously-skip-permissions (sandboxes only)").option("--json", "Output as JSON").action(async (action2, task = [], opts) => {
+    const args = [action2, ...task, opts.dryRun ? "--dry-run" : undefined, opts.forceOracle ? "--force-oracle" : undefined, opts.fast ? `--fast ${quoteLocalCommandArg(opts.fast)}` : undefined, opts.oracle ? `--oracle ${quoteLocalCommandArg(opts.oracle)}` : undefined, opts.auto ? `--auto ${quoteLocalCommandArg(opts.auto)}` : undefined, opts.maxTurns ? `--max-turns ${opts.maxTurns}` : undefined, opts.skipPermissions ? "--skip-permissions" : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
+    await runLocalTextCommand(() => Promise.resolve().then(() => (init_escalate(), exports_escalate)), args);
+  });
+  program2.command("arena [task...]").alias("best-of").description("Run N agents on the same task in isolated worktrees, judge the diffs, and surface the winner").option("--agents <n>", "Number of competing agents (default 3)").option("--models <list>", "Comma-separated per-agent models").option("--apply", "Apply the winning diff to the working tree").option("--keep", "Keep the candidate worktrees after judging").option("--dry-run", "Run offline without calling any model").option("--max-turns <n>", "Max agentic turns per agent").option("--skip-permissions", "Pass --dangerously-skip-permissions to each agent (sandboxes only)").option("--json", "Output as JSON").action(async (task = [], opts) => {
+    const args = [...task, opts.agents ? `--agents ${opts.agents}` : undefined, opts.models ? `--models ${quoteLocalCommandArg(opts.models)}` : undefined, opts.apply ? "--apply" : undefined, opts.keep ? "--keep" : undefined, opts.dryRun ? "--dry-run" : undefined, opts.maxTurns ? `--max-turns ${opts.maxTurns}` : undefined, opts.skipPermissions ? "--skip-permissions" : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
+    await runLocalTextCommand(() => Promise.resolve().then(() => (init_arena2(), exports_arena)), args);
+  });
+  program2.command("ci-loop").alias("heal").description("Self-healing CI: run a build/test command and, on failure, capture the error, fix it, and re-run with bounded retries").option("--command <cmd>", 'Command to run (default "bun test")').option("--max-attempts <n>", "Maximum fix attempts (default 3)").option("--from-log <path>", "Seed the first failure from an existing log file").option("--commit", "Commit each fix (self-review gated)").option("--push", "Commit and push each fix").option("--dry-run", "Show the plan without running").option("--skip-permissions", "Pass --dangerously-skip-permissions to the fix agent (sandboxes only)").option("--max-turns <n>", "Max agentic turns for the fix agent").option("--json", "Output as JSON").action(async (opts) => {
+    const args = [opts.command ? `--command ${quoteLocalCommandArg(opts.command)}` : undefined, opts.maxAttempts ? `--max-attempts ${opts.maxAttempts}` : undefined, opts.fromLog ? `--from-log ${quoteLocalCommandArg(opts.fromLog)}` : undefined, opts.commit ? "--commit" : undefined, opts.push ? "--push" : undefined, opts.dryRun ? "--dry-run" : undefined, opts.skipPermissions ? "--skip-permissions" : undefined, opts.maxTurns ? `--max-turns ${opts.maxTurns}` : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
+    await runLocalTextCommand(() => Promise.resolve().then(() => (init_ci_loop(), exports_ci_loop)), args);
+  });
+  program2.command("artifacts [action] [id]").alias("artifact").description("Reviewable deliverables (plans, diffs, test runs) with approve/reject/feedback under .ur/artifacts").option("--kind <kind>", "Artifact kind: plan|diff|test-run|screenshot|browser-recording|note").option("--title <text>", "Artifact title").option("--body <text>", "Inline artifact body").option("--file <path>", "Attach an existing file as the artifact body").option("--summary <text>", "Short summary line").option("--feedback <text>", "Feedback text for reject/feedback").option("--command <cmd>", 'Command for capture-tests (default "bun test")').option("--json", "Output as JSON").action(async (action2, id, opts) => {
+    const args = [action2, id, opts.kind ? `--kind ${quoteLocalCommandArg(opts.kind)}` : undefined, opts.title ? `--title ${quoteLocalCommandArg(opts.title)}` : undefined, opts.body ? `--body ${quoteLocalCommandArg(opts.body)}` : undefined, opts.file ? `--file ${quoteLocalCommandArg(opts.file)}` : undefined, opts.summary ? `--summary ${quoteLocalCommandArg(opts.summary)}` : undefined, opts.feedback ? `--feedback ${quoteLocalCommandArg(opts.feedback)}` : undefined, opts.command ? `--command ${quoteLocalCommandArg(opts.command)}` : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
+    await runLocalTextCommand(() => Promise.resolve().then(() => (init_artifacts2(), exports_artifacts)), args);
+  });
   program2.command("trigger [action]").alias("mention").description("Parse a GitHub/Slack webhook payload and optionally launch a headless UR run").option("--file <path>", "Webhook payload JSON file").option("--source <source>", "Force payload source: github|slack|generic").option("--keyword <keyword>", "Mention/command that triggers a run (default /ur)").option("--max-turns <n>", "Max agentic turns for the launched run").option("--dry-run", "Show the command without executing it (run action)").option("--json", "Output as JSON").action(async (action2, opts) => {
     const args = [action2, opts.file ? `--file ${quoteLocalCommandArg(opts.file)}` : undefined, opts.source ? `--source ${quoteLocalCommandArg(opts.source)}` : undefined, opts.keyword ? `--keyword ${quoteLocalCommandArg(opts.keyword)}` : undefined, opts.maxTurns ? `--max-turns ${opts.maxTurns}` : undefined, opts.dryRun ? "--dry-run" : undefined, opts.json ? "--json" : undefined].filter(Boolean).join(" ");
     await runLocalTextCommand(() => Promise.resolve().then(() => (init_trigger(), exports_trigger)), args);
@@ -505200,7 +505228,7 @@ if (false) {}
 async function main2() {
   const args = process.argv.slice(2);
   if (args.length === 1 && (args[0] === "--version" || args[0] === "-v" || args[0] === "-V")) {
-    console.log(`${"1.13.8"} (Ur)`);
+    console.log(`${"1.13.9"} (Ur)`);
     return;
   }
   if (args[0] === "a2a" && args[1] === "serve" && !args.includes("--help") && !args.includes("-h")) {

package/docs/AGENT_FEATURES.md

@@ -77,3 +77,33 @@ Cline/Roo, and Copilot workflows.
   concept — installing a mode just writes a scoped agent definition.
 - The self-review gate is heuristic and deterministic; it is the automatic
   safety net on the PR path, not a replacement for the model-driven review.
+
+## v1.13.9 Additions
+
+Five additions from a comparison with current Kiro/Spec Kit, Amp, Cursor,
+Jules, and Antigravity workflows. All keep model and exec behind injectable
+runners, so the core logic is deterministic and unit-tested offline.
+
+| Addition | Surface | What it adds |
+| --- | --- | --- |
+| Spec-driven development | `ur spec init\|generate\|approve\|run\|status` + `.ur/specs/` | requirements -> design -> tasks documents and a phase/approval record; executes the Spec Kit / Kiro `- [ ] T1: ...` task list one task at a time, checking off each PASS |
+| In-loop model escalation | `ur escalate plan\|run\|oracle\|policy` + `.ur/escalation.json` | capability-aware fast/oracle tiers from `model-doctor`; routine work runs fast and auto-escalates hard/failed work to the strong model; `oracle` is a one-shot second opinion |
+| Best-of-N judging | `ur arena "<task>" [--agents N] [--apply]` | runs N agents on one task in isolated worktrees, scores diffs with the self-review gate + verdict/diff heuristics, surfaces (optionally applies) the winner |
+| Self-healing CI loop | `ur ci-loop [--command ...] [--commit] [--push]` | run -> on failure summarize -> fix agent -> re-run, bounded by retries; commits/pushes are self-review gated; `--from-log` seeds the first failure |
+| Verifiable artifacts | `ur artifacts add\|capture-diff\|capture-tests\|approve\|reject` + `.ur/artifacts/` | reviewable deliverables with pending/approved/rejected status and threaded feedback; threads into the provenance stack (`claim-ledger`, `trace`, `evidence`) |
+
+### Commands
+
+```sh
+ur spec init checkout --goal "1. add cart 2. add payment 3. add receipt"
+ur spec approve checkout requirements
+ur spec run checkout --all
+ur escalate plan "debug the race condition in the scheduler"
+ur escalate run "refactor the cache layer" --force-oracle
+ur escalate oracle "is this lock-free queue correct?"
+ur arena "implement the rate limiter" --agents 3 --apply
+ur ci-loop --command "bun test" --max-attempts 3
+ur artifacts capture-diff
+ur artifacts capture-tests --command "bun test"
+ur artifacts approve 1
+```

package/docs/AGENT_TRENDS.md

@@ -23,6 +23,14 @@ ur code-index build
 ur code-index search "where is the rate limiter configured"
 ur role-mode install all
 ur agent-task pr --create --dry-run   # runs the self-review gate first
+ur spec init checkout --goal "1. add cart 2. add payment 3. add receipt"
+ur spec run checkout --all --dry-run
+ur escalate plan "debug the scheduler race"
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-diff
+ur artifacts capture-tests --command "bun test"
 ur claim-ledger validate
 ur browser-qa validate
 ```
@@ -52,6 +60,26 @@ Inside an interactive session:
 | Security and prompt-injection resistance | Covered | allow/ask/deny permissions, shell safety analysis, secret scan, untrusted web-content guidance, OS-level execution sandbox (macOS Seatbelt, Linux bubblewrap) | Continuously test web/MCP injection cases |
 | Agent identity and delegated authorization | Partial | MCP OAuth/XAA helpers, local trust boundaries, permission rules | Add portable cross-agent identity only with an opt-in A2A task adapter |
 | Multimodal workflows | Partial | `/image`, `/video`, `/youtube`, `/voice`, browser workflows | Add model-aware multimodal capability reporting for local Ollama setups |
+| Spec-driven development | Covered | `ur spec` scaffolds requirements/design/tasks under `.ur/specs/`, tracks phase/approvals, and runs the Spec Kit / Kiro task list one task at a time | Add bidirectional sync with an external `specs/` directory |
+| Capability-aware model escalation | Covered | `ur escalate` selects fast/oracle tiers from `model-doctor`, runs routine work fast, and auto-escalates hard/failed work to the strong local model | Learn per-model success rates to tune the difficulty threshold |
+| Best-of-N agent judging | Covered | `ur arena` runs N agents per task in isolated worktrees and judges diffs with the self-review gate; winner is selectable/appliable | Add an optional model judge alongside the deterministic scorer |
+| Self-healing CI | Covered | `ur ci-loop` runs a command, summarizes failures, invokes a fix agent, and re-runs with bounded retries; commits/pushes are self-review gated | Wire to `ur trigger` so a failed CI webhook auto-launches the loop |
+| Verifiable artifacts | Covered | `ur artifacts` records plans/diffs/test-runs with approve/reject/feedback under `.ur/artifacts/` | Attach browser-QA screenshots and link artifacts to claim-ledger entries |
+
+## v1.13.9 Direct CLI Surfaces
+
+These surfaces are registered as normal shell subcommands and as local slash
+commands, so users can run them directly without inserting `--` before their
+feature-specific flags:
+
+```sh
+ur spec init demo --goal "1. add a utils.add function 2. add a test"
+ur spec run demo --all --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-tests --command "bun test"
+```
 
 ## A2A Position
 

package/docs/USAGE.md

@@ -84,6 +84,11 @@ UR includes slash commands and CLI subcommands for common workflows:
 - `ur agents` to list configured agents
 - `ur agent-trends` to inspect coverage for current agent technology trends
 - `ur a2a card` to print UR's Agent Card metadata for A2A discovery
+- `ur spec ...` to scaffold requirements, design, and tasks, then run a spec task list
+- `ur escalate ...` to plan, run, or ask an oracle model for hard tasks
+- `ur arena ...` to run multiple agents on the same task and select a winner
+- `ur ci-loop ...` to run tests, repair failures, and rerun with a bounded loop
+- `ur artifacts ...` to capture reviewable diffs, test runs, notes, and feedback
 - `ur doctor` to inspect CLI health
 - `ur update` or `ur upgrade` to check for updates
 
@@ -92,6 +97,17 @@ Interactive sessions also check the published package version and show
 
 Run each command with `--help` for exact flags.
 
+Agent platform examples:
+
+```sh
+ur spec init demo --goal "1. add a utils.add function 2. add a test"
+ur spec run demo --all --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-diff
+```
+
 ## Permissions
 
 By default, UR asks before sensitive tool actions. For automation, use explicit allow and deny lists:

package/docs/VALIDATION.md

@@ -17,7 +17,7 @@ You need:
 
 ```sh
 ur --version
-# expected: 1.13.8 (Ur)
+# expected: 1.13.9 (Ur)
 ```
 
 ## 1. Marketplace tree resolves
@@ -184,6 +184,22 @@ for any literal `<system-reminder>` text. There should be none. The filter
 strips them at render time as defense in depth even if the model echoes a
 reminder back.
 
+## 9. Direct agent-platform commands parse feature flags
+
+These commands should parse their own flags directly, without requiring a `--`
+separator after the command name:
+
+```sh
+ur spec init validation-demo --goal "1. add a helper 2. add a test"
+ur spec run validation-demo --all --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-tests --command "bun test"
+```
+
+Expected: no `unknown option` or `too many arguments` parser errors.
+
 ## What to do if any step fails
 
 - Step 1 (marketplace): check `ls ~/.ur/marketplaces/` — `ur-plugins-official`
@@ -196,3 +212,7 @@ reminder back.
   to register — file an issue with the version (`ur --version`).
 - Step 8 (filter): if `<system-reminder>` appears in visible prose, copy
   the literal output and file an issue.
+- Step 9 (direct commands): run `ur --help` and confirm `spec`, `arena`,
+  `escalate`, `ci-loop`, and `artifacts` appear. If `unknown option` or
+  `too many arguments` appears, reinstall `ur-agent@latest` and verify the
+  npm version with `npm view ur-agent version`.

package/documentation/app.js

@@ -13,9 +13,15 @@ const featureGroups = [
   },
   {
     title: 'Agent platform',
-    tags: ['workflow', 'pattern', 'crew', 'goal'],
-    text: 'Durable workflows, collaboration patterns, parallel crews, long-horizon goals, live execution boards, and resumable checkpoint state.',
-    commands: ['ur workflow', 'ur pattern', 'ur crew', 'ur goal'],
+    tags: ['spec', 'workflow', 'pattern', 'crew', 'goal'],
+    text: 'Spec-driven development, durable workflows, collaboration patterns, parallel crews, long-horizon goals, live execution boards, and resumable checkpoint state.',
+    commands: ['ur spec', 'ur workflow', 'ur pattern', 'ur crew', 'ur goal'],
+  },
+  {
+    title: 'Judging, escalation, and repair',
+    tags: ['oracle', 'arena', 'CI', 'artifacts'],
+    text: 'Capability-aware fast/oracle model routing, best-of-N agent judging, self-healing CI loops, and reviewable artifacts for diffs, test runs, plans, and feedback.',
+    commands: ['ur escalate', 'ur arena', 'ur ci-loop', 'ur artifacts'],
   },
   {
     title: 'Automation and triggers',
@@ -32,8 +38,8 @@ const featureGroups = [
   {
     title: 'Evaluation and verification',
     tags: ['evals', 'review', 'QA'],
-    text: 'Replayable eval suites, self-review PR gate, browser QA fixtures, verifier reminders, trace inspection, and subagent timelines.',
-    commands: ['ur eval', 'ur agent-task', 'ur browser-qa', '/verify', '/trace'],
+    text: 'Replayable eval suites, self-review PR gate, browser QA fixtures, verifier reminders, trace inspection, reviewable artifacts, and subagent timelines.',
+    commands: ['ur eval', 'ur agent-task', 'ur browser-qa', 'ur artifacts', '/verify', '/trace'],
   },
   {
     title: 'Interoperability',
@@ -113,6 +119,20 @@ const commands = [
     summary: 'List configured agents and project agents available to sessions.',
     examples: ['ur agents', 'ur --agents \'{"reviewer":{"description":"Reviews code","prompt":"Review carefully"}}\''],
   },
+  {
+    name: 'arena',
+    category: 'Agent Platform',
+    aliases: ['best-of'],
+    summary: 'Run multiple agents on the same task in isolated worktrees, score their diffs, and optionally apply the winning patch.',
+    examples: ['ur arena "implement a debounce helper" --agents 2 --dry-run', 'ur arena "implement the rate limiter" --agents 3', 'ur arena "fix the parser" --agents 3 --apply'],
+  },
+  {
+    name: 'artifacts',
+    category: 'Evidence',
+    aliases: ['artifact'],
+    summary: 'Record reviewable deliverables under `.ur/artifacts` with pending, approved, rejected, and feedback states.',
+    examples: ['ur artifacts list', 'ur artifacts capture-diff', 'ur artifacts capture-tests --command "bun test"', 'ur artifacts approve 1', 'ur artifacts reject 1 --feedback "Needs a failing test first"'],
+  },
   {
     name: 'auth',
     category: 'Ops',
@@ -134,6 +154,13 @@ const commands = [
     summary: 'Validate and smoke-run browser replay fixtures under `.ur/browser-qa`.',
     examples: ['ur browser-qa list', 'ur browser-qa validate', 'ur browser-qa run home-page-smoke --dry-run'],
   },
+  {
+    name: 'ci-loop',
+    category: 'Automation',
+    aliases: ['heal'],
+    summary: 'Run a build or test command, summarize failures, invoke a fix agent, and rerun with a bounded retry budget.',
+    examples: ['ur ci-loop --command "bun test" --dry-run', 'ur ci-loop --command "bun test" --max-attempts 3', 'ur ci-loop --from-log failure.log --dry-run', 'ur ci-loop --command "bun test" --commit'],
+  },
   {
     name: 'claim-ledger',
     category: 'Evidence',
@@ -162,6 +189,13 @@ const commands = [
     summary: 'Check health of the installation and configured environment.',
     examples: ['ur doctor', 'ur ur-doctor', 'ur model-doctor'],
   },
+  {
+    name: 'escalate',
+    category: 'Models',
+    aliases: [],
+    summary: 'Plan, run, or consult a capability-aware fast/oracle model path for hard reasoning, debugging, review, and refactor tasks.',
+    examples: ['ur escalate plan "debug the scheduler race"', 'ur escalate run "refactor the cache layer" --force-oracle --dry-run', 'ur escalate oracle "is this lock-free queue correct?"', 'ur escalate policy --fast qwen2.5-coder --oracle qwen3-coder:480b-cloud'],
+  },
   {
     name: 'eval',
     category: 'Verification',
@@ -253,6 +287,13 @@ const commands = [
     summary: 'Build and search a project-local memory index over durable memory, docs, README, and instructions.',
     examples: ['ur semantic-memory build', 'ur semantic-memory search "release process"', 'ur semantic-memory status --json'],
   },
+  {
+    name: 'spec',
+    category: 'Agent Platform',
+    aliases: ['specs'],
+    summary: 'Scaffold requirements, design, and task documents under `.ur/specs`, track approvals, and run the task list one item at a time.',
+    examples: ['ur spec init demo --goal "1. add a utils.add function 2. add a test"', 'ur spec status demo', 'ur spec approve demo requirements', 'ur spec run demo --all --dry-run', 'ur spec generate demo tasks --dry-run'],
+  },
   {
     name: 'setup-token',
     category: 'Ops',
@@ -291,7 +332,7 @@ const slashGroups = [
   },
   {
     title: 'Editing and delivery',
-    items: ['/diff', '/commit', '/commit-push-pr', '/review', '/verify', '/trace', '/agent-task'],
+    items: ['/diff', '/commit', '/commit-push-pr', '/review', '/verify', '/trace', '/agent-task', '/artifacts'],
     text: 'Review changes, create commits, prepare PRs, inspect the trace, and run verification.',
   },
   {
@@ -301,8 +342,8 @@ const slashGroups = [
   },
   {
     title: 'Agents and orchestration',
-    items: ['/agents', '/agent-templates', '/workflow', '/pattern', '/crew', '/goal', '/route', '/role-mode'],
-    text: 'Manage agents, install role modes, run workflows, and coordinate multi-agent work.',
+    items: ['/agents', '/agent-templates', '/spec', '/workflow', '/pattern', '/crew', '/goal', '/arena', '/route', '/role-mode'],
+    text: 'Manage agents, install role modes, run specs and workflows, and coordinate multi-agent work.',
   },
   {
     title: 'Memory and evidence',
@@ -311,13 +352,13 @@ const slashGroups = [
   },
   {
     title: 'Automation and evals',
-    items: ['/automation', '/trigger', '/eval', '/browser-qa', '/actions', '/stability'],
-    text: 'Run recurring prompts, webhook-triggered runs, browser smoke checks, evals, and stability diagnostics.',
+    items: ['/automation', '/trigger', '/ci-loop', '/eval', '/browser-qa', '/actions', '/stability'],
+    text: 'Run recurring prompts, webhook-triggered runs, self-healing CI loops, browser smoke checks, evals, and stability diagnostics.',
   },
   {
     title: 'Models, tools, and interop',
-    items: ['/model', '/model-doctor', '/model-route', '/mcp', '/plugin', '/skills', '/sdk', '/a2a-card'],
-    text: 'Pick models, inspect capabilities, manage MCP/plugin extensions, and expose interop surfaces.',
+    items: ['/model', '/model-doctor', '/model-route', '/escalate', '/mcp', '/plugin', '/skills', '/sdk', '/a2a-card'],
+    text: 'Pick models, inspect capabilities, escalate to oracle models, manage MCP/plugin extensions, and expose interop surfaces.',
   },
   {
     title: 'Security operations',
@@ -362,6 +403,11 @@ const projectFiles = [
     text: 'Workflow YAML specs and checkpoint state for `ur workflow` and goal resumes.',
     example: 'ur workflow init release',
   },
+  {
+    title: '.ur/specs/',
+    text: 'Spec-driven requirements, design, task lists, phase state, and approvals for `ur spec`.',
+    example: 'ur spec init demo --goal "1. add a helper 2. add a test"',
+  },
   {
     title: '.ur/automations/',
     text: 'Cron-like automation specs for project-local scheduled headless prompts.',
@@ -382,6 +428,11 @@ const projectFiles = [
     text: 'Claim provenance ledger and evidence files.',
     example: 'ur claim-ledger validate',
   },
+  {
+    title: '.ur/artifacts/',
+    text: 'Reviewable plans, diffs, test runs, screenshots, notes, approvals, rejections, and feedback.',
+    example: 'ur artifacts capture-diff',
+  },
   {
     title: '.ur/browser-qa/',
     text: 'Browser replay fixtures and smoke-test targets.',
@@ -410,6 +461,31 @@ const examples = [
     text: 'Dry-run first, then create the PR after the deterministic gate passes.',
     code: 'ur agent-task pr --create --dry-run\nur agent-task pr --create',
   },
+  {
+    title: 'Spec-driven implementation',
+    text: 'Create requirements, design, and tasks, then run one task at a time.',
+    code: 'ur spec init demo --goal "1. add a utils.add function 2. add a test"\nur spec status demo\nur spec run demo --all --dry-run',
+  },
+  {
+    title: 'Best-of-N agent run',
+    text: 'Let isolated agents attempt the same task and surface the strongest diff.',
+    code: 'ur arena "implement a debounce helper" --agents 2 --dry-run\nur arena "fix the parser" --agents 3 --apply',
+  },
+  {
+    title: 'Model escalation',
+    text: 'Plan a fast/oracle route or force the oracle path for hard work.',
+    code: 'ur escalate plan "debug the scheduler race"\nur escalate run "refactor the cache layer" --force-oracle --dry-run',
+  },
+  {
+    title: 'Self-healing CI',
+    text: 'Run a test command, summarize failures, attempt a bounded fix loop, and rerun.',
+    code: 'ur ci-loop --command "bun test" --dry-run\nur ci-loop --command "bun test" --max-attempts 3',
+  },
+  {
+    title: 'Reviewable artifacts',
+    text: 'Capture diffs or test runs for approval and feedback.',
+    code: 'ur artifacts capture-diff\nur artifacts capture-tests --command "bun test"\nur artifacts approve 1',
+  },
   {
     title: 'A2A local task server',
     text: 'Expose Agent Card discovery and token-gated task execution.',

package/documentation/index.html

@@ -43,7 +43,7 @@
     <main id="content" class="content">
       <header class="topbar">
         <div>
-          <p class="eyebrow">Version 1.13.8</p>
+          <p class="eyebrow">Version 1.13.9</p>
           <h1>UR Agent Documentation</h1>
           <p class="lead">A practical, tutorial-style reference for installing, configuring, automating, extending, and operating UR Agent.</p>
         </div>
@@ -249,6 +249,68 @@ ur automation run-due --dry-run
 ur automation install --platform launchd --interval 300
 ur automation status</code></pre>
           </article>
+
+          <article>
+            <h3>Drive a change from a spec</h3>
+            <ol>
+              <li>Create a spec with requirements, design, tasks, and approval state.</li>
+              <li>Inspect or approve each phase.</li>
+              <li>Run the task list one item at a time, or use <code>--all</code>.</li>
+            </ol>
+            <pre><code>ur spec init demo --goal "1. add a utils.add function 2. add a test"
+ur spec status demo
+ur spec approve demo requirements
+ur spec run demo --all --dry-run</code></pre>
+          </article>
+
+          <article>
+            <h3>Escalate hard work to an oracle model</h3>
+            <ol>
+              <li>Ask UR to plan the fast/oracle model route.</li>
+              <li>Run routine work on the fast tier.</li>
+              <li>Force or auto-trigger oracle escalation for hard debugging and review.</li>
+            </ol>
+            <pre><code>ur escalate plan "debug the scheduler race"
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur escalate oracle "is this lock-free queue correct?"</code></pre>
+          </article>
+
+          <article>
+            <h3>Compare multiple agent attempts</h3>
+            <ol>
+              <li>Run multiple agents against the same task in isolated worktrees.</li>
+              <li>Let the deterministic self-review gate score the candidate diffs.</li>
+              <li>Apply the winner only when you are ready.</li>
+            </ol>
+            <pre><code>ur arena "implement a debounce helper" --agents 2 --dry-run
+ur arena "fix the parser" --agents 3
+ur arena "fix the parser" --agents 3 --apply</code></pre>
+          </article>
+
+          <article>
+            <h3>Repair failing CI in a bounded loop</h3>
+            <ol>
+              <li>Run the build or test command.</li>
+              <li>Summarize the failure and launch a fix attempt.</li>
+              <li>Rerun until the command passes or the retry budget is exhausted.</li>
+            </ol>
+            <pre><code>ur ci-loop --command "bun test" --dry-run
+ur ci-loop --command "bun test" --max-attempts 3
+ur ci-loop --from-log failure.log --dry-run</code></pre>
+          </article>
+
+          <article>
+            <h3>Capture reviewable artifacts</h3>
+            <ol>
+              <li>Capture the current diff or a test run under <code>.ur/artifacts</code>.</li>
+              <li>Review the saved body and status.</li>
+              <li>Approve, reject, or add feedback.</li>
+            </ol>
+            <pre><code>ur artifacts capture-diff
+ur artifacts capture-tests --command "bun test"
+ur artifacts show 1
+ur artifacts approve 1</code></pre>
+          </article>
         </div>
       </section>
 
@@ -361,9 +423,17 @@ ur automation daemon --once --dry-run</code></pre>
             <h3>Need evidence of what happened</h3>
             <pre><code>/trace 20
 ur agent-inspect --file session.jsonl
+ur artifacts list
 ur eval report starter
 ur claim-ledger validate</code></pre>
           </article>
+          <article>
+            <h3>New agent-platform command is missing</h3>
+            <pre><code>ur --version
+ur --help | grep -E "spec|arena|escalate|ci-loop|artifacts"
+npm install -g ur-agent@latest --registry=https://registry.npmjs.org/
+hash -r</code></pre>
+          </article>
         </div>
       </section>
     </main>

package/examples/agent_features.md

@@ -40,6 +40,20 @@ ur claim-ledger validate
 ur browser-qa validate
 ```
 
+Run the v1.13.9 spec, escalation, judging, CI, and artifact flows:
+
+```sh
+ur spec init demo --goal "1. add a utils.add function 2. add a test"
+ur spec status demo
+ur spec run demo --all --dry-run
+ur escalate plan "debug the scheduler race"
+ur escalate run "refactor the cache layer" --force-oracle --dry-run
+ur arena "implement a debounce helper" --agents 2 --dry-run
+ur ci-loop --command "bun test" --dry-run
+ur artifacts capture-diff
+ur artifacts capture-tests --command "bun test"
+```
+
 Run the opt-in A2A server on loopback:
 
 ```sh

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ur-agent",
-  "version": "1.13.8",
+  "version": "1.13.9",
   "description": "UR terminal coding agent CLI",
   "type": "module",
   "packageManager": "bun@1.3.14",