@desplega.ai/agent-swarm 1.158.0 → 1.159.0

package/dist/{index-f6cryxwe.js → index-4a5njnm1.js}

@@ -9,6 +9,7 @@ import {
   require_groovy,
   require_java,
   require_javascript,
+  require_json,
   require_kotlin,
   require_lua,
   require_nix,
@@ -20,7 +21,7 @@ import {
   require_scala,
   require_swift,
   require_typescript
-} from "./cli-vj6h9kc2.js";
+} from "./cli-0m7wct0d.js";
 import {
   __commonJS
 } from "./cli-bc05qbss.js";
@@ -9030,64 +9031,6 @@ var require_jboss_cli = __commonJS(function(exports, module) {
   module.exports = jbossCli;
 });
 
-// node_modules/highlight.js/lib/languages/json.js
-var require_json = __commonJS(function(exports, module) {
-  function json(hljs) {
-    const LITERALS = {
-      literal: "true false null"
-    };
-    const ALLOWED_COMMENTS = [
-      hljs.C_LINE_COMMENT_MODE,
-      hljs.C_BLOCK_COMMENT_MODE
-    ];
-    const TYPES = [
-      hljs.QUOTE_STRING_MODE,
-      hljs.C_NUMBER_MODE
-    ];
-    const VALUE_CONTAINER = {
-      end: ",",
-      endsWithParent: true,
-      excludeEnd: true,
-      contains: TYPES,
-      keywords: LITERALS
-    };
-    const OBJECT = {
-      begin: /\{/,
-      end: /\}/,
-      contains: [
-        {
-          className: "attr",
-          begin: /"/,
-          end: /"/,
-          contains: [hljs.BACKSLASH_ESCAPE],
-          illegal: "\\n"
-        },
-        hljs.inherit(VALUE_CONTAINER, {
-          begin: /:/
-        })
-      ].concat(ALLOWED_COMMENTS),
-      illegal: "\\S"
-    };
-    const ARRAY = {
-      begin: "\\[",
-      end: "\\]",
-      contains: [hljs.inherit(VALUE_CONTAINER)],
-      illegal: "\\S"
-    };
-    TYPES.push(OBJECT, ARRAY);
-    ALLOWED_COMMENTS.forEach(function(rule) {
-      TYPES.push(rule);
-    });
-    return {
-      name: "JSON",
-      contains: TYPES,
-      keywords: LITERALS,
-      illegal: "\\S"
-    };
-  }
-  module.exports = json;
-});
-
 // node_modules/highlight.js/lib/languages/julia.js
 var require_julia = __commonJS(function(exports, module) {
   function julia(hljs) {

package/dist/{index-a3vn96n8.js → index-5sz16ksh.js}

@@ -3,7 +3,7 @@ import {
 } from "./cli-ep19k3mb.js";
 import {
   agentFsProvisionSeeder
-} from "./cli-xhaeg2nc.js";
+} from "./cli-mzkqpxee.js";
 import {
   extractArgsJsonSchema,
   extractScriptSignature,
@@ -13,16 +13,26 @@ import {
   upsertScriptByName,
   validateDefinition,
   validateScriptImports
-} from "./cli-fgqxwrpv.js";
+} from "./cli-fjtp3463.js";
 import"./cli-epan13p1.js";
 import"./cli-y89t4nca.js";
 import"./cli-f14fvzag.js";
-import"./cli-987hg0aa.js";
-import"./cli-53sz8gkz.js";
-import"./cli-65hjmev5.js";
-import"./cli-xberxa1r.js";
-import"./cli-aehm1rbq.js";
+import"./cli-rfezr056.js";
+import"./cli-vhjwh6cz.js";
+import"./cli-3dpj7atn.js";
+import"./cli-gzyh0j0g.js";
+import"./cli-rb9m6rpe.js";
+import"./cli-rykfmgwg.js";
+import"./cli-vwbbaecp.js";
+import"./cli-qv4jv8bx.js";
+import"./cli-kc3dp84d.js";
+import"./cli-10ym38qc.js";
+import"./cli-bsakbbkm.js";
+import"./cli-wgjx0q33.js";
+import"./cli-q51yprfq.js";
+import"./cli-3er6gcsn.js";
 import"./cli-2658f6at.js";
+import"./cli-yatxqynm.js";
 import {
   computeContentHash,
   createScheduledTask,
@@ -39,20 +49,28 @@ import {
   updateSkill,
   updateWorkflow,
   upsertSkillFiles
-} from "./cli-47m6dkd3.js";
-import"./cli-4198qc9v.js";
-import"./cli-3gmcwfyx.js";
-import"./cli-ggm92wcn.js";
-import"./cli-19jenss3.js";
-import"./cli-dv6cdjs2.js";
+} from "./cli-g9df2m37.js";
+import"./cli-e4xnc0qp.js";
+import"./cli-ardpzhjm.js";
 import"./cli-n7h1kqpf.js";
-import"./cli-de1396j2.js";
+import"./cli-rgjprct3.js";
+import"./cli-dv6cdjs2.js";
 import"./cli-cqt19wg6.js";
+import"./cli-19jenss3.js";
+import"./cli-de1396j2.js";
 import"./cli-ej6gbxfb.js";
+import"./cli-7zttzetj.js";
 import"./cli-sd0mxa3c.js";
 import"./cli-w5e1d1vv.js";
-import"./cli-c07r9a2m.js";
+import"./cli-48527fpw.js";
 import"./cli-r2ap2czm.js";
+import"./cli-13hw4z91.js";
+import"./cli-btbzvq95.js";
+import"./cli-1m2e086m.js";
+import"./cli-ykk5jaax.js";
+import"./cli-bzr0ftht.js";
+import"./cli-bd957dgb.js";
+import"./cli-pzxba7gw.js";
 import"./cli-zf8jjwex.js";
 import {
   __toESM
@@ -5085,6 +5103,8 @@ export default async function taskContextGathering(args: any, ctx: any) {
 var task_failure_audit_default = `import { z } from "zod";
 import { publishCatalogReportPage } from "./catalog-report";
 
+const MAX_TASK_SCAN_LIMIT = 500;
+
 export const argsSchema = z.object({
   days: z
     .number()
@@ -5100,8 +5120,9 @@ export const argsSchema = z.object({
     .number()
     .int()
     .positive()
+    .max(MAX_TASK_SCAN_LIMIT)
     .optional()
-    .describe("Max failed tasks to scan (default 500)"),
+    .describe("Max failed tasks to scan (default 500, max 500)"),
   publishPage: z.boolean().optional().describe("Publish an authed HTML page (default true)"),
 });
 
@@ -5109,20 +5130,37 @@ const REASON_PATTERNS: any[] = [
   { key: "sigterm/killed", re: /sigterm|sigkill|killed|143|137/i },
   { key: "timeout", re: /time?d?\\s*out|timeout|deadline/i },
   { key: "context-window", re: /context (window|limit|saturat)|peakcontext|compact/i },
+  { key: "reboot-sweep", re: /reboot sweep/i },
   { key: "not-found", re: /not found|404|missing|no such/i },
   { key: "auth/credentials", re: /unauthorized|401|403|credential|token|forbidden/i },
-  { key: "ci/checks-failed", re: /ci|check.?s? fail|lint|tsc|test.?s? fail/i },
+  { key: "ci/checks-failed", re: /\\bci\\b|check.?s? fail|lint|tsc|test.?s? fail/i },
   { key: "network", re: /network|econn|fetch failed|socket|dns|502|503|504/i },
   { key: "cancelled", re: /cancel|aborted/i },
 ];
 
+function sanitizeUntrustedReasonSample(reason: unknown): string {
+  return String(reason)
+    .replace(/[\\u0000-\\u001f\\u007f-\\u009f]/g, " ")
+    .replace(/\\s+/g, " ")
+    .trim()
+    .slice(0, 200);
+}
+
+function rowsToObjects(result: any): any[] {
+  const payload = result?.data ?? result;
+  const columns: string[] = payload?.columns ?? [];
+  return (payload?.rows ?? []).map((row: any) =>
+    Array.isArray(row) ? Object.fromEntries(columns.map((column, i) => [column, row[i]])) : row,
+  );
+}
+
 function reasonCluster(reason: string): string {
   const r = (reason || "").trim();
   if (!r) return "(no reason given)";
   for (const p of REASON_PATTERNS) {
     if (p.re.test(r)) return p.key;
   }
-  return r.toLowerCase().slice(0, 48);
+  return "other";
 }
 
 /** Cluster recently failed swarm tasks by reason, agent, or schedule. */
@@ -5131,7 +5169,7 @@ export default async function taskFailureAudit(args: any, ctx: any) {
   if (!parsed.success) return { error: "invalid args: " + parsed.error.message };
   const days = parsed.data.days || 7;
   const groupBy = parsed.data.groupBy || "reason";
-  const limit = parsed.data.limit || 500;
+  const limit = Math.min(parsed.data.limit ?? MAX_TASK_SCAN_LIMIT, MAX_TASK_SCAN_LIMIT);
   const publishPage = parsed.data.publishPage !== false;
 
   const since = new Date(Date.now() - days * 86400000).toISOString();
@@ -5146,17 +5184,49 @@ export default async function taskFailureAudit(args: any, ctx: any) {
   const payload: any = res && res.data ? res.data : res;
   const tasks: any = payload && Array.isArray(payload.tasks) ? payload.tasks : [];
 
+  const failureReasons = new Map<string, string>();
+  if (groupBy === "reason") {
+    const tasksNeedingReason = tasks.filter((task: any) => !task.failureReason && task.id);
+    const taskIds = tasksNeedingReason.map((task: any) => task.id as string);
+    if (taskIds.length > 0) {
+      const placeholders = taskIds.map(() => "?").join(", ");
+      const reasonResult: any = await ctx.swarm.db_query({
+        sql: \`SELECT id, failureReason FROM agent_tasks WHERE id IN (\${placeholders})\`,
+        params: taskIds,
+      });
+      const reasonPayload: any = reasonResult?.data ?? reasonResult;
+      if (
+        reasonResult?.success === false ||
+        reasonPayload?.success === false ||
+        reasonPayload?.error
+      ) {
+        return { error: "failure reason projection failed with status " + reasonResult?.status };
+      }
+      if (reasonPayload?.truncated) {
+        return {
+          error: \`failure reason projection truncated (\${reasonPayload.rows?.length ?? 0} of \${reasonPayload.total ?? "unknown"} rows)\`,
+        };
+      }
+      for (const row of rowsToObjects(reasonResult)) {
+        if (typeof row?.id === "string" && typeof row.failureReason === "string") {
+          failureReasons.set(row.id, row.failureReason);
+        }
+      }
+    }
+  }
+
   const groups: any = {};
   for (const t of tasks) {
     let key: string;
     if (groupBy === "agent") key = t.agentId || "(unassigned)";
     else if (groupBy === "schedule") key = t.scheduleId || "(not scheduled)";
-    else key = reasonCluster(t.failureReason || "");
-    if (!groups[key]) groups[key] = { key, count: 0, taskIds: [], sampleReason: "" };
+    else key = reasonCluster(failureReasons.get(t.id) || t.failureReason || "");
+    if (!groups[key]) groups[key] = { key, count: 0, taskIds: [], untrustedWorkerTextSample: "" };
     groups[key].count++;
     if (groups[key].taskIds.length < 5) groups[key].taskIds.push(t.id);
-    if (!groups[key].sampleReason && t.failureReason) {
-      groups[key].sampleReason = String(t.failureReason).slice(0, 200);
+    const failureReason = failureReasons.get(t.id) || t.failureReason;
+    if (!groups[key].untrustedWorkerTextSample && failureReason) {
+      groups[key].untrustedWorkerTextSample = sanitizeUntrustedReasonSample(failureReason);
     }
   }
 
@@ -5202,7 +5272,7 @@ export default async function taskFailureAudit(args: any, ctx: any) {
                   key: group.key,
                   count: group.count,
                   taskIds: group.taskIds,
-                  sampleReason: group.sampleReason,
+                  untrustedWorkerTextSample: group.untrustedWorkerTextSample,
                 },
               ],
             })),
@@ -5659,7 +5729,7 @@ var config_default = `{
 `;
 
 // templates/skills/agent-browser/content.md
-var content_default = '# agent-browser\n\n`agent-browser` (vercel-labs) is the swarm\'s browser-automation CLI. It drives a headless Chromium over CDP and returns accessibility-tree snapshots with compact `@eN` refs. Use it for any browser task: verify a UI change, take a screenshot, walk a page, fill a form, extract page text, reproduce a frontend bug, or attach UI evidence to a PR, issue, Linear comment, or Slack thread.\n\nDo not use `qa-use`. It is not installed in the worker image any more.\n\n## Step 0: check that the CLI is present\n\nThe full worker image (`agent-swarm-worker:latest`) ships `agent-browser` and a headless Chromium. The slim image (`:slim`) has neither. The first command of any browser work is:\n\n```bash\ncommand -v agent-browser\n```\n\nIf it prints nothing, you are on the slim image. Say so in your progress report ("agent-browser is not available on this worker image") and fall back to manual QA: write the exact steps a human should run and mark the browser test cases as **Blocked**, not failed. Do not install a browser or the CLI yourself.\n\n## Step 1: load the version-matched guide\n\nThe CLI bundles its own usage guide. Load it once per task before the first browser command. Do not guess flags from memory.\n\n```bash\nagent-browser skills get core          # overview + common patterns\nagent-browser skills get core --full   # adds the full command reference\nagent-browser skills list              # specialized guides (dogfood, electron, slack, ...)\n```\n\n## Step 2: the core loop\n\n```bash\nagent-browser open <url>\nagent-browser snapshot -i              # accessibility tree, interactive elements only, @eN refs\nagent-browser click @e12               # act on refs from the snapshot\nagent-browser fill @e7 "text"\nagent-browser screenshot /tmp/<name>.png\nagent-browser close\n```\n\n- Re-run `snapshot` after every navigation or state change. Refs are only valid for the snapshot that produced them.\n- Run one browser session at a time. Call `store-progress` between page batches so the heartbeat watchdog sees you.\n- The browser is headless. Local servers inside the worker container are reachable at `http://localhost:<port>`.\n- The image launches Chromium with `--no-sandbox,--disable-dev-shm-usage` through `AGENT_BROWSER_ARGS`. If you pass your own `--args`, include `--no-sandbox` again or Chrome will not start.\n\n## Recording\n\nDefault: record with `--cursor`, drive every supported pointer action (`click`, `mouse move`, `drag`) with `--human`, and ship the **1.5x video**. Keep the 1x original only if a reviewer asks for it. Human pointer movement follows an eased curve; use `--seed <n>` on `mouse move` to make the take reproducible instead of using a bare move.\n\nOpen the page first, then record the interaction:\n\n```bash\nagent-browser record start ./in.mp4 --cursor\nagent-browser snapshot -i\nagent-browser mouse move 600 400 --human --seed 42 --duration 1400\nagent-browser click @e3 --human          # use a ref from the current snapshot\n# Perform the remaining QA steps; use --human for drag actions too.\nagent-browser record stop\nffmpeg -y -i in.mp4 -filter:v "setpts=PTS/1.5,fps=30" -an \\\n  -c:v libx264 -preset veryfast -crf 23 -pix_fmt yuv420p out-1.5x.mp4\n```\n\nSpeed-up is a post-process step: `record start` has no speed or human flag. Keep `fps=30` to preserve a steady 30 fps output rather than uneven frame drops at an inferred rate. `-an` disables audio because agent-browser recordings carry no audio track. The worker ships only `ffmpeg`, not `ffprobe`; inspect duration with `ffmpeg -i out-1.5x.mp4 2>&1 | grep Duration`.\n\nAdd `--contact-sheet` to the start command for a timestamped PNG summary of visual changes. Recording needs `ffmpeg` on PATH; check `agent-browser doctor` before starting. Stop the recording before closing the browser so the video is saved. Upload the 1.5x file through the same agent-fs QA path and signed-URL steps as screenshots below, and link it in the PR body.\n\n## Step 3: share the screenshot through agent-fs\n\nScreenshots on the worker disk disappear with the task. Upload them to agent-fs under the qa path convention and share the signed URL. `--file` is binary-safe. `--content` is text-only and mangles PNGs.\n\n```bash\nagent-fs write thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png \\\n  --file /tmp/<name>.png -m "<what it shows>"\nagent-fs stat thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png --json        # confirm size > 0\nagent-fs signed-url thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png --json  # 24h default, --expires-in up to 7d\n```\n\n- Embed the URL as `![caption](<url>)` in the PR body, review comment, Linear comment, or Slack message.\n- In `store-progress`, list the upload in the `attachments` field with `kind: "agent-fs"` and the path, and paste the signed URL in the progress text.\n- If `agent-fs auth whoami` fails, report the local path, say the upload was skipped, and continue.\n\nThe `artifacts` skill holds the full agent-fs recipe and the naming conventions.\n';
+var content_default = '# agent-browser\n\n`agent-browser` (vercel-labs) is the swarm\'s browser-automation CLI. It drives a headless Chromium over CDP and returns accessibility-tree snapshots with compact `@eN` refs. Use it for any browser task: verify a UI change, take a screenshot, walk a page, fill a form, extract page text, reproduce a frontend bug, or attach UI evidence to a PR, issue, Linear comment, or Slack thread.\n\nDo not use `qa-use`. It is not installed in the worker image any more.\n\n## Step 0: check that the CLI is present\n\nThe full worker image (`agent-swarm-worker:latest`) ships `agent-browser` and a headless Chromium. The slim image (`:slim`) has neither. The first command of any browser work is:\n\n```bash\ncommand -v agent-browser\n```\n\nIf it prints nothing, you are on the slim image. Say so in your progress report ("agent-browser is not available on this worker image") and fall back to manual QA: write the exact steps a human should run and mark the browser test cases as **Blocked**, not failed. Do not install a browser or the CLI yourself.\n\n## Step 1: load the version-matched guide\n\nThe CLI bundles its own usage guide. Load it once per task before the first browser command. Do not guess flags from memory.\n\n```bash\nagent-browser skills get core          # overview + common patterns\nagent-browser skills get core --full   # adds the full command reference\nagent-browser skills list              # specialized guides (dogfood, electron, slack, ...)\n```\n\n## Step 2: the core loop\n\n```bash\nagent-browser open <url>\nagent-browser snapshot -i              # accessibility tree, interactive elements only, @eN refs\nagent-browser click @e12               # act on refs from the snapshot\nagent-browser fill @e7 "text"\nagent-browser screenshot /tmp/<name>.png\nagent-browser close\n```\n\n- Re-run `snapshot` after every navigation or state change. Refs are only valid for the snapshot that produced them.\n- Run one browser session at a time. Call `store-progress` between page batches so the heartbeat watchdog sees you.\n- The browser is headless. Local servers inside the worker container are reachable at `http://localhost:<port>`.\n- The image launches Chromium with `--no-sandbox,--disable-dev-shm-usage` through `AGENT_BROWSER_ARGS`. If you pass your own `--args`, include `--no-sandbox` again or Chrome will not start.\n\n## Recording\n\nDefault: record with `--cursor`, drive every supported pointer action (`click`, `mouse move`, `drag`) with `--human`, and ship the **1.5x video**. Keep the 1x original only if a reviewer asks for it. Human pointer movement follows an eased curve; use `--seed <n>` on `mouse move` to make the take reproducible instead of using a bare move.\n\nOpen the page first, then record the interaction:\n\n```bash\nagent-browser record start ./in.mp4 --cursor\nagent-browser snapshot -i\nagent-browser mouse move 600 400 --human --seed 42 --duration 1400\nagent-browser click @e3 --human          # use a ref from the current snapshot\n# Perform the remaining QA steps; use --human for drag actions too.\nagent-browser record stop\nffmpeg -y -i in.mp4 -filter:v "setpts=PTS/1.5,fps=30" -an \\\n  -c:v libx264 -preset veryfast -crf 23 -pix_fmt yuv420p out-1.5x.mp4\n```\n\nSpeed-up is a post-process step: `record start` has no speed or human flag. Keep `fps=30` to preserve a steady 30 fps output rather than uneven frame drops at an inferred rate. `-an` disables audio because agent-browser recordings carry no audio track. The worker ships only `ffmpeg`, not `ffprobe`; inspect duration with `ffmpeg -i out-1.5x.mp4 2>&1 | grep Duration`.\n\nAdd `--contact-sheet` to the start command for a timestamped PNG summary of visual changes. Recording needs `ffmpeg` on PATH; check `agent-browser doctor` before starting. Stop the recording before closing the browser so the video is saved. Upload the 1.5x file through the same agent-fs QA path as screenshots below, and link it in the PR body.\n\n## Step 3: share the screenshot through agent-fs\n\nScreenshots on the worker disk disappear with the task. Upload them to agent-fs under the qa path convention. Use `share-create` when a person needs to open the file, and `signed-url` for raw embeds such as an image in GitHub PR markdown. `--file` is binary-safe. `--content` is text-only and mangles PNGs.\n\n```bash\nagent-fs write thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png \\\n  --file /tmp/<name>.png -m "<what it shows>"\nagent-fs stat thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png --json        # confirm size > 0\nagent-fs share-create thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png --json\nagent-fs signed-url thoughts/<agent-id>/qa/<topic>-screenshots/<name>.png --json  # raw URL for embeds; 24h default, --expires-in up to 7d\n```\n\n- Embed the signed URL as `![caption](<url>)` in the PR body, review comment, Linear comment, or Slack message.\n- In `store-progress`, list the upload in the `attachments` field with `kind: "agent-fs"` and the path, and paste the `share-create` link for people who need to open the file.\n- If `agent-fs auth whoami` fails, report the local path, say the upload was skipped, and continue.\n\nThe `artifacts` skill holds the full agent-fs recipe and the naming conventions.\n';
 
 // templates/skills/apps/config.json
 var config_default2 = `{
@@ -7145,7 +7215,7 @@ var config_default20 = `{
   "displayName": "Heartbeat Runbook",
   "slug": "heartbeat-runbook",
   "title": "Heartbeat Runbook",
-  "description": "Heartbeat, HEARTBEAT.md, standing orders, heartbeat-checklist task, boot-triage task: how the lead keeps its heartbeat runbook short and handles a checklist or boot-triage task. Covers the tracked-item cap, lift triggers, the \`Heartbeat Audit\` and \`boot-triage\` scripts, and reboot-interrupted work. Lead only.",
+  "description": "Heartbeat, HEARTBEAT.md, standing orders, heartbeat-checklist task, boot-triage task: how the lead keeps its heartbeat runbook short and handles a checklist or boot-triage task. Covers the tracked-item cap, lift triggers, the \`schedule-health\`, \`task-failure-audit\` and \`boot-triage\` scripts, and reboot-interrupted work. Lead only.",
   "version": "1.0.0",
   "category": "skills",
   "placeholders": [],
@@ -7187,8 +7257,8 @@ Two kinds of sections:
 
 1. Read the latest runbook. The snapshot in the task may be stale.
 2. Prune first. Check every tracked item against its lift trigger. Remove resolved, stale, and past-date items.
-3. Run the seeded audit: \`script-run\` with name \`Heartbeat Audit\` and \`args: { heartbeatMarkdown: <the runbook text> }\`. It reports resolved stale PRs, pool-target risk schedules, schedule and provider failure clusters, and whether the daily blocker digest ran today.
-4. Read the system status and the audit result for stalled tasks, idle workers next to open work, and anomalies.
+3. Run the seeded scripts: \`script-run\` with name \`schedule-health\`, then \`task-failure-audit\`, both with \`args: { days: 1, publishPage: false }\`. They report failing schedules and failure clusters. Check any other standing order in the runbook yourself.
+4. Read the system status and the script results for stalled tasks, idle workers next to open work, and anomalies.
 5. Reboot-interrupted failures: a failure reason "worker session not found" or "worker session heartbeat is stale" means a server restart cut the task off. For each one: \`get-task-details\` on the task, confirm a retry task tagged \`reboot-retry\` exists and moves, recreate the task when no retry exists and the work is still needed. These are never "expected cleanup".
 6. Act with your tools: create tasks, cancel stuck ones, post to Slack under the \`slack-interaction\` skill rules.
 7. Update the runbook after pruning.
@@ -10766,7 +10836,7 @@ The swarm ships named scripts at global scope. Each one replaces a multi-step to
 | \`complete-task\` | \`{ taskId, output }\` | finish a task from inside a script |
 | \`report-progress\` | \`{ taskId, note }\` | a progress note from inside a script |
 | \`swarm-overview\` | \`{}\` | agents and task counts |
-| \`Heartbeat Audit\`, \`boot-triage\` | see \`heartbeat-runbook\` | the lead's heartbeat data gathering |
+| \`schedule-health\`, \`task-failure-audit\`, \`boot-triage\` | see \`heartbeat-runbook\` | the lead's heartbeat data gathering |
 
 ## Authoring contract
 
@@ -11781,10 +11851,22 @@ Use this skill when you need to change an existing workflow without breaking liv
 - Make routing explicit. Branching nodes should have named pass/fail routes, and silent skip paths should still produce an observable outcome when operators need to know what happened.
 - Wire inputs deliberately. Node executors receive the raw workflow context plus resolved \`inputs\` aliases, so a condition can use either a local alias or a node-id-prefixed path. Confirm the chosen path against the recorded step input.
 - Keep schemas tight. If an agent-task has an \`outputSchema\`, include the expected JSON shape in the task prompt and route it to a worker/provider that is known to return structured output correctly.
-- Prefer reusable script nodes for deterministic shared logic. Agent tasks are best for judgment, investigation, or work that genuinely needs an LLM.
+- Prefer reusable script nodes for deterministic shared logic. Agent tasks are best for investigation or work that genuinely needs an LLM. For a bounded judgment, use \`system-one-decision\` (see Choosing a decider).
 - Scope parallel branches so they do not overwrite one another. Fan-out tasks should have separate context keys or branch-specific output fields.
 - Make retry paths idempotent. A rerun should detect existing artifacts, comments, PRs, or notifications and update or skip them rather than duplicating work.
 
+### Choosing a decider
+
+When a node has to decide, pick the cheapest node that can decide. Use \`system-one-decision\` without being asked when the decision is a bounded judgment.
+
+| The decision is | Use |
+|---|---|
+| A fact: a count, PR state, flag, date, lookup, regex, or schema check | \`script\`, \`property-match\`, or \`code-match\` |
+| A bounded judgment: pass/fail, pick one of N, a score on a rubric, or the probability that a claim is true | \`system-one-decision\` |
+| Free-form generation, or findings a later node reads | \`raw-llm\` or \`agent-task\` |
+
+Jev is weak at counting. For a hybrid, count in a \`script\` and pass the number to \`system-one-decision\` as part of \`state\`.
+
 ### \`swarm-script\` Timeout Limit
 
 - Keep \`config.timeoutMs\` at or below \`300000\` (5 minutes); the default remains \`30000\` (30 seconds).
@@ -11854,6 +11936,74 @@ Use these shapes as a starting point, then confirm them against the current exec
 
 \`validate\` checks the named upstream node output. Supply either \`schema\` for a deterministic structural check or \`prompt\` for a judgment-based check. Its output is \`{ pass, reasoning, confidence }\`, routed through \`pass\` or \`fail\`.
 
+### \`system-one-decision\` (SystemOne Decision)
+
+**Before you add the first \`system-one-decision\` node to a workflow, confirm its key works.** A node with no working key fails its whole run, and a save only warns. Do these in order and stop at the first failure:
+
+1. Pick the provider. \`typesafe\` (the default) needs the global secret \`TYPESAFE_API_KEY\`. \`openrouter\` needs \`OPENROUTER_API_KEY\`. \`laya\` needs the global secret \`LAYA_API_KEY\` and the global config \`LAYA_URL\`, the base URL of its server. Use the provider the requester named. If they named none, use \`typesafe\`. If its key is missing but another provider's key exists, ask which to use rather than switching, because the accounts bill separately.
+2. Check the key is set: \`get-config\` with \`key\` set to that name and no \`includeSecrets\`. A masked value (\`********\`) means a value exists. No entry means it is missing. Never pass \`includeSecrets\`, and never read the value. For \`laya\`, check \`LAYA_URL\` the same way; it is not secret, so its value shows.
+3. Confirm it works with one cheap call. Create a throwaway one-node workflow, trigger it, read the run, then \`delete-workflow\` it:
+
+   \`\`\`json
+   {
+     "nodes": [
+       {
+         "id": "ping",
+         "type": "system-one-decision",
+         "config": {
+           "provider": "typesafe",
+           "state": "ping",
+           "questions": { "ping": { "type": "noul", "instructions": "Is the state the word ping?" } },
+           "returns": { "ping": { "type": "noul" } },
+           "timeoutMs": 15000,
+           "maxRetries": 0
+         }
+       }
+     ]
+   }
+   \`\`\`
+
+   A \`completed\` run means the key works. A \`failed\` run carries the reason: \`<KEY> is not configured\` (missing; for \`laya\` it can name \`LAYA_URL\` or \`LAYA_API_KEY\`, or both), or \`<KEY> was rejected by <host> (HTTP 401)\` (present but refused). To probe \`laya\`, set \`"provider": "laya"\` in the ping node. If \`create-workflow\` says \`system-one-decision\` is an unregistered executor type, the node is not deployed on this swarm yet: stop and say so.
+4. If the key is missing or was rejected, **do not build the node.** Ask a human for the key with \`request-human-input\` or in the thread. Name the exact key and where it goes: the Secrets page (Settings > Secrets), or for \`LAYA_URL\` a global config value (\`set-config\`, scope \`global\`). Never ask them to paste it into chat, a task, or a definition, and never write a key into a definition.
+
+Afterwards, a \`warnings\` entry on \`create-workflow\` or a patch tool means the key went missing since you checked. Treat it as step 4.
+
+\`\`\`json
+{
+  "type": "system-one-decision",
+  "inputs": { "pr": "trigger.pullRequest" },
+  "config": {
+    "provider": "typesafe",
+    "model": "jev-1.13.0",
+    "state": "{{pr}}",
+    "questions": {
+      "ready": {
+        "type": "noul",
+        "instructions": "Is this pull request ready to merge?",
+        "criteria": { "true": "Tests pass and the change matches its description", "false": "Missing tests or scope creep" }
+      },
+      "risk": {
+        "type": "choice",
+        "instructions": "How risky is this change?",
+        "criteria": { "low": "Docs or tests only", "medium": "Contained behavior change", "high": "Touches auth, data, or billing" }
+      }
+    },
+    "returns": { "ready": { "type": "noul" }, "risk": { "type": "choice" } }
+  },
+  "next": "gate"
+}
+\`\`\`
+
+- \`provider\` is \`typesafe\` (default), \`openrouter\`, or \`laya\`, and must be a literal, not a \`{{token}}\`. \`model\` is that provider's own id (\`jev-1.13.0\` on \`typesafe\`, \`typesafe/jev-1.13\` on \`openrouter\`, a checkpoint name such as \`multilingual\` on \`laya\`); leave it unset for the provider's default. \`laya\` has no default and sends no \`model\`, because it silently ignores one it does not know: leave it unset unless you mean a specific checkpoint. All three take the same request and return the same answers. There is no fallback between them. Never use OpenRouter's \`typesafe/jev-router\`, which is a chat router that hands the request to another model.
+- \`state\` is required: text, a string array, or a JSON object. An exact \`{{token}}\` keeps the upstream JSON type. Every question in one call shares the state and cannot see the other answers, so a dependent judgment needs its own node.
+- Each question is \`noul\` (probability that a claim is true; optional \`criteria: { true, false }\`), \`choice\` (2 to 255 options; \`criteria: { option: description }\`), or \`score\` (2 to 10 ordered levels; \`criteria: [level, ...]\`).
+- \`returns\` repeats every question id and its type. A mismatch is rejected when the workflow is saved.
+- The output is \`{ model, answers, usage }\`, plus \`routing: { model }\` on \`laya\` (the checkpoint that answered). Read a field as \`<node-id>.answers.<question>.<field>\`, for example \`qualification.answers.risk.confidence\`. A \`noul\` answer is only \`{ type, noul }\` and has no confidence. A \`choice\` answer has \`choice\`, \`probabilities\`, and \`confidence\`. A \`score\` answer has \`score\`, \`legend\`, \`probabilities\`, and \`confidence\`.
+- A valid low-confidence answer is a success. To have a person review the uncertain ones, set \`humanReview\` on the node (below). To route on a threshold yourself, keep it in the next node: \`property-match\` (\`gt\`, \`lt\`) or \`code-match\`, with the uncertain band routed to \`human-in-the-loop\`. Do not invent a global threshold.
+- \`humanReview: { band: { min, max }, approvers, title?, timeout?, notifications? }\` sends an answer to a person when \`min <= confidence <= max\` (0 to 1, both ends inside). It raises a \`human-in-the-loop\` approval (same approvers, timeout, notifications, \`waiting\` run state), so use the same \`approvers\` shape. \`choice\` and \`score\` are tested on their \`confidence\` (on \`laya\` that is its \`answer_confidence\`, the top probability); a \`noul\` on \`max(noul, 1 - noul)\`. Any answer in the band makes the run wait. \`next\` must then be a port map: \`approved\` (required, every accepted answer), and optionally \`rejected\` and \`timeout\`; a string or list \`next\` is refused. The output stays \`{ model, answers, usage }\` on every path, plus \`review\` (\`status\`, and per question \`confidence\`, \`inBand\`, \`decidedBy\`). A person's answer replaces the model's in \`answers\`; \`probabilities\` and \`confidence\` stay the model's.
+- Do not set \`retry\` or \`validation.retry\` on a \`system-one-decision\` node. It retries connection errors, 408, 429, and 5xx itself (\`config.maxRetries\`, 0 to 3, default 2) inside \`config.timeoutMs\` (default 30000). A 401, a 422, or an answer that fails validation ends after one attempt.
+- The node reads its provider's key (\`TYPESAFE_API_KEY\`, \`OPENROUTER_API_KEY\`, or \`LAYA_API_KEY\`, and for \`laya\` the server URL \`LAYA_URL\`) server-side. The key never appears in the definition, the step output, or an error. A run whose key or \`LAYA_URL\` is missing fails before any node executes, and a 401 or 403 fails the step as \`<KEY> was rejected\`. An unresolved \`{{token}}\` fails the step before any request.
+
 ### \`swarm-script\`
 
 \`\`\`json
@@ -15022,12 +15172,11 @@ You are Lead. Produce one concise daily digest of blockers, stale claims, open P
 
 Run these read-only global scripts first. Use their outputs as evidence, then apply judgment:
 
-1. \`script-run\` global script \`Heartbeat Audit\` with args \`{ "heartbeatMarkdown": "<current /workspace/HEARTBEAT.md text>" }\`
-2. \`script-run\` global script \`schedule-health\` with args \`{ "days": 7, "publishPage": true }\`
-3. \`script-run\` global script \`task-failure-audit\` with args \`{ "days": 7, "groupBy": "reason", "publishPage": true }\`
-4. Read \`GET /status\`. If the \`embeddings\` milestone is \`unverified\`, append this line to the digest: "Memory search is off: set OPENAI_API_KEY on the API server to enable it."
+1. \`script-run\` global script \`schedule-health\` with args \`{ "days": 7, "publishPage": true }\`
+2. \`script-run\` global script \`task-failure-audit\` with args \`{ "days": 7, "groupBy": "reason", "publishPage": true }\`
+3. Read \`GET /status\`. If the \`embeddings\` milestone is \`unverified\`, append this line to the digest: "Memory search is off: set OPENAI_API_KEY on the API server to enable it."
 
-Do not script-ify judgment or notification copy. Use the script outputs to identify stale blocker claims, schedule risks, provider failure clusters, and digest-run health.
+Do not script-ify judgment or notification copy. Use the script outputs to identify schedule risks and provider failure clusters.
 
 ## Phase 1: Gather Blockers
 
@@ -16392,18 +16541,7 @@ var config_default66 = `{
 `;
 
 // templates/workflows/claude-code-changelog-watch/content.md
-var content_default66 = `# Claude Code Changelog Watch
-
-This topology-preserving self-hosted port removes installation-specific identities, endpoints, and credentials while retaining the live workflow's nodes, edges, input mappings, guards, retries, cooldown, and triggers. Configure the declared template parameters and integrations before enabling it.
-
-\`\`\`json
-{"name":"claude-code-changelog-watch","description":"Changelog watcher with deduplication: fetch, gate on a new version, publish an in-app receipt plus any configured delivery providers, then commit the version marker.","nodes":[{"id":"check","type":"swarm-script","label":"Fetch changelog + compare vs KV","config":{"scriptName":"claude-code-changelog-check","scope":"global","args":{"mode":"check"}},"next":"gate"},{"id":"gate","type":"property-match","label":"Gate: only continue on a new version","config":{"mode":"all","conditions":[{"field":"check.result.isNew","op":"eq","value":true}]},"next":{"true":"post"}},{"id":"post","type":"agent-task","label":"Post new version to Slack","config":{"model":"sonnet","tags":["changelog","claude-code","workflow"],"priority":50,"template":"**Claude Code new version announcement**\\n\\nA new Claude Code version was detected by the claude-code-changelog-watch workflow.\\n\\nNew version: {{check.result.latestVersion}} (released {{check.result.releaseDate}}, previous known: {{check.result.lastKnown}})\\n\\nRaw release notes:\\n{{check.result.section}}\\n\\nSteps:\\n1. ONE \`slack-post\` to the configured Slack notification target, **max 400 chars**:\\n\\n\`\`\`\\n:rocket: *Claude Code {{check.result.latestVersion}}* — <the one change that matters to us, one line>\\n<https://code.claude.com/docs/en/changelog|changelog>\\n\`\`\`\\n\\nRules:\\n- **One line.** Pick the single item that affects how we run the swarm (a fix we were hitting, a flag we use, a breaking change). Not 3-5 bullets.\\n- If a second item genuinely matters, one more bullet. Never more than two.\\n- **Routine release with nothing relevant to us ⇒ still post, but the one line is just the headline feature.** Never paste the release notes.\\n- No preamble, no \\"is out!\\", no per-surface breakdown (VSCode/CLI/SDK), no closing line.\\n\\n2. Complete with output \\"Posted Claude Code {{check.result.latestVersion}} to in-app activity and configured delivery providers.\\" plus the charCount.\\n\\nDo NOT update any version state — the workflow's commit node handles that after you complete. Do NOT post more than once."},"next":"commit","inputs":{"check":"check"}},{"id":"commit","type":"swarm-script","label":"Commit new version to KV","config":{"scriptName":"claude-code-changelog-check","scope":"global","args":{"mode":"commit","version":"{{check.result.latestVersion}}"}},"inputs":{"check":"check"}}],"onNodeFailure":"fail"}
-\`\`\`
-
-
-
-
-`;
+var content_default66 = '# Claude Code Changelog Watch\n\nThis topology-preserving self-hosted port removes installation-specific identities, endpoints, and credentials while retaining the live workflow\'s nodes, edges, input mappings, guards, retries, cooldown, and triggers. Configure the declared template parameters and integrations before enabling it.\n\nPrerequisite: the `check` and `commit` nodes run the global script `claude-code-changelog-check`, which is not seeded. Author it before enabling the workflow, or every run fails at the first node.\n\n```json\n{"name":"claude-code-changelog-watch","description":"Changelog watcher with deduplication: fetch, gate on a new version, publish an in-app receipt plus any configured delivery providers, then commit the version marker.","nodes":[{"id":"check","type":"swarm-script","label":"Fetch changelog + compare vs KV","config":{"scriptName":"claude-code-changelog-check","scope":"global","args":{"mode":"check"}},"next":"gate"},{"id":"gate","type":"property-match","label":"Gate: only continue on a new version","config":{"mode":"all","conditions":[{"field":"check.result.isNew","op":"eq","value":true}]},"next":{"true":"post"}},{"id":"post","type":"agent-task","label":"Post new version to Slack","config":{"model":"sonnet","tags":["changelog","claude-code","workflow"],"priority":50,"template":"**Claude Code new version announcement**\\n\\nA new Claude Code version was detected by the claude-code-changelog-watch workflow.\\n\\nNew version: {{check.result.latestVersion}} (released {{check.result.releaseDate}}, previous known: {{check.result.lastKnown}})\\n\\nRaw release notes:\\n{{check.result.section}}\\n\\nSteps:\\n1. ONE `slack-post` to the configured Slack notification target, **max 400 chars**:\\n\\n```\\n:rocket: *Claude Code {{check.result.latestVersion}}* — <the one change that matters to us, one line>\\n<https://code.claude.com/docs/en/changelog|changelog>\\n```\\n\\nRules:\\n- **One line.** Pick the single item that affects how we run the swarm (a fix we were hitting, a flag we use, a breaking change). Not 3-5 bullets.\\n- If a second item genuinely matters, one more bullet. Never more than two.\\n- **Routine release with nothing relevant to us ⇒ still post, but the one line is just the headline feature.** Never paste the release notes.\\n- No preamble, no \\"is out!\\", no per-surface breakdown (VSCode/CLI/SDK), no closing line.\\n\\n2. Complete with output \\"Posted Claude Code {{check.result.latestVersion}} to in-app activity and configured delivery providers.\\" plus the charCount.\\n\\nDo NOT update any version state — the workflow\'s commit node handles that after you complete. Do NOT post more than once."},"next":"commit","inputs":{"check":"check"}},{"id":"commit","type":"swarm-script","label":"Commit new version to KV","config":{"scriptName":"claude-code-changelog-check","scope":"global","args":{"mode":"commit","version":"{{check.result.latestVersion}}"}},"inputs":{"check":"check"}}],"onNodeFailure":"fail"}\n```\n\n\n\n\n';
 
 // templates/workflows/competitor-radar/config.json
 var config_default67 = `{
@@ -16671,6 +16809,8 @@ var content_default72 = `# PR Review Status Sweep
 
 This topology-preserving self-hosted port removes installation-specific identities, endpoints, and credentials while retaining the live workflow's nodes, edges, input mappings, guards, retries, cooldown, and triggers. Configure the declared template parameters and integrations before enabling it.
 
+Prerequisite: the \`sweep\` node runs the agent-scoped script \`pr-review-status-sweep\`, which is not seeded. Author it before enabling the workflow, or every run fails at that node.
+
 \`\`\`json
 {"name":"pr-review-status-sweep","description":"Cron-triggered deterministic sweep for {{REPO_URL}} open PRs. The steady-state path is swarm-script only: enumerate non-draft PRs, run global pr-review-status, enforce KV run/per-PR leases and idempotency markers, and stay silent on clean sweeps. The single Phase A agent-task node is gated on actionableCount > 0. Phase B is disabled: no auto-push, no merge, no thread resolution.","nodes":[{"id":"sweep","type":"swarm-script","label":"Deterministic PR review action-item sweep","config":{"scriptName":"pr-review-status-sweep","scope":"agent","args":{"repo":"{{REPO_URL}}","limit":50,"phaseBEnabled":false,"slackChannelId":null,"slackThreadTs":null}},"next":"has-action-items"},{"id":"has-action-items","type":"property-match","label":"Gate: only continue when actionItems > 0","config":{"mode":"all","conditions":[{"field":"sweep.result.actionableCount","op":"gt","value":0}]},"next":{"true":"handle-action-items"}},{"id":"handle-action-items","type":"agent-task","label":"Phase A handler for unprocessed review action items","config":{"template":"{{sweep.result.handlerPrompt}}","tags":["pr-review-status","phase-a","review-action-items"],"priority":60,"dir":"/workspace/repository","vcsRepo":"{{REPO_URL}}","model":"gpt-5.5"},"inputs":{"sweep":"sweep"}}],"onNodeFailure":"fail"}
 \`\`\`

package/dist/{index-c6zsv1bd.js → index-bjmjh9h4.js}

@@ -2,23 +2,23 @@ import {
   getEmbeddingProvider,
   getMemoryStore,
   resetEmbeddingProvider
-} from "./cli-65hjmev5.js";
-import"./cli-xberxa1r.js";
-import"./cli-aehm1rbq.js";
+} from "./cli-kc3dp84d.js";
+import"./cli-10ym38qc.js";
 import"./cli-2658f6at.js";
-import"./cli-47m6dkd3.js";
-import"./cli-4198qc9v.js";
-import"./cli-3gmcwfyx.js";
-import"./cli-ggm92wcn.js";
-import"./cli-19jenss3.js";
-import"./cli-dv6cdjs2.js";
+import"./cli-g9df2m37.js";
+import"./cli-e4xnc0qp.js";
+import"./cli-ardpzhjm.js";
 import"./cli-n7h1kqpf.js";
-import"./cli-de1396j2.js";
+import"./cli-rgjprct3.js";
+import"./cli-dv6cdjs2.js";
 import"./cli-cqt19wg6.js";
+import"./cli-19jenss3.js";
+import"./cli-de1396j2.js";
 import"./cli-ej6gbxfb.js";
+import"./cli-7zttzetj.js";
 import"./cli-sd0mxa3c.js";
 import"./cli-w5e1d1vv.js";
-import"./cli-c07r9a2m.js";
+import"./cli-48527fpw.js";
 import"./cli-r2ap2czm.js";
 import"./cli-zf8jjwex.js";
 import"./cli-bc05qbss.js";

package/dist/{index-chgdkq36.js → index-cd151qkq.js}

@@ -4,53 +4,57 @@ import {
   runScheduleNow,
   startScheduler,
   stopScheduler
-} from "./cli-ftfvggzx.js";
+} from "./cli-79aq9cgb.js";
 import"./cli-0z2v4nhw.js";
-import"./cli-tt9k8r35.js";
-import"./cli-vhjwh6cz.js";
+import"./cli-cpvsaqsw.js";
 import"./cli-re8z5p8p.js";
-import"./cli-3dpj7atn.js";
-import"./cli-aw1jwp1r.js";
-import"./cli-aky8tctm.js";
-import"./cli-g8djp6qe.js";
-import"./cli-ws6rqycm.js";
-import"./cli-wscdvcqz.js";
-import"./cli-fgqxwrpv.js";
+import"./cli-jsp14b6c.js";
+import"./cli-z9x0sh1t.js";
+import"./cli-9yg65c1j.js";
+import"./cli-cygyqj3b.js";
+import"./cli-m4excttz.js";
+import"./cli-0n2e4x49.js";
+import"./cli-fjtp3463.js";
 import"./cli-epan13p1.js";
 import"./cli-y89t4nca.js";
 import"./cli-f14fvzag.js";
-import"./cli-987hg0aa.js";
-import"./cli-53sz8gkz.js";
-import"./cli-jsp14b6c.js";
-import"./cli-65hjmev5.js";
-import"./cli-xberxa1r.js";
-import"./cli-bsakbbkm.js";
+import"./cli-rfezr056.js";
+import"./cli-vhjwh6cz.js";
+import"./cli-3dpj7atn.js";
+import"./cli-gzyh0j0g.js";
+import"./cli-rb9m6rpe.js";
+import"./cli-rykfmgwg.js";
+import"./cli-vwbbaecp.js";
+import"./cli-qv4jv8bx.js";
 import"./cli-fad8m16k.js";
+import"./cli-kc3dp84d.js";
+import"./cli-10ym38qc.js";
+import"./cli-bsakbbkm.js";
 import"./cli-51tf7ac3.js";
-import"./cli-aehm1rbq.js";
-import"./cli-j57qkrpq.js";
+import"./cli-wgjx0q33.js";
 import"./cli-q51yprfq.js";
 import"./cli-3er6gcsn.js";
 import"./cli-2658f6at.js";
 import"./cli-yatxqynm.js";
-import"./cli-47m6dkd3.js";
-import"./cli-4198qc9v.js";
-import"./cli-3gmcwfyx.js";
-import"./cli-ggm92wcn.js";
-import"./cli-19jenss3.js";
-import"./cli-dv6cdjs2.js";
+import"./cli-g9df2m37.js";
+import"./cli-e4xnc0qp.js";
+import"./cli-ardpzhjm.js";
 import"./cli-n7h1kqpf.js";
-import"./cli-de1396j2.js";
+import"./cli-rgjprct3.js";
+import"./cli-dv6cdjs2.js";
 import"./cli-cqt19wg6.js";
+import"./cli-19jenss3.js";
+import"./cli-de1396j2.js";
 import"./cli-ej6gbxfb.js";
+import"./cli-7zttzetj.js";
 import"./cli-sd0mxa3c.js";
 import"./cli-w5e1d1vv.js";
-import"./cli-c07r9a2m.js";
+import"./cli-48527fpw.js";
 import"./cli-r2ap2czm.js";
-import"./cli-5b6b62tz.js";
+import"./cli-13hw4z91.js";
 import"./cli-btbzvq95.js";
 import"./cli-1m2e086m.js";
-import"./cli-mcnhgnn1.js";
+import"./cli-ykk5jaax.js";
 import"./cli-bzr0ftht.js";
 import"./cli-bd957dgb.js";
 import"./cli-pzxba7gw.js";