agents-relay 1.0.164 → 1.0.165

package/dist/cli.js

@@ -18,7 +18,7 @@ import { decisionMode, LayaCliDecisionEngine } from './decision.js';
 import { discoverAgents } from './registry.js';
 import { AgentObjectivePlanner, CommandObjectivePlanner } from './planner.js';
 import { extendRetryBudget, transitionJobEvent, transitionTaskEvent } from './scheduler.js';
-import { dueBuckets, processDueScheduledJobs, syncScheduleLabels } from './scheduled-jobs.js';
+import { assertScheduledAutonomousRepositoryCapability, dueBuckets, processDueScheduledJobs, syncScheduleLabels } from './scheduled-jobs.js';
 import { resolveExecutionContext } from './execution-context.js';
 import { defaultWorkspaceRoot, resolveManagedProjectPath, resolveRepositoryProjectPath } from './workspace.js';
 import { runBlockerCommand } from './cli-blocker.js';
@@ -35,6 +35,7 @@ export async function ensureManagedGitHubJob(client, repositoryName, trustedAuth
     const store = new GitHubStore(client, repositoryName, pr.number, trustedAuthors);
     try {
         const existing = await store.load(options.id);
+        await assertScheduledAutonomousRepositoryCapability(client, repositoryName, existing);
         if (existing.schedule)
             await syncScheduleLabels(client, repositoryName, existing);
         return { job: existing, pr };
@@ -65,6 +66,7 @@ export async function ensureManagedGitHubJob(client, repositoryName, trustedAuth
     };
     if (options.schedule)
         job.schedule = options.schedule;
+    await assertScheduledAutonomousRepositoryCapability(client, repositoryName, job);
     await store.saveJob(job);
     if (job.schedule)
         await syncScheduleLabels(client, repositoryName, job);
@@ -448,6 +450,7 @@ async function runJobCommand(action, args) {
             throw new Error('--continue-kind and --continue-target must be supplied together');
         job.continuation = next;
     }
+    await assertScheduledAutonomousRepositoryCapability(auth.client, repo, job);
     job.updatedAt = new Date().toISOString();
     await store.saveJob(job);
     if (hasArg(args, '--schedule') && job.schedule)

package/dist/reconciler.js

@@ -228,9 +228,17 @@ export class Reconciler extends ReconcilerReviewBase {
         }
     }
     async recoverLostExecutions(job, now) {
-        for (const task of job.tasks.filter(item => item.state === 'RUNNING' || (item.state === 'QUEUED' && item.executionId !== null))) {
-            const expired = task.leaseExpiresAt !== null && new Date(task.leaseExpiresAt).getTime() <= now;
-            if (!expired)
+        const candidates = job.tasks.filter(item => item.state === 'RUNNING' || (item.state === 'QUEUED' && item.executionId !== null));
+        for (const staleTask of candidates) {
+            if (staleTask.leaseExpiresAt === null || new Date(staleTask.leaseExpiresAt).getTime() > now)
+                continue;
+            // Re-read durable state before applying lease recovery: another reconciler may have accepted a terminal event or launched a newer execution.
+            const task = (await this.store.load(job.id)).tasks.find(item => item.id === staleTask.id);
+            if (!task)
+                continue;
+            const sameGeneration = task.executionId === staleTask.executionId && task.leaseOwner === staleTask.leaseOwner && task.leaseExpiresAt === staleTask.leaseExpiresAt;
+            const recoverable = task.state === 'RUNNING' || (task.state === 'QUEUED' && task.executionId !== null);
+            if (!sameGeneration || !recoverable || task.leaseExpiresAt === null || new Date(task.leaseExpiresAt).getTime() > now)
                 continue;
             this.live.get(task.id)?.execution.cancel();
             const planner = this.plannerLive.get(task.id);
@@ -239,8 +247,7 @@ export class Reconciler extends ReconcilerReviewBase {
                 planner.controller.abort();
                 this.plannerLive.delete(task.id);
             }
-            const failedEvent = task.state === 'RUNNING' ? 'task.failed' : 'fail';
-            await transitionTaskEvent(task, failedEvent);
+            await transitionTaskEvent(task, task.state === 'RUNNING' ? 'task.failed' : 'fail');
             task.error = 'Lease expired';
             task.leaseOwner = null;
             task.leaseExpiresAt = null;
@@ -248,12 +255,11 @@ export class Reconciler extends ReconcilerReviewBase {
             if (task.attempt < task.maxAttempts) {
                 await transitionTaskEvent(task, 'retry');
                 await this.store.saveTask(task);
+                continue;
             }
-            else {
-                task.error += ' after maximum attempts';
-                await this.store.saveTask(task);
-                await this.emit(eventFor(job.id, task.id, task.parentTaskId, 'task.failed', 'failed', task.error, 'user', { reason: 'lease_expired' }));
-            }
+            task.error += ' after maximum attempts';
+            await this.store.saveTask(task);
+            await this.emit(eventFor(job.id, task.id, task.parentTaskId, 'task.failed', 'failed', task.error, 'user', { reason: 'lease_expired' }));
         }
     }
     async planJob(jobId, guidance) {

package/dist/scheduled-jobs.js

@@ -1,6 +1,7 @@
 import { GitHubStore, loadManagedGitHubPullRequestGraphql } from './store.js';
 import { bucketStart, nextScheduleRun, parseRunBucketLabel, runBucketLabel, scheduleBucket } from './scheduler.js';
 export const AUTONOMOUS_LABEL = 'agents-relay:autonomous';
+export const AUTONOMOUS_SCHEDULER_WORKFLOW = '.github/workflows/autonomous-scheduler.yml';
 function searchPath(query, page) {
     return `search/issues?q=${encodeURIComponent(query)}&sort=created&order=asc&per_page=100&page=${page}`;
 }
@@ -17,6 +18,21 @@ export function indexedDueQuery(repository, bucket) {
     const label = runBucketLabel(bucket);
     return `repo:${repository} is:open is:pr label:"${AUTONOMOUS_LABEL}" label:"${label}"`;
 }
+export async function assertScheduledAutonomousRepositoryCapability(client, repository, job) {
+    if (job.executionMode !== 'autonomous' || !job.schedule)
+        return;
+    const metadata = await client.request(`repos/${repository}`);
+    const defaultBranch = typeof metadata.default_branch === 'string' && metadata.default_branch ? metadata.default_branch : 'main';
+    try {
+        await client.request(`repos/${repository}/contents/${AUTONOMOUS_SCHEDULER_WORKFLOW}?ref=${encodeURIComponent(defaultBranch)}`);
+    }
+    catch (error) {
+        const message = error instanceof Error ? error.message : String(error);
+        if (!/404|Not Found/i.test(message))
+            throw error;
+        throw new Error(`SCHEDULED_AUTONOMOUS_UNAVAILABLE: ${repository} default branch ${defaultBranch} must contain ${AUTONOMOUS_SCHEDULER_WORKFLOW} before creating or enabling a scheduled autonomous Job`);
+    }
+}
 async function issueLabels(client, repository, prNumber) {
     const labels = [];
     let page = 1;

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agents-relay",
-  "version": "1.0.164",
+  "version": "1.0.165",
   "description": "Durable async agent jobs coordinated through GitHub pull requests",
   "type": "module",
   "bin": {

package/skills/agents-relay/contracts/task-job-contract.md

@@ -109,7 +109,9 @@ SHA-bound final reviewer. For example, `video-director + market + style ->
 review-chair -> unified revision plan` is a project pattern, not a hard-coded
 Relay reviewer list.
 
-A scheduled autonomous job adds cron/timezone/next-run and missed-run/concurrency policy to the trusted job marker, plus the `agents-relay:autonomous` label and one bounded time-of-day `agents-relay:next-run:*` index label. The GitHub heartbeat discovers only indexed due candidates, validates the marker's exact `nextRunAt`, claims the slot idempotently, advances the durable next run, and pulses `agents-relay:schedule-wake`. GitHub webhook delivery then wakes local Relay for planner/worker execution. While the schedule is active, the durable Job remains `ACTIVE`; between runs its derived runtime status is `WAITING`. Scheduled recurring Jobs do not enter one-shot final-review/auto-merge after each satisfied run; older-cycle failures are historical evidence and do not block a later slot.
+A scheduled autonomous job adds cron/timezone/next-run and missed-run/concurrency policy to the trusted job marker, plus the `agents-relay:autonomous` label and one bounded time-of-day `agents-relay:next-run:*` index label. The target repository's default branch **must** contain `.github/workflows/autonomous-scheduler.yml`; this repository-level heartbeat is a required capability, not optional deployment glue. Job creation or update that would result in an autonomous Job with a schedule must fail loudly when that workflow is absent instead of persisting a schedule that can never advance. Unscheduled autonomous Jobs and fixed Jobs do not require this workflow.
+
+The GitHub heartbeat discovers only indexed due candidates, validates the marker's exact `nextRunAt`, claims the slot idempotently, advances the durable next run, and pulses `agents-relay:schedule-wake`. GitHub webhook delivery then wakes local Relay for planner/worker execution. While the schedule is active, the durable Job remains `ACTIVE`; between runs its derived runtime status is `WAITING`. Scheduled recurring Jobs do not enter one-shot final-review/auto-merge after each satisfied run; older-cycle failures are historical evidence and do not block a later slot.
 
 
 ## Task evidence and head identity