agents-relay 2.0.66 → 2.0.67

package/dist/adapters.js

@@ -146,7 +146,7 @@ export function parseDriverJson(output) {
     throw new Error('browser-worker driver returned no submitted receipt');
 }
 function browserWorkspaceCli(override = process.env.AGENTS_RELAY_BROWSER_WORKSPACE_COMMAND) {
-    return override ? { command: override, prefix: [] } : { command: 'npx', prefix: ['browser-workspace'] };
+    return override ? { command: override, prefix: [] } : { command: 'uvx', prefix: ['browser-workspace'] };
 }
 function browserWorkspaceCommand(cli, args, stdin, signal) {
     return new Promise((resolve, reject) => {

package/dist/reconciler-runtime.js

@@ -110,8 +110,16 @@ export class ReconcilerRuntimeBase {
             return activeOwner.applyEvent(event);
         if (event.type === 'task.started')
             return this.markWorkerStarted(event);
-        if (['task.completed', 'task.failed', 'task.blocked', 'task.cancelled'].includes(event.type))
-            return this.applyTerminalEvent(event);
+        if (['task.completed', 'task.failed', 'task.blocked', 'task.cancelled'].includes(event.type)) {
+            const result = await this.applyTerminalEvent(event);
+            if (event.type !== 'task.failed' || event.source?.watchdog !== true || event.data?.workflowEvent !== 'watchdog.failed' || result.reconcile)
+                return result;
+            // The watchdog has already committed FAILED. The graph owns the recovery
+            // action; this correlated event wakes the graph evaluation, not a retry.
+            const durable = (await this.store.load(event.job_id)).tasks.find(task => task.id === event.task_id);
+            return durable?.state === 'FAILED' && durable.executionHistory?.some(history => history.id === event.data?.executionId)
+                ? { applied: true, reconcile: true, reason: 'watchdog.failure-fact' } : result;
+        }
         if (['review.started', 'review.approved', 'review.changes_required', 'review.blocked'].includes(event.type))
             return this.applyReviewEvent(event);
         if (event.type === 'job.wake' || event.type === 'github.webhook')
@@ -285,7 +293,7 @@ export class ReconcilerRuntimeBase {
             return;
         if (task.adapter !== 'chatgpt' && task.executionId === executionId && live?.executionId === executionId)
             rearmTerminalEventDeadline(this.terminalTimers, taskId, task.timeoutMs - (Date.now() - live.launchBarrier), this.options.postExitTerminalGraceMs ?? 15_000, () => this.detach(this.timeoutTask(jobId, taskId, executionId), jobId, taskId, 'post-exit terminal event timeout'));
-        await this.emit(eventFor(jobId, taskId, task.parentTaskId, task.adapter === 'chatgpt' ? 'task.process.async_exited' : 'task.process.exited', live?.execution.processExit ? (live.execution.processExit.exitCode === 0 ? 'succeeded' : 'failed') : (error ? 'failed' : 'succeeded'), result?.summary ?? (live?.execution.processExit?.terminationReason === 'parent-shutdown' ? 'Worker interrupted by daemon shutdown' : error ? 'Worker runtime exited with error' : 'Worker runtime exited'), 'orchestrator', { authoritative: false, waitingForTerminalEvent: true, exitCode: live?.execution.processExit?.exitCode ?? null,
+        await this.emit(eventFor(jobId, taskId, task.parentTaskId, task.adapter === 'chatgpt' ? 'task.process.async_exited' : 'task.process.exited', live?.execution.processExit ? (live.execution.processExit.exitCode === 0 ? 'succeeded' : 'failed') : (error ? 'failed' : 'succeeded'), result?.summary ?? (live?.execution.processExit?.terminationReason === 'parent-shutdown' ? 'Worker interrupted by daemon shutdown' : error ? `Worker exited: ${error}${live?.execution.processExit ? ` (exit=${live.execution.processExit.exitCode ?? 'null'}${live.execution.processExit.signal ? ` signal=${live.execution.processExit.signal}` : ''})` : ''}` : 'Worker runtime exited'), 'orchestrator', { authoritative: false, waitingForTerminalEvent: true, exitCode: live?.execution.processExit?.exitCode ?? null,
             signal: live?.execution.processExit?.signal ?? null, terminationReason: live?.execution.processExit?.terminationReason ?? null, stderr: live?.execution.processExit?.stderr ?? '', processError: error, executionId, pid: live?.execution.pid ?? null }, { id: executionEventSource(jobId, taskId, executionId), agent: 'relay', component: 'agents-relay' }));
     }
     async timeoutTask(jobId, taskId, executionId) {
@@ -313,7 +321,7 @@ export class ReconcilerRuntimeBase {
             this.clearExecution(taskId, executionId);
             return;
         }
-        const event = eventFor(jobId, taskId, transition.task.parentTaskId, 'task.failed', 'failed', transition.task.error ?? failureMessage, 'user', { reason: failureReason, exitCode: exit?.exitCode ?? null, signal: exit?.signal ?? null, timeoutMs: transition.task.timeoutMs, workflowEvent: 'watchdog.failed' }, { agent: 'relay', component: 'agents-relay', watchdog: true });
+        const event = eventFor(jobId, taskId, transition.task.parentTaskId, 'task.failed', 'failed', transition.task.error ?? failureMessage, 'user', { reason: failureReason, exitCode: exit?.exitCode ?? null, signal: exit?.signal ?? null, timeoutMs: transition.task.timeoutMs, workflowEvent: 'watchdog.failed', executionId }, { agent: 'relay', component: 'agents-relay', watchdog: true });
         await this.emit(event);
         // Provider quota failures are recoverable. Drop the stale selection so the
         // next launch runs the normal worker/model router with fresh usage data.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agents-relay",
-  "version": "2.0.66",
+  "version": "2.0.67",
   "description": "Durable async agent jobs coordinated through GitHub pull requests",
   "type": "module",
   "bin": {