Retain skipped-lock settlement and failed native cancellation work

Co-Authored-By: Paperclip <noreply@paperclip.ing>

server/src/services/heartbeat/agent-status.test.ts

@@ -6,23 +6,29 @@ import {
 } from "@paperclipai/db";
 import { and, eq, sql } from "drizzle-orm";
 import { afterAll, beforeAll, beforeEach, describe, expect, it } from "vitest";
+import { resolveExternalTestDatabaseUrl } from "../../__tests__/helpers/external-test-database.js";
 import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "../../__tests__/helpers/embedded-postgres.js";
 import { createHeartbeatAgentStatus, settledAgentWorkCondition } from "./agent-status.js";
 
-const support = await getEmbeddedPostgresTestSupport();
+const external = resolveExternalTestDatabaseUrl("PAPERCLIP_AGENT_STATUS_TEST_DATABASE_URL");
+const support = external ? { supported: true } : await getEmbeddedPostgresTestSupport();
 const describePostgres = support.supported ? describe : describe.skip;
 if (!support.supported) console.warn(`Skipping agent status database tests: ${support.reason}`);
 
 describePostgres("heartbeat agent status", () => {
   let db: Db;
-  let database: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>>;
+  let database: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | undefined;
   let service: ReturnType<typeof createHeartbeatAgentStatus>;
   const live = new Set<string>();
   const old = () => new Date(Date.now() - 60 * 60_000);
 
   beforeAll(async () => {
-    database = await startEmbeddedPostgresTestDatabase("paperclip-agent-status-");
-    db = createDb(database.connectionString);
+    if (!external) database = await startEmbeddedPostgresTestDatabase("paperclip-agent-status-");
+    db = createDb(external ?? database!.connectionString);
+    if (external) {
+      db.$client.options.onnotice = () => {};
+      await db.execute(sql`truncate companies cascade`);
+    }
     service = createHeartbeatAgentStatus(db);
   }, EMBEDDED_POSTGRES_TEST_TIMEOUT_MS);
   beforeEach(async () => {
@@ -38,7 +44,7 @@ describePostgres("heartbeat agent status", () => {
     await db.delete(agents);
     await db.delete(companies);
   });
-  afterAll(async () => { await database?.cleanup(); });
+  afterAll(async () => { await db?.$client.end({ timeout: 1 }); await database?.cleanup(); });
 
   async function seed(status = "interrupted") {
     const companyId = randomUUID(), agentId = randomUUID(), runId = randomUUID(), issueId = randomUUID();

server/src/services/heartbeat/agent-status.ts

@@ -134,7 +134,13 @@ export function createHeartbeatAgentStatus(db: Db) {
         const [locked] = await tx.select({ id: agents.id }).from(agents).where(and(
           eq(agents.id, candidate.id), eq(agents.companyId, candidate.companyId),
         )).for("update", { skipLocked: true });
-        if (!locked) return null;
+        if (!locked) {
+          const [pending] = await tx.select({ id: agents.id }).from(agents).where(and(
+            eq(agents.id, candidate.id), eq(agents.companyId, candidate.companyId),
+          ));
+          if (pending) scope.onDeferredDeadline?.(Date.now() + 30_000);
+          return null;
+        }
         const [current] = await tx.select().from(agents).where(and(
           eq(agents.id, candidate.id), eq(agents.companyId, candidate.companyId),
           eq(agents.status, "running"), eq(agents.lifecycleState, "ready"),

server/src/services/heartbeat/live-recovery-work.ts

@@ -1,3 +1,4 @@
+import { pendingFailedNativeRetryCancellationCondition } from "../native-runtime/native-cancellation-request.js";
 import { settledNativeProcessIdentityCondition } from "../native-local-process-stop.js";
 import { and, asc, eq, gt, inArray, isNotNull, isNull, or, sql } from "drizzle-orm";
 import { agents, environmentLeases, heartbeatRuns, nativeRunFinalizations, type Db } from "@paperclipai/db";
@@ -69,7 +70,8 @@ export function registerLiveRecoveryWork(db: Db, coordinator: ReturnType<typeof
               kind === "native" ? and(eq(heartbeatRuns.runtimeMode, "native"), inArray(heartbeatRuns.status, ["running", "failed"]),
                 eq(nativeRunFinalizations.phase, "retryable_failure"), isNull(nativeRunFinalizations.resultId),
                 sql`${heartbeatRuns.contextSnapshot}->'nativeQuestionCancellation' is null`)
-                : kind === "question" ? and(inArray(heartbeatRuns.status, ["queued", "running", "scheduled_retry"]),
+                : kind === "question" ? and(or(inArray(heartbeatRuns.status, ["queued", "running", "scheduled_retry"]),
+                    pendingFailedNativeRetryCancellationCondition()),
                   sql`${heartbeatRuns.contextSnapshot}->'nativeQuestionCancellation' is not null`)
                   : kind === "active" ? and(eq(heartbeatRuns.status, "running"),
                     sql`${heartbeatRuns.contextSnapshot}->'nativeQuestionCancellation' is null`)

server/src/services/heartbeat/recovery.ts

@@ -1,3 +1,4 @@
+import { pendingFailedNativeRetryCancellationCondition } from "../native-runtime/native-cancellation-request.js";
 import { registerLiveRecoveryWork } from "./live-recovery-work.js";
 import { nativeEnvironmentSettlementDisposition, nativeEnvironmentSettlementWork } from "../native-runtime/native-environment-settlement-work.js";
 import { nativeWorkspaceFinalizationWork } from "../native-runtime/native-workspace-finalization-work.js";
@@ -2127,9 +2128,9 @@ export function createHeartbeatRecovery(db: Db, dependencies: HeartbeatRecoveryD
         and(
           scope.companyId ? eq(heartbeatRuns.companyId, scope.companyId) : undefined,
           scope.runId ? eq(heartbeatRuns.id, scope.runId) : undefined,
-          inArray(heartbeatRuns.status, [
+          or(inArray(heartbeatRuns.status, [
             ...CANCELLABLE_HEARTBEAT_RUN_STATUSES,
-          ]),
+          ]), pendingFailedNativeRetryCancellationCondition()),
           sql`${heartbeatRuns.contextSnapshot} -> ${NATIVE_QUESTION_CANCELLATION_CONTEXT_KEY} is not null`,
         ),
       );

server/src/services/heartbeat/run-control.ts

@@ -1242,18 +1242,19 @@ export function createHeartbeatRunControl(db: Db, dependencies: HeartbeatRunCont
     // under lock, and the final CAS requires its own unchanged acknowledged
     // retry fence. Re-reading only retryable_failure here would strand replay.
     const pendingNativeRetry =
-      run.runtimeMode === "native" && run.status === "failed" && (
+      run.runtimeMode === "native" && run.status === "failed" && Boolean(run.nativeIssueId) && (
         caseHandoffRetryClaimed || Boolean(options.cancellationRequestId) || await db
-          .select({ runId: nativeRunFinalizations.runId })
+          .select({ phase: nativeRunFinalizations.phase, failureCode: nativeRunFinalizations.failureCode })
           .from(nativeRunFinalizations)
           .where(
             and(
               eq(nativeRunFinalizations.runId, run.id),
               eq(nativeRunFinalizations.companyId, run.companyId),
-              eq(nativeRunFinalizations.phase, "retryable_failure"),
+              eq(nativeRunFinalizations.issueId, run.nativeIssueId!),
             ),
           )
-          .then((rows) => rows.length > 0)
+          .then(([coordinator]) => nativeRetryCancellationEligible({ runId: run!.id, companyId: run!.companyId,
+            issueId: run!.nativeIssueId!, resultJson: run!.resultJson }, coordinator))
       );
     if (
       !pendingNativeRetry &&

server/src/services/native-runtime/native-cancellation-request.ts

@@ -41,6 +41,32 @@ export function nativeRetryCancellationEligible(input: {
       && !!native.acknowledgementAuditId && native.acknowledgementAuditId !== native.intentAuditId));
 }
 
+export function pendingFailedNativeRetryCancellationCondition() {
+  const native = sql`${heartbeatRuns.resultJson}->'nativeCancellation'`;
+  const continuingStop = sql`${nativeRunFinalizations.phase} = 'terminal_failure'
+    and ${nativeRunFinalizations.failureCode} = 'native_retry_cancelled'
+    and ${native}->>'schema' = 'paperclip.native-cancellation.v1'
+    and jsonb_typeof(${native}->'intentId') = 'string' and length(${native}->>'intentId') > 0
+    and ${native}->>'runId' = ${heartbeatRuns.id}::text
+    and ${native}->>'companyId' = ${heartbeatRuns.companyId}::text
+    and ${native}->>'issueId' = ${heartbeatRuns.nativeIssueId}::text
+    and ${native}->>'scope' = 'run'
+    and ${native}->>'dispatchState' in ('pending', 'acknowledged')
+    and jsonb_typeof(${native}->'dispatched') = 'boolean'
+    and jsonb_typeof(${native}->'intentAuditId') = 'string' and length(${native}->>'intentAuditId') > 0
+    and (${native}->>'dispatchState' = 'pending' or (
+      jsonb_typeof(${native}->'acknowledgementAuditId') = 'string'
+      and length(${native}->>'acknowledgementAuditId') > 0
+      and ${native}->>'acknowledgementAuditId' <> ${native}->>'intentAuditId'))`;
+  return sql`${heartbeatRuns.runtimeMode} = 'native' and ${heartbeatRuns.status} = 'failed'
+    and exists (select 1 from ${nativeRunFinalizations}
+      where ${nativeRunFinalizations.runId} = ${heartbeatRuns.id}
+        and ${nativeRunFinalizations.companyId} = ${heartbeatRuns.companyId}
+        and ${nativeRunFinalizations.issueId} = ${heartbeatRuns.nativeIssueId}
+        and (${nativeRunFinalizations.phase} = 'retryable_failure' or (${continuingStop}))
+        and ${nativeRunFinalizations.resultId} is null)`;
+}
+
 /** Final failed -> cancelled CAS: a later board/recovery outcome must win.
  * The row-locking subquery prevents a coordinator-only writer from changing
  * the retry disposition between this check and the status update. */