Self-healing queue: transient provider failures park the provider, never burn retries

The July 9 run died at 07:22 when the GPT account hit its plan-side usage
limit: every later request failed with "The usage limit has been reached",
each failure counted against the 3-attempt retry budget, and 31 tasks were
abandoned for good while the worker kept hammering 12 doomed requests a
minute until the queue drained.

Root fix, three parts sharing one classifier:
- isTransientProviderFailure() in provider-runtime-domain recognises
  provider-side verdicts (usage limit, rate limit, 429, overloaded) plus the
  internal monthly-quota message; matching is against recorded
  task_runs.error_message rows, so historical damage heals retroactively.
- enqueueHeartbeatRuns computes the retry budget with that predicate instead
  of an exact match on the internal quota string alone.
- A transient failure parks the provider for a 10-minute cooldown: the
  heartbeat stops enqueuing its tasks and the worker leaves its queued runs
  unclaimed, then a single probe run re-arms or clears the park. Transitions
  are logged once each way.

Tests: predicate unit tests, budget-exemption regression on the raw provider
message, cooldown park/resume with an injected clock, claim exclusion.

tests/unit/task-queue-worker.test.ts

@@ -50,4 +50,29 @@ describe("task queue worker claim", () => {
     expect(states).toEqual(["running", "running"]);
     connection.close();
   });
+
+  test("leaves runs of a cooling-down provider queued instead of claiming them", () => {
+    const connection = new DatabaseConnection(join(tmpdir(), `ac-queue-${randomUUID()}.db`));
+    const organization = new OrganizationService(connection.db);
+    let orgId = "";
+    let agentId = "";
+    let providerId = "";
+    let taskId = "";
+    connection.transaction(() => {
+      orgId = organization.createOrganization({ organizationName: "Acme", employeeName: "Dana", mission: "m", goal: "g" });
+      providerId = (connection.db.prepare("select id from providers where org_id = ? and provider_key = 'openai'").get(orgId) as { id: string }).id;
+      agentId = organization.createAgent({ orgId, name: "CEO", role: "CEO", department: "Executive", modelProviderId: providerId, modelId: "gpt-5.4", budgetCents: 25000, managerAgentId: null });
+      taskId = organization.createTask({
+        orgId, title: "Kickoff", description: "Start.", status: TASK_STATUS.BACKLOG, assigneeAgentId: agentId,
+        risk: RISK_LEVEL.LOW, projectId: null, goalId: null, workspaceId: null, priority: TASK_PRIORITY.NORMAL, requiresFilesystem: false,
+      });
+    });
+    const runId = seedQueuedRun(connection, orgId, taskId, agentId, providerId);
+
+    expect(claimNextQueuedRun(connection, [providerId])).toBeNull();
+    expect(connection.db.prepare("select state from task_runs where id = ?").get(runId)).toEqual({ state: "queued" });
+
+    expect(claimNextQueuedRun(connection, [])?.id).toBe(runId);
+    connection.close();
+  });
 });