From 42fd568cf8f588334cacc6004aa23aff54daa52b Mon Sep 17 00:00:00 2001 From: Dotta <34892728+cryppadotta@users.noreply.github.com> Date: Sat, 31 Oct 2026 09:41:27 -0500 Subject: [PATCH] Drive issue recovery from committed changes and exact deadlines (#18402) Reviewed and verified at 11b49125db5ea1b274e69faf9d1abe057cdbb551. Co-Authored-By: Paperclip --- doc/plans/2026-10-30-issue-recovery-sleep.md | 32 ++ .../src/__tests__/company-portability.test.ts | 1 + .../issue-recovery-deadlines.test.ts | 525 ++++++++++++++++++ .../issue-recovery-work-lifecycle.test.ts | 149 +++++ .../issue-tree-control-service.test.ts | 2 +- .../__tests__/scoped-deadline-work.test.ts | 101 +++- .../server-startup-feedback-export.test.ts | 6 +- .../task-watchdogs-classifier.test.ts | 37 +- server/src/index.ts | 76 +-- server/src/services/agent-conversations.ts | 2 + .../telegram/attachment-failure.ts | 2 + server/src/services/company-deletion.ts | 2 + server/src/services/company-portability.ts | 6 +- .../services/delivery-work-notifications.ts | 6 + server/src/services/documents.ts | 11 + ...l-conversation-settlement-notifications.ts | 4 +- server/src/services/heartbeat.ts | 29 +- server/src/services/instance-settings.ts | 3 + server/src/services/issue-comment-writes.ts | 3 + server/src/services/issue-recovery-actions.ts | 6 + .../services/issue-recovery-notifications.ts | 16 + server/src/services/issue-tree-control.ts | 8 +- server/src/services/issues.ts | 50 +- .../src/services/legacy-controller-lease.ts | 12 +- .../chat-attachment-reuse.test.ts | 2 +- .../native-runtime/chat-attachment-reuse.ts | 6 +- .../native-runner-file-handoff.test.ts | 8 +- .../native-runner-file-handoff.ts | 6 +- .../native-workspace-finalizer.test.ts | 10 +- ...ative-status-reassessment-notifications.ts | 4 +- server/src/services/recovery/service.ts | 69 ++- server/src/services/recovery/work.ts | 113 ++++ .../services/run-dispatch-notifications.ts | 2 + server/src/services/scoped-deadline-work.ts | 20 +- server/src/services/system-recovery.ts | 2 + .../src/services/task-watchdog-diagnostics.ts | 16 - server/src/services/task-watchdog-work.ts | 49 ++ server/src/services/task-watchdogs.ts | 44 +- 38 files changed, 1224 insertions(+), 216 deletions(-) create mode 100644 doc/plans/2026-10-30-issue-recovery-sleep.md create mode 100644 server/src/__tests__/issue-recovery-deadlines.test.ts create mode 100644 server/src/__tests__/issue-recovery-work-lifecycle.test.ts create mode 100644 server/src/services/issue-recovery-notifications.ts create mode 100644 server/src/services/recovery/work.ts delete mode 100644 server/src/services/task-watchdog-diagnostics.ts create mode 100644 server/src/services/task-watchdog-work.ts diff --git a/doc/plans/2026-10-30-issue-recovery-sleep.md b/doc/plans/2026-10-30-issue-recovery-sleep.md new file mode 100644 index 00000000000..f6a8bcaba11 --- /dev/null +++ b/doc/plans/2026-10-30-issue-recovery-sleep.md @@ -0,0 +1,32 @@ +# Issue recovery without periodic scans + +The issue recovery owners reconstruct their current obligations once at startup. Ordinary comment writes invalidate only the affected issue for assignment and lock recovery. Lifecycle, graph, run, configuration and eligibility changes invalidate their company. The coordinator keeps scopes, per-issue deadlines, and per-entry failures in memory. Its pending check does not query the database. + +| Owner | Durable truth and producer boundary | Deadline or event | Exit | +| --- | --- | --- | --- | +| Stranded assignment | Visible assigned todo/in-progress/review issues; issue create/update/checkout/release; run lifecycle and execution control; agent/company/budget/configuration; interaction, approval and subtree hold changes | A committed eligibility change. A transient continuation uses the latest finish plus the existing exponential delay. | An execution path, durable wait, escalation, or current ineligibility. | +| Orphan blocker assignment | Agent-created unassigned todo/blocked blockers with a nonterminal dependent; issue, relation, agent and company changes | Once per changed company, independent of assignment candidates. | Assigned, no longer blocking, or creator cannot execute until its next eligibility change. | +| Active recovery actions | Active/escalated action records, including actions on completed sources; action, issue, run and wait changes | Once per changed company, independent of assignment candidates. | Resolved, restored path, explicit hold or a separately owned retry. | +| Resolved dependency | Blocked assigned issues and company-scoped blocker relations; blocker status or relation changes through issue service and import; run/control and pause gate changes | The committing change. A failed enqueue retains that issue with error backoff. | Existing idempotent wake, live path, unresolved dependency or deliberate self-block. | +| Task watchdog | Active issue watchdogs and their current source subtree; normal watchdog upsert/disable; issue/comment/document/work-product and wait changes | Exact source creation plus the existing 15-second first-run grace. An incomplete scan retains the watchdog with error backoff. | Live path, open/reviewed reusable review, disabled configuration, or ineligible source. | +| Stale issue lock | Existing checkout/execution run references; issue and run lifecycle changes | A committing ownership change, or the fresh owning controller's saved lease expiry. | No stale reference, a valid owner, or the existing guarded terminalization and lock clear. | + +Local comment hints do not broaden into an assignment check for every open task. A real PostgreSQL regression starts with1,000 open assigned issues, writes one comment through `issueService.addComment`, and observes exactly one assignment check; a subsequent company eligibility notification still checks all1,000. Restoring the previous comment hint makes that same regression check all1,000 after the comment. The test substitutes the expensive assignment decision only to count its invocations; it uses the real transaction, notification, coordinator and paged SQL. Separate producer acceptance cases exercise real recovery decisions and process execution. + +Parent/descendant disposition repair and shared execution references make status and run changes broader than a comment. Their existing notification boundaries deliberately retain company scope. Orphan blockers, active recovery actions, resolved dependencies and watchdogs also keep their company/subtree duties; an issue comment does not drop those independent obligations. The scope serializer selects known primitive fields and never serializes an entire insert or update object. + +Reconstruction uses keyset pages of at most100rows. Repeated company hints coalesce reconstruction for30seconds. Already-known entry deadlines preempt that spacing without an early probe on each comment. Scheduling suppression is read once per pass. A failed read keeps scoped backoff debt. The two subsidiary company repairs do not run inside the per-issue loop. Legacy direct aggregate API calls retain both repairs. + +The owner methods accept company and issue/watchdog identity. A narrowed lock check still reads other same-company references before using terminal-issue authority. A stale terminal alias cannot end an active issue's shared run. The controller lease owner supplies its fresh expiry; the existing write predicate revalidates the observed boot ID and database-clock expiry. + +Producer coverage uses the existing run-dispatch, execution-control, issue-review-state, native status reassessment and external conversation settlement boundaries. Direct gaps have explicit signals inside their owning transaction: document writes/import, attachment removal, blocker import, recovery-action adoption/mutation, conversation pause release, Telegram failure comment replacement, native artifact title/metadata updates and company deletion. Metadata-only comment classification that does not change timestamp, visibility or execution eligibility needs no additional watchdog activation. Approval links and decisions use their existing issue-review/continuation effects. Work-product create/update/delete/import uses its existing native status boundary. + +The new owners replace only these four startup and periodic calls. Deferred comments, silent active runs and residual orphan/resource recovery retain their existing backstop until the next slice. Every previously migrated native-owner skip remains unchanged. + +The ordinary dependency and watchdog process controls request completion through a loopback test-operator boundary before exiting. That boundary validates the actual run/company/agent and uses issue service; the watchdog control also disables its source through watchdog service. These cases prove normal completion without creating new disposition debt. The separate incomplete-process control prints an execution proof but cannot apply a task disposition, so the test operator completes that task through issue service after the existing policy saves a retry. If the existing continuation policy already saved a disposition-repair retry, the test preserves its actual timer and stored deadline on the real clock. Cleanup joins both competing coordinators before inspecting cancellation. A separate acceptance case deliberately waits for a production-created retry and verifies that exact row becomes cancelled, then all registered deadlines settle before the twenty-minute virtual idle measurement. Its120-second budget covers the existing60-second retry,30-second reconstruction and real I/O; the ordinary dependency test retains90seconds. Installing fake timers after an owner armed a real timer left that timer waiting on wall time despite virtual advances, so cleanup does not switch clocks while any owner obligation remains. The final quiet proof requires no registered deadlines, no tracked in-flight work and no owner SQL. It does not claim a saved future retry is already drained. + +Active action repair has no separate grace or lease countdown. Its delayed disposition repair first writes a scheduled-retry run, then mirrors the date into action wakePolicy.retryAt and timeoutAt. The dispatch owner owns that saved run deadline. Other skipped gates wait for their existing execution, wait, pause, budget, or finalizer producer; the company action worker does not add a polling fallback. + +Agent Chat is an instance-wide eligibility gate for saved conversation comments. An effective disabled-to-enabled transition publishes the existing stranded-assignment topic before the settings write in the same transaction. The worker reconstructs eligible conversation assignments after commit; other issue owners are not activated by this flag. Effective unchanged values, unrelated flags and disabling do not publish assignment hints. A rolled-back enable leaves the accepted comment parked. + +The real PostgreSQL control accepts a valid conversation comment while chat is enabled, disables chat before registering recovery, and proves the outbox stays quiet. Committing the ordinary settings enable alone launches one real process. That process calls a controlled loopback reply boundary which writes the agent comment through issue service; normal conversation completion consumes the message and returns to waiting. Rollback, unchanged/unrelated settings and disable-before-dispatch controls retain input without launching a run. Idle checks inspect actual PostgreSQL statements over twenty virtual minutes, including transactional queries. diff --git a/server/src/__tests__/company-portability.test.ts b/server/src/__tests__/company-portability.test.ts index fdf00b828af..f6dbbf552b6 100644 --- a/server/src/__tests__/company-portability.test.ts +++ b/server/src/__tests__/company-portability.test.ts @@ -4168,6 +4168,7 @@ describe("company portability", () => { const insertedRelationValues: Array> = []; const monitorUpdates: Array> = []; const db = { + transaction: async (write: (tx: unknown) => Promise) => write(db), insert: () => ({ values: (rows: Array>) => ({ onConflictDoNothing: async () => { diff --git a/server/src/__tests__/issue-recovery-deadlines.test.ts b/server/src/__tests__/issue-recovery-deadlines.test.ts new file mode 100644 index 00000000000..c155007f253 --- /dev/null +++ b/server/src/__tests__/issue-recovery-deadlines.test.ts @@ -0,0 +1,525 @@ +import { createServer } from "node:http"; +import { setImmediate as immediate } from "node:timers/promises"; +import { idleWorkSnapshot } from "../services/task-admission.js"; +import { randomUUID } from "node:crypto"; +import { and, eq, sql } from "drizzle-orm"; +import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from "vitest"; +import { agents, authUsers, companies, companyMemberships, createDb, heartbeatRuns, issueRecoveryActions, issueRelations, issues, issueWatchdogs, issueComments } from "@paperclipai/db"; +import { resolveExternalTestDatabaseUrl } from "./helpers/external-test-database.js"; +import { getEmbeddedPostgresTestSupport, startEmbeddedPostgresTestDatabase } from "./helpers/embedded-postgres.js"; +import { heartbeatService } from "../services/heartbeat.js"; +import { instanceSettingsService } from "../services/instance-settings.js"; +import { undeliveredConversationComments } from "../services/agent-conversations.js"; +import { DELIVERY_QUEUES, subscribeDeliveryWork } from "../services/delivery-work-notifications.js"; +import { issueService } from "../services/issues.js"; +import { issueRecoveryActionService } from "../services/issue-recovery-actions.js"; +import { registerIssueRecoveryWork } from "../services/recovery/work.js"; +import { notifyIssueRecovery } from "../services/issue-recovery-notifications.js"; +import { taskWatchdogService } from "../services/task-watchdogs.js"; +import { createDeliveryWorkCoordinator } from "../services/delivery-work-coordinator.js"; + +vi.setConfig({ testTimeout: 90_000 }); + +const external = resolveExternalTestDatabaseUrl("PAPERCLIP_ISSUE_RECOVERY_TEST_DATABASE_URL"); +const support = external ? { supported: true } : await getEmbeddedPostgresTestSupport(); +describe.skipIf(!support.supported)("issue recovery production producers and deadlines", () => { + let database: Awaited> | undefined; + let db: ReturnType; + let heartbeat: ReturnType; + let coordinator: ReturnType; + let worker: ReturnType["registerIssueStateRecoveryWork"]>; + let dispatch: ReturnType["registerRunDispatchWork"]>; + let cancellation: ReturnType["registerScheduledRetryCancellationWork"]>; + let draining = false; + const tasks = new Map number | null; hasPending: () => Promise }>(); + const errors: unknown[] = []; + const passes = new Set>(); + const extraStops: Array<() => Promise> = []; + const extraDeadlines: Array<() => number | null> = []; + beforeAll(async () => { + if (!external) database = await startEmbeddedPostgresTestDatabase("issue-recovery-work-"); + db = createDb(external ?? database!.connectionString, { maxConnections: 6, idleTimeoutSeconds: 0, maxLifetimeSeconds: 0 }); + await Promise.all(Array.from({ length: 6 }, () => db.execute(sql`select pg_sleep(0.01)`))); + }, 90_000); + beforeEach(async () => { + await db.execute(sql`TRUNCATE companies CASCADE`); + heartbeat = heartbeatService(db); draining = false; errors.length = 0; + }); + afterEach(async () => { + for (const stop of extraStops.splice(0)) await stop(); + extraDeadlines.length = 0; + await worker?.stop(); await dispatch?.stop(); await cancellation?.stop(); await coordinator?.stop(); + await heartbeat.drainActiveRunExecutions(); + vi.useRealTimers(); vi.restoreAllMocks(); + expect(errors).toEqual([]); + }); + afterAll(async () => { await db?.$client.end({ timeout: 1 }); await database?.cleanup(); }); + async function start() { + coordinator = createDeliveryWorkCoordinator({ owner: db, canRun: () => !draining, canReconcile: () => true, + onError: error => errors.push(error) }); + tasks.clear(); + const register = coordinator.register.bind(coordinator); + coordinator.register = (queue, task) => { + tasks.set(queue, task); + return register(queue, { ...task, run: signal => { + const work = task.run(signal); passes.add(work); + void work.then(() => passes.delete(work), () => passes.delete(work)); + return work; + } }); + }; + worker = heartbeat.registerIssueStateRecoveryWork(coordinator, () => !draining); + dispatch = heartbeat.registerRunDispatchWork(coordinator, () => !draining); + cancellation = heartbeat.registerScheduledRetryCancellationWork(coordinator, () => !draining); + await Promise.all([worker.ready, dispatch.ready, cancellation.ready]); + } + async function compete() { + const other = heartbeatService(db); + const competing = createDeliveryWorkCoordinator({ owner: db, canRun: () => true, onError: error => errors.push(error) }); + const register = competing.register.bind(competing); + competing.register = (queue, task) => register(queue, { ...task, run: signal => { + const pass = task.run(signal); passes.add(pass); + void pass.then(() => passes.delete(pass), () => passes.delete(pass)); + return pass; + } }); + const work = other.registerIssueStateRecoveryWork(competing, () => true); + extraStops.push(() => competing.stop()); extraDeadlines.push(competing.nextWakeAt); await work.ready; + } + async function fixture() { + const companyId = randomUUID(); + await db.insert(authUsers).values({ id: "recovery-user", name: "Recovery operator", email: "recovery-user@example.test", createdAt: new Date(), updatedAt: new Date() }).onConflictDoNothing(); + await db.insert(companies).values({ id: companyId, name: "Recovery", issuePrefix: `R${companyId.slice(0, 7)}`, + requireBoardApprovalForNewAgents: false, defaultResponsibleUserId: "recovery-user" }); + await db.insert(companyMemberships).values({ companyId, principalId: "recovery-user", principalType: "user", status: "active", membershipRole: "owner" }); + const [agent] = await db.insert(agents).values({ companyId, name: "Recovery process", role: "engineer", status: "idle", + adapterType: "process", adapterConfig: { command: process.execPath, args: ["-e", "console.log('recovery-proof')"], cwd: process.cwd() }, + runtimeConfig: { heartbeat: { enabled: true, intervalSec: 0, wakeOnDemand: true } }, + }).returning(); + return { companyId, agentId: agent.id }; + } + async function completingProvider(f: { companyId: string; agentId: string }, beforeComplete?: () => Promise) { + const failures: unknown[] = []; + const listener = createServer(async (request, response) => { + try { + let body = ""; + for await (const chunk of request) body += chunk; + const { runId } = JSON.parse(body) as { runId: string }; + const [run] = await db.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.id, runId), + eq(heartbeatRuns.companyId, f.companyId), eq(heartbeatRuns.agentId, f.agentId))); + if (!run?.contextSnapshot?.issueId) throw new Error("Unknown controlled task run"); + await beforeComplete?.(); + await issueService(db).update(String(run.contextSnapshot.issueId), { status: "done" }); + response.end("ok"); + } catch (error) { failures.push(error); response.statusCode = 500; response.end("completion failed"); } + }); + await new Promise(resolve => listener.listen(0, "127.0.0.1", resolve)); + extraStops.push(async () => { listener.closeAllConnections(); await new Promise(resolve => listener.close(() => resolve())); }); + const port = (listener.address() as { port: number }).port; + const script = `fetch("http://127.0.0.1:${port}/complete", {method:"POST", body:JSON.stringify({runId:process.env.PAPERCLIP_RUN_ID})}).then(async response=>{if(!response.ok)throw new Error(await response.text());console.log("recovery-proof")}).catch(error=>{console.error(error);process.exitCode=1})`; + await db.update(agents).set({ adapterConfig: { command: process.execPath, args: ["-e", script], cwd: process.cwd() } }) + .where(eq(agents.id, f.agentId)); + return failures; + } + async function settled() { + await vi.waitFor(async () => { + await Promise.allSettled([...passes]); + await heartbeat.drainActiveRunExecutions(); + const wake = coordinator.nextWakeAt(); + const detail = wake === null ? "" : JSON.stringify({ now: Date.now(), tasks: await Promise.all([...tasks].map(async ([queue, task]) => ({ queue, at: task.nextRunAt?.(), pending: await task.hasPending() }))), + runs: (await db.select().from(heartbeatRuns)).map(run => ({ id: run.id, status: run.status, error: run.errorCode, lease: run.controllerLeaseExpiresAt, reason: run.contextSnapshot?.wakeReason })) }); + expect(wake, detail).toBeNull(); + expect(extraDeadlines.map(next => next())).toEqual(extraDeadlines.map(() => null)); + expect(idleWorkSnapshot().active).toBe(0); + }, { timeout: 40_000 }); + } + async function quiet() { + await settled(); + expect(await db.select().from(heartbeatRuns).where(sql`${heartbeatRuns.status} in ('queued', 'running')`)).toHaveLength(0); + const reads = vi.spyOn(db, "select"); const executes = vi.spyOn(db, "execute"); + const selected = reads.mock.calls.length, executed = executes.mock.calls.length; + const statements: string[] = [], priorDebug = db.$client.options.debug; + db.$client.options.debug = (_connection, query) => { statements.push(query); }; + if (!vi.isFakeTimers()) vi.useFakeTimers({ toFake: ["Date", "setTimeout", "clearTimeout"] }); + try { + await vi.advanceTimersByTimeAsync(20 * 60_000); + expect(reads).toHaveBeenCalledTimes(selected); expect(executes).toHaveBeenCalledTimes(executed); + expect(statements).toEqual([]); + } finally { vi.useRealTimers(); db.$client.options.debug = priorDebug; reads.mockRestore(); executes.mockRestore(); } + } + async function finish(issueId: string) { + const retries = () => db.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.status, "scheduled_retry"), + sql`${heartbeatRuns.contextSnapshot}->>'issueId' = ${issueId}`)); + const before = await retries(); + await issueService(db).update(issueId, { status: "done" }); + // Closing one blocker can legitimately start its dependent. Wait for this + // task's dispatch and execution; quiet() verifies the whole fixture later. + await vi.waitFor(async () => { + await Promise.allSettled([...passes]); + await heartbeat.drainActiveRunExecutions(); + expect(await db.select().from(heartbeatRuns).where(and( + sql`${heartbeatRuns.contextSnapshot}->>'issueId' = ${issueId}`, + sql`${heartbeatRuns.status} in ('queued', 'running')`, + ))).toHaveLength(0); + }, { timeout: 15_000 }); + const saved = [...new Map([...before, ...await retries()].map(run => [run.id, run])).values()]; + if (saved.length > 0) { + const trace: unknown[] = []; + await vi.waitFor(async () => { + await Promise.allSettled([...passes]); + await heartbeat.drainActiveRunExecutions(); + const remaining = await retries(); + if (remaining.length > 0) trace.push({ now: Date.now(), + deadlines: [coordinator.nextWakeAt(), ...extraDeadlines.map(next => next())], + remaining: remaining.map(run => ({ id: run.id, at: run.scheduledRetryAt })) }); + expect(remaining, JSON.stringify(trace)).toHaveLength(0); + }, { timeout: Math.max(...saved.map(run => run.scheduledRetryAt!.getTime())) - Date.now() + 30_000 }); + for (const retry of saved) { + const [settledRetry] = await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, retry.id)); + expect(settledRetry.status).toBe("cancelled"); + } + } + } + async function completed(issueId: string) { + let runId: string | undefined; + await vi.waitFor(async () => { + const runs = await db.select().from(heartbeatRuns).where(sql`${heartbeatRuns.contextSnapshot}->>'issueId' = ${issueId}`); + const run = runs.find(row => row.status === "running" || row.status === "succeeded"); + expect(run).toBeDefined(); runId = run!.id; + }, { timeout: 15_000 }); + await vi.waitFor(async () => { + await heartbeat.drainActiveRunExecutions(); + const [current] = await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, runId!)); + expect(current.status, JSON.stringify({ error: current.error, code: current.errorCode, stderr: current.stderrExcerpt })).toBe("succeeded"); + }, { timeout: 15_000 }); + const [run] = await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, runId!)); + expect(run.stdoutExcerpt).toContain("recovery-proof"); + return run; + } + async function savedConversation(withMessage = true) { + const f = await fixture(), settings = instanceSettingsService(db); + await settings.updateExperimental({ enableAgentChat: true, enableConferenceRoomChat: false }); + const replies: string[] = [], failures: unknown[] = []; + const listener = createServer(async (request, response) => { + try { + let body = ""; + for await (const chunk of request) body += chunk; + const { runId } = JSON.parse(body) as { runId: string }; + const [run] = await db.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.id, runId), + eq(heartbeatRuns.companyId, f.companyId), eq(heartbeatRuns.agentId, f.agentId))); + if (!run) throw new Error("Unknown controlled conversation run"); + await issueService(db).addComment(String(run.contextSnapshot?.issueId), "Saved chat delivered", { + agentId: f.agentId, runId: run.id, + }); + replies.push(run.id); response.end("ok"); + } catch (error) { failures.push(error); response.statusCode = 500; response.end("controlled reply failed"); } + }); + await new Promise(resolve => listener.listen(0, "127.0.0.1", resolve)); + extraStops.push(async () => { listener.closeAllConnections(); await new Promise(resolve => listener.close(() => resolve())); }); + const port = (listener.address() as { port: number }).port; + const script = `fetch("http://127.0.0.1:${port}/reply", {method:"POST", body:JSON.stringify({runId:process.env.PAPERCLIP_RUN_ID})}).then(async response=>{if(!response.ok)throw new Error(await response.text());console.log("recovery-proof")}).catch(error=>{console.error(error);process.exitCode=1})`; + await db.update(agents).set({ adapterConfig: { command: process.execPath, args: ["-e", script], cwd: process.cwd() } }) + .where(eq(agents.id, f.agentId)); + const chat = await issueService(db).create(f.companyId, { title: "Saved conversation", status: "in_review", + conversationAgentId: f.agentId, conversationUserId: "recovery-user", assigneeAgentId: f.agentId, + conversationState: "waiting" }); + const message = withMessage ? await issueService(db).addComment(chat.id, "Keep this message", { userId: "recovery-user" }, { clientRequestId: randomUUID() }) : null; + await settings.updateExperimental({ enableAgentChat: false }); + await start(); await quiet(); + expect(replies).toEqual([]); + return { ...f, settings, chat, message, replies, failures }; + } + it("dispatches a saved conversation only from the committed Agent Chat enable transition", async () => { + const f = await savedConversation(); + expect(await undeliveredConversationComments(db, f.companyId, f.chat.id)).toHaveLength(1); + await f.settings.updateExperimental({ enableAgentChat: true }); + expect(coordinator.nextWakeAt()).not.toBeNull(); + await vi.waitFor(async () => expect(await db.select().from(heartbeatRuns) + .where(eq(heartbeatRuns.companyId, f.companyId))).toHaveLength(1), { timeout: 40_000 }); + const run = await completed(f.chat.id); + expect(f.replies).toEqual([run.id]); expect(f.failures).toEqual([]); + expect(await undeliveredConversationComments(db, f.companyId, f.chat.id)).toEqual([]); + expect((await db.select().from(issues).where(eq(issues.id, f.chat.id)))[0]) + .toMatchObject({ conversationState: "waiting", executionRunId: null }); + expect(await db.select().from(issueComments).where(and(eq(issueComments.createdByRunId, run.id), + eq(issueComments.authorAgentId, f.agentId)))).toHaveLength(1); + await quiet(); + let hints = 0; + const stop = subscribeDeliveryWork(db, DELIVERY_QUEUES.strandedAssignments, () => { hints++; }); + try { await f.settings.updateExperimental({ enableAgentChat: true }); expect(hints).toBe(0); await quiet(); } + finally { stop(); } + expect(f.replies).toEqual([run.id]); + }); + it("keeps disabled saved conversations parked after rollback, unrelated flags and unchanged values", async () => { + const f = await savedConversation(); + await expect(db.transaction(async tx => { + await instanceSettingsService(tx as unknown as typeof db).updateExperimental({ enableAgentChat: true }); + throw new Error("chat flag rollback"); + })).rejects.toThrow("chat flag rollback"); + await quiet(); + expect((await f.settings.getExperimental()).enableAgentChat).toBe(false); + let hints = 0; + const stop = subscribeDeliveryWork(db, DELIVERY_QUEUES.strandedAssignments, () => { hints++; }); + try { + await f.settings.updateExperimental({ enableConferenceRoomChat: true }); + await f.settings.updateExperimental({ enableAgentChat: false }); + expect(hints).toBe(0); await quiet(); + } finally { stop(); } + expect(f.replies).toEqual([]); expect(f.failures).toEqual([]); + expect(await db.select().from(heartbeatRuns)).toEqual([]); + expect(await undeliveredConversationComments(db, f.companyId, f.chat.id)).toHaveLength(1); + }); + it("does not dispatch an accepted saved message after Agent Chat is disabled", async () => { + const f = await savedConversation(false); + await f.settings.updateExperimental({ enableAgentChat: true }); await quiet(); + draining = true; + await issueService(db).addComment(f.chat.id, "Retain while disabled", { userId: "recovery-user" }, { clientRequestId: randomUUID() }); + let hints = 0; + const stop = subscribeDeliveryWork(db, DELIVERY_QUEUES.strandedAssignments, () => { hints++; }); + try { await f.settings.updateExperimental({ enableAgentChat: false }); expect(hints).toBe(0); } + finally { stop(); } + draining = false; await quiet(); + expect(f.replies).toEqual([]); expect(f.failures).toEqual([]); + expect(await db.select().from(heartbeatRuns)).toEqual([]); + expect(await undeliveredConversationComments(db, f.companyId, f.chat.id)).toHaveLength(1); + }); + it("keeps empty, configured idle, and terminal history quiet", async () => { + await fixture(); await start(); await quiet(); + }); + it("creates a blocking child through the ordinary root service transaction", async () => { + const f = await fixture(); + const parent = await issueService(db).create(f.companyId, { title: "Parent", status: "todo" }); + const child = await issueService(db).createChild(parent.id, { title: "Blocking child", status: "todo", blockParentUntilDone: true }); + expect(child.parentBlockerAdded).toBe(true); + expect(await db.select().from(issueRelations).where(and(eq(issueRelations.companyId, f.companyId), + eq(issueRelations.issueId, child.issue.id), eq(issueRelations.relatedIssueId, parent.id)))).toHaveLength(1); + }); + it.each(["startup", "committed"])("restores blocker-only and completed-action debt with no assignment candidates (%s)", async mode => { + const f = await fixture(); + if (mode === "committed") { await start(); await quiet(); } + const blocker = await issueService(db).create(f.companyId, { title: "Orphan blocker", status: "blocked", createdByAgentId: f.agentId }); + const dependent = await issueService(db).create(f.companyId, { title: "Blocked dependent", status: "blocked", blockedByIssueIds: [blocker.id] }); + const completedSource = await issueService(db).create(f.companyId, { title: "Completed source", status: "done" }); + const action = await issueRecoveryActionService(db).upsertSourceScoped({ companyId: f.companyId, sourceIssueId: completedSource.id, + kind: "stranded_assigned_issue", ownerType: "agent", ownerAgentId: f.agentId, cause: "stranded_assigned_issue", + fingerprint: "source-terminal", nextAction: "Restore work", wakePolicy: { type: "wake_owner" }, evidence: {} }); + if (mode === "startup") await start(); + await vi.waitFor(async () => { + expect((await db.select().from(issues).where(eq(issues.id, blocker.id)))[0].assigneeAgentId).toBe(f.agentId); + expect((await db.select().from(issueRecoveryActions).where(eq(issueRecoveryActions.id, action.id)))[0].status).toBe("resolved"); + }, { timeout: 40_000 }); + await finish(blocker.id); await finish(dependent.id); await quiet(); + }); + it("bounds subsidiary scans for100 assignment candidates and coalesces repeated company writes", async () => { + const f = await fixture(), foreign = await fixture(); + await db.update(agents).set({ lifecycleState: "preparing" }).where(eq(agents.id, f.agentId)); + await db.insert(issues).values(Array.from({ length: 100 }, (_, index) => ({ companyId: f.companyId, + title: `Waiting setup ${index}`, status: "todo", assigneeAgentId: f.agentId }))); + const [source] = await db.insert(issues).values({ companyId: f.companyId, title: "Done source", status: "done" }).returning(); + const action = await issueRecoveryActionService(db).upsertSourceScoped({ companyId: f.companyId, sourceIssueId: source.id, + kind: "stranded_assigned_issue", ownerType: "agent", ownerAgentId: f.agentId, cause: "stranded_assigned_issue", + fingerprint: "query-budget", nextAction: "Restore work", wakePolicy: { type: "wake_owner" }, evidence: {} }); + const scans = { blockers: 0, actions: 0, loads: 0 }; + const originalSelect = db.select.bind(db); + vi.spyOn(db, "select").mockImplementation(((fields?: Record) => { + const query = originalSelect(fields as never); const from = query.from.bind(query); + query.from = ((table: unknown) => { + if (table === issues && fields?.id === issues.id && fields.companyId === issues.companyId && Object.keys(fields).length === 2) scans.loads++; + if (table === issueRelations && fields?.createdByAgentId === issues.createdByAgentId) scans.blockers++; + if (table === issueRecoveryActions && fields?.action === issueRecoveryActions) scans.actions++; + return from(table as never); + }) as typeof query.from; + return query; + }) as typeof db.select); + await start(); await settled(); + expect(scans.actions).toBe(1); expect(scans.blockers).toBe(0); expect(scans.loads).toBeLessThanOrEqual(8); + expect((await originalSelect().from(issueRecoveryActions).where(eq(issueRecoveryActions.id, action.id)))[0].status).toBe("resolved"); + const [foreignSource] = await db.insert(issues).values({ companyId: foreign.companyId, title: "Foreign done", status: "done" }).returning(); + const [foreignAction] = await db.insert(issueRecoveryActions).values({ companyId: foreign.companyId, sourceIssueId: foreignSource.id, + kind: "stranded_assigned_issue", ownerType: "board", cause: "stranded_assigned_issue", fingerprint: "foreign-query-budget", nextAction: "Inspect" }).returning(); + const before = { ...scans }; + for (let index = 0; index < 100; index++) await db.transaction(tx => notifyIssueRecovery(tx, { companyId: f.companyId })); + await new Promise(resolve => setTimeout(resolve, 100)); + expect(scans.loads).toBe(before.loads); + await settled(); + expect(scans.actions).toBe(before.actions); expect(scans.blockers).toBe(before.blockers); + expect(scans.loads).toBeLessThanOrEqual(before.loads + 4); + expect((await originalSelect().from(issueRecoveryActions).where(eq(issueRecoveryActions.id, foreignAction.id)))[0].status).toBe("active"); + expect(await originalSelect().from(heartbeatRuns)).toHaveLength(0); await quiet(); + }); + it("limits an ordinary comment to its issue among one thousand open assignments", async () => { + const f = await fixture(); + const rows = await db.insert(issues).values(Array.from({ length: 1000 }, (_, index) => ({ + companyId: f.companyId, title: `Open work ${index}`, status: "todo", assigneeAgentId: f.agentId, + }))).returning({ id: issues.id }); + const checked: string[] = []; + vi.useFakeTimers({ toFake: ["Date", "setTimeout", "clearTimeout"] }); + coordinator = createDeliveryWorkCoordinator({ owner: db, canRun: () => true, onError: error => errors.push(error) }); + const register = coordinator.register.bind(coordinator); + coordinator.register = (queue, task) => register(queue, { ...task, run: signal => { + const pass = task.run(signal); passes.add(pass); + void pass.then(() => passes.delete(pass), () => passes.delete(pass)); + return pass; + } }); + // Observe the actual paged reconstruction boundary without executing one + // thousand adapters. The producer, transaction, coordinator and SQL are real; + // the other acceptance cases exercise the resulting recovery decisions. + worker = registerIssueRecoveryWork(db, coordinator, { + stranded: async scope => { checked.push(scope.issueId); }, + orphanBlockers: async () => {}, recoveryActions: async () => {}, + dependencies: async () => ({ enqueueFailed: 0 }), locks: async () => {}, + watchdogs: async () => ({ incomplete: 0 }), schedulingSuppressed: async () => false, + }, () => true); + await worker.ready; + async function settleWork() { + for (let step = 0; step < 120; step++) { + await vi.advanceTimersByTimeAsync(1000); + await Promise.allSettled([...passes]); await immediate(); + if (coordinator.nextWakeAt() === null && idleWorkSnapshot().active === 0) return; + } + throw new Error("Recovery did not settle its committed work within two virtual minutes"); + } + await settleWork(); + expect(new Set(checked).size).toBe(1000); + checked.length = 0; + await issueService(db).addComment(rows[0].id, "New evidence on this task", { userId: "recovery-user" }); + await settleWork(); + expect(checked).toEqual([rows[0].id]); + // Company eligibility changes still reconstruct all assignments. Narrowing + // comment hints must not hide unrelated work after an operator resumes it. + checked.length = 0; + await db.transaction(tx => notifyIssueRecovery(tx, { companyId: f.companyId })); + await settleWork(); + expect(new Set(checked).size).toBe(1000); + await quiet(); + }); + it("dispatches an ordinary new assignment after commit and returns to quiet after completion", async () => { + const f = await fixture(); await start(); await quiet(); + const issue = await issueService(db).create(f.companyId, { title: "Recover assignment", status: "todo", assigneeAgentId: f.agentId }); + await completed(issue.id); + await finish(issue.id); await quiet(); + }, 90_000); + it("reacts to blocker resolution once and dispatches the durable dependency wake", async () => { + const f = await fixture(); + const blocker = await issueService(db).create(f.companyId, { title: "Blocker", status: "todo" }); + const dependent = await issueService(db).create(f.companyId, { title: "Dependent", status: "blocked", assigneeAgentId: f.agentId, + blockedByIssueIds: [blocker.id] }); + const failures = await completingProvider(f); + await start(); await quiet(); + await compete(); + await issueService(db).update(blocker.id, { status: "done" }); + const run = await completed(dependent.id); + expect(run.contextSnapshot?.wakeReason).toBe("issue_blockers_resolved"); + expect(failures).toEqual([]); + await finish(dependent.id); await quiet(); + expect(await db.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.companyId, f.companyId), + sql`${heartbeatRuns.contextSnapshot}->>'wakeReason' = 'issue_blockers_resolved'`))).toHaveLength(1); + expect(await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.companyId, f.companyId))).toHaveLength(1); + }, 90_000); + it("settles saved disposition debt on its original real-clock timers before measuring idle", async () => { + const f = await fixture(); + const blocker = await issueService(db).create(f.companyId, { title: "Saved debt blocker", status: "todo" }); + const issue = await issueService(db).create(f.companyId, { title: "Saved disposition debt", status: "blocked", + assigneeAgentId: f.agentId, blockedByIssueIds: [blocker.id] }); + await start(); await compete(); + await issueService(db).update(blocker.id, { status: "done" }); + await completed(issue.id); + let retryId: string | undefined; + await vi.waitFor(async () => { + const [retry] = await db.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.status, "scheduled_retry"), + sql`${heartbeatRuns.contextSnapshot}->>'issueId' = ${issue.id}`)); + expect(retry).toBeDefined(); retryId = retry!.id; + }, { timeout: 40_000 }); + await finish(issue.id); await quiet(); + expect((await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, retryId!)))[0].status).toBe("cancelled"); + }, 120_000); + it("uses ordinary watchdog configuration and subtree closure to dispatch a reusable review", async () => { + const f = await fixture(); + const source = await issueService(db).create(f.companyId, { title: "Finished subtree", status: "done" }); + const failures = await completingProvider(f, () => taskWatchdogService(db).disableForIssue(f.companyId, source.id)); + await start(); await quiet(); + await compete(); + const watchdog = await taskWatchdogService(db).upsertForIssue(f.companyId, source.id, { agentId: f.agentId }); + let reviewId: string | undefined; + await vi.waitFor(async () => { + const [row] = await db.select().from(issueWatchdogs).where(eq(issueWatchdogs.id, watchdog.watchdog.id)); + expect(row.watchdogIssueId).toBeTruthy(); reviewId = row.watchdogIssueId!; + }, { timeout: 15_000 }); + await completed(reviewId!); + expect(failures).toEqual([]); + expect(await db.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.companyId, f.companyId), + sql`${heartbeatRuns.contextSnapshot}->>'wakeReason' = 'task_watchdog_stopped_subtree'`))).toHaveLength(1); + await finish(reviewId!); + await taskWatchdogService(db).disableForIssue(f.companyId, source.id); + if (!vi.isFakeTimers()) vi.useFakeTimers({ toFake: ["Date", "setTimeout", "clearTimeout"] }); await quiet(); + }, 90_000); + it("bounds ordinary writes to their company and reconstructs foreign stale debt after restart", async () => { + const selected = await fixture(); await start(); await quiet(); + const foreign = await fixture(); + const [run] = await db.insert(heartbeatRuns).values({ companyId: foreign.companyId, agentId: foreign.agentId, + status: "failed", finishedAt: new Date() }).returning(); + const [stale] = await db.insert(issues).values({ companyId: foreign.companyId, title: "Foreign stale lock", status: "done", + checkoutRunId: run.id }).returning(); + await issueService(db).create(selected.companyId, { title: "Selected change", status: "done" }); await quiet(); + expect((await db.select().from(issues).where(eq(issues.id, stale.id)))[0].checkoutRunId).toBe(run.id); + await worker.stop(); await dispatch.stop(); await cancellation.stop(); await coordinator.stop(); + heartbeat = heartbeatService(db); await start(); await quiet(); + expect((await db.select().from(issues).where(eq(issues.id, stale.id)))[0].checkoutRunId).toBeNull(); + }); + it("fences nested assignment writes until outer commit and ignores rollback", async () => { + const f = await fixture(); await start(); await quiet(); + let committedId = ""; + await db.transaction(async outer => { + await outer.transaction(async nested => { + const issue = await issueService(db).create(f.companyId, { title: "Nested commit", status: "todo", assigneeAgentId: f.agentId }, nested); + committedId = issue.id; + }); + await new Promise(resolve => setTimeout(resolve, 100)); + expect(await db.select().from(heartbeatRuns)).toHaveLength(0); + }); + await completed(committedId); await finish(committedId); await settled(); + await expect(db.transaction(async outer => { + await outer.transaction(async nested => { + await issueService(db).create(f.companyId, { title: "Nested rollback", status: "todo", assigneeAgentId: f.agentId }, nested); + }); + throw new Error("rollback control"); + })).rejects.toThrow("rollback control"); + await quiet(); + expect(await db.select().from(issues).where(eq(issues.title, "Nested rollback"))).toHaveLength(0); + }, 90_000); + it("retains the first committed assignment during drain and executes on resume", async () => { + const f = await fixture(); await start(); await quiet(); draining = true; + const issue = await issueService(db).create(f.companyId, { title: "Drained assignment", status: "todo", assigneeAgentId: f.agentId }); + await new Promise(resolve => setTimeout(resolve, 100)); + const reads = vi.spyOn(db, "select"); + if (!vi.isFakeTimers()) vi.useFakeTimers({ toFake: ["Date", "setTimeout", "clearTimeout"] }); + try { await vi.advanceTimersByTimeAsync(90_000); expect(reads).not.toHaveBeenCalled(); } + finally { vi.useRealTimers(); reads.mockRestore(); } + expect(await db.select().from(heartbeatRuns)).toHaveLength(0); + draining = false; worker.wake(); dispatch.wake(); + await completed(issue.id); await finish(issue.id); await quiet(); + }, 90_000); + it("retains a fresh subtree's exact first-run grace then disarms on disable", async () => { + const f = await fixture(); + const source = await issueService(db).create(f.companyId, { title: "Fresh unassigned subtree", status: "todo" }); + await start(); await quiet(); + await taskWatchdogService(db).upsertForIssue(f.companyId, source.id, { agentId: f.agentId }); + await vi.waitFor(() => expect(coordinator.nextWakeAt()).toBe(source.createdAt.getTime() + 15_000), { timeout: 5_000 }); + expect(await db.select().from(issues).where(eq(issues.originKind, "task_watchdog"))).toHaveLength(0); + await taskWatchdogService(db).disableForIssue(f.companyId, source.id); + if (!vi.isFakeTimers()) vi.useFakeTimers({ toFake: ["Date", "setTimeout", "clearTimeout"] }); await quiet(); + }); + it("waits for a live foreign controller's exact stored lease before clearing a terminal lock", async () => { + const f = await fixture(); + const source = await issueService(db).create(f.companyId, { title: "Remote owner", status: "done" }); + const lease = new Date(Date.now() + 5_000); + const [run] = await db.insert(heartbeatRuns).values({ companyId: f.companyId, agentId: f.agentId, status: "running", + runtimeMode: "legacy", controllerBootId: randomUUID(), controllerLeaseExpiresAt: lease, + contextSnapshot: { issueId: source.id }, processPid: 2_000_000_000, startedAt: new Date() }).returning(); + await db.update(issues).set({ executionRunId: run.id }).where(eq(issues.id, source.id)); + await start(); + await vi.waitFor(() => expect(coordinator.nextWakeAt()).toBe(lease.getTime()), { timeout: 3_000 }); + expect((await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, run.id)))[0].status).toBe("running"); + await vi.waitFor(async () => expect((await db.select().from(issues).where(eq(issues.id, source.id)))[0].executionRunId).toBeNull(), { timeout: 12_000 }); + expect((await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, run.id)))[0].status).toBe("succeeded"); + if (!vi.isFakeTimers()) vi.useFakeTimers({ toFake: ["Date", "setTimeout", "clearTimeout"] }); await quiet(); + }, 90_000); +}); diff --git a/server/src/__tests__/issue-recovery-work-lifecycle.test.ts b/server/src/__tests__/issue-recovery-work-lifecycle.test.ts new file mode 100644 index 00000000000..52f465daa8e --- /dev/null +++ b/server/src/__tests__/issue-recovery-work-lifecycle.test.ts @@ -0,0 +1,149 @@ +import { PgDialect } from "drizzle-orm/pg-core"; +import { afterEach, describe, expect, it, vi } from "vitest"; +import { issueRecoveryActions, issueWatchdogs } from "@paperclipai/db"; +import { installDatabaseWorkSignals } from "../../../packages/db/src/work-signals.js"; +import { createDeliveryWorkCoordinator } from "../services/delivery-work-coordinator.js"; +import { notifyIssueRecovery } from "../services/issue-recovery-notifications.js"; +import { registerIssueRecoveryWork } from "../services/recovery/work.js"; +import { idleWorkSnapshot } from "../services/task-admission.js"; + +const stops: Array<() => Promise> = []; +afterEach(async () => { for (const stop of stops.splice(0)) await stop(); vi.useRealTimers(); }); +function fixture() { + vi.useFakeTimers(); vi.setSystemTime(1_000_000); + const dialect = new PgDialect(); + const rows = { issues: [] as Array<{ id: string; companyId: string }>, watchdogs: [] as Array<{ id: string; companyId: string }>, blockers: [] as Array<{ id: string; companyId: string }>, actions: [] as Array<{ id: string; companyId: string }> }; + const execute = vi.fn(async (query: any) => { + if (dialect.sqlToQuery(query).sql.includes("pg_current_xact_id")) return [{ xid: "42" }]; + throw new Error("unexpected SQL"); + }); + const load = vi.fn((table: unknown, distinct = false) => distinct + ? table === issueRecoveryActions ? rows.actions : rows.blockers + : table === issueWatchdogs ? rows.watchdogs : rows.issues); + const query = (distinct = false) => ({ from: (table: unknown) => ({ where: () => ({ orderBy: () => ({ limit: async () => load(table, distinct) }) }) }) }); + const db: any = installDatabaseWorkSignals({ execute, + select: () => query(), selectDistinct: () => query(true), + transaction: async (callback: (tx: any) => Promise) => callback({ execute, select: db.select, selectDistinct: db.selectDistinct, transaction: db.transaction }), + }); + const state = { draining: false, standby: false, suppressed: false, deadline: null as number | null, fail: false, incomplete: false }; + const check = vi.fn(async (scope: { onDeferredDeadline(at: number): void }) => { + if (state.fail) throw new Error("database unavailable"); + if (state.deadline !== null && state.deadline > Date.now()) scope.onDeferredDeadline(state.deadline); + }); + const orphanBlockers = vi.fn(async () => {}), recoveryActions = vi.fn(async () => {}); + const suppression = vi.fn(async () => state.suppressed); + const owner = { orphanBlockers, recoveryActions, stranded: check, dependencies: async (scope: any) => { await check(scope); return { enqueueFailed: 0 }; }, + locks: check, watchdogs: async (scope: any) => { await check(scope); return { incomplete: state.incomplete ? 1 : 0 }; }, + schedulingSuppressed: suppression }; + const coordinator = createDeliveryWorkCoordinator({ owner: db, canRun: () => !state.standby, + canReconcile: () => !state.standby, onError: vi.fn() }); + const worker = registerIssueRecoveryWork(db, coordinator, owner, () => !state.draining && !state.standby); + stops.push(() => coordinator.stop()); + return { db, rows, state, check, load, coordinator, worker, orphanBlockers, recoveryActions, suppression, + notify: () => db.transaction((tx: any) => notifyIssueRecovery(tx, { companyId: "selected" })), + settle: () => vi.advanceTimersByTimeAsync(1_000) }; +} +describe("issue recovery obligation lifecycle", () => { + it("has no timer, SQL, or owner probe after empty reconstruction", async () => { + const f = fixture(); await f.worker.ready; + expect(f.coordinator.nextWakeAt()).toBeNull(); const loaded = f.load.mock.calls.length; + await vi.advanceTimersByTimeAsync(20 * 60_000); + expect(f.load).toHaveBeenCalledTimes(loaded); expect(f.check).not.toHaveBeenCalled(); + }); + it("reads scheduling suppression once per pass instead of once per issue", async () => { + const f = fixture(); + f.rows.issues.push(...Array.from({ length: 25 }, (_, index) => ({ id: `issue-${index}`, companyId: "selected" }))); + await f.worker.ready; + expect(f.check).toHaveBeenCalledTimes(75); + expect(f.suppression).toHaveBeenCalledTimes(6); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("backs off a failed suppression read without probing an empty or failed owner repeatedly", async () => { + const f = fixture(); f.suppression.mockRejectedValueOnce(new Error("settings unavailable")); + await f.worker.ready; const reads = f.suppression.mock.calls.length; + expect(f.coordinator.nextWakeAt()).toBe(1_030_000); + await vi.advanceTimersByTimeAsync(29_999); expect(f.suppression).toHaveBeenCalledTimes(reads); + await vi.advanceTimersByTimeAsync(1); expect(f.suppression).toHaveBeenCalledTimes(reads + 1); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("normalizes a wide scope with cyclic SQL objects before publishing work hints", async () => { + const f = fixture(); await f.worker.ready; + const wide = { companyId: "selected", endpointId: issueRecoveryActions.id, table: issueRecoveryActions }; + await f.db.transaction((tx: object) => notifyIssueRecovery(tx, wide)); await f.settle(); + expect(f.coordinator.nextWakeAt()).toBeNull(); + const loads = f.load.mock.calls.length; + await vi.advanceTimersByTimeAsync(20 * 60_000); expect(f.load).toHaveBeenCalledTimes(loads); + }); + it("runs orphan blocker and action duties without assignment entries", async () => { + const f = fixture(); f.rows.blockers.push({ id: "selected", companyId: "selected" }); + f.rows.actions.push({ id: "selected", companyId: "selected" }); await f.worker.ready; + expect(f.check).not.toHaveBeenCalled(); + expect(f.orphanBlockers).toHaveBeenCalledExactlyOnceWith({ companyId: "selected" }); + expect(f.recoveryActions).toHaveBeenCalledExactlyOnceWith({ companyId: "selected" }); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("coalesces repeated company reconstruction without delaying an existing lease deadline", async () => { + const f = fixture(); f.rows.issues.push({ id: "issue", companyId: "selected" }); + f.state.deadline = 1_015_000; await f.worker.ready; + await f.notify(); await f.settle(); const loaded = f.load.mock.calls.length, checked = f.check.mock.calls.length; + for (let index = 0; index < 100; index++) { await f.notify(); await vi.advanceTimersByTimeAsync(10); } + expect(f.load).toHaveBeenCalledTimes(loaded); expect(f.check).toHaveBeenCalledTimes(checked); + await vi.advanceTimersByTimeAsync(13_000); + expect(f.state.deadline).toBe(1_015_000); + expect(f.coordinator.nextWakeAt()).toBe(1_031_000); + await vi.advanceTimersByTimeAsync(16_000); + expect(f.load.mock.calls.length).toBeGreaterThan(loaded); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("retains exact grace and lease deadlines without early owner probes", async () => { + const f = fixture(); f.rows.issues.push({ id: "issue", companyId: "selected" }); + f.rows.watchdogs.push({ id: "watchdog", companyId: "selected" }); f.state.deadline = 1_015_000; + await f.worker.ready; expect(f.coordinator.nextWakeAt()).toBe(1_015_000); + const checked = f.check.mock.calls.length; + await vi.advanceTimersByTimeAsync(14_999); expect(f.check).toHaveBeenCalledTimes(checked); + await vi.advanceTimersByTimeAsync(1); expect(f.check.mock.calls.length).toBe(checked * 2); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("releases settled producer holds during domain drain while coordinator remains open", async () => { + const f = fixture(); await f.worker.ready; f.state.draining = true; + f.rows.issues.push({ id: "issue", companyId: "selected" }); + await f.notify(); await f.settle(); const loaded = f.load.mock.calls.length; + await vi.advanceTimersByTimeAsync(90_000); + expect(f.load).toHaveBeenCalledTimes(loaded); expect(f.check).not.toHaveBeenCalled(); + expect(idleWorkSnapshot().active).toBe(0); + f.state.draining = false; f.worker.wake(); await f.settle(); + expect(f.check).toHaveBeenCalled(); expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("retries concrete failed entries and then disarms without reloading the company", async () => { + const f = fixture(); f.rows.issues.push({ id: "issue", companyId: "selected" }); f.state.fail = true; + await f.worker.ready; const loaded = f.load.mock.calls.length; + expect(f.coordinator.nextWakeAt()).toBe(1_030_000); + await vi.advanceTimersByTimeAsync(29_999); const checked = f.check.mock.calls.length; + f.state.fail = false; await vi.advanceTimersByTimeAsync(1); + expect(f.check.mock.calls.length).toBe(checked * 2); expect(f.load).toHaveBeenCalledTimes(loaded); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("keeps an incomplete watchdog subtree as concrete retry debt", async () => { + const f = fixture(); f.rows.watchdogs.push({ id: "watchdog", companyId: "selected" }); f.state.incomplete = true; + await f.worker.ready; expect(f.coordinator.nextWakeAt()).toBe(1_030_000); + const loaded = f.load.mock.calls.length; f.state.incomplete = false; + await vi.advanceTimersByTimeAsync(30_000); + expect(f.check).toHaveBeenCalledTimes(2); expect(f.load).toHaveBeenCalledTimes(loaded); + expect(f.coordinator.nextWakeAt()).toBeNull(); + }); + it("keeps a concurrent producer dirty until the in-flight owner has completed", async () => { + const f = fixture(); f.rows.issues.push({ id: "issue", companyId: "selected" }); await f.worker.ready; + let release!: () => void; const held = new Promise(resolve => { release = resolve; }); + f.check.mockImplementationOnce(() => held); + await f.notify(); await f.settle(); await f.notify(); release(); await f.settle(); await vi.advanceTimersByTimeAsync(30_000); + expect(f.coordinator.nextWakeAt()).toBeNull(); + expect(f.check.mock.calls.length).toBeGreaterThan(3); + }); + it("retains startup work on standby and cancels future deadlines on shutdown", async () => { + const f = fixture(); f.state.standby = true; f.rows.watchdogs.push({ id: "watchdog", companyId: "selected" }); + await f.worker.ready; await vi.advanceTimersByTimeAsync(90_000); expect(f.load).not.toHaveBeenCalled(); + f.state.standby = false; f.state.deadline = Date.now() + 60_000; f.worker.wake(); await f.settle(); + expect(f.check).toHaveBeenCalledOnce(); await f.worker.stop(); + await vi.advanceTimersByTimeAsync(120_000); expect(f.check).toHaveBeenCalledOnce(); + }); +}); diff --git a/server/src/__tests__/issue-tree-control-service.test.ts b/server/src/__tests__/issue-tree-control-service.test.ts index 923f399d3bd..e98efb18309 100644 --- a/server/src/__tests__/issue-tree-control-service.test.ts +++ b/server/src/__tests__/issue-tree-control-service.test.ts @@ -41,7 +41,7 @@ describeEmbeddedPostgres("issueTreeControlService", () => { beforeAll(async () => { if (externalUrl) { await applyPendingMigrations(externalUrl); - db = createDb(externalUrl); + db = createDb(externalUrl, { maxConnections: 6 }); return; } tempDb = await startEmbeddedPostgresTestDatabase("paperclip-issue-tree-control-"); diff --git a/server/src/__tests__/scoped-deadline-work.test.ts b/server/src/__tests__/scoped-deadline-work.test.ts index 7c6792c287b..3d838bb6c96 100644 --- a/server/src/__tests__/scoped-deadline-work.test.ts +++ b/server/src/__tests__/scoped-deadline-work.test.ts @@ -10,7 +10,7 @@ afterEach(async () => { await coordinator?.stop(); vi.useRealTimers(); }); it("preserves a subsecond replacement deadline when the owner does not require pass spacing", async () => { vi.useFakeTimers(); const onError = vi.fn(); - const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []) }); + const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []), transaction: vi.fn(async () => undefined) }); coordinator = createDeliveryWorkCoordinator({ owner, canRun: () => true, onError }); const now = Date.now(); let dueAt = now + 60_000; @@ -43,7 +43,7 @@ type Entry = { id: string; companyId: string; issueId: string; dueAt: number }; function concurrentFixture(entries: Entry[], limit = 4, concurrent = true) { vi.useFakeTimers(); const onError = vi.fn(); - const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []) }); + const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []), transaction: vi.fn(async () => undefined) }); let canRun = true; let releaseAll = false; const releases = new Map void>(); @@ -177,7 +177,7 @@ it("stops starting checks and awaits every admitted check during shutdown", asyn it("keeps failures isolated and retries their deadline without repeating successful checks", async () => { vi.useFakeTimers(); - const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []) }); + const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []), transaction: vi.fn(async () => undefined) }); const onError = vi.fn(); coordinator = createDeliveryWorkCoordinator({ owner, canRun: () => true, onError }); const entries = [entry("1", "shared"), entry("2", "shared"), entry("3")]; @@ -200,3 +200,98 @@ it("keeps failures isolated and retries their deadline without repeating success expect(load).toHaveBeenCalledOnce(); expect(coordinator.nextWakeAt()).toBeNull(); }); + + +it("joins one beforePass across keyed parallel checks while retaining per-task order", async () => { + vi.useFakeTimers(); + const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []), transaction: vi.fn(async () => undefined) }); + const onError = vi.fn(), beforePass = vi.fn(async () => {}); + const started: string[] = [], completed = new Set(), releases = new Map void>(); + let releaseAll = false; + const entries = [entry("first", "shared"), entry("second", "shared"), entry("independent", "other")]; + const load = vi.fn(async () => entries.filter(row => !completed.has(row.id))); + coordinator = createDeliveryWorkCoordinator({ owner, canRun: () => true, onError }); + const worker = registerScopedDeadlineWork(coordinator, { + queue: DELIVERY_QUEUES.nativeResponsePresentation, minimumPassIntervalMs: 0, + concurrentChecks: { limit: 2, key: (row: Entry) => `${row.companyId}:${row.issueId}` }, + reconstructionIntervalMs: 30_000, beforePass, + decodeScope: hint => hint === "*" ? undefined : hint, + matches: (row, companyId?: string) => companyId === undefined || row.companyId === companyId, + load, + check: async row => { + started.push(row.id); + if (!releaseAll) await new Promise(resolve => releases.set(row.id, resolve)); + completed.add(row.id); + return null; + }, + }, () => true); + try { + await vi.advanceTimersByTimeAsync(0); + expect(started).toEqual(["first", "independent"]); + expect(beforePass).toHaveBeenCalledOnce(); + worker.invalidate("company"); + await vi.advanceTimersByTimeAsync(0); + expect(beforePass).toHaveBeenCalledOnce(); + releases.get("independent")!(); + await vi.advanceTimersByTimeAsync(0); + expect(started).not.toContain("second"); + releases.get("first")!(); + await vi.advanceTimersByTimeAsync(0); + expect(started).toEqual(["first", "independent", "second"]); + expect(beforePass).toHaveBeenCalledOnce(); + } finally { + releaseAll = true; for (const release of releases.values()) release(); await worker.ready; + } + await vi.advanceTimersByTimeAsync(1); + expect(beforePass).toHaveBeenCalledTimes(2); + expect(load).toHaveBeenCalledTimes(2); + expect(coordinator.nextWakeAt()).toBeNull(); + await vi.advanceTimersByTimeAsync(120_000); + expect(load).toHaveBeenCalledTimes(2); expect(beforePass).toHaveBeenCalledTimes(2); + expect(onError).not.toHaveBeenCalled(); +}); + +it("keeps an exact deadline and late reconstruction debt with concurrency enabled across drain", async () => { + vi.useFakeTimers(); + const owner = installDatabaseWorkSignals({ execute: vi.fn(async () => []), transaction: vi.fn(async () => undefined) }); + const onError = vi.fn(), beforePass = vi.fn(async () => {}); + let canRun = true, completed = false, entered!: () => void, release!: () => void; + const loading = new Promise(resolve => { entered = resolve; }); + const held = new Promise(resolve => { release = resolve; }); + const now = Date.now(), dueAt = now + 5_000; + const candidate = { ...entry("saved", "task"), dueAt }; + const load = vi.fn(async () => { if (load.mock.calls.length === 2) { entered(); await held; } return completed ? [] : [candidate]; }); + const check = vi.fn(async () => { completed = true; return null; }); + coordinator = createDeliveryWorkCoordinator({ owner, canRun: () => canRun, onError }); + const worker = registerScopedDeadlineWork(coordinator, { + queue: DELIVERY_QUEUES.nativeResponsePresentation, minimumPassIntervalMs: 0, + concurrentChecks: { limit: 2, key: (row: Entry) => row.issueId }, + reconstructionIntervalMs: 30_000, beforePass, + decodeScope: hint => hint === "*" ? undefined : hint, + matches: (row, companyId?: string) => companyId === undefined || row.companyId === companyId, + load, check, + }, () => canRun); + await worker.ready; + worker.invalidate("company"); + try { + await vi.advanceTimersByTimeAsync(1); await loading; + worker.invalidate("company"); + } finally { release(); } + await vi.advanceTimersByTimeAsync(0); + expect(load).toHaveBeenCalledTimes(2); + expect(coordinator.nextWakeAt()).toBe(dueAt); + await vi.advanceTimersByTimeAsync(4_999); + expect(check).toHaveBeenCalledOnce(); expect(load).toHaveBeenCalledTimes(2); + expect(coordinator.nextWakeAt()).toBe(now + 30_001); + canRun = false; worker.wake(); + await vi.advanceTimersByTimeAsync(20_000); + expect(load).toHaveBeenCalledTimes(2); expect(check).toHaveBeenCalledOnce(); + canRun = true; worker.wake(); + await vi.advanceTimersByTimeAsync(5_001); + expect(load).toHaveBeenCalledTimes(3); expect(check).toHaveBeenCalledOnce(); + expect(beforePass).toHaveBeenCalledTimes(4); + expect(coordinator.nextWakeAt()).toBeNull(); + await vi.advanceTimersByTimeAsync(120_000); + expect(load).toHaveBeenCalledTimes(3); expect(check).toHaveBeenCalledOnce(); + expect(onError).not.toHaveBeenCalled(); +}); diff --git a/server/src/__tests__/server-startup-feedback-export.test.ts b/server/src/__tests__/server-startup-feedback-export.test.ts index e00c8519df7..a26d94f50d4 100644 --- a/server/src/__tests__/server-startup-feedback-export.test.ts +++ b/server/src/__tests__/server-startup-feedback-export.test.ts @@ -134,6 +134,7 @@ const { })), reconcileHotRestartAdoption: vi.fn(async () => ({ mode: "none" })), reapOrphanedRuns: vi.fn(async () => ({ reaped: 0, runIds: [] })), + registerIssueStateRecoveryWork: vi.fn((_coordinator: unknown, _canRun: () => boolean) => ({ ready: Promise.resolve() })), registerRunDispatchWork: vi.fn((_coordinator: unknown, _canRun: () => boolean) => ({ ready: Promise.resolve() })), registerScheduledRetryCancellationWork: vi.fn((_coordinator: unknown, _canRun: () => boolean) => ({ ready: Promise.resolve() })), registerStoppedInstructionCollectionWork: vi.fn((_coordinator: unknown, _canRun: () => boolean) => ({ ready: Promise.resolve() })), @@ -927,6 +928,7 @@ describe("startServer feedback export wiring", () => { it.each([false, true])("registers retry and queued dispatch only when maintenance is enabled (%s)", async enabled => { loadConfigMock.mockReturnValue(buildTestConfig({ heartbeatSchedulerEnabled: enabled })); await startServer(); await settleStartupHousekeeping(); + expect(heartbeatServiceMock.registerIssueStateRecoveryWork).toHaveBeenCalledTimes(enabled ? 1 : 0); expect(heartbeatServiceMock.registerRunDispatchWork).toHaveBeenCalledTimes(enabled ? 1 : 0); if (enabled) { const [coordinator, admitted] = heartbeatServiceMock.registerRunDispatchWork.mock.calls[0]; @@ -1334,11 +1336,11 @@ describe("startServer feedback export wiring", () => { await startServer(); await settleStartupHousekeeping(); expect(heartbeatServiceMock.reconcileCostAccounting).toHaveBeenCalledTimes(1); - expect(heartbeatServiceMock.sweepStaleIssueLocks).toHaveBeenCalledTimes(1); + expect(heartbeatServiceMock.sweepStaleIssueLocks).not.toHaveBeenCalled(); expect(intervalCallback).not.toBeNull(); intervalCallback?.(); await new Promise((resolve) => setImmediate(resolve)); - expect(heartbeatServiceMock.sweepStaleIssueLocks).toHaveBeenCalledTimes(2); + expect(heartbeatServiceMock.sweepStaleIssueLocks).not.toHaveBeenCalled(); expect(heartbeatServiceMock.reapOrphanedRuns).toHaveBeenLastCalledWith({ staleThresholdMs: 300_000, skipScheduledRetryCancellation: true, skipCapturedInstructionCommit: true, skipInstructionDirectoryCleanup: true, skipStoppedInstructionCollection: true, skipCancelledWorkspacePreservation: true, skipObsoletePolicyReviews: true, skipAutomaticCompletionReviews: true, skipUnsafeWorkspaceExports: true, skipNativePendingEffects: true, skipNativeResponsePresentation: true, skipNativeReviewResponse: true, skipNativeStatusReassessment: true, skipRetainedNativeSessionCleanup: true, skipNativeWorkspaceFinalization: true, skipNativeResultCommit: true, skipNativeRunProjection: true, skipNativeRecoveryNotices: true, skipExternalConversationSettlement: true, skipExternalAgentSettlement: true, skipNativeEnvironmentSettlement: true }); expect(heartbeatServiceMock.reconcileCostAccounting).toHaveBeenCalledTimes(1); expect(heartbeatServiceMock.promoteDueScheduledRetries).not.toHaveBeenCalled(); diff --git a/server/src/__tests__/task-watchdogs-classifier.test.ts b/server/src/__tests__/task-watchdogs-classifier.test.ts index 16ef800c088..71865c75dfe 100644 --- a/server/src/__tests__/task-watchdogs-classifier.test.ts +++ b/server/src/__tests__/task-watchdogs-classifier.test.ts @@ -1,8 +1,6 @@ -import { describe, expect, it, vi } from "vitest"; +import { describe, expect, it } from "vitest"; import { classifyTaskWatchdogSubtree, type TaskWatchdogClassifierIssue } from "../services/task-watchdogs.ts"; -import { createIncompleteTaskWatchdogScanReporter } from "../services/task-watchdog-diagnostics.ts"; - const companyId = "company-1"; const sourceId = "source-1"; const childId = "child-1"; @@ -37,39 +35,6 @@ function classify(overrides: Partial { - it("reports an unchanged incomplete scan once across startup and a day of periodic ticks", () => { - const warn = vi.fn(); - const report = createIncompleteTaskWatchdogScanReporter(warn); - report({ incomplete: 2, incompleteIssueIds: [sourceId, childId] }, "startup"); - for (let tick = 0; tick < 2880; tick += 1) { - report({ incomplete: 2, incompleteIssueIds: [childId, sourceId] }, "periodic"); - } - expect(warn).toHaveBeenCalledTimes(1); - expect(warn).toHaveBeenCalledWith( - { incomplete: 2, newIncompleteIssueIds: [sourceId, childId] }, - "startup task-watchdog reconciliation found incomplete subtree scans", - ); - }); - - it("reports new incomplete issues and reports a resolved issue if it becomes incomplete again", () => { - const warn = vi.fn(); - const report = createIncompleteTaskWatchdogScanReporter(warn); - report({ incomplete: 1, incompleteIssueIds: [sourceId] }, "startup"); - report({ incomplete: 2, incompleteIssueIds: [sourceId, childId] }, "periodic"); - expect(warn).toHaveBeenLastCalledWith( - { incomplete: 2, newIncompleteIssueIds: [childId] }, - "periodic task-watchdog reconciliation found incomplete subtree scans", - ); - report({ incomplete: 0, incompleteIssueIds: [] }, "periodic"); - expect(warn).toHaveBeenCalledTimes(2); - report({ incomplete: 1, incompleteIssueIds: [sourceId] }, "periodic"); - expect(warn).toHaveBeenCalledTimes(3); - expect(warn).toHaveBeenLastCalledWith( - { incomplete: 1, newIncompleteIssueIds: [sourceId] }, - "periodic task-watchdog reconciliation found incomplete subtree scans", - ); - }); - it("does not produce a stopped fingerprint from an incomplete scan", () => { const result = classify({ subtreeIncomplete: true }); expect(result.state).toBe("incomplete"); diff --git a/server/src/index.ts b/server/src/index.ts index cd8bb951946..0ebe5c3332c 100644 --- a/server/src/index.ts +++ b/server/src/index.ts @@ -109,7 +109,6 @@ import { createApp } from "./app.js"; import { initializeCloudRuntimeConfig } from "./services/cloud-runtime-config.js"; import { loadCloudBootstrapConfig, loadConfig, type Config } from "./config.js"; import { logger } from "./middleware/logger.js"; -import { createIncompleteTaskWatchdogScanReporter } from "./services/task-watchdog-diagnostics.js"; import { setStartupRecoveryPhase } from "./startup-recovery-state.js"; import { StartupRefusalError, @@ -973,9 +972,6 @@ async function startServerWithDatabaseTeardown( } }; const pluginWorkerManager = createPluginWorkerManager(); - const reportIncompleteWatchdogScans = createIncompleteTaskWatchdogScanReporter( - (details, message) => logger.warn(details, message), - ); const heartbeat = config.heartbeatSchedulerEnabled ? heartbeatService(db as any, { pluginWorkerManager }) : null; @@ -1796,47 +1792,10 @@ async function startServerWithDatabaseTeardown( "startup session-goal recovery resumed durable agent goals", ); } - const reconciled = await heartbeat.reconcileStrandedAssignedIssues(); - if ( - reconciled.assignmentDispatched > 0 || - reconciled.dispatchRequeued > 0 || - reconciled.continuationRequeued > 0 || - reconciled.successfulRunHandoffEscalated > 0 || - reconciled.successfulRunHandoffRetried > 0 || - reconciled.escalated > 0 - ) { - logger.warn( - { ...reconciled }, - "startup heartbeat recovery changed assigned issue state", - ); - } - - const dependencyWakesReconciled = await heartbeat.reconcileResolvedDependencyWakes(); - if (dependencyWakesReconciled.healed > 0) { - logger.warn( - { ...dependencyWakesReconciled }, - "startup dependency-wake reconciliation restored task execution paths", - ); - } - - const taskWatchdogsReconciled = await heartbeat.reconcileTaskWatchdogs(); - reportIncompleteWatchdogScans(taskWatchdogsReconciled, "startup"); - if (taskWatchdogsReconciled.triggered > 0) { - logger.warn( - { ...taskWatchdogsReconciled }, - "startup task-watchdog reconciliation triggered watchdog work", - ); - } - const scanned = await heartbeat.scanSilentActiveRuns(); if (scanned.created > 0 || scanned.escalated > 0) { logger.warn({ ...scanned }, "startup active-run output watchdog created review work"); } - - const swept = await heartbeat.sweepStaleIssueLocks(); - if (swept.cleared > 0) { - logger.warn({ ...swept }, "startup stale-lock sweeper cleared issue locks"); - } })().catch((err) => { logger.error({ err }, "startup heartbeat recovery failed"); throw err; @@ -1845,6 +1804,8 @@ async function startServerWithDatabaseTeardown( await startupHeartbeatRecovery; } + if (config.heartbeatSchedulerEnabled) await heartbeat.registerIssueStateRecoveryWork(deliveryWork, + () => !isIdleTaskDrainActive() && !isWarmStandby() && !heartbeatSchedulerStopped).ready; if (config.heartbeatSchedulerEnabled) await heartbeat.registerRunDispatchWork(deliveryWork, () => !isIdleTaskDrainActive() && !isWarmStandby() && !heartbeatSchedulerStopped).ready; if (config.heartbeatSchedulerEnabled) await heartbeat.registerScheduledRetryCancellationWork(deliveryWork, @@ -2051,33 +2012,6 @@ async function startServerWithDatabaseTeardown( .reapOrphanedRuns({ staleThresholdMs: 5 * 60 * 1000, skipScheduledRetryCancellation: true, skipCapturedInstructionCommit: true, skipInstructionDirectoryCleanup: true, skipStoppedInstructionCollection: true, skipCancelledWorkspacePreservation: true, skipObsoletePolicyReviews: true, skipAutomaticCompletionReviews: true, skipUnsafeWorkspaceExports: true, skipNativePendingEffects: true, skipNativeResponsePresentation: true, skipNativeReviewResponse: true, skipNativeStatusReassessment: true, skipRetainedNativeSessionCleanup: true, skipNativeWorkspaceFinalization: true, skipNativeResultCommit: true, skipNativeRunProjection: true, skipNativeRecoveryNotices: true, skipExternalConversationSettlement: true, skipExternalAgentSettlement: true, skipNativeEnvironmentSettlement: true }) .then(async () => { await heartbeat.resumeQueuedRuns(); - const reconciled = await heartbeat.reconcileStrandedAssignedIssues({ skipExternalConversationSettlement: true }); - if ( - reconciled.assignmentDispatched > 0 || - reconciled.dispatchRequeued > 0 || - reconciled.continuationRequeued > 0 || - reconciled.successfulRunHandoffEscalated > 0 || - reconciled.successfulRunHandoffRetried > 0 || - reconciled.escalated > 0 - ) { - logger.warn( - { ...reconciled }, - "periodic heartbeat recovery changed assigned issue state", - ); - } - }) - .then(async () => { - const reconciled = await heartbeat.reconcileResolvedDependencyWakes(); - if (reconciled.healed > 0) { - logger.warn({ ...reconciled }, "periodic dependency-wake reconciliation restored task execution paths"); - } - }) - .then(async () => { - const reconciled = await heartbeat.reconcileTaskWatchdogs(); - reportIncompleteWatchdogScans(reconciled, "periodic"); - if (reconciled.triggered > 0) { - logger.warn({ ...reconciled }, "periodic task-watchdog reconciliation triggered watchdog work"); - } }) .then(async () => { const scanned = await heartbeat.scanSilentActiveRuns(); @@ -2085,12 +2019,6 @@ async function startServerWithDatabaseTeardown( logger.warn({ ...scanned }, "periodic active-run output watchdog created review work"); } }) - .then(async () => { - const swept = await heartbeat.sweepStaleIssueLocks(); - if (swept.cleared > 0) { - logger.warn({ ...swept }, "periodic stale-lock sweeper cleared issue locks"); - } - }) .catch((err) => { logger.error({ err }, "periodic heartbeat recovery failed"); })); diff --git a/server/src/services/agent-conversations.ts b/server/src/services/agent-conversations.ts index a6b70361945..d491c104684 100644 --- a/server/src/services/agent-conversations.ts +++ b/server/src/services/agent-conversations.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; import { notifyUnsafeWorkspaceExportRecovery } from "./unsafe-workspace-export-notifications.js"; import { FAST_RESPONSE_AGENT_GUIDANCE, fastResponseHistoryBody } from "@paperclipai/shared"; @@ -547,6 +548,7 @@ export async function resumeConversationForReset(db: Db, comment: typeof issueCo eq(issues.id, comment.issueId), eq(issues.companyId, comment.companyId), )).for("update"); if (!isConversation(issue) || comment.conversationSessionGeneration != null) return; + await notifyIssueRecovery(tx, { companyId: issue.companyId }); const released = await tx.update(issueTreeHolds).set({ status: "released", releasedAt: new Date(), updatedAt: new Date(), releasedByActorType: "user", releasedByUserId: comment.authorUserId, diff --git a/server/src/services/chat-channels/telegram/attachment-failure.ts b/server/src/services/chat-channels/telegram/attachment-failure.ts index 58d5d4a2677..785b3116baf 100644 --- a/server/src/services/chat-channels/telegram/attachment-failure.ts +++ b/server/src/services/chat-channels/telegram/attachment-failure.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "../../issue-recovery-notifications.js"; import { createProviderEffects, type ProviderEffectTarget } from "../provider-effects.js"; import type { EndpointRow, RuntimeContext, InboundRuntimeContext } from "../runtime-types.js"; @@ -78,6 +79,7 @@ export function createTelegramAttachmentFailure(db: Db, options: TelegramAttachm })(), ); const effect = await db.transaction(async (tx) => { + await notifyIssueRecovery(tx, { companyId: input.endpoint.companyId }); // Replace the optimistic attachment placeholder with an explicit safe // Paperclip-visible failure. The message link stays authoritative for // exact provider redelivery, while no agent wakeup is enqueued for an diff --git a/server/src/services/company-deletion.ts b/server/src/services/company-deletion.ts index 7ab88aadfa9..26bc4e081a1 100644 --- a/server/src/services/company-deletion.ts +++ b/server/src/services/company-deletion.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { notifyUnsafeWorkspaceExportRecovery } from "./unsafe-workspace-export-notifications.js"; import { notifyCancelledWorkspacePreservation } from "./cancelled-workspace-preservation-notifications.js"; import { notifyInstructionCollection } from "./instruction-collection-notifications.js"; @@ -71,6 +72,7 @@ export async function deleteCompany(db: Db, id: string) { const [existing] = await tx.select({ id: companies.id }).from(companies) .where(eq(companies.id, id)).for("no key update"); if (!existing) return null; + await notifyIssueRecovery(tx, { companyId: id }); await notifyChatCompanyConfiguration(tx, id); await chatCompanyDeletion.deleteCompanyData(tx, id); await notifyDeliveryWork(tx, DELIVERY_QUEUES.skillSourceSync); diff --git a/server/src/services/company-portability.ts b/server/src/services/company-portability.ts index dc7dca311d6..585b8fcf5f4 100644 --- a/server/src/services/company-portability.ts +++ b/server/src/services/company-portability.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { createAgentLifecycle } from "./agent-lifecycle.js"; import { agentAppearanceSchema, agentHarnessType, paperclipRunnerProfileForHarness, agentRunner, type AgentRunnerChoice } from "@paperclipai/shared"; import { resolveNewAgentRunnerForCompany } from "./agent-runner-selection.js"; @@ -6465,7 +6466,9 @@ export function companyPortabilityService(db: Db, storage?: StorageService) { } if (relationRows.length > 0) { const relationCompanyId = targetCompany.id; - await db + await db.transaction(async tx => { + await notifyIssueRecovery(tx, { companyId: relationCompanyId }); + await tx .insert(issueRelations) .values(relationRows.map((row) => ({ companyId: relationCompanyId, @@ -6476,6 +6479,7 @@ export function companyPortabilityService(db: Db, storage?: StorageService) { createdByUserId: actorUserId ?? null, }))) .onConflictDoNothing(); + }); } } diff --git a/server/src/services/delivery-work-notifications.ts b/server/src/services/delivery-work-notifications.ts index 7388bdb8861..8a9fdbe5686 100644 --- a/server/src/services/delivery-work-notifications.ts +++ b/server/src/services/delivery-work-notifications.ts @@ -2,6 +2,12 @@ import { signalDatabaseWork, subscribeDatabaseWork } from "@paperclipai/db"; /** Topics for existing durable queues; register intent before their writes. */ export const DELIVERY_QUEUES = { + orphanBlockers: "orphan-blockers", + activeRecoveryActions: "active-recovery-actions", + strandedAssignments: "stranded-assignments", + resolvedDependencies: "resolved-dependencies", + taskWatchdogs: "task-watchdogs", + staleIssueLocks: "stale-issue-locks", scheduledRetryDispatch: "scheduled-retry-dispatch", queuedRunDispatch: "queued-run-dispatch", runEvidenceMigration: "run-evidence-migration", diff --git a/server/src/services/documents.ts b/server/src/services/documents.ts index 493c495e007..814c68eeea7 100644 --- a/server/src/services/documents.ts +++ b/server/src/services/documents.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { randomUUID } from "node:crypto"; import { and, asc, desc, eq, sql } from "drizzle-orm"; import type { Db } from "@paperclipai/db"; @@ -275,6 +276,7 @@ export function documentService(db: Db) { .where(eq(issueDocuments.issueId, issue.id)); const fallbackKey = nextAvailableDocumentKey(key, issueDocumentKeys.map((row) => row.key)); + await notifyIssueRecovery(tx, { companyId: issue.companyId }); const [document] = await tx .insert(documents) .values({ @@ -376,6 +378,7 @@ export function documentService(db: Db) { }); } + await notifyIssueRecovery(tx, { companyId: issue.companyId }); const nextRevisionNumber = existing.latestRevisionNumber + 1; const [revision] = await tx .insert(documentRevisions) @@ -438,6 +441,7 @@ export function documentService(db: Db) { throw conflict("Document does not exist yet", { key }); } + await notifyIssueRecovery(tx, { companyId: issue.companyId }); const [document] = await tx .insert(documents) .values({ @@ -592,6 +596,9 @@ export function documentService(db: Db) { }); } await db.transaction(async (tx) => { + for (const companyId of new Set(rows.map(row => row.companyId))) { + await notifyIssueRecovery(tx, { companyId }); + } await insertRowsInChunks(tx, documents, documentRows); await insertRowsInChunks(tx, documentRevisions, revisionRows); await insertRowsInChunks(tx, issueDocuments, linkRows); @@ -644,6 +651,7 @@ export function documentService(db: Db) { }); } + await notifyIssueRecovery(tx, { companyId: existing.companyId }); const now = new Date(); const nextRevisionNumber = existing.latestRevisionNumber + 1; const [restoredRevision] = await tx @@ -722,6 +730,7 @@ export function documentService(db: Db) { }; } + await notifyIssueRecovery(tx, { companyId: existing.companyId }); const now = new Date(); await tx .update(documents) @@ -769,6 +778,7 @@ export function documentService(db: Db) { }; } + await notifyIssueRecovery(tx, { companyId: existing.companyId }); const now = new Date(); await tx .update(documents) @@ -817,6 +827,7 @@ export function documentService(db: Db) { }); } + await notifyIssueRecovery(tx, { companyId: existing.companyId }); await tx.delete(issueDocuments).where(eq(issueDocuments.documentId, existing.id)); await tx.delete(documents).where(eq(documents.id, existing.id)); diff --git a/server/src/services/external-conversation-settlement-notifications.ts b/server/src/services/external-conversation-settlement-notifications.ts index 46f4493ff2a..d5e4cdd506c 100644 --- a/server/src/services/external-conversation-settlement-notifications.ts +++ b/server/src/services/external-conversation-settlement-notifications.ts @@ -1,7 +1,9 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; import type { ExternalConversationSettlementScope } from "./slack-conversation-lifecycle.js"; -export function notifyExternalConversationSettlement(tx: object, scope?: ExternalConversationSettlementScope) { +export async function notifyExternalConversationSettlement(tx: object, scope?: ExternalConversationSettlementScope) { + await notifyIssueRecovery(tx, scope); return notifyDeliveryWork(tx, DELIVERY_QUEUES.externalConversationSettlement, scope ? JSON.stringify({ companyId: scope.companyId, issueId: scope.issueId }) : "*"); } diff --git a/server/src/services/heartbeat.ts b/server/src/services/heartbeat.ts index 0fdefcf3109..fb96234ff6f 100644 --- a/server/src/services/heartbeat.ts +++ b/server/src/services/heartbeat.ts @@ -1,3 +1,4 @@ +import { registerIssueRecoveryWork } from "./recovery/work.js"; import { registerRunDispatchWork } from "./heartbeat/dispatch-work.js"; import { NATIVE_RETAINED_OWNER_WAIT } from "./native-runtime/native-controller-recovery.js"; import { externalConversationSettlementWork } from "./external-conversation-settlement-work.js"; @@ -1618,15 +1619,15 @@ export function heartbeatService( void reportRunFailure(db, updated, failureReport); } - async function reconcileStrandedAssignedIssues(opts?: { skipExternalConversationSettlement?: boolean }) { + async function reconcileStrandedAssignedIssues(opts?: Parameters[0]) { return recovery.reconcileStrandedAssignedIssues({ - skipExternalConversationSettlement: opts?.skipExternalConversationSettlement, + ...opts, issueCreatedAtGte: await getWorktreeExecutionCutoff(), }); } - async function sweepStaleIssueLocks() { - return recovery.sweepStaleIssueLocks(); + async function sweepStaleIssueLocks(opts?: Parameters[0]) { + return recovery.sweepStaleIssueLocks(opts); } function issueIdFromRunContext(contextSnapshot: unknown) { @@ -1656,10 +1657,7 @@ export function heartbeatService( }); } - async function reconcileTaskWatchdogs(opts?: { - companyId?: string | null; - runId?: string | null; - }) { + async function reconcileTaskWatchdogs(opts?: Parameters[0]) { return taskWatchdogs.reconcileTaskWatchdogs({ ...opts, issueCreatedAtGte: await getWorktreeExecutionCutoff(), @@ -1684,10 +1682,7 @@ export function heartbeatService( return recovery.buildRunOutputSilence(run, now); } - async function reconcileResolvedDependencyWakes(opts?: { - runId?: string | null; - companyId?: string | null; - }) { + async function reconcileResolvedDependencyWakes(opts?: Parameters[0]) { return recovery.reconcileResolvedDependencyWakeBackstop(opts); } @@ -4236,6 +4231,16 @@ export function heartbeatService( computeTaskDrain, applyTaskDrain, + registerIssueStateRecoveryWork: (coordinator: Parameters[1], canRun: () => boolean) => + registerIssueRecoveryWork(db, coordinator, { + stranded: scope => reconcileStrandedAssignedIssues({ ...scope, skipExternalConversationSettlement: true, skipRelatedRecovery: true }), + orphanBlockers: recovery.reconcileUnassignedBlockingIssues, + recoveryActions: recovery.reconcileActiveRecoveryActions, + dependencies: reconcileResolvedDependencyWakes, + locks: sweepStaleIssueLocks, + watchdogs: reconcileTaskWatchdogs, + schedulingSuppressed: async () => (await getSchedulingSuppression(true)).suppressed, + }, () => canRun() && readTaskDrain(new Date()) === null), registerRunDispatchWork: (coordinator: Parameters[0], canRun: () => boolean) => registerRunDispatchWork(coordinator, { promoteDueScheduledRetries, diff --git a/server/src/services/instance-settings.ts b/server/src/services/instance-settings.ts index 174c39d6125..e2a045f9c62 100644 --- a/server/src/services/instance-settings.ts +++ b/server/src/services/instance-settings.ts @@ -624,11 +624,14 @@ export function instanceSettingsService(db: Db, options: InstanceSettingsService } } } + const chatBecameEnabled = !toExperimentalView(current.experimental).enableAgentChat + && toExperimentalView(nextExperimental).enableAgentChat; const now = new Date(); const [updated] = await db.transaction(async tx => { await notifyDeliveryWork(tx, DELIVERY_QUEUES.mcpEvents, "*"); await notifyDeliveryWork(tx, DELIVERY_QUEUES.dotEvents, "*"); await notifyDeliveryWork(tx, DELIVERY_QUEUES.grokDispatch); + if (chatBecameEnabled) await notifyDeliveryWork(tx, DELIVERY_QUEUES.strandedAssignments, "*"); if (patch.enableWorktreeRunExecution !== undefined) await notifyScheduledRetryCancellation(tx); if (patch.enableWorktreeRunExecution !== undefined) { await notifyRunDispatch(tx); diff --git a/server/src/services/issue-comment-writes.ts b/server/src/services/issue-comment-writes.ts index e24e78e9855..39d8f6f891c 100644 --- a/server/src/services/issue-comment-writes.ts +++ b/server/src/services/issue-comment-writes.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import type { PgInsertValue } from "drizzle-orm/pg-core"; import { issueComments, type Db } from "@paperclipai/db"; import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; @@ -6,6 +7,8 @@ type WriteDb = Db | Parameters[0]>[0]; export function insertIssueComment(db: WriteDb, input: PgInsertValue & { companyId: string }) { return db.transaction(async tx => { + await notifyIssueRecovery(tx, { companyId: input.companyId, + issueId: typeof input.issueId === "string" ? input.issueId : undefined }); await notifyDeliveryWork(tx, DELIVERY_QUEUES.dotEvents, `company:${input.companyId}`); return tx.insert(issueComments).values(input).returning(); }); diff --git a/server/src/services/issue-recovery-actions.ts b/server/src/services/issue-recovery-actions.ts index 48fb001c0b4..316eb413afe 100644 --- a/server/src/services/issue-recovery-actions.ts +++ b/server/src/services/issue-recovery-actions.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { notifyNativeRecoveryNotices } from "./native-recovery-notice-notifications.js"; import { notifyUnsafeWorkspaceExportRecovery } from "./unsafe-workspace-export-notifications.js"; import { writeExecutionControl } from "./execution-control-notifications.js"; @@ -322,6 +323,7 @@ export function issueRecoveryActionService(db: DbOrTransaction) { ): Promise { try { const created = await db.transaction(async (tx) => { + await notifyIssueRecovery(tx, { companyId: input.companyId }); await notifyNativeRecoveryNotices(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); await notifyDeliveryWork(tx, DELIVERY_QUEUES.executionDisposition); await notifyDeliveryWork(tx, DELIVERY_QUEUES.executionContinuation); @@ -413,6 +415,7 @@ export function issueRecoveryActionService(db: DbOrTransaction) { Math.min(nextAttemptCount, effectiveMaxAttempts), ); const [exhausted] = await writeExecutionControl(db, [DELIVERY_QUEUES.executionDisposition, DELIVERY_QUEUES.executionContinuation], async tx => { + await notifyIssueRecovery(tx, { companyId: input.companyId }); await notifyNativeRecoveryNotices(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); if ((!input.preserveExistingOwner && existing.cause !== input.cause) || (input.evidence?.runId !== undefined && input.evidence.runId !== existing.evidence?.runId)) { @@ -474,6 +477,7 @@ export function issueRecoveryActionService(db: DbOrTransaction) { return toReadModel(exhausted); } const [updated] = await writeExecutionControl(db, [DELIVERY_QUEUES.executionDisposition, DELIVERY_QUEUES.executionContinuation], async tx => { + await notifyIssueRecovery(tx, { companyId: input.companyId }); await notifyNativeRecoveryNotices(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); if ((!input.preserveExistingOwner && existing.cause !== input.cause) || (input.evidence?.runId !== undefined && input.evidence.runId !== existing.evidence?.runId)) { @@ -548,6 +552,7 @@ export function issueRecoveryActionService(db: DbOrTransaction) { try { const [created] = await writeExecutionControl(db, [DELIVERY_QUEUES.executionDisposition, DELIVERY_QUEUES.executionContinuation], async tx => { + await notifyIssueRecovery(tx, { companyId: input.companyId }); await notifyNativeRecoveryNotices(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); await notifyUnsafeWorkspaceExportRecovery(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); return tx @@ -595,6 +600,7 @@ export function issueRecoveryActionService(db: DbOrTransaction) { const pending = await tx.select({ id: issueRecoveryActions.id }).from(issueRecoveryActions) .where(and(...predicates)).limit(1); if (!pending.length) return []; + await notifyIssueRecovery(tx, { companyId: input.companyId }); await notifyNativeRecoveryNotices(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); await notifyUnsafeWorkspaceExportRecovery(tx, { companyId: input.companyId, issueId: input.sourceIssueId }); return tx diff --git a/server/src/services/issue-recovery-notifications.ts b/server/src/services/issue-recovery-notifications.ts new file mode 100644 index 00000000000..7b709960831 --- /dev/null +++ b/server/src/services/issue-recovery-notifications.ts @@ -0,0 +1,16 @@ +import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; + +/** An issue hint is reserved for local facts such as comments. Lifecycle, + * graph, run and eligibility changes retain company scope because their + * consequences can include ancestors and shared execution references. */ +export type IssueRecoveryScope = { companyId: string; issueId?: string }; + +export async function notifyIssueRecovery(transaction: object, scope?: IssueRecoveryScope) { + const companyHint = scope ? JSON.stringify({ companyId: scope.companyId }) : "*"; + const issueHint = scope ? JSON.stringify({ companyId: scope.companyId, issueId: scope.issueId }) : "*"; + for (const queue of [DELIVERY_QUEUES.orphanBlockers, DELIVERY_QUEUES.activeRecoveryActions, DELIVERY_QUEUES.strandedAssignments, DELIVERY_QUEUES.resolvedDependencies, + DELIVERY_QUEUES.taskWatchdogs, DELIVERY_QUEUES.staleIssueLocks]) { + await notifyDeliveryWork(transaction, queue, + queue === DELIVERY_QUEUES.strandedAssignments || queue === DELIVERY_QUEUES.staleIssueLocks ? issueHint : companyHint); + } +} diff --git a/server/src/services/issue-tree-control.ts b/server/src/services/issue-tree-control.ts index 0d7633f846a..ff558b81ef0 100644 --- a/server/src/services/issue-tree-control.ts +++ b/server/src/services/issue-tree-control.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; import { notifyNativeStatusReassessment } from "./native-status-reassessment-notifications.js"; import { notifyUnsafeWorkspaceExportRecovery } from "./unsafe-workspace-export-notifications.js"; @@ -758,6 +759,7 @@ export function issueTreeControlService(db: Db) { const releaseReason = input.reason ?? "Subtree resume applied."; const { hold: resumeHold } = await db.transaction(async (tx) => { + await notifyIssueRecovery(tx, { companyId }); const [createdHold] = await tx .insert(issueTreeHolds) .values({ @@ -836,6 +838,7 @@ export function issueTreeControlService(db: Db) { } const { hold, members } = await db.transaction(async (tx) => { + await notifyIssueRecovery(tx, { companyId }); const [createdHold] = await tx .insert(issueTreeHolds) .values({ @@ -1177,7 +1180,9 @@ export function issueTreeControlService(db: Db) { throw conflict("Issue tree hold is already released"); } - const [updated] = await db + const [updated] = await db.transaction(async tx => { + await notifyIssueRecovery(tx, { companyId }); + return tx .update(issueTreeHolds) .set({ status: "released", @@ -1195,6 +1200,7 @@ export function issueTreeControlService(db: Db) { }) .where(and(eq(issueTreeHolds.id, holdId), eq(issueTreeHolds.companyId, companyId))) .returning(); + }); const members = await db .select() diff --git a/server/src/services/issues.ts b/server/src/services/issues.ts index cc9293db472..4264478de85 100644 --- a/server/src/services/issues.ts +++ b/server/src/services/issues.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { notifyRunDispatch } from "./run-dispatch-notifications.js"; import { notifyExternalConversationSettlement } from "./external-conversation-settlement-notifications.js"; import { notifyNativeRecoveryNotices } from "./native-recovery-notice-notifications.js"; @@ -7628,6 +7629,7 @@ export function issueService(db: Db) { await assertNoBlockingCycles(companyId, issueId, deduped, dbOrTx); } + await notifyIssueRecovery(dbOrTx, { companyId }); await dbOrTx .delete(issueRelations) .where( @@ -9676,27 +9678,30 @@ export function issueService(db: Db) { }); if (blockParentUntilDone) { - const existingBlockers = await db - .select({ blockerIssueId: issueRelations.issueId }) - .from(issueRelations) - .where( - and( - eq(issueRelations.companyId, parent.companyId), - eq(issueRelations.relatedIssueId, parent.id), - eq(issueRelations.type, "blocks"), - ), + await db.transaction(async tx => { + const existingBlockers = await tx + .select({ blockerIssueId: issueRelations.issueId }) + .from(issueRelations) + .where( + and( + eq(issueRelations.companyId, parent.companyId), + eq(issueRelations.relatedIssueId, parent.id), + eq(issueRelations.type, "blocks"), + ), + ); + await syncBlockedByIssueIds( + parent.id, + parent.companyId, + [ + ...new Set([ + ...existingBlockers.map((row) => row.blockerIssueId), + child.id, + ]), + ], + { agentId: actorAgentId ?? null, userId: actorUserId ?? null }, + tx, ); - await syncBlockedByIssueIds( - parent.id, - parent.companyId, - [ - ...new Set([ - ...existingBlockers.map((row) => row.blockerIssueId), - child.id, - ]), - ], - { agentId: actorAgentId ?? null, userId: actorUserId ?? null }, - ); + }); [child] = await withIssueRelationSummaries( parent.companyId, [child], @@ -11495,7 +11500,9 @@ export function issueService(db: Db) { await notifyTerminalWorkspaceWork(tx, `issue:${id}`); } if (patch.status !== undefined || patch.assigneeAgentId !== undefined || patch.assigneeUserId !== undefined - || patch.hiddenAt !== undefined || patch.conversationAgentId !== undefined) { + || patch.hiddenAt !== undefined || patch.conversationAgentId !== undefined || patch.parentId !== undefined + || patch.executionState !== undefined || patch.executionRunId !== undefined || patch.checkoutRunId !== undefined + || blockedByIssueIds !== undefined) { await notifyRunDispatch(tx, { companyId: receiptExisting.companyId }); await notifyDeliveryWork(tx, DELIVERY_QUEUES.agentTimers); } @@ -13816,6 +13823,7 @@ export function issueService(db: Db) { .then((rows) => rows[0] ?? null); if (!existing) return null; + await notifyIssueRecovery(tx, { companyId: existing.companyId }); await tx.delete(issueAttachments).where(eq(issueAttachments.id, id)); await tx.delete(assets).where(eq(assets.id, existing.assetId)); return existing; diff --git a/server/src/services/legacy-controller-lease.ts b/server/src/services/legacy-controller-lease.ts index 55a8439debc..22fa078f459 100644 --- a/server/src/services/legacy-controller-lease.ts +++ b/server/src/services/legacy-controller-lease.ts @@ -77,14 +77,18 @@ async function renewOnLivenessPool( }); } -export async function hasLiveLegacyController(db: Db, run: Run): Promise { - if (run.runtimeMode === "native" || !run.controllerBootId) return false; - const [owner] = await db.select({ id: heartbeatRuns.id }).from(heartbeatRuns).where(and( +export async function liveLegacyControllerExpiresAt(db: Db, run: Run): Promise { + if (run.runtimeMode === "native" || !run.controllerBootId) return null; + const [owner] = await db.select({ expiresAt: heartbeatRuns.controllerLeaseExpiresAt }).from(heartbeatRuns).where(and( eq(heartbeatRuns.id, run.id), eq(heartbeatRuns.companyId, run.companyId), eq(heartbeatRuns.status, "running"), gt(heartbeatRuns.controllerLeaseExpiresAt, sql`clock_timestamp()`), )); - return Boolean(owner); + return owner?.expiresAt ?? null; +} + +export async function hasLiveLegacyController(db: Db, run: Run): Promise { + return (await liveLegacyControllerExpiresAt(db, run)) !== null; } export type RevokedLegacyControllerState = Pick; diff --git a/server/src/services/native-runtime/chat-attachment-reuse.test.ts b/server/src/services/native-runtime/chat-attachment-reuse.test.ts index ccd4bbe30d6..d0de5ab04c9 100644 --- a/server/src/services/native-runtime/chat-attachment-reuse.test.ts +++ b/server/src/services/native-runtime/chat-attachment-reuse.test.ts @@ -73,7 +73,7 @@ describe("native same-conversation chat attachment reuse", () => { beforeAll(async () => { const external = resolveExternalTestDatabaseUrl("PAPERCLIP_CHAT_REUSE_TEST_DATABASE_URL"); if (!external) temporary = await startEmbeddedPostgresTestDatabase("native-chat-reuse-"); - db = createDb(external ?? temporary!.connectionString); + db = createDb(external ?? temporary!.connectionString, { maxConnections: 6 }); const storageRoot = await mkdtemp( path.join(tmpdir(), "paperclip-chat-reuse-"), ); diff --git a/server/src/services/native-runtime/chat-attachment-reuse.ts b/server/src/services/native-runtime/chat-attachment-reuse.ts index cc7990e9b7a..6cc44299ee7 100644 --- a/server/src/services/native-runtime/chat-attachment-reuse.ts +++ b/server/src/services/native-runtime/chat-attachment-reuse.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "../issue-recovery-notifications.js"; import { createHash } from "node:crypto"; import { and, desc, eq, inArray, isNull, sql } from "drizzle-orm"; @@ -1582,7 +1583,9 @@ export async function prepareReusedChatAttachment(input: { if (!workProduct) { throw new Error("paperclip_runner_chat_attachment_origin_not_persisted"); } - await input.db + await input.db.transaction(async tx => { + await notifyIssueRecovery(tx, { companyId: input.binding.companyId }); + await tx .update(issueWorkProducts) .set({ title: input.title, @@ -1602,6 +1605,7 @@ export async function prepareReusedChatAttachment(input: { eq(issueWorkProducts.createdByRunId, input.binding.runId), ), ); + }); const comment = await issueService(input.db).addComment( input.binding.issueId, `Prepared ${input.title} for this response.`, diff --git a/server/src/services/native-runtime/native-runner-file-handoff.test.ts b/server/src/services/native-runtime/native-runner-file-handoff.test.ts index 0abae30539f..e302c432190 100644 --- a/server/src/services/native-runtime/native-runner-file-handoff.test.ts +++ b/server/src/services/native-runtime/native-runner-file-handoff.test.ts @@ -1,3 +1,4 @@ +import { resolveExternalTestDatabaseUrl } from "../../__tests__/helpers/external-test-database.js"; import type { PrpStructuredRunResult } from "../../vendor/paperclip-runner/index.js"; import { nativeCompletionFeedback } from "./native-completion-feedback.js"; import { createHash, randomUUID } from "node:crypto"; @@ -61,10 +62,9 @@ describe("native runner file handoff", () => { const runId = "00000000-0000-4000-8000-000000009104"; beforeAll(async () => { - temporary = await startEmbeddedPostgresTestDatabase( - "native-runner-file-handoff-", - ); - db = createDb(temporary.connectionString); + const external = resolveExternalTestDatabaseUrl("PAPERCLIP_NATIVE_HANDOFF_TEST_DATABASE_URL"); + if (!external) temporary = await startEmbeddedPostgresTestDatabase("native-runner-file-handoff-"); + db = createDb(external ?? temporary!.connectionString, { maxConnections: 6 }); temporaryRoot = await mkdtemp( path.join(tmpdir(), "paperclip-native-file-handoff-"), ); diff --git a/server/src/services/native-runtime/native-runner-file-handoff.ts b/server/src/services/native-runtime/native-runner-file-handoff.ts index 6f2c32beec8..420380500ea 100644 --- a/server/src/services/native-runtime/native-runner-file-handoff.ts +++ b/server/src/services/native-runtime/native-runner-file-handoff.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "../issue-recovery-notifications.js"; import { createHash, randomUUID } from "node:crypto"; import { execFile } from "node:child_process"; import { constants } from "node:fs"; @@ -1265,7 +1266,9 @@ export async function prepareNativeRunnerFileHandoff(input: { ) { throw new Error("paperclip_runner_file_handoff_origin_not_persisted"); } - await input.db + await input.db.transaction(async tx => { + await notifyIssueRecovery(tx, { companyId: input.binding.companyId }); + await tx .update(issueWorkProducts) .set({ title: verified.title, updatedAt: new Date() }) .where( @@ -1276,6 +1279,7 @@ export async function prepareNativeRunnerFileHandoff(input: { eq(issueWorkProducts.createdByRunId, input.binding.runId), ), ); + }); const comment = await issueService(input.db).addComment( input.binding.issueId, `Prepared ${verified.title} for this response.`, diff --git a/server/src/services/native-runtime/native-workspace-finalizer.test.ts b/server/src/services/native-runtime/native-workspace-finalizer.test.ts index 59270a2bb65..53063f345e9 100644 --- a/server/src/services/native-runtime/native-workspace-finalizer.test.ts +++ b/server/src/services/native-runtime/native-workspace-finalizer.test.ts @@ -131,7 +131,7 @@ describe("native workspace finalization recovery", () => { const external = resolveExternalTestDatabaseUrl("PAPERCLIP_NATIVE_WORKSPACE_FINALIZER_TEST_DATABASE_URL"); if (!external) temporary = await startEmbeddedPostgresTestDatabase("paperclip-native-workspace-finalizer-"); connectionString = external ?? temporary!.connectionString; - db = createDb(connectionString); + db = createDb(connectionString, { maxConnections: 6 }); await db.insert(companies).values([ { id: companyId, name: "Native workspace owner", issuePrefix: "NWO" }, @@ -452,7 +452,7 @@ describe("native workspace finalization recovery", () => { const seeded = await seedRun({ executionWorkspaceId: randomUUID(), title: "Live copyback" }); const live = await withNativeWorkspaceFinalizationOwnership({ db, companyId, runId: seeded.runId }, async (ownership) => { await ownership.assertHeld(); - expect(await resumeNativeWorkspaceFinalization({ db: createDb(connectionString), runId: seeded.runId })).toBeNull(); + expect(await resumeNativeWorkspaceFinalization({ db: createDb(connectionString, { maxConnections: 6 }), runId: seeded.runId })).toBeNull(); expect(await db.select().from(workspaceOperations).where(eq(workspaceOperations.heartbeatRunId, seeded.runId))).toEqual([]); return "copied"; }); @@ -476,7 +476,7 @@ describe("native workspace finalization recovery", () => { try { await entered; await db.execute(sql`select pg_terminate_backend(pid) from pg_locks where locktype = 'advisory' and database = (select oid from pg_database where datname = current_database()) and pid <> pg_backend_pid()`); - const second = await withNativeWorkspaceFinalizationOwnership({ db: createDb(connectionString), companyId, runId: seeded.runId }, async () => "must not run"); + const second = await withNativeWorkspaceFinalizationOwnership({ db: createDb(connectionString, { maxConnections: 6 }), companyId, runId: seeded.runId }, async () => "must not run"); expect(second).toEqual({ acquired: false, reason: "busy" }); const [held] = await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.id, seeded.runId)); expect(held.runnerProfileJson?.nativeWorkspaceFinalizationOwner).toBeTruthy(); @@ -489,7 +489,7 @@ describe("native workspace finalization recovery", () => { it("recovers its own joined copyback receipt after the application pool disconnects during cleanup", async () => { const seeded = await seedRun({ executionWorkspaceId: randomUUID(), title: "Reconnect joined copyback" }); - const interruptedDb = createDb(connectionString); + const interruptedDb = createDb(connectionString, { maxConnections: 6 }); let joined = false; await expect(withNativeWorkspaceFinalizationOwnership({ db: interruptedDb, companyId, runId: seeded.runId }, async () => { await fs.writeFile(path.join(workspaceRoot, "joined-copyback.txt"), "durable work"); @@ -507,7 +507,7 @@ describe("native workspace finalization recovery", () => { .toEqual({ acquired: false, reason: "owner_unverified" }); } await db.update(heartbeatRuns).set({ runnerProfileJson: beforeReconnect.runnerProfileJson }).where(eq(heartbeatRuns.id, seeded.runId)); - expect(await withNativeWorkspaceFinalizationOwnership({ db: createDb(connectionString), companyId, runId: seeded.runId }, async () => "resumed")) + expect(await withNativeWorkspaceFinalizationOwnership({ db: createDb(connectionString, { maxConnections: 6 }), companyId, runId: seeded.runId }, async () => "resumed")) .toEqual({ acquired: true, value: "resumed" }); }); diff --git a/server/src/services/native-status-reassessment-notifications.ts b/server/src/services/native-status-reassessment-notifications.ts index fb845523bb4..d3b543d9914 100644 --- a/server/src/services/native-status-reassessment-notifications.ts +++ b/server/src/services/native-status-reassessment-notifications.ts @@ -1,8 +1,10 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; export type NativeStatusReassessmentScope = { companyId: string; issueId?: string; runId?: string; agentId?: string }; -export function notifyNativeStatusReassessment(tx: object, scope: NativeStatusReassessmentScope) { +export async function notifyNativeStatusReassessment(tx: object, scope: NativeStatusReassessmentScope) { + await notifyIssueRecovery(tx, scope ? { companyId: scope.companyId } : undefined); return notifyDeliveryWork(tx, DELIVERY_QUEUES.nativeStatusReassessment, JSON.stringify({ companyId: scope.companyId, issueId: scope.issueId, runId: scope.runId, agentId: scope.agentId })); } diff --git a/server/src/services/recovery/service.ts b/server/src/services/recovery/service.ts index e3596791942..07e8605bd73 100644 --- a/server/src/services/recovery/service.ts +++ b/server/src/services/recovery/service.ts @@ -27,7 +27,7 @@ import { decideLegacyContinuation, legacyDispositionEpisode, legacyDispositionFingerprint, LEGACY_DISPOSITION_REPAIR_INSTRUCTION, type LegacyDispositionEpisode, } from "./legacy-continuation.js"; -import { CONTROLLER_LEASE_LOST_FAILURE_CODE, hasLiveLegacyController } from "../legacy-controller-lease.js"; +import { CONTROLLER_LEASE_LOST_FAILURE_CODE, hasLiveLegacyController, liveLegacyControllerExpiresAt } from "../legacy-controller-lease.js"; import { isCompletedOnboardingHandoffWake } from "../chat-completion-delivery.js"; import { instanceSettingsService } from "../instance-settings.js"; import { isWaitingConversation, settleConversationTurnForRun, deliverConversationComments } from "../agent-conversations.js"; @@ -245,6 +245,7 @@ type ResolvedDependencyWakeBackstopOptions = { runId?: string | null; companyId?: string | null; blockerIssueId?: string | null; + issueId?: string; source?: ResolvedDependencyWakeBackstopSource; }; @@ -2202,7 +2203,7 @@ export function recoveryService( return Boolean(budgetBlock); } - async function reconcileUnassignedBlockingIssues() { + async function reconcileUnassignedBlockingIssues(opts?: { companyId?: string }) { const candidates = await db .select({ id: issues.id, @@ -2216,6 +2217,8 @@ export function recoveryService( .where( and( eq(issueRelations.type, "blocks"), + eq(issueRelations.companyId, issues.companyId), + opts?.companyId ? eq(issues.companyId, opts.companyId) : undefined, inArray(issues.status, ["todo", "blocked"]), isNull(issues.assigneeAgentId), isNull(issues.assigneeUserId), @@ -3500,7 +3503,7 @@ export function recoveryService( return Boolean(run || wake); } - async function reconcileActiveRecoveryActions() { + async function reconcileActiveRecoveryActions(opts?: { companyId?: string }) { const rows = await db .select({ action: issueRecoveryActions, @@ -3514,7 +3517,8 @@ export function recoveryService( eq(issues.companyId, issueRecoveryActions.companyId), ), ) - .where(inArray(issueRecoveryActions.status, ["active", "escalated"])); + .where(and(inArray(issueRecoveryActions.status, ["active", "escalated"]), + opts?.companyId ? eq(issueRecoveryActions.companyId, opts.companyId) : undefined)); const result = { requeued: 0, @@ -4526,14 +4530,20 @@ export function recoveryService( } async function reconcileStrandedAssignedIssues(opts?: { + companyId?: string; + issueId?: string; + onDeferredDeadline?: (at: number) => void; issueCreatedAtGte?: Date | null; skipExternalConversationSettlement?: boolean; + skipRelatedRecovery?: boolean; }) { const candidates = await db .select(recoveryIssueFields) .from(issues) .where( and( + opts?.companyId ? eq(issues.companyId, opts.companyId) : undefined, + opts?.issueId ? eq(issues.id, opts.issueId) : undefined, isNull(issues.assigneeUserId), inArray(issues.status, ["todo", "in_progress", "in_review"]), or( @@ -5714,6 +5724,7 @@ export function recoveryService( classification.baseBackoffMs * Math.pow(2, Math.max(0, consecutive - 1)); if (elapsed < requiredDelay) { + opts?.onDeferredDeadline?.(latestFinishedAt.getTime() + requiredDelay); result.skipped += 1; continue; } @@ -5773,16 +5784,18 @@ export function recoveryService( } } - const orphanBlockerRecovery = await reconcileUnassignedBlockingIssues(); - result.orphanBlockersAssigned = orphanBlockerRecovery.assigned; - result.skipped += orphanBlockerRecovery.skipped; - result.issueIds.push(...orphanBlockerRecovery.issueIds); + if (!opts?.skipRelatedRecovery) { + const orphanBlockerRecovery = await reconcileUnassignedBlockingIssues(opts); + result.orphanBlockersAssigned = orphanBlockerRecovery.assigned; + result.skipped += orphanBlockerRecovery.skipped; + result.issueIds.push(...orphanBlockerRecovery.issueIds); - const activeRecovery = await reconcileActiveRecoveryActions(); - result.continuationRequeued += activeRecovery.requeued; - result.escalated += activeRecovery.escalated; - result.skipped += activeRecovery.skipped; - result.issueIds.push(...activeRecovery.issueIds); + const activeRecovery = await reconcileActiveRecoveryActions(opts); + result.continuationRequeued += activeRecovery.requeued; + result.escalated += activeRecovery.escalated; + result.skipped += activeRecovery.skipped; + result.issueIds.push(...activeRecovery.issueIds); + } result.issueIds = [...new Set(result.issueIds)]; return result; @@ -5815,7 +5828,7 @@ export function recoveryService( source === "workspace.finalize" ? "workspace_finalize_reconciliation" : "issue_graph_liveness_reconciliation"; - const useCursor = !opts?.blockerIssueId; + const useCursor = !opts?.blockerIssueId && !opts?.issueId; const queryCandidates = (afterIssueId: string | null) => { const filters = [ @@ -5825,6 +5838,7 @@ export function recoveryService( sql`${issues.assigneeAgentId} is not null`, ]; if (opts?.companyId) filters.push(eq(issues.companyId, opts.companyId)); + if (opts?.issueId) filters.push(eq(issues.id, opts.issueId)); if (afterIssueId) filters.push(gt(issues.id, afterIssueId)); if (opts?.blockerIssueId) { @@ -6115,6 +6129,7 @@ export function recoveryService( // fallback below. Without it, a terminal issue named in the run context // snapshot would still terminalize the shared run and defeat the guard. runReferencedByActiveIssue?: boolean; + onDeferredDeadline?: (at: number) => void; }, ): Promise<{ terminalized: boolean; status: string }> { // Act only on a run in "running" status. A "queued" run has no process yet, @@ -6130,8 +6145,11 @@ export function recoveryService( // Another controller may own a sandbox run whose PID has no meaning on // this host. Its live lease owns both execution and finalization, even if // the issue is already terminal or this process has no in-memory handle. - if (await hasLiveLegacyController(db, run)) + const controllerDeadline = await liveLegacyControllerExpiresAt(db, run); + if (controllerDeadline) { + options?.onDeferredDeadline?.(controllerDeadline.getTime()); return { terminalized: false, status: run.status }; + } const pid = run.processPid ?? null; const processGroupId = run.processGroupId ?? null; @@ -6352,7 +6370,7 @@ export function recoveryService( // still claims to be live but can no longer reach a terminal status on its // own, so a stuck "running" run can no longer block the sweep. Idempotent and // safe: clears at most one row's worth of lock columns per candidate. - async function sweepStaleIssueLocks() { + async function sweepStaleIssueLocks(opts?: { companyId?: string; issueId?: string; onDeferredDeadline?: (at: number) => void }) { const result = { cleared: 0, issueIds: [] as string[], @@ -6369,7 +6387,9 @@ export function recoveryService( }) .from(issues) .where( - sql`(${issues.checkoutRunId} is not null or ${issues.executionRunId} is not null)`, + and(sql`(${issues.checkoutRunId} is not null or ${issues.executionRunId} is not null)`, + opts?.companyId ? eq(issues.companyId, opts.companyId) : undefined, + opts?.issueId ? eq(issues.id, opts.issueId) : undefined), ); const referencedRunIds = [ @@ -6384,7 +6404,8 @@ export function recoveryService( ? await db .select() .from(heartbeatRuns) - .where(inArray(heartbeatRuns.id, referencedRunIds)) + .where(and(inArray(heartbeatRuns.id, referencedRunIds), + opts?.companyId ? eq(heartbeatRuns.companyId, opts.companyId) : undefined)) : []; const runStatusById = new Map(); for (const row of runRows) runStatusById.set(row.id, row.status); @@ -6395,8 +6416,15 @@ export function recoveryService( // the same run id in a stale lock column. The terminal reference alone must // not terminalize a run that an active issue still owns, so exclude these // runs from the issue-terminal authority below. + const ownershipReferences = opts?.issueId && referencedRunIds.length > 0 + ? await db.select({ companyId: issues.companyId, status: issues.status, + checkoutRunId: issues.checkoutRunId, executionRunId: issues.executionRunId }).from(issues).where(and( + opts.companyId ? eq(issues.companyId, opts.companyId) : undefined, + or(inArray(issues.checkoutRunId, referencedRunIds), inArray(issues.executionRunId, referencedRunIds)), + )) + : candidates; const runIdsReferencedByActiveIssue = new Set(); - for (const issue of candidates) { + for (const issue of ownershipReferences) { if (issue.status === "done" || issue.status === "cancelled") continue; for (const runId of [issue.checkoutRunId, issue.executionRunId]) { if (runId) runIdsReferencedByActiveIssue.add(runId); @@ -6437,6 +6465,7 @@ export function recoveryService( referencingIssueTerminalStatus: issueTerminalStatusByRunId.get(row.id) ?? null, runReferencedByActiveIssue: runIdsReferencedByActiveIssue.has(row.id), + onDeferredDeadline: opts?.onDeferredDeadline, }); runStatusById.set(row.id, outcome.status); if (outcome.terminalized) result.terminalizedRunIds.push(row.id); @@ -6540,6 +6569,8 @@ export function recoveryService( recordWatchdogDecision, scanSilentActiveRuns, reconcileStrandedAssignedIssues, + reconcileUnassignedBlockingIssues, + reconcileActiveRecoveryActions, reconcileLegacyContinuation, legacyRepairDispatchBlock, sweepStaleIssueLocks, diff --git a/server/src/services/recovery/work.ts b/server/src/services/recovery/work.ts new file mode 100644 index 00000000000..407e4f1eb6d --- /dev/null +++ b/server/src/services/recovery/work.ts @@ -0,0 +1,113 @@ +import { registerTaskWatchdogWork } from "../task-watchdog-work.js"; +import { and, asc, eq, gt, inArray, isNotNull, isNull, or, sql } from "drizzle-orm"; +import { issueRecoveryActions, issueRelations, issues, type Db } from "@paperclipai/db"; +import type { createDeliveryWorkCoordinator } from "../delivery-work-coordinator.js"; +import { DELIVERY_QUEUES, type DeliveryQueue } from "../delivery-work-notifications.js"; +import type { IssueRecoveryScope } from "../issue-recovery-notifications.js"; +import { registerScopedDeadlineWork } from "../scoped-deadline-work.js"; + +type Entry = { id: string; companyId: string; dueAt: number }; +type Scope = { companyId: string; issueId: string; onDeferredDeadline: (at: number) => void }; +const PAGE_SIZE = 100; + +export function registerIssueRecoveryWork( + db: Db, + coordinator: ReturnType, + owner: { + stranded(scope: Scope): Promise; + orphanBlockers(scope: { companyId: string }): Promise; + recoveryActions(scope: { companyId: string }): Promise; + dependencies(scope: Scope): Promise<{ enqueueFailed: number }>; + locks(scope: Scope): Promise; + watchdogs(scope: { companyId: string; watchdogId: string; onDeferredDeadline: (at: number) => void }): Promise<{ incomplete: number }>; + schedulingSuppressed(): Promise; + }, + canRun: () => boolean, +) { + function register(queue: DeliveryQueue, statuses: string[] | null, check: (scope: Scope) => Promise) { + const cursors = new Map(); + let enabled = false; + return registerScopedDeadlineWork(coordinator, { + queue, + reconstructionIntervalMs: 30_000, + beforePass: async () => { enabled = !(await owner.schedulingSuppressed()); }, + decodeScope: hint => hint === "*" ? undefined : JSON.parse(hint) as IssueRecoveryScope, + matches: (entry, scope) => !scope || (entry.companyId === scope.companyId && (!scope.issueId || entry.id === scope.issueId)), + load: async scope => { + const key = scope ? JSON.stringify([scope.companyId, scope.issueId]) : "*"; + if (!enabled) { cursors.delete(key); return []; } + const cursor = cursors.get(key); + const rows = await db.select({ id: issues.id, companyId: issues.companyId }).from(issues).where(and( + scope ? eq(issues.companyId, scope.companyId) : undefined, + scope?.issueId ? eq(issues.id, scope.issueId) : undefined, + cursor ? gt(issues.id, cursor) : undefined, + statuses ? inArray(issues.status, statuses) : or(isNotNull(issues.checkoutRunId), isNotNull(issues.executionRunId)), + statuses ? isNull(issues.hiddenAt) : undefined, + statuses ? isNull(issues.assigneeUserId) : undefined, + statuses ? or(isNotNull(issues.assigneeAgentId), eq(issues.status, "in_review")) : undefined, + )).orderBy(asc(issues.id)).limit(PAGE_SIZE); + const complete = rows.length < PAGE_SIZE; + if (complete) cursors.delete(key); else cursors.set(key, rows.at(-1)!.id); + return { rows: rows.map(row => ({ ...row, dueAt: Date.now() })), complete }; + }, + check: async entry => { + if (!enabled) return null; + let next: number | null = null; + await check({ companyId: entry.companyId, issueId: entry.id, + onDeferredDeadline: at => { next = next === null ? at : Math.min(next, at); } }); + return next === null ? null : { ...entry, dueAt: next }; + }, + }, canRun); + } + function registerCompany(queue: DeliveryQueue, kind: "blockers" | "actions", check: (scope: { companyId: string }) => Promise) { + const cursors = new Map(); + let enabled = false; + return registerScopedDeadlineWork(coordinator, { + queue, + reconstructionIntervalMs: 30_000, + beforePass: async () => { enabled = !(await owner.schedulingSuppressed()); }, + decodeScope: hint => hint === "*" ? undefined : JSON.parse(hint) as IssueRecoveryScope, + matches: (entry, scope) => !scope || entry.companyId === scope.companyId, + load: async scope => { + const key = scope?.companyId ?? "*"; + if (!enabled) { cursors.delete(key); return []; } + const cursor = cursors.get(key); + const rows = kind === "actions" + ? await db.selectDistinct({ id: issueRecoveryActions.companyId, companyId: issueRecoveryActions.companyId }) + .from(issueRecoveryActions).where(and(inArray(issueRecoveryActions.status, ["active", "escalated"]), + scope ? eq(issueRecoveryActions.companyId, scope.companyId) : undefined, + cursor ? gt(issueRecoveryActions.companyId, cursor) : undefined)) + .orderBy(asc(issueRecoveryActions.companyId)).limit(PAGE_SIZE) + : await db.selectDistinct({ id: issues.companyId, companyId: issues.companyId }).from(issues).where(and( + inArray(issues.status, ["todo", "blocked"]), isNull(issues.assigneeAgentId), isNull(issues.assigneeUserId), + isNotNull(issues.createdByAgentId), + scope ? eq(issues.companyId, scope.companyId) : undefined, + cursor ? gt(issues.companyId, cursor) : undefined, + sql`exists (select 1 from ${issueRelations} r inner join ${issues} dependent + on dependent.id = r.related_issue_id and dependent.company_id = r.company_id + where r.company_id = ${issues.companyId} and r.issue_id = ${issues.id} + and r.type = 'blocks' and dependent.status not in ('done', 'cancelled'))`, + )).orderBy(asc(issues.companyId)).limit(PAGE_SIZE); + const complete = rows.length < PAGE_SIZE; + if (complete) cursors.delete(key); else cursors.set(key, rows.at(-1)!.id); + return { rows: rows.map(row => ({ ...row, dueAt: Date.now() })), complete }; + }, + check: async entry => { if (enabled) await check({ companyId: entry.companyId }); return null; }, + }, canRun); + } + const assignments = register(DELIVERY_QUEUES.strandedAssignments, ["todo", "in_progress", "in_review"], owner.stranded); + const orphanBlockers = registerCompany(DELIVERY_QUEUES.orphanBlockers, "blockers", owner.orphanBlockers); + const recoveryActions = registerCompany(DELIVERY_QUEUES.activeRecoveryActions, "actions", owner.recoveryActions); + const dependencies = register(DELIVERY_QUEUES.resolvedDependencies, ["blocked"], async scope => { + const result = await owner.dependencies(scope); + if (result.enqueueFailed > 0) throw new Error("Resolved dependency wake remains undelivered"); + }); + const locks = register(DELIVERY_QUEUES.staleIssueLocks, null, owner.locks); + const watchdogs = registerTaskWatchdogWork(db, coordinator, { + reconcile: owner.watchdogs, enabled: async () => !(await owner.schedulingSuppressed()), + }, canRun); + const workers = [assignments, orphanBlockers, recoveryActions, dependencies, locks, watchdogs]; + return { ready: Promise.all(workers.map(worker => worker.ready)), + wake() { for (const worker of workers) worker.invalidate(); }, + async stop() { await Promise.all(workers.map(worker => worker.stop())); } }; +} diff --git a/server/src/services/run-dispatch-notifications.ts b/server/src/services/run-dispatch-notifications.ts index 276edacab23..4fca35c1d2a 100644 --- a/server/src/services/run-dispatch-notifications.ts +++ b/server/src/services/run-dispatch-notifications.ts @@ -1,8 +1,10 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { DELIVERY_QUEUES, notifyDeliveryWork } from "./delivery-work-notifications.js"; export type RunDispatchScope = { companyId: string }; export async function notifyRunDispatch(transaction: object, scope?: RunDispatchScope) { + await notifyIssueRecovery(transaction, scope ? { companyId: scope.companyId } : undefined); const hint = scope ? JSON.stringify({ companyId: scope.companyId }) : "*"; await notifyDeliveryWork(transaction, DELIVERY_QUEUES.queuedRunDispatch, hint); } diff --git a/server/src/services/scoped-deadline-work.ts b/server/src/services/scoped-deadline-work.ts index 8c94a863ccd..fd90a9b372e 100644 --- a/server/src/services/scoped-deadline-work.ts +++ b/server/src/services/scoped-deadline-work.ts @@ -13,6 +13,8 @@ export function registerScopedDeadlineWork( batchSize?: number; minimumPassIntervalMs?: number; concurrentChecks?: { limit: number; key(entry: Entry): string }; + reconstructionIntervalMs?: number; + beforePass?(): Promise; decodeScope(hint: string): Scope | undefined; matches(entry: Entry, scope?: Scope): boolean; load(scope?: Scope, signal?: AbortSignal): Promise; @@ -29,6 +31,7 @@ export function registerScopedDeadlineWork( const entries = new Map(); const failures = new Map(); const scopeFailures = new Map(); + const reconstructAfter = new Map(); let earliest = 0; let lastCompany: string | null = null; function failed(map: typeof failures, id: string) { @@ -38,13 +41,14 @@ export function registerScopedDeadlineWork( function dirtyScopes() { return [...dirty].filter(hint => hint !== "*" || !scopeFailures.has(hint)) .filter(hint => !scans.has(hint) || scopeFailures.has(hint)) + .filter(hint => (reconstructAfter.get(hint) ?? 0) <= Date.now() || scopeFailures.has(hint)) .map(hint => { try { return options.decodeScope(hint); } catch { return undefined; } }); } function next() { if (!canRun()) return dirty.size > 0 || entries.size > 0 ? Date.now() + 30_000 : null; let nextAt: number | null = null; const take = (at: number) => { nextAt = nextAt === null ? at : Math.min(nextAt, at); }; - for (const hint of dirty) take(Math.max(earliest, scopeFailures.get(hint)?.retryAt ?? 0)); + for (const hint of dirty) take(Math.max(earliest, reconstructAfter.get(hint) ?? 0, scopeFailures.get(hint)?.retryAt ?? 0)); const unavailable = dirtyScopes(); for (const entry of entries.values()) if (!unavailable.some(scope => options.matches(entry, scope))) take(Math.max(earliest, entry.dueAt, failures.get(entry.id)?.retryAt ?? 0)); @@ -58,9 +62,18 @@ export function registerScopedDeadlineWork( } }, run: async signal => { if (!canRun() || Date.now() < earliest) return; + if ((options.reconstructionIntervalMs ?? 0) > 0) for (const [hint, until] of reconstructAfter) { + if (until <= Date.now()) reconstructAfter.delete(hint); + } + const ready = [...dirty].filter(hint => Math.max(reconstructAfter.get(hint) ?? 0, scopeFailures.get(hint)?.retryAt ?? 0) <= Date.now()); + if (ready.length === 0 && ![...entries.values()].some(entry => Math.max(entry.dueAt, failures.get(entry.id)?.retryAt ?? 0) <= Date.now())) return; earliest = Date.now() + (options.minimumPassIntervalMs ?? 1000); + try { await options.beforePass?.(); } catch (error) { + for (const hint of ready) failed(scopeFailures, hint); + for (const entry of entries.values()) if (entry.dueAt <= Date.now()) failed(failures, entry.id); + throw error; + } const errors: unknown[] = []; - const ready = [...dirty].filter(hint => (scopeFailures.get(hint)?.retryAt ?? 0) <= Date.now()); const requested = ready.includes("*") ? ["*", ...ready.filter(hint => hint !== "*")].slice(0, 25) : ready.slice(0, 25); @@ -85,6 +98,9 @@ export function registerScopedDeadlineWork( entries.delete(entry.id); failures.delete(entry.id); } scans.delete(hint); + if ((options.reconstructionIntervalMs ?? 0) > 0) { + reconstructAfter.set(hint, Date.now() + options.reconstructionIntervalMs!); + } if ((versions.get(hint) ?? 0) !== scan.version) dirty.add(hint); else versions.delete(hint); if (!scope) scopeFailures.clear(); else scopeFailures.delete(hint); } catch (error) { diff --git a/server/src/services/system-recovery.ts b/server/src/services/system-recovery.ts index a554a765c4c..347593dafed 100644 --- a/server/src/services/system-recovery.ts +++ b/server/src/services/system-recovery.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { and, eq, sql } from "drizzle-orm"; import { heartbeatRuns, issueComments, issueRecoveryActions, type Db } from "@paperclipai/db"; import { writeExecutionControl } from "./execution-control-notifications.js"; @@ -11,6 +12,7 @@ export async function adoptSystemRecovery(db: Db, source: WorkspaceRecoverySourc .where(and(eq(issueRecoveryActions.companyId, source.companyId), eq(issueRecoveryActions.id, source.actionId), eq(issueRecoveryActions.sourceIssueId, source.issueId))).for("update"); if (!existing || existing.evidence.systemRecovery) return; + await notifyIssueRecovery(tx, { companyId: source.companyId }); await notifyDeliveryWork(tx, DELIVERY_QUEUES.workspaceRecovery); const state = createSystemRecovery(source.runId); // Atomic, once per source. An exhausted previous execution budget is history; diff --git a/server/src/services/task-watchdog-diagnostics.ts b/server/src/services/task-watchdog-diagnostics.ts deleted file mode 100644 index ea08eebe2b4..00000000000 --- a/server/src/services/task-watchdog-diagnostics.ts +++ /dev/null @@ -1,16 +0,0 @@ -export function createIncompleteTaskWatchdogScanReporter( - warn: (details: { incomplete: number; newIncompleteIssueIds: string[] }, message: string) => void, -) { - let previousIncompleteIssueIds = new Set(); - return (result: { incomplete: number; incompleteIssueIds: string[] }, phase: "startup" | "periodic") => { - const currentIssueIds = new Set(result.incompleteIssueIds); - const newIncompleteIssueIds = [...currentIssueIds].filter((id) => !previousIncompleteIssueIds.has(id)); - previousIncompleteIssueIds = currentIssueIds; - if (newIncompleteIssueIds.length === 0) return; - warn( - { incomplete: result.incomplete, newIncompleteIssueIds }, - `${phase} task-watchdog reconciliation found incomplete subtree scans`, - ); - }; -} - diff --git a/server/src/services/task-watchdog-work.ts b/server/src/services/task-watchdog-work.ts new file mode 100644 index 00000000000..98794472da2 --- /dev/null +++ b/server/src/services/task-watchdog-work.ts @@ -0,0 +1,49 @@ +import { and, asc, eq, gt } from "drizzle-orm"; +import { issueWatchdogs, type Db } from "@paperclipai/db"; +import type { createDeliveryWorkCoordinator } from "./delivery-work-coordinator.js"; +import { DELIVERY_QUEUES } from "./delivery-work-notifications.js"; +import type { IssueRecoveryScope } from "./issue-recovery-notifications.js"; +import { registerScopedDeadlineWork } from "./scoped-deadline-work.js"; + +type Entry = { id: string; companyId: string; dueAt: number }; + +export function registerTaskWatchdogWork( + db: Db, + coordinator: ReturnType, + owner: { + enabled(): Promise; + reconcile(scope: { companyId: string; watchdogId: string; onDeferredDeadline: (at: number) => void }): Promise<{ incomplete: number }>; + }, + canRun: () => boolean, +) { + const cursors = new Map(); + let enabled = false; + return registerScopedDeadlineWork(coordinator, { + queue: DELIVERY_QUEUES.taskWatchdogs, + reconstructionIntervalMs: 30_000, + beforePass: async () => { enabled = await owner.enabled(); }, + decodeScope: hint => hint === "*" ? undefined : JSON.parse(hint) as IssueRecoveryScope, + matches: (entry, scope) => !scope || entry.companyId === scope.companyId, + load: async scope => { + const key = scope?.companyId ?? "*"; + if (!enabled) { cursors.delete(key); return []; } + const cursor = cursors.get(key); + const rows = await db.select({ id: issueWatchdogs.id, companyId: issueWatchdogs.companyId }) + .from(issueWatchdogs).where(and(eq(issueWatchdogs.status, "active"), + scope ? eq(issueWatchdogs.companyId, scope.companyId) : undefined, + cursor ? gt(issueWatchdogs.id, cursor) : undefined)) + .orderBy(asc(issueWatchdogs.id)).limit(100); + const complete = rows.length < 100; + if (complete) cursors.delete(key); else cursors.set(key, rows.at(-1)!.id); + return { rows: rows.map(row => ({ ...row, dueAt: Date.now() })), complete }; + }, + check: async entry => { + if (!enabled) return null; + let next: number | null = null; + const result = await owner.reconcile({ companyId: entry.companyId, watchdogId: entry.id, + onDeferredDeadline: at => { next = next === null ? at : Math.min(next, at); } }); + if (result.incomplete > 0) throw new Error(`Task watchdog ${entry.id} in company ${entry.companyId} has an incomplete subtree`); + return next === null ? null : { ...entry, dueAt: next }; + }, + }, canRun); +} diff --git a/server/src/services/task-watchdogs.ts b/server/src/services/task-watchdogs.ts index cf8d92d39df..dd1aa980d3c 100644 --- a/server/src/services/task-watchdogs.ts +++ b/server/src/services/task-watchdogs.ts @@ -1,3 +1,4 @@ +import { notifyIssueRecovery } from "./issue-recovery-notifications.js"; import { createHash } from "node:crypto"; import { and, asc, eq, gte, inArray, isNull, or, sql } from "drizzle-orm"; import type { Db } from "@paperclipai/db"; @@ -831,7 +832,7 @@ async function updateIssueWatchdogRow( return updated; } -export async function upsertIssueWatchdogForIssue( +async function upsertIssueWatchdogInTransaction( dbOrTx: any, companyId: string, issueId: string, @@ -847,12 +848,13 @@ export async function upsertIssueWatchdogForIssue( .where(and(eq(issueWatchdogs.companyId, companyId), eq(issueWatchdogs.issueId, issueId))) .then((rows: IssueWatchdogRow[]) => rows[0] ?? null); + await notifyIssueRecovery(dbOrTx, { companyId }); if (existing) { const updated = await updateIssueWatchdogRow(dbOrTx, existing, input, now); return { watchdog: toIssueWatchdog(updated), created: false }; } - const insertResult: { row: IssueWatchdogRow; created: boolean } = await dbOrTx + const insertResult: { row: IssueWatchdogRow; created: boolean } = await dbOrTx.transaction(async (tx: Db) => tx .insert(issueWatchdogs) .values({ companyId, @@ -870,7 +872,7 @@ export async function upsertIssueWatchdogForIssue( updatedAt: now, }) .returning() - .then((rows: IssueWatchdogRow[]) => ({ row: rows[0], created: true })) + .then((rows: IssueWatchdogRow[]) => ({ row: rows[0], created: true }))) .catch(async (error: unknown) => { if (!isIssueWatchdogUniqueConflict(error)) throw error; const winner = await dbOrTx @@ -885,6 +887,15 @@ export async function upsertIssueWatchdogForIssue( return { watchdog: toIssueWatchdog(insertResult.row), created: insertResult.created }; } +export function upsertIssueWatchdogForIssue( + dbOrTx: Db | Parameters[0]>[0], + companyId: string, + issueId: string, + input: IssueWatchdogUpsertInput, +): Promise<{ watchdog: IssueWatchdog; created: boolean }> { + return dbOrTx.transaction(tx => upsertIssueWatchdogInTransaction(tx, companyId, issueId, input)); +} + export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) { const issuesSvc = issueService(db); @@ -1478,7 +1489,7 @@ export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) return created; } - async function evaluateWatchdog(row: IssueWatchdogRow, opts: { runId?: string | null } = {}) { + async function evaluateWatchdog(row: IssueWatchdogRow, opts: { runId?: string | null; onDeferredDeadline?: (at: number) => void } = {}) { const watchdog = await markTerminalWatchdogIssueReviewed(row, opts); const sourceIssue = await db .select() @@ -1491,6 +1502,13 @@ export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) const input = await collectClassifierInput(watchdog.companyId, watchdog); const classification = classifyTaskWatchdogSubtree(input); + if (classification.state === "pending_first_run") { + const pending = new Set(classification.pendingIssueIds); + for (const issue of input.issues) if (pending.has(issue.id)) { + const createdAt = toEpochMs(issue.createdAt); + if (createdAt !== null) opts.onDeferredDeadline?.(createdAt + TASK_WATCHDOG_FIRST_RUN_GRACE_MS); + } + } if (classification.state !== "stopped") { return { state: classification.state, reason: classification.reason, classification }; } @@ -1610,13 +1628,14 @@ export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) }; } - async function listActiveWatchdogsForCompany(companyId?: string | null) { + async function listActiveWatchdogsForCompany(companyId?: string | null, watchdogId?: string) { return db .select() .from(issueWatchdogs) .where(and( eq(issueWatchdogs.status, "active"), ...(companyId ? [eq(issueWatchdogs.companyId, companyId)] : []), + watchdogId ? eq(issueWatchdogs.id, watchdogId) : undefined, )); } @@ -1746,14 +1765,16 @@ export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) issueId: string, actor: ActorFields = {}, ): Promise => { - await assertWatchedIssue(db, companyId, issueId); - const existing = await db + return db.transaction(async tx => { + await assertWatchedIssue(tx, companyId, issueId); + const existing = await tx .select() .from(issueWatchdogs) .where(and(eq(issueWatchdogs.companyId, companyId), eq(issueWatchdogs.issueId, issueId))) .then((rows) => rows[0] ?? null); if (!existing || existing.status === "disabled") return null; - const [updated] = await db + await notifyIssueRecovery(tx, { companyId }); + const [updated] = await tx .update(issueWatchdogs) .set({ status: "disabled", @@ -1765,14 +1786,17 @@ export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) .where(eq(issueWatchdogs.id, existing.id)) .returning(); return toIssueWatchdog(updated); + }); }, reconcileTaskWatchdogs: async (opts: { companyId?: string | null; runId?: string | null; + watchdogId?: string; + onDeferredDeadline?: (at: number) => void; issueCreatedAtGte?: Date | null; } = {}) => { - let rows = await listActiveWatchdogsForCompany(opts.companyId ?? null); + let rows = await listActiveWatchdogsForCompany(opts.companyId ?? null, opts.watchdogId); if (opts.issueCreatedAtGte) { const watchdogIssueIds = [...new Set(rows.map((row) => row.issueId))]; const eligibleIssueIds = new Set( @@ -1802,7 +1826,7 @@ export function taskWatchdogService(db: Db, deps: TaskWatchdogServiceDeps = {}) }; for (const row of rows) { result.checked += 1; - const evaluated = await evaluateWatchdog(row, { runId: opts.runId ?? null }); + const evaluated = await evaluateWatchdog(row, { runId: opts.runId ?? null, onDeferredDeadline: opts.onDeferredDeadline }); if (evaluated.state === "triggered") { result.triggered += 1; result.watchdogIssueIds.push(evaluated.watchdogIssueId);