diff --git a/doc/task-recovery.md b/doc/task-recovery.md index bc59048df5a..9198e53c9e5 100644 --- a/doc/task-recovery.md +++ b/doc/task-recovery.md @@ -33,6 +33,12 @@ The source recovery action holds a validated `systemRecovery` record. Its revision and generation fence late bookkeeping writes. Physical exports still use the existing workspace ownership lock and controller stop receipts. +The export owner can reopen its exact stopped sandbox through the environment +runtime's recovery path. This path checks the current source action, run, +environment, allocation, stop-only intent, and physical ownership claim before +calling the provider. The retained-source fence still blocks ordinary resume +and destruction. Recovery does not clear it to gain access to the saved files. + Execution containment and file preservation are independent facts: - Another agent needs authoritative containment of the old executor. @@ -113,6 +119,8 @@ Run the focused PostgreSQL/filesystem suites from `server/`: `server/scripts/workspace-recovery-provider.test.mjs` is an opt-in controlled Daytona probe. It requires `PAPERCLIP_RECOVERY_LIVE=1`, `DAYTONA_API_KEY`, `PAPERCLIP_DAYTONA_SDK_PATH` and an immutable `PAPERCLIP_RECOVERY_IMAGE`. +An immutable provider snapshot UUID in `PAPERCLIP_RECOVERY_SNAPSHOT_ID` can +replace the image digest. The probe checks its ID and active state first. It interrupts export, joins the first controller, starts a second controller and verifies files, preservation receipts, agent-start count and external-operation count before diff --git a/maps/agent-access-map/recovery.md b/maps/agent-access-map/recovery.md index 2b379352797..77ea407fd97 100644 --- a/maps/agent-access-map/recovery.md +++ b/maps/agent-access-map/recovery.md @@ -212,6 +212,12 @@ Gaps: An acknowledged retry can remain pending or fail; report actual useful res Capability ID: `recovery/workspace`. +The internal preservation resume path grants no board or agent execution API. +It requires the exact source action, company, run, lease and environment, a +held physical workspace owner, and its current stop-only cleanup claim. The +ordinary resume and destruction fences still apply to protected sources. The +assembled-runtime regression checks this separation before any provider call. + Review: `operation-reviewed`. Each workspace repair/export/reconstruction/physical-owner operation has its own proof and authority. diff --git a/maps/feature-map/recovery.md b/maps/feature-map/recovery.md index 8f9f00902b5..4fb2ff30d4d 100644 --- a/maps/feature-map/recovery.md +++ b/maps/feature-map/recovery.md @@ -222,6 +222,14 @@ cover quiet live recovery, read-only access, stale or missing stop proof, source-only repair, and preserved task status. These tests use fixtures; separately verify original files and their attached artifact before recording a real repair. +For a source with a retained-file protection marker, exercise recovery through +the assembled environment runtime. Its exact preservation owner may reopen the +stopped allocation to read saved files; ordinary resume stays blocked. Reject a +changed claim, missing stop intent, wrong lease or wrong environment before a +provider call. Verify saved and newer local files, one preservation receipt, and +no additional agent turn. The PostgreSQL regression covers this boundary; the +opt-in provider probe also uses this runtime path with the protection marker. + Repeat source-only repair with a `succeeded` legacy run that still has a retained file obligation. Its result must remain successful, its current task owner and status must stay unchanged, and later saved input must become eligible for normal diff --git a/server/scripts/workspace-recovery-provider.test.mjs b/server/scripts/workspace-recovery-provider.test.mjs index a9902ae5808..e4a7411dae6 100644 --- a/server/scripts/workspace-recovery-provider.test.mjs +++ b/server/scripts/workspace-recovery-provider.test.mjs @@ -15,6 +15,7 @@ import { NOOP_PLUGIN_TRACER } from "@paperclipai/plugin-sdk"; import { startEmbeddedPostgresTestDatabase } from "../src/__tests__/helpers/embedded-postgres.js"; import { readSystemRecovery } from "../src/services/system-recovery-state.js"; import { recoverRetainedWorkspace } from "../src/services/workspace-recovery.js"; +import { classifyEnvironmentCapabilities, environmentRuntimeService } from "../src/services/environment-runtime.js"; import { attachPreservedWorkspaceSnapshots } from "../src/services/workspace-recovery-snapshot.js"; import { performSyncOut } from "../../packages/plugins/sandbox-providers/daytona/src/file-sync.js"; @@ -68,7 +69,11 @@ it.skipIf(!live || !worker)("provider controller", async () => { }, syncOut: operations => performSyncOut({ sandbox, operations, remoteDir: f.remoteCwd, timeoutSeconds: 120 }), } }; - const environmentRuntime = { + const driver = { + driver: "sandbox", + acquireRunLease: async () => { throw new Error("Recovery must not acquire another sandbox"); }, + releaseRunLease: async () => { throw new Error("Recovery must not destroy its retained source"); }, + resolveCapabilities: async () => classifyEnvironmentCapabilities({ verifiedMethods: [] }), resumeRunLease: async () => { await sandbox.start(120); await sandbox.refreshData(); if (sandbox.state !== "started") throw new Error("Provider did not confirm start"); @@ -80,6 +85,7 @@ it.skipIf(!live || !worker)("provider controller", async () => { return { providerLeaseId: sandbox.id, state: "stopped" }; }, }; + const environmentRuntime = environmentRuntimeService(db, { drivers: [driver] }); await recoverRetainedWorkspace({ db, ...f, environmentRuntime }); const [action] = await db.select().from(issueRecoveryActions).where(eq(issueRecoveryActions.id, f.actionId)); const state = readSystemRecovery(action.evidence); @@ -90,7 +96,9 @@ it.skipIf(!live || !worker)("provider controller", async () => { it.skipIf(!live || Boolean(worker))("preserves provider files across an interrupted export and controller restart without restarting the old agent", async () => { const image = process.env.PAPERCLIP_RECOVERY_IMAGE; - if (!image?.includes("@sha256:")) throw new Error("An immutable qualification image is required"); + const snapshotId = process.env.PAPERCLIP_RECOVERY_SNAPSHOT_ID; + if (!image?.includes("@sha256:") && !/^[0-9a-f-]{36}$/i.test(snapshotId ?? "")) + throw new Error("An immutable qualification image or snapshot ID is required"); const directory = await mkdtemp(path.join(os.tmpdir(), "paperclip-provider-recovery-")); const priorHome = process.env.PAPERCLIP_HOME; process.env.PAPERCLIP_HOME = path.join(directory, "home"); @@ -100,11 +108,16 @@ it.skipIf(!live || Boolean(worker))("preserves provider files across an interrup const db = createDb(database.connectionString); const daytona = await client(); let sandbox; - const evidence = { image, interrupted: false, restored: false, oldAgentStarts: null, externalOperations: null, + const evidence = { image, snapshotId, interrupted: false, restored: false, oldAgentStarts: null, externalOperations: null, prematureCleanup: false, controllerProcesses: [], snapshotCount: 0 }; try { - sandbox = await daytona.create({ image, autoStopInterval: 10, autoArchiveInterval: 60, - resources: { cpu: 2, memory: 4, disk: 10 }, labels: { purpose: "paperclip-recovery-qualification" } }, { timeout: 300 }); + if (snapshotId) { + const snapshot = await daytona.snapshot.get(snapshotId); + expect(snapshot.id).toBe(snapshotId); + expect(snapshot.state).toBe("active"); + } + sandbox = await daytona.create({ ...(snapshotId ? { snapshot: snapshotId } : { image, resources: { cpu: 2, memory: 4, disk: 10 } }), + autoStopInterval: 10, autoArchiveInterval: 60, labels: { purpose: "paperclip-recovery-qualification" } }, { timeout: 300 }); const remoteCwd = "/tmp/paperclip-recovery-fixture"; await sandbox.process.executeCommand(`mkdir -p ${remoteCwd}`, undefined, undefined, 30); await sandbox.process.createSession("old-agent"); @@ -124,7 +137,8 @@ it.skipIf(!live || Boolean(worker))("preserves provider files across an interrup const [lease] = await db.insert(environmentLeases).values({ companyId, issueId, heartbeatRunId: runId, environmentId: environment.id, provider: "daytona", providerLeaseId: sandbox.id, leasePolicy: "retain_on_failure", status: "released", releasedAt: new Date(), - metadata: { remoteCwd, driver: "sandbox", pluginId: randomUUID(), sandboxProviderPlugin: true } }).returning(); + metadata: { remoteCwd, driver: "sandbox", pluginId: randomUUID(), sandboxProviderPlugin: true, + workspaceRestoreRecovery: { schema: "paperclip.workspace-restore-recovery.v1", runId } } }).returning(); const recovery = { schema: "paperclip.workspace-restore-recovery.v1", leaseIds: [lease.id] }; await db.update(heartbeatRuns).set({ resultJson: { workspaceRestoreRecovery: recovery, workspaceRestoreFailure: "restore_failed" } }) .where(eq(heartbeatRuns.id, runId)); diff --git a/server/src/services/environment-runtime.ts b/server/src/services/environment-runtime.ts index 7d14dbf7c81..da016c92491 100644 --- a/server/src/services/environment-runtime.ts +++ b/server/src/services/environment-runtime.ts @@ -4,6 +4,8 @@ import { allowLegacyShutdownWorkspaceCleanup, legacyShutdownWorkspaceResourcePro import { nativeWorkspaceExportPendingForLease } from "./native-runtime/native-workspace-finalization-state.js"; import { beginIdleTrackedWork } from "./task-admission.js"; import { historicalProviderCredentials } from "./historical-provider-credentials.js"; +import { ownedWorkspaceRecoveryLease, type WorkspaceRecoverySourceIdentity } from "./workspace-recovery-source.js"; +import type { NativeWorkspaceFinalizationOwnership } from "./native-runtime/native-workspace-finalization-ownership.js"; import { hasStopOnlyCleanup, prepareSandboxStopAndRetain, readStopOnlyCleanup, settleStopOnlyCleanup, stopOnlyCleanupKey } from "./sandbox-stop-and-retain.js"; import { JsonRpcCallError, readEnvironmentAcquisitionDiagnostic, readEnvironmentCreationCleanupError } from "@paperclipai/plugin-sdk"; import { preserveEnvironmentSyncOutErrorDiagnostic } from "./environment-sync-out-error.js"; @@ -4569,6 +4571,19 @@ export function environmentRuntimeService( return await driver.resumeRunLease(input); }, + async resumeWorkspaceRecoveryLease(input: { + source: WorkspaceRecoverySourceIdentity; leaseId: string; environmentId: string; + ownership: NativeWorkspaceFinalizationOwnership; + }): Promise { + const { lease, environment } = await ownedWorkspaceRecoveryLease(db, { ...input.source, + leaseId: input.leaseId, environmentId: input.environmentId, ownership: input.ownership }); + const driver = requireDriverKey(getLeaseDriverKey(lease, environment as Environment)); + if (!driver.resumeRunLease) throw new Error(`Environment driver "${driver.driver}" does not support lease resume.`); + // Maintenance reopens the protected source only to preserve its files. + // Ordinary resume and destructive cleanup keep their existing fences. + return await driver.resumeRunLease({ environment: environment as Environment, lease: lease as EnvironmentLease }); + }, + async destroyRunLease(input: EnvironmentDriverLeaseInput): Promise { if (await nativeWorkspaceExportPendingForLease(db, input.lease)) return null; if (await legacyShutdownWorkspaceResourceProtected(db, input.lease)) return null; diff --git a/server/src/services/workspace-recovery-source.ts b/server/src/services/workspace-recovery-source.ts index cd5e0b61f24..ab8517aa88c 100644 --- a/server/src/services/workspace-recovery-source.ts +++ b/server/src/services/workspace-recovery-source.ts @@ -3,11 +3,31 @@ import { environmentLeases, environments, heartbeatRuns, issueRecoveryActions, n import { adapterExecutionControls } from "./adapter-execution-control.js"; import { readNativeWorkspaceSyncReference } from "./native-runtime/native-workspace-sync.js"; import { SystemRecoveryFailure } from "./system-recovery-state.js"; +import type { NativeWorkspaceFinalizationOwnership } from "./native-runtime/native-workspace-finalization-ownership.js"; +import { readStopOnlyCleanup } from "./sandbox-stop-and-retain.js"; export const workspaceExportCauses = ["native_workspace_sync_out_unrecoverable", "native_workspace_sync_out_retry_exhausted"]; export const terminalWorkspaceRunStates = ["failed", "interrupted", "timed_out", "cancelled", "succeeded"]; export type WorkspaceRecoverySourceIdentity = { companyId: string; issueId: string; runId: string; actionId: string }; +/** The preservation owner may reopen only its exact stop-only allocation. + * This does not release the source's ordinary execution or destruction fence. */ +export async function ownedWorkspaceRecoveryLease(db: Db, input: WorkspaceRecoverySourceIdentity & { + leaseId: string; environmentId: string; ownership: NativeWorkspaceFinalizationOwnership; +}) { + await input.ownership.assertHeld(); + const inspected = await inspectWorkspaceRecoverySource(db, input); + const source = inspected.sources.find(item => item.lease.id === input.leaseId); + if (!source || source.environment.id !== input.environmentId || source.lease.status !== "pending_cleanup" + || source.lease.metadata?.pendingCleanupInFlight !== true + || source.lease.metadata?.pendingCleanupAttemptId !== input.ownership.token + || !readStopOnlyCleanup(source.lease)) { + throw new SystemRecoveryFailure("source_binding_invalid", "service_required"); + } + await input.ownership.assertHeld(); + return source; +} + /** Resolve only the immutable source recorded by the failed run. Never discover * a candidate by recency, mutable adapter configuration, or a provider search. */ export async function inspectWorkspaceRecoverySource(db: Db, input: WorkspaceRecoverySourceIdentity) { diff --git a/server/src/services/workspace-recovery.test.ts b/server/src/services/workspace-recovery.test.ts index 2576dbe394b..6b10de5b617 100644 --- a/server/src/services/workspace-recovery.test.ts +++ b/server/src/services/workspace-recovery.test.ts @@ -1,6 +1,7 @@ import { prepareHeartbeatWorkspace } from "./heartbeat/workspace-preparation.js"; import { createHeartbeatWorkspaceResolver, resolveExecutionWorkspaceReuseRequestForIssue } from "./heartbeat/workspaces.js"; import { environmentService } from "./environments.js"; +import { classifyEnvironmentCapabilities, environmentRuntimeService } from "./environment-runtime.js"; import { environmentRunOrchestrator } from "./environment-run-orchestrator.js"; import { executionWorkspaceService } from "./execution-workspaces.js"; import { workspaceOperationService } from "./workspace-operations.js"; @@ -111,7 +112,11 @@ describe("automatic retained workspace recovery", () => { fingerprint: runId, nextAction: "Manual repair required", evidence: { runId, workspaceRestoreFailure: "restore_failed", workspaceRestoreRecovery: recovery } }); const runtime = { resumeRunLease: vi.fn(async (_input: { lease: EnvironmentLease }) => ({ providerLeaseId, metadata: { remoteCwd: remote } })), retryPendingSandboxTeardown: vi.fn(async () => ({ providerLeaseId, state: "stopped" })) }; - const input = { db, companyId, issueId, runId, actionId, environmentRuntime: runtime as never }; + const environmentRuntime = environmentRuntimeService(db, { drivers: [{ driver: "sandbox", + acquireRunLease: vi.fn(), releaseRunLease: vi.fn(), ...runtime, + resolveCapabilities: async () => classifyEnvironmentCapabilities({ verifiedMethods: [], declared: null, narrowing: null }), + }] }); + const input = { db, companyId, issueId, runId, actionId, environmentRuntime }; return { ...input, input, runtime, host, remote, lease, providerLeaseId }; } const action = async (id: string) => (await db.select().from(issueRecoveryActions).where(eq(issueRecoveryActions.id, id)))[0]!; @@ -283,6 +288,52 @@ describe("automatic retained workspace recovery", () => { expect(await db.select().from(workspaceOperations).where(and(eq(workspaceOperations.companyId, f.companyId), eq(workspaceOperations.phase, "workspace_recovery")))).toHaveLength(1); }, 30_000); + it("recovers a protected retained source through the assembled environment runtime", async () => { + const f = await seed(); + await db.update(environmentLeases).set({ metadata: { ...f.lease.metadata, + workspaceRestoreRecovery: { schema: "paperclip.workspace-restore-recovery.v1", runId: f.runId }, + remoteExecutionTermination: remoteTerminationReceipt(f.lease, { providerLeaseId: f.providerLeaseId, state: "stopped" }), + } }).where(eq(environmentLeases.id, f.lease.id)); + const runtime = f.input.environmentRuntime; + const [lease] = await db.select().from(environmentLeases).where(eq(environmentLeases.id, f.lease.id)); + const [environment] = await db.select().from(environments).where(eq(environments.id, lease.environmentId!)); + expect(await runtime.resumeRunLease({ environment: environment as never, lease: lease as EnvironmentLease })).toBeNull(); + expect(f.runtime.resumeRunLease).not.toHaveBeenCalled(); + await recoverRetainedWorkspace({ ...f.input, environmentRuntime: runtime }); + expect(readWorkspaceRecovery((await action(f.actionId)).evidence)?.status).toBe("recovered"); + expect(await readFile(path.join(f.host, "saved.txt"), "utf8")).toBe("finished work\n"); + expect(await readFile(path.join(f.host, "newer.txt"), "utf8")).toBe("newer local work\n"); + expect(f.runtime.resumeRunLease).toHaveBeenCalledOnce(); + await recoverRetainedWorkspace({ ...f.input, environmentRuntime: runtime }); + expect(f.runtime.resumeRunLease).toHaveBeenCalledOnce(); + expect(await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.companyId, f.companyId))).toHaveLength(1); + expect(await db.select().from(agentWakeupRequests).where(eq(agentWakeupRequests.companyId, f.companyId))).toHaveLength(0); + }, 30_000); + + it.each(["changed_claim", "missing_stop_intent", "wrong_lease", "wrong_environment"])( + "does not reopen a retained source without exact recovery authority: %s", async kind => { + const f = await seed(); + const runtime = f.input.environmentRuntime; + const resume = runtime.resumeWorkspaceRecoveryLease.bind(runtime); + vi.spyOn(runtime, "resumeWorkspaceRecoveryLease").mockImplementationOnce(async input => { + if (kind === "changed_claim") await db.update(environmentLeases).set({ metadata: sql` + ${environmentLeases.metadata} || '{"pendingCleanupAttemptId":"other-owner"}'::jsonb` + }).where(eq(environmentLeases.id, f.lease.id)); + if (kind === "missing_stop_intent") await db.update(environmentLeases).set({ metadata: sql` + ${environmentLeases.metadata} - 'sandboxStopAndRetain'` + }).where(eq(environmentLeases.id, f.lease.id)); + return resume({ ...input, + ...(kind === "wrong_lease" ? { leaseId: randomUUID() } : {}), + ...(kind === "wrong_environment" ? { environmentId: randomUUID() } : {}), + }); + }); + await recoverRetainedWorkspace(f.input); + expect(readSystemRecovery((await action(f.actionId)).evidence)?.failure?.code).toBe("source_binding_invalid"); + expect(f.runtime.resumeRunLease).not.toHaveBeenCalled(); + expect(await readFile(path.join(f.remote, "saved.txt"), "utf8")).toBe("finished work\n"); + expect(await db.select().from(heartbeatRuns).where(eq(heartbeatRuns.companyId, f.companyId))).toHaveLength(1); + }, 30_000); + it("keeps verified copyback files in the preserved workspace on ordinary Retry", async () => { const f = await seed(); await recoverRetainedWorkspace(f.input); diff --git a/server/src/services/workspace-recovery.ts b/server/src/services/workspace-recovery.ts index 5b880d5b65f..ec050a5b519 100644 --- a/server/src/services/workspace-recovery.ts +++ b/server/src/services/workspace-recovery.ts @@ -169,8 +169,8 @@ export async function recoverRetainedWorkspace(input: Source & { db: Db; environ }).catch(() => undefined); }, 30_000); let stopSettled = false; try { - const opened = await input.environmentRuntime.resumeRunLease({ environment: environment as unknown as Environment, - lease: cleanupLease as EnvironmentLease }); + const opened = await input.environmentRuntime.resumeWorkspaceRecoveryLease({ source: input, + leaseId: cleanupLease.id, environmentId: environment.id, ownership }); if (opened?.providerLeaseId !== lease.providerLeaseId || opened.metadata?.remoteCwd !== remoteCwd) throw new SystemRecoveryFailure("source_binding_invalid", "service_required"); await inspectWorkspaceRecoverySource(db, input);