Files
PaperClipAI/server/src/services/native-runtime/native-controller-migration.ts
T
DottaandPaperclip 72f7b42fe3 Preserve settled failed controller state during online migration (#19678)
## Thinking Path

> - Paperclip controls agent work across web-server releases.
> - Volume-free servers need retained controller state in shared
storage.
> - Successful settled sources already support online migration.
> - Some retained failed sources have no accepted result and must stay
available for recovery inspection.
> - This change copies those sources under task, coordinator and
publication fences while unrelated work continues.
> - The original files, failed status and recovery warnings remain
unchanged.

## Linked Issues or Issue Description

Refs #19038. Refs #19631.

**What are you trying to improve?**
Preserve retained failed controller files without waiting for global
idle.

**What problem does this solve?**
The online producer skips terminal failed controllers. Their files can
still be needed for recovery inspection even when no accepted provider
artifact proves executable continuation.

**What would the improvement look like?**
A settled exact source can enter the existing encrypted archive store.
An accepted committed failed source can use the existing checkpoint
import. Busy, changed, unowned or foreign sources remain blocked.

## What Changed

- Add a source owner bound to the selected task session, run,
coordinator generation, admitted input and file digests.
- Check the task, physical finalizer lock, released coordinator,
canonical resume source and active related turns before upload and
before publication.
- Preserve failed sources through the existing encrypted archive format.
Do not treat archived bytes as execution authority or old-writer stop
proof.
- Allow the existing accepted committed checkpoint import for a finished
failed run without changing its status.
- Validate admitted input bindings before looking up local controller
files.
- Document the online preservation path and the final static writer
fence.

## Verification

- Real PostgreSQL: 125 cases passed across migration, controller
recovery and durable backup storage. One added assertion inspected an
unadmitted queued fixture; it was corrected while retaining the
queued-turn preservation and stale-publication assertions. The final
migration rerun passes 51/51; the other three affected suites pass
75/75.
- Genuine prepatch RED: online failed-source preservation and accepted
committed failed-source import both fail on the previous producer and
recovery owners.
- New cases cover independent restore after deleting the original
source, an expired but non-null coordinator owner, source mutation after
upload, a new related queued turn during upload, foreign input binding
and an accepted committed failed result.
- The full rebased server source and test-tree typecheck passes after
restoring its missing ignored workspace SDK link and building that
existing dependency.
- Module boundaries and whitespace checks pass.
- Rebased onto current master; both provider-artifact imports and the
new archive owner are preserved. Rebased type and module-boundary checks
pass. All six archive cases pass on the exact rebased head (39.68
seconds). All CI gates pass on exact head
81fc974cd9. Fresh Greptile review is 5/5
with no unresolved comments. No serving migration, deletion or
deployment is performed by this PR.

- Review memory fix: 64 KiB streamed hashes avoid retaining another
controller string at each publication fence. A 256 MiB source is hashed
three times while the original string remains live under a 512 MiB heap.
The old full-string comparison reproduces an OOM; the fixed two-case
suite passes. Full source/test-tree typecheck and module boundaries pass
on the new code. All six real-PostgreSQL archive cases pass again with
streaming enabled (17.31 seconds); ownership, queued-turn and
post-upload mutation guards remain covered.

## Risks

- This is a copy-only preservation operation. It does not prove the
original process has stopped. Final enrollment must arm static ephemeral
mode on the original volume, observe the old deployment stopped and
repeat data eligibility.
- A source change during upload leaves an unpublished pending object.
The normal retention owner handles obsolete attempts; the source remains
required until a verified current archive exists.
- An archive is forensic evidence. It does not make an unaccepted failed
provider result resumable.

## Model Used

OpenAI Codex, GPT-6 family, with reasoning and code execution. The host
does not expose the exact serving model ID or context-window size.

## Checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
- [x] I have not referenced internal/instance-local Paperclip issues or
links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip`
URLs)
- [x] My branch name describes the change (e.g. `docs/...`, `fix/...`)
and contains no internal Paperclip ticket id or instance-derived details
- [x] I have run tests locally and they pass
- [x] I have added or updated tests where applicable
- [x] I have updated relevant documentation to reflect my changes
- [x] I have considered and documented any risks above
- [x] All Paperclip CI gates are green
- [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups
- [x] I will address all Greptile and reviewer comments before
requesting merge

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-11-06 18:38:50 -06:00

372 lines
25 KiB
TypeScript

import { constants } from "node:fs";
import { lstat, open, readdir } from "node:fs/promises";
import { join } from "node:path";
import { and, eq, inArray, or, sql } from "drizzle-orm";
import { heartbeatRuns, issues, nativeRunFinalizations, type Db } from "@paperclipai/db";
import { captureLegacyDurablePrpCheckpoint, parseNativeExecutionInput } from "../../vendor/paperclip-runner/index.js";
import { offlineMigrationExecutionWhere } from "../offline-migration-execution.js";
import { findNativeSessionResumeRun } from "./native-session-resume.js";
import { nativeControllerMigrationDescriptor } from "./native-session-executor.js";
import { hasNativeRunnerCheckpoint, loadNativeRunnerCheckpoint } from "./native-runner-checkpoint.js";
import { importNativeControllerRecovery, readNativeControllerRecovery } from "./native-controller-recovery.js";
import { nativeHarnessStateBase } from "./native-harness-backup-stamp.js";
import { providerPackWorkspaceId, resolveRemoteProviderPackAuthority } from "./remote-provider-pack-authority.js";
import { nativeSha256 } from "./canonical.js";
import { readNativeWorkspaceSyncReference } from "./native-workspace-sync.js";
import type { StorageService } from "../../storage/types.js";
import { durableNativeHarnessStorage } from "./native-harness-backup-storage.js";
import { archiveFailedLegacyNativeController, hasArchivedLegacyNativeController } from "./native-controller-archive.js";
import { redactRunnerApiPayloads } from "./runner-api-log-redaction.js";
import { archiveSettledFailedNativeController } from "./native-controller-archive-source.js";
import { nativeControllerSourceDigest } from "./native-controller-source-digest.js";
type Selected = { id: string; companyId: string; agentId: string; issueId: string; sessionId: string; createdAt: Date; lastRunId: string };
function record(value: unknown): Record<string, unknown> {
return value && typeof value === "object" && !Array.isArray(value) ? value as Record<string, unknown> : {};
}
async function confirmedOlderSuccessfulSnapshot(db: Db, selected: Selected,
source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>,
paths: Awaited<ReturnType<typeof localPaths>>, olderRunId: unknown) {
const snapshot = record(source.runnerProfileJson.sessionCheckpoint), identity = record(snapshot.identity);
const scope = { companyId: selected.companyId, agentId: selected.agentId, issueId: selected.issueId, sessionId: selected.sessionId };
if (source.status !== "failed" || identity.runId !== source.id
|| Object.entries(scope).some(([key, value]) => identity[key] !== value)
|| paths.execution.binding.runId !== source.id || paths.execution.binding.companyId !== selected.companyId
|| paths.execution.binding.agentId !== selected.agentId || paths.execution.binding.issueId !== selected.issueId
|| paths.execution.session.normalizedSessionId !== selected.sessionId
|| typeof snapshot.sessionId !== "string" || !snapshot.sessionId.trim()
|| typeof olderRunId !== "string" || olderRunId === source.id
|| !/^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$/i.test(olderRunId)) return null;
const [prior] = await db.select({ createdAt: heartbeatRuns.createdAt, finishedAt: heartbeatRuns.finishedAt,
runnerInstanceId: heartbeatRuns.runnerInstanceId, snapshot: sql<unknown>`${heartbeatRuns.runnerProfileJson}->'sessionCheckpoint'` })
.from(heartbeatRuns).where(and(eq(heartbeatRuns.id, olderRunId), eq(heartbeatRuns.companyId, selected.companyId),
eq(heartbeatRuns.agentId, selected.agentId), eq(heartbeatRuns.nativeIssueId, selected.issueId),
eq(heartbeatRuns.nativeSessionId, selected.sessionId), eq(heartbeatRuns.runtimeMode, "native"), eq(heartbeatRuns.status, "succeeded")));
const priorSnapshot = record(prior?.snapshot), priorIdentity = record(priorSnapshot.identity);
if (!prior?.finishedAt || prior.createdAt >= source.createdAt
|| !source.runnerInstanceId || prior.runnerInstanceId !== source.runnerInstanceId
|| priorIdentity.runId !== olderRunId || Object.entries(scope).some(([key, value]) => priorIdentity[key] !== value)
|| priorSnapshot.sessionId !== snapshot.sessionId || priorSnapshot.backendKind !== snapshot.backendKind) return null;
const [failed] = await db.select({ finishedAt: heartbeatRuns.finishedAt, startedAt: heartbeatRuns.startedAt }).from(heartbeatRuns).where(and(
eq(heartbeatRuns.id, source.id), eq(heartbeatRuns.companyId, selected.companyId), eq(heartbeatRuns.agentId, selected.agentId),
eq(heartbeatRuns.nativeIssueId, selected.issueId), eq(heartbeatRuns.nativeSessionId, selected.sessionId),
eq(heartbeatRuns.runtimeMode, "native"), eq(heartbeatRuns.status, "failed")));
return failed?.finishedAt && prior.finishedAt <= (failed.startedAt ?? source.createdAt) ? priorSnapshot : null;
}
async function hasConfirmedOlderSupervisor(db: Db, selected: Selected,
source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>,
paths: Awaited<ReturnType<typeof localPaths>>, supervisor: unknown) {
const olderSnapshot = record(record(supervisor).snapshot);
const prior = await confirmedOlderSuccessfulSnapshot(db, selected, source, paths, record(olderSnapshot.identity).runId);
return prior !== null && nativeSha256(prior) === nativeSha256(redactRunnerApiPayloads(olderSnapshot));
}
async function hasConfirmedOlderController(db: Db, selected: Selected,
source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>,
paths: Awaited<ReturnType<typeof localPaths>>, controller: string, artifact?: { version: string; digest: string }) {
const identity = record(record(JSON.parse(controller)).identity);
if (!await confirmedOlderSuccessfulSnapshot(db, selected, source, paths, identity.runId)) return false;
try {
captureLegacyDurablePrpCheckpoint(controller, { runId: String(identity.runId),
runnerInstanceId: source.runnerInstanceId!, normalizedSessionId: selected.sessionId }, artifact);
return true;
} catch { return false; }
}
async function* retainedSources(db: Db, signal?: AbortSignal) {
let after: string | undefined;
for (;;) {
signal?.throwIfAborted();
const rows = await db.execute<Selected>(sql`select s.id, s.company_id as "companyId", s.agent_id as "agentId",
r.native_issue_id as "issueId", r.native_session_id as "sessionId", r.created_at as "createdAt", r.id as "lastRunId"
from agent_task_sessions s join heartbeat_runs r on r.id = s.last_run_id
and r.company_id = s.company_id and r.agent_id = s.agent_id
where s.adapter_type = 'paperclip_runner' and r.native_issue_id is not null and r.native_session_id is not null
${after ? sql`and s.id > ${after}::uuid` : sql``} order by s.id limit 100`);
for (const selected of rows) {
signal?.throwIfAborted();
const source = await findNativeSessionResumeRun(db, { companyId: selected.companyId, agentId: selected.agentId,
issueId: selected.issueId, normalizedSessionId: selected.sessionId,
beforeCreatedAt: new Date(selected.createdAt), includeProgressBarrier: true });
if (source) yield { selected, source };
}
if (rows.length < 100) return;
after = rows.at(-1)!.id;
}
}
async function readPrivateSource(file: string, maxBytes: number): Promise<string | undefined> {
const handle = await open(file, constants.O_RDONLY | constants.O_NOFOLLOW).catch((error: NodeJS.ErrnoException) => {
if (error.code === "ENOENT") return undefined; throw error;
});
if (!handle) return undefined;
try {
const stat = await handle.stat();
if (!stat.isFile() || stat.nlink !== 1 || stat.size > maxBytes) throw new Error("native_controller_migration_unsafe_source");
return await handle.readFile("utf8");
} finally { await handle.close(); }
}
async function localPaths(source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>) {
const execution = parseNativeExecutionInput(source.runnerProfileJson.nativeExecutionInput);
if (execution.binding.companyId !== source.companyId || execution.binding.agentId !== source.agentId
|| execution.binding.issueId !== source.nativeIssueId || execution.binding.runId !== source.id
|| execution.session.normalizedSessionId !== source.nativeSessionId) throw new Error("native_controller_migration_artifact_binding");
const descriptor = nativeControllerMigrationDescriptor(execution, source.runnerProfileJson.nativeToolContractFingerprint);
const root = await lstat(descriptor.root).catch((error: NodeJS.ErrnoException) => {
if (error.code === "ENOENT") return undefined; throw error;
});
if (root && (!root.isDirectory() || root.isSymbolicLink())) throw new Error("native_controller_migration_unsafe_source");
const control = join(descriptor.root, "control-plane");
const directory = await lstat(control).catch((error: NodeJS.ErrnoException) => {
if (error.code === "ENOENT") return undefined; throw error;
});
if (directory && (!directory.isDirectory() || directory.isSymbolicLink())) throw new Error("native_controller_migration_unsafe_source");
return { ...descriptor, execution, controlFile: join(control, "control-plane-state.json") };
}
export async function readLegacyNativeControllerArchiveSource(source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>) {
const paths = await localPaths(source);
const controller = await readPrivateSource(paths.controlFile, 256 * 1024 * 1024);
const supervisor = paths.execution.session.lifecyclePolicy.mode === "warm"
? await readPrivateSource(paths.supervisorPath, 4 * 1024 * 1024) : undefined;
return { paths, controller, supervisor };
}
export async function readLegacyNativeControllerArchiveDigests(source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>) {
const paths = await localPaths(source);
return { controllerDigest: await nativeControllerSourceDigest(paths.controlFile, 256 * 1024 * 1024),
supervisorDigest: paths.execution.session.lifecyclePolicy.mode === "warm"
? await nativeControllerSourceDigest(paths.supervisorPath, 4 * 1024 * 1024) : undefined };
}
function preservedFailedCheckpoint(source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>,
sessionId: string, checkpoint: Awaited<ReturnType<typeof loadNativeRunnerCheckpoint>>) {
return source.status === "failed" && source.runnerProfileJson.sessionCheckpoint == null
&& checkpoint?.runId === source.id && checkpoint.recoveryEvidence.runnerInstanceId === source.runnerInstanceId
&& checkpoint.recoveryEvidence.normalizedSessionId === sessionId;
}
export async function hasLocalNativeControllerObligations(db: Db, storage?: StorageService | null): Promise<boolean> {
const roots = await readdir(nativeHarnessStateBase()).catch((error: NodeJS.ErrnoException) => {
if (error.code === "ENOENT") return [] as string[]; throw error;
});
if (!roots.length) return false;
for await (const { selected, source } of retainedSources(db)) {
const binding = { companyId: selected.companyId, issueId: selected.issueId, runId: source.id };
if (readNativeControllerRecovery(source.runnerProfileJson.nativeControllerRecovery, source.runnerProfileJson.sessionCheckpoint)
&& await hasNativeRunnerCheckpoint(db, binding)) continue;
if (source.status === "failed" && source.runnerProfileJson.sessionCheckpoint == null
&& preservedFailedCheckpoint(source, selected.sessionId, await loadNativeRunnerCheckpoint(db, binding))) continue;
const paths = await localPaths(source);
const present = await lstat(paths.controlFile).catch((error: NodeJS.ErrnoException) => {
if (error.code === "ENOENT") return undefined; throw error;
});
if (present && source.status === "failed") {
const archiveStorage = storage === undefined ? durableNativeHarnessStorage() : storage;
const controller = await readPrivateSource(paths.controlFile, 256 * 1024 * 1024);
const supervisor = paths.execution.session.lifecyclePolicy.mode === "warm"
? await readPrivateSource(paths.supervisorPath, 4 * 1024 * 1024) : undefined;
if (controller !== undefined && archiveStorage && await hasArchivedLegacyNativeController(db, { ...binding, storage: archiveStorage, controller, supervisor })) continue;
}
if (present || await hasNativeRunnerCheckpoint(db, binding)) return true;
}
return false;
}
function hasMatchingControllerRecovery(selected: Selected,
source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>,
checkpoint: Awaited<ReturnType<typeof loadNativeRunnerCheckpoint>>) {
const metadata = readNativeControllerRecovery(source.runnerProfileJson.nativeControllerRecovery, source.runnerProfileJson.sessionCheckpoint);
const snapshot = source.runnerProfileJson.sessionCheckpoint as { identity?: Record<string, unknown> } | null;
return Boolean(checkpoint && metadata?.checkpoint?.runId === source.id
&& metadata.checkpoint.runnerInstanceId === source.runnerInstanceId
&& metadata.checkpoint.normalizedSessionId === selected.sessionId
&& snapshot?.identity?.runId === source.id && snapshot.identity.companyId === selected.companyId
&& snapshot.identity.agentId === selected.agentId && snapshot.identity.issueId === selected.issueId
&& snapshot.identity.sessionId === selected.sessionId
&& checkpoint.recoveryEvidence.runnerInstanceId === source.runnerInstanceId
&& checkpoint.recoveryEvidence.normalizedSessionId === selected.sessionId);
}
async function readMigrationMaterial(db: Db, selected: Selected,
source: NonNullable<Awaited<ReturnType<typeof findNativeSessionResumeRun>>>,
checkpoint: Awaited<ReturnType<typeof loadNativeRunnerCheckpoint>>) {
const paths = await localPaths(source);
const legacyControllerState = checkpoint ? undefined : await readPrivateSource(paths.controlFile, 256 * 1024 * 1024);
let legacyRunnerArtifact: { version: string; digest: string } | undefined;
if (!checkpoint && legacyControllerState === undefined) return { paths, legacyControllerState, legacyRunnerArtifact, supervisor: undefined };
if (legacyControllerState !== undefined && await readPrivateSource(join(paths.root, "provider-pack-authority.json"), 512 * 1024)) {
const identity = JSON.parse(legacyControllerState).identity;
const execution = paths.execution;
const [admission] = await db.select({ workspace: sql<unknown>`${heartbeatRuns.runnerProfileJson}->'nativeWorkspaceSync'` })
.from(heartbeatRuns).where(and(eq(heartbeatRuns.id, source.id), eq(heartbeatRuns.companyId, selected.companyId),
eq(heartbeatRuns.agentId, selected.agentId)));
const workspace = readNativeWorkspaceSyncReference(admission?.workspace);
const remoteCwd = workspace?.remoteCwd ?? execution.workspace.cwd;
if (typeof identity?.environmentLeaseId !== "string" || !remoteCwd
|| (workspace && workspace.workspaceId !== execution.binding.executionWorkspaceId)) {
throw new Error("native_controller_migration_artifact_binding");
}
const unavailable = (): never => { throw new Error("native_controller_migration_artifact_unavailable"); };
legacyRunnerArtifact = resolveRemoteProviderPackAuthority({ stateDirectory: paths.root, reattach: true,
binding: { companyId: selected.companyId, agentId: selected.agentId,
workspaceId: providerPackWorkspaceId(execution.binding.executionWorkspaceId, source.id, identity.environmentLeaseId),
sessionId: selected.sessionId, runnerInstanceId: source.runnerInstanceId!,
environmentLeaseId: identity.environmentLeaseId, remoteCwd,
providerDigest: nativeSha256(execution.provider) },
current: unavailable, runnerArtifact: unavailable }).runnerArtifact;
}
const supervisor = !checkpoint && paths.execution.session.lifecyclePolicy.mode === "warm"
? await readPrivateSource(paths.supervisorPath, 4 * 1024 * 1024) : undefined;
return { paths, legacyControllerState, legacyRunnerArtifact, supervisor };
}
export async function migrateNativeControllers(db: Db, input: { writersStopped: true; signal: AbortSignal; storage?: StorageService }) {
const [active] = await db.select({ id: heartbeatRuns.id }).from(heartbeatRuns).where(offlineMigrationExecutionWhere()).limit(1);
if (!input.writersStopped || active) throw new Error("native_controller_migration_requires_offline_writers");
const counts = { inspected: 0, imported: 0, unchanged: 0, sourceAlreadyAbsent: 0, archivedFailed: 0, preservedFailed: 0 };
for await (const { selected, source } of retainedSources(db, input.signal)) {
counts.inspected++;
const binding = { companyId: selected.companyId, issueId: selected.issueId, runId: source.id };
const checkpoint = await loadNativeRunnerCheckpoint(db, binding);
if (preservedFailedCheckpoint(source, selected.sessionId, checkpoint)) { counts.preservedFailed++; continue; }
if (hasMatchingControllerRecovery(selected, source, checkpoint)) { counts.unchanged++; continue; }
const { paths, legacyControllerState, legacyRunnerArtifact, supervisor } = await readMigrationMaterial(db, selected, source, checkpoint);
if (!checkpoint && legacyControllerState === undefined) { counts.sourceAlreadyAbsent++; continue; }
input.signal.throwIfAborted();
let result: Awaited<ReturnType<typeof importNativeControllerRecovery>>;
try {
result = await importNativeControllerRecovery(db, { ...binding, agentId: selected.agentId,
normalizedSessionId: selected.sessionId, expectedConfigDigest: paths.configDigest,
supervisor: supervisor === undefined ? undefined : JSON.parse(supervisor),
offline: { writersStopped: true, legacyControllerState, legacyRunnerArtifact } });
} catch (error) {
const storage = input.storage ?? durableNativeHarnessStorage();
if (!(error instanceof Error) || source.status !== "failed" || legacyControllerState === undefined || !storage) throw error;
const archivable = error.message === "native_runner_checkpoint_artifact_unproven"
|| error.message === "native_runner_checkpoint_binding_mismatch"
&& await hasConfirmedOlderController(db, selected, source, paths, legacyControllerState, legacyRunnerArtifact);
if (!archivable) throw error;
await archiveFailedLegacyNativeController(db, { ...binding, storage, controller: legacyControllerState, supervisor,
writersStopped: true, signal: input.signal });
counts.archivedFailed++;
continue;
}
if (result.kind !== "imported" && result.kind !== "unchanged") {
if (result.kind === "missing_evidence" && result.reason === "stale_supervisor_snapshot"
&& legacyControllerState !== undefined && supervisor !== undefined
&& await hasConfirmedOlderSupervisor(db, selected, source, paths, JSON.parse(supervisor))) {
const storage = input.storage ?? durableNativeHarnessStorage();
if (storage) {
await archiveFailedLegacyNativeController(db, { ...binding, storage, controller: legacyControllerState, supervisor,
writersStopped: true, signal: input.signal });
counts.archivedFailed++;
continue;
}
}
throw new Error(`native_controller_migration_blocked:${source.id}:${"reason" in result ? result.reason : result.kind}`);
}
counts[result.kind]++;
}
return counts;
}
function onlineControllerSourceDeferral(error: unknown): string | null {
if (!(error instanceof Error)) return null;
const reasons: Record<string, string> = {
native_runner_checkpoint_artifact_unproven: "artifact_unproven",
native_runner_checkpoint_binding_mismatch: "checkpoint_binding",
native_controller_migration_source_changed: "source_changed",
native_controller_migration_unsafe_source: "unsafe_source",
native_controller_migration_artifact_binding: "artifact_binding",
native_controller_migration_artifact_unavailable: "artifact_unavailable",
native_controller_archive_source_unsettled: "archive_source_unsettled",
};
if (reasons[error.message]) return reasons[error.message];
if (error.message.startsWith("runner_remote_provider_artifact_incompatible:")) return "artifact_incompatible";
if (error instanceof SyntaxError) return "invalid_source_json";
if (["ENOENT", "ENOTDIR", "EISDIR", "ELOOP", "EACCES", "EPERM"].includes((error as NodeJS.ErrnoException).code ?? "")) return "source_unavailable";
return null;
}
export async function prestageNativeControllers(db: Db, input: { signal: AbortSignal; storage?: StorageService }) {
const counts = { inspected: 0, imported: 0, unchanged: 0, archivedFailed: 0, sourceAlreadyAbsent: 0, deferred: {} as Record<string, number> };
const defer = (reason: string) => { counts.deferred[reason] = (counts.deferred[reason] ?? 0) + 1; };
for await (const { selected, source } of retainedSources(db, input.signal)) {
counts.inspected++;
input.signal.throwIfAborted();
let outcome = await db.transaction(async tx => {
await tx.execute(sql`set local lock_timeout = '1s'`);
const [task] = await tx.select().from(issues).where(and(eq(issues.companyId, selected.companyId),
eq(issues.id, selected.issueId))).for("update");
if (!task || task.executionRunId || task.checkoutRunId) return "source_active";
const [owner] = await tx.select().from(nativeRunFinalizations).where(and(
eq(nativeRunFinalizations.companyId, selected.companyId), eq(nativeRunFinalizations.issueId, selected.issueId),
eq(nativeRunFinalizations.runId, source.id))).for("update");
if (!owner || owner.leaseOwner || owner.phase !== "committed" || !owner.resultId || owner.recoveryState) return "owner_not_released";
const [current] = await tx.select().from(heartbeatRuns).where(and(eq(heartbeatRuns.id, source.id),
eq(heartbeatRuns.companyId, selected.companyId), eq(heartbeatRuns.agentId, selected.agentId),
eq(heartbeatRuns.nativeIssueId, selected.issueId), eq(heartbeatRuns.nativeSessionId, selected.sessionId))).for("update");
if (!current || !["succeeded", "failed"].includes(current.status) || !current.finishedAt) return "source_not_successful";
const [active] = await tx.select({ id: heartbeatRuns.id }).from(heartbeatRuns).where(and(
eq(heartbeatRuns.companyId, selected.companyId), inArray(heartbeatRuns.status, ["queued", "running"]),
or(eq(heartbeatRuns.nativeIssueId, selected.issueId), eq(heartbeatRuns.issueId, selected.issueId),
eq(heartbeatRuns.nativeSessionId, selected.sessionId)))).limit(1);
if (active) return "source_active";
const scoped = tx as unknown as Db;
const binding = { companyId: selected.companyId, issueId: selected.issueId, runId: source.id };
const checkpoint = await loadNativeRunnerCheckpoint(scoped, binding);
const profile = record(current.runnerProfileJson);
const freshSource = { ...source, status: current.status, runnerInstanceId: current.runnerInstanceId,
runnerProfileJson: { nativeToolContractFingerprint: profile.nativeToolContractFingerprint,
nativeExecutionInput: profile.nativeExecutionInput, sessionCheckpoint: profile.sessionCheckpoint,
nativeControllerRecovery: profile.nativeControllerRecovery } };
if (hasMatchingControllerRecovery(selected, freshSource, checkpoint)) return "unchanged";
const material = await readMigrationMaterial(scoped, selected, freshSource, checkpoint);
if (!checkpoint && material.legacyControllerState === undefined) return "source_already_absent";
input.signal.throwIfAborted();
const result = await importNativeControllerRecovery(scoped, { ...binding, agentId: selected.agentId,
normalizedSessionId: selected.sessionId, expectedConfigDigest: material.paths.configDigest,
supervisor: material.supervisor === undefined ? undefined : JSON.parse(material.supervisor),
legacyCheckpoint: { legacyControllerState: material.legacyControllerState,
legacyRunnerArtifact: material.legacyRunnerArtifact } });
if (result.kind !== "imported" && result.kind !== "unchanged") return "source_unproven";
if (material.legacyControllerState !== undefined
&& await readPrivateSource(material.paths.controlFile, 256 * 1024 * 1024) !== material.legacyControllerState) {
throw new Error("native_controller_migration_source_changed");
}
if (material.supervisor !== undefined
&& await readPrivateSource(material.paths.supervisorPath, 4 * 1024 * 1024) !== material.supervisor) {
throw new Error("native_controller_migration_source_changed");
}
input.signal.throwIfAborted();
return result.kind;
}).catch(error => {
input.signal.throwIfAborted();
const reason = onlineControllerSourceDeferral(error);
if (reason) return reason;
if (error?.code === "55P03" || error?.cause?.code === "55P03") return "source_busy";
throw error;
});
if (source.status === "failed" && ["owner_not_released", "artifact_unproven", "checkpoint_binding", "source_unproven", "artifact_binding"].includes(outcome)) {
const storage = input.storage ?? durableNativeHarnessStorage();
if (storage) outcome = await archiveSettledFailedNativeController(db, { selected, source, storage, signal: input.signal }).catch(error => {
input.signal.throwIfAborted();
const reason = onlineControllerSourceDeferral(error);
if (reason) return reason;
if (error?.code === "55P03" || error?.cause?.code === "55P03") return "source_busy";
throw error;
});
}
if (outcome === "archived_failed") counts.archivedFailed++;
else if (outcome === "imported" || outcome === "unchanged") counts[outcome]++;
else if (outcome === "source_already_absent") counts.sourceAlreadyAbsent++;
else defer(outcome);
}
return counts;
}