mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-27 02:44:50 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - Agent environments can leave pending teardown or unverified provider resources. > - Recovery must preserve those resources until ownership and workspace safety allow cleanup. > - Empty maintenance scans keep an idle instance and its database active. > - The existing rows, transaction signals, and scheduler can represent the actual recovery obligation. > - This pull request schedules pending cleanup and historical verification only while work remains. > - An empty or fully verified instance stops these scans without losing cleanup recovery. ## Linked Issues or Issue Description **What happened?** The server scanned pending environment cleanup on its maintenance tick. The run reaper also scanned it even when it recovered no runs or active leases. Historical resource verification scanned every five minutes, including when all history already had valid cleanup proof. **What did you expect?** Writes should wake cleanup. Pending rows, deferred orphan buffers, and unverified history should retain recovery deadlines. When none remain, these workers should make no periodic database or provider calls. **Steps to reproduce** Start a configured instance with no pending leases and fully verified history. Leave it idle. Observe repeated pending-cleanup and historical-verification reads from the maintenance paths. Related: #17106 supplies the preceding login-cleanup migration. #13523 improves lease-reaper query indexes. #16809 addresses reusable-sandbox recovery authority. This PR keeps those authority checks in their existing services. ## What Changed - Register two workers with the existing delivery coordinator and shared scheduler. Remove their unconditional maintenance-tick calls. Run the reaper's inline pending cleanup only after it recovers actual work. - Add commit-aware signals to the audited lease and custom-image writers. Existing transactions notify directly; other writers use one small transaction helper. No tables or migrations are added. - Derive pending cleanup deadlines from the existing row backoff and retry or claim metadata. Retain a historical retry only while an unverified candidate exists. - Register unwritten orphan buffers across runtimes that share the database handle. Buffer registration wakes recovery without a database connection. Load the existing spool at startup and retry failed or capacity-limited loads while needed. - Isolate spool failures per runtime. Attempt all buffers and persisted pending rows, then retain a retry for any failed spool. - Document producer coverage, idle behavior, and remaining blockers. Update the sleep inventory. - Repair the inherited CSS-recovery E2E test: the current build no longer emits task-page CSS. Exercise the actual lazy environment stylesheet, preserving real network failure, recovery, and bounded reload assertions. ## Verification October 24 integration update: merged current master and resolved the runtime/spool conflicts. Preserve serialized ingestion of records appended after startup. Plugin replacement failures now register deferred recovery with an idle hold; concurrent callers share one persistence attempt. The producer audit includes this new writer. - Focused cleanup selection: 270 tests now pass across five suites. The initial run lacked a built plugin SDK and executed no tests; building the SDK fixed setup. The new concurrent-flush assertion then reproduced duplicate rows; a single-flight guard fixed it and all 18 plugin integration tests passed on rerun. - Server typecheck passed. After review fixes, all 211 tests across the cleanup worker, real orphan spool, environment runtime, and plugin integration suites passed. These overlap the earlier focused selection. The rate-limit test initially expected a write after twenty idle minutes to wait; corrected it to assert that subsequent writes cannot accelerate the five-minute cadence. - Review fixes preserve retries for unreadable spool directories/records, keep historical provider checks off the startup wait while joining them at shutdown, and restore their independent five-minute minimum spacing. The complete [CI matrix](https://github.com/paperclipai/paperclip/actions/runs/40108905033) passed on final commit `79ae1589c3c7b924db4bedb337d0c7ed3d95020b`, including all E2E shards, server/workspace tests, runner checks, typecheck, build/public-install verification, and security checks. - CI found a stale E2E asset matcher: `issue-detail-*.css` is no longer emitted. Both corrected browser tests passed against a fresh production UI build and disposable local instance. Fresh Greptile review is 5/5 on that same final commit, with all review threads resolved. Previous implementation verification: - `pnpm -r typecheck` and `pnpm build` passed. - New PostgreSQL worker suite: 12 tests passed. Covers quiet configured state, verified history, writes, outer commit and rollback, retry deadlines, restart, drain, deferred orphan buffers, spool failure, pagination, provider uncertainty, shutdown, and the idle run-reaper path. - Worker and environment runtime suites after review fix: 183 tests passed. A new assertion reproduced buffer starvation before the fix. Updated transaction fault injection and isolated simulated-instance database handles. Server typecheck also passed after the fix. - Run-recovery suites: 58 tests passed. Pending-cleanup suite: 38 tests passed after updating the logging fixture to seed real orphan recovery; an idle reaper no longer invokes cleanup. - Stop and workspace-recovery integration selection: 268 tests passed; two live-provider tests skipped by their environment gate. This overlaps the worker suite and is not an additional unique-test count. - Started the full local `pnpm test:run`, then stopped that older duplicate run after CI found the fixture mismatch. The corrected 38-test suite passed locally. The full sharded [CI matrix](https://github.com/paperclipai/paperclip/actions/runs/39678174479) passed on final commit `fc0ff3c4554ca4190a8b0b81ec06ef7065b8ad2c`, including build, typecheck, runner, server, workspace, and E2E checks. This is not a claim that the local full run completed. ## Risks - Missing a future producer signal could delay discovery until restart. The producer audit is documented in `doc/idle-environment-cleanup.md`. Independent SQL writers and another server process are outside the existing process-local notification contract. - Historical candidates blocked by ownership or provider uncertainty keep a five-minute retry until they can be verified. Provider destruction, claim fencing, Stop retention, and workspace safety remain controlled by their existing services. - This does not remove orphan-active discovery or legacy shutdown settlement from run recovery. Active custom-image expiry is also still periodic. External wake coverage does not change. - Local tests prove these workers become quiet and recover. They do not establish deployed instance suspension or fleet cost savings. ## Model Used OpenAI Codex (GPT-6), with code execution and reasoning. The exact serving model ID and context size were not exposed. ## 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>
1816 lines
74 KiB
TypeScript
1816 lines
74 KiB
TypeScript
import { writeEnvironmentCleanup, notifyEnvironmentCleanup } from "./environment-cleanup-notifications.js";
|
|
import { withoutCleanupVerification } from "./cleanup-verification-proof.js";
|
|
import { randomUUID } from "node:crypto";
|
|
|
|
import { SANDBOX_PLATFORM_PROBE_METADATA_KEY } from "./environment-custom-image-runtime.js";
|
|
import { and, desc, eq, inArray, isNull, ne, sql, type SQL } from "drizzle-orm";
|
|
import type { Db } from "@paperclipai/db";
|
|
import {
|
|
agents,
|
|
builtInManagedResources,
|
|
companies,
|
|
companySecretBindings,
|
|
environmentCustomImageSetupSessions,
|
|
environmentLeases,
|
|
environments,
|
|
executionWorkspaces,
|
|
instanceSettings,
|
|
issues,
|
|
projects,
|
|
} from "@paperclipai/db";
|
|
import {
|
|
ENVIRONMENT_DRIVERS,
|
|
ENVIRONMENT_LEASE_CLEANUP_STATUSES,
|
|
ENVIRONMENT_LEASE_POLICIES,
|
|
ENVIRONMENT_LEASE_STATUSES,
|
|
ENVIRONMENT_STATUSES,
|
|
type CreateEnvironment,
|
|
type Environment,
|
|
type EnvironmentDeleteBlastRadius,
|
|
type EnvironmentDeleteBlockedReason,
|
|
type EnvironmentLease,
|
|
type EnvironmentLeaseCleanupStatus,
|
|
type EnvironmentLeasePolicy,
|
|
type EnvironmentLeaseStatus,
|
|
type UpdateEnvironment,
|
|
} from "@paperclipai/shared";
|
|
import { conflict, forbidden } from "../errors.js";
|
|
import { logActivity } from "./activity-log.js";
|
|
import { isCloudManagedInstance } from "./cloud-instance.js";
|
|
import {
|
|
resourceStatus,
|
|
stockHash,
|
|
type ManagedResourceStockStatus,
|
|
} from "./managed-resource-drift.js";
|
|
|
|
type EnvironmentRow = typeof environments.$inferSelect;
|
|
type EnvironmentLeaseRow = typeof environmentLeases.$inferSelect;
|
|
const DEFAULT_LOCAL_ENVIRONMENT_NAME = "Local";
|
|
const DEFAULT_LOCAL_ENVIRONMENT_DESCRIPTION =
|
|
"Default execution environment for Paperclip runs on this machine.";
|
|
|
|
const DEFAULT_KUBERNETES_ENVIRONMENT_NAME = "Kubernetes Sandbox";
|
|
const DEFAULT_KUBERNETES_ENVIRONMENT_DESCRIPTION =
|
|
"Managed Kubernetes sandbox environment for hosted tenant execution.";
|
|
/** Provider key (== plugin driverKey) of the first-party Kubernetes sandbox provider. */
|
|
const KUBERNETES_PROVIDER_KEY = "kubernetes";
|
|
/** Metadata marker for the company's managed-by-config Kubernetes sandbox environment. */
|
|
const KUBERNETES_MANAGED_MARKER = "managedKubernetesSandbox";
|
|
const ACTIVE_CUSTOM_IMAGE_SETUP_STATUSES = ["starting", "waiting_for_user", "capturing"] as const;
|
|
|
|
/**
|
|
* Configuration accepted by `ensureKubernetesEnvironment`. Mirrors the keys of
|
|
* the kubernetes sandbox-provider `configSchema` that an operator typically
|
|
* pins for a hosted cloud instance. Stored verbatim in `environment.config`
|
|
* (the plugin validates/defaults it via `kubernetesProviderConfigSchema` at
|
|
* lease time); `provider` is always forced to "kubernetes".
|
|
*/
|
|
export interface KubernetesEnvironmentConfigInput {
|
|
backend?: "sandbox-cr" | "job";
|
|
inCluster?: boolean;
|
|
runtimeClassName?: string;
|
|
egressMode?: "cilium" | "standard";
|
|
egressAllowFqdns?: string[];
|
|
egressAllowCidrs?: string[];
|
|
namespacePrefix?: string;
|
|
imageRegistry?: string;
|
|
adapterType?: string;
|
|
/**
|
|
* Sandbox lease RPC timeout in milliseconds. Read at lease time by
|
|
* `resolvePluginSandboxRpcTimeoutMs` to extend the worker-manager call
|
|
* timeout when acquiring a lease may take minutes (e.g. a cold node
|
|
* scale-up on an autoscale-to-zero pool). Stored verbatim in the
|
|
* environment config and validated by the sandbox config schema.
|
|
*/
|
|
timeoutMs?: number;
|
|
adapters?: import("@paperclipai/shared").AdapterRegistryEntry[];
|
|
[key: string]: unknown;
|
|
}
|
|
|
|
/**
|
|
* Input to `ensureManagedSandboxEnvironment`. Provider-agnostic: `provider`
|
|
* is the sandbox plugin's driver key and is forced into `config.provider`;
|
|
* the rest of `config` is stored verbatim for the plugin to validate at
|
|
* lease time.
|
|
*/
|
|
export interface ManagedSandboxEnvironmentInput {
|
|
/** Company whose managed-resource binding should be reconciled. Omit at instance boot to bind every company. */
|
|
companyId?: string;
|
|
name: string;
|
|
description?: string;
|
|
/** Sandbox provider key (the plugin's driverKey, e.g. "kubernetes", "daytona"). */
|
|
provider: string;
|
|
config?: Record<string, unknown>;
|
|
/**
|
|
* Extra metadata markers stamped on the managed row (e.g. the legacy
|
|
* kubernetes marker `managedKubernetesSandbox` that
|
|
* `findKubernetesEnvironment` keys on).
|
|
*/
|
|
extraMetadata?: Record<string, unknown>;
|
|
/** Version label recorded with the stock binding; hashes remain the drift authority. */
|
|
stockVersion?: string;
|
|
/**
|
|
* Asserts the caller's deployment gives no operator any path to hand-edit
|
|
* this row (currently only true for the PAPERCLIP_MANAGED_CONFIG applier,
|
|
* where `enableManagedSandboxOnly` removes the tenant's own environment
|
|
* choice entirely). When set, a plain content-hash mismatch against a real
|
|
* prior binding is treated as ordinary stock drift instead of an operator
|
|
* customization to protect — see the `operator_modified` handling below.
|
|
* Leave unset for any caller (self-hosted `kubernetes-execution-mode`
|
|
* bootstrap, tests, admin routes) where an operator could realistically
|
|
* have edited the row through the normal environments UI/API.
|
|
*/
|
|
platformFullyManaged?: boolean;
|
|
}
|
|
|
|
export type ManagedSandboxEnvironmentReconcileAction =
|
|
| "added"
|
|
| "updated"
|
|
| "unchanged"
|
|
| "skipped";
|
|
|
|
export interface ManagedSandboxEnvironmentReconcileResult {
|
|
environment: Environment;
|
|
action: ManagedSandboxEnvironmentReconcileAction;
|
|
/** Classification observed before this reconciliation wrote anything. */
|
|
stockStatus: ManagedResourceStockStatus;
|
|
/** True only when operator drift prevented the available stock update. */
|
|
updateAvailable: boolean;
|
|
stockHash: string;
|
|
}
|
|
|
|
function cloneRecord(value: unknown, fallback: Record<string, unknown> | null = null): Record<string, unknown> | null {
|
|
if (!value || typeof value !== "object" || Array.isArray(value)) return fallback;
|
|
return { ...(value as Record<string, unknown>) };
|
|
}
|
|
|
|
function readEnum<T extends string>(value: string | null, allowed: readonly T[], fieldName: string): T | null {
|
|
if (value === null) return null;
|
|
if ((allowed as readonly string[]).includes(value)) return value as T;
|
|
throw new Error(`Unexpected ${fieldName} value: ${value}`);
|
|
}
|
|
|
|
function hasConstraintName(error: unknown, constraintName: string): boolean {
|
|
if (typeof error !== "object" || error === null) return false;
|
|
const candidate = error as {
|
|
constraint?: unknown;
|
|
constraint_name?: unknown;
|
|
cause?: unknown;
|
|
};
|
|
return candidate.constraint === constraintName
|
|
|| candidate.constraint_name === constraintName
|
|
|| hasConstraintName(candidate.cause, constraintName);
|
|
}
|
|
|
|
function toEnvironment(row: EnvironmentRow): Environment {
|
|
return {
|
|
id: row.id,
|
|
name: row.name,
|
|
description: row.description ?? null,
|
|
driver: readEnum(row.driver, ENVIRONMENT_DRIVERS, "environment driver") ?? "local",
|
|
status: readEnum(row.status, ENVIRONMENT_STATUSES, "environment status") ?? "active",
|
|
config: cloneRecord(row.config, {}) ?? {},
|
|
envVars: cloneRecord(row.envVars, {}) ?? {},
|
|
metadata: cloneRecord(row.metadata),
|
|
createdAt: row.createdAt,
|
|
updatedAt: row.updatedAt,
|
|
} as Environment;
|
|
}
|
|
|
|
type EnvironmentListFilters = {
|
|
status?: string;
|
|
driver?: string;
|
|
};
|
|
|
|
function resolveListFilters(
|
|
companyIdOrFilters?: string | EnvironmentListFilters,
|
|
maybeFilters?: EnvironmentListFilters,
|
|
): EnvironmentListFilters {
|
|
if (typeof companyIdOrFilters === "string") {
|
|
return maybeFilters ?? {};
|
|
}
|
|
return companyIdOrFilters ?? {};
|
|
}
|
|
|
|
function resolveCreateInput(
|
|
companyIdOrInput: string | CreateEnvironment,
|
|
maybeInput?: CreateEnvironment,
|
|
): CreateEnvironment {
|
|
if (typeof companyIdOrInput === "string") {
|
|
if (!maybeInput) throw new Error("Create environment input is required");
|
|
return maybeInput;
|
|
}
|
|
return companyIdOrInput;
|
|
}
|
|
|
|
function resolveKubernetesConfig(
|
|
companyIdOrConfig: string | KubernetesEnvironmentConfigInput,
|
|
maybeConfig?: KubernetesEnvironmentConfigInput,
|
|
): KubernetesEnvironmentConfigInput {
|
|
if (typeof companyIdOrConfig === "string") {
|
|
if (!maybeConfig) throw new Error("Kubernetes environment config is required");
|
|
return maybeConfig;
|
|
}
|
|
return companyIdOrConfig;
|
|
}
|
|
|
|
function toEnvironmentLease(row: EnvironmentLeaseRow): EnvironmentLease {
|
|
return {
|
|
id: row.id,
|
|
companyId: row.companyId,
|
|
environmentId: row.environmentId,
|
|
executionWorkspaceId: row.executionWorkspaceId ?? null,
|
|
issueId: row.issueId ?? null,
|
|
heartbeatRunId: row.heartbeatRunId ?? null,
|
|
status: readEnum(row.status, ENVIRONMENT_LEASE_STATUSES, "environment lease status") ?? "active",
|
|
leasePolicy: readEnum(row.leasePolicy, ENVIRONMENT_LEASE_POLICIES, "environment lease policy") ?? "ephemeral",
|
|
provider: row.provider ?? null,
|
|
providerLeaseId: row.providerLeaseId ?? null,
|
|
acquiredAt: row.acquiredAt,
|
|
lastUsedAt: row.lastUsedAt,
|
|
expiresAt: row.expiresAt ?? null,
|
|
releasedAt: row.releasedAt ?? null,
|
|
failureReason: row.failureReason ?? null,
|
|
cleanupStatus: readEnum(
|
|
row.cleanupStatus,
|
|
ENVIRONMENT_LEASE_CLEANUP_STATUSES,
|
|
"environment lease cleanup status",
|
|
),
|
|
metadata: cloneRecord(row.metadata),
|
|
createdAt: row.createdAt,
|
|
updatedAt: row.updatedAt,
|
|
};
|
|
}
|
|
|
|
function countFromRows(rows: Array<{ count: number | string | null | undefined }>): number {
|
|
return Number(rows[0]?.count ?? 0);
|
|
}
|
|
|
|
type DbTransaction = Parameters<Parameters<Db["transaction"]>[0]>[0];
|
|
type EnvironmentWriteDb = Pick<Db | DbTransaction, "select" | "insert" | "update" | "delete">;
|
|
|
|
const MANAGED_ENVIRONMENT_BUNDLE_KEY = "managed-sandbox-environment";
|
|
const MANAGED_ENVIRONMENT_RESOURCE_KIND = "environment";
|
|
const MANAGED_ENVIRONMENT_RESOURCE_KEY = "managed-sandbox";
|
|
const MANAGED_ENVIRONMENT_STOCK_VERSION = "managed-environment-v1";
|
|
const MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_METADATA_KEY = "_paperclipManagedArchiveToken";
|
|
const MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_DEFAULTS_KEY = "_paperclipManagedArchiveToken";
|
|
|
|
function managedEnvironmentBaselineDefaults(
|
|
defaultsJson: Record<string, unknown>,
|
|
): Record<string, unknown> {
|
|
const baseline = { ...defaultsJson };
|
|
delete baseline[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_DEFAULTS_KEY];
|
|
return baseline;
|
|
}
|
|
|
|
function withoutManagedEnvironmentArchiveToken(
|
|
metadata: Record<string, unknown> | null,
|
|
): Record<string, unknown> | null {
|
|
if (!metadata) return null;
|
|
const next = { ...metadata };
|
|
delete next[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_METADATA_KEY];
|
|
return next;
|
|
}
|
|
|
|
function managedMetadataKeys(
|
|
desiredMetadata: Record<string, unknown>,
|
|
bindings: Array<{ defaultsJson: Record<string, unknown> }>,
|
|
): string[] {
|
|
const keys = new Set([
|
|
"managedByPaperclip",
|
|
"managedSandboxProvider",
|
|
KUBERNETES_MANAGED_MARKER,
|
|
...Object.keys(desiredMetadata),
|
|
]);
|
|
for (const binding of bindings) {
|
|
const metadata = cloneRecord(binding.defaultsJson.metadata);
|
|
for (const key of Object.keys(metadata ?? {})) keys.add(key);
|
|
}
|
|
return [...keys].sort((left, right) => left.localeCompare(right));
|
|
}
|
|
|
|
function managedEnvironmentStock(input: {
|
|
name: string;
|
|
description: string | null;
|
|
config: Record<string, unknown>;
|
|
metadata: Record<string, unknown> | null;
|
|
status: string;
|
|
}, metadataKeys: readonly string[]): Record<string, unknown> {
|
|
const metadata = input.metadata ?? {};
|
|
return {
|
|
name: input.name,
|
|
description: input.description,
|
|
config: input.config,
|
|
metadata: Object.fromEntries(
|
|
metadataKeys.map((key) => [key, Object.prototype.hasOwnProperty.call(metadata, key) ? metadata[key] : null]),
|
|
),
|
|
status: input.status,
|
|
};
|
|
}
|
|
|
|
function mergeManagedEnvironmentMetadata(
|
|
current: Record<string, unknown> | null,
|
|
desired: Record<string, unknown>,
|
|
keys: readonly string[],
|
|
): Record<string, unknown> {
|
|
const merged = { ...(current ?? {}) };
|
|
for (const key of keys) {
|
|
const value = Object.prototype.hasOwnProperty.call(desired, key) ? desired[key] : null;
|
|
if (value === null || value === undefined) delete merged[key];
|
|
else merged[key] = value;
|
|
}
|
|
return merged;
|
|
}
|
|
|
|
function preserveInvalidatedSnapshotProofs(replacement: SQL): SQL {
|
|
const proofs = sql`(select coalesce(jsonb_object_agg(entry.key, entry.value || '{"invalidated":true}'::jsonb), '{}'::jsonb)
|
|
from jsonb_each(coalesce(${environments.metadata}->${SANDBOX_PLATFORM_PROBE_METADATA_KEY}, '{}'::jsonb)) as entry
|
|
where entry.value->>'v' = '2')`;
|
|
return sql`case when ${proofs} = '{}'::jsonb then ${replacement}
|
|
else coalesce(${replacement}, '{}'::jsonb) || jsonb_build_object(${SANDBOX_PLATFORM_PROBE_METADATA_KEY}::text, ${proofs}) end`;
|
|
}
|
|
|
|
export function environmentService(db: Db) {
|
|
/**
|
|
* Idempotently ensure THE Paperclip-managed sandbox environment for this
|
|
* instance, configured for an arbitrary sandbox provider plugin. Mirrors
|
|
* `ensureLocalEnvironment`; the partial unique index
|
|
* `environments_managed_sandbox_idx` enforces at most one managed sandbox
|
|
* row per instance, so this function owns that single slot regardless of
|
|
* provider:
|
|
*
|
|
* - A stock-controlled managed row advances to a new stock hash in the same
|
|
* transaction as its managed fields, including provider switches.
|
|
* - A stock-current row is returned without an environment write.
|
|
* - An operator-modified or previously unmanaged row is preserved and
|
|
* reported as skipped; its user-owned fields are never folded into stock.
|
|
*/
|
|
const ensureManagedSandboxEnvironment = async (
|
|
input: ManagedSandboxEnvironmentInput,
|
|
): Promise<ManagedSandboxEnvironmentReconcileResult> => {
|
|
const desiredConfig: Record<string, unknown> = {
|
|
...(input.config ?? {}),
|
|
provider: input.provider,
|
|
};
|
|
const desiredMetadata: Record<string, unknown> = {
|
|
managedByPaperclip: true,
|
|
managedSandboxProvider: input.provider,
|
|
...(input.extraMetadata ?? {}),
|
|
};
|
|
if (desiredMetadata[KUBERNETES_MANAGED_MARKER] !== true) {
|
|
desiredMetadata[KUBERNETES_MANAGED_MARKER] = null;
|
|
}
|
|
|
|
let activityCompanyIds: string[] = [];
|
|
let trackingInitialized = false;
|
|
let providerReactivated = false;
|
|
const reconciliation = await db.transaction(
|
|
async (tx): Promise<ManagedSandboxEnvironmentReconcileResult> => {
|
|
const companyIds = input.companyId
|
|
? [input.companyId]
|
|
: await tx.select({ id: companies.id }).from(companies).then((rows) => rows.map((row) => row.id));
|
|
activityCompanyIds = companyIds;
|
|
|
|
// Take the sandbox-row lock BEFORE reading the stock bindings. Two
|
|
// passes can reconcile the same slot concurrently (the boot ensure and
|
|
// the async provider-recovery reactivation, or two app builds during a
|
|
// rolling deploy). Concurrent passes serialize on this lock, and under
|
|
// READ COMMITTED each later statement sees a fresh snapshot — so a pass
|
|
// that blocks here then reads the bindings the winning pass committed,
|
|
// not a snapshot from before it waited. Reading bindings first left a
|
|
// window where a waiting pass compared the winner's fresh row against
|
|
// its own stale binding hash, misclassified the mismatch as
|
|
// `operator_modified`, and — once `platformFullyManaged` turns that
|
|
// into an update — rolled the row back to its own older stock.
|
|
const sandboxRows = await tx
|
|
.select()
|
|
.from(environments)
|
|
.where(eq(environments.driver, "sandbox"))
|
|
.for("update");
|
|
|
|
const bindingConditions = and(
|
|
eq(builtInManagedResources.bundleKey, MANAGED_ENVIRONMENT_BUNDLE_KEY),
|
|
eq(builtInManagedResources.resourceKind, MANAGED_ENVIRONMENT_RESOURCE_KIND),
|
|
eq(builtInManagedResources.resourceKey, MANAGED_ENVIRONMENT_RESOURCE_KEY),
|
|
...(companyIds.length > 0 ? [inArray(builtInManagedResources.companyId, companyIds)] : []),
|
|
);
|
|
const bindings = companyIds.length > 0
|
|
? await tx.select().from(builtInManagedResources).where(bindingConditions)
|
|
: [];
|
|
trackingInitialized = bindings.length < companyIds.length;
|
|
const keys = managedMetadataKeys(desiredMetadata, bindings);
|
|
|
|
let row = sandboxRows.find(
|
|
(candidate) => (candidate.metadata as Record<string, unknown> | null)?.managedByPaperclip === true,
|
|
) ?? sandboxRows.find((candidate) => candidate.name === input.name) ?? null;
|
|
|
|
const writeBindings = async (
|
|
environmentId: string,
|
|
stockVersion: string,
|
|
installedStockHash: string,
|
|
defaultsJson: Record<string, unknown>,
|
|
replace: boolean,
|
|
) => {
|
|
const targetCompanyIds = replace
|
|
? companyIds
|
|
: companyIds.filter(
|
|
(companyId) => !bindings.some((binding) => binding.companyId === companyId),
|
|
);
|
|
if (targetCompanyIds.length === 0) return;
|
|
const values = targetCompanyIds.map((companyId) => ({
|
|
companyId,
|
|
bundleKey: MANAGED_ENVIRONMENT_BUNDLE_KEY,
|
|
resourceKind: MANAGED_ENVIRONMENT_RESOURCE_KIND,
|
|
resourceKey: MANAGED_ENVIRONMENT_RESOURCE_KEY,
|
|
resourceId: environmentId,
|
|
stockVersion,
|
|
stockHash: installedStockHash,
|
|
defaultsJson,
|
|
}));
|
|
const insert = tx.insert(builtInManagedResources).values(values);
|
|
if (!replace) {
|
|
await insert.onConflictDoNothing({
|
|
target: [
|
|
builtInManagedResources.companyId,
|
|
builtInManagedResources.bundleKey,
|
|
builtInManagedResources.resourceKind,
|
|
builtInManagedResources.resourceKey,
|
|
],
|
|
});
|
|
return;
|
|
}
|
|
await insert.onConflictDoUpdate({
|
|
target: [
|
|
builtInManagedResources.companyId,
|
|
builtInManagedResources.bundleKey,
|
|
builtInManagedResources.resourceKind,
|
|
builtInManagedResources.resourceKey,
|
|
],
|
|
set: {
|
|
resourceId: environmentId,
|
|
stockVersion,
|
|
stockHash: installedStockHash,
|
|
defaultsJson,
|
|
updatedAt: new Date(),
|
|
},
|
|
});
|
|
};
|
|
|
|
if (!row) {
|
|
const nameOwner = await tx
|
|
.select()
|
|
.from(environments)
|
|
.where(eq(environments.name, input.name))
|
|
.then((rows) => rows[0] ?? null);
|
|
if (nameOwner && nameOwner.driver !== "sandbox") {
|
|
throw new Error(
|
|
`Failed to ensure managed sandbox environment: environment "${input.name}" already exists with driver "${nameOwner.driver}"`,
|
|
);
|
|
}
|
|
const now = new Date();
|
|
const inserted = await tx
|
|
.insert(environments)
|
|
.values({
|
|
name: input.name,
|
|
description: input.description ?? null,
|
|
driver: "sandbox",
|
|
status: "active",
|
|
config: desiredConfig,
|
|
envVars: {},
|
|
metadata: mergeManagedEnvironmentMetadata(null, desiredMetadata, keys),
|
|
createdAt: now,
|
|
updatedAt: now,
|
|
})
|
|
// Either the managed-slot partial index or the global name index
|
|
// can select the concurrent winner. Treat both as convergence and
|
|
// reselect that winner under lock below.
|
|
.onConflictDoNothing()
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
if (inserted) {
|
|
const stock = managedEnvironmentStock({
|
|
name: inserted.name,
|
|
description: inserted.description ?? null,
|
|
config: inserted.config,
|
|
metadata: inserted.metadata,
|
|
status: inserted.status,
|
|
}, keys);
|
|
const latestStockHash = stockHash(stock);
|
|
await writeBindings(
|
|
inserted.id,
|
|
input.stockVersion ?? MANAGED_ENVIRONMENT_STOCK_VERSION,
|
|
latestStockHash,
|
|
stock,
|
|
true,
|
|
);
|
|
return {
|
|
environment: toEnvironment(inserted),
|
|
action: "added",
|
|
stockStatus: "missing",
|
|
updateAvailable: false,
|
|
stockHash: latestStockHash,
|
|
};
|
|
}
|
|
row = await tx
|
|
.select()
|
|
.from(environments)
|
|
.where(eq(environments.driver, "sandbox"))
|
|
.for("update")
|
|
.then(
|
|
(rows) => rows.find(
|
|
(candidate) => (candidate.metadata as Record<string, unknown> | null)?.managedByPaperclip === true,
|
|
) ?? null,
|
|
);
|
|
if (!row) throw new Error("Failed to ensure managed sandbox environment");
|
|
}
|
|
|
|
const nameOwner = await tx
|
|
.select({ id: environments.id })
|
|
.from(environments)
|
|
.where(eq(environments.name, input.name))
|
|
.then((rows) => rows[0] ?? null);
|
|
const desiredName = nameOwner && nameOwner.id !== row.id ? row.name : input.name;
|
|
const desiredStock = managedEnvironmentStock({
|
|
name: desiredName,
|
|
description: input.description ?? null,
|
|
config: desiredConfig,
|
|
metadata: desiredMetadata,
|
|
status: "active",
|
|
}, keys);
|
|
const latestStockHash = stockHash(desiredStock);
|
|
const currentStock = managedEnvironmentStock({
|
|
name: row.name,
|
|
description: row.description ?? null,
|
|
config: row.config,
|
|
metadata: row.metadata,
|
|
status: row.status,
|
|
}, keys);
|
|
const currentHash = stockHash(currentStock);
|
|
const matchingBindings = bindings.filter((binding) => binding.resourceId === row!.id);
|
|
const rowArchiveToken = (row.metadata as Record<string, unknown> | null)
|
|
?.[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_METADATA_KEY];
|
|
let stockStatus = resourceStatus({
|
|
resourceId: row.id,
|
|
currentHash,
|
|
bindingStockHash: matchingBindings[0]?.stockHash ?? null,
|
|
latestStockHash,
|
|
});
|
|
if (stockStatus === "operator_modified") {
|
|
const stockControlledBinding = matchingBindings.find(
|
|
(binding) => resourceStatus({
|
|
resourceId: row!.id,
|
|
currentHash,
|
|
bindingStockHash: binding.stockHash,
|
|
latestStockHash,
|
|
}) === "stock_update_available",
|
|
);
|
|
if (stockControlledBinding) stockStatus = "stock_update_available";
|
|
}
|
|
const operatorReaffirmedArchive = row.status === "archived" && matchingBindings.some(
|
|
(binding) => {
|
|
const bindingToken = binding.defaultsJson[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_DEFAULTS_KEY];
|
|
return binding.defaultsJson.status === "archived" &&
|
|
typeof bindingToken === "string" &&
|
|
bindingToken !== rowArchiveToken;
|
|
},
|
|
);
|
|
if (operatorReaffirmedArchive) stockStatus = "operator_modified";
|
|
|
|
// `platformFullyManaged` callers (currently: the PAPERCLIP_MANAGED_CONFIG
|
|
// applier) assert that nothing in their deployment can hand-edit this
|
|
// row — the product gives a cloud-harness tenant no path to it, unlike
|
|
// the general self-hosted contract this function otherwise protects
|
|
// (see "classifies operator drift" in environment-service.test.ts,
|
|
// which exercises a real operator edit and must keep winning). Under
|
|
// that assertion, a plain content-hash mismatch against a real prior
|
|
// binding can only be drift between two platform-driven reconciliation
|
|
// passes (e.g. a stock hash recorded by an older app build before a
|
|
// later stock field was added), never a customization to protect —
|
|
// apply it like any other stock-outdated row.
|
|
//
|
|
// Two things the bypass must never touch:
|
|
// - A row with NO matching binding. `row` can be a same-name sandbox
|
|
// row that was never Paperclip-managed (the fallback lookup above).
|
|
// It also reads as `operator_modified`, but there is no prior
|
|
// platform pass to have drifted from — adopting it would overwrite
|
|
// a tenant-created environment and stamp it managed. Require a
|
|
// binding for this exact row, so "prior binding" is enforced, not
|
|
// just documented.
|
|
// - Archive-reaffirmation. A `sandbox_image` update must never
|
|
// resurrect a row something else deliberately kept archived after
|
|
// Paperclip's own provider-unavailability archival, so that path
|
|
// still skips below regardless of this flag.
|
|
if (
|
|
input.platformFullyManaged &&
|
|
stockStatus === "operator_modified" &&
|
|
!operatorReaffirmedArchive &&
|
|
matchingBindings.length > 0
|
|
) {
|
|
stockStatus = "stock_update_available";
|
|
}
|
|
|
|
if (stockStatus === "operator_modified") {
|
|
const baseline = matchingBindings[0];
|
|
let baselineDefaults = baseline
|
|
? managedEnvironmentBaselineDefaults(baseline.defaultsJson)
|
|
: desiredStock;
|
|
let baselineHash = baseline?.stockHash ?? latestStockHash;
|
|
|
|
// Provider unavailability is an operational state transition, not
|
|
// an operator edit. If the binding records that Paperclip archived
|
|
// this row, restore only its availability status. Keep every other
|
|
// operator-modified field intact and leave the stock update pending.
|
|
// A manually archived row still has an active binding baseline, so
|
|
// it remains operator_modified and is not reactivated here.
|
|
const archivedByReconciler = row.status === "archived" &&
|
|
typeof rowArchiveToken === "string" &&
|
|
matchingBindings.some((binding) => {
|
|
const bindingDefaults = binding.defaultsJson;
|
|
return bindingDefaults.status === "archived" &&
|
|
bindingDefaults[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_DEFAULTS_KEY] === rowArchiveToken;
|
|
});
|
|
if (archivedByReconciler) {
|
|
const reactivated = await tx
|
|
.update(environments)
|
|
.set({
|
|
status: "active",
|
|
metadata: withoutManagedEnvironmentArchiveToken(row.metadata),
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(and(eq(environments.id, row.id), eq(environments.status, "archived")))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!reactivated) {
|
|
throw new Error("Managed sandbox environment changed during reactivation");
|
|
}
|
|
row = reactivated;
|
|
providerReactivated = true;
|
|
|
|
for (const binding of matchingBindings) {
|
|
const reactivatedDefaults = {
|
|
...managedEnvironmentBaselineDefaults(binding.defaultsJson),
|
|
status: "active",
|
|
};
|
|
const reactivatedHash = stockHash(reactivatedDefaults);
|
|
await tx
|
|
.update(builtInManagedResources)
|
|
.set({
|
|
stockHash: reactivatedHash,
|
|
defaultsJson: reactivatedDefaults,
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(and(
|
|
eq(builtInManagedResources.id, binding.id),
|
|
eq(builtInManagedResources.resourceId, row.id),
|
|
));
|
|
if (binding.id === baseline?.id) {
|
|
baselineDefaults = reactivatedDefaults;
|
|
baselineHash = reactivatedHash;
|
|
}
|
|
}
|
|
}
|
|
await writeBindings(
|
|
row.id,
|
|
baseline?.stockVersion ?? input.stockVersion ?? MANAGED_ENVIRONMENT_STOCK_VERSION,
|
|
baselineHash,
|
|
baselineDefaults,
|
|
false,
|
|
);
|
|
return {
|
|
environment: toEnvironment(row),
|
|
action: "skipped",
|
|
stockStatus,
|
|
updateAvailable: true,
|
|
stockHash: latestStockHash,
|
|
};
|
|
}
|
|
|
|
if (stockStatus === "stock_current") {
|
|
await writeBindings(
|
|
row.id,
|
|
input.stockVersion ?? MANAGED_ENVIRONMENT_STOCK_VERSION,
|
|
latestStockHash,
|
|
desiredStock,
|
|
false,
|
|
);
|
|
return {
|
|
environment: toEnvironment(row),
|
|
action: "unchanged",
|
|
stockStatus,
|
|
updateAvailable: false,
|
|
stockHash: latestStockHash,
|
|
};
|
|
}
|
|
|
|
const updated = await tx
|
|
.update(environments)
|
|
.set({
|
|
name: desiredName,
|
|
description: input.description ?? null,
|
|
config: desiredConfig,
|
|
metadata: withoutManagedEnvironmentArchiveToken(
|
|
mergeManagedEnvironmentMetadata(row.metadata, desiredMetadata, keys),
|
|
),
|
|
status: "active",
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(eq(environments.id, row.id))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!updated) throw new Error("Managed sandbox environment changed during reconciliation");
|
|
await writeBindings(
|
|
updated.id,
|
|
input.stockVersion ?? MANAGED_ENVIRONMENT_STOCK_VERSION,
|
|
latestStockHash,
|
|
desiredStock,
|
|
true,
|
|
);
|
|
return {
|
|
environment: toEnvironment(updated),
|
|
action: "updated",
|
|
stockStatus,
|
|
updateAvailable: false,
|
|
stockHash: latestStockHash,
|
|
};
|
|
},
|
|
);
|
|
if (reconciliation.action !== "unchanged" || trackingInitialized) {
|
|
const action = reconciliation.action === "added"
|
|
? "environment.managed_stock_added"
|
|
: reconciliation.action === "updated"
|
|
? "environment.managed_stock_updated"
|
|
: reconciliation.action === "skipped"
|
|
? "environment.managed_stock_skipped"
|
|
: "environment.managed_stock_tracking_initialized";
|
|
await Promise.all(activityCompanyIds.map((companyId) => logActivity(db, {
|
|
companyId,
|
|
actorType: "system",
|
|
actorId: "managed-environment-reconciler",
|
|
action,
|
|
entityType: "environment",
|
|
entityId: reconciliation.environment.id,
|
|
details: {
|
|
provider: input.provider,
|
|
reconciliationAction: reconciliation.action,
|
|
stockStatus: reconciliation.stockStatus,
|
|
updateAvailable: reconciliation.updateAvailable,
|
|
stockHash: reconciliation.stockHash,
|
|
providerReactivated,
|
|
},
|
|
})));
|
|
}
|
|
return reconciliation;
|
|
};
|
|
|
|
/**
|
|
* Archive the Paperclip-managed sandbox row when its provider became
|
|
* unavailable (plugin missing, not ready, or its worker not running), so
|
|
* run scheduling stops selecting an environment whose lease acquisition
|
|
* cannot succeed (`resolveEnvironment` rejects non-active rows).
|
|
*
|
|
* Scoped to the row provisioned for the SAME provider: a row that a
|
|
* provider switch left on a different provider is not touched (the ensure
|
|
* path adopts it once the new provider is healthy). Reactivation is
|
|
* automatic — the next successful `ensureManagedSandboxEnvironment` stamps
|
|
* the row `active` again.
|
|
*
|
|
* Returns the archived environment, or null when there is no active
|
|
* managed row for this provider.
|
|
*/
|
|
const archiveManagedSandboxEnvironment = async (
|
|
input: { provider: string; companyId?: string },
|
|
): Promise<Environment | null> => {
|
|
let activityCompanyIds: string[] = [];
|
|
const archived = await db.transaction(async (tx) => {
|
|
const existing = await tx
|
|
.select()
|
|
.from(environments)
|
|
.where(eq(environments.driver, "sandbox"))
|
|
.for("update")
|
|
.then(
|
|
(rows) => rows.find(
|
|
(row) => (row.metadata as Record<string, unknown> | null)?.managedByPaperclip === true,
|
|
) ?? null,
|
|
);
|
|
if (!existing || existing.status !== "active") return null;
|
|
const rowProvider = (existing.metadata as Record<string, unknown> | null)
|
|
?.managedSandboxProvider;
|
|
if (rowProvider !== input.provider) return null;
|
|
|
|
const companyIds = input.companyId
|
|
? [input.companyId]
|
|
: await tx.select({ id: companies.id }).from(companies).then((rows) => rows.map((row) => row.id));
|
|
activityCompanyIds = companyIds;
|
|
const bindings = companyIds.length > 0
|
|
? await tx
|
|
.select()
|
|
.from(builtInManagedResources)
|
|
.where(and(
|
|
inArray(builtInManagedResources.companyId, companyIds),
|
|
eq(builtInManagedResources.bundleKey, MANAGED_ENVIRONMENT_BUNDLE_KEY),
|
|
eq(builtInManagedResources.resourceKind, MANAGED_ENVIRONMENT_RESOURCE_KIND),
|
|
eq(builtInManagedResources.resourceKey, MANAGED_ENVIRONMENT_RESOURCE_KEY),
|
|
eq(builtInManagedResources.resourceId, existing.id),
|
|
))
|
|
: [];
|
|
const archiveToken = randomUUID();
|
|
const archivedMetadata = {
|
|
...(existing.metadata ?? {}),
|
|
[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_METADATA_KEY]: archiveToken,
|
|
};
|
|
const archived = await tx
|
|
.update(environments)
|
|
.set({
|
|
status: "archived",
|
|
metadata: archivedMetadata,
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(and(eq(environments.id, existing.id), eq(environments.status, "active")))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!archived) return null;
|
|
|
|
// Archival is a Paperclip-owned availability transition. Record only
|
|
// that status change in each installed baseline. Deriving the new hash
|
|
// from defaultsJson keeps operator-modified row fields out of stock.
|
|
for (const binding of bindings) {
|
|
const archivedStock = {
|
|
...managedEnvironmentBaselineDefaults(binding.defaultsJson),
|
|
status: "archived",
|
|
};
|
|
await tx
|
|
.update(builtInManagedResources)
|
|
.set({
|
|
stockHash: stockHash(archivedStock),
|
|
defaultsJson: {
|
|
...archivedStock,
|
|
[MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_DEFAULTS_KEY]: archiveToken,
|
|
},
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(and(
|
|
eq(builtInManagedResources.id, binding.id),
|
|
eq(builtInManagedResources.resourceId, existing.id),
|
|
));
|
|
}
|
|
return toEnvironment(archived);
|
|
});
|
|
if (archived) {
|
|
await Promise.all(activityCompanyIds.map((companyId) => logActivity(db, {
|
|
companyId,
|
|
actorType: "system",
|
|
actorId: "managed-environment-reconciler",
|
|
action: "environment.managed_provider_unavailable_archived",
|
|
entityType: "environment",
|
|
entityId: archived.id,
|
|
details: { provider: input.provider },
|
|
})));
|
|
}
|
|
return archived;
|
|
};
|
|
|
|
return {
|
|
recordSandboxPlatformProbe: async (input: {
|
|
environmentId: string;
|
|
companyId: string;
|
|
config: Record<string, unknown>;
|
|
proof: Record<string, unknown> | null;
|
|
}): Promise<boolean> => {
|
|
const existing = sql`coalesce(${environments.metadata}->${SANDBOX_PLATFORM_PROBE_METADATA_KEY}, '{}'::jsonb)`;
|
|
const previous = sql`${existing}->${input.companyId}`;
|
|
const probes = input.proof === null
|
|
? sql`case when ${previous}->>'v' = '2'
|
|
then jsonb_set(${existing}, ARRAY[${input.companyId}]::text[], ${previous} || '{"invalidated":true}'::jsonb, true)
|
|
else ${existing} - ${input.companyId} end`
|
|
: sql`${existing} || ${JSON.stringify({ [input.companyId]: input.proof })}::jsonb`;
|
|
const rows = await db.update(environments).set({
|
|
metadata: sql`jsonb_set(coalesce(${environments.metadata}, '{}'::jsonb), ARRAY[${SANDBOX_PLATFORM_PROBE_METADATA_KEY}]::text[], ${probes}, true)`,
|
|
}).where(and(eq(environments.id, input.environmentId), eq(environments.driver, "sandbox"), eq(environments.config, input.config))).returning({ id: environments.id });
|
|
return rows.length > 0;
|
|
},
|
|
list: async (
|
|
companyIdOrFilters?: string | EnvironmentListFilters,
|
|
maybeFilters?: EnvironmentListFilters,
|
|
): Promise<Environment[]> => {
|
|
const filters = resolveListFilters(companyIdOrFilters, maybeFilters);
|
|
const conditions = [];
|
|
if (filters.status) conditions.push(eq(environments.status, filters.status));
|
|
if (filters.driver) conditions.push(eq(environments.driver, filters.driver));
|
|
const rows = await db
|
|
.select()
|
|
.from(environments)
|
|
.where(conditions.length > 0 ? and(...conditions) : undefined)
|
|
.orderBy(desc(environments.updatedAt), desc(environments.createdAt));
|
|
return rows.map(toEnvironment);
|
|
},
|
|
|
|
getById: async (id: string): Promise<Environment | null> => {
|
|
const row = await db.select().from(environments).where(eq(environments.id, id)).then((rows) => rows[0] ?? null);
|
|
return row ? toEnvironment(row) : null;
|
|
},
|
|
|
|
/**
|
|
* List the companies that own an environment through a built-in managed
|
|
* resource binding. A managed sandbox row binds to each company that the
|
|
* instance provisions it for. An operator-created environment has no
|
|
* binding, so this returns an empty list. The caller treats an empty list
|
|
* as an instance-global environment with no company owner.
|
|
*/
|
|
listBoundCompanyIds: async (environmentId: string): Promise<string[]> => {
|
|
const rows = await db
|
|
.select({ companyId: builtInManagedResources.companyId })
|
|
.from(builtInManagedResources)
|
|
.where(
|
|
and(
|
|
eq(builtInManagedResources.resourceKind, MANAGED_ENVIRONMENT_RESOURCE_KIND),
|
|
eq(builtInManagedResources.resourceId, environmentId),
|
|
),
|
|
);
|
|
return Array.from(new Set(rows.map((row) => row.companyId)));
|
|
},
|
|
|
|
getLeaseById: async (id: string): Promise<EnvironmentLease | null> => {
|
|
const row = await db
|
|
.select()
|
|
.from(environmentLeases)
|
|
.where(eq(environmentLeases.id, id))
|
|
.then((rows) => rows[0] ?? null);
|
|
return row ? toEnvironmentLease(row) : null;
|
|
},
|
|
|
|
/**
|
|
* Idempotently ensure THE local-driver environment row; the partial
|
|
* unique index `environments_local_driver_idx` enforces at most one per
|
|
* instance.
|
|
*
|
|
* On a cloud-managed instance an existing row is additionally ADOPTED —
|
|
* stamped `managedByPaperclip: true` (other metadata preserved) — so the
|
|
* single local slot is platform-owned there by construction, mirroring
|
|
* `ensureManagedSandboxEnvironment`'s adoption of the sandbox slot. This
|
|
* is what lets the environment-routes write floor treat a local row's
|
|
* platform markers as live state rather than a stale leftover: every
|
|
* caller (company creation, the heartbeat, run orchestration) converges
|
|
* the marker. Self-hosted instances keep the historical behavior:
|
|
* an existing row is returned untouched.
|
|
*/
|
|
ensureLocalEnvironment: async (_companyId?: string): Promise<Environment> => {
|
|
const now = new Date();
|
|
const insert = () =>
|
|
db
|
|
.insert(environments)
|
|
.values({
|
|
name: DEFAULT_LOCAL_ENVIRONMENT_NAME,
|
|
description: DEFAULT_LOCAL_ENVIRONMENT_DESCRIPTION,
|
|
driver: "local",
|
|
status: "active",
|
|
config: {},
|
|
envVars: {},
|
|
metadata: {
|
|
managedByPaperclip: true,
|
|
defaultForInstance: true,
|
|
},
|
|
createdAt: now,
|
|
updatedAt: now,
|
|
})
|
|
.onConflictDoNothing({
|
|
target: [environments.driver],
|
|
where: sql`${environments.driver} = 'local'`,
|
|
})
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
const row = await insert().catch((error: unknown) => {
|
|
if (hasConstraintName(error, "environments_name_idx")) {
|
|
return null;
|
|
}
|
|
throw error;
|
|
});
|
|
if (row) return toEnvironment(row);
|
|
|
|
const existing = await db
|
|
.select()
|
|
.from(environments)
|
|
.where(eq(environments.driver, "local"))
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!existing) {
|
|
throw new Error("Failed to ensure local environment");
|
|
}
|
|
const existingMetadata = (existing.metadata ?? {}) as Record<string, unknown>;
|
|
if (isCloudManagedInstance() && existingMetadata.managedByPaperclip !== true) {
|
|
const adopted = await db
|
|
.update(environments)
|
|
.set({
|
|
metadata: { ...existingMetadata, managedByPaperclip: true },
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(eq(environments.id, existing.id))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? existing);
|
|
return toEnvironment(adopted);
|
|
}
|
|
return toEnvironment(existing);
|
|
},
|
|
|
|
ensureManagedSandboxEnvironment,
|
|
|
|
archiveManagedSandboxEnvironment,
|
|
|
|
/**
|
|
* Idempotently ensure a managed Kubernetes sandbox environment exists for
|
|
* an instance, configured from instance/operator-supplied config. A thin
|
|
* wrapper over `ensureManagedSandboxEnvironment` that pins the provider to
|
|
* "kubernetes" and stamps the legacy marker `findKubernetesEnvironment`
|
|
* keys on. On subsequent calls stock-controlled config advances in place;
|
|
* operator modifications remain untouched for explicit review.
|
|
*/
|
|
ensureKubernetesEnvironment: async (
|
|
companyIdOrConfig: string | KubernetesEnvironmentConfigInput,
|
|
maybeConfig?: KubernetesEnvironmentConfigInput,
|
|
): Promise<Environment> => {
|
|
const config = resolveKubernetesConfig(companyIdOrConfig, maybeConfig);
|
|
return ensureManagedSandboxEnvironment({
|
|
companyId: typeof companyIdOrConfig === "string" ? companyIdOrConfig : undefined,
|
|
name: DEFAULT_KUBERNETES_ENVIRONMENT_NAME,
|
|
description: DEFAULT_KUBERNETES_ENVIRONMENT_DESCRIPTION,
|
|
provider: KUBERNETES_PROVIDER_KEY,
|
|
config,
|
|
extraMetadata: { [KUBERNETES_MANAGED_MARKER]: true },
|
|
}).then((result) => result.environment);
|
|
},
|
|
|
|
/**
|
|
* Find the active managed Kubernetes sandbox environment, if one
|
|
* exists. Read-only counterpart to `ensureKubernetesEnvironment` used by the
|
|
* per-run execution guard (which must not silently create config-less envs).
|
|
*/
|
|
findKubernetesEnvironment: async (_companyId?: string): Promise<Environment | null> => {
|
|
const rows = await db
|
|
.select()
|
|
.from(environments)
|
|
.where(
|
|
and(
|
|
eq(environments.driver, "sandbox"),
|
|
eq(environments.status, "active"),
|
|
),
|
|
)
|
|
.orderBy(desc(environments.updatedAt));
|
|
const match = rows.find(
|
|
(row) =>
|
|
(row.metadata as Record<string, unknown> | null)?.[KUBERNETES_MANAGED_MARKER] === true,
|
|
);
|
|
return match ? toEnvironment(match) : null;
|
|
},
|
|
|
|
/**
|
|
* Find the platform-managed sandbox environment (the single
|
|
* `managedByPaperclip`-marked slot row), if one exists. Read-only
|
|
* counterpart to `ensureManagedSandboxEnvironment`. The default
|
|
* (active-only) form serves the managed-sandbox-only run guard — which
|
|
* must fail closed rather than create a config-less environment when
|
|
* the slot is empty or archived (the provisioner archives it while its
|
|
* provider plugin is down). `includeArchived` serves reconciliation
|
|
* cleanup, which must find the row even after the provisioner archived
|
|
* it.
|
|
*/
|
|
findManagedSandboxEnvironment: async (
|
|
_companyId?: string,
|
|
options?: { includeArchived?: boolean },
|
|
): Promise<Environment | null> => {
|
|
const rows = await db
|
|
.select()
|
|
.from(environments)
|
|
.where(
|
|
options?.includeArchived === true
|
|
? eq(environments.driver, "sandbox")
|
|
: and(
|
|
eq(environments.driver, "sandbox"),
|
|
eq(environments.status, "active"),
|
|
),
|
|
)
|
|
.orderBy(desc(environments.updatedAt));
|
|
const match = rows.find(
|
|
(row) => (row.metadata as Record<string, unknown> | null)?.managedByPaperclip === true,
|
|
);
|
|
return match ? toEnvironment(match) : null;
|
|
},
|
|
|
|
create: async (
|
|
companyIdOrInput: string | CreateEnvironment,
|
|
maybeInput?: CreateEnvironment,
|
|
options?: { db?: EnvironmentWriteDb },
|
|
): Promise<Environment> => {
|
|
const input = resolveCreateInput(companyIdOrInput, maybeInput);
|
|
const now = new Date();
|
|
const row = await (options?.db ?? db)
|
|
.insert(environments)
|
|
.values({
|
|
name: input.name,
|
|
description: input.description ?? null,
|
|
driver: input.driver,
|
|
status: input.status ?? "active",
|
|
config: input.config ?? {},
|
|
envVars: (input as CreateEnvironment & { envVars?: Record<string, unknown> }).envVars ?? {},
|
|
metadata: input.metadata ?? null,
|
|
createdAt: now,
|
|
updatedAt: now,
|
|
})
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null)
|
|
.catch((error) => {
|
|
if (hasConstraintName(error, "environments_name_idx")) {
|
|
throw conflict(`An environment named "${input.name}" already exists for this instance.`);
|
|
}
|
|
if (hasConstraintName(error, "environments_local_driver_idx")) {
|
|
throw conflict("A local environment already exists for this instance.");
|
|
}
|
|
throw error;
|
|
});
|
|
if (!row) {
|
|
throw new Error("Failed to create environment");
|
|
}
|
|
return toEnvironment(row);
|
|
},
|
|
|
|
update: async (
|
|
id: string,
|
|
patch: UpdateEnvironment,
|
|
options?: { db?: EnvironmentWriteDb },
|
|
): Promise<Environment | null> => {
|
|
const writeDb = options?.db ?? db;
|
|
const values: Partial<typeof environments.$inferInsert> = {
|
|
updatedAt: new Date(),
|
|
};
|
|
if (patch.name !== undefined) values.name = patch.name;
|
|
if (patch.description !== undefined) values.description = patch.description ?? null;
|
|
if (patch.driver !== undefined) values.driver = patch.driver;
|
|
if (patch.status !== undefined) values.status = patch.status;
|
|
if (patch.config !== undefined) values.config = patch.config;
|
|
if ("envVars" in patch && patch.envVars !== undefined) {
|
|
values.envVars = (patch.envVars ?? {}) as Record<string, unknown>;
|
|
}
|
|
const changesTarget = patch.config !== undefined || patch.driver !== undefined;
|
|
let metadataUpdate: SQL | undefined;
|
|
if (patch.metadata !== undefined) {
|
|
const userMetadata = withoutManagedEnvironmentArchiveToken(patch.metadata ?? null);
|
|
if (userMetadata) delete userMetadata[SANDBOX_PLATFORM_PROBE_METADATA_KEY];
|
|
if (changesTarget) {
|
|
const replacement = userMetadata === null ? sql`null::jsonb` : sql`${JSON.stringify(userMetadata)}::jsonb`;
|
|
metadataUpdate = preserveInvalidatedSnapshotProofs(replacement);
|
|
} else {
|
|
const replacement = userMetadata === null ? sql`null::jsonb` : sql`${JSON.stringify(userMetadata)}::jsonb`;
|
|
metadataUpdate = sql`case when ${environments.metadata} ? ${SANDBOX_PLATFORM_PROBE_METADATA_KEY}
|
|
then coalesce(${replacement}, '{}'::jsonb) || jsonb_build_object(
|
|
${SANDBOX_PLATFORM_PROBE_METADATA_KEY}::text, ${environments.metadata}->${SANDBOX_PLATFORM_PROBE_METADATA_KEY})
|
|
else ${replacement} end`;
|
|
}
|
|
} else if (changesTarget || patch.status !== undefined) {
|
|
metadataUpdate = sql`${environments.metadata} - ${MANAGED_ENVIRONMENT_ARCHIVE_TOKEN_METADATA_KEY}`;
|
|
if (changesTarget) metadataUpdate = preserveInvalidatedSnapshotProofs(sql`${metadataUpdate} - ${SANDBOX_PLATFORM_PROBE_METADATA_KEY}`);
|
|
}
|
|
|
|
const row = await writeDb
|
|
.update(environments)
|
|
.set({ ...values, ...(metadataUpdate ? { metadata: metadataUpdate } : {}) })
|
|
.where(eq(environments.id, id))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null)
|
|
.catch((error) => {
|
|
if (hasConstraintName(error, "environments_name_idx")) {
|
|
throw conflict(`An environment named "${patch.name}" already exists for this instance.`);
|
|
}
|
|
if (hasConstraintName(error, "environments_local_driver_idx")) {
|
|
throw conflict("A local environment already exists for this instance.");
|
|
}
|
|
throw error;
|
|
});
|
|
return row ? toEnvironment(row) : null;
|
|
},
|
|
|
|
remove: async (id: string): Promise<Environment | null> => {
|
|
const row = await db
|
|
.delete(environments)
|
|
.where(eq(environments.id, id))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
return row ? toEnvironment(row) : null;
|
|
},
|
|
|
|
removeIfDeletable: async (id: string): Promise<Environment | null> => {
|
|
const row = await db
|
|
.delete(environments)
|
|
.where(
|
|
and(
|
|
eq(environments.id, id),
|
|
ne(environments.driver, "local"),
|
|
sql`not exists (
|
|
select 1 from ${instanceSettings}
|
|
where ${instanceSettings.defaultEnvironmentId} = ${environments.id}
|
|
)`,
|
|
// A `pending_cleanup` lease is the durable teardown reference for an
|
|
// orphan sandbox. The environment foreign key uses
|
|
// `on delete set null`, so a delete keeps the lease row but drops its
|
|
// environment reference. This predicate refuses the delete while such
|
|
// a lease exists, so the operator resolves the cleanup first and the
|
|
// lease keeps its environment link. It runs in the same statement as
|
|
// the delete, so it also closes the check-to-delete race.
|
|
sql`not exists (
|
|
select 1 from ${environmentLeases}
|
|
where ${environmentLeases.environmentId} = ${environments.id}
|
|
and ${environmentLeases.status} = 'pending_cleanup'
|
|
)`,
|
|
// A reusable lease keeps a provider sandbox after a run releases
|
|
// it, including when the run failed but release succeeded.
|
|
// Deleting the environment would set its reference to
|
|
// null, and both the normal release path and scoped reusable cleanup
|
|
// require that environment context. Refuse the delete atomically
|
|
// until the owning issue/workspace destroys the reusable sandbox.
|
|
sql`not exists (
|
|
select 1 from ${environmentLeases}
|
|
where ${environmentLeases.environmentId} = ${environments.id}
|
|
and ${environmentLeases.leasePolicy} = 'reuse_by_environment'
|
|
and ${environmentLeases.status} in ('active', 'released', 'retained', 'failed')
|
|
)`,
|
|
),
|
|
)
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
return row ? toEnvironment(row) : null;
|
|
},
|
|
|
|
/**
|
|
* Return true when the environment has one or more leases in the terminal
|
|
* `pending_cleanup` state. Each such lease is the only durable provider
|
|
* reference for an orphan sandbox that a teardown retry must destroy. The
|
|
* delete guard and the provider-change guard call this to protect that
|
|
* reference.
|
|
*/
|
|
hasUnresolvedPendingCleanupLeases: async (environmentId: string): Promise<boolean> => {
|
|
const rows = await db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(environmentLeases)
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.environmentId, environmentId),
|
|
eq(environmentLeases.status, "pending_cleanup"),
|
|
),
|
|
);
|
|
return countFromRows(rows) > 0;
|
|
},
|
|
|
|
getDeleteBlastRadius: async (id: string): Promise<EnvironmentDeleteBlastRadius | null> => {
|
|
const environment = await db
|
|
.select({
|
|
id: environments.id,
|
|
driver: environments.driver,
|
|
})
|
|
.from(environments)
|
|
.where(eq(environments.id, id))
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!environment) return null;
|
|
|
|
const [
|
|
instanceDefaultRows,
|
|
agentDefaultRows,
|
|
executionWorkspaceRows,
|
|
issueRows,
|
|
projectRows,
|
|
secretBindingRows,
|
|
activeLeaseRows,
|
|
pendingCleanupLeaseRows,
|
|
reusableSandboxLeaseRows,
|
|
activeSetupRows,
|
|
] = await Promise.all([
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(instanceSettings)
|
|
.where(eq(instanceSettings.defaultEnvironmentId, id)),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(agents)
|
|
.where(eq(agents.defaultEnvironmentId, id)),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(executionWorkspaces)
|
|
.where(sql`${executionWorkspaces.metadata} -> 'config' ->> 'environmentId' = ${id}`),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(issues)
|
|
.where(sql`${issues.executionWorkspaceSettings} ->> 'environmentId' = ${id}`),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(projects)
|
|
.where(sql`${projects.executionWorkspacePolicy} ->> 'environmentId' = ${id}`),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(companySecretBindings)
|
|
.where(
|
|
and(
|
|
eq(companySecretBindings.targetType, "environment"),
|
|
eq(companySecretBindings.targetId, id),
|
|
),
|
|
),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(environmentLeases)
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.environmentId, id),
|
|
eq(environmentLeases.status, "active"),
|
|
),
|
|
),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(environmentLeases)
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.environmentId, id),
|
|
eq(environmentLeases.status, "pending_cleanup"),
|
|
),
|
|
),
|
|
db
|
|
.select({
|
|
leaseId: environmentLeases.id,
|
|
executionWorkspaceId: environmentLeases.executionWorkspaceId,
|
|
executionWorkspaceName: executionWorkspaces.name,
|
|
issueId: environmentLeases.issueId,
|
|
issueIdentifier: issues.identifier,
|
|
issueTitle: issues.title,
|
|
})
|
|
.from(environmentLeases)
|
|
.leftJoin(executionWorkspaces, eq(environmentLeases.executionWorkspaceId, executionWorkspaces.id))
|
|
.leftJoin(issues, eq(environmentLeases.issueId, issues.id))
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.environmentId, id),
|
|
eq(environmentLeases.leasePolicy, "reuse_by_environment"),
|
|
inArray(environmentLeases.status, ["active", "released", "retained", "failed"]),
|
|
),
|
|
),
|
|
db
|
|
.select({ count: sql<number>`count(*)::int` })
|
|
.from(environmentCustomImageSetupSessions)
|
|
.where(
|
|
and(
|
|
eq(environmentCustomImageSetupSessions.environmentId, id),
|
|
inArray(environmentCustomImageSetupSessions.status, [...ACTIVE_CUSTOM_IMAGE_SETUP_STATUSES]),
|
|
),
|
|
),
|
|
]);
|
|
|
|
const isManagedLocal = environment.driver === "local";
|
|
const isInstanceDefault = countFromRows(instanceDefaultRows) > 0;
|
|
const pendingCleanupLeaseCount = countFromRows(pendingCleanupLeaseRows);
|
|
const reusableSandboxLeaseHolders = reusableSandboxLeaseRows.map((row) => ({
|
|
leaseId: row.leaseId,
|
|
executionWorkspaceId: row.executionWorkspaceId,
|
|
executionWorkspaceName: row.executionWorkspaceName,
|
|
issueId: row.issueId,
|
|
issueIdentifier: row.issueIdentifier,
|
|
issueTitle: row.issueTitle,
|
|
}));
|
|
const reusableSandboxLeaseCount = reusableSandboxLeaseHolders.length;
|
|
const deleteBlockedReasons: EnvironmentDeleteBlockedReason[] = [];
|
|
if (isManagedLocal) deleteBlockedReasons.push("managed_local");
|
|
if (isInstanceDefault) deleteBlockedReasons.push("instance_default");
|
|
// A `pending_cleanup` lease is the durable teardown reference for an orphan
|
|
// sandbox. The environment foreign key uses `on delete set null`, so a
|
|
// delete keeps the lease but drops its environment reference. Block the
|
|
// delete until the sweep resolves the lease, so the operator resolves the
|
|
// cleanup first and the lease keeps its environment link.
|
|
if (pendingCleanupLeaseCount > 0) deleteBlockedReasons.push("pending_sandbox_cleanup");
|
|
if (reusableSandboxLeaseCount > 0) deleteBlockedReasons.push("reusable_sandbox_lease");
|
|
const activeLeaseCount = countFromRows(activeLeaseRows);
|
|
const activeCustomImageSetupSessionCount = countFromRows(activeSetupRows);
|
|
|
|
return {
|
|
environmentId: id,
|
|
canDelete: deleteBlockedReasons.length === 0,
|
|
deleteBlockedReasons,
|
|
pendingCleanupLeaseCount,
|
|
reusableSandboxLeaseCount,
|
|
reusableSandboxLeaseHolders,
|
|
staticReferences: {
|
|
isManagedLocal,
|
|
isInstanceDefault,
|
|
agentDefaultCount: countFromRows(agentDefaultRows),
|
|
executionWorkspaceSelectionCount: countFromRows(executionWorkspaceRows),
|
|
issueSelectionCount: countFromRows(issueRows),
|
|
projectSelectionCount: countFromRows(projectRows),
|
|
secretBindingCount: countFromRows(secretBindingRows),
|
|
},
|
|
activeRuntimeUse: {
|
|
activeLeaseCount,
|
|
activeCustomImageSetupSessionCount,
|
|
hasActiveRuntimeUse: activeLeaseCount > 0 || activeCustomImageSetupSessionCount > 0,
|
|
},
|
|
};
|
|
},
|
|
|
|
listLeases: async (
|
|
environmentId: string,
|
|
filters: {
|
|
status?: string;
|
|
} = {},
|
|
): Promise<EnvironmentLease[]> => {
|
|
const conditions = [eq(environmentLeases.environmentId, environmentId)];
|
|
if (filters.status) conditions.push(eq(environmentLeases.status, filters.status));
|
|
const rows = await db
|
|
.select()
|
|
.from(environmentLeases)
|
|
.where(and(...conditions))
|
|
.orderBy(desc(environmentLeases.lastUsedAt), desc(environmentLeases.createdAt));
|
|
return rows.map(toEnvironmentLease);
|
|
},
|
|
|
|
acquireLease: async (input: {
|
|
companyId: string;
|
|
environmentId: string;
|
|
executionWorkspaceId?: string | null;
|
|
issueId?: string | null;
|
|
heartbeatRunId?: string | null;
|
|
leasePolicy?: EnvironmentLeasePolicy;
|
|
provider?: string | null;
|
|
providerLeaseId?: string | null;
|
|
expiresAt?: Date | null;
|
|
metadata?: Record<string, unknown> | null;
|
|
/**
|
|
* Atomically retire the previous database ownership record when this
|
|
* acquisition reuses the same provider resource for a new run. The
|
|
* provider resume happens before this write, so a failed transaction
|
|
* leaves the prior retained row recoverable instead of publishing two
|
|
* reusable owners for one sandbox.
|
|
*/
|
|
replacesReusableLeaseId?: string | null;
|
|
/**
|
|
* Reactivate the exact lease row already owned by this heartbeat run.
|
|
* Native same-run recovery re-enters environment startup after the
|
|
* provider process is interrupted; it must not manufacture a second
|
|
* database owner for the same run and provider resource.
|
|
*/
|
|
reusesReusableLeaseId?: string | null;
|
|
/**
|
|
* Re-check the environment company binding inside the lease insert
|
|
* transaction. The login routes set this to close the check-to-lease
|
|
* race: managed reconciliation can bind a sandbox to another company
|
|
* between the route guard and this acquire. When the environment is
|
|
* bound to a company other than `companyId`, the insert throws the 403
|
|
* `environment_company_mismatch` and no lease row is created (fail
|
|
* closed). An unbound (instance-global) environment stays open to every
|
|
* member. All other callers keep the plain, non-transactional insert.
|
|
*/
|
|
assertCompanyBinding?: boolean;
|
|
}): Promise<EnvironmentLease> => {
|
|
const now = new Date();
|
|
const values = {
|
|
companyId: input.companyId,
|
|
environmentId: input.environmentId,
|
|
executionWorkspaceId: input.executionWorkspaceId ?? null,
|
|
issueId: input.issueId ?? null,
|
|
heartbeatRunId: input.heartbeatRunId ?? null,
|
|
status: "active" as const,
|
|
leasePolicy: input.leasePolicy ?? "ephemeral",
|
|
provider: input.provider ?? null,
|
|
providerLeaseId: input.providerLeaseId ?? null,
|
|
acquiredAt: now,
|
|
lastUsedAt: now,
|
|
expiresAt: input.expiresAt ?? null,
|
|
releasedAt: null,
|
|
failureReason: null,
|
|
cleanupStatus: null,
|
|
metadata: withoutCleanupVerification(input.metadata),
|
|
createdAt: now,
|
|
updatedAt: now,
|
|
};
|
|
if (
|
|
(input.replacesReusableLeaseId || input.reusesReusableLeaseId) &&
|
|
((!input.executionWorkspaceId && (!input.issueId || typeof input.metadata?.agentId !== "string")) || !input.providerLeaseId)
|
|
) {
|
|
throw new Error(
|
|
"A reusable lease handoff requires a workspace or agent-bound task, and a provider lease id.",
|
|
);
|
|
}
|
|
if (input.reusesReusableLeaseId && !input.heartbeatRunId) {
|
|
throw new Error(
|
|
"A same-run reusable lease reacquisition requires a heartbeat run id.",
|
|
);
|
|
}
|
|
if (input.replacesReusableLeaseId && input.reusesReusableLeaseId) {
|
|
throw new Error(
|
|
"A reusable lease cannot be replaced and reacquired in the same operation.",
|
|
);
|
|
}
|
|
const row =
|
|
input.assertCompanyBinding ||
|
|
input.replacesReusableLeaseId ||
|
|
input.reusesReusableLeaseId
|
|
? await db.transaction(async (tx) => {
|
|
if (input.assertCompanyBinding) {
|
|
// Lock the environment row first. Managed reconciliation locks the
|
|
// same sandbox environment rows with `for update` before it writes a
|
|
// company binding, so this lock serializes the two transactions on
|
|
// this row and closes the time-of-check to time-of-use window.
|
|
await tx
|
|
.select({ id: environments.id })
|
|
.from(environments)
|
|
.where(eq(environments.id, input.environmentId))
|
|
.for("update");
|
|
// Re-read the company binding inside the locked transaction. A
|
|
// binding a reconciliation committed after the route guard now
|
|
// appears here. Reject a foreign-company environment before the
|
|
// insert, so the login holds no lease.
|
|
const boundRows = await tx
|
|
.select({ companyId: builtInManagedResources.companyId })
|
|
.from(builtInManagedResources)
|
|
.where(
|
|
and(
|
|
eq(
|
|
builtInManagedResources.resourceKind,
|
|
MANAGED_ENVIRONMENT_RESOURCE_KIND,
|
|
),
|
|
eq(
|
|
builtInManagedResources.resourceId,
|
|
input.environmentId,
|
|
),
|
|
),
|
|
);
|
|
const boundCompanyIds = Array.from(
|
|
new Set(boundRows.map((boundRow) => boundRow.companyId)),
|
|
);
|
|
if (
|
|
boundCompanyIds.length > 0 &&
|
|
!boundCompanyIds.includes(input.companyId)
|
|
) {
|
|
throw forbidden(
|
|
"The selected environment belongs to another company.",
|
|
{
|
|
code: "environment_company_mismatch",
|
|
},
|
|
);
|
|
}
|
|
}
|
|
if (input.replacesReusableLeaseId) {
|
|
const retired = await tx
|
|
.update(environmentLeases)
|
|
.set({
|
|
status: "expired",
|
|
releasedAt: now,
|
|
lastUsedAt: now,
|
|
updatedAt: now,
|
|
cleanupStatus: "success",
|
|
})
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.id, input.replacesReusableLeaseId),
|
|
eq(environmentLeases.companyId, input.companyId),
|
|
eq(environmentLeases.environmentId, input.environmentId),
|
|
input.executionWorkspaceId
|
|
? eq(environmentLeases.executionWorkspaceId, input.executionWorkspaceId)
|
|
: and(
|
|
isNull(environmentLeases.executionWorkspaceId),
|
|
eq(environmentLeases.issueId, input.issueId!),
|
|
sql`${environmentLeases.metadata}->>'agentId' = ${input.metadata!.agentId}`,
|
|
),
|
|
eq(environmentLeases.leasePolicy, "reuse_by_environment"),
|
|
eq(
|
|
environmentLeases.providerLeaseId,
|
|
input.providerLeaseId!,
|
|
),
|
|
inArray(environmentLeases.status, [
|
|
"released",
|
|
"retained",
|
|
]),
|
|
),
|
|
)
|
|
.returning({ id: environmentLeases.id });
|
|
if (retired.length !== 1) {
|
|
throw conflict(
|
|
"Reusable sandbox lease ownership changed during acquisition.",
|
|
);
|
|
}
|
|
}
|
|
if (input.reusesReusableLeaseId) {
|
|
const reacquired = await tx
|
|
.update(environmentLeases)
|
|
.set({
|
|
status: "active",
|
|
releasedAt: null,
|
|
lastUsedAt: now,
|
|
expiresAt: input.expiresAt ?? null,
|
|
failureReason: null,
|
|
cleanupStatus: null,
|
|
metadata: withoutCleanupVerification(input.metadata),
|
|
updatedAt: now,
|
|
})
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.id, input.reusesReusableLeaseId),
|
|
eq(environmentLeases.companyId, input.companyId),
|
|
eq(environmentLeases.environmentId, input.environmentId),
|
|
input.executionWorkspaceId
|
|
? eq(environmentLeases.executionWorkspaceId, input.executionWorkspaceId)
|
|
: and(
|
|
isNull(environmentLeases.executionWorkspaceId),
|
|
eq(environmentLeases.issueId, input.issueId!),
|
|
sql`${environmentLeases.metadata}->>'agentId' = ${input.metadata!.agentId}`,
|
|
),
|
|
eq(
|
|
environmentLeases.heartbeatRunId,
|
|
input.heartbeatRunId!,
|
|
),
|
|
eq(environmentLeases.leasePolicy, "reuse_by_environment"),
|
|
eq(
|
|
environmentLeases.providerLeaseId,
|
|
input.providerLeaseId!,
|
|
),
|
|
inArray(environmentLeases.status, [
|
|
"active",
|
|
"released",
|
|
"retained",
|
|
]),
|
|
),
|
|
)
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!reacquired) {
|
|
throw conflict(
|
|
"Reusable sandbox lease ownership changed during reacquisition.",
|
|
);
|
|
}
|
|
return reacquired;
|
|
}
|
|
return tx
|
|
.insert(environmentLeases)
|
|
.values(values)
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
})
|
|
: await db
|
|
.insert(environmentLeases)
|
|
.values(values)
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
if (!row) {
|
|
throw new Error("Failed to acquire environment lease");
|
|
}
|
|
return toEnvironmentLease(row);
|
|
},
|
|
|
|
releaseLease: async (
|
|
id: string,
|
|
status: Extract<EnvironmentLeaseStatus, "released" | "expired" | "failed" | "retained" | "pending_cleanup"> = "released",
|
|
options?: {
|
|
expectedPendingCleanupAttemptId?: string;
|
|
failureReason?: string;
|
|
cleanupStatus?: EnvironmentLeaseCleanupStatus;
|
|
remoteExecutionTermination?: Record<string, unknown>;
|
|
},
|
|
) => {
|
|
const now = new Date();
|
|
const releaseMetadata = options?.remoteExecutionTermination
|
|
? sql`coalesce(${environmentLeases.metadata}, '{}'::jsonb) || ${JSON.stringify({ remoteExecutionTermination: options.remoteExecutionTermination })}::jsonb`
|
|
: sql`${environmentLeases.metadata} - 'remoteExecutionTermination'`;
|
|
const cleanupSettled = options?.expectedPendingCleanupAttemptId && options.cleanupStatus === "success"
|
|
&& status !== "pending_cleanup";
|
|
const row = await writeEnvironmentCleanup(db, tx => tx
|
|
.update(environmentLeases)
|
|
.set({
|
|
status,
|
|
releasedAt: status === "retained" ? null : now,
|
|
lastUsedAt: now,
|
|
updatedAt: now,
|
|
...(options?.failureReason !== undefined ? { failureReason: options.failureReason } : {}),
|
|
...(options?.cleanupStatus !== undefined ? { cleanupStatus: options.cleanupStatus } : {}),
|
|
// A later release without a receipt cannot reuse an earlier stop's
|
|
// authority (for example after a same-run lease resume).
|
|
metadata: cleanupSettled
|
|
? sql`coalesce(${releaseMetadata}, '{}'::jsonb) || '{"pendingCleanupInFlight":false,"pendingCleanupLeaseExpiresAtMs":0}'::jsonb`
|
|
: releaseMetadata,
|
|
})
|
|
.where(and(eq(environmentLeases.id, id), options?.expectedPendingCleanupAttemptId
|
|
? and(eq(environmentLeases.status, "pending_cleanup"),
|
|
sql`${environmentLeases.metadata}->>'pendingCleanupAttemptId' = ${options.expectedPendingCleanupAttemptId}`)
|
|
: undefined))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null));
|
|
return row ? toEnvironmentLease(row) : null;
|
|
},
|
|
|
|
/**
|
|
* Record a lease-less orphan sandbox directly in the terminal
|
|
* `pending_cleanup` state with one atomic insert. The sweep reads a row with
|
|
* status `pending_cleanup` and cleanup status `failed`, so this insert makes
|
|
* the orphan visible to recovery immediately. It never passes through the
|
|
* `active` state, so a process or database crash cannot strand the row in an
|
|
* intermediate state that no sweep finds. The insert skips the company
|
|
* binding assertion, so it records the orphan even for a foreign-bound
|
|
* environment.
|
|
*
|
|
* The insert runs in a transaction that first locks the environment row with
|
|
* `for update`. The delete path (`removeIfDeletable`) refuses a delete while a
|
|
* `pending_cleanup` lease exists, so this lock serializes the two writes:
|
|
*
|
|
* - The environment still exists: the insert records the orphan with the
|
|
* environment reference. A concurrent delete blocks on the lock, then its
|
|
* `not exists (pending_cleanup)` predicate fails, so the delete refuses.
|
|
* - The environment is already gone (a delete won the race before this
|
|
* insert): the insert records the orphan with a null environment
|
|
* reference. The row carries the immutable provider metadata the sweep
|
|
* needs, so the teardown still runs. This closes the window the finding
|
|
* describes, where the foreign-key insert fails after a delete.
|
|
*/
|
|
insertPendingCleanupLease: async (input: {
|
|
companyId: string;
|
|
environmentId: string;
|
|
executionWorkspaceId?: string | null;
|
|
issueId?: string | null;
|
|
heartbeatRunId?: string | null;
|
|
provider?: string | null;
|
|
providerLeaseId?: string | null;
|
|
metadata?: Record<string, unknown> | null;
|
|
failureReason: string;
|
|
}): Promise<EnvironmentLease> => {
|
|
const now = new Date();
|
|
const row = await db.transaction(async (tx) => {
|
|
// Lock the environment row so a concurrent delete cannot commit between
|
|
// this read and the insert. An absent row means a delete already removed
|
|
// the environment, so record the orphan with a null reference.
|
|
const environmentRows = await tx
|
|
.select({ id: environments.id })
|
|
.from(environments)
|
|
.where(eq(environments.id, input.environmentId))
|
|
.for("update");
|
|
const environmentIdForRow = environmentRows[0]?.id ?? null;
|
|
await notifyEnvironmentCleanup(tx);
|
|
return tx
|
|
.insert(environmentLeases)
|
|
.values({
|
|
companyId: input.companyId,
|
|
environmentId: environmentIdForRow,
|
|
executionWorkspaceId: input.executionWorkspaceId ?? null,
|
|
issueId: input.issueId ?? null,
|
|
heartbeatRunId: input.heartbeatRunId ?? null,
|
|
status: "pending_cleanup" as const,
|
|
leasePolicy: "ephemeral",
|
|
provider: input.provider ?? null,
|
|
providerLeaseId: input.providerLeaseId ?? null,
|
|
acquiredAt: now,
|
|
lastUsedAt: now,
|
|
expiresAt: null,
|
|
releasedAt: now,
|
|
failureReason: input.failureReason,
|
|
cleanupStatus: "failed",
|
|
metadata: withoutCleanupVerification(input.metadata),
|
|
createdAt: now,
|
|
updatedAt: now,
|
|
})
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null);
|
|
});
|
|
if (!row) {
|
|
throw new Error("Failed to record pending sandbox cleanup lease");
|
|
}
|
|
return toEnvironmentLease(row);
|
|
},
|
|
|
|
updateLeaseMetadata: async (
|
|
id: string,
|
|
metadata: Record<string, unknown> | null,
|
|
): Promise<EnvironmentLease | null> => {
|
|
const row = await writeEnvironmentCleanup(db, tx => tx
|
|
.update(environmentLeases)
|
|
.set({
|
|
metadata: withoutCleanupVerification(metadata),
|
|
lastUsedAt: new Date(),
|
|
updatedAt: new Date(),
|
|
})
|
|
.where(eq(environmentLeases.id, id))
|
|
.returning()
|
|
.then((rows) => rows[0] ?? null));
|
|
return row ? toEnvironmentLease(row) : null;
|
|
},
|
|
|
|
releaseLeasesForRun: async (
|
|
heartbeatRunId: string,
|
|
status: Extract<EnvironmentLeaseStatus, "released" | "expired" | "failed"> = "released",
|
|
): Promise<EnvironmentLease[]> => {
|
|
const now = new Date();
|
|
const rows = await writeEnvironmentCleanup(db, tx => tx
|
|
.update(environmentLeases)
|
|
.set({
|
|
status,
|
|
releasedAt: now,
|
|
lastUsedAt: now,
|
|
updatedAt: now,
|
|
})
|
|
.where(
|
|
and(
|
|
eq(environmentLeases.heartbeatRunId, heartbeatRunId),
|
|
eq(environmentLeases.status, "active"),
|
|
),
|
|
)
|
|
.returning());
|
|
return rows.map(toEnvironmentLease);
|
|
},
|
|
};
|
|
}
|