mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-03 17:51:58 +01:00
## Thinking Path > - Paperclip must keep admitted remote work alive while its main server is replaced. > - Runner owns recovery mechanics and exposes opaque checkpoints through #17097. > - The server owns company scope, encryption, Stop, tool authority and execution ownership. > - A successor must prove current ownership before it adopts the original execution. > - Checkpoint bursts must also leave capacity for normal requests and lease renewal. > - This PR persists and adopts that authority through the existing runtime boundaries. ## Linked Issues or Issue Description **What existing behavior does this improve?** Remote agents retain the original execution during a bounded main-server outage. **Current behavior** A server restart can lose the controller's local state and connection. An unsafe replacement could repeat a turn or an uncertain mutation. Checkpoint writes in the request pool can also delay ordinary requests during an aligned burst. **Proposed behavior** Restore encrypted control records from Postgres and adopt the original runner under a fenced lease. Recover known tool receipts through current tool authority. Give control checkpoints a shared pool capped at two connections per database owner. Depends on #17097. Successors are #17455 and #17456. Qualification and presentation remain separate review slices. ## What Changed - Add company/run-bound encrypted checkpoint records and migration 0394. Keep the SQL idempotent after renumbering against current master. - Recover startup and expired ownership through native runtime and heartbeat. Preserve the sandbox lease, admitted runner artifact, harness configuration, native session and active turn. - Keep Stop, finalization, preparation ownership and stale-writer fencing transactional. Preserve graceful detach and natural crash takeover. - Recover committed tool receipts through the existing authority. Reauthorize reads and hold uncertain mutations. - Bound startup retention with the existing coordinator and preserve zero idle scans. - Share at most two checkpoint connections per database client. Keep application and liveness capacity separate. Close the checkpoint pool during shutdown; late writes cannot reopen it. - Count SQL across both application and checkpoint clients. Prove request/liveness progress, command recovery and failure after pool shutdown with real Postgres. ## Verification Project creation recovery now uses the existing project activity receipt owner. It retains authenticated input normalization, fingerprint checks and current run authority after the receipt lock. An absent receipt returns no result before mutation. The new lost-HTTP-response and no-effect regression uses real API routes and Postgres. The seven transport cases pass locally. This Mac skips all 20 database cases. On current source `5de803c2cd`, Linux [job 122593415890](https://github.com/paperclipai/paperclip/actions/runs/40620576702/job/122593415890) executes all 20 project-tool cases successfully (9.480 seconds), including the committed-project lost-response regression. Its shard passes 1,627 cases with three unrelated skips. Server typecheck passes. The transport regression initially has two failures; a subsequent incorrect expectation about schema defaults was corrected before the final pass. Ordinary execution adds no checkpoint writes or recurring work. Current candidate `5de803c2cd` includes the project-creation receipt recovery fix and master `2cd747d1b6`. Migration 0394 retains the prior idempotent checkpoint DDL. Every master SQL file and journal entry is preserved. Snapshots 0390–0394, migration checks and server typecheck pass. The ordinary warm-turn regression fails on its second turn before `a219ab51ad`. After correction, three completed warm turns select the correct prior checkpoint and preserve the original session. All 288 provider-wiring cases pass. The control plane, external persistence callback, identity rotation and filesystem are real; the backend and database-load seam are scripted. The 13 warm admission/configuration variants also pass after final master integration. This does not qualify an underlying harness. At current source `5de803c2cd`, Linux [job 122593415907](https://github.com/paperclipai/paperclip/actions/runs/40620576702/job/122593415907) passes all 940 native-session-executor cases (61.431 seconds), including the warm external-checkpoint behavior; the shard passes 2,358 cases with one skip. Current [Runner job 122593415475](https://github.com/paperclipai/paperclip/actions/runs/40620576702/job/122593415475) passes the native recovery lane: 115 passes and five container-only skips, including the encrypted restore guard, fresh preparation (63.189 seconds), blocked claim lock (1.226 seconds) and recovery beyond 101 blocked owners (3.897 seconds). The first lane passes 2,215 cases with one skip. The SQL cost test reports zero idle and streaming SQL for both output volumes; this is component evidence, not a production capacity claim. At prior candidate `1ff7bb44f4`, Linux job 122549307215 passes all 938 native-executor cases, including the three-turn external-checkpoint regression. Job 122549306469 passes the native recovery lane with 115 passes and five container-only skips, including the encrypted-restore session guard, fresh preparation (63.664 seconds), claim-lock contention (3.961 seconds), and 101-owner recovery (3.824 seconds). This Mac skips the real-Postgres suite. The earlier full local executor attempt has 921 passes and 16 failures during embedded-Postgres initialization before assertions. The original fixture collisions and their corrections remain recorded. At earlier candidate `8fbe62b41d`, server shard job 122535673841 has 3,876 passes, one failure and one skip in an unchanged expiry-worker retry/drain timing test. The same server/database tree on qualification source `b64cac6951` passes all 20 expiry cases and all 3,877 shard cases. The single diagnostic retry, job 122541891915, passes all 20 expiry cases and all 3,877 shard cases (one skip). No assertion was weakened. The original failure remains recorded and its exact timing race is not proven. All Actions checks and legacy status passed on `8fbe62b41d`, with completed Greptile 5/5 and no open feedback. The next candidate `1ff7bb44f4` also passed all Actions checks and Greptile 5/5. Its Paperclip Review remained queued before the new master conflict required integration. The new candidate needs fresh exact-head CI and reviews; old checks do not qualify it. Migration generation is checkpoint-only, all master SQL and journal entries remain unchanged, and migration checks, server typecheck and all 13 warm-owner variants pass after integration. The first migration check was blocked by TSX sandbox IPC; its permitted repeat passes. The first warm-test command used an incorrect path and ran no tests; the corrected command supplies the 13-case receipt. All 16 database pool-lifetime/options/teardown cases pass after granting loopback permission; the first batch had two EPERM failures and 14 passes. Earlier semantic-tool/HTTP recovery, adoption, encryption-batch, zero-streaming-write and idle-SQL receipts remain source-attributed in the [qualification record](https://github.com/paperclipai/paperclip/blob/2ff66f57da0da35bac1c19a2366ea4b84d87a986/doc/plans/2026-10-22-hot-upgrade-qualification.md). That record retains earlier assertion, setup and cleanup failures and their corrections. No failed gate is waived. The historical 300-session component campaign passes four after phases: steady read p99 is 107–108 ms at 500 reads/s and 100 writes/s; aligned-burst read p99 is 103–105 ms after the bounded pool, versus 584–689 ms before. This comparison isolates the persistence corrections. It does not measure the final stack's hosted active-agent capacity. The hosted zero-agent API pair leaves SQL and CPU essentially unchanged, but both arms fail absolute latency gates and candidate peak cgroup memory fails its gate. The active-agent/viewer matrix, different-artifact upgrade and rollback remain open. Run `PAPERCLIP_TEST_DATABASE_URL=<owned-disposable-postgres> pnpm --filter @paperclipai/server exec vitest run src/services/native-runtime/native-runner-restart-recovery.integration.test.ts`. Previous head `f2db8a6568` had one failed workspace setup gate: [job 122555672441](https://github.com/paperclipai/paperclip/actions/runs/40608984238/job/122555672441) passes all 4,169 UI tests and 285 CLI cases (one skip), but the company import/export suite reaches its 30-second health deadline during doctor startup. Its output does not reach the server-start step. The CLI, server, database, shared, adapter and plugin trees are identical on qualification source `a866619d7b`, whose [job 122555886663](https://github.com/paperclipai/paperclip/actions/runs/40609057937/job/122555886663) passes that fixture and all 286 CLI cases. The one diagnostic retry, [job 122561057225](https://github.com/paperclipai/paperclip/actions/runs/40608984238/job/122561057225), passes the formerly failing fixture and all 286 CLI cases. All Actions checks and legacy status on `f2db8a6568` pass. Its exact-head Greptile completed at 5/5 with no open feedback. The current integrated head requires fresh checks and a completed Paperclip Review before merge. The original failure remains recorded; its exact timing cause is unproven. A repeated failure requires investigation and repair rather than another retry. All current-head CI, legacy status, exact-head completed Greptile 5/5, resolved feedback and ordinary GitHub merge eligibility remain required before merge. The latest integration preserves master’s published Copilot v70 profiles and every published migration. Checkpoint migration `0394_conscious_whizzer.sql` was generated with `pnpm db:generate` and retains the prior idempotent DDL. The Runner vendor rebuild and replay parity checks pass. Server typecheck and all 13 warm-owner variants pass after that rebuild. The imported report-lock patch is byte-identical to master; its intentional patch-context whitespace is retained, and the feature delta passes whitespace checks. No hosted experiment was run. ## Risks The pool adds up to two active connections per instance, shared across agents. Checkpoint delivery can wait behind that bound; it still requires its commit. Steady component-test Postgres CPU rises by about 1.7 percentage points of a two-CPU allocation. These corrections do not remove the stack's control and renewal writes. The migration and key must survive replacement. Fresh-database tests and local load do not establish different-artifact hosted upgrade or rollback continuity. ## Model Used OpenAI GPT-6 through Codex, with reasoning, repository tools and code execution. The runtime does not expose a more specific 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 - [ ] 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 - [ ] All Paperclip CI gates are green - [ ] 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>
921 lines
36 KiB
TypeScript
921 lines
36 KiB
TypeScript
import { beforeEach, describe, expect, it, vi } from "vitest";
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Hoisted mocks — must be declared before any imports that reference them
|
|
// ---------------------------------------------------------------------------
|
|
|
|
const mockResolveEnvironmentExecutionTarget = vi.hoisted(() => vi.fn());
|
|
const mockAdapterExecutionTargetToRemoteSpec = vi.hoisted(() => vi.fn());
|
|
const mockBuildWorkspaceRealizationRequest = vi.hoisted(() => vi.fn());
|
|
const mockUpdateLeaseMetadata = vi.hoisted(() => vi.fn());
|
|
const mockUpdateExecutionWorkspace = vi.hoisted(() => vi.fn());
|
|
const mockLogActivity = vi.hoisted(() => vi.fn());
|
|
const mockLoggerInfo = vi.hoisted(() => vi.fn());
|
|
const mockGetEnvironment = vi.hoisted(() => vi.fn());
|
|
const mockGetLease = vi.hoisted(() => vi.fn());
|
|
|
|
vi.mock("../services/environment-execution-target.js", () => ({
|
|
resolveEnvironmentExecutionTarget: mockResolveEnvironmentExecutionTarget,
|
|
resolveEnvironmentExecutionTransport: vi.fn().mockResolvedValue(null),
|
|
}));
|
|
|
|
vi.mock("@paperclipai/adapter-utils/execution-target", () => ({
|
|
adapterExecutionTargetToRemoteSpec: mockAdapterExecutionTargetToRemoteSpec,
|
|
}));
|
|
|
|
vi.mock("../services/workspace-realization.js", () => ({
|
|
buildWorkspaceRealizationRequest: mockBuildWorkspaceRealizationRequest,
|
|
}));
|
|
|
|
vi.mock("../services/environments.js", () => ({
|
|
environmentService: vi.fn(() => ({
|
|
ensureLocalEnvironment: vi.fn(),
|
|
getById: mockGetEnvironment,
|
|
getLeaseById: mockGetLease,
|
|
acquireLease: vi.fn(),
|
|
releaseLease: vi.fn(),
|
|
updateLeaseMetadata: mockUpdateLeaseMetadata,
|
|
})),
|
|
}));
|
|
|
|
vi.mock("../services/execution-workspaces.js", () => ({
|
|
executionWorkspaceService: vi.fn(() => ({
|
|
update: mockUpdateExecutionWorkspace,
|
|
})),
|
|
}));
|
|
|
|
vi.mock("../services/activity-log.js", () => ({
|
|
logActivity: mockLogActivity,
|
|
}));
|
|
|
|
vi.mock("../middleware/logger.js", () => ({
|
|
logger: {
|
|
info: mockLoggerInfo,
|
|
warn: vi.fn(),
|
|
error: vi.fn(),
|
|
debug: vi.fn(),
|
|
},
|
|
}));
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Imports after mocks
|
|
// ---------------------------------------------------------------------------
|
|
|
|
import {
|
|
environmentRunOrchestrator,
|
|
EnvironmentRunError,
|
|
} from "../services/environment-run-orchestrator.ts";
|
|
import type { Environment, EnvironmentLease, ExecutionWorkspace } from "@paperclipai/shared";
|
|
import type { RealizedExecutionWorkspace } from "../services/workspace-runtime.ts";
|
|
import type { EnvironmentRuntimeService } from "../services/environment-runtime.ts";
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Fixtures
|
|
// ---------------------------------------------------------------------------
|
|
|
|
function makeEnvironment(driver: string = "local"): Environment {
|
|
return {
|
|
id: "env-1",
|
|
companyId: "company-1",
|
|
name: "Test Environment",
|
|
description: null,
|
|
driver: driver as Environment["driver"],
|
|
status: "active",
|
|
config: {},
|
|
metadata: null,
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
};
|
|
}
|
|
|
|
function makeLease(overrides: Partial<EnvironmentLease> = {}): EnvironmentLease {
|
|
return {
|
|
id: "lease-1",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
status: "active",
|
|
leasePolicy: "ephemeral",
|
|
provider: "local",
|
|
providerLeaseId: null,
|
|
acquiredAt: new Date(),
|
|
lastUsedAt: new Date(),
|
|
expiresAt: null,
|
|
releasedAt: null,
|
|
failureReason: null,
|
|
cleanupStatus: null,
|
|
metadata: null,
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function makeExecutionWorkspace(cwd: string = "/workspace/project"): RealizedExecutionWorkspace {
|
|
return {
|
|
baseCwd: "/workspace",
|
|
source: "project_primary",
|
|
projectId: "project-1",
|
|
workspaceId: "ws-1",
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
cwd,
|
|
branchName: null,
|
|
worktreePath: null,
|
|
warnings: [],
|
|
created: false,
|
|
};
|
|
}
|
|
|
|
function makePersistedExecutionWorkspace(
|
|
overrides: Partial<ExecutionWorkspace> = {},
|
|
): ExecutionWorkspace {
|
|
return {
|
|
id: "ew-1",
|
|
companyId: "company-1",
|
|
projectId: "project-1",
|
|
projectWorkspaceId: null,
|
|
sourceIssueId: null,
|
|
mode: "standard",
|
|
strategyType: "project_primary",
|
|
name: "workspace",
|
|
status: "open",
|
|
cwd: "/workspace/project",
|
|
repoUrl: null,
|
|
baseRef: null,
|
|
branchName: null,
|
|
providerType: "local",
|
|
providerRef: null,
|
|
derivedFromExecutionWorkspaceId: null,
|
|
lastUsedAt: new Date(),
|
|
openedAt: new Date(),
|
|
closedAt: null,
|
|
cleanupEligibleAt: null,
|
|
cleanupReason: null,
|
|
config: null,
|
|
metadata: null,
|
|
createdAt: new Date(),
|
|
updatedAt: new Date(),
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
function makeRealizeInput(overrides: {
|
|
environment?: Environment;
|
|
lease?: EnvironmentLease;
|
|
persistedExecutionWorkspace?: ExecutionWorkspace | null;
|
|
} = {}): Parameters<ReturnType<typeof environmentRunOrchestrator>["realizeForRun"]>[0] {
|
|
return {
|
|
environment: overrides.environment ?? makeEnvironment("local"),
|
|
lease: overrides.lease ?? makeLease(),
|
|
adapterType: "claude_local",
|
|
companyId: "company-1",
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
executionWorkspace: makeExecutionWorkspace(),
|
|
effectiveExecutionWorkspaceMode: null,
|
|
persistedExecutionWorkspace: overrides.persistedExecutionWorkspace !== undefined
|
|
? overrides.persistedExecutionWorkspace
|
|
: null,
|
|
};
|
|
}
|
|
|
|
function makeMockRuntime(overrides: Partial<EnvironmentRuntimeService> = {}): EnvironmentRuntimeService {
|
|
return {
|
|
acquireRunLease: vi.fn(),
|
|
releaseRunLeases: vi.fn(),
|
|
execute: vi.fn().mockResolvedValue({
|
|
exitCode: 0,
|
|
signal: null,
|
|
timedOut: false,
|
|
stdout: "",
|
|
stderr: "",
|
|
}),
|
|
realizeWorkspace: vi.fn().mockResolvedValue({
|
|
cwd: "/workspace/project",
|
|
metadata: {
|
|
workspaceRealization: {
|
|
version: 1,
|
|
mode: "copy",
|
|
authoritativeRoot: "/workspace/project",
|
|
pathAliases: [],
|
|
outboundRestorePaths: [],
|
|
driver: "local",
|
|
cwd: "/workspace/project",
|
|
},
|
|
},
|
|
}),
|
|
...overrides,
|
|
} as unknown as EnvironmentRuntimeService;
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Tests
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describe("environmentRunOrchestrator — realizeForRun", () => {
|
|
const mockDb = {} as any;
|
|
|
|
beforeEach(() => {
|
|
vi.clearAllMocks();
|
|
|
|
mockBuildWorkspaceRealizationRequest.mockReturnValue({
|
|
version: 1,
|
|
adapterType: "claude_local",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
requestedMode: null,
|
|
source: {
|
|
kind: "project_primary",
|
|
localPath: "/workspace/project",
|
|
projectId: null,
|
|
projectWorkspaceId: null,
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
branchName: null,
|
|
worktreePath: null,
|
|
},
|
|
runtimeOverlay: {
|
|
provisionCommand: null,
|
|
},
|
|
});
|
|
|
|
mockAdapterExecutionTargetToRemoteSpec.mockReturnValue({
|
|
kind: "local",
|
|
environmentId: "env-1",
|
|
leaseId: "lease-1",
|
|
});
|
|
|
|
mockUpdateLeaseMetadata.mockResolvedValue(null);
|
|
mockUpdateExecutionWorkspace.mockResolvedValue(null);
|
|
mockLogActivity.mockResolvedValue(undefined);
|
|
});
|
|
|
|
it.each([false, true])("only requests active-work cancellation for explicit Stop: %s", async (cancelActiveWork) => {
|
|
const releaseRunLeases = vi.fn().mockResolvedValue([]);
|
|
const runtime = makeMockRuntime({ releaseRunLeases });
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
await orchestrator.releaseForRun({
|
|
heartbeatRunId: "run-1", companyId: "company-1", agentId: "agent-1",
|
|
providerResourceDisposition: "stop_and_retain", cancelActiveWork,
|
|
});
|
|
expect(releaseRunLeases).toHaveBeenCalledWith(
|
|
"run-1", "released", expect.any(Function), "stop_and_retain",
|
|
...(cancelActiveWork ? [true] : []),
|
|
);
|
|
});
|
|
|
|
it("happy path: returns lease, executionTarget, and remoteExecution on successful realization", async () => {
|
|
const executionTarget = { kind: "local", environmentId: "env-1", leaseId: "lease-1" };
|
|
const remoteExecution = { kind: "local", environmentId: "env-1", leaseId: "lease-1" };
|
|
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue(executionTarget);
|
|
mockAdapterExecutionTargetToRemoteSpec.mockReturnValue(remoteExecution);
|
|
|
|
const runtime = makeMockRuntime();
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
const result = await orchestrator.realizeForRun(makeRealizeInput());
|
|
|
|
expect(result.lease).toBeDefined();
|
|
expect(result.executionTarget).toEqual({
|
|
...executionTarget,
|
|
workspaceRealization: {
|
|
mode: "copy",
|
|
authoritativeRoot: "/workspace/project",
|
|
pathAliases: [],
|
|
outboundRestorePaths: [],
|
|
},
|
|
});
|
|
expect(result.remoteExecution).toEqual(remoteExecution);
|
|
expect(result.workspaceRealization).toEqual(
|
|
expect.objectContaining({ version: 1, driver: "local" }),
|
|
);
|
|
|
|
expect(runtime.realizeWorkspace).toHaveBeenCalledOnce();
|
|
expect(mockResolveEnvironmentExecutionTarget).toHaveBeenCalledOnce();
|
|
});
|
|
|
|
it("uses an in-place authoritative root on the adapter execution target", async () => {
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({
|
|
kind: "remote",
|
|
transport: "sandbox",
|
|
remoteCwd: "/copied/workspace",
|
|
});
|
|
const runtime = makeMockRuntime({
|
|
realizeWorkspace: vi.fn().mockResolvedValue({
|
|
cwd: "/app",
|
|
metadata: {
|
|
workspaceRealization: {
|
|
version: 1,
|
|
mode: "in_place",
|
|
authoritativeRoot: "/app",
|
|
pathAliases: [],
|
|
outboundRestorePaths: [],
|
|
},
|
|
},
|
|
}),
|
|
});
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
const result = await orchestrator.realizeForRun(
|
|
makeRealizeInput({ environment: makeEnvironment("sandbox") }),
|
|
);
|
|
|
|
expect(result.executionTarget).toEqual(expect.objectContaining({
|
|
kind: "remote",
|
|
transport: "sandbox",
|
|
remoteCwd: "/app",
|
|
workspaceRealization: {
|
|
mode: "in_place",
|
|
authoritativeRoot: "/app",
|
|
pathAliases: [],
|
|
outboundRestorePaths: [],
|
|
},
|
|
}));
|
|
});
|
|
|
|
it("realization failure: runtime.realizeWorkspace throws → EnvironmentRunError with code workspace_realization_failed", async () => {
|
|
const runtime = makeMockRuntime({
|
|
realizeWorkspace: vi.fn().mockRejectedValue(new Error("sandbox unreachable")),
|
|
});
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await expect(orchestrator.realizeForRun(makeRealizeInput())).rejects.toSatisfy(
|
|
(err: unknown) =>
|
|
err instanceof EnvironmentRunError &&
|
|
err.code === "workspace_realization_failed" &&
|
|
err.environmentId === "env-1" &&
|
|
err.driver === "local",
|
|
);
|
|
|
|
expect(mockResolveEnvironmentExecutionTarget).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("target resolution failure: resolveEnvironmentExecutionTarget throws → EnvironmentRunError with code transport_resolution_failed", async () => {
|
|
mockResolveEnvironmentExecutionTarget.mockRejectedValue(new Error("network error"));
|
|
|
|
const runtime = makeMockRuntime();
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await expect(orchestrator.realizeForRun(makeRealizeInput())).rejects.toSatisfy(
|
|
(err: unknown) =>
|
|
err instanceof EnvironmentRunError &&
|
|
err.code === "transport_resolution_failed" &&
|
|
err.environmentId === "env-1",
|
|
);
|
|
});
|
|
|
|
it("non-sandbox driver skips workspace realization and goes straight to target resolution", async () => {
|
|
const environment = makeEnvironment("plugin" as Environment["driver"]);
|
|
const executionTarget = null;
|
|
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue(executionTarget);
|
|
|
|
const runtime = makeMockRuntime();
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
const result = await orchestrator.realizeForRun(
|
|
makeRealizeInput({ environment }),
|
|
);
|
|
|
|
expect(runtime.realizeWorkspace).not.toHaveBeenCalled();
|
|
expect(result.workspaceRealization).toEqual({});
|
|
expect(result.executionTarget).toBeNull();
|
|
});
|
|
|
|
it("forwards authorized project IDs to task-only providers without staging directories", async () => {
|
|
const environment = makeEnvironment("plugin" as Environment["driver"]);
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({ kind: "remote", transport: "sandbox",
|
|
providerKey: "plugin", remoteCwd: "provider/project", runnerTask: vi.fn() });
|
|
const runtime = makeMockRuntime({ supportsTasks: vi.fn().mockResolvedValue(true) });
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
const input = { ...makeRealizeInput({ environment }), adapterType: "paperclip_runner",
|
|
runnerTaskProjectIds: ["anchor", "authorized-reference", "anchor"] };
|
|
input.executionWorkspace.projectId = "anchor";
|
|
const result = await orchestrator.realizeForRun(input);
|
|
expect(result.executionTarget).toMatchObject({ runnerTaskProjectIds: ["anchor", "authorized-reference"] });
|
|
expect(runtime.realizeWorkspace).not.toHaveBeenCalled();
|
|
expect(runtime.execute).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("persisted metadata is updated on lease and execution workspace after realization", async () => {
|
|
const persistedExecutionWorkspace = makePersistedExecutionWorkspace();
|
|
const updatedLease = makeLease({
|
|
metadata: { workspaceRealization: { version: 1, driver: "local", cwd: "/workspace/project" } },
|
|
});
|
|
const updatedEw = { ...persistedExecutionWorkspace, metadata: { workspaceRealizationRequest: {}, workspaceRealization: {} } };
|
|
|
|
mockUpdateLeaseMetadata.mockResolvedValue(updatedLease);
|
|
mockUpdateExecutionWorkspace.mockResolvedValue(updatedEw);
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({ kind: "local", environmentId: "env-1", leaseId: "lease-1" });
|
|
|
|
const runtime = makeMockRuntime();
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
const result = await orchestrator.realizeForRun(
|
|
makeRealizeInput({ persistedExecutionWorkspace }),
|
|
);
|
|
|
|
// Lease metadata should have been updated with workspaceRealization
|
|
expect(mockUpdateLeaseMetadata).toHaveBeenCalledOnce();
|
|
expect(mockUpdateLeaseMetadata).toHaveBeenCalledWith(
|
|
"lease-1",
|
|
expect.objectContaining({ workspaceRealization: expect.any(Object) }),
|
|
);
|
|
|
|
// Execution workspace metadata should have been updated
|
|
expect(mockUpdateExecutionWorkspace).toHaveBeenCalledOnce();
|
|
expect(mockUpdateExecutionWorkspace).toHaveBeenCalledWith(
|
|
"ew-1",
|
|
expect.objectContaining({
|
|
metadata: expect.objectContaining({
|
|
workspaceRealizationRequest: expect.any(Object),
|
|
workspaceRealization: expect.any(Object),
|
|
}),
|
|
}),
|
|
);
|
|
|
|
// The returned lease should reflect the updated value
|
|
expect(result.lease).toEqual(updatedLease);
|
|
expect(result.persistedExecutionWorkspace).toEqual(updatedEw);
|
|
});
|
|
|
|
it("runs a remote provision command after workspace realization when configured", async () => {
|
|
mockBuildWorkspaceRealizationRequest.mockReturnValue({
|
|
version: 1,
|
|
adapterType: "claude_local",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
requestedMode: null,
|
|
source: {
|
|
kind: "project_primary",
|
|
localPath: "/workspace/project",
|
|
projectId: null,
|
|
projectWorkspaceId: null,
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
branchName: null,
|
|
worktreePath: null,
|
|
},
|
|
runtimeOverlay: {
|
|
provisionCommand: "npm install -g @anthropic-ai/claude-code",
|
|
},
|
|
});
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({
|
|
kind: "remote",
|
|
transport: "ssh",
|
|
remoteCwd: "/remote/workspace",
|
|
environmentId: "env-1",
|
|
leaseId: "lease-1",
|
|
spec: {
|
|
host: "ssh.example.test",
|
|
port: 22,
|
|
username: "ssh-user",
|
|
remoteCwd: "/remote/workspace",
|
|
remoteWorkspacePath: "/remote/workspace",
|
|
privateKey: null,
|
|
knownHosts: null,
|
|
strictHostKeyChecking: true,
|
|
},
|
|
});
|
|
|
|
const runtime = makeMockRuntime({
|
|
realizeWorkspace: vi.fn().mockResolvedValue({
|
|
cwd: "/remote/workspace",
|
|
metadata: {
|
|
workspaceRealization: {
|
|
version: 1,
|
|
transport: "ssh",
|
|
remote: { path: "/remote/workspace" },
|
|
},
|
|
},
|
|
}),
|
|
});
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await orchestrator.realizeForRun(makeRealizeInput({
|
|
environment: makeEnvironment("ssh"),
|
|
}));
|
|
|
|
// The `ssh` driver runs the command on the remote host that shares the
|
|
// workspace path, so the configured provision command still runs there.
|
|
expect(runtime.execute).toHaveBeenCalledOnce();
|
|
expect(runtime.execute).toHaveBeenCalledWith(expect.objectContaining({
|
|
environment: expect.objectContaining({ driver: "ssh" }),
|
|
lease: expect.objectContaining({ id: "lease-1" }),
|
|
command: "bash",
|
|
args: ["-lc", "npm install -g @anthropic-ai/claude-code"],
|
|
cwd: "/remote/workspace",
|
|
env: {
|
|
SHELL: "/bin/bash",
|
|
},
|
|
}));
|
|
// The sandbox skip log is specific to the sandbox driver; ssh stays quiet.
|
|
expect(mockLoggerInfo).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("skips the host provision command for a sandbox environment and logs the skip", async () => {
|
|
mockBuildWorkspaceRealizationRequest.mockReturnValue({
|
|
version: 1,
|
|
adapterType: "claude_local",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
requestedMode: null,
|
|
source: {
|
|
kind: "project_primary",
|
|
localPath: "/workspace/project",
|
|
projectId: null,
|
|
projectWorkspaceId: null,
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
branchName: null,
|
|
worktreePath: null,
|
|
},
|
|
runtimeOverlay: {
|
|
provisionCommand: "npm install -g @anthropic-ai/claude-code",
|
|
},
|
|
});
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({
|
|
kind: "remote",
|
|
transport: "sandbox",
|
|
providerKey: "e2b",
|
|
remoteCwd: "/remote/workspace",
|
|
environmentId: "env-1",
|
|
leaseId: "lease-1",
|
|
});
|
|
|
|
const runtime = makeMockRuntime({
|
|
realizeWorkspace: vi.fn().mockResolvedValue({
|
|
cwd: "/remote/workspace",
|
|
metadata: {
|
|
workspaceRealization: {
|
|
version: 1,
|
|
transport: "sandbox",
|
|
remote: { path: "/remote/workspace" },
|
|
},
|
|
},
|
|
}),
|
|
});
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await orchestrator.realizeForRun(makeRealizeInput({
|
|
environment: makeEnvironment("sandbox"),
|
|
}));
|
|
|
|
// The sandbox receives the provisioned tree through the adapter stage.sync
|
|
// step, so the orchestrator must not run the host command in the sandbox.
|
|
expect(runtime.execute).not.toHaveBeenCalled();
|
|
// The skip is observable: exactly one log line records it with the driver.
|
|
expect(mockLoggerInfo).toHaveBeenCalledOnce();
|
|
expect(mockLoggerInfo).toHaveBeenCalledWith(
|
|
expect.objectContaining({ driver: "sandbox", environmentId: "env-1" }),
|
|
expect.stringContaining("Skip host provisionCommand"),
|
|
);
|
|
});
|
|
|
|
it("does not rerun the provision command during local environment realization", async () => {
|
|
mockBuildWorkspaceRealizationRequest.mockReturnValue({
|
|
version: 1,
|
|
adapterType: "claude_local",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
requestedMode: null,
|
|
source: {
|
|
kind: "project_primary",
|
|
localPath: "/workspace/project",
|
|
projectId: null,
|
|
projectWorkspaceId: null,
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
branchName: null,
|
|
worktreePath: null,
|
|
},
|
|
runtimeOverlay: {
|
|
provisionCommand: "npm install -g @anthropic-ai/claude-code",
|
|
},
|
|
});
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({
|
|
kind: "local",
|
|
environmentId: "env-1",
|
|
leaseId: "lease-1",
|
|
});
|
|
|
|
const runtime = makeMockRuntime();
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await orchestrator.realizeForRun(makeRealizeInput({
|
|
environment: makeEnvironment("local"),
|
|
}));
|
|
|
|
// Local workspace provisioning already ran the command before realizeForRun.
|
|
expect(runtime.execute).not.toHaveBeenCalled();
|
|
// The sandbox skip log is specific to the sandbox driver; local stays quiet.
|
|
expect(mockLoggerInfo).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it("runs project-level provision commands for ssh environments", async () => {
|
|
mockBuildWorkspaceRealizationRequest.mockReturnValue({
|
|
version: 1,
|
|
adapterType: "gemini_local",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
requestedMode: null,
|
|
source: {
|
|
kind: "project_primary",
|
|
localPath: "/workspace/project",
|
|
projectId: null,
|
|
projectWorkspaceId: null,
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
branchName: null,
|
|
worktreePath: null,
|
|
},
|
|
runtimeOverlay: {
|
|
provisionCommand: "npm install -g @google/gemini-cli",
|
|
},
|
|
});
|
|
mockResolveEnvironmentExecutionTarget.mockResolvedValue({
|
|
kind: "remote",
|
|
transport: "ssh",
|
|
remoteCwd: "/remote/workspace",
|
|
environmentId: "env-1",
|
|
leaseId: "lease-1",
|
|
spec: {
|
|
host: "ssh.example.test",
|
|
port: 22,
|
|
username: "ssh-user",
|
|
remoteCwd: "/remote/workspace",
|
|
remoteWorkspacePath: "/remote/workspace",
|
|
privateKey: null,
|
|
knownHosts: null,
|
|
strictHostKeyChecking: true,
|
|
},
|
|
});
|
|
|
|
const runtime = makeMockRuntime({
|
|
realizeWorkspace: vi.fn().mockResolvedValue({
|
|
cwd: "/remote/workspace",
|
|
metadata: {
|
|
workspaceRealization: {
|
|
version: 1,
|
|
transport: "ssh",
|
|
remote: { path: "/remote/workspace" },
|
|
},
|
|
},
|
|
}),
|
|
});
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await orchestrator.realizeForRun(makeRealizeInput({
|
|
environment: makeEnvironment("ssh"),
|
|
lease: makeLease({
|
|
provider: "ssh",
|
|
metadata: {
|
|
driver: "ssh",
|
|
remoteCwd: "/remote/workspace",
|
|
remoteWorkspacePath: "/remote/workspace",
|
|
host: "ssh.example.test",
|
|
port: 22,
|
|
username: "ssh-user",
|
|
},
|
|
}),
|
|
}));
|
|
|
|
expect(runtime.execute).toHaveBeenCalledWith(expect.objectContaining({
|
|
command: "bash",
|
|
args: ["-lc", "npm install -g @google/gemini-cli"],
|
|
}));
|
|
expect(mockResolveEnvironmentExecutionTarget).toHaveBeenCalledOnce();
|
|
});
|
|
|
|
it("surfaces remote provision command failures before resolving the adapter target", async () => {
|
|
mockBuildWorkspaceRealizationRequest.mockReturnValue({
|
|
version: 1,
|
|
adapterType: "claude_local",
|
|
companyId: "company-1",
|
|
environmentId: "env-1",
|
|
executionWorkspaceId: null,
|
|
issueId: null,
|
|
heartbeatRunId: "run-1",
|
|
requestedMode: null,
|
|
source: {
|
|
kind: "project_primary",
|
|
localPath: "/workspace/project",
|
|
projectId: null,
|
|
projectWorkspaceId: null,
|
|
repoUrl: null,
|
|
repoRef: null,
|
|
strategy: "project_primary",
|
|
branchName: null,
|
|
worktreePath: null,
|
|
},
|
|
runtimeOverlay: {
|
|
provisionCommand: "install-tool",
|
|
},
|
|
});
|
|
|
|
const runtime = makeMockRuntime({
|
|
execute: vi.fn().mockResolvedValue({
|
|
exitCode: 127,
|
|
signal: null,
|
|
timedOut: false,
|
|
stdout: "",
|
|
stderr: "/bin/sh: install-tool: not found\n",
|
|
}),
|
|
});
|
|
const orchestrator = environmentRunOrchestrator(mockDb, { environmentRuntime: runtime });
|
|
|
|
await expect(orchestrator.realizeForRun(makeRealizeInput({
|
|
environment: makeEnvironment("ssh"),
|
|
}))).rejects.toSatisfy(
|
|
(err: unknown) =>
|
|
err instanceof EnvironmentRunError &&
|
|
err.code === "workspace_realization_failed" &&
|
|
String(err.message).includes("install-tool: not found"),
|
|
);
|
|
|
|
expect(mockResolveEnvironmentExecutionTarget).not.toHaveBeenCalled();
|
|
});
|
|
});
|
|
|
|
|
|
describe("native runner lifecycle changes before lease acquisition", () => {
|
|
it.each([undefined, "account:generation"])("uses a warm plugin lease only with a managed credential identity: %s", async managedAiCredentialIdentity => {
|
|
const environment = { ...makeEnvironment("plugin"), config: { pluginKey: "fixture", driverKey: "tasks", driverConfig: {} } };
|
|
mockGetEnvironment.mockResolvedValue(environment);
|
|
const acquireRunLease = vi.fn(async input => ({ environment: input.environment,
|
|
lease: makeLease({ leasePolicy: input.environment.config.runnerLifecycleMode === "warm" ? "reuse_by_environment" : "ephemeral" }), leaseContext: {} }));
|
|
const orchestrator = environmentRunOrchestrator({} as never, { environmentRuntime: makeMockRuntime({ acquireRunLease }) });
|
|
const result = await orchestrator.acquireForRun({ companyId: "company-1", selectedEnvironmentId: "env-1", localEnvironmentId: "local",
|
|
adapterType: "paperclip_runner", adapterConfig: { lifecycleMode: "warm" }, managedAiCredentialIdentity,
|
|
issueId: "task-1", heartbeatRunId: "run-1", agentId: "agent-1", persistedExecutionWorkspace: null, executionWorkspaceSettings: null });
|
|
expect(result.environment.config.runnerLifecycleMode).toBe(managedAiCredentialIdentity ? "warm" : "per_turn");
|
|
expect(result.lease.leasePolicy).toBe(managedAiCredentialIdentity ? "reuse_by_environment" : "ephemeral");
|
|
expect(environment.config).not.toHaveProperty("runnerLifecycleMode");
|
|
});
|
|
|
|
it("requests a reusable lease when an existing task switches from per-turn to warm", async () => {
|
|
const environment = { ...makeEnvironment("sandbox"), config: { provider: "daytona", reuseLease: false } };
|
|
mockGetEnvironment.mockResolvedValue(environment);
|
|
const acquireRunLease = vi.fn(async (input) => ({
|
|
environment: input.environment,
|
|
lease: makeLease({ leasePolicy: input.environment.config.reuseLease ? "reuse_by_environment" : "ephemeral" }),
|
|
leaseContext: { executionWorkspaceId: "existing-workspace", executionWorkspaceMode: "shared_workspace" },
|
|
}));
|
|
const orchestrator = environmentRunOrchestrator({} as never, { environmentRuntime: makeMockRuntime({ acquireRunLease }) });
|
|
const input = {
|
|
companyId: "company-1", selectedEnvironmentId: "env-1", localEnvironmentId: "local",
|
|
adapterType: "paperclip_runner", issueId: "existing-task", heartbeatRunId: "run-1", agentId: "agent-1",
|
|
runnerTaskProjectIds:["anchor","authorized-reference"],
|
|
persistedExecutionWorkspace: { id: "existing-workspace", mode: "shared_workspace" as const },
|
|
executionWorkspaceSettings: null,
|
|
};
|
|
const cold = await orchestrator.acquireForRun({ ...input, adapterConfig: { lifecycleMode: "per_turn" } });
|
|
expect(cold.lease.leasePolicy).toBe("ephemeral");
|
|
const warm = await orchestrator.acquireForRun({ ...input, heartbeatRunId: "run-2", adapterConfig: { lifecycleMode: "warm", idleTimeoutMs: 60_000 } });
|
|
expect(warm.lease.leasePolicy).toBe("reuse_by_environment");
|
|
expect(warm.environment.config).toEqual({ provider: "daytona", reuseLease: true });
|
|
expect(acquireRunLease.mock.calls[1][0].persistedExecutionWorkspace).toEqual(input.persistedExecutionWorkspace);
|
|
expect(acquireRunLease.mock.calls[1][0].configuredEnvironment).toBe(environment);
|
|
expect(acquireRunLease.mock.calls[1][0].runnerTaskProjectIds).toEqual(input.runnerTaskProjectIds);
|
|
// Run-scoped adaptation must not change the shared environment or other agents.
|
|
expect(environment.config).toEqual({ provider: "daytona", reuseLease: false });
|
|
const coldAgain = await orchestrator.acquireForRun({ ...input, heartbeatRunId: "run-3", adapterConfig: { lifecycleMode: "per_turn" } });
|
|
expect(coldAgain.lease.leasePolicy).toBe("ephemeral");
|
|
});
|
|
|
|
it.each([
|
|
["paperclip_runner", undefined, undefined, false],
|
|
["paperclip_runner", "inherit", "per_turn", false],
|
|
["paperclip_runner", "per_turn", "warm", false],
|
|
["paperclip_runner", "warm", "per_turn", true],
|
|
["paperclip_runner", "inherit", "warm", true],
|
|
["codex_local", "inherit", "warm", false],
|
|
])("respects environment precedence and adapter scope (%s, %s, %s)", async (adapterType, runnerLifecycleMode, lifecycleMode, expectedReuse) => {
|
|
const environment = { ...makeEnvironment("sandbox"), config: { provider: "daytona", reuseLease: false, runnerLifecycleMode } };
|
|
mockGetEnvironment.mockResolvedValue(environment);
|
|
const acquireRunLease = vi.fn(async (input) => ({ environment: input.environment, lease: makeLease(), leaseContext: {} }));
|
|
const orchestrator = environmentRunOrchestrator({} as never, { environmentRuntime: makeMockRuntime({ acquireRunLease }) });
|
|
await orchestrator.acquireForRun({
|
|
companyId: "company-1", selectedEnvironmentId: "env-1", localEnvironmentId: "local", adapterType,
|
|
adapterConfig: { lifecycleMode }, issueId: "task-1", heartbeatRunId: "run-1", agentId: "agent-1",
|
|
persistedExecutionWorkspace: null, executionWorkspaceSettings: null,
|
|
});
|
|
expect(acquireRunLease.mock.calls[0][0].environment.config.reuseLease).toBe(expectedReuse);
|
|
});
|
|
});
|
|
|
|
|
|
describe("admitted native lifecycle recovery", () => {
|
|
it.each([
|
|
["warm", "per_turn", "per_turn", true],
|
|
["per_turn", "warm", "warm", false],
|
|
] as const)("preserves admitted %s over changed agent/environment settings", async (admittedLifecycleMode, lifecycleMode, runnerLifecycleMode, expectedReuse) => {
|
|
const environment = { ...makeEnvironment("sandbox"), config: { provider: "daytona", reuseLease: false, runnerLifecycleMode } };
|
|
mockGetEnvironment.mockResolvedValue(environment);
|
|
const acquireRunLease = vi.fn(async (input) => ({ environment: input.environment, lease: makeLease(), leaseContext: {} }));
|
|
const orchestrator = environmentRunOrchestrator({} as never, { environmentRuntime: makeMockRuntime({ acquireRunLease }) });
|
|
await orchestrator.acquireForRun({
|
|
companyId: "company-1", selectedEnvironmentId: "env-1", localEnvironmentId: "local",
|
|
adapterType: "paperclip_runner", adapterConfig: { lifecycleMode }, admittedLifecycleMode,
|
|
issueId: "task-1", heartbeatRunId: "run-1", agentId: "agent-1",
|
|
persistedExecutionWorkspace: null, executionWorkspaceSettings: null,
|
|
});
|
|
expect(acquireRunLease.mock.calls[0][0].environment.config.reuseLease).toBe(expectedReuse);
|
|
expect(environment.config.reuseLease).toBe(false);
|
|
});
|
|
});
|
|
|
|
describe("live remote runner lease reattachment", () => {
|
|
const input = {
|
|
companyId: "company-1", selectedEnvironmentId: "env-1", localEnvironmentId: "local",
|
|
adapterType: "paperclip_runner", admittedLifecycleMode: "per_turn" as const,
|
|
issueId: "task-1", heartbeatRunId: "run-1", agentId: "agent-1",
|
|
persistedExecutionWorkspace: { id: "ew-1", mode: "shared_workspace" as const },
|
|
executionWorkspaceSettings: null,
|
|
reattachRemoteLease: { leaseId: "lease-1", providerLeaseId: "original-sandbox", remoteCwd: "/remote/workspace" },
|
|
};
|
|
const originalLease = () => makeLease({
|
|
provider: "daytona", providerLeaseId: "original-sandbox", issueId: "task-1", executionWorkspaceId: "ew-1",
|
|
metadata: { agentId: "agent-1", remoteCwd: "/remote/workspace",
|
|
sandboxLeaseAcquisition: { outcome: "created", providerLeaseId: "original-sandbox" } },
|
|
});
|
|
beforeEach(() => {
|
|
vi.clearAllMocks();
|
|
mockGetEnvironment.mockResolvedValue({ ...makeEnvironment("sandbox"), config: { provider: "daytona", reuseLease: false } });
|
|
mockGetLease.mockResolvedValue(originalLease());
|
|
});
|
|
it("reattaches the original active ephemeral lease without acquiring or resuming a sandbox", async () => {
|
|
const savedLease = originalLease();
|
|
mockGetLease.mockResolvedValue(savedLease);
|
|
const runtime = makeMockRuntime();
|
|
const result = await environmentRunOrchestrator({} as never, { environmentRuntime: runtime }).acquireForRun(input);
|
|
expect(mockGetLease).toHaveBeenCalledWith("lease-1");
|
|
expect(runtime.acquireRunLease).not.toHaveBeenCalled();
|
|
expect(result.lease).toEqual(savedLease);
|
|
expect(result.leaseContext.executionWorkspaceId).toBe("ew-1");
|
|
expect(result.environment.config.reuseLease).toBe(false);
|
|
});
|
|
it.each(["active", "foreign-company", "revoked", "undispatched", "stopped"])("inspects the original plugin task lease (%s)", async state => {
|
|
mockGetEnvironment.mockResolvedValue(makeEnvironment("plugin"));
|
|
const lease = originalLease();
|
|
lease.metadata = { agentId: "agent-1", runnerTaskLease: true,
|
|
runnerTaskDispatched: state !== "undispatched", runnerTaskExecutionStopped: state === "stopped" };
|
|
if (state === "foreign-company") lease.companyId = "foreign";
|
|
if (state === "revoked") lease.status = "released";
|
|
mockGetLease.mockResolvedValue(lease);
|
|
const runtime = makeMockRuntime();
|
|
const acquired = environmentRunOrchestrator({} as never, { environmentRuntime: runtime }).acquireForRun({
|
|
...input, reattachRemoteLease: { kind: "plugin_task", leaseId: lease.id },
|
|
});
|
|
if (state === "active") await expect(acquired).resolves.toMatchObject({ lease });
|
|
else await expect(acquired).rejects.toThrow("native_remote_recovery_lease_mismatch");
|
|
expect(runtime.acquireRunLease).not.toHaveBeenCalled();
|
|
});
|
|
it.each([
|
|
{ companyId: "foreign" }, { environmentId: "foreign" }, { heartbeatRunId: "another-run" },
|
|
{ issueId: "another-task" }, { executionWorkspaceId: "another-workspace" },
|
|
{ providerLeaseId: "replacement" }, { provider: "another-provider" },
|
|
{ status: "released" }, { expiresAt: new Date(0) }, { releasedAt: new Date() }, { cleanupStatus: "pending" },
|
|
{ metadata: { agentId: "another-agent", remoteCwd: "/remote/workspace" } },
|
|
{ metadata: { agentId: "agent-1", remoteCwd: "/other/workspace" } },
|
|
] as Partial<EnvironmentLease>[])("fails closed before provider acquisition for a mismatched lease %j", async (override) => {
|
|
mockGetLease.mockResolvedValue({ ...originalLease(), ...override });
|
|
const runtime = makeMockRuntime();
|
|
await expect(environmentRunOrchestrator({} as never, { environmentRuntime: runtime }).acquireForRun(input))
|
|
.rejects.toThrow("native_remote_recovery_lease_mismatch");
|
|
expect(runtime.acquireRunLease).not.toHaveBeenCalled();
|
|
});
|
|
it("never replaces a missing original lease", async () => {
|
|
mockGetLease.mockResolvedValue(null);
|
|
const runtime = makeMockRuntime();
|
|
await expect(environmentRunOrchestrator({} as never, { environmentRuntime: runtime }).acquireForRun(input))
|
|
.rejects.toThrow("native_remote_recovery_lease_mismatch");
|
|
expect(runtime.acquireRunLease).not.toHaveBeenCalled();
|
|
});
|
|
});
|