Files
PaperClipAI/tests/runner-e2e/live-fixtures.ts
DottaandPaperclip 7956056b2f Merge current master and qualify managed Codex onboarding
Reconcile actual master 833769ab with preserved Codex 1a0ca662 and reviewed private onboarding preparation a758b226. Preserve the merged prerequisite and current native/security changes, saved runner choices, managed-image qualification and current Storybook identities.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-10-13 10:21:06 -05:00

434 lines
17 KiB
TypeScript

import { verifyInstalledDaytonaPlugin } from "./installed-daytona-plugin.js";
import { NATIVE_COMPLETION_BUDGET_CENTS } from "./native-completion-defaults.js";
import path from "node:path";
import { installedReleaseDaytonaPlugin } from "./installed-release.js";
import { isManagedHiringCase } from "./chat-cases.js";
import { FixtureRegistry } from "./fixture-registry.js";
import { isImmutableDaytonaImage } from "./catalog.js";
import { TASK_TITLE_BUDGET_CENTS } from "./task-titles.js";
import { stageGrokSubscriptionFixture } from "./grok-subscription-fixture.js";
import type { RunnerApi } from "./api.js";
import type {
CredentialName,
MatrixExecution,
SecretReference,
SecretReferenceMap,
RunnerE2ERuntimeUsage,
} from "./types.js";
interface CompanyRecord {
id: string;
issuePrefix?: string | null;
name: string;
}
interface SecretRecord {
id: string;
}
interface PluginRecord {
id: string;
pluginKey: string;
status: string;
}
interface EnvironmentRecord {
id: string;
driver: string;
config?: Record<string, unknown>;
}
interface AgentRecord {
id: string;
name: string;
companyId: string;
}
interface ManagedAccountFixture {
connectionId: string;
binding: {
provider: "openai" | "anthropic" | "openrouter";
method: "api_key";
mode: "responsible_user";
};
}
interface ProjectRecord {
id: string;
name: string;
primaryWorkspace?: {
id: string;
cwd?: string | null;
} | null;
}
export interface LiveFixtureValues {
company: CompanyRecord;
secretRefs: SecretReferenceMap;
environment: EnvironmentRecord;
agent: AgentRecord;
project?: ProjectRecord;
aiConnection?: ManagedAccountFixture;
setupProbe?: { leaseId: string; durationMs: number; defaultRunner?: string };
setupLeases?: Array<{ leaseId: string; phase: "platform" | "adapter"; durationMs: number }>;
setupLeaseAccountingIncomplete?: boolean;
setupQualification?: { recorded: boolean; adapterType: string | null; platformResponses: number; adapterResponses: number };
onboardingRuntime?: {
mode: "production-wizard" | "post-onboarding-runtime-switch";
originalAdapterType: string;
originalModel: string | null;
testedAdapterType: string;
};
teardown(): Promise<void>;
}
function value<T>(resolved: ReadonlyMap<string, unknown>, id: string): T {
const result = resolved.get(id);
if (!result) throw new Error(`Missing resolved fixture ${id}`);
return result as T;
}
export function selectFixtureRuntimeLeases<T extends {
id: string; provider?: string | null; heartbeatRunId?: string | null; issueId?: string | null;
}>(input: { leases: T[]; runIds: string[]; issueId?: string; setupProbeLeaseId?: string; setupLeaseIds?: readonly string[] }): T[] {
const selectedRunIds = new Set(input.runIds);
const setupIds = new Set([...(input.setupLeaseIds ?? []), ...(input.setupProbeLeaseId ? [input.setupProbeLeaseId] : [])]);
const relevant = input.leases.filter(lease => lease.provider === "daytona" && (
setupIds.has(lease.id) || (input.setupLeaseIds === undefined && selectedRunIds.size === 0)
|| (lease.heartbeatRunId && selectedRunIds.has(lease.heartbeatRunId))
|| (input.issueId && lease.issueId === input.issueId)
));
return input.setupLeaseIds !== undefined || relevant.length > 0 ? relevant : input.leases;
}
export function fixtureRuntimeCostCoverage(usage: RunnerE2ERuntimeUsage, fixtures: Pick<LiveFixtureValues, "setupLeaseAccountingIncomplete">): RunnerE2ERuntimeUsage {
if (!fixtures.setupLeaseAccountingIncomplete) return usage;
const { estimatedListCostUsd: _estimate, ...known } = usage;
return { ...known, costStatus: "unavailable", costSource: "provider_cost_unavailable" };
}
export async function deleteDaytonaEnvironment(api: Pick<RunnerApi, "delete">, environmentId: string) {
const deadlineAt = Date.now() + 120_000;
let lastError: unknown;
while (Date.now() < deadlineAt) {
try {
await api.delete(
`/api/environments/${environmentId}?destroyReusableSandboxLeases=true`,
{
allowNotFound: true,
},
);
return;
} catch (error) {
lastError = error;
await new Promise((resolve) => setTimeout(resolve, 3_000));
}
}
throw new Error(
`Daytona lease cleanup failed: ${lastError instanceof Error ? lastError.message : String(lastError)}`,
);
}
export async function installFixtureDaytonaProvider(api: Pick<RunnerApi, "post">, execution: MatrixExecution) {
const installed = await verifyInstalledDaytonaPlugin(process.env, [execution]);
return api.post<PluginRecord>("/api/plugins/install", {
packageName: installed?.packageRoot ?? path.resolve(import.meta.dirname, "../../packages/plugins/sandbox-providers/daytona"),
isLocalPath: true,
}, { timeout: 120_000 });
}
export async function setupLiveFixtures(input: {
api: RunnerApi;
execution: MatrixExecution;
executionNonce: string;
workspacePath: string;
credentials: Partial<Record<CredentialName, string>>;
daytonaImage?: string;
}): Promise<LiveFixtureValues> {
const { api, execution } = input;
const registry = new FixtureRegistry();
let setupProbe: LiveFixtureValues["setupProbe"];
if (execution.environment.id === "daytona") {
registry.register<PluginRecord>({
id: "sandbox-provider",
async setup() {
return installFixtureDaytonaProvider(api, execution);
},
async teardown() {
// The plugin is installed only in the isolated instance/database. The
// launcher removes that complete instance after the environment lease
// has been destroyed, so no global uninstall mutation is necessary.
},
});
}
registry.register<CompanyRecord>({
id: "company",
async setup() {
return api.post<CompanyRecord>("/api/companies", {
name: `Runner E2E ${execution.id} ${input.executionNonce}`,
description: "Ephemeral paid full-stack runner acceptance fixture",
budgetMonthlyCents: ["native-completion", "native-instruction-consolidation", "native-connection-guidance"].includes(execution.suite.id)
|| (execution.suite.id === "everyday-workflows" && ["hire-reuse", "delegate-feedback"].includes(execution.task.id)) ? NATIVE_COMPLETION_BUDGET_CENTS
: execution.suite.id === "task-titles" ? TASK_TITLE_BUDGET_CENTS
: ["stock-harness", "task-workspaces"].includes(execution.suite.id) ? 1_000 : 0,
});
},
async teardown() {
// The isolated instance/database is removed by the launcher. Do not call
// company deletion here: metered runs intentionally retain cost-event
// references until that instance-wide teardown.
},
});
registry.register<SecretReferenceMap>({
id: "secrets",
dependencies: ["company"],
async setup(resolved) {
const company = value<CompanyRecord>(resolved, "company");
const refs: SecretReferenceMap = {};
for (const credentialName of execution.requiredCredentials) {
if (credentialName === "GROK_AUTH_JSON") continue;
const rawValue = input.credentials[credentialName];
if (!rawValue) throw new Error(`Missing credential ${credentialName}`);
const secret = await api.postSensitive<SecretRecord>(
`/api/companies/${company.id}/secrets`,
{
name: `Runner E2E ${credentialName} ${input.executionNonce}`,
key: credentialName,
value: rawValue,
description: `Ephemeral credential for ${execution.id}`,
},
);
refs[credentialName] = {
type: "secret_ref",
secretId: secret.id,
version: "latest",
} satisfies SecretReference;
}
return refs;
},
});
const grokSubscription = execution.profile.credential === "GROK_AUTH_JSON";
if (grokSubscription) {
registry.register<() => Promise<void>>({
id: "subscription-login",
dependencies: ["company"],
async setup(resolved) {
const raw = input.credentials.GROK_AUTH_JSON;
if (!raw) throw new Error("Missing credential GROK_AUTH_JSON");
return stageGrokSubscriptionFixture({
raw, companyId: value<CompanyRecord>(resolved, "company").id,
environment: process.env,
});
},
async teardown(remove) { await remove(); },
});
}
registry.register<EnvironmentRecord>({
id: "environment",
dependencies: [
"company",
"secrets",
...(grokSubscription ? ["subscription-login"] : []),
...(execution.environment.id === "daytona" ? ["sandbox-provider"] : []),
],
async setup(resolved) {
const company = value<CompanyRecord>(resolved, "company");
const secretRefs = value<SecretReferenceMap>(resolved, "secrets");
if (execution.environment.id === "local") {
// Paperclip has one instance-managed local environment. The company
// creation API ensures it exists; creating a second local environment
// is intentionally rejected by the public API.
const environments = await api.get<EnvironmentRecord[]>(
`/api/companies/${company.id}/environments?driver=local`,
);
const local = environments.find(
(candidate) => candidate.driver === "local",
);
if (!local)
throw new Error(
"Isolated Paperclip instance did not create its managed local environment",
);
return local;
}
return api.post<EnvironmentRecord>(
`/api/companies/${company.id}/environments`,
execution.environment.buildEnvironment({
secretRefs,
daytonaImage: input.daytonaImage,
executionId: input.executionNonce,
}),
);
},
async teardown(environment) {
if (execution.environment.id === "daytona") {
await deleteDaytonaEnvironment(api, environment.id);
}
},
});
const managedHiring = isManagedHiringCase(execution.suite.id, execution.task.id);
if (managedHiring) {
registry.register<ManagedAccountFixture>({
id: "ai-connection",
dependencies: ["company"],
async setup(resolved) {
const company = value<CompanyRecord>(resolved, "company");
const key = execution.profile.credential;
const provider = key === "ANTHROPIC_API_KEY" ? "anthropic"
: key === "OPENROUTER_API_KEY" ? "openrouter"
: key === "OPENAI_API_KEY" ? "openai" : null;
if (!provider) throw new Error(`Unsupported managed hiring credential ${key}`);
const apiKey = input.credentials[key];
if (!apiKey) throw new Error(`Missing credential ${key}`);
const account = await api.postSensitive<{ connectionId: string }>(
`/api/companies/${company.id}/ai-connections`,
{
provider,
method: "api_key",
name: `Runner E2E account ${input.executionNonce}`,
ownership: "personal",
apiKey,
agentIds: [],
allAgents: false,
},
);
return {
connectionId: account.connectionId,
binding: { provider, method: "api_key", mode: "responsible_user" },
};
},
});
}
registry.register<AgentRecord>({
id: "agent",
dependencies: [
"company",
"secrets",
"environment",
...(grokSubscription ? ["subscription-login"] : []),
...(managedHiring ? ["ai-connection"] : []),
],
async setup(resolved) {
const company = value<CompanyRecord>(resolved, "company");
const environment = value<EnvironmentRecord>(resolved, "environment");
const secretRefs = value<SecretReferenceMap>(resolved, "secrets");
const agent = execution.profile.buildAgent({
environmentId: environment.id,
environmentFixtureId: execution.environment.id,
workspacePath: input.workspacePath,
secretRefs,
executionId: input.executionNonce,
});
const autoCodex = agent.adapterType === "codex_local" && (agent.runner === undefined || agent.runner === "auto");
const nativeCodex = agent.adapterType === "paperclip_runner" && (agent.adapterConfig as Record<string, unknown>).provider === "codex";
if (environment.driver === "sandbox" && execution.profile.generation === "native"
&& execution.profile.provider === "codex" && agent.runner !== "legacy" && (autoCodex || nativeCodex)) {
if (!isImmutableDaytonaImage(String(environment.config?.image ?? "")) || environment.config?.snapshot) {
throw new Error("Native Codex qualification requires this fixture's immutable image-backed environment.");
}
const startedAt = Date.now();
const probe = await api.post<{ ok: boolean; details?: { platformQualificationRecorded?: boolean; leaseId?: string } }>(
`/api/environments/${environment.id}/probe?companyId=${encodeURIComponent(company.id)}`,
{}, { timeout: 330_000 },
);
if (probe.ok !== true || probe.details?.platformQualificationRecorded !== true || !probe.details.leaseId) {
throw new Error("Native Codex image qualification was not recorded; agent creation was not attempted.");
}
setupProbe = { leaseId: probe.details.leaseId, durationMs: Date.now() - startedAt };
if (autoCodex) {
const adapters = await api.get<Array<{ type: string; defaultRunner?: string; supportedRunners?: string[] }>>(
`/api/adapters?companyId=${encodeURIComponent(company.id)}&environmentId=${encodeURIComponent(environment.id)}`,
);
const selected = adapters.find(adapter => adapter.type === "codex_local");
if (selected?.defaultRunner !== "paperclip" || !selected.supportedRunners?.includes("paperclip")) {
throw new Error("The qualified image does not advertise native Codex as its server-owned default.");
}
setupProbe.defaultRunner = selected.defaultRunner;
}
}
if (["stock-harness", "native-connection-guidance"].includes(execution.suite.id)
|| (execution.suite.id === "everyday-workflows" && ["hire-reuse", "delegate-feedback"].includes(execution.task.id))) {
agent.budgetMonthlyCents = 1_000;
}
if (managedHiring) {
const account = value<ManagedAccountFixture>(resolved, "ai-connection");
const config = agent.adapterConfig as Record<string, unknown>;
delete config.env;
agent.runtimeConfig = {
...(agent.runtimeConfig as Record<string, unknown>),
aiConnection: account.binding,
};
}
return api.post<AgentRecord>(
`/api/companies/${company.id}/agents`,
agent,
);
},
async teardown() {
// Agent state is instance-local. Daytona environment teardown below is
// the only fixture cleanup that must reach an external provider.
},
});
if (execution.task.flow === "warm_three_turn"
|| (execution.suite.id === "extended-harnesses" && execution.task.id === "file-edit-validate")) {
registry.register<ProjectRecord>({
id: "project",
dependencies: ["company", "environment"],
async setup(resolved) {
const company = value<CompanyRecord>(resolved, "company");
const environment = value<EnvironmentRecord>(resolved, "environment");
return api.post<ProjectRecord>(
`/api/companies/${company.id}/projects`,
{
name: `Runner E2E workspace project ${input.executionNonce}`,
description:
"Ephemeral project anchoring the fixture execution workspace and file copy-back",
executionWorkspacePolicy: {
enabled: true,
defaultMode: "shared_workspace",
sharedWorkspaceConcurrency: "serialize",
allowIssueOverride: false,
environmentId: environment.id,
workspaceStrategy: { type: "project_primary" },
},
workspace: {
name: "Primary",
sourceType: "local_path",
cwd: input.workspacePath,
isPrimary: true,
},
},
);
},
async teardown() {
// The isolated instance is deleted after provider resources are gone.
},
});
}
const setup = await registry.setupAll();
return {
company: value<CompanyRecord>(setup.values, "company"),
secretRefs: value<SecretReferenceMap>(setup.values, "secrets"),
environment: value<EnvironmentRecord>(setup.values, "environment"),
agent: value<AgentRecord>(setup.values, "agent"),
...(setupProbe ? { setupProbe } : {}),
...(setup.values.has("project")
? { project: value<ProjectRecord>(setup.values, "project") }
: {}),
...(managedHiring
? {
aiConnection: value<ManagedAccountFixture>(
setup.values,
"ai-connection",
),
}
: {}),
teardown: setup.teardown,
};
}