PaperClipAI/tests/runner-e2e/first-task-fixtures.ts

import { normalizePaperclipOperationalSkillPreference } from "../../packages/adapter-utils/src/server-utils.js";
import { isDeepStrictEqual } from "node:util";
import type { RunnerApi } from "./api.js";
import { deleteDaytonaEnvironment, installFixtureDaytonaProvider, type LiveFixtureValues } from "./live-fixtures.js";
import { isImmutableDaytonaImage } from "./catalog.js";
import type { CredentialName, MatrixExecution } from "./types.js";

export const MANAGED_FIRST_TASK_CELL = "confirmation-replies.runner-codex.daytona.task-card-accept";
export function isManagedFirstTask(execution: Pick<MatrixExecution, "id">): boolean {
  return execution.id === MANAGED_FIRST_TASK_CELL;
}

interface FirstTaskRuntimeBound {
  timeoutSec: 180;
  maxConcurrentRuns: 1;
  before: Record<string, unknown>;
  after: Record<string, unknown>;
}

export type FirstTaskFixtureValues = LiveFixtureValues & {
  onboardingRuntimeBound?: FirstTaskRuntimeBound;
};

export async function startFirstTaskWithRuntimeBound(input: {
  api: Pick<RunnerApi, "get" | "patch">;
  execution: MatrixExecution;
  agent: Record<string, any>;
  observe: (bound: FirstTaskRuntimeBound) => void;
  start: () => Promise<void>;
}): Promise<void> {
  if (input.execution.profile.id === "runner-codex") {
    const snapshot = (agent: Record<string, any>) => structuredClone(Object.fromEntries([
      "id", "companyId", "adapterType", "adapterConfig", "runtimeConfig", "permissions", "defaultEnvironmentId", "budgetMonthlyCents", "metadata",
    ].map(key => [key, agent?.[key]]))) as Record<string, any>;
    const before = snapshot(input.agent);
    if (!before.id || !before.companyId || before.adapterType !== "paperclip_runner" || before.adapterConfig?.provider !== "codex") {
      throw new Error("First-task runtime bound requires the wizard's original native Codex selection");
    }
    const agentPath = `/api/agents/${encodeURIComponent(before.id)}`;
    if (!isDeepStrictEqual(snapshot(await input.api.get(agentPath)), before)) {
      throw new Error("The automatic wizard configuration changed before the first-task runtime bound");
    }
    const runtimeConfig = { ...before.runtimeConfig, heartbeat: { ...before.runtimeConfig?.heartbeat, maxConcurrentRuns: 1 } };
    await input.api.patch(agentPath, { adapterConfig: { timeoutSec: 180 }, runtimeConfig });
    const after = snapshot(await input.api.get(agentPath));
    const expected = { ...before, adapterConfig: { ...before.adapterConfig, timeoutSec: 180 }, runtimeConfig };
    if (!isDeepStrictEqual(after, expected)) {
      throw new Error("The first-task runtime bound was not confirmed with the original execution and account settings");
    }
    input.observe({ timeoutSec: 180, maxConcurrentRuns: 1, before, after });
  }
  await input.start();
}

export async function provisionFirstTaskFixtures(input: {
  api: Pick<RunnerApi, "get" | "patch" | "postSensitive"> & Partial<Pick<RunnerApi, "post" | "delete">>;
  execution: MatrixExecution;
  nonce: string;
  daytonaImage?: string;
  company: LiveFixtureValues["company"];
  credentials: Partial<Record<CredentialName, string>>;
}): Promise<FirstTaskFixtureValues> {
  const { api, execution, nonce, company, credentials } = input;
  const managed = isManagedFirstTask(execution);
  if (
    !["first-task", "completion-updates", "confirmation-replies"].includes(execution.suite.id) || execution.task.flow !== "first_task" ||
    (execution.environment.id !== "local" && !managed) ||
    ![
      "legacy-codex",
      "legacy-claude",
      "runner-codex",
      "runner-acpx-claude",
    ].includes(execution.profile.id)
  ) {
    throw new Error(
      "First-task fixtures require a supported local onboarding profile",
    );
  }
  if (managed && (!isImmutableDaytonaImage(input.daytonaImage) || !api.post || !api.delete)) {
    throw new Error("Managed onboarding requires the immutable image and normal environment create/cleanup APIs");
  }
  const required = managed ? [execution.profile.credential, "DAYTONA_API_KEY" as const] : [execution.profile.credential];
  for (const name of required) if (!credentials[name]) throw new Error(`Missing credential ${name}`);
  const previousSettings = managed ? await api.get<{
    defaultEnvironmentId: string | null;
    experimental: { enableManagedSandboxOnly: boolean };
  }>("/api/instance/settings") : null;
  if (managed && (!previousSettings ||
    (previousSettings.defaultEnvironmentId !== null && typeof previousSettings.defaultEnvironmentId !== "string") ||
    typeof previousSettings.experimental?.enableManagedSandboxOnly !== "boolean")) {
    throw new Error("Managed onboarding fixture prior instance settings could not be read");
  }
  await api.patch(`/api/companies/${company.id}`, { budgetMonthlyCents: 500 });
  let localEnvironment: LiveFixtureValues["environment"] | undefined;
  if (!managed) {
    const environments = await api.get<Array<LiveFixtureValues["environment"]>>(`/api/companies/${company.id}/environments?driver=local`);
    localEnvironment = environments.find(candidate => candidate.driver === "local");
    if (!localEnvironment) throw new Error("Onboarding fixture local environment missing");
  }
  const secretRefs: LiveFixtureValues["secretRefs"] = {};
  for (const name of required) {
    const secret = await api.postSensitive<{ id: string }>(`/api/companies/${company.id}/secrets`, {
      name: `First task ${name}`, key: name, value: credentials[name],
    });
    secretRefs[name] = { type: "secret_ref", secretId: secret.id, version: "latest" };
  }
  let environment: LiveFixtureValues["environment"];
  let teardown = async () => {};
  if (managed) {
    const remoteApi = api as Pick<RunnerApi, "post" | "delete">;
    await installFixtureDaytonaProvider(remoteApi, execution);
    environment = await remoteApi.post<LiveFixtureValues["environment"]>(`/api/companies/${company.id}/environments`,
      execution.environment.buildEnvironment({ secretRefs, daytonaImage: input.daytonaImage, executionId: nonce }));
    let restoreDefault = false;
    let restoreManagedOnly = false;
    let environmentDeleted = false;
    teardown = async () => {
      const failures: unknown[] = [];
      if (restoreManagedOnly) {
        try {
          await api.patch("/api/instance/settings/experimental", { enableManagedSandboxOnly: previousSettings!.experimental.enableManagedSandboxOnly });
          restoreManagedOnly = false;
        } catch (error) { failures.push(error); }
      }
      if (restoreDefault) {
        try {
          await api.patch("/api/instance/settings", { defaultEnvironmentId: previousSettings!.defaultEnvironmentId });
          restoreDefault = false;
        } catch (error) { failures.push(error); }
      }
      if (!restoreDefault && !environmentDeleted) {
        try {
          await deleteDaytonaEnvironment(remoteApi, environment.id);
          environmentDeleted = true;
        } catch (error) { failures.push(error); }
      }
      if (failures.length) throw new AggregateError(failures, restoreDefault
        ? "Managed onboarding fixture cleanup failed; instance default restoration is unconfirmed and environment deletion was not attempted"
        : "Managed onboarding fixture cleanup failed");
    };
    try {
      restoreDefault = true;
      await api.patch("/api/instance/settings", { defaultEnvironmentId: environment.id });
      restoreManagedOnly = true;
      await api.patch("/api/instance/settings/experimental", { enableManagedSandboxOnly: true });
    } catch (error) {
      try { await teardown(); } catch (cleanup) { throw new AggregateError([error, cleanup], "Managed onboarding fixture setup and cleanup failed"); }
      throw error;
    }
  } else environment = localEnvironment!;

  return {
    company,
    environment,
    secretRefs,
    agent: { id: "", name: `Garden lead ${nonce}`, companyId: company.id },
    ...(managed ? { setupLeases: [], setupQualification: { recorded: false, adapterType: null, platformResponses: 0, adapterResponses: 0 } } : {}),
    teardown,
  };
}

export function firstTaskNativeRuntimePatch(
  execution: MatrixExecution,
  fixtures: LiveFixtureValues,
  agent: Record<string, any>,
) {
  if (!["runner-codex", "runner-acpx-claude"].includes(execution.profile.id))
    throw new Error("Unsupported native first-task profile");
  const built = execution.profile.buildAgent({
    environmentId: fixtures.environment.id,
    environmentFixtureId: "local",
    workspacePath: agent.adapterConfig?.cwd ?? "",
    secretRefs: fixtures.secretRefs,
    executionId: execution.id,
  });
  const config = {
    ...agent.adapterConfig,
    ...(built.adapterConfig as Record<string, unknown>),
  };
  // Preserve the wizard's model choice (including its unset provider default).
  if (agent.adapterConfig?.model == null) delete config.model;
  else config.model = agent.adapterConfig.model;
  return {
    adapterType: "paperclip_runner",
    adapterConfig: normalizePaperclipOperationalSkillPreference(
      "paperclip_runner",
      config,
    ),
  };
}