mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-06 23:20:53 +01:00
Devin FoleyandPaperclip
81ecaf0654
Failed lifecycle verification could allocate another test environment every minute indefinitely. Count failed host verification tests separately from claims, persist a repair wait for confirmed configuration failures or three generic failed tests, and clear it through authorized retry or execution configuration changes. Preserve typed temporary execution-target failures through adapter checks so timeouts, transport failures and interrupted probes keep automatic recovery. Retain existing readiness, authorization, termination and cleanup gates. Document the policy and add real PostgreSQL persistence and actual OpenCode adapter regressions. Verified 398 focused tests (one Windows-only test skipped on macOS), repository-wide typecheck and build, structural checks, fully green current-head CI and Greptile 5/5 with no unresolved comments. Co-Authored-By: Paperclip <noreply@paperclip.ing>
68 lines
3.8 KiB
TypeScript
68 lines
3.8 KiB
TypeScript
import { mkdtemp, rm } from "node:fs/promises";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
import { afterAll, beforeAll, describe, expect, it, vi } from "vitest";
|
|
import type { AdapterExecutionTarget } from "@paperclipai/adapter-utils/execution-target";
|
|
|
|
// Keep the real directory, command and adapter checks. Runtime staging is a
|
|
// separate operation and must not copy files or contact a provider in this test.
|
|
vi.mock("@paperclipai/adapter-utils/execution-target", async importOriginal => ({
|
|
...await importOriginal<typeof import("@paperclipai/adapter-utils/execution-target")>(),
|
|
prepareAdapterExecutionTargetRuntime: async () => ({
|
|
workspaceRemoteDir: "/workspace", runtimeRootDir: "/workspace/.paperclip-runtime",
|
|
assetDirs: {}, restoreWorkspace: async () => {},
|
|
}),
|
|
}));
|
|
|
|
import { testEnvironment } from "@paperclipai/adapter-opencode-local/server";
|
|
import { assertHarnessTestPassed } from "../services/agent-harness-verification.js";
|
|
import { lifecycleFailureMessage, lifecycleVerificationNeedsRetry } from "../modules/agent-lifecycle/application/failure.js";
|
|
|
|
describe("remote harness verification recovery", () => {
|
|
let configHome: string;
|
|
beforeAll(async () => { configHome = await mkdtemp(path.join(os.tmpdir(), "paperclip-remote-verification-")); });
|
|
afterAll(async () => { if (configHome) await rm(configHome, { recursive: true, force: true }); });
|
|
const context = { stage: "host" as const, phase: "verifying" as const, verificationFailures: 100 };
|
|
|
|
it.each([
|
|
["directory", "timeout"], ["directory", "transport"],
|
|
["command", "timeout"], ["command", "transport"],
|
|
["directory", "missing"], ["command", "missing"],
|
|
] as const)("retains %s %s through the real adapter check and recovers when repaired", async (check, fault) => {
|
|
let failing = true;
|
|
const target: AdapterExecutionTarget = {
|
|
kind: "remote", transport: "sandbox", remoteCwd: "/workspace", runner: {
|
|
execute: async input => {
|
|
const script = input.args?.join(" ") ?? "";
|
|
const selected = check === "directory" ? script.includes("[ -d ") : script.includes("command -v ");
|
|
if (failing && selected && fault === "transport") {
|
|
throw Object.assign(new Error("private provider output"), { code: "ECONNRESET" });
|
|
}
|
|
return {
|
|
exitCode: failing && selected ? fault === "timeout" ? null : 1 : 0,
|
|
timedOut: failing && selected && fault === "timeout", signal: null, stderr: "", pid: null,
|
|
startedAt: new Date().toISOString(),
|
|
stdout: input.command === "opencode" ? JSON.stringify({ type: "text", part: { text: "hello" } }) : "",
|
|
};
|
|
},
|
|
},
|
|
};
|
|
const run = () => testEnvironment({ companyId: "company", adapterType: "opencode_local", executionTarget: target,
|
|
config: { command: "opencode", model: "provider/model", env: { XDG_CONFIG_HOME: configHome } } });
|
|
const result = await run();
|
|
const failed = result.checks.find(entry => entry.code === (check === "directory" ? "opencode_cwd_invalid" : "opencode_command_unresolvable"));
|
|
expect(failed?.level).toBe("error");
|
|
expect(failed?.retryable === true).toBe(fault !== "missing");
|
|
let error: unknown;
|
|
try { assertHarnessTestPassed(result); } catch (caught) { error = caught; }
|
|
expect(error).toMatchObject({ code: fault !== "missing" ? "test_environment_unavailable"
|
|
: check === "directory" ? "harness_cwd_invalid" : "harness_command_unavailable" });
|
|
expect(lifecycleVerificationNeedsRetry(context, error)).toBe(fault === "missing");
|
|
expect(lifecycleFailureMessage(context, error)).not.toContain("private provider output");
|
|
if (fault !== "missing") expect(lifecycleFailureMessage(context, error)).toContain("retry automatically");
|
|
failing = false;
|
|
const recovered = await run();
|
|
expect(() => assertHarnessTestPassed(recovered)).not.toThrow();
|
|
});
|
|
});
|