Files
PaperClipAI/tests/runner-e2e/chat-catalog-fingerprint.test.ts
T

130 lines
10 KiB
TypeScript

import { CHAT_OPENCODE_MODEL } from "./chat-runtime-profile.js";
import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from "node:fs";
import { tmpdir } from "node:os";
import path from "node:path";
import { pathToFileURL } from "node:url";
import { afterEach, expect, it, vi } from "vitest";
import { assertChatCatalogFingerprintLane, chatCatalogCaseFingerprint, chatCatalogSpawnedSourceEntries, fingerprintChatDependencyClosure } from "./chat-catalog-fingerprint.js";
import { findChatCatalogCase, loadChatCatalogImplementation, type ChatCatalogDescriptor } from "./chat-catalog-registry.js";
const directories: string[] = [];
afterEach(() => { vi.unstubAllEnvs(); for (const directory of directories.splice(0)) rmSync(directory, { recursive: true, force: true }); });
function fixture() {
const root = mkdtempSync(path.join(tmpdir(), "chat-fingerprint-")); directories.push(root);
const write = (file: string, body: string) => writeFileSync(path.join(root, file), body);
write("shared.ts", 'export { value } from "./transitive.js";');
write("selected.ts", 'import { value } from "./shared.js"; export const result = value;');
write("transitive.ts", "export const value = 1;");
write("unselected.ts", 'throw new Error("Unselected module must never execute");');
return { root, write, fingerprint: () => fingerprintChatDependencyClosure({ root, entries: ["selected.ts"], selected: { id: "selected", query: "Exact request" } }).digest };
}
it("invalidates shared, selected and transitive dependencies while ignoring an unloaded domain", () => {
for (const target of ["shared.ts", "selected.ts", "transitive.ts"]) {
const f = fixture(); const before = f.fingerprint();
f.write("unselected.ts", "export const changed = true;"); expect(f.fingerprint()).toBe(before);
f.write(target, "export const changed = true;"); expect(f.fingerprint()).not.toBe(before);
}
});
it("binds actual spawned supervisor and entry bytes even when launch refers to them only by path", () => {
expect(chatCatalogSpawnedSourceEntries).toEqual(["tests/runner-e2e/server.ts", "tests/runner-e2e/server-entry.ts"]);
for (const changed of chatCatalogSpawnedSourceEntries) {
const f = fixture(); mkdirSync(path.join(f.root, "tests/runner-e2e"), { recursive: true });
for (const file of chatCatalogSpawnedSourceEntries) f.write(file, "export const behavior = 'original';");
const fingerprint = () => fingerprintChatDependencyClosure({ root: f.root, entries: ["selected.ts", ...chatCatalogSpawnedSourceEntries], selected: {} });
const before = fingerprint();
expect(before.sources.map(row => row.file)).toEqual(expect.arrayContaining([...chatCatalogSpawnedSourceEntries]));
f.write(changed, "export const behavior = 'changed executable';"); expect(fingerprint().digest).not.toBe(before.digest);
}
});
it("conservatively binds unknown dynamic imports", () => {
const f = fixture(); f.write("selected.ts", "export const load = (name: string) => import(name);");
const before = f.fingerprint(); f.write("unselected.ts", "export const changed = true;");
expect(f.fingerprint()).not.toBe(before);
});
it("executes only the selected domain and rejects metadata drift", async () => {
const f = fixture();
const descriptor: ChatCatalogDescriptor = { scenarioId: "selected", modulePath: "./chat-catalog-domains/selected.js", exportName: "cases",
sourceFiles: ["selected.ts"], oracleVersion: "v1", expectedRunCount: 1, turnTimeoutMs: 100, attemptTimeoutMs: 1000 };
f.write("selected.mjs", `globalThis.__selectedChatLoads = (globalThis.__selectedChatLoads ?? 0) + 1; export const cases = [{...${JSON.stringify(descriptor)}, setup(){}, observe(){}, grade(){}, verifyResult(){}}];`);
f.write("unselected.mjs", 'throw new Error("Unselected domain executed");');
const requested: string[] = [];
const loaded = await loadChatCatalogImplementation(descriptor, async specifier => {
requested.push(specifier);
return import(pathToFileURL(path.join(f.root, "selected.mjs")).href);
});
expect(loaded.scenarioId).toBe("selected"); expect(requested).toHaveLength(1);
expect(requested[0]).toContain("/chat-catalog-domains/selected.js");
await expect(loadChatCatalogImplementation({ ...descriptor, expectedRunCount: 2 }, async () => ({ cases: [loaded] }))).rejects.toThrow("Runtime descriptor drift");
});
it("refuses formerly inactive launch targets and source drift falls back conservatively", () => {
const lane = { suiteId: "chat-features", flow: "agent_chat", environment: "local" };
expect(assertChatCatalogFingerprintLane(lane, {}, [])).toMatchObject({ installedLane: false });
for (const changed of [{ ...lane, environment: "daytona" }, { ...lane, flow: "github_review_journey" }])
expect(() => assertChatCatalogFingerprintLane(changed, {}, [])).toThrow();
expect(() => assertChatCatalogFingerprintLane(lane, { PAPERCLIP_RUNNER_E2E_INSTALLED_CLI: "/candidate" }, [])).toThrow();
expect(() => assertChatCatalogFingerprintLane(lane, {}, ["--target-config"])).toThrow();
const f = fixture(); f.write("selected.ts", "export const load=(name:string)=>import(name);");
const before = fingerprintChatDependencyClosure({ root: f.root, entries: ["selected.ts"], selected: lane,
reviewedDynamicResolutions: { "selected.ts": { sourceSha256: "outdated", resolution: "reviewed-inactive", dependencies: [] } } });
expect(before.unknownDynamicImports).toEqual(["selected.ts"]);
f.write("unselected.ts", "export const changed=true;");
expect(fingerprintChatDependencyClosure({ root: f.root, entries: ["selected.ts"], selected: lane }).digest).not.toBe(before.digest);
});
it("binds selected and spawned code, conservatively closing unresolved CLI and production loaders", () => {
const descriptor = findChatCatalogCase("projects.create-project")!;
const result = chatCatalogCaseFingerprint(descriptor, { suiteId: "chat-features", flow: "agent_chat", environment: "local" });
const files = result.sources.map(source => source.file);
expect(files).toContain("tests/runner-e2e/chat-catalog-domains/internal-projects.ts");
expect(files).toContain("tests/runner-e2e/chat-catalog-domains/internal-support.ts");
expect(files).toContain("packages/adapter-utils/src/workspace-snapshot-thread-worker.ts");
expect(files).toEqual(expect.arrayContaining([...chatCatalogSpawnedSourceEntries, "tests/runner-e2e/chat-catalog-domains/internal-goals.ts"]));
expect(files).toContain("tests/runner-e2e/chat-catalog-domains/identity-auth.ts");
expect(result.unknownDynamicImports).toEqual(expect.arrayContaining(["cli/src/commands/run.ts", "server/src/adapters/plugin-loader.ts"]));
});
it("fails closed when preserved prerequisites or a rejected query lack their independent verifier", async () => {
const base: ChatCatalogDescriptor = { scenarioId: "selected", modulePath: "./chat-catalog-domains/selected.js", exportName: "cases",
sourceFiles: ["selected.ts"], oracleVersion: "v1", expectedRunCount: 1, turnTimeoutMs: 100, attemptTimeoutMs: 1000 };
const callbacks = { setup() {}, observe() {}, grade() {}, verifyResult() {} };
const setup = { ...base, setupPolicy: { funding: "preserve-scenario" as const, invariantCheckIds: ["saved-budget"] } };
await expect(loadChatCatalogImplementation(setup, async () => ({ cases: [{ ...setup, ...callbacks }] }))).rejects.toThrow("independent prerequisite assertions");
const rejected = { ...base, queryOutcome: "rejected" as const };
await expect(loadChatCatalogImplementation(rejected, async () => ({ cases: [{ ...rejected, ...callbacks }] }))).rejects.toThrow("independent rejection evidence");
});
it("replays the retained public name-only identity after raw selected inputs have been removed", () => {
const descriptor = findChatCatalogCase("projects.create-project")!;
const execution = { executionId: "offline-selected", suiteId: "chat-features", flow: "agent_chat", environment: "local" };
const names = { credentialNames: ["OPENAI_API_KEY"], referenceNames: [], externalRequirements: [] };
const before = chatCatalogCaseFingerprint(descriptor, execution, names).digest;
vi.stubEnv("PAPERCLIP_CHAT_PRIVATE_INPUTS", "/removed/owned-secret-file.json");
expect(chatCatalogCaseFingerprint(descriptor, execution, names).digest).toBe(before);
expect(() => chatCatalogCaseFingerprint(descriptor, execution)).toThrow();
});
it("binds extensionless TSX components and directory TSX entries", () => {
const f = fixture(); mkdirSync(path.join(f.root, "nested"));
f.write("selected.ts", 'export { value } from "./Component";');
f.write("Component.tsx", 'export { value } from "./nested";');
f.write("nested/index.tsx", 'export const value = "actual component";');
const before = f.fingerprint();
f.write("nested/index.tsx", 'export const value = "changed component";');
expect(f.fingerprint()).not.toBe(before);
expect(fingerprintChatDependencyClosure({ root: f.root, entries: ["selected.ts"], selected: {} }).sources.map(row => row.file))
.toEqual(expect.arrayContaining(["Component.tsx", "nested/index.tsx"]));
});
it("rejects a missing extensionless component instead of binding an unrelated TSX file", () => {
const f = fixture();
f.write("selected.ts", 'export { value } from "./MissingComponent";');
f.write("OtherComponent.tsx", 'export const value = "unrelated";');
expect(f.fingerprint).toThrow("Unresolved fingerprint dependency: ./MissingComponent");
});
it("admits installed OpenCode only for its exact reviewed model, case and source-local lane", () => {
const lane = { suiteId: "chat-features", flow: "agent_chat", environment: "local", scenarioId: "instance-operations.update-instance", installedSource: "published-global-npm",
profile: { id: "runner-opencode", provider: "opencode", model: CHAT_OPENCODE_MODEL, adapterType: "paperclip_runner", credential: "OPENROUTER_API_KEY" } };
expect(assertChatCatalogFingerprintLane(lane, {}, []).installedLane).toBe(true);
expect(() => assertChatCatalogFingerprintLane({ ...lane, profile: { ...lane.profile, provider: "codex" } }, {}, [])).toThrow();
expect(() => assertChatCatalogFingerprintLane({ ...lane, scenarioId: "tasks.create-backlog" }, { PAPERCLIP_RUNNER_E2E_INSTALLED_CLI: "/candidate" }, [])).toThrow();
});