Files
ThothII/backend/test/pi-management.test.ts
T

250 lines
10 KiB
TypeScript

import { mkdtempSync, readFileSync, readdirSync, rmSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { expect, test, vi } from "vitest";
import { loadConfig } from "../src/config.js";
import {
PiManagementError,
createPiManagement,
type PiExecFile,
} from "../src/pi/management.js";
function configFor(settingsFile = join(mkdtempSync(join(tmpdir(), "tht-pi-management-")), "settings.json")) {
return loadConfig({
THT_HARNESS_DIR: "../harness",
SETTINGS_FILE: settingsFile,
PI_BIN: "/usr/local/bin/pi",
PI_MANAGEMENT_TIMEOUT_MS: "750",
});
}
const supportedModels = [
{ provider: "zai", id: "glm-5.2", name: "GLM 5.2", reasoning: true },
{ provider: "deepseek", id: "deepseek-v4", name: "DeepSeek V4", reasoning: true },
];
function successfulExec(calls: Array<{ command: string; args: string[]; timeout: number }>): PiExecFile {
return async (command, args, options) => {
calls.push({ command, args, timeout: options.timeout });
return { stdout: "pi 0.80.3\n", stderr: "" };
};
}
// Catches a Pi executable that emits unexpected text or is invoked through a shell, which could
// turn a version display into a command-injection or information-disclosure surface.
test("status parses only a Pi version from a fixed execFile argument array", async () => {
const calls: Array<{ command: string; args: string[]; timeout: number }> = [];
const service = createPiManagement(configFor(), {
execute: successfulExec(calls),
listModels: async () => supportedModels,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.status()).resolves.toEqual({
version: "0.80.3",
ready: true,
config: { provider: "zai", model: "glm-5.2", reasoning: "medium" },
checkedAt: "2026-08-05T10:00:00.000Z",
});
expect(calls).toEqual([{ command: "/usr/local/bin/pi", args: ["--version"], timeout: 750 }]);
});
// Catches an options response that leaks provider metadata or lets callers choose model IDs that
// Pi did not explicitly enable for this installation.
test("options expose only closed provider, model, and reasoning choices", async () => {
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.options()).resolves.toEqual({
providers: ["zai", "deepseek"],
models: [
{ provider: "zai", id: "glm-5.2" },
{ provider: "deepseek", id: "deepseek-v4" },
],
reasoning: ["low", "medium", "high"],
checkedAt: "2026-08-05T10:00:00.000Z",
});
});
// Catches configuration writes that accept whitespace, unknown choices, or extra free-form fields
// before reaching the durable installation settings file.
test("config rejects invalid free-form values before writing settings", async () => {
const directory = mkdtempSync(join(tmpdir(), "tht-pi-management-invalid-"));
try {
let writes = 0;
const service = createPiManagement(configFor(join(directory, "settings.json")), {
execute: successfulExec([]),
listModels: async () => supportedModels,
readSettings: () => ({}),
saveSettings: () => { writes += 1; return {}; },
});
await expect(service.configure({
provider: "zai ", model: "glm-5.2", reasoning: "medium", unexpected: "value",
} as any)).rejects.toMatchObject<PiManagementError>({ code: "pi_management_invalid_config" });
expect(writes).toBe(0);
} finally {
rmSync(directory, { recursive: true, force: true });
}
});
// Catches a non-atomic implementation that can leave partial settings or temporary files after a
// normal installation-default update.
test("config validates closed choices and atomically persists non-secret defaults", async () => {
const directory = mkdtempSync(join(tmpdir(), "tht-pi-management-write-"));
const settingsFile = join(directory, "settings.json");
try {
const service = createPiManagement(configFor(settingsFile), {
execute: successfulExec([]),
listModels: async () => supportedModels,
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.configure({
provider: "zai", model: "glm-5.2", reasoning: "high",
})).resolves.toEqual({
provider: "zai", model: "glm-5.2", reasoning: "high", updatedAt: "2026-08-05T10:00:00.000Z",
});
expect(JSON.parse(readFileSync(settingsFile, "utf8"))).toEqual({
provider: "zai", model: "glm-5.2", thinking: "high",
});
expect(readdirSync(directory)).toEqual(["settings.json"]);
} finally {
rmSync(directory, { recursive: true, force: true });
}
});
// Catches a hung Pi smoke check that leaves an operator waiting indefinitely or returns raw child
// diagnostics containing provider credentials.
test("smoke uses the configured timeout and reports a sanitized timeout", async () => {
const calls: Array<{ command: string; args: string[]; timeout: number }> = [];
const service = createPiManagement(configFor(), {
execute: async (command, args, options) => {
calls.push({ command, args, timeout: options.timeout });
throw Object.assign(new Error("provider token=raw-provider-token"), { code: "ETIMEDOUT" });
},
listModels: async () => supportedModels,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.test()).resolves.toEqual({
ready: false,
message: "Pi smoke check timed out",
checkedAt: "2026-08-05T10:00:00.000Z",
});
expect(calls).toEqual([{ command: "/usr/local/bin/pi", args: ["--version"], timeout: 750 }]);
});
// Catches a smoke endpoint that validates only the Pi binary/model catalogue and never makes a
// request through the configured provider and model.
test("smoke exercises the configured provider and model", async () => {
const providerChecks: unknown[] = [];
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async (request) => { providerChecks.push(request); },
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
await expect(service.test()).resolves.toEqual({
ready: true,
checkedAt: "2026-08-05T10:00:00.000Z",
});
expect(providerChecks).toEqual([{
provider: "zai", model: "glm-5.2", reasoning: "medium", timeoutMs: expect.any(Number),
}]);
});
// Catches expired provider credentials being treated as ready or raw provider diagnostics being
// reflected through the management API.
test("smoke fails closed and sanitizes configured-provider authentication errors", async () => {
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async () => {
throw new Error('401 {"token":"raw-expired-token","output":"raw-provider-output"}');
},
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
const result = await service.test();
expect(result).toEqual({
ready: false,
message: "Pi provider smoke check failed",
checkedAt: "2026-08-05T10:00:00.000Z",
});
expect(JSON.stringify(result)).not.toMatch(/raw-expired-token|raw-provider-output/);
});
// Catches separate per-phase timeouts that allow a later provider turn to exceed the one
// end-to-end Pi Management smoke budget.
test("smoke applies one deadline across version and a hung provider turn", async () => {
vi.useFakeTimers();
vi.setSystemTime(new Date("2026-08-05T10:00:00.000Z"));
try {
const providerTimeouts: number[] = [];
const service = createPiManagement(configFor(), {
execute: async () => await new Promise((resolve) => setTimeout(
() => resolve({ stdout: "pi 0.80.3\n", stderr: "" }),
500,
)),
listModels: async () => supportedModels,
readSettings: () => ({ provider: "zai", model: "glm-5.2", thinking: "medium" }),
smokeProvider: async ({ timeoutMs }) => {
providerTimeouts.push(timeoutMs);
await new Promise(() => {});
},
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
let settled = false;
const pending = service.test().finally(() => { settled = true; });
await vi.advanceTimersByTimeAsync(500);
expect(providerTimeouts).toEqual([250]);
await vi.advanceTimersByTimeAsync(249);
expect(settled).toBe(false);
await vi.advanceTimersByTimeAsync(1);
await expect(pending).resolves.toEqual({
ready: false,
message: "Pi smoke check timed out",
checkedAt: "2026-08-05T10:00:00.000Z",
});
} finally {
vi.useRealTimers();
}
});
// Catches an unbounded diagnostics endpoint or one that returns bearer tokens and connection
// passwords captured in Pi output.
test("logs keep only the latest 200 redacted lines", async () => {
const source = Array.from({ length: 205 }, (_, index) => `line-${index + 1}`);
source[203] = "Authorization: Bearer raw-bearer-token";
source[204] = "database_url=postgres://thoth:raw-db-password@example.invalid/db";
source[202] = '{"token":"raw-json-secret","password":"raw-json-password"}';
source[201] = "THT_MODEL_API_KEY=raw-env-secret";
const service = createPiManagement(configFor(), {
execute: successfulExec([]),
listModels: async () => supportedModels,
readLogs: () => source.join("\n"),
now: () => new Date("2026-08-05T10:00:00.000Z"),
});
const logs = await service.logs();
expect(logs.checkedAt).toBe("2026-08-05T10:00:00.000Z");
expect(logs.lines).toHaveLength(200);
expect(logs.lines[0]).toBe("line-6");
expect(logs.lines.join("\n")).not.toContain("raw-bearer-token");
expect(logs.lines.join("\n")).not.toContain("raw-db-password");
expect(logs.lines.join("\n")).not.toContain("raw-json-secret");
expect(logs.lines.join("\n")).not.toContain("raw-json-password");
expect(logs.lines.join("\n")).not.toContain("raw-env-secret");
expect(logs.lines.join("\n")).toContain("[REDACTED]");
});