Files
penguin-harness/packages/cli/test/model-ref-pairing.test.ts
T
Yaowei Zheng d4faee3a1e Changelog, dev startup, README, AgentHub 0.4.0, model catalog, and landing site (#7)
Branch-length batch covering tooling, the model layer, the Web App and the public
surfaces. Highlights:

- Changelog: a per-release `changelog/<version>/` tree, grouped by the surface each
  change touches, with a root CHANGELOG.md holding one line per release.
- Dev startup: `scripts/dev-prebuild.mjs` serializes the skills+core prebuild behind a
  lock and keeps `pnpm install` current; `pnpm dev` runs server+web together.
- AgentHub 0.3.3 -> 0.4.0: OmniMessage complete payloads carry one opaque `fidelity`
  object in place of item-level `signature`/`phase`, threaded verbatim through Trace,
  replay and resume; malformed classification adapted to the new error types.
- Model layer: a model is always referenced by an explicit `(provider, model_id)` pair.
  The provider is never inferred, guessed or defaulted -- both the catalog inference and
  the unique-match config resolution are gone, and CLI, SDK, server routes and
  run_subagent all require the complete pair. Catalog gains the Qwen Token Plan, Qwen
  Pay-As-You-Go and Fireworks AI gateways, plus an expanded OpenRouter group.
- Web App: catalog preset sync and per-group speed test on the Models page, positional
  slash commands, a markdown renderer, skill-library update reminders, and a vertically
  centred draft page whose upward menus size themselves to the room available.
- Public surfaces: restructured READMEs, the penguin.ooo landing site and blog, refreshed
  benchmark results for both suites, and the demo videos playing on the landing page.

Includes the fixes from a full review of the branch: 23 confirmed findings, among them a
provider-inference bug that could send one vendor's API key to another vendor's endpoint,
and an Escape handler that destroyed the composer's contents unrecoverably.

Verified on the branch head: pnpm test (1127 passing, 7 packages), pnpm typecheck and
pnpm format:check clean, Playwright e2e 14/14.
2026-07-21 17:43:31 +08:00

107 lines
4.1 KiB
TypeScript

/**
* `penguin run` / `penguin chat`: a model reference is always an explicit
* (provider, model_id) pair. Commander can only mark each option required on its own, so
* the "both or neither" rule is enforced inside the action — supplying exactly one of
* --model-id / --provider is a usage error (never a lookup against the configured models),
* while supplying neither falls back to the Project's default model.
*/
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { Command } from "commander";
import { registerChatCommand } from "../src/commands/chat.js";
import { registerRunCommand } from "../src/commands/run.js";
import { getMessages } from "../src/i18n.js";
// The --resume case below reaches createAgent, which initializes Agent state on disk; point
// the data root at a throwaway directory so no test ever writes to the real ~/.penguin/data.
let tmpHome: string;
let prevHome: string | undefined;
beforeEach(async () => {
prevHome = process.env.PENGUIN_HOME;
tmpHome = await fs.mkdtemp(path.join(os.tmpdir(), "penguin-cli-pairing-"));
process.env.PENGUIN_HOME = tmpHome;
});
afterEach(async () => {
if (prevHome === undefined) delete process.env.PENGUIN_HOME;
else process.env.PENGUIN_HOME = prevHome;
await fs.rm(tmpHome, { recursive: true, force: true });
});
/** Runs one command, capturing stdout / stderr and the exit code (without exiting the process). */
async function runCommand(
register: (program: Command, t: ReturnType<typeof getMessages>) => void,
args: string[],
): Promise<{ out: string; err: string; code: number }> {
const program = new Command();
program.exitOverride();
register(program, getMessages("en"));
const out: string[] = [];
const err: string[] = [];
const outSpy = vi.spyOn(process.stdout, "write").mockImplementation((chunk) => {
out.push(String(chunk));
return true;
});
const errSpy = vi.spyOn(process.stderr, "write").mockImplementation((chunk) => {
err.push(String(chunk));
return true;
});
const prevExitCode = process.exitCode;
process.exitCode = undefined;
try {
await program.parseAsync(["node", "penguin", ...args]);
return { out: out.join(""), err: err.join(""), code: Number(process.exitCode ?? 0) };
} catch (e) {
const exitCode = (e as { exitCode?: number }).exitCode;
return { out: out.join(""), err: err.join(""), code: exitCode || 1 };
} finally {
outSpy.mockRestore();
errSpy.mockRestore();
process.exitCode = prevExitCode;
}
}
describe("run: --model-id and --provider must be given together", () => {
it("--model-id without --provider: error on stderr, exit code 1", async () => {
const bad = await runCommand(registerRunCommand, [
"run",
"-m",
"hi",
"--model-id",
"deepseek-v4-flash",
]);
expect(bad.code).toBe(1);
expect(bad.err).toContain("--model-id and --provider must be given together");
});
it("--provider without --model-id: same error (the pair is never half-specified)", async () => {
const bad = await runCommand(registerRunCommand, ["run", "-m", "hi", "--provider", "deepseek"]);
expect(bad.code).toBe(1);
expect(bad.err).toContain("--model-id and --provider must be given together");
});
});
describe("chat: --model-id and --provider must be given together", () => {
it("--model-id without --provider: error on stderr, exit code 1", async () => {
const bad = await runCommand(registerChatCommand, ["chat", "--model-id", "deepseek-v4-flash"]);
expect(bad.code).toBe(1);
expect(bad.err).toContain("--model-id and --provider must be given together");
});
it("--resume plus a lone --model-id keeps the more specific resume error", async () => {
const bad = await runCommand(registerChatCommand, [
"chat",
"--resume",
"sess-1",
"--model-id",
"deepseek-v4-flash",
]);
expect(bad.code).toBe(1);
expect(bad.out).toContain("--resume does not accept");
expect(`${bad.out}${bad.err}`).not.toContain("must be given together");
});
});