stack/packages/discord/tests/engine.test.mjs

import { test } from "node:test";
import assert from "node:assert/strict";
import { readFileSync } from "node:fs";
import { join } from "node:path";
import { createEngine, buildPiArgs, PI_FIXED_ARGS, TOOLS_EXTENSION, READONLY_TOOLS_EXTENSION, assistantText } from "../src/engine-pi.mjs";
import { existsSync } from "node:fs";
import { makeRoot } from "./helpers.mjs";

const fakePi = join(import.meta.dirname, "fake-pi.mjs");

// pi writes agent_settled after agent_end, at times in the next stdout
// chunk, and the fake mirrors a command to its log only once it has read
// it. Both are a few milliseconds; wait for them instead of racing them.
async function until(check, ms = 1000) {
  for (let i = 0; i < ms / 10; i += 1) {
    if (check()) return true;
    await new Promise((res) => setTimeout(res, 10));
  }
  return check();
}
const idle = (engine) => until(() => !engine.busy);

function start(root, extra = {}) {
  const logPath = join(root, "commands.jsonl");
  const logs = [];
  const engine = createEngine({
    command: process.execPath, args: [fakePi], cwd: root, env: { ...process.env, FAKE_PI_LOG: logPath },
    log: (m) => logs.push(m), ...extra,
  });
  engine.start();
  return { engine, logs, commands: () => readFileSync(logPath, "utf8").trim().split("\n").filter(Boolean).map((l) => JSON.parse(l)) };
}

test("engine: buildPiArgs carries the fixed flags, engine settings, session dir and prompt file", () => {
  const args = buildPiArgs({ provider: "zai", model: "glm-5.3", thinking: "high", sessionDir: "/s", appendSystemPromptFile: "/p.md", continueSession: true });
  for (const f of PI_FIXED_ARGS) assert.ok(args.includes(f), f);
  assert.ok(args.includes("--no-tools") && args.includes("--offline"));
  assert.deepEqual(args.slice(-9), ["--provider", "zai", "--model", "glm-5.3", "--thinking", "high", "--session-dir", "/s", "--append-system-prompt", "/p.md", "--continue"].slice(-9));
  assert.ok(!buildPiArgs({ provider: "p", model: "m", thinking: "off", sessionDir: "/s", appendSystemPromptFile: "/p", continueSession: false }).includes("--continue"));
  assert.equal(assistantText({ content: [{ type: "thinking", thinking: "x" }, { type: "text", text: " a " }, { type: "text", text: "b" }] }), "a b".replace(" ", " "));
  assert.ok(!args.includes("--no-builtin-tools") && !args.includes("--extension"), "no extension without tools");
});

test("engine: with tools, buildPiArgs turns pi's own tools off, loads the extension explicitly and allowlists exactly our three", () => {
  const tools = { roots: [{ name: "docs", path: "/r" }], maxFileBytes: 4096, maxCallsPerTurn: 8 };
  const args = buildPiArgs({ provider: "p", model: "m", thinking: "off", sessionDir: "/s", appendSystemPromptFile: "/p", continueSession: false, tools });
  assert.ok(!args.includes("--no-tools"), "--no-tools would hide the extension's tools too");
  assert.ok(args.includes("--no-extensions"), "discovery stays off; only the explicit path loads");
  assert.ok(args.includes("--no-builtin-tools"));
  assert.equal(args[args.indexOf("--extension") + 1], TOOLS_EXTENSION);
  assert.equal(READONLY_TOOLS_EXTENSION, TOOLS_EXTENSION);
  assert.equal(args[args.indexOf("--tools") + 1], "list_dir,read_file,search");
  assert.ok(existsSync(TOOLS_EXTENSION), TOOLS_EXTENSION);
  assert.ok(TOOLS_EXTENSION.endsWith("/packages/discord/extension/tools.mjs"));
  const rw = buildPiArgs({ provider: "p", model: "m", thinking: "off", sessionDir: "/s", appendSystemPromptFile: "/p", continueSession: false, tools: { ...tools, roots: [{ name: "docs", path: "/r" }, { name: "vault", path: "/v", write: true }] } });
  assert.equal(rw[rw.indexOf("--tools") + 1], "list_dir,read_file,search,write_file,edit_file", "a writable root adds exactly the two write tools");
});

test("engine: a run with tool turns settles once, on the answer, with every tool call in the result", async () => {
  const { engine } = start(makeRoot());
  const r = await engine.prompt("tools 3");
  assert.equal(r.text, "read 3 file(s)");
  assert.equal(r.turns, 2);
  assert.equal(r.tools.length, 3);
  assert.deepEqual(r.tools[0], { name: "read_file", root: "docs", path: "f1.md", ok: true, reason: null, bytes: 9, ms: 2 });
  assert.equal(r.tools[2].ok, false);
  assert.match(r.tools[2].reason, /budget/);
  const plain = await engine.prompt("hello");
  assert.equal(plain.text, "echo: hello");
  assert.deepEqual(plain.tools, []);
  assert.equal(plain.turns, 1);
  await idle(engine);
  assert.equal(engine.busy, false);
  await engine.stop();
});

test("engine: a run that ends on a tool-only turn fails the prompt as empty; a retried run settles on the real end", async () => {
  const { engine } = start(makeRoot());
  const r = await engine.prompt("toolonly");
  assert.equal(r.text, "", "no text: the connector turns this into engine-empty");
  assert.equal(r.tools.length, 1);
  const again = await engine.prompt("retry");
  assert.equal(again.text, "after retry");
  await engine.stop();
});

test("engine: one prompt, one turn, text and usage come back", async () => {
  const { engine } = start(makeRoot());
  try {
    const r = await engine.prompt("hello");
    assert.equal(r.text, "echo: hello");
    assert.deepEqual(r.usage, { input: 3, output: 2 });
    await idle(engine);
    assert.equal(engine.busy, false);
  } finally {
    await engine.stop();
  }
});

test("engine: a prompt while streaming is held until pi settles, then sent as its own run, and answered in order", async () => {
  const { engine, commands } = start(makeRoot());
  const first = engine.prompt("slow 150");
  await new Promise((r) => setTimeout(r, 20));
  assert.equal(engine.busy, true);
  const second = engine.prompt("second");
  assert.equal(engine.pendingCount, 2);
  await new Promise((r) => setTimeout(r, 20));
  assert.equal(commands().filter((c) => c.type === "prompt").length, 1, "the second prompt is not sent while pi is busy");
  const [r1, r2] = await Promise.all([first, second]);
  assert.equal(r1.text, "slow reply");
  assert.equal(r2.text, "echo: second");
  const prompts = commands().filter((c) => c.type === "prompt");
  assert.equal(prompts.length, 2);
  // Never a pi follow-up: pi would fold it into the first run and close both
  // answers with one agent_end (the live loss of 2026-09-17).
  assert.equal(prompts[0].streamingBehavior, undefined);
  assert.equal(prompts[1].streamingBehavior, undefined);
  await idle(engine);
  assert.equal(engine.busy, false);
  await engine.stop();
});

test("engine: a held prompt that times out before pi settles fails on its own and is never sent", async () => {
  const { engine, commands } = start(makeRoot());
  const first = engine.prompt("slow 200");
  await new Promise((r) => setTimeout(r, 20));
  await assert.rejects(engine.prompt("late one", { timeoutMs: 50 }), (e) => e.details.code === "timeout" && /waiting for the engine/.test(e.message));
  const r1 = await first;
  assert.equal(r1.text, "slow reply");
  await idle(engine);
  assert.deepEqual(commands().filter((c) => c.type === "prompt").map((c) => c.message), ["slow 200"]);
  assert.deepEqual(commands().filter((c) => c.type === "abort"), [], "a held turn is not aborted; pi never had it");
  await engine.stop();
});

test("engine: timeout sends abort and fails only that turn; the process stays", async () => {
  const { engine, commands, logs } = start(makeRoot());
  await assert.rejects(engine.prompt("slow 5000", { timeoutMs: 100 }), (err) => err.details.code === "timeout");
  assert.ok(await until(() => commands().some((c) => c.type === "abort")), "abort reached pi");
  assert.ok(logs.some((l) => /timed out/.test(l)));
  const r = await engine.prompt("again");
  assert.equal(r.text, "echo: again");
  await engine.stop();
});

test("engine: tool events from a run that outlived its timeout never land in the next prompt's record", async () => {
  const { engine } = start(makeRoot());
  try {
    await assert.rejects(engine.prompt("late 200", { timeoutMs: 40 }), (err) => err.details.code === "timeout");
    const r = await engine.prompt("after late");
    assert.equal(r.text, "echo: after late");
    assert.deepEqual(r.tools, [], "the dead run's read is not this prompt's evidence");
    assert.equal(r.turns, 1, "the dead run's turns are not counted here");
  } finally {
    await engine.stop();
  }
});

test("engine: a malformed JSONL line fails the turn, not the process", async () => {
  const { engine, logs } = start(makeRoot());
  await assert.rejects(engine.prompt("garbage"), (err) => err.details.code === "engine-protocol");
  assert.ok(logs.some((l) => /malformed/.test(l)));
  const r = await engine.prompt("still here");
  assert.equal(r.text, "echo: still here");
  await engine.stop();
});

test("engine: a turn that ends in error rejects with the error code; process exit fails pending turns", async () => {
  const root = makeRoot();
  let exited = null;
  const { engine } = start(root, { onExit: (e) => (exited = e) });
  await assert.rejects(engine.prompt("error"), (err) => err.details.code === "engine-error" && /fake provider error/.test(err.message));
  const pending = engine.prompt("slow 5000");
  await new Promise((r) => setTimeout(r, 20));
  await engine.stop();
  await assert.rejects(pending, (err) => err.details.code === "engine-down");
  assert.ok(exited);
  await assert.rejects(engine.prompt("x"), /not running/);
});