Files
stack/packages/cli/tests/session-launch.test.mjs
T
jason.woltje 39eadf8ba8 Row 332 R2 (#1830): hermetic pi launches in cli tests, pi bundle default, review F2 and F3
The cli tests that launch pi deleted only the session login names, so pi's
preflight passed or refused by whatever provider keys the host exported. A
shared helper now deletes every credential pi's preflight reads and gives pi
launches one made-up key. The refusal itself is unchanged.

pi bundle() takes a default argument again, so a call with none returns the
non-proxy bundle, as before P3. pi.bundle leaves out a launch.models entry
whose provider has no proxy route instead of failing every pi launch (F2);
malformed proxy entries still refuse. The invalid session proxy context
BundleError gets the code invalid-proxy-context. New tests cover F2, the code,
and the three proxy account branches in the launcher (F3).
2026-11-02 15:22:17 -06:00

415 lines
21 KiB
JavaScript

// Session runs (row 269, 264b, #1774): every session of a thread runs on its
// own, with its own store under threads/<b>/<t>/sessions/<s>/ and its own
// workspace under session-workspaces/<b>/<instance>/<s>/, and a lock beside
// the workspace keeps it to one writer. A legacy session (op legacy-3l) keeps
// the thread's old store, and its workspace shows inside the sandbox at the
// old instance path. Real runners in the bwrap sandbox; a stub adapter keeps
// a history in the store and answers with what it found, its cwd and what
// the cwd holds.
//
// The host is thread-launch.test.mjs's: startBroker on bootConfig's config,
// with the ops the broker child forwards, and the human capability from
// bindHuman directly.
import { test } from "node:test";
import assert from "node:assert/strict";
import { spawn, spawnSync } from "node:child_process";
import { chmodSync, existsSync, mkdirSync, readdirSync, readFileSync, symlinkSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import { fileURLToPath } from "node:url";
import { launchDoc } from "../../business/tests/helpers.mjs";
import { BusError } from "../../bus/src/broker.mjs";
import { startBroker } from "../../bus/src/runtime.mjs";
import { Store } from "../../bus/src/store.mjs";
import { transition } from "../../processing-control/src/state.mjs";
import { gitEnv } from "../../seat/src/checkout.mjs";
import { startTimeOf } from "../../seat/src/proc.mjs";
import { sandboxProblem } from "../../seat/src/sandbox.mjs";
import { launchLogFile, readSessions, Registry } from "../../seat/src/session.mjs";
import { bootConfig, loadSystem } from "../src/config.mjs";
import { createLauncher } from "../src/launcher.mjs";
import { fakeHarnesses, fixture, tmp, withoutHostCredentials } from "./helpers.mjs";
// A thread made by hand gets the default session the 3k-3l migration gives a legacy thread, with
// the thread's id (as in thread-launch.test.mjs).
const DEFAULT_SESSION = [
"INSERT INTO sessions(at,business,thread,id,instance,owner,name,op) SELECT at,business,id,id,instance,owner,'default','legacy-3l' FROM threads WHERE id=?",
"INSERT INTO session_defaults(at,thread,session,by) SELECT at,id,id,'migration-3l' FROM threads WHERE id=?",
];
const ADAPTER = fileURLToPath(new URL("./fixtures/session-adapter.mjs", import.meta.url));
const skip = sandboxProblem() ?? false;
async function until(fn, ms = 20000) {
const end = Date.now() + ms;
while (Date.now() < end) {
const v = await fn();
if (v) return v;
await new Promise((r) => setTimeout(r, 50));
}
throw new Error("timed out waiting");
}
// A mutant's kill is an assertion failure, not a timeout (sage-2707), so the waits a mutant could
// stall return what they last saw and the assertions after them decide.
async function settle(fn, ms = 20000) {
const end = Date.now() + ms;
let v;
while (Date.now() < end) {
v = await fn();
if (v) return v;
await new Promise((r) => setTimeout(r, 50));
}
return v;
}
function gitIn(cwd, ...args) {
const r = spawnSync("git", ["-c", "user.name=test", "-c", "[email protected]", "-C", cwd, ...args], { env: gitEnv(), encoding: "utf8" });
assert.equal(r.status, 0, r.stderr);
}
// Each directory made 0700, as the store and workspace checks want.
function privateDir(...parts) {
for (let i = 1; i <= parts.length; i++) {
const d = join(...parts.slice(0, i));
if (!existsSync(d)) mkdirSync(d, { mode: 0o700 });
if (i > 1) chmodSync(d, 0o700);
}
return join(...parts);
}
// The assistant is the thread instance; sonnet is its model's limit.
function prepare(t, { sonnet = 3, idle = 1 } = {}) {
const root = tmp(t, "mosaic-session-");
const f = fixture(root, "acme", (doc) => {
doc.roles.chief.vars = { harness: "pi", model: "claude-opus-5-5", thinking: "high" };
doc.roles.assistant = { definition: "assistant", vars: { harness: "pi", model: "claude-sonnet-5-5", thinking: "high" } };
doc.launch = launchDoc("chief", ["coder", "assistant"], { opus: 1, sonnet });
doc.launch.threadIdleSeconds = idle;
return doc;
});
withoutHostCredentials(f.env, { piKey: true });
const project = f.doc.projects.stack.root;
gitIn(project, "init", "-q", "-b", "main");
writeFileSync(join(project, "file.txt"), "one\n");
gitIn(project, "add", "file.txt");
gitIn(project, "commit", "-q", "-m", "one");
const adapter = join(root, "adapter.sh");
writeFileSync(adapter, `exec '${process.execPath}' '${ADAPTER}'\n`, { mode: 0o644 });
return { root, f, adapter };
}
// A host and its launcher on the prepared root. `ops` replaces launch ops, given the runtime.
async function start(t, { f, adapter }, { tickMs = 100, ops: replace } = {}) {
const system = loadSystem({ env: f.env });
const { trackers, ...boot } = bootConfig({ system, businessId: "acme", env: f.env });
assert.equal(trackers, undefined);
const runtime = await startBroker(boot);
const ops = {
identity: (m) => runtime.identity(m.cap),
authorizeLaunch: (m) => runtime.authorizeLaunch(m.cap, m.instance),
refuse: (m) => runtime.refuse(m.cap, m.code, m.subject),
endLaunch: (m) => runtime.endLaunch(m.record),
credentialStatus: (m) => runtime.credentialStatus(m.business, m.role),
threadsState: (m) => runtime.threadsState(m.business),
threadIdle: (m) => runtime.threadIdle(m.record),
mayLaunch: (m) => runtime.mayLaunch(m),
landHeld: (m) => runtime.landHeld(m.record),
landHolders: (m) => runtime.landHolders(m.business),
landRelease: (m) => runtime.landRelease(m.record),
...replace?.(runtime),
};
const refusing = (what, fn) => async (m) => {
try {
return fn(m);
} catch (e) {
const code = e instanceof BusError ? e.code : `${what}-refused`;
throw Object.assign(new Error(`${what} refused: ${code}`), { code });
}
};
const hooks = [];
let closing = null;
const host = {
business: "acme",
path: runtime.path,
dataRoot: f.dataRoot,
op: refusing("launch-op", (m) => {
if (!Object.hasOwn(ops, m.op)) throw new BusError("invalid-host-request");
return ops[m.op](m);
}),
bindLaunch: refusing("launch bind", (r) => runtime.bindLaunch(r)),
beforeClose: (fn) => void hooks.push(fn),
};
const logs = [];
const launcher = createLauncher({
host,
system,
env: f.env,
makeLoader: await fakeHarnesses(t, { pi: adapter, "claude-code": adapter }),
sessionDefaults: { pollInterval: 100 },
harnessVersion: "0.85.1",
readOnly: [ADAPTER],
threadTickMs: tickMs,
log: (l) => logs.push(l),
});
const close = () =>
(closing ??= (async () => {
for (const fn of hooks) await fn(0);
await runtime.close();
})());
t.after(close);
await launcher.listen();
const human = runtime.broker.bindHuman({ business: "acme", human: f.doc.human, via: "cli", outsideAgent: true });
const call = (verb, args = {}) => runtime.broker.request(human, { verb, args });
return { host, runtime, launcher, call, logs, close };
}
const launchLog = (f) =>
existsSync(launchLogFile(f.dataRoot, "acme"))
? readFileSync(launchLogFile(f.dataRoot, "acme"), "utf8").trim().split("\n").map((l) => JSON.parse(l))
: [];
const events = (f, event) => launchLog(f).filter((e) => e.event === event);
const sessionWs = (f, session) => join(f.dataRoot, "session-workspaces", "acme", "assistant", session);
// The refusals once there are n, or once anything launched.
const outcome = async (f, n = 1) => {
await settle(() => events(f, "refused").length >= n || events(f, "launch").length);
return events(f, "refused").map((e) => [e.session, e.code]);
};
const historyOf = (p) => (existsSync(p) ? readFileSync(p, "utf8") : null);
// Send to one session of a thread; reply() waits for the assistant's RESULT reply in that session.
function send(call, thread, session, body) {
const sent = call("thread.send", { thread, ...(session ? { session } : {}), body });
const reply = async () => {
const r = await until(() => call("thread.messages", { thread, ...(session ? { session } : {}) }).find((m) => m.in_reply_to === sent.id && m.class === "RESULT"));
assert.equal(r.from_role, "assistant");
return JSON.parse(r.body.match(/THREAD (\{.*\})/)[1]);
};
return { sent, reply };
}
// A thread made with thread.create, its default session and a second named one.
function twoSessions(call) {
const project = call("project.create", { name: "stack work", repo: "stack" }).id;
const A = call("thread.create", { project, name: "alpha" }).id;
const [{ id: D }] = call("session.list", { thread: A });
const S = call("session.create", { thread: A, name: "second", op: "op-second" }).id;
return { project, A, D, S };
}
test("REQ-THREAD-2 REQ-LAUNCH-1 two sessions of one thread, and another thread's default, run at once, each with its own store and workspace; a restart of one resumes only that one", { skip, timeout: 90000 }, async (t) => {
const prepared = prepare(t, { idle: 5 });
const { f } = prepared;
const host = await start(t, prepared);
const { project, A, D, S } = twoSessions(host.call);
const B = host.call("thread.create", { project, name: "beta" }).id;
const [{ id: BD }] = host.call("session.list", { thread: B });
const toD = send(host.call, A, D, "first for D");
const toS = send(host.call, A, S, "first for S");
const toB = send(host.call, B, null, "first for B");
// All three run together (M1, M2: a shared workspace would refuse the second start busy).
await settle(() => readSessions(f.dataRoot).length === 3 || events(f, "refused").length);
assert.deepEqual(events(f, "refused"), []);
assert.deepEqual(readSessions(f.dataRoot).map((s) => [s.thread, s.session]).sort(), [[A, D], [A, S], [B, BD]].sort());
const [sawD, sawS, sawB] = await Promise.all([toD.reply(), toS.reply(), toB.reply()]);
// Each session's history is its own (M5), and each runs in its own workspace at its own path (M8).
assert.deepEqual([sawD.body, sawD.before, sawD.cwd], ["first for D", [], sessionWs(f, D)]);
assert.deepEqual([sawS.body, sawS.before, sawS.cwd], ["first for S", [], sessionWs(f, S)]);
assert.deepEqual([sawB.body, sawB.before, sawB.cwd], ["first for B", [], sessionWs(f, BD)]);
const store = (thread, session) => join(f.dataRoot, "threads", "acme", thread, "sessions", session, "session", "history");
assert.deepEqual([historyOf(store(A, D)), historyOf(store(A, S)), historyOf(store(B, BD))], ["first for D\n", "first for S\n", "first for B\n"]);
for (const thread of [A, B]) assert.equal(existsSync(join(f.dataRoot, "threads", "acme", thread, "session")), false);
assert.equal(existsSync(join(f.dataRoot, "workspaces", "acme", "assistant")), false, "no thread session uses the old instance workspace");
for (const e of events(f, "launch")) assert.ok([D, S, BD].includes(e.session), JSON.stringify(e));
// All three stop when idle, and each lock goes with its run.
await until(() => events(f, "end").length === 3, 30000);
assert.deepEqual(readSessions(f.dataRoot), []);
for (const s of [D, S, BD]) assert.equal(existsSync(`${sessionWs(f, s)}.lock`), false, s);
// The named session's next message starts only that session (M9), which finds only its history.
const again = await send(host.call, A, S, "second for S").reply();
assert.deepEqual([again.before, again.cwd], [["first for S"], sessionWs(f, S)]);
assert.deepEqual(events(f, "launch").slice(3).map((e) => [e.thread, e.session]), [[A, S]]);
assert.equal(historyOf(store(A, D)), "first for D\n");
});
// D9 (M7): a thread from before 3l. Its legacy session resumes from the thread's old store, and
// its new workspace shows at the old instance path, which the transcripts recorded as the cwd.
// The old host workspace isn't mounted.
test("REQ-THREAD-2 REQ-LAUNCH-1 a legacy session resumes the thread's old store at the old in-sandbox cwd, in a workspace of its own", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
const store = new Store(f.dataRoot);
const at = () => new Date().toISOString();
store.run("INSERT INTO projects(id,at,business,name,repo,created_by) VALUES(?,?,?,?,?,?)", "p-hand", at(), "acme", "hand made", "stack", "jason");
store.run("INSERT INTO threads(id,at,business,project,instance,owner,name) VALUES(?,?,?,?,?,?,?)", "th-legacy", at(), "acme", "p-hand", "assistant", "jason", "old");
for (const sql of DEFAULT_SESSION) store.run(sql, "th-legacy");
store.close();
const old = privateDir(f.dataRoot, "threads", "acme", "th-legacy");
writeFileSync(join(privateDir(old, "session"), "history"), "old sentinel\n");
privateDir(old, "claude-projects");
writeFileSync(join(privateDir(f.dataRoot, "workspaces", "acme", "assistant"), "old-file"), "the 264a workspace\n");
const host = await start(t, prepared);
const saw = await send(host.call, "th-legacy", null, "after 3l").reply();
assert.deepEqual(saw.before, ["old sentinel"]);
assert.equal(saw.cwd, join(f.dataRoot, "workspaces", "acme", "assistant"));
assert.equal(saw.entries.includes("old-file"), false, "the old host workspace isn't mounted");
assert.equal(readFileSync(join(old, "session", "history"), "utf8"), "old sentinel\nafter 3l\n");
assert.equal(existsSync(join(old, "sessions")), false);
assert.ok(existsSync(sessionWs(f, "th-legacy")));
assert.deepEqual(readdirSync(join(f.dataRoot, "workspaces", "acme", "assistant")), ["old-file"]);
assert.deepEqual(events(f, "launch").map((e) => [e.thread, e.session]), [["th-legacy", "th-legacy"]]);
});
// T2, M3: another host's live lock on the session's workspace refuses the start before any
// checkout. Once that host is gone the lock is stale, and the next start takes it over.
test("REQ-THREAD-2 REQ-LAUNCH-1 a live lock on a session workspace refuses session-workspace-busy before any checkout; a stale one is taken over", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
const host = await start(t, prepared);
const { A, S } = twoSessions(host.call);
const other = spawn("sleep", ["60"], { stdio: "ignore" });
const gone = new Promise((r) => other.once("exit", r));
t.after(() => other.kill("SIGKILL"));
const otherStart = await until(() => startTimeOf(other.pid));
privateDir(f.dataRoot, "session-workspaces", "acme", "assistant");
const lock = `${sessionWs(f, S)}.lock`;
const held = `${JSON.stringify({ hostPid: other.pid, hostStartTime: otherStart, business: "acme", instance: "assistant", thread: A, session: S })}\n`;
writeFileSync(lock, held, { mode: 0o600 });
const toS = send(host.call, A, S, "for S");
assert.deepEqual(await outcome(f), [[S, "session-workspace-busy"]]);
assert.equal(events(f, "refused")[0].thread, A);
assert.deepEqual(events(f, "launch"), []);
assert.deepEqual(readSessions(f.dataRoot), []);
assert.deepEqual(readdirSync(sessionWs(f, S)), [], "no checkout");
assert.equal(readFileSync(lock, "utf8"), held);
other.kill("SIGKILL");
await gone;
const saw = await toS.reply();
assert.deepEqual([saw.before, saw.cwd], [[], sessionWs(f, S)]);
await until(() => events(f, "end").length === 1);
assert.equal(existsSync(lock), false);
});
// Q2 (BUILD.md:177-179, t1-sessions.md:109): an earlier host's sessionless run of the instance is
// still live, so no session of it starts until that run has exited. A sleep child stands in for
// its runner; its outer pid is gone, so recover() has nothing to kill and keeps it as a survivor.
test("REQ-THREAD-2 REQ-LAUNCH-1 a session start refuses legacy-run-live while an earlier host's sessionless run lives, and starts once it has exited", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
const runner = spawn("sleep", ["60"], { stdio: "ignore" });
const gone = new Promise((r) => runner.once("exit", r));
t.after(() => runner.kill("SIGKILL"));
const runnerStartTime = await until(() => startTimeOf(runner.pid));
new Registry(f.dataRoot).add({ business: "acme", instance: "assistant", thread: "th-old", run: "run-left", harness: "pi", pid: 2 ** 22 + 7, startTime: "gone", runnerPid: runner.pid, runnerStartTime });
const host = await start(t, prepared);
assert.ok(host.logs.includes(`run run-left (assistant) from an earlier host still runs (pid ${2 ** 22 + 7}, runner ${runner.pid}): no session of assistant starts until it exits`), host.logs.join("\n"));
const { A, S } = twoSessions(host.call);
const toS = send(host.call, A, S, "for S");
assert.deepEqual(await outcome(f), [[S, "legacy-run-live"]]);
assert.equal(events(f, "refused")[0].thread, A);
assert.deepEqual(events(f, "launch"), [], "nothing spawned");
assert.deepEqual(readSessions(f.dataRoot), []);
assert.equal(existsSync(sessionWs(f, S)), false, "refused before the workspace");
runner.kill("SIGKILL");
await gone;
assert.equal(await settle(() => events(f, "launch").length), 1, "it starts once the run has exited");
const saw = await toS.reply();
assert.deepEqual([saw.before, saw.cwd], [[], sessionWs(f, S)]);
await until(() => events(f, "end").length === 1);
});
// T2, C3: a symlinked session root refuses session-workspace-unsafe, at the segment check.
test("REQ-THREAD-2 REQ-LAUNCH-1 a symlinked session workspace root refuses session-workspace-unsafe and launches nothing", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
const elsewhere = privateDir(prepared.root, "elsewhere");
symlinkSync(elsewhere, join(f.dataRoot, "session-workspaces"));
const host = await start(t, prepared);
const { A, D } = twoSessions(host.call);
send(host.call, A, D, "for D");
assert.deepEqual(await outcome(f), [[D, "session-workspace-unsafe"]]);
assert.deepEqual(events(f, "launch"), []);
assert.deepEqual(readdirSync(elsewhere), []);
});
// T2, M4: every segment of the session path is a real directory, but workspaces/<b> is a symlink
// to it, so only the realpath compare finds that the session workspace holds the legacy root.
test("REQ-THREAD-2 REQ-LAUNCH-1 a session workspace that holds the legacy workspace root refuses session-workspace-overlap and launches nothing", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
const host = await start(t, prepared);
const { A, D } = twoSessions(host.call);
const ws = privateDir(f.dataRoot, "session-workspaces", "acme", "assistant", D);
symlinkSync(ws, join(privateDir(f.dataRoot, "workspaces"), "acme"));
send(host.call, A, D, "for D");
assert.deepEqual(await outcome(f), [[D, "session-workspace-overlap"]]);
assert.deepEqual(events(f, "launch"), []);
assert.deepEqual(readdirSync(ws), []);
});
// T2: a symlink among the store's segments refuses thread-store-refused before the workspace.
test("REQ-THREAD-2 REQ-LAUNCH-1 a symlinked session store refuses thread-store-refused and makes no workspace", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
const host = await start(t, prepared);
const { A, D } = twoSessions(host.call);
const elsewhere = privateDir(prepared.root, "elsewhere");
symlinkSync(elsewhere, join(privateDir(f.dataRoot, "threads", "acme", A), "sessions"));
send(host.call, A, D, "for D");
assert.deepEqual(await outcome(f), [[D, "thread-store-refused"]]);
assert.match(events(f, "refused")[0].why, /is unsafe$/);
assert.deepEqual(events(f, "launch"), []);
assert.deepEqual(readdirSync(elsewhere), []);
assert.equal(existsSync(join(f.dataRoot, "session-workspaces")), false);
});
// T2, M6 and the halt fence (C2). The credentialStatus op runs in start() after check() returned.
// Its first call halts and resumes, a new generation with no halt, so only start()'s own
// admission(admissionGeneration) refuses, before the session workspace is made. On the retry,
// the recheck's mayLaunch op (inside check(), after the lock is taken) halts once it has answered,
// and the recheck's admission() refuses processing-halted. Neither attempt spawns, and the second releases its lock.
test("REQ-THREAD-2 REQ-LAUNCH-1 a named session's start refuses processing-generation-changed, then processing-halted, after check() and before any spawn", { skip, timeout: 60000 }, async (t) => {
const prepared = prepare(t);
const { f } = prepared;
let credentials = 0;
let halts = 0;
const halt = () => transition(f.dataRoot, { business: "acme", human: f.doc.human, halted: true });
const host = await start(t, prepared, {
ops: (runtime) => ({
credentialStatus: (m) => {
if (m.role === "assistant" && ++credentials === 1) {
transition(f.dataRoot, { business: "acme", human: f.doc.human, halted: false, generation: halt().generation });
halts++;
}
return runtime.credentialStatus(m.business, m.role);
},
// The halt lands after the op answers: halted inside it, the bus's own fence
// (runtime.mjs processingWork) throws and the launcher refuses limit-check-failed.
mayLaunch: async (m) => {
const may = await runtime.mayLaunch(m);
if (m.instance === "assistant" && credentials === 2 && halts === 1) {
halt();
halts++;
}
return may;
},
}),
});
const { A, S } = twoSessions(host.call);
send(host.call, A, S, "for S");
const refused = await outcome(f, 2);
assert.deepEqual(refused, [[S, "processing-generation-changed"], [S, "processing-halted"]]);
assert.deepEqual([credentials, halts], [2, 2], "check() passed both times");
assert.equal(events(f, "launch").length, 0);
assert.deepEqual(readSessions(f.dataRoot), []);
assert.equal(existsSync(join(f.dataRoot, "launches", "acme")), false, "no run directory");
assert.ok(existsSync(sessionWs(f, S)), "the retry made the workspace");
assert.equal(existsSync(`${sessionWs(f, S)}.lock`), false, "and released its lock");
});