fix(coding-agent): let a started RPC or print shutdown finish; only a repeated signal forces exit (#11752)

Follow-up to #11746 for the case @fcatuhe reported on #11599: a second
shutdown trigger cut off cleanup.

Problem: Paseo stops pi by closing stdin and sending SIGTERM in the same
tick (SIGKILL 2 s later); systemd sends SIGTERM and stdin closes after.
In RPC mode:

- stdin EOF, then SIGTERM: `shutdown()` removed pi's SIGTERM handler
when it started, so the signal killed pi (exit 143) mid-`dispose()`.
- SIGTERM, then stdin EOF: the second `shutdown()` call ran
`process.exit()`.

A pending MCP token refresh was lost: the server had rotated the refresh
token, the next pi sent the old one, and the server revoked the grant.

Rule after this change: once a shutdown has started, a stdin EOF or a
single signal does not interrupt it; a second signal exits at once.
SIGKILL still always works.

- **RPC mode** (`rpc-mode.ts`): signal handlers stay registered until
exit; `shutdown()` runs once and later calls do nothing; the signal
handler counts signals and exits only on a repeated one.
- **Print mode** (`print-mode.ts`): the final `finally` removed the
signal handlers before `disposeRuntime()`, so a signal during the final
disposal killed pi. Handlers are now removed after it,
`disposeRuntime()` returns the shared in-flight disposal (a signal then
waits for it), and a repeated signal exits at once, as before.
- **Interactive mode**: unchanged. It already lets a started shutdown
finish.

Docs (`docs/rpc.md`) and the CHANGELOG are updated.

## Testing
- `test/rpc-prompt-response-semantics.test.ts`: EOF then SIGTERM,
SIGTERM then EOF (both wait for a slow dispose, exit once with 0 and
143), and EOF then two SIGTERMs (exits at once with 143). All three fail
on main.
- `test/print-mode.test.ts`: SIGTERM during the final disposal waits for
it, a second SIGTERM exits with 143, handlers are removed afterwards.
Fails on main.
- Real process, `pi --mode rpc` with a `session_shutdown` handler that
takes 1 s and real signals:
  - EOF then SIGTERM: cleanup done, exit 0 (main: no cleanup, exit 143)
  - SIGTERM then EOF: cleanup done, exit 143
  - EOF then two SIGTERMs: exit 143 at once
- `npm run check` passes; all `test/rpc*` and `test/print-mode` tests
pass.
This commit is contained in:
Petr Houška 2026-11-03 22:21:44 +01:00 • committed by GitHub
parent efb45b51d4
commit ace560c302
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 167 additions and 26 deletions

View file

@ -152,4 +152,37 @@ describe("runPrintMode", () => {
expect(exitCode).toBe(1);
expect(errorSpy).toHaveBeenCalled();
});
// A signal during the final disposal used to hit no handler and kill pi mid-dispose.
it("waits for the final disposal when SIGTERM arrives during it, and exits on a repeated SIGTERM", async () => {
const exitSpy = vi.spyOn(process, "exit").mockImplementation((() => undefined) as never);
const runtimeHost = createRuntimeHost(createAssistantMessage({ text: "done" }));
let finishDispose = () => {};
runtimeHost.dispose.mockImplementation(
() =>
new Promise<void>((resolve) => {
finishDispose = resolve;
}),
);
const listenersBefore = process.listenerCount("SIGTERM");
const run = runPrintMode(runtimeHost as unknown as Parameters<typeof runPrintMode>[0], {
mode: "text",
initialMessage: "Say done",
});
await vi.waitFor(() => expect(runtimeHost.dispose).toHaveBeenCalledTimes(1));
expect(process.listenerCount("SIGTERM")).toBe(listenersBefore + 1);
process.emit("SIGTERM");
await new Promise((resolve) => setTimeout(resolve, 10));
expect(exitSpy).not.toHaveBeenCalled();
expect(runtimeHost.dispose).toHaveBeenCalledTimes(1);
process.emit("SIGTERM");
expect(exitSpy).toHaveBeenCalledWith(143);
finishDispose();
await run;
expect(process.listenerCount("SIGTERM")).toBe(listenersBefore);
});
});

View file

@ -8,7 +8,7 @@ import {
getModel,
type Model,
} from "@earendil-works/pi-ai/compat";
import { afterEach, describe, expect, it, vi } from "vitest";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { AgentSession } from "../src/core/agent-session.ts";
import type { AgentSessionRuntime } from "../src/core/agent-session-runtime.ts";
import { AuthStorage } from "../src/core/auth-storage.ts";
@ -162,6 +162,7 @@ async function createRuntimeHost(options: {
async function startRpcMode(options: Parameters<typeof createRuntimeHost>[0]): Promise<{
lineHandler: (line: string) => void;
runtimeHost: AgentSessionRuntime;
cleanup: () => Promise<void>;
}> {
rpcIo.outputLines = [];
@ -171,7 +172,7 @@ async function startRpcMode(options: Parameters<typeof createRuntimeHost>[0]): P
void runRpcMode(runtimeHost);
await vi.waitFor(() => expect(rpcIo.lineHandler).toBeDefined());
return { lineHandler: rpcIo.lineHandler!, cleanup };
return { lineHandler: rpcIo.lineHandler!, runtimeHost, cleanup };
}
describe("RPC prompt response semantics", () => {
@ -550,3 +551,94 @@ describe("RPC extension shutdown requests", () => {
}
});
});
describe("RPC shutdown triggers", () => {
// Earlier tests leave RPC instances listening (process.exit never runs). Detach every signal and
// stdin "end" listener so emitted triggers reach only this test's instance, then restore them.
const signals: NodeJS.Signals[] = ["SIGTERM", "SIGHUP"];
let savedSignalListeners: Array<[NodeJS.Signals, NodeJS.SignalsListener[]]> = [];
let savedEndListeners: Array<() => void> = [];
beforeEach(() => {
savedSignalListeners = signals.map((signal) => [signal, process.listeners(signal)]);
savedEndListeners = process.stdin.listeners("end") as Array<() => void>;
for (const signal of signals) process.removeAllListeners(signal);
process.stdin.removeAllListeners("end");
});
afterEach(() => {
for (const signal of signals) process.removeAllListeners(signal);
process.stdin.removeAllListeners("end");
for (const [signal, listeners] of savedSignalListeners) {
for (const listener of listeners) process.on(signal, listener);
}
for (const listener of savedEndListeners) process.stdin.on("end", listener);
rpcIo.outputLines = [];
rpcIo.lineHandler = undefined;
vi.restoreAllMocks();
});
async function startWithSlowDispose() {
const exitSpy = vi.spyOn(process, "exit").mockImplementation((() => undefined) as never);
vi.spyOn(process.stdin, "pause").mockImplementation(() => process.stdin);
const started = await startRpcMode({ withAuth: false, responseDelayMs: 0 });
let finishDispose = () => {};
const disposeFinished = new Promise<void>((resolve) => {
finishDispose = resolve;
});
vi.mocked(started.runtimeHost.dispose).mockImplementation(() => disposeFinished);
return { ...started, exitSpy, finishDispose };
}
// fcatuhe's report on #11599: Paseo closes stdin and sends SIGTERM together.
it("lets a shutdown started by stdin EOF finish when one SIGTERM follows", async () => {
const { runtimeHost, exitSpy, finishDispose, cleanup } = await startWithSlowDispose();
try {
process.stdin.emit("end");
await vi.waitFor(() => expect(runtimeHost.dispose).toHaveBeenCalledTimes(1));
// Without a listener, a real SIGTERM would kill the process mid-dispose.
expect(process.listenerCount("SIGTERM")).toBe(1);
process.emit("SIGTERM");
await sleep(10);
expect(exitSpy).not.toHaveBeenCalled();
finishDispose();
await vi.waitFor(() => expect(exitSpy).toHaveBeenCalledWith(0));
expect(exitSpy).toHaveBeenCalledTimes(1);
} finally {
await cleanup();
}
});
it("lets a shutdown started by SIGTERM finish when stdin EOF follows", async () => {
const { runtimeHost, exitSpy, finishDispose, cleanup } = await startWithSlowDispose();
try {
process.emit("SIGTERM");
await vi.waitFor(() => expect(runtimeHost.dispose).toHaveBeenCalledTimes(1));
process.stdin.emit("end");
await sleep(10);
expect(exitSpy).not.toHaveBeenCalled();
finishDispose();
await vi.waitFor(() => expect(exitSpy).toHaveBeenCalledWith(143));
expect(exitSpy).toHaveBeenCalledTimes(1);
expect(runtimeHost.dispose).toHaveBeenCalledTimes(1);
} finally {
await cleanup();
}
});
it("exits at once on a repeated signal during shutdown", async () => {
const { runtimeHost, exitSpy, cleanup } = await startWithSlowDispose();
try {
process.stdin.emit("end");
await vi.waitFor(() => expect(runtimeHost.dispose).toHaveBeenCalledTimes(1));
process.emit("SIGTERM");
process.emit("SIGTERM");
expect(exitSpy).toHaveBeenCalledTimes(1);
expect(exitSpy).toHaveBeenCalledWith(143);
} finally {
await cleanup();
}
});
});