Compare commits

..

1 Commits

Author SHA1 Message Date
agent_coder 15a9eba562 fix(delivery): immutable-кэш ассетов — отключить дефолтный cacheControl @fastify/static (#452)
Хэшированные ассеты отдавали 'cache-control: public, max-age=0' вместо
'public, max-age=31536000, immutable' → повторные заходы ревалидировали каждый
ассет (десятки 304 × мобильный RTT), главный выигрыш #346 не реализовывался.
Причина: у @fastify/static опция cacheControl:true по умолчанию пишет свой
Cache-Control (из maxAge, дефолт 0) ПОСЛЕ setHeaders-колбэка, затирая immutable-
заголовок из resolveStaticAssetHeaders. Фикс — cacheControl:false, колбэк
владеет заголовком. preCompressed не конфликтовал, потому баг был только в
заголовках.

Крайние случаи проверены: locales/vad/иконки получают только vary (без
cache-control → браузер ревалидирует по etag — ок); index.html отдаётся
отдельным wildcard-роутом со своим no-cache (не затронут); preCompressed .br
получает путь с /assets/ → маппинг матчит, immutable ставится.

Тест: bare-fastify + inject() — /assets/<hashed>.js содержит immutable+
max-age=31536000, /locales/en.json — нет. Мутационно: cacheControl:true роняет
ассерт immutable. jest static.module → 5/5.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-10 07:30:44 +03:00
4 changed files with 82 additions and 369 deletions
@@ -28,10 +28,7 @@ const h = vi.hoisted(() => ({
body: Record<string, unknown>;
}) => { body: Record<string, unknown> };
prepareReconnectToStreamRequest?: () => { api?: string };
fetch?: (
input: unknown,
init?: { method?: string; body?: unknown },
) => Promise<unknown>;
fetch?: (input: unknown, init?: { method?: string }) => Promise<unknown>;
},
},
}));
@@ -203,244 +200,6 @@ describe("ChatThread — send now (#198)", () => {
});
});
// #396: in autonomous mode a live sendNow must additionally request the
// AUTHORITATIVE server stop of the detached run (a local abort is only a client
// disconnect the server ignores) and arm a bounded 409 retry so the re-POST
// converges once the one-active-run slot frees. Legacy mode is unchanged.
describe("ChatThread — send now server-stop + supersede retry (#396)", () => {
beforeEach(resetState);
afterEach(cleanup);
// A settled assistant tail => no mount resume (attemptResumeRef false), so the
// "Send now" button is visible for the NEW local streaming turn while
// autonomous runs are enabled.
const settledTail = () => [
row("u1", "user", undefined, "hi"),
row("a1", "assistant", "succeeded", "done"),
];
it("autonomous: sendNow during a live stream calls onServerStop with the chat id", () => {
const { onServerStop } = renderThread({
autonomousRunsEnabled: true,
initialRows: settledTail(),
});
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
expect(h.state.stop).toHaveBeenCalledTimes(1);
expect(onServerStop).toHaveBeenCalledWith("c1");
});
it("legacy (autonomous off): sendNow does NOT call onServerStop and does NOT retry the send", async () => {
const { onServerStop } = renderThread({
autonomousRunsEnabled: false,
initialRows: settledTail(),
});
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
expect(onServerStop).not.toHaveBeenCalled();
// The supersede retry must NOT be armed: a POST that 409s is returned as-is
// (single fetch, no retry).
const fetchMock = vi
.fn()
.mockResolvedValue(
new Response(JSON.stringify({ code: "A_RUN_ALREADY_ACTIVE" }), {
status: 409,
}),
);
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
expect(fetchMock).toHaveBeenCalledTimes(1);
expect(res.status).toBe(409);
});
it("armed supersede send retries 409 A_RUN_ALREADY_ACTIVE and succeeds once the slot frees", async () => {
renderThread({ autonomousRunsEnabled: true, initialRows: settledTail() });
// Arm the retry by performing a live sendNow (autonomous branch sets the ref).
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
const fetchMock = vi
.fn()
// First POST: the old detached run still holds the slot -> 409.
.mockResolvedValueOnce(
new Response(JSON.stringify({ code: "A_RUN_ALREADY_ACTIVE" }), {
status: 409,
}),
)
// Retry: the server stop settled the old run -> 200.
.mockResolvedValueOnce(new Response("ok", { status: 200 }));
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
expect(fetchMock).toHaveBeenCalledTimes(2);
expect(res.status).toBe(200);
});
it("supersede retry is one-shot: a later send (ref cleared) does NOT retry a 409", async () => {
renderThread({ autonomousRunsEnabled: true, initialRows: settledTail() });
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now")); // arms the one-shot
// First armed send: immediately succeeds, consuming the arm.
let fetchMock = vi
.fn()
.mockResolvedValue(new Response("ok", { status: 200 }));
vi.stubGlobal("fetch", fetchMock);
await act(async () => {
await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
});
});
expect(fetchMock).toHaveBeenCalledTimes(1);
// A subsequent send is NOT armed -> a 409 is returned as-is (no retry).
fetchMock = vi.fn().mockResolvedValue(
new Response(JSON.stringify({ code: "A_RUN_ALREADY_ACTIVE" }), {
status: 409,
}),
);
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
expect(fetchMock).toHaveBeenCalledTimes(1);
expect(res.status).toBe(409);
});
it("supersede retry is bounded: exhaustion surfaces the 409 error", async () => {
renderThread({ autonomousRunsEnabled: true, initialRows: settledTail() });
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
// Every attempt 409s -> after 4 attempts the last 409 surfaces.
const fetchMock = vi.fn().mockResolvedValue(
new Response(JSON.stringify({ code: "A_RUN_ALREADY_ACTIVE" }), {
status: 409,
}),
);
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
// 4 attempts total (1 immediate + 3 backoff retries), then give up.
expect(fetchMock).toHaveBeenCalledTimes(4);
expect(res.status).toBe(409);
});
it("armed supersede send does NOT retry a non-409 status", async () => {
renderThread({ autonomousRunsEnabled: true, initialRows: settledTail() });
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
const fetchMock = vi
.fn()
.mockResolvedValue(new Response("boom", { status: 500 }));
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
expect(fetchMock).toHaveBeenCalledTimes(1);
expect(res.status).toBe(500);
});
// Strand-path regression: sendNow arms the supersede retry, but if the promoted
// head is removed before the abort's onFinish lands, flushNext() sends nothing
// (returns false) and NO re-POST consumes the arm. The arm must be disarmed on
// that no-send branch so the NEXT unrelated NORMAL send does not inherit it and
// silently retry a genuine 409 (e.g. a legitimate two-tab conflict) 4x instead
// of surfacing it immediately.
it("strand-path: a stranded supersede arm (flushNext no-send) does NOT retry a later normal 409", async () => {
renderThread({ autonomousRunsEnabled: true, initialRows: settledTail() });
// Arm the retry via a live autonomous sendNow (promotes the head + arms).
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
// Remove the promoted head BEFORE the abort lands, so flushNext() returns
// false (no POST) and the arm would strand without the disarm fix.
fireEvent.click(screen.getByLabelText("Remove queued message"));
// The abort's onFinish now takes the flushOnAbortRef branch, calls flushNext()
// which finds an empty queue and returns false -> the no-send disarm must run.
act(() => {
h.state.onFinish?.({
message: { id: "a1", role: "assistant", parts: [] },
isAbort: true,
isDisconnect: false,
isError: false,
});
});
// No re-POST was sent (nothing to flush).
expect(h.state.sendMessage).not.toHaveBeenCalled();
// A subsequent NORMAL send that 409s must be returned as-is (exactly 1 fetch):
// the stranded arm must NOT cause the genuine 409 to be retried.
const fetchMock = vi
.fn()
.mockResolvedValue(
new Response(JSON.stringify({ code: "A_RUN_ALREADY_ACTIVE" }), {
status: 409,
}),
);
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
expect(fetchMock).toHaveBeenCalledTimes(1);
expect(res.status).toBe(409);
});
it("armed supersede send does NOT retry a 409 with a different (non-A_RUN_ALREADY_ACTIVE) body", async () => {
renderThread({ autonomousRunsEnabled: true, initialRows: settledTail() });
fireEvent.click(screen.getByTestId("queue-btn"));
fireEvent.click(screen.getByLabelText("Send now"));
const fetchMock = vi.fn().mockResolvedValue(
new Response(JSON.stringify({ code: "SOMETHING_ELSE" }), {
status: 409,
}),
);
vi.stubGlobal("fetch", fetchMock);
let res!: Response;
await act(async () => {
res = (await h.state.transport!.fetch!("http://x", {
method: "POST",
body: "{}",
})) as Response;
});
expect(fetchMock).toHaveBeenCalledTimes(1);
expect(res.status).toBe(409);
});
});
// #388: the editor selection is snapshotted at send time and nested inside
// openPage on the wire. The getter is read live from a ref, so each send ships a
// fresh snapshot.
@@ -70,36 +70,6 @@ const RECONNECT_MAX_ATTEMPTS = 5;
// Backoff before attempt N (1-based): 1s, 2s, 4s, 8s, 16s.
const RECONNECT_BASE_DELAY_MS = 1000;
// #396: bounded retry for the "Interrupt and send now" re-send when it races the
// authoritative server stop of the just-superseded detached run. The re-POST can
// arrive before the old run has released the one-active-run slot, so the server
// returns 409 A_RUN_ALREADY_ACTIVE. The server stop guarantees the slot frees, so
// a few short backoffs converge. 4 total attempts: attempt 1 fires immediately,
// then these are the waits BEFORE attempts 2, 3 and 4 (150ms, 300ms, 600ms). If
// all 4 attempts 409, the last 409 surfaces (the banner) — acceptable per #396.
const SUPERSEDE_RETRY_DELAYS_MS = [150, 300, 600];
// The server error code that means "another run is already active for this chat".
const A_RUN_ALREADY_ACTIVE = "A_RUN_ALREADY_ACTIVE";
/**
* #396: defensively decide whether a 409 response is the one-active-run gate
* rejection (code A_RUN_ALREADY_ACTIVE) vs. some other 409. Reads a CLONE so the
* original response body stays intact for the caller when it is returned as-is.
* Any parse failure or unexpected shape => false (do NOT retry).
*/
async function isRunAlreadyActive(response: Response): Promise<boolean> {
try {
const body = (await response.clone().json()) as unknown;
return (
typeof body === "object" &&
body !== null &&
(body as { code?: unknown }).code === A_RUN_ALREADY_ACTIVE
);
} catch {
return false;
}
}
/** The page the user is currently viewing, sent as chat context. */
export interface OpenPageContext {
id: string;
@@ -356,26 +326,6 @@ export default function ChatThread({
const flushOnAbortRef = useRef(false);
const interruptNextSendRef = useRef(false);
// #396: one-shot arm for the bounded 409 A_RUN_ALREADY_ACTIVE retry on the
// "Interrupt and send now" re-send in autonomous mode. sendNow triggers the
// authoritative server stop of the detached run, but that stop and the
// onFinish->flushNext re-POST race: the new POST can hit the one-active-run
// gate before the old detached run has settled, yielding a spurious 409. When
// this ref is armed, the transport's send path retries that 409 with a short
// bounded backoff (the server stop guarantees convergence). A normal send (ref
// not armed) must STILL fail a 409 instantly (e.g. a genuine two-tab conflict).
//
// INVARIANT: sendNow arms this only to be consumed by the ONE re-POST that
// flushNext fires from onFinish. But that re-POST does not always happen (the
// promoted head may be gone, the finish may be a resumed turn, or the arm may
// race a stale finish). To keep the arm strictly one-shot it is disarmed on
// EVERY path where the paired interrupt one-shots (flushOnAbortRef /
// interruptNextSendRef) are cleared without a POST: the transport POST branch
// consumes it (read-and-clear), the onFinish `!flushNext()` no-send branch
// clears it, and the isStreaming-defuse effect clears it symmetrically. So it
// can never leak into a later, unrelated send and retry that send's genuine 409.
const supersedeRetryRef = useRef(false);
// #234 F5: the user pressed Stop while streaming a BRAND-NEW chat whose server
// chat id has not been adopted yet (the `start` chunk carrying it hadn't landed
// when Stop was pressed). A local SSE abort alone does NOT stop the DETACHED
@@ -432,43 +382,7 @@ export default function ChatThread({
}`,
}),
fetch: async (input: RequestInfo | URL, init: RequestInit = {}) => {
if ((init.method ?? "GET") !== "GET") {
// Send path (POST). #396: read-and-clear the one-shot supersede arm
// here so it is strictly scoped to THIS send. When unarmed, behave
// exactly as before — a single fetch, a 409 surfaces instantly (a
// genuine two-tab conflict must NOT be retried).
const supersede = supersedeRetryRef.current;
supersedeRetryRef.current = false;
if (!supersede) return fetch(input, init);
// Buffer a ReadableStream body once so each retry can replay it.
// DefaultChatTransport sends the body as a JSON STRING (replayable as
// is), but guard defensively in case a future SDK streams it.
let sendInit = init;
if (init.body instanceof ReadableStream) {
const buffered = await new Response(init.body).arrayBuffer();
sendInit = { ...init, body: buffered };
}
// Bounded retry: attempt 1 fires immediately, then wait between
// attempts per SUPERSEDE_RETRY_DELAYS_MS. Retry ONLY on a real
// 409 A_RUN_ALREADY_ACTIVE; any other status/body is returned as-is.
for (let attempt = 0; ; attempt++) {
const response = await fetch(input, sendInit);
if (
response.status !== 409 ||
attempt >= SUPERSEDE_RETRY_DELAYS_MS.length ||
!(await isRunAlreadyActive(response))
) {
return response;
}
// The old detached run has not released the one-active-run slot
// yet; the server stop we requested guarantees it will, so back off
// and re-POST (the 409 fired before the user message was persisted,
// so re-POSTing is safe — no duplicate rows).
await new Promise((r) =>
setTimeout(r, SUPERSEDE_RETRY_DELAYS_MS[attempt]),
);
}
}
if ((init.method ?? "GET") !== "GET") return fetch(input, init); // send path untouched
// Reconnect GET: the SDK passes no AbortSignal, so wire our own controller
// for observer Stop / unmount abort.
const controller = new AbortController();
@@ -648,14 +562,9 @@ export default function ChatThread({
setStopNotice(null);
// If the promoted head vanished (e.g. the user removed it before the
// abort landed) flushNext sends nothing — clear the one-shot interrupt
// tag AND the #396 supersede arm so neither can leak onto the next
// unrelated send (no re-POST will consume the arm here). On a real send
// the tag is consumed by prepareSendMessagesRequest and the arm by the
// transport POST branch, so both stay untouched then.
if (!flushNext()) {
interruptNextSendRef.current = false;
supersedeRetryRef.current = false;
}
// tag so it can't leak onto the next unrelated send. On a real send the
// tag is consumed by prepareSendMessagesRequest and stays untouched.
if (!flushNext()) interruptNextSendRef.current = false;
return;
}
if (isAbort || isDisconnect || isError) return;
@@ -964,30 +873,6 @@ export default function ChatThread({
setQueue(promoteToHead(queuedRef.current, id));
flushOnAbortRef.current = true;
interruptNextSendRef.current = true;
// #396: in autonomous mode the turn is a DETACHED run — a local stop()
// is only a client disconnect the server ignores, so the run keeps going.
// The onFinish->flushNext re-POST would then hit the one-active-run gate
// and get a spurious 409 A_RUN_ALREADY_ACTIVE. Mirror handleStop: request
// the AUTHORITATIVE server stop so the detached run settles, and arm the
// one-shot bounded 409 retry BEFORE stop() so the re-send converges once
// the slot frees. Read chatId live from chatIdRef (adopted at the `start`
// chunk). If it is not known yet (brand-new chat, first moment of its
// first turn), defer the server stop via stopPendingRef exactly as
// handleStop does — the onServerChatId adoption effect fires it once the
// id lands; the retry stays armed so the re-send still converges then.
if (autonomousRunsEnabled) {
supersedeRetryRef.current = true; // arm the bounded 409 retry
if (chatIdRef.current) {
onServerStop?.(chatIdRef.current);
} else {
// Same #234-F5 sub-window limitation documented in handleStop: if the
// local abort below cancels the reader before the `start` chunk lands,
// the adoption effect never runs and the deferred stop never fires. Not
// a regression; at minimum we don't strand refs (the isStreaming effect
// defuses stopPendingRef on the next turn start).
stopPendingRef.current = true;
}
}
stop(); // -> onFinish({ isAbort: true }) flushes the promoted head
} else {
// Nothing to interrupt: just send it now (no interrupt note).
@@ -999,7 +884,7 @@ export default function ChatThread({
sendMessageRef.current?.({ text: msg.text });
}
},
[setQueue, stop, setResumedTurnPair, autonomousRunsEnabled, onServerStop],
[setQueue, stop, setResumedTurnPair],
);
// Stop the current turn. ALWAYS abort the local SSE (`stop()`) so the composer
@@ -1059,13 +944,6 @@ export default function ChatThread({
setStopNotice(null);
flushOnAbortRef.current = false;
interruptNextSendRef.current = false;
// #396: symmetric with the other one-shot interrupt flags — defuse a stale
// supersede arm that was set but whose expected re-POST never fired (the
// turn finished in the same tick as the click, or the promoted head was
// gone), so it can never leak into this (or a later) turn's send and retry
// that send's genuine 409. A legit arm is consumed by the transport POST
// branch before this new turn streams, so this does not clobber it.
supersedeRetryRef.current = false;
// #234 F5: a new turn is starting — drop any pending deferred-stop from a
// previous turn that never adopted an id, so it can never fire against this
// (or a later) unrelated turn's run. A deferred stop for the CURRENT turn is
@@ -1,3 +1,8 @@
import * as fs from 'node:fs';
import * as os from 'node:os';
import { join } from 'node:path';
import Fastify, { FastifyInstance } from 'fastify';
import fastifyStatic from '@fastify/static';
import { resolveStaticAssetHeaders } from './static.module';
// Unit tests for the static-asset cache classifier extracted from the
@@ -33,3 +38,69 @@ describe('resolveStaticAssetHeaders', () => {
expect(headers['vary']).toBe('Accept-Encoding');
});
});
// Integration test proving the ACTUAL response header emitted by @fastify/static
// with the exact registration options StaticModule uses. This is the regression
// guard for #452: without `cacheControl: false`, @fastify/static writes its own
// `Cache-Control: public, max-age=0` AFTER the setHeaders callback, overwriting
// the immutable header — the /assets/ assertion below would then fail.
describe('static.module @fastify/static registration (integration)', () => {
let app: FastifyInstance;
let tmpDir: string;
beforeAll(async () => {
tmpDir = fs.mkdtempSync(join(os.tmpdir(), 'static-module-spec-'));
fs.mkdirSync(join(tmpDir, 'assets'), { recursive: true });
fs.mkdirSync(join(tmpDir, 'locales'), { recursive: true });
fs.writeFileSync(
join(tmpDir, 'assets', 'index-a1b2c3.js'),
'console.log(1);',
);
fs.writeFileSync(join(tmpDir, 'locales', 'en.json'), '{"hello":"world"}');
app = Fastify();
// Mirror StaticModule.onModuleInit's registration options exactly.
await app.register(fastifyStatic, {
root: tmpDir,
wildcard: false,
preCompressed: true,
cacheControl: false,
setHeaders: (res, filePath) => {
for (const [name, value] of Object.entries(
resolveStaticAssetHeaders(filePath),
)) {
res.setHeader(name, value);
}
},
});
await app.ready();
});
afterAll(async () => {
await app.close();
fs.rmSync(tmpDir, { recursive: true, force: true });
});
it('serves a hashed /assets/ file with an immutable, 1-year cache-control', async () => {
const res = await app.inject({
method: 'GET',
url: '/assets/index-a1b2c3.js',
});
expect(res.statusCode).toBe(200);
const cacheControl = res.headers['cache-control'];
expect(cacheControl).toContain('immutable');
expect(cacheControl).toContain('max-age=31536000');
});
it('serves a non-hashed /locales/ file WITHOUT an immutable cache-control', async () => {
const res = await app.inject({ method: 'GET', url: '/locales/en.json' });
expect(res.statusCode).toBe(200);
// resolveStaticAssetHeaders sets no cache-control here and cacheControl:false
// stops @fastify/static from adding one, so the browser revalidates by
// etag/last-modified — either an absent header or one without `immutable`.
const cacheControl = res.headers['cache-control'];
if (cacheControl !== undefined) {
expect(cacheControl).not.toContain('immutable');
}
});
});
@@ -115,6 +115,11 @@ export class StaticModule implements OnModuleInit {
// Serve the build-time .br/.gz neighbour when the client accepts it
// (see vite-plugin-compression2 in apps/client/vite.config.ts).
preCompressed: true,
// @fastify/static's default cacheControl:true writes its own
// Cache-Control (from maxAge, default 0) AFTER the setHeaders callback,
// silently overwriting the immutable header that resolveStaticAssetHeaders
// sets — disable it so setHeaders/resolveStaticAssetHeaders own the header.
cacheControl: false,
setHeaders: (res, filePath) => {
for (const [name, value] of Object.entries(
resolveStaticAssetHeaders(filePath),