Compare commits

..

1 Commits

Author SHA1 Message Date
diegosouzapw
3ce03abae3 fix(sse): add first-byte watchdog to the TLS-fingerprint transport (#12656)
The wreq-js TLS-fingerprint transport resolved the Response as soon as
upstream headers arrived, with zero guard around how long the caller then
waited for the body's first byte. TlsClient's only timing control, a flat
timeout, defaults to 600_000ms, matching the reported 90-600s stall window
exactly.

Add guardTlsFirstByte() (open-sse/utils/tlsFirstByteWatchdog.ts), which
races the body's first read() against a short, env-overridable watchdog
(TLS_FIRST_BYTE_WATCHDOG_MS, default 10s). A healthy body is unaffected
(bytes already buffered are replayed through a passthrough stream); a
stalled body cancels the wreq reader and throws, letting proxyFetch's
existing TLS-fallback catch blocks fall through to the direct/proxy
dispatcher. A non-replay-safe request (e.g. a POST with a body) still
throws instead of being silently retried, reusing isTlsFallbackReplaySafe.
2026-09-10 15:35:13 -03:00
12 changed files with 304 additions and 146 deletions

View File

@@ -1646,6 +1646,7 @@ CURSOR_USER_AGENT="Cursor/3.4"
# ── TLS client (wreq-js fingerprint proxy) ──
# TLS_CLIENT_TIMEOUT_MS=600000 # Inherits from FETCH_TIMEOUT_MS by default
# TLS_FIRST_BYTE_WATCHDOG_MS=10000 # #12656: bounds time-to-first-byte on the wreq body (0 disables)
# ── API Bridge (/v1 proxy server) ──
# API_BRIDGE_PROXY_TIMEOUT_MS=600000 # Proxy hop timeout (default: 10min)

View File

@@ -35,24 +35,16 @@ export function resolveOpencodeTarget(opts = {}) {
baseUrl = `http://localhost:${Number(opts.port ?? process.env.PORT ?? 20128) || 20128}`;
}
// Precedence: explicit --api-key flag > OMNIROUTE_API_KEY env var > active
// context's management token. A context's accessToken/apiKey is a CLI
// management credential (oma_live_...) with no /v1/* inference scope — it
// must never silently outrank a real inference key the caller supplied
// either as a flag or via the ambient env var (mirrors the explicit >
// ambient-env > context precedence documented in bin/cli/api.mjs's
// buildHeaders()). Only fall back to the context token when neither an
// explicit flag nor the env var is set.
let apiKey = opts.apiKey ?? opts["api-key"];
if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
if (!apiKey) {
try {
const c = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
apiKey = c?.accessToken || c?.apiKey || "";
apiKey = c?.accessToken || c?.apiKey;
} catch {
/* no context auth */
}
}
if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
return { baseUrl: baseUrl.replace(/\/+$/, ""), apiKey };
}
@@ -185,17 +177,8 @@ export function registerSetupOpencode(program) {
"--allow-container-write",
"Write even when the target is inside a container and not mounted from the host"
)
.action(async (opts, cmd) => {
// Commander parses the ancestor program's own global --api-key option
// (bin/cli/program.mjs, bound to .env("OMNIROUTE_API_KEY")) against any
// occurrence of the flag in argv, so it wins the value even when the
// user typed --api-key AFTER `setup-opencode` — this local option's own
// `opts.apiKey` never sees it. cmd.optsWithGlobals() resolves to the
// correct value either way ("globals overwrite locals" is exactly the
// outcome we want here, since the global option is where the value
// always actually lands).
const resolvedOpts = { ...opts, apiKey: cmd.optsWithGlobals().apiKey ?? opts.apiKey };
const code = await runSetupOpencodeCommand(resolvedOpts);
.action(async (opts) => {
const code = await runSetupOpencodeCommand(opts);
if (code !== 0) process.exit(code);
});
}

View File

@@ -0,0 +1 @@
- fix(sse): add first-byte watchdog to the TLS-fingerprint transport so a stalled wreq body falls back instead of hanging for minutes (#12656)

View File

@@ -1 +0,0 @@
- fix(cli): setup-opencode no longer sends an active context's management token to `/v1/models` when `--api-key`/`OMNIROUTE_API_KEY` is supplied — an explicit flag or the env var now always outranks the context's token, and the flag itself is no longer swallowed by the parent program's global `--api-key` option (#12783)

View File

@@ -729,6 +729,7 @@ REQUEST_TIMEOUT_MS (global override)
│ ├─→ FETCH_HEADERS_TIMEOUT_MS (inherits from FETCH_TIMEOUT_MS)
│ ├─→ FETCH_BODY_TIMEOUT_MS (inherits from FETCH_TIMEOUT_MS)
│ ├─→ TLS_CLIENT_TIMEOUT_MS (inherits from FETCH_TIMEOUT_MS)
│ │ └── TLS_FIRST_BYTE_WATCHDOG_MS (independent, default: 10000)
│ ├── FETCH_CONNECT_TIMEOUT_MS (independent, default: 30000)
│ └── FETCH_KEEPALIVE_TIMEOUT_MS (independent, default: 4000)
├─→ STREAM_IDLE_TIMEOUT_MS (inherits from REQUEST_TIMEOUT_MS, default: 600000)
@@ -766,6 +767,7 @@ REQUEST_TIMEOUT_MS (global override)
| `FETCH_CONNECT_TIMEOUT_MS` | `30000` | TCP connection establishment timeout. |
| `FETCH_KEEPALIVE_TIMEOUT_MS` | `4000` | Keep-alive socket idle timeout. |
| `TLS_CLIENT_TIMEOUT_MS` | = `FETCH_TIMEOUT_MS` | TLS fingerprint proxy (wreq-js) timeout. |
| `TLS_FIRST_BYTE_WATCHDOG_MS` | `10000` | Bounds time-to-first-byte on the wreq-js TLS-fingerprint transport's body specifically; `TLS_CLIENT_TIMEOUT_MS` alone cannot catch a stalled body since it resolves as soon as headers arrive (#12656). A timeout cancels the wreq reader and falls back to the direct/proxy dispatcher; `0` disables the watchdog. |
| `API_BRIDGE_PROXY_TIMEOUT_MS` | `30000` | Proxy hop timeout for `/v1` bridge requests. |
| `FIRECRAWL_BASE_URL` | `https://api.firecrawl.dev` | Point the Firecrawl web-fetch executor at a self-hosted instance (API key optional off-cloud). |
| `FIRECRAWL_TIMEOUT_MS` | `30000` | Per-request timeout for the Firecrawl web-fetch executor. |

View File

@@ -31,6 +31,13 @@ unavailable; a caller may explicitly select a fallback outside this wrapper.
- Proxy resolution (priority): `HTTPS_PROXY``HTTP_PROXY``ALL_PROXY` (also lower-case)
- Timeout: `TLS_CLIENT_TIMEOUT_MS` (inherits from `FETCH_TIMEOUT_MS`, default 600000)
- `wreq-js` Response is fetch-compatible (`headers`, `text()`, `json()`, `clone()`, `body`).
- First-byte watchdog (`open-sse/utils/tlsFirstByteWatchdog.ts`, #12656): `TlsClient.fetch()`
resolves as soon as upstream headers arrive, so `TLS_CLIENT_TIMEOUT_MS` alone cannot bound a
body that never yields a first byte. `guardTlsFirstByte()` races the body's first `read()`
against `TLS_FIRST_BYTE_WATCHDOG_MS` (default `10000`, `0` disables it); a healthy body is
unaffected, while a stalled body cancels the wreq reader and lets `proxyFetch`'s existing
TLS-fallback logic fall through to the direct/proxy dispatcher (a non-replay-safe request, e.g.
a POST with a body, still throws instead of being silently retried).
### Web-cookie provider transport — wreq-js 3.2.0

View File

@@ -13,7 +13,7 @@ import {
proxyConfigToUrl,
proxyUrlForLogs,
} from "./proxyDispatcher.ts";
import tlsClient, { type TlsFetchOptions } from "./tlsClient.ts";
import tlsClient, { type TlsFetchOptions, guardTlsFirstByte } from "./tlsClient.ts";
import { isProxyReachable } from "@/lib/proxyHealth";
import {
isControlPlaneProxyDirectFallbackEnabled,
@@ -807,7 +807,7 @@ async function patchedFetch(
...tlsProfileForProvider(tlsStore?.provider),
});
if (tlsStore) tlsStore.used = true;
return response;
return await guardTlsFirstByte(response);
} catch (error) {
if (isCallerAbort(error, getEffectiveSignal(input, options))) throw error;
const sessionHadCookies =
@@ -1100,7 +1100,7 @@ async function patchedFetch(
...tlsProfileForProvider(tlsStore?.provider),
});
if (tlsStore) tlsStore.used = true;
return response;
return await guardTlsFirstByte(response);
} catch (error) {
if (isCallerAbort(error, getEffectiveSignal(input, options))) throw error;
const sessionHadCookies =

View File

@@ -1,6 +1,9 @@
import { createHash } from "node:crypto";
import * as nodeModule from "node:module";
import { getTlsClientTimeoutConfig } from "@/shared/utils/runtimeTimeouts";
// #12656 — re-exported so proxyFetch.ts (frozen at its file-size cap) can
// import the first-byte watchdog alongside TlsClient without adding a line.
export { guardTlsFirstByte } from "./tlsFirstByteWatchdog.ts";
const runtimeRequire = nodeModule.createRequire(import.meta.url);

View File

@@ -0,0 +1,115 @@
import { getTlsFirstByteWatchdogMs } from "@/shared/utils/runtimeTimeouts";
// #12656 — the wreq-js TLS-fingerprint transport resolves the Response as
// soon as upstream headers arrive, with zero protection around how long the
// caller then waits for the body's first byte. The only timing guard on that
// path, TlsClient's flat `timeout`, defaults to 600_000ms — matching the
// reported 90-600s stall window exactly. This module races the body's first
// `read()` against a short, env-overridable watchdog: a healthy body is
// completely unaffected (bytes already buffered are replayed through a
// passthrough stream, nothing is dropped), while a body that never yields
// within the deadline cancels the wreq reader and throws so the caller
// (proxyFetch's existing TLS-fallback catch blocks) can fall back to the
// direct/proxy dispatcher instead of hanging for minutes.
export const TLS_FIRST_BYTE_WATCHDOG_TIMEOUT_CODE = "TLS_FIRST_BYTE_WATCHDOG_TIMEOUT";
type BodyReader = ReadableStreamDefaultReader<Uint8Array>;
type FirstReadResult = ReadableStreamReadResult<Uint8Array>;
function createWatchdogTimeoutError(timeoutMs: number): Error & { code: string } {
const err = new Error(
`TLS fingerprint transport produced no first byte within ${timeoutMs}ms`
) as Error & { code: string };
err.name = "TimeoutError";
err.code = TLS_FIRST_BYTE_WATCHDOG_TIMEOUT_CODE;
return err;
}
export function isTlsFirstByteWatchdogTimeout(err: unknown): boolean {
return (
!!err &&
typeof err === "object" &&
"code" in err &&
(err as { code?: unknown }).code === TLS_FIRST_BYTE_WATCHDOG_TIMEOUT_CODE
);
}
async function raceFirstChunk(reader: BodyReader, timeoutMs: number): Promise<FirstReadResult> {
let timer: ReturnType<typeof setTimeout> | undefined;
const timeoutPromise = new Promise<never>((_, reject) => {
timer = setTimeout(() => reject(createWatchdogTimeoutError(timeoutMs)), timeoutMs);
timer.unref?.();
});
try {
return await Promise.race([reader.read(), timeoutPromise]);
} finally {
clearTimeout(timer);
}
}
async function pumpRemainingChunks(
reader: BodyReader,
controller: ReadableStreamDefaultController<Uint8Array>
): Promise<void> {
try {
for (;;) {
const { done, value } = await reader.read();
if (done) {
controller.close();
return;
}
if (value) controller.enqueue(value);
}
} catch (error) {
controller.error(error);
}
}
function buildPassthroughStream(
reader: BodyReader,
firstChunk: FirstReadResult
): ReadableStream<Uint8Array> {
return new ReadableStream<Uint8Array>({
start(controller) {
if (firstChunk.value) controller.enqueue(firstChunk.value);
if (firstChunk.done) {
controller.close();
return;
}
void pumpRemainingChunks(reader, controller);
},
cancel(reason) {
void reader.cancel(reason).catch(() => {});
},
});
}
/**
* Guard a TLS-fingerprint Response's first body byte with a short watchdog.
* Resolves with an equivalent Response (status/headers preserved) whose body
* has already produced at least one byte, or throws
* TLS_FIRST_BYTE_WATCHDOG_TIMEOUT after cancelling the reader so the caller
* can fall back to another transport.
*/
export async function guardTlsFirstByte(
response: Response,
timeoutMs: number = getTlsFirstByteWatchdogMs()
): Promise<Response> {
if (!timeoutMs || timeoutMs <= 0 || !response.body) return response;
const reader = response.body.getReader();
let firstChunk: FirstReadResult;
try {
firstChunk = await raceFirstChunk(reader, timeoutMs);
} catch (error) {
await reader.cancel(error).catch(() => {});
throw error;
}
return new Response(buildPassthroughStream(reader, firstChunk), {
status: response.status,
statusText: response.statusText,
headers: response.headers,
});
}

View File

@@ -35,6 +35,14 @@ export const DEFAULT_MAIN_SERVER_HEADERS_TIMEOUT_MS = 66_000;
// failure, wait this long for the real completion to land. Set to 0 to
// disable and restore the old immediate-fail behavior.
export const DEFAULT_STREAM_DISCONNECT_GRACE_PERIOD_MS = 10_000;
// #12656 — the wreq-js TLS-fingerprint transport resolves the Response as
// soon as upstream headers arrive; the only timing guard on the body itself
// was TlsClient's flat `timeout` (defaults to DEFAULT_FETCH_TIMEOUT_MS =
// 600_000ms), matching the reporter's observed 90-600s stall range exactly.
// This bounds time-to-first-byte specifically for that transport so a wedged
// wreq body falls back fast instead of riding the 10-minute ceiling. Set to
// 0 to disable the watchdog entirely.
export const DEFAULT_TLS_FIRST_BYTE_WATCHDOG_MS = 10_000;
function hasEnvValue(env: EnvSource, name: string): boolean {
const raw = env[name];
@@ -212,6 +220,16 @@ export function getTlsClientTimeoutConfig(
};
}
export function getTlsFirstByteWatchdogMs(
env: EnvSource = process.env,
logger?: TimeoutLogger
): number {
return readTimeoutMs(env, "TLS_FIRST_BYTE_WATCHDOG_MS", DEFAULT_TLS_FIRST_BYTE_WATCHDOG_MS, {
allowZero: true,
logger,
});
}
export function getApiBridgeTimeoutConfig(
env: EnvSource = process.env,
logger?: TimeoutLogger

View File

@@ -1,121 +0,0 @@
import assert from "node:assert/strict";
import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { test } from "node:test";
import { resolveOpencodeTarget } from "../../bin/cli/commands/setup-opencode.mjs";
/** Point OMNIROUTE_CONTEXT config resolution at an isolated, throwaway DATA_DIR. */
function withIsolatedContext(contextConfig, fn) {
const dir = mkdtempSync(join(tmpdir(), "omniroute-setup-opencode-test-"));
const originalDataDir = process.env.DATA_DIR;
process.env.DATA_DIR = dir;
writeFileSync(
join(dir, "config.json"),
JSON.stringify({
version: 1,
currentContext: "remote",
contexts: { remote: contextConfig },
})
);
try {
return fn();
} finally {
if (originalDataDir === undefined) delete process.env.DATA_DIR;
else process.env.DATA_DIR = originalDataDir;
rmSync(dir, { recursive: true, force: true });
}
}
function withEnvApiKey(value, fn) {
const original = process.env.OMNIROUTE_API_KEY;
if (value === undefined) delete process.env.OMNIROUTE_API_KEY;
else process.env.OMNIROUTE_API_KEY = value;
try {
return fn();
} finally {
if (original === undefined) delete process.env.OMNIROUTE_API_KEY;
else process.env.OMNIROUTE_API_KEY = original;
}
}
test("setup-opencode: --api-key typed AFTER the subcommand name is not stolen by the parent program's global option", async () => {
const { createProgram } = await import("../../bin/cli/program.mjs");
const program = createProgram();
const setupOpencode = program.commands.find((c) => c.name() === "setup-opencode");
assert.ok(setupOpencode, "setup-opencode subcommand must be registered");
let capturedApiKey;
setupOpencode._actionHandler = null; // avoid the real network-calling action
setupOpencode.action((opts, cmd) => {
capturedApiKey = cmd.optsWithGlobals().apiKey ?? opts.apiKey;
});
await program.parseAsync(
[
"node",
"omniroute",
"setup-opencode",
"--remote",
"http://100.64.0.1:20128",
"--api-key",
"sk-TESTKEY123",
],
{ from: "node" }
);
assert.equal(
capturedApiKey,
"sk-TESTKEY123",
"the CLI-supplied --api-key value must reach the setup-opencode action handler"
);
});
test("resolveOpencodeTarget: (a) explicit --api-key flag wins over an active context's management token", () => {
withEnvApiKey(undefined, () => {
withIsolatedContext(
{ baseUrl: "http://100.64.0.1:20128", accessToken: "oma_live_CONTEXT_TOKEN" },
() => {
const { apiKey } = resolveOpencodeTarget({ apiKey: "sk-FLAG", context: "remote" });
assert.equal(apiKey, "sk-FLAG");
}
);
});
});
test("resolveOpencodeTarget: (b) OMNIROUTE_API_KEY env wins over an active context's management token when no flag is passed", () => {
withEnvApiKey("sk-ENVKEY", () => {
withIsolatedContext(
{ baseUrl: "http://100.64.0.1:20128", accessToken: "oma_live_CONTEXT_TOKEN" },
() => {
const { apiKey } = resolveOpencodeTarget({ context: "remote" });
assert.equal(apiKey, "sk-ENVKEY");
}
);
});
});
test("resolveOpencodeTarget: (c) the context's token is used only when neither a flag nor the env var is set", () => {
withEnvApiKey(undefined, () => {
withIsolatedContext(
{ baseUrl: "http://100.64.0.1:20128", accessToken: "oma_live_CONTEXT_TOKEN" },
() => {
const { apiKey } = resolveOpencodeTarget({ context: "remote" });
assert.equal(apiKey, "oma_live_CONTEXT_TOKEN");
}
);
});
});
test("resolveOpencodeTarget: falls back to '' when neither a flag, env var, nor a resolvable context is present", () => {
withEnvApiKey(undefined, () => {
withIsolatedContext({ baseUrl: "http://100.64.0.1:20128" }, () => {
const { apiKey } = resolveOpencodeTarget({
remote: "http://100.64.0.1:20128",
context: "__no-such-context__",
});
assert.equal(apiKey, "");
});
});
});

View File

@@ -0,0 +1,150 @@
import assert from "node:assert/strict";
import test from "node:test";
import {
proxyFetch,
runWithTlsTracking,
setTlsClientForTest,
} from "../../open-sse/utils/proxyFetch.ts";
import type { TlsFetchOptions } from "../../open-sse/utils/tlsClient.ts";
// #12656 — when ENABLE_TLS_FINGERPRINT=true, the wreq-js TLS-fingerprint
// transport used to return the Response as soon as headers resolved, with no
// guard on how long the caller then waited for the body's first byte (the
// only timing control, TlsClient's flat `timeout`, defaults to 600_000ms).
// These tests promote the RED probe from the #12656 plan-file into a
// permanent regression suite for the first-byte watchdog added in
// open-sse/utils/tlsFirstByteWatchdog.ts.
type EnvState = Record<string, string | undefined>;
const ENV_KEYS = [
"ENABLE_TLS_FINGERPRINT",
"TLS_FINGERPRINT_PROVIDERS",
"TLS_FIRST_BYTE_WATCHDOG_MS",
] as const;
async function withEnv(env: EnvState, fn: () => Promise<void> | void): Promise<void> {
const prior = Object.fromEntries(ENV_KEYS.map((key) => [key, process.env[key]]));
for (const key of ENV_KEYS) {
if (env[key] === undefined) delete process.env[key];
else process.env[key] = env[key];
}
try {
await fn();
} finally {
for (const key of ENV_KEYS) {
if (prior[key] === undefined) delete process.env[key];
else process.env[key] = prior[key];
}
setTlsClientForTest(null);
}
}
function fakeTlsClient(fetch: (url: string, options?: TlsFetchOptions) => Promise<Response>) {
return { available: true, fetch };
}
function neverYieldingBody(): ReadableStream<Uint8Array> {
return new ReadableStream<Uint8Array>({
pull() {
// Never enqueue, never close — simulates the reported wreq stall.
},
});
}
test("#12656 (a) a stalled wreq body falls back to the direct dispatcher within the watchdog window", async () => {
await withEnv({ ENABLE_TLS_FINGERPRINT: "true", TLS_FIRST_BYTE_WATCHDOG_MS: "80" }, async () => {
setTlsClientForTest(
fakeTlsClient(
async () =>
new Response(neverYieldingBody(), {
status: 200,
headers: { "content-type": "text/event-stream" },
})
)
);
let dispatcherCalls = 0;
const startedAt = Date.now();
const tracked = await runWithTlsTracking("openai", () =>
proxyFetch(
"https://example-provider.test/v1/chat/completions",
{ method: "GET" },
{
undiciFetch: async () => {
dispatcherCalls++;
return new Response("fallback-body", { status: 200 });
},
}
)
);
const elapsedMs = Date.now() - startedAt;
assert.equal(dispatcherCalls, 1);
assert.equal(await tracked.result.text(), "fallback-body");
// Well under the OLD 600_000ms flat TlsClient timeout — proves the
// watchdog fired instead of riding the default request timeout.
assert.ok(elapsedMs < 5_000, `expected fast fallback, took ${elapsedMs}ms`);
// tlsStore.used is flipped back to false on the fallback path in
// proxyFetch's existing catch block, same as any other TLS failure.
assert.equal(tracked.tlsFingerprintUsed, false);
});
});
test("#12656 (b) a healthy/fast wreq body is unaffected by the watchdog", async () => {
await withEnv({ ENABLE_TLS_FINGERPRINT: "true", TLS_FIRST_BYTE_WATCHDOG_MS: "80" }, async () => {
setTlsClientForTest(fakeTlsClient(async () => new Response("healthy-body", { status: 200 })));
let dispatcherCalls = 0;
const tracked = await runWithTlsTracking("openai", () =>
proxyFetch(
"https://example-provider.test/v1/chat/completions",
{ method: "GET" },
{
undiciFetch: async () => {
dispatcherCalls++;
return new Response("fallback-body", { status: 200 });
},
}
)
);
assert.equal(dispatcherCalls, 0);
assert.equal(await tracked.result.text(), "healthy-body");
assert.equal(tracked.tlsFingerprintUsed, true);
});
});
test("#12656 (c) a non-replay-safe POST throws on watchdog timeout instead of silently retrying", async () => {
await withEnv({ ENABLE_TLS_FINGERPRINT: "true", TLS_FIRST_BYTE_WATCHDOG_MS: "80" }, async () => {
setTlsClientForTest(
fakeTlsClient(
async () =>
new Response(neverYieldingBody(), {
status: 200,
headers: { "content-type": "text/event-stream" },
})
)
);
let dispatcherCalls = 0;
await assert.rejects(
runWithTlsTracking("openai", () =>
proxyFetch(
"https://example-provider.test/v1/chat/completions",
{ method: "POST", body: "{}" },
{
undiciFetch: async () => {
dispatcherCalls++;
return new Response("unexpected", { status: 200 });
},
}
)
),
(error: Error) =>
error.message === "TLS fingerprint request failed; request is not safe to replay"
);
assert.equal(dispatcherCalls, 0);
});
});