fix(server): throttle the cost-bearing proxies by default

The OpenAI endpoints (/api/realtime/token, /api/openai/hud-summary) now
allow 30 requests per minute per client IP and the Google Places endpoints
120, the caps the Pinokio build already ships. GEV_RATELIMIT_OPENAI_PER_MIN
and GEV_RATELIMIT_GOOGLE_PER_MIN still override them and exactly 0 disables
them; an unreadable value falls back to the default rather than to
unlimited.

Salvaged from #683 onto current main.

Co-authored-by: Sameh Khamis <[email protected]>
Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

server/providers/common/rate-limit.js

@@ -2,24 +2,49 @@ import { makeRateLimiter } from '../../../src/sources/rateLimit.js';
 export { makeRateLimiter } from '../../../src/sources/rateLimit.js';
 
 /**
- * Opt-in per-IP rate limiter for the cost-bearing API proxies (OpenAI / Google).
- * DEFAULT IS UNLIMITED: when the env var is unset, `0`, or non-numeric, this
- * returns `null` and the caller skips the check entirely — a runtime no-op that
- * preserves the original behavior. Only a positive integer N enables a fixed
- * 60s window of N requests/IP (built lazily once, then reused so its per-IP
- * window state persists across requests). The global backstop is set to a
- * generous multiple of the per-IP cap so a single host can't starve the rest.
+ * Resolve the per-IP, per-minute cap for a cost-bearing proxy from its env var.
  *
- * @param {string|undefined} envValue - Raw env value (requests/min/IP).
+ * The default is ON. An unset or blank value takes `defaultPerMin`; a positive
+ * integer overrides it; an explicit `0` disables the limiter for deployments
+ * that genuinely want no throttle.
+ *
+ * A value that cannot be read as a number — a typo, a stray unit, a negative —
+ * also takes the default rather than disabling the guard. That asymmetry is the
+ * point: `GEV_RATELIMIT_OPENAI_PER_MIN=3O` should not quietly hand an exposed
+ * server's API key to whoever asks. Removing the throttle stays possible, but
+ * only by saying `0`, which cannot be typed by accident.
+ *
+ * @param {string|number|undefined|null} envValue - Raw env value (requests/min/IP).
+ * @param {number} defaultPerMin - Cap to apply when the value is absent or unreadable.
+ * @returns {number} Requests/min/IP; `0` means unlimited.
+ */
+export function resolvePerMinuteCap(envValue, defaultPerMin) {
+  const raw = typeof envValue === 'string' ? envValue.trim() : envValue;
+  if (raw === undefined || raw === null || raw === '') return defaultPerMin;
+  const parsed = Number(raw);
+  if (!Number.isFinite(parsed) || parsed < 0) return defaultPerMin;
+  return Math.floor(parsed); // includes the explicit 0 = unlimited opt-out
+}
+
+/**
+ * Per-IP rate limiter for the cost-bearing API proxies (OpenAI / Google).
+ * Returns `null` only when the cap resolves to `0` (the explicit opt-out), in
+ * which case the caller skips the check entirely. Otherwise a fixed 60s window
+ * of N requests/IP, built lazily once and reused so its per-IP window state
+ * persists across requests. The global backstop is a generous multiple of the
+ * per-IP cap so a single host can't starve the rest.
+ *
+ * @param {string|number|undefined|null} envValue - Raw env value (requests/min/IP).
+ * @param {number} defaultPerMin - Cap to apply when the value is absent or unreadable.
  * @returns {((key:string)=>boolean)|null} An `allow(key)` fn, or null when unlimited.
  */
-export function makeOptInRateLimiter(envValue) {
-  const max = Number(envValue);
-  if (!Number.isFinite(max) || max <= 0) return null; // unset/0/garbage -> unlimited
+export function makeCostRateLimiter(envValue, defaultPerMin) {
+  const max = resolvePerMinuteCap(envValue, defaultPerMin);
+  if (max <= 0) return null; // explicit opt-out
   return makeRateLimiter({
     windowMs: 60_000,
-    max: Math.floor(max),
-    globalMax: Math.floor(max) * 20,
+    max,
+    globalMax: max * 20,
   });
 }
 

server/providers/openai/hud-summary.js

@@ -2,7 +2,7 @@ import {
   HUD_SUMMARY_INSTRUCTIONS,
   keylessHudSummaryResponse,
 } from '../../../src/hudSummaryResponse.js';
-import { enforceOptInRateLimit, openAiRateLimiter } from './rate-limit.js';
+import { enforceRateLimit, openAiRateLimiter } from './rate-limit.js';
 import { readRequestBody } from '../common/request.js';
 import { OPENAI_HUD_SUMMARY_MODEL_DEFAULT } from './constants.js';
 
@@ -46,10 +46,10 @@ async function handleHudSummary(req, res) {
     return;
   }
 
-  // Opt-in per-IP throttle (GEV_RATELIMIT_OPENAI_PER_MIN). Keyless HUD
-  // fallback has no provider cost and resolves above without consuming a
-  // paid-endpoint quota slot.
-  if (!enforceOptInRateLimit(openAiRateLimiter(), req, res)) return;
+  // Per-IP throttle (GEV_RATELIMIT_OPENAI_PER_MIN). On by default; 0 disables.
+  // Keyless HUD fallback has no provider cost and resolves above without
+  // consuming a paid-endpoint quota slot.
+  if (!enforceRateLimit(openAiRateLimiter(), req, res)) return;
 
   try {
     const body = await readRequestBody(req, 64 * 1024);

server/providers/openai/rate-limit.js

@@ -1,33 +1,46 @@
-import { makeOptInRateLimiter, clientKey } from '../common/rate-limit.js';
+import { makeCostRateLimiter, clientKey } from '../common/rate-limit.js';
+
+/**
+ * Requests/min/IP applied when GEV_RATELIMIT_OPENAI_PER_MIN is unset. Both
+ * places that already name a value agree on it: `.env.example` recommends 30
+ * and the Pinokio build ships 30 (pinokio/_ENVIRONMENT), so the packaged app
+ * is unaffected and only an unconfigured server changes. The HUD asks for a
+ * summary every 15s (HUD_SUMMARY_INTERVAL_MS), so an open tab spends 4/min and
+ * a voice session adds one token mint; the cap clears ordinary use several
+ * times over and bites only a caller working the endpoint far harder than the
+ * app does.
+ */
+const OPENAI_DEFAULT_PER_MIN = 30;
 
 // Built LAZILY on first request, NOT at module load: `.env` values are applied to process.env later
 // (the plugin config hook calls loadEnv → process.env, AFTER this module is imported), so reading
-// process.env here at import time would always see them unset and silently stay unlimited even when
+// process.env here at import time would always see them unset and fall back to the default even when
 // configured via .env. Building on first request (like the OPENAI_API_KEY reads) sees the loaded env;
-// the result is cached so the limiter's per-IP window state persists. `null` = unlimited (default).
+// the result is cached so the limiter's per-IP window state persists. `null` = the explicit 0 opt-out.
 let _openAiRateLimiter;
 
-/** OpenAI cost endpoints (realtime/token + hud-summary). Null = unlimited (default). */
+/** OpenAI cost endpoints (realtime/token + hud-summary). Null only when set to 0. */
 function openAiRateLimiter() {
   if (_openAiRateLimiter === undefined)
-    _openAiRateLimiter = makeOptInRateLimiter(
+    _openAiRateLimiter = makeCostRateLimiter(
       process.env.GEV_RATELIMIT_OPENAI_PER_MIN,
+      OPENAI_DEFAULT_PER_MIN,
     );
   return _openAiRateLimiter;
 }
 
 /**
- * Apply an opt-in limiter to a request, writing a 429 when over the cap.
- * When `limiter` is null (unlimited, the default) this is a no-op returning
- * `true`, so the handler proceeds exactly as before.
+ * Apply the limiter to a request, writing a 429 when over the cap.
+ * When `limiter` is null — the explicit `0` opt-out — this is a no-op
+ * returning `true`, so the handler proceeds unthrottled.
  *
  * @param {((key:string)=>boolean)|null} limiter
  * @param {import('http').IncomingMessage} req
  * @param {import('http').ServerResponse} res
  * @returns {boolean} True if the request may proceed; false if a 429 was sent.
  */
-function enforceOptInRateLimit(limiter, req, res) {
-  if (!limiter) return true; // unlimited (default) — no behavior change
+function enforceRateLimit(limiter, req, res) {
+  if (!limiter) return true; // explicit 0 opt-out — unthrottled
   if (limiter(clientKey(req))) return true;
   res.statusCode = 429;
   res.setHeader('Content-Type', 'application/json');
@@ -36,4 +49,4 @@ function enforceOptInRateLimit(limiter, req, res) {
   return false;
 }
 
-export { enforceOptInRateLimit, openAiRateLimiter };
+export { enforceRateLimit, openAiRateLimiter, OPENAI_DEFAULT_PER_MIN };

server/providers/openai/realtime.js

@@ -1,4 +1,4 @@
-import { enforceOptInRateLimit, openAiRateLimiter } from './rate-limit.js';
+import { enforceRateLimit, openAiRateLimiter } from './rate-limit.js';
 import {
   resolveVoiceModel,
   isKnownVoiceTier,
@@ -31,8 +31,8 @@ function createRealtimeTokenHandler({
       return;
     }
 
-    // Opt-in per-IP throttle (GEV_RATELIMIT_OPENAI_PER_MIN). No-op when unset.
-    if (!enforceOptInRateLimit(openAiRateLimiter(), req, res)) return;
+    // Per-IP throttle (GEV_RATELIMIT_OPENAI_PER_MIN). On by default; 0 disables.
+    if (!enforceRateLimit(openAiRateLimiter(), req, res)) return;
 
     const apiKey = resolveApiKey();
     if (!apiKey) {

server/providers/places.js

@@ -7,7 +7,7 @@ export {
 export { installRouteMiddleware } from './places/routes.js';
 export {
   makeRateLimiter,
-  makeOptInRateLimiter,
+  makeCostRateLimiter,
   clientKey,
 } from './common/rate-limit.js';
 export { haversineKm } from './common/geo.js';

server/providers/places/google.js

@@ -2,7 +2,7 @@ import {
   googleServerApiKey,
   keylessGooglePlacesResponse,
 } from './google-key.js';
-import { makeOptInRateLimiter, clientKey } from '../common/rate-limit.js';
+import { makeCostRateLimiter, clientKey } from '../common/rate-limit.js';
 import { admitSameSite } from '../common/same-site.js';
 import {
   projectNearbyPlaces,
@@ -10,14 +10,27 @@ import {
 } from '../../../src/data/placeProviderPayloads.js';
 
 // Construct lazily after the standalone environment has loaded.
-// undefined = not built yet; null = unlimited; fn = active limiter
+// undefined = not built yet; null = the explicit 0 opt-out; fn = active limiter
 let _googleRateLimiter;
 
-/** Google cost endpoint (nearby-places). Null = unlimited (default). */
+/**
+ * Requests/min/IP applied when GEV_RATELIMIT_GOOGLE_PER_MIN is unset. This is
+ * the value the Pinokio build already ships (pinokio/_ENVIRONMENT), so the
+ * packaged app keeps behaving exactly as it does today and only an
+ * unconfigured server changes — from unlimited to what the product already
+ * runs with. Places calls are user-driven (a search, a nearby lookup, an
+ * installation probe) rather than polled, so this sits far above what the app
+ * generates and bites only a caller enumerating the endpoint. `.env.example`
+ * suggests a tighter 60 when the host is not localhost; that still applies.
+ */
+export const GOOGLE_DEFAULT_PER_MIN = 120;
+
+/** Google cost endpoints (nearby-places + text-search). Null only when set to 0. */
 function googleRateLimiter() {
   if (_googleRateLimiter === undefined)
-    _googleRateLimiter = makeOptInRateLimiter(
+    _googleRateLimiter = makeCostRateLimiter(
       process.env.GEV_RATELIMIT_GOOGLE_PER_MIN,
+      GOOGLE_DEFAULT_PER_MIN,
     );
   return _googleRateLimiter;
 }
@@ -84,7 +97,7 @@ export function googlePlacesContextProxy({
       }
       const { latitude, longitude } = coordinates;
 
-      // Opt-in per-IP throttle (GEV_RATELIMIT_GOOGLE_PER_MIN). No-op when unset.
+      // Per-IP throttle (GEV_RATELIMIT_GOOGLE_PER_MIN). On by default; 0 disables.
       // Inlined (not the shared helper) so the 429 body keeps this endpoint's
       // `places: []` contract that the client expects on every error response.
       const _grl = googleRateLimiter();
@@ -204,7 +217,7 @@ export function googlePlacesContextProxy({
       }
       const { latitude, longitude } = coordinates;
 
-      // Opt-in per-IP throttle (GEV_RATELIMIT_GOOGLE_PER_MIN). No-op when unset.
+      // Per-IP throttle (GEV_RATELIMIT_GOOGLE_PER_MIN). On by default; 0 disables.
       // Inlined (like nearby-places) so the 429 body keeps the `places: []`
       // contract the client expects on every error response.
       const _grl = googleRateLimiter();