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/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) {