Changing ratelimit

README.md

@@ -35,7 +35,7 @@ npm run keys:env
 
 The global context limit defaults to 256k tokens and can be changed with `MAX_CONTEXT_TOKENS`.
 
-Inference requests are limited per client IP to 2 requests per second, 100 requests per five hours, and $10 of reported upstream cost per five hours. Railway's `X-Real-IP` header is used to identify clients.
+Inference requests are limited per client IP to 2 requests per second, 100 requests per five hours, and $15 of reported upstream cost per five hours. Railway's `X-Real-IP` header is used to identify clients.
 
 To exempt trusted clients from those proxy limits, set `UNLIMITED_API_KEYS` to a JSON array and have the client send a configured key using `Authorization: Bearer <key>` or `x-api-key`. These keys only bypass this proxy's rate and spend limits; they do not bypass upstream OpenCode Go limits.
 

src/rate-limit.js

@@ -4,7 +4,7 @@ const FIVE_HOURS = 5 * 60 * 60 * 1_000;
 export const RATE_LIMITS = {
   requestsPerSecond: 2,
   requestsPerFiveHours: 100,
-  spendPerFiveHours: 10,
+  spendPerFiveHours: 15,
 };
 
 function prune(timestamps, now, window) {

test/rate-limit.test.js

@@ -10,7 +10,7 @@ describe('rate limiter', () => {
     expect(limiter.check('ip').allowed).toBe(false);
     time = 1_001;
     expect(limiter.check('ip').allowed).toBe(true);
-    limiter.recordCost('ip', 10);
+    limiter.recordCost('ip', 15);
     expect(limiter.check('ip').allowed).toBe(false);
     time = 5 * 60 * 60 * 1_000 + 1_002;
     expect(limiter.check('ip').allowed).toBe(true);