Skip to content

7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

TypeScript

fix(server): error handler crash + missing platforms + per-provider timeout (#7)

Tashfeen694d75cf7ca6
diff --git a/server/src/middleware/errorHandler.ts b/server/src/middleware/errorHandler.ts
index 5a1473ca..77efee7e 100644
--- a/server/src/middleware/errorHandler.ts
+++ b/server/src/middleware/errorHandler.ts
@@ -1,8 +1,10 @@
import type { Request, Response, NextFunction } from 'express';
-export function errorHandler(err: Error, _req: Request, res: Response, _next: NextFunction) {
+export function errorHandler(err: Error, _req: Request, res: Response, next: NextFunction) {
console.error('[Error]', err.message);
+ if (res.headersSent) return next(err);
+
const status = (err as any).status ?? 500;
res.status(status).json({
error: {
diff --git a/server/src/providers/openai-compat.ts b/server/src/providers/openai-compat.ts
index 64a98a94..0ba4e9d0 100644
--- a/server/src/providers/openai-compat.ts
+++ b/server/src/providers/openai-compat.ts
@@ -17,6 +17,9 @@ export class OpenAICompatProvider extends BaseProvider {
private readonly baseUrl: string;
private readonly extraHeaders: Record<string, string>;
private readonly validateUrl?: string;
+ /** Per-provider HTTP timeout override. Cloud APIs finish in ~15s; locally-hosted
+ * inference (llama.cpp / vLLM on CPU) can take 30-120s for long prompts. Default 15000. */
+ private readonly timeoutMs: number;
constructor(opts: {
platform: Platform;
@@ -24,6 +27,7 @@ export class OpenAICompatProvider extends BaseProvider {
baseUrl: string;
extraHeaders?: Record<string, string>;
validateUrl?: string;
+ timeoutMs?: number;
}) {
super();
this.platform = opts.platform;
@@ -31,6 +35,7 @@ export class OpenAICompatProvider extends BaseProvider {
this.baseUrl = opts.baseUrl;
this.extraHeaders = opts.extraHeaders ?? {};
this.validateUrl = opts.validateUrl;
+ this.timeoutMs = opts.timeoutMs ?? 15000;
}
async chatCompletion(
@@ -56,7 +61,7 @@ export class OpenAICompatProvider extends BaseProvider {
tool_choice: options?.tool_choice,
parallel_tool_calls: options?.parallel_tool_calls,
}),
- });
+ }, this.timeoutMs);
if (!res.ok) {
const err = await res.json().catch(() => ({}));
@@ -92,7 +97,7 @@ export class OpenAICompatProvider extends BaseProvider {
parallel_tool_calls: options?.parallel_tool_calls,
stream: true,
}),
- });
+ }, this.timeoutMs);
if (!res.ok) {
const err = await res.json().catch(() => ({}));
diff --git a/server/src/routes/keys.ts b/server/src/routes/keys.ts
index 4b78b292..728b240c 100644
--- a/server/src/routes/keys.ts
+++ b/server/src/routes/keys.ts
@@ -9,6 +9,7 @@ export const keysRouter = Router();
const PLATFORMS = [
'google', 'groq', 'cerebras', 'sambanova', 'nvidia', 'mistral',
'openrouter', 'github', 'huggingface', 'cohere', 'cloudflare',
+ 'zhipu', 'moonshot', 'minimax',
] as const;
const addKeySchema = z.object({