Cap OpenRouter max_tokens — some models default to their full context window

agent/src/openrouter.js

@@ -15,6 +15,10 @@ export async function askOpenRouter(model, prompt) {
     body: JSON.stringify({
       model: model || DEFAULT_MODEL,
       messages: [{ role: "user", content: prompt }],
+      // Some models default max_tokens to their full context window (e.g. 65536),
+      // which can exceed available credit balance before a single token is generated.
+      // This is a quick chat reply, not a long-form task — cap it.
+      max_tokens: 1024,
     }),
   });