Ask options — timeouts, params, system message

Three knobs shape how an ask reaches the provider: how long an invocation may take, which wire parameters go with the request, and what extra system text every prompt carries.

Timeouts

nola.config.ts

import { openai } from "@nola-lang/providers";
import { defineConfig } from "@nola-lang/runtime";

export default defineConfig({
  providers: { default: openai({ model: "gpt-5-mini" }) },
  ask: { timeoutMs: 60_000 },   // per-invocation; 0 disables
});

• ask.timeoutMs is the default per-invocation timeout (60 000 ms when unset). It is the root frame’s abort signal: when it elapses, every provider call in that invocation receives the signal. 0 disables it.
• .withTimeout(ms) on the intent an infer function returns overrides it for that invocation — see Intent methods.
• The timeout bounds provider round trips only. Once a call intent’s arguments are filled, the callee’s own promise runs to completion, the same as a plain await fn() in your code.

Params

Wire-tuning knobs travel with the intent:

tuned.tsi

export infer function tagline(.product: string) {
  return ask (..`a creative tagline`<string>).withParams({
    temperature: 0.9,
    maxOutputTokens: 200,
    providerOptions: { reasoning: { effort: "low" } },   // passed through to the provider untouched
  });
}

• temperature and maxOutputTokens are typed; providerOptions is an opaque, JSON-serializable bag of provider-specific knobs passed through to the provider’s complete() untouched.
• Merge rule: patch fields win per field, and providerOptions merges per key rather than being replaced wholesale — both when chaining .withParams() and along the frame chain (nearest wins).
• Params are part of the ask fingerprint: two asks that differ only in params never share a replay or cache entry — see Record and replay.

System message

nola.config.ts

import { openai } from "@nola-lang/providers";
import { defineConfig } from "@nola-lang/runtime";

export default defineConfig({
  providers: { default: openai({ model: "gpt-5-mini" }) },
  system: { message: "Answer in British English." },
});

system.message is extra system-prompt text composed after the Nola protocol preamble on every ask. Use it for global tone and policy; use instruction markers and prompt templates for anything specific to one function or one ask.

Next: Environments and secrets