Reasoning Effort

Reasoning effort is route-level model tuning for OpenAI-backed agent() routes.

Use it when one agent route needs a different reasoning budget than the rest of the app. A support coordinator might stay cheap and fast, while a tool-heavy planning route might ask for deeper reasoning.

Quick start

Set reasoning.effort on an agent() descriptor:

src/app/support/[tenant]/index.ts

import { agent } from "@dawn-ai/sdk"
 
export default agent({
  model: "gpt-5.1",
  reasoning: { effort: "high" },
  systemPrompt: "You are a careful support assistant.",
})

ReasoningConfig is exported from @dawn-ai/sdk.

Supported values

Dawn's type surface accepts:

type ReasoningEffort =
  | "none"
  | "minimal"
  | "low"
  | "medium"
  | "high"
  | "xhigh"

The model provider decides which values are meaningful for a given model. Non-reasoning models ignore the setting in Dawn's current OpenAI-backed materialization path.

If you omit reasoning, Dawn does not pass a reasoningEffort value. The model/provider default applies.

Where it applies

Reasoning effort applies to Dawn's agent() descriptor path, where @dawn-ai/langchain materializes the descriptor with ChatOpenAI.

It does not automatically affect:

workflow routes
raw graph routes
chain routes
models you instantiate manually inside your own graph or chain

For those paths, configure reasoning on the model instance you create.

What Dawn passes through

Dawn maps:

reasoning: { effort: "high" }

to the ChatOpenAI option:

{ reasoningEffort: "high" }

No prompt fragment, tool, state field, or stream event is added. Reasoning effort is descriptor configuration, not a file-based marker.

Choosing a value

Start without a value unless you have evidence that a route needs one.

Use lower values for routes where latency and cost matter more than deliberation:

reasoning: { effort: "minimal" }

Use higher values when the route is tool-heavy, planning-heavy, or asked to synthesize several pieces of evidence:

reasoning: { effort: "high" }

Avoid using reasoning effort as a substitute for better tools or clearer route design. If the agent lacks the right context, increasing reasoning will not create it.

Subagents

Reasoning effort is per descriptor.

If a parent and child route need different budgets, set them separately:

// parent
export default agent({
  model: "gpt-5.1",
  reasoning: { effort: "low" },
  systemPrompt: "Coordinate the work.",
})
 
// child
export default agent({
  model: "gpt-5.1",
  reasoning: { effort: "high" },
  systemPrompt: "Analyze the evidence carefully.",
})