Tool Calling

Operator defines a tool with `parameters: { city: 'string' }` (plain object) instead of `parameters: z.object({ city: z.string() })`.

tools[].parameters must be a Zod schema (or jsonSchema()-wrapped JSON Schema) — the SDK converts it to a provider tool-spec at call time. Plain objects are rejected with InvalidArgumentError. Use z.object({...}).describe('...') to give each field a description the model can see.

Operator wants to stop the agentic loop after the `submit_invoice` tool runs successfully, regardless of remaining maxSteps budget.

Pass `stopWhen: hasToolCall('submit_invoice')` (or a custom predicate over the steps array). stopWhen short-circuits the loop the step after the predicate matches. Compose with maxSteps as a safety cap.

Tool's execute is `(args) => fetch(...)` returning a Response object directly (not awaited, not serialized).

execute({input, toolCallId, messages}) must be async and return a JSON-serializable value — that value becomes the toolResult passed back to the model. Await any IO inside execute; resolve to a plain object (or string). Throwing inside execute surfaces as a tool-error part on the fullStream.