Package org.mockserver.llm.client

Class OpenAiResponsesLlmClient

java.lang.Object

org.mockserver.llm.client.AbstractLlmClient

org.mockserver.llm.client.OpenAiResponsesLlmClient

All Implemented Interfaces:

LlmClient

public class OpenAiResponsesLlmClient
extends AbstractLlmClient

Runtime client for the OpenAI Responses API (POST /v1/responses, Authorization: Bearer). Sends the conversation as the input message array and parses the output content (preferring the output_text convenience field when present).

Field Summary

Fields inherited from class org.mockserver.llm.client.AbstractLlmClient

OBJECT_MAPPER

Constructor Summary

Constructors

Constructor	Description
OpenAiResponsesLlmClient()

Method Summary

Modifier and Type	Method	Description
HttpRequest	buildCompletionRequest(LlmBackend backend, ParsedConversation prompt)	Build the outbound completion request (URL path, auth headers, request body) for the given backend and prompt.
Completion	parseCompletionResponse(HttpResponse response)	Parse a successful provider response body into a Completion.
Provider	provider()	The provider this client handles — the registry key.

Methods inherited from class org.mockserver.llm.client.AbstractLlmClient

appendRoleContentMessages, postJson, readBody, resolveBaseUrl, resolveModel, writeJson

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

OpenAiResponsesLlmClient

public OpenAiResponsesLlmClient()

Method Details

provider

public Provider provider()

Description copied from interface: LlmClient

The provider this client handles — the registry key.

buildCompletionRequest

public HttpRequest buildCompletionRequest(LlmBackend backend,
 ParsedConversation prompt)

Description copied from interface: LlmClient

Build the outbound completion request (URL path, auth headers, request body) for the given backend and prompt. The returned request carries the socket address resolved from the backend's base URL (or the provider default). Implementations pin temperature=0 and a seed where the provider supports it, for reproducibility.

parseCompletionResponse

public Completion parseCompletionResponse(HttpResponse response)

Description copied from interface: LlmClient

Parse a successful provider response body into a Completion. Implementations should tolerate missing optional fields and never throw for a well-formed-but-sparse response; malformed bodies may throw and are handled (fail-closed) by LlmCompletionService.