Package org.mockserver.model

Class HttpLlmResponse

java.lang.Object

org.mockserver.model.ObjectWithReflectiveEqualsHashCodeToString

org.mockserver.model.ObjectWithJsonToString

org.mockserver.model.Action<HttpLlmResponse>

org.mockserver.model.HttpLlmResponse

public class HttpLlmResponse
extends Action<HttpLlmResponse>

Nested Class Summary

Nested classes/interfaces inherited from class org.mockserver.model.Action

Action.Direction, Action.Type

Constructor Summary

Constructors

Constructor	Description
HttpLlmResponse()

Method Summary

Modifier and Type	Method	Description
boolean	equals(Object o)
LlmChaosProfile	getChaos()
Completion	getCompletion()
LlmContentFilter	getContentFilter()
LlmConversationMatcher	getConversationMatcher()	Returns the conversation matcher for evaluation.
ConversationPredicates	getConversationPredicates()
EmbeddingResponse	getEmbedding()
String	getModel()
ModerationResponse	getModeration()
Provider	getProvider()
RerankResponse	getRerank()
Action.Type	getType()
int	hashCode()
static HttpLlmResponse	llmResponse()
HttpLlmResponse	withChaos(LlmChaosProfile chaos)	Optional fault/chaos profile applied when returning this response — probabilistic errors, mid-stream truncation, malformed SSE.
HttpLlmResponse	withCompletion(Completion completion)
HttpLlmResponse	withContentFilter(LlmContentFilter contentFilter)	Optional Azure OpenAI content-filter severities.
HttpLlmResponse	withConversationMatcher(LlmConversationMatcher conversationMatcher)
HttpLlmResponse	withConversationPredicates(ConversationPredicates conversationPredicates)
HttpLlmResponse	withEmbedding(EmbeddingResponse embedding)
HttpLlmResponse	withModel(String model)
HttpLlmResponse	withModeration(ModerationResponse moderation)	Configure this response as an OpenAI Moderations endpoint response (POST /v1/moderations) — a flagged/not-flagged verdict with per-category scores.
HttpLlmResponse	withProvider(Provider provider)
HttpLlmResponse	withRerank(RerankResponse rerank)

Methods inherited from class org.mockserver.model.Action

getDelay, getExpectationId, isPrimary, setExpectationId, withDelay, withDelay, withPrimary

Methods inherited from class org.mockserver.model.ObjectWithJsonToString

toString

Methods inherited from class org.mockserver.model.ObjectWithReflectiveEqualsHashCodeToString

fieldsExcludedFromEqualsAndHashCode

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Details

HttpLlmResponse

public HttpLlmResponse()

Method Details

llmResponse

public static HttpLlmResponse llmResponse()

withProvider

public HttpLlmResponse withProvider(Provider provider)

getProvider

public Provider getProvider()

withModel

public HttpLlmResponse withModel(String model)

getModel

public String getModel()

withCompletion

public HttpLlmResponse withCompletion(Completion completion)

getCompletion

public Completion getCompletion()

withEmbedding

public HttpLlmResponse withEmbedding(EmbeddingResponse embedding)

getEmbedding

public EmbeddingResponse getEmbedding()

withRerank

public HttpLlmResponse withRerank(RerankResponse rerank)

getRerank

public RerankResponse getRerank()

withModeration

public HttpLlmResponse withModeration(ModerationResponse moderation)

Configure this response as an OpenAI Moderations endpoint response (POST /v1/moderations) — a flagged/not-flagged verdict with per-category scores. When set, the response returns the moderations wire shape instead of a completion.

getModeration

public ModerationResponse getModeration()

withContentFilter

public HttpLlmResponse withContentFilter(LlmContentFilter contentFilter)

Optional Azure OpenAI content-filter severities. When set on an Azure response, the content_filter_results (per choice) and prompt_filter_results (top-level) annotations are added so agents can detect filtering. Also shapes the severities of a chaos content-filter block.

getContentFilter

public LlmContentFilter getContentFilter()

withConversationPredicates

public HttpLlmResponse withConversationPredicates(ConversationPredicates conversationPredicates)

getConversationPredicates

public ConversationPredicates getConversationPredicates()

withChaos

public HttpLlmResponse withChaos(LlmChaosProfile chaos)

Optional fault/chaos profile applied when returning this response — probabilistic errors, mid-stream truncation, malformed SSE.

getChaos

public LlmChaosProfile getChaos()

withConversationMatcher

public HttpLlmResponse withConversationMatcher(LlmConversationMatcher conversationMatcher)

getConversationMatcher

public LlmConversationMatcher getConversationMatcher()

Returns the conversation matcher for evaluation. If not explicitly set, lazily reconstructs it from conversationPredicates (which survives JSON round-tripping). Returns null if neither is set.

getType

public Action.Type getType()

Specified by:

getType in class Action<HttpLlmResponse>

equals

public boolean equals(Object o)

Overrides:

equals in class Action<HttpLlmResponse>

hashCode

public int hashCode()

Overrides:

hashCode in class Action<HttpLlmResponse>