Package org.mockserver.llm.client

Class LlmProviderSniffer

java.lang.Object

org.mockserver.llm.client.LlmProviderSniffer

public final class LlmProviderSniffer
extends Object

Maps a forwarded request's target host/URL to an LLM Provider, enabling GenAI observability on the proxy/forward path. Pure function of its inputs (request host/path, configuration) — no shared mutable state.

Detection order:

1. Well-known provider hosts (exact or wildcard match)
2. Configured mockserver.llmBaseUrl Ollama host match
3. Fallback to configured mockserver.llmProvider — only when the request path looks like an LLM endpoint (contains any of /chat/completions, /messages, /completions, /responses, /embeddings, /v1/, :generatecontent, /api/generate, /api/chat)

Returns Optional.empty() when the request is not LLM traffic.

Method Summary

Modifier and Type	Method	Description
static String	extractModelFromRequest(HttpRequest request)	Extract the model name from the forwarded request body.
static String	extractModelFromResponse(HttpResponse response)	Extract the model name from the forwarded response body.
static Optional<Provider>	sniff(HttpRequest forwardedRequest)	Sniff the LLM provider from a forwarded request's target host.
static Optional<Provider>	sniffByHost(String host)	Sniff the LLM provider from an explicit host string (for unit testing or callers that already have the host extracted).
static Optional<Provider>	sniffByHostAndPath(String host, String path)	Sniff the LLM provider from an explicit host and path.

Methods inherited from class java.lang.Object

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

Method Details

sniff

public static Optional<Provider> sniff(HttpRequest forwardedRequest)

Sniff the LLM provider from a forwarded request's target host.

Parameters:

forwardedRequest - the request that was forwarded to the upstream

Returns:

the detected provider, or empty if this is not LLM traffic

sniffByHost

public static Optional<Provider> sniffByHost(String host)

Sniff the LLM provider from an explicit host string (for unit testing or callers that already have the host extracted). Equivalent to sniffByHostAndPath(host, null) — the configured-provider fallback is only applied when the path looks like an LLM endpoint, so with a null path the fallback is skipped.

sniffByHostAndPath

public static Optional<Provider> sniffByHostAndPath(String host,
 String path)

Sniff the LLM provider from an explicit host and path.

Parameters:

host - the target host (may be null)

path - the request path (may be null) — used only for the configured-provider fallback gate

extractModelFromResponse

public static String extractModelFromResponse(HttpResponse response)

Extract the model name from the forwarded response body. Providers typically include a "model" field in their JSON response (OpenAI, Anthropic, Gemini use this pattern). Returns null if extraction fails.

extractModelFromRequest

public static String extractModelFromRequest(HttpRequest request)

Extract the model name from the forwarded request body. Providers typically include a "model" field in their JSON request body. Returns null if extraction fails.