me.kpavlov.aimocks:ai-mocks-openai-standalone

Mokksy and AI-Mocks

Mokksy and AI-Mocks are mock HTTP and LLM (Large Language Model) servers inspired by WireMock, with support for response streaming and Server-Side Events (SSE). They are designed to build, test, and mock LLM responses for development purposes.

Mokksy

Mokksy is a mock HTTP server built with Kotlin and Ktor. It addresses the limitations of WireMock by supporting true SSE and streaming responses, making it particularly useful for integration testing LLM clients.

Core Features

• Flexibility to control server response directly via ApplicationCall object.
• Built with Kotest Assertions.
• Fluent modern Kotlin DSL API.
• Support for simulating streamed responses and Server-Side Events (SSE) with delays between chunks.
• Support for simulating response delays.

Example Usages

Responding with Predefined Responses

// given
val expectedResponse =
  // language=json
  """
    {
        "response": "Pong"
    }
    """.trimIndent()

mokksy.get {
  path = beEqual("/ping")
  containsHeader("Foo", "bar")
} respondsWith {
  body = expectedResponse
}

// when
val result = client.get("/ping") {
  headers.append("Foo", "bar")
}

// then
assertThat(result.status).isEqualTo(HttpStatusCode.OK)
assertThat(result.bodyAsText()).isEqualTo(expectedResponse)

POST Request

// given
val id = Random.nextInt()
val expectedResponse =
  // language=json
  """
    {
        "id": "$id",
        "name": "thing-$id"
    }
    """.trimIndent()

mokksy.post {
  path = beEqual("/things")
  bodyContains("\"$id\"")
} respondsWith {
  body = expectedResponse
  httpStatus = HttpStatusCode.Created
  headers {
    // type-safe builder style
    append(HttpHeaders.Location, "/things/$id")
  }
  headers += "Foo" to "bar" // list style
}

// when
val result =
  client.post("/things") {
    headers.append("Content-Type", "application/json")
    setBody(
      // language=json
      """
            {
                "id": "$id"
            }
            """.trimIndent(),
    )
  }

// then
assertThat(result.status).isEqualTo(HttpStatusCode.Created)
assertThat(result.bodyAsText()).isEqualTo(expectedResponse)
assertThat(result.headers["Location"]).isEqualTo("/things/$id")
assertThat(result.headers["Foo"]).isEqualTo("bar")

Server-Side Events (SSE) Response

Server-Side Events (SSE) is a technology that allows a server to push updates to the client over a single, long-lived HTTP connection, enabling real-time updates without requiring the client to continuously poll the server for new data.

mokksy.post {
  path = beEqual("/sse")
} respondsWithSseStream {
  flow =
    flow {
      delay(200.milliseconds)
      emit(
        ServerSentEvent(
          data = "One",
        ),
      )
      delay(50.milliseconds)
      emit(
        ServerSentEvent(
          data = "Two",
        ),
      )
    }
}

// when
val result = client.post("/sse")

// then
assertThat(result.status)
  .isEqualTo(HttpStatusCode.OK)
assertThat(result.contentType())
  .isEqualTo(ContentType.Text.EventStream.withCharsetIfNeeded(Charsets.UTF_8))
assertThat(result.bodyAsText())
  .isEqualTo("data: One\r\ndata: Two\r\n")

AI-Mocks

AI-Mocks is a specialized mock server implementations (e.g., mocking OpenAI API) built using Mokksy.

It supports mocking following AI services:

• OpenAI - ai-mocks-openai
• Anthropic - ai-mocks-anthropic
• Google VertexAI Gemini - ai-mocks-gemini
• Ollama - ai-mocks-ollama
• Agent-to-Agent (A2A) Protocol - ai-mocks-a2a

Feature Support Matrix

Feature	OpenAI	Anthropic	Gemini	Ollama	A2A
Chat Completions	✅	✅	✅	✅	✅
Streaming	✅	✅	✅	✅	✅
Embeddings	✅	❌	❌	✅	❌
Moderation	✅	❌	❌	❌	❌
Additional APIs	Responses	-	-	Generate	Full A2A Protocol (11 endpoints)

Enjoying LLM integration testing? ❤️

How to build

Building project locally:

gradle build

or using Make:

make

Contributing

I do welcome contributions! Please see the Contributing Guidelines for details.