OpenAI¶

Simulate OpenAI chat completions in your tests.

Compatibility

See Compatibility for providers, transports, and framework recipes.

How it works¶

Tenro intercepts the OpenAI SDK's outbound HTTP request and returns your configured response. No real network call is made.

import openai

response = openai.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}]
)
# In tests, Tenro returns your simulated response

Capabilities¶

Capability	Supported	Notes
TEXT	Yes	Basic text generation
TOOL_CALLS	Yes	OpenAI-style `tools` parameter
STRUCTURED_OUTPUT	Yes	JSON Schema-based output
JSON_MODE	Yes	`response_format: {"type": "json_object"}`
STREAMING	Coming soon	Server-sent events

Simulating responses¶

Basic text¶

from tenro import Provider
from tenro.simulate import llm, tool

llm.simulate(Provider.OPENAI, response="Hello!")

With tool calls¶

Use ToolCall to simulate LLM responses that include tool calls:

from tenro import Provider, ToolCall
from tenro.simulate import llm

# Single response with text + tool call (nested list = one LLM call)
llm.simulate(
    provider=Provider.OPENAI,
    responses=[["I'll search for that.", ToolCall(search, query="AI")]]
)

# Tool call only (no text)
llm.simulate(
    provider=Provider.OPENAI,
    responses=[ToolCall("search", query="AI")]
)

Multi-turn conversations¶

from tenro import Provider
from tenro.simulate import llm, tool

llm.simulate(
    provider=Provider.OPENAI,
    responses=[
        "Let me think about that...",  # First LLM call
        "Here's my answer: 42"          # Second LLM call
    ]
)

Response format¶

Tenro returns a valid ChatCompletion object:

{
    "id": "chatcmpl-...",
    "object": "chat.completion",
    "created": 1234567890,
    "model": "gpt-4o",
    "choices": [{
        "index": 0,
        "message": {
            "role": "assistant",
            "content": "Hello!",
            "tool_calls": None
        },
        "finish_reason": "stop"
    }],
    "usage": {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}
}