tests/test_chat.py

import os
os.environ["MOCK_INFERENCE"] = "true"

from fastapi.testclient import TestClient
from app import app

client = TestClient(app)

def test_chat_completions():
    payload = {
        "model": "plain-qwen-0.5b",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Hello!"}
        ],
        "temperature": 0.0,
        "max_tokens": 100,
        "stream": False,
        "run_id": "test-run-123",
        "question_id": "test-q-456",
        "return_final_prompt": True
    }
    
    response = client.post("/v1/chat/completions", json=payload)
    assert response.status_code == 200
    json_data = response.json()
    assert json_data["object"] == "chat.completion"
    assert "choices" in json_data
    assert json_data["choices"][0]["message"]["role"] == "assistant"
    assert "benchmark_metrics" in json_data
    
    metrics = json_data["benchmark_metrics"]
    assert metrics["model_id"] == "plain-qwen-0.5b"
    assert metrics["run_id"] == "test-run-123"
    assert metrics["question_id"] == "test-q-456"
    assert "prompt_tokens" in metrics
    assert "completion_tokens" in metrics