"""llm.complete: `max_tokens` and `timeout` are threaded into the backend call.

The OpenAI client is faked so nothing hits a network. We assert the generation
cap reaches the create() call and the fast-fail timeout reaches the client (with
max_retries=0 so summary.py owns the retry policy, not the SDK).
"""
from __future__ import annotations

import types

import pytest

from lyra import llm


@pytest.fixture
def fake_openai(monkeypatch):
    recorded: dict = {}

    class FakeCompletions:
        def create(self, **kwargs):
            recorded["create"] = kwargs
            msg = types.SimpleNamespace(content="ok")
            return types.SimpleNamespace(choices=[types.SimpleNamespace(message=msg)])

    class FakeClient:
        def __init__(self, **kwargs):
            recorded["client"] = kwargs
            self.chat = types.SimpleNamespace(completions=FakeCompletions())

    monkeypatch.setattr(llm, "OpenAI", FakeClient)
    monkeypatch.setattr(llm, "load", lambda: types.SimpleNamespace(
        mi50_base_url="http://mi50/v1", mi50_model="local-gpu",
        cloud_model="gpt-4o-mini", openai_api_key="sk-test", local_model="l",
    ))
    return recorded


def test_mi50_threads_max_tokens_and_timeout(fake_openai):
    out = llm.complete([{"role": "user", "content": "hi"}],
                       backend="mi50", max_tokens=768, timeout=150)

    assert out == "ok"
    assert fake_openai["create"]["max_tokens"] == 768
    assert fake_openai["client"]["timeout"] == 150
    assert fake_openai["client"]["max_retries"] == 0


def test_cloud_threads_max_tokens_and_timeout(fake_openai):
    llm.complete([{"role": "user", "content": "hi"}],
                 backend="cloud", max_tokens=768, timeout=150)

    assert fake_openai["create"]["max_tokens"] == 768
    assert fake_openai["client"]["timeout"] == 150
    assert fake_openai["client"]["max_retries"] == 0


def test_default_bounds_calls_even_without_explicit_timeout(fake_openai):
    # No cap / timeout passed -> still bounded: 300s default + no SDK retries, so
    # no call can silently inherit the SDK's 600s x2 (~30 min). No length cap
    # unless asked, though.
    llm.complete([{"role": "user", "content": "hi"}], backend="mi50")

    assert "max_tokens" not in fake_openai["create"]
    assert fake_openai["client"]["timeout"] == 300
    assert fake_openai["client"]["max_retries"] == 0