126 lines
4.2 KiB
Python
126 lines
4.2 KiB
Python
import asyncio
|
|
|
|
import pytest
|
|
|
|
from nanobot.providers.base import GenerationSettings, LLMProvider, LLMResponse
|
|
|
|
|
|
class ScriptedProvider(LLMProvider):
|
|
def __init__(self, responses):
|
|
super().__init__()
|
|
self._responses = list(responses)
|
|
self.calls = 0
|
|
self.last_kwargs: dict = {}
|
|
|
|
async def chat(self, *args, **kwargs) -> LLMResponse:
|
|
self.calls += 1
|
|
self.last_kwargs = kwargs
|
|
response = self._responses.pop(0)
|
|
if isinstance(response, BaseException):
|
|
raise response
|
|
return response
|
|
|
|
def get_default_model(self) -> str:
|
|
return "test-model"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_chat_with_retry_retries_transient_error_then_succeeds(monkeypatch) -> None:
|
|
provider = ScriptedProvider([
|
|
LLMResponse(content="429 rate limit", finish_reason="error"),
|
|
LLMResponse(content="ok"),
|
|
])
|
|
delays: list[int] = []
|
|
|
|
async def _fake_sleep(delay: int) -> None:
|
|
delays.append(delay)
|
|
|
|
monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
|
|
|
|
response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
|
|
|
|
assert response.finish_reason == "stop"
|
|
assert response.content == "ok"
|
|
assert provider.calls == 2
|
|
assert delays == [1]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_chat_with_retry_does_not_retry_non_transient_error(monkeypatch) -> None:
|
|
provider = ScriptedProvider([
|
|
LLMResponse(content="401 unauthorized", finish_reason="error"),
|
|
])
|
|
delays: list[int] = []
|
|
|
|
async def _fake_sleep(delay: int) -> None:
|
|
delays.append(delay)
|
|
|
|
monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
|
|
|
|
response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
|
|
|
|
assert response.content == "401 unauthorized"
|
|
assert provider.calls == 1
|
|
assert delays == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_chat_with_retry_returns_final_error_after_retries(monkeypatch) -> None:
|
|
provider = ScriptedProvider([
|
|
LLMResponse(content="429 rate limit a", finish_reason="error"),
|
|
LLMResponse(content="429 rate limit b", finish_reason="error"),
|
|
LLMResponse(content="429 rate limit c", finish_reason="error"),
|
|
LLMResponse(content="503 final server error", finish_reason="error"),
|
|
])
|
|
delays: list[int] = []
|
|
|
|
async def _fake_sleep(delay: int) -> None:
|
|
delays.append(delay)
|
|
|
|
monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
|
|
|
|
response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
|
|
|
|
assert response.content == "503 final server error"
|
|
assert provider.calls == 4
|
|
assert delays == [1, 2, 4]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_chat_with_retry_preserves_cancelled_error() -> None:
|
|
provider = ScriptedProvider([asyncio.CancelledError()])
|
|
|
|
with pytest.raises(asyncio.CancelledError):
|
|
await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_chat_with_retry_uses_provider_generation_defaults() -> None:
|
|
"""When callers omit generation params, provider.generation defaults are used."""
|
|
provider = ScriptedProvider([LLMResponse(content="ok")])
|
|
provider.generation = GenerationSettings(temperature=0.2, max_tokens=321, reasoning_effort="high")
|
|
|
|
await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
|
|
|
|
assert provider.last_kwargs["temperature"] == 0.2
|
|
assert provider.last_kwargs["max_tokens"] == 321
|
|
assert provider.last_kwargs["reasoning_effort"] == "high"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_chat_with_retry_explicit_override_beats_defaults() -> None:
|
|
"""Explicit kwargs should override provider.generation defaults."""
|
|
provider = ScriptedProvider([LLMResponse(content="ok")])
|
|
provider.generation = GenerationSettings(temperature=0.2, max_tokens=321, reasoning_effort="high")
|
|
|
|
await provider.chat_with_retry(
|
|
messages=[{"role": "user", "content": "hello"}],
|
|
temperature=0.9,
|
|
max_tokens=9999,
|
|
reasoning_effort="low",
|
|
)
|
|
|
|
assert provider.last_kwargs["temperature"] == 0.9
|
|
assert provider.last_kwargs["max_tokens"] == 9999
|
|
assert provider.last_kwargs["reasoning_effort"] == "low"
|