ZNJJ-api-server/test/backends/test_sla_alignment.py

"""超时/重试配置与 SDK 适配契约。

LLM max_retries 表示额外重试次数；FastGPT SDK 同名参数实际表示
总尝试次数，需要 +1 转换。退避统一为 1、2、4 秒。
超时分别约束一次 LLM 尝试与 FastGPT HTTP SDK，不代表整轮总期限。
"""

import inspect

from src.agent.llm import OpenAILLMService
from src.core.fastgpt_client import FASTGPT_MAX_RETRIES, FASTGPT_TIMEOUT_SECONDS


def test_llm_default_timeout_matches_fastgpt_client():
    signature = inspect.signature(OpenAILLMService.__init__)
    default_timeout = signature.parameters["timeout_seconds"].default
    assert default_timeout == FASTGPT_TIMEOUT_SECONDS == 60.0


def test_llm_default_max_retries_matches_fastgpt_client():
    signature = inspect.signature(OpenAILLMService.__init__)
    default_retries = signature.parameters["max_retries"].default
    assert default_retries == FASTGPT_MAX_RETRIES == 3


def test_named_profile_defaults_match_fastgpt_client(monkeypatch):
    """未显式配置 _TIMEOUT_SECONDS/_MAX_RETRIES 的 profile 取 SLA 默认值。"""
    monkeypatch.setenv("LLM_PROVIDERS", "probe")
    monkeypatch.setenv("LLM_PROBE_BASE_URL", "http://127.0.0.1:1/v1")
    monkeypatch.setenv("LLM_PROBE_API_KEY", "probe-key")
    monkeypatch.setenv("LLM_PROBE_MODEL", "probe-model")

    from src.core.config import Config

    # LLM_PROVIDERS 是 import 时固化的类属性，需直接替换
    monkeypatch.setattr(Config, "LLM_PROVIDERS", "probe")
    profile = Config.llm_profile("probe")
    assert profile["timeout_seconds"] == FASTGPT_TIMEOUT_SECONDS
    assert profile["max_retries"] == FASTGPT_MAX_RETRIES


import asyncio
from unittest.mock import AsyncMock
import httpx
import pytest
from fastapi import FastAPI
from fastgpt_client.exceptions import APIError
from src.core import fastgpt_client as wiring
from src.core.config import Config


@pytest.mark.asyncio
async def test_fastgpt_sdk_uses_same_attempt_count_and_backoff(monkeypatch):
    monkeypatch.setattr(Config, "validate", lambda: None)
    monkeypatch.setattr(Config, "AGENT_BACKEND", "fastgpt")
    monkeypatch.setattr(Config, "FASTGPT_BASE_URL", "http://audit")
    monkeypatch.setattr(Config, "FASTGPT_API_KEY", "audit")
    sleep = AsyncMock()
    monkeypatch.setattr(asyncio, "sleep", sleep)
    async with wiring.lifespan(FastAPI()):
        client = wiring.get_fastgpt_client()
        request = AsyncMock(return_value=httpx.Response(503))
        with pytest.raises(APIError):
            await client._retry_request_async(request, "audit")
        assert request.await_count == 4
        assert [call.args[0] for call in sleep.await_args_list] == [1, 2, 4]


@pytest.mark.asyncio
async def test_llm_backoff_uses_same_delays(monkeypatch):
    sleep = AsyncMock()
    monkeypatch.setattr(asyncio, "sleep", sleep)
    llm = OpenAILLMService(model="audit", api_key="audit")
    for attempt in range(3):
        await llm._retry_delay(attempt)
    assert [call.args[0] for call in sleep.await_args_list] == [1, 2, 4]