ZNJJ-api-server/test/agent/test_llm_error_mapping.py

"""LLM 错误分类测试：鉴权/限流可区分上报（两后端错误码等价的关键）。

对照 FastGPT 后端：401 -> ChatBackendAuthenticationError、
429 -> ChatBackendRateLimitError（endpoint 已有对应响应分支）。
LangGraph 链路由 OpenAILLMService 抛出可区分子类、
LangGraphBackend 翻译为 ChatBackend* 错误。
"""

from types import SimpleNamespace
from unittest.mock import AsyncMock

import httpx
import pytest
from openai import AuthenticationError, RateLimitError

from src.agent.llm import (
    LLMAPIError,
    LLMAuthError,
    LLMRateLimitError,
    OpenAILLMService,
)
from src.backends.chat import (
    ChatBackendAuthenticationError,
    ChatBackendRateLimitError,
    ChatInput,
)
from src.backends.langgraph import LangGraphBackend


def _status_error(cls, status: int) -> Exception:
    request = httpx.Request("POST", "http://llm.local/v1/chat/completions")
    response = httpx.Response(status, request=request)
    return cls("error", response=response, body=None)


def _service_with_failing_llm(exc: Exception, max_retries: int = 0):
    """complete 固定抛 exc 的 OpenAILLMService（client 打桩）。"""
    llm = OpenAILLMService(model="test", api_key="test", max_retries=max_retries)
    create = AsyncMock(side_effect=exc)
    llm._client = SimpleNamespace(ainvoke=create)
    return llm, create


@pytest.mark.asyncio
async def test_authentication_error_raises_llm_auth_error_without_retry():
    llm, create = _service_with_failing_llm(
        _status_error(AuthenticationError, 401), max_retries=2
    )
    with pytest.raises(LLMAuthError):
        await llm.complete("系统", "输入")
    # 401 不可重试：只调用一次
    assert create.call_count == 1


@pytest.mark.asyncio
async def test_rate_limit_error_retries_then_raises_llm_rate_limit_error():
    llm, create = _service_with_failing_llm(
        _status_error(RateLimitError, 429), max_retries=2
    )
    with pytest.raises(LLMRateLimitError):
        await llm.complete("系统", "输入")
    assert create.call_count == 3   # 首次 + 2 次重试


@pytest.mark.asyncio
async def test_llm_error_subclasses_are_api_errors():
    """子类兼容既有 LLMAPIError 捕获（不破坏现有 except 顺序）。"""
    assert issubclass(LLMAuthError, LLMAPIError)
    assert issubclass(LLMRateLimitError, LLMAPIError)


class _GraphRaising:
    """ainvoke 固定抛指定异常的图替身。"""

    def __init__(self, exc: Exception):
        self._exc = exc

    async def ainvoke(self, *args, **kwargs):
        raise self._exc


@pytest.mark.asyncio
async def test_langgraph_backend_maps_auth_error_to_backend_error():
    backend = LangGraphBackend(
        graph=_GraphRaising(LLMAuthError("bad key")),
        llm=SimpleNamespace(),
    )
    with pytest.raises(ChatBackendAuthenticationError):
        await backend.complete(
            ChatInput(session_id="s1", text="你好", client_mode="direct")
        )


@pytest.mark.asyncio
async def test_langgraph_backend_maps_rate_limit_to_backend_error():
    backend = LangGraphBackend(
        graph=_GraphRaising(LLMRateLimitError("限流")),
        llm=SimpleNamespace(),
    )
    with pytest.raises(ChatBackendRateLimitError):
        await backend.complete(
            ChatInput(session_id="s1", text="你好", client_mode="direct")
        )


@pytest.mark.asyncio
async def test_langgraph_backend_stream_propagates_mapped_errors():
    """stream 经由 complete 实现，映射自动生效。"""
    backend = LangGraphBackend(
        graph=_GraphRaising(LLMAuthError("bad key")),
        llm=SimpleNamespace(),
    )
    with pytest.raises(ChatBackendAuthenticationError):
        async for _ in backend.stream(
            ChatInput(session_id="s1", text="你好", client_mode="direct")
        ):
            pass


@pytest.mark.asyncio
async def test_langgraph_backend_other_llm_errors_still_raise_api_error():
    """其余 LLM 错误保持原样上抛（endpoint 落 500 通用分支）。"""
    from src.agent.llm import LLMAPIError, LLMTimeoutError

    backend = LangGraphBackend(
        graph=_GraphRaising(LLMTimeoutError("超时")),
        llm=SimpleNamespace(),
    )
    with pytest.raises(LLMTimeoutError):
        await backend.complete(
            ChatInput(session_id="s1", text="你好", client_mode="direct")
        )