Eric Wang
ca73b1e8c5
Closes the error-code gap between LangGraph and FastGPT backends: the endpoint's 401/429 branches previously could never trigger under the LangGraph backend because all provider failures collapsed into LLMAPIError (500). - agent/llm: LLMAuthError / LLMRateLimitError as LLMAPIError subclasses; OpenAILLMService raises them from openai AuthenticationError (401, no retry) and RateLimitError (429, after bounded retries exhausted) - backends/langgraph: _complete_turn translates LLMAuthError -> ChatBackendAuthenticationError and LLMRateLimitError -> ChatBackendRateLimitError; stream reuses complete() so the mapping applies to both paths; other errors (timeout etc.) propagate unchanged - endpoint untouched: existing 401/429 response branches now fire for both backends Verified: 212 unit tests (7 new error-mapping tests)
135 lines
4.3 KiB
Python
135 lines
4.3 KiB
Python
"""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(
|
||
chat=SimpleNamespace(completions=SimpleNamespace(create=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")
|
||
)
|