Eric Wang
24e2cfbe10
- Validate stage prefixes before forwarding model tokens. Invalid prefixes may use the existing repair budget; once output starts, validation failure aborts the turn without appending a regenerated reply. Bound the token queue and close inner streams when consumption stops. - Replace delete-time lock eviction with reference-counted session locks covering holders and waiters. Serialize set/get with chat/stream/delete and release cancelled waiters without replacing a live lock. - Store person synonyms under workflow-native driver keys and expose consistent alias views to single/group reads and graph prompt injection. - Separate committed field patches from public formUpdate visibility. Commit callbacks keep repository fields synchronized even when updates are hidden or the consumer closes after graph completion. - Disable OpenAI SDK automatic retries. Own bounded retry attempts in the application, use 1/2/4 second backoff, retry streams only before text is emitted, enforce attempt timeouts, and close upstream/client resources. - Translate FastGPT SDK max_retries (total attempts) from the configured extra-retry count, and verify the real SDK loop uses four attempts. - Document the per-LLM budget and streaming failure semantics without claiming the whole multi-call HTTP turn has the same timeout. Validation: 267 offline tests passed, including actual SDK requests through MockTransport, stream repair/abort, timeout/close, lock races, aliases and formUpdate visibility; existing four dependency deprecation warnings.
119 lines
3.8 KiB
Python
119 lines
3.8 KiB
Python
"""OpenAILLMService.stream_tokens 测试（模型侧流式）。
|
|
|
|
mock 客户端返回 token 事件流；验证消息构造与 complete 一致、
|
|
错误分类（401/429/超时/连接）与不重试语义。
|
|
"""
|
|
|
|
import asyncio
|
|
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,
|
|
LLMTimeoutError,
|
|
OpenAILLMService,
|
|
)
|
|
|
|
|
|
def _event(content):
|
|
return SimpleNamespace(
|
|
choices=[SimpleNamespace(delta=SimpleNamespace(content=content))]
|
|
)
|
|
|
|
|
|
def _service_with_stream(events):
|
|
llm = OpenAILLMService(
|
|
model="test-model", api_key="test", base_url="http://llm.local/v1",
|
|
timeout_seconds=5, temperature=0, extra_body={"reasoning_effort": "none"},
|
|
)
|
|
|
|
class _Stream:
|
|
def __init__(self, items):
|
|
self._items = list(items)
|
|
|
|
def __aiter__(self):
|
|
return self._aiter()
|
|
|
|
async def _aiter(self):
|
|
for item in self._items:
|
|
yield item
|
|
|
|
create = AsyncMock(return_value=_Stream(events))
|
|
llm._client = SimpleNamespace(
|
|
chat=SimpleNamespace(completions=SimpleNamespace(create=create))
|
|
)
|
|
return llm, create
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_tokens_yields_incrementally_and_forwards_kwargs():
|
|
llm, create = _service_with_stream([_event("你"), _event(""), _event("好")])
|
|
tokens = [
|
|
token async for token in
|
|
llm.stream_tokens("系统", "输入", history=[{"role": "assistant", "content": "h"}])
|
|
]
|
|
assert tokens == ["你", "好"] # 空 delta 被跳过
|
|
|
|
kwargs = create.call_args.kwargs
|
|
assert kwargs["model"] == "test-model"
|
|
assert kwargs["stream"] is True
|
|
assert kwargs["temperature"] == 0
|
|
assert kwargs["extra_body"]["reasoning_effort"] == "none" # extra_body 透传
|
|
assert kwargs["messages"][0] == {"role": "system", "content": "系统"}
|
|
assert kwargs["messages"][-1] == {"role": "user", "content": "输入"}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_tokens_maps_authentication_error():
|
|
request = httpx.Request("POST", "http://llm.local/v1/chat/completions")
|
|
exc = AuthenticationError("bad key", response=httpx.Response(401, request=request), body=None)
|
|
|
|
llm, create = _service_with_stream([])
|
|
create.side_effect = exc
|
|
with pytest.raises(LLMAuthError):
|
|
async for _ in llm.stream_tokens("系统", "输入"):
|
|
pass
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_tokens_maps_rate_limit_error():
|
|
request = httpx.Request("POST", "http://llm.local/v1/chat/completions")
|
|
exc = RateLimitError("slow down", response=httpx.Response(429, request=request), body=None)
|
|
|
|
llm, create = _service_with_stream([])
|
|
create.side_effect = exc
|
|
with pytest.raises(LLMRateLimitError):
|
|
async for _ in llm.stream_tokens("系统", "输入"):
|
|
pass
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_stream_tokens_times_out_on_stale_stream():
|
|
"""末 token 迟到同样算超时（asyncio.timeout 包整个迭代）。"""
|
|
|
|
class _HangingStream:
|
|
def __aiter__(self):
|
|
return self._gen()
|
|
|
|
async def _gen(self):
|
|
yield _event("你")
|
|
await asyncio.sleep(30) # 超过 timeout_seconds=5
|
|
yield _event("好")
|
|
|
|
llm = OpenAILLMService(model="m", api_key="k", timeout_seconds=0.2)
|
|
create = AsyncMock(return_value=_HangingStream())
|
|
llm._client = SimpleNamespace(
|
|
chat=SimpleNamespace(completions=SimpleNamespace(create=create))
|
|
)
|
|
tokens = []
|
|
with pytest.raises(LLMTimeoutError):
|
|
async for token in llm.stream_tokens("系统", "输入"):
|
|
tokens.append(token)
|
|
assert tokens == ["你"] # 超时前已流出的 token 保留
|