feat: Phase 1+2 — project setup and core infrastructure

- requirements.txt, config.yaml, .env, Dockerfile, docker-compose.yml
- app/core: config (YAML+env override), logging (JSON structured),
  exceptions (typed hierarchy), json_utils (Markdown fence stripping)
- app/clients: LLMClient ABC + ZhipuAIClient (run_in_executor),
  StorageClient ABC + RustFSClient (boto3 head_object for size check)
- app/main.py: FastAPI app with health endpoint and router registration
- app/core/dependencies.py: lru_cache singleton factories
- tests/conftest.py: mock_llm, mock_storage, test_app, client fixtures
- pytest.ini: asyncio_mode=auto
- 11 unit tests passing
This commit is contained in:
wh
2026-04-10 15:22:45 +08:00
parent 4162d9f4e6
commit e1eb5e47b1
54 changed files with 716 additions and 0 deletions

40
tests/test_llm_client.py Normal file
View File

@@ -0,0 +1,40 @@
import pytest
from unittest.mock import MagicMock, patch
from app.clients.llm.zhipuai_client import ZhipuAIClient
from app.core.exceptions import LLMCallError
@pytest.fixture
def mock_sdk_response():
resp = MagicMock()
resp.choices[0].message.content = '{"result": "ok"}'
return resp
@pytest.fixture
def client():
with patch("app.clients.llm.zhipuai_client.ZhipuAI"):
c = ZhipuAIClient(api_key="test-key")
return c
@pytest.mark.asyncio
async def test_chat_returns_content(client, mock_sdk_response):
client._client.chat.completions.create.return_value = mock_sdk_response
result = await client.chat("glm-4-flash", [{"role": "user", "content": "hello"}])
assert result == '{"result": "ok"}'
@pytest.mark.asyncio
async def test_chat_vision_returns_content(client, mock_sdk_response):
client._client.chat.completions.create.return_value = mock_sdk_response
result = await client.chat_vision("glm-4v-flash", [{"role": "user", "content": []}])
assert result == '{"result": "ok"}'
@pytest.mark.asyncio
async def test_llm_call_error_on_sdk_exception(client):
client._client.chat.completions.create.side_effect = RuntimeError("quota exceeded")
with pytest.raises(LLMCallError, match="大模型调用失败"):
await client.chat("glm-4-flash", [{"role": "user", "content": "hi"}])