xsl
f46ecc5eb0
Two defects that only surface against the real DeepSeek API, both of which break the cost model rather than the code: deepseek-v4-flash enables thinking mode by default. The same single-turn question took 13.5s with it on and 1.8s with it off, and the thinking tokens are billed at the output rate. That misses NFR-PERF-02b (15s per turn) and inflates every conversational call. SceneConfig now carries an explicit `thinking` flag, all four V1 scenes set it to false, and the provider always sends the parameter rather than relying on the upstream default. Reasoning tokens are recorded separately in Usage.tokens_reasoning so the cost of ever turning it back on is visible. DeepSeek moves to peak/off-peak pricing on 2026-08-17, with peak (Beijing 09:00-12:00 and 14:00-18:00) at twice the off-peak rate. Reports are generated mostly during peak hours, so a single blended rate would leave ob_ai_call -- the only input to V2 pricing -- off by nearly a factor of two. PeakAwareRateTable resolves the rate at call time; cost is computed and stored then, never recomputed later at whatever the current rate happens to be. Also here: - Replace the live API key in the redaction test with a synthetic one. The test that proves we redact secrets was itself a secret leak waiting for its first commit. - Correct LLM_COST_RATES_JSON, which held placeholder rates. - Make ids.SnowflakeGenerator take an injectable clock so rollover and clock-rollback are testable without patching a slots class. - Rename exceptions to the -Error suffix (N818) and clear the remaining ruff, mypy and import-linter findings, including two dead lines: a duplicate pytestmark assignment and a no-op assert on a None return. Gates: ruff, mypy (96 files incl. tests), 4/4 import contracts, detect-secrets, 166 unit + 3 integration tests, migration up/down round-trip.
102 lines
3.3 KiB
Python
Executable File
102 lines
3.3 KiB
Python
Executable File
"""End-to-end vertical slice against real PostgreSQL + Redis.
|
|
|
|
Run with ``make up && make migrate`` first, or let ``scripts/smoke.sh`` do it.
|
|
Skipped automatically when the infrastructure is not reachable, so ``make test``
|
|
stays fast and hermetic.
|
|
|
|
The LLM provider is faked here — ``scripts/smoke.sh`` is the one that proves the
|
|
real DeepSeek path.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import uuid
|
|
from decimal import Decimal
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
|
|
def _infra_available() -> bool:
|
|
return bool(os.getenv("MEIDA_RUN_INTEGRATION"))
|
|
|
|
|
|
pytestmark = [
|
|
pytest.mark.integration,
|
|
pytest.mark.skipif(
|
|
not _infra_available(),
|
|
reason="set MEIDA_RUN_INTEGRATION=1 with PostgreSQL and Redis running",
|
|
),
|
|
]
|
|
|
|
|
|
@pytest.fixture
|
|
async def client() -> Any:
|
|
import httpx
|
|
|
|
from apps.api.main import create_app
|
|
from packages.llm.types import ProviderResponse, Usage
|
|
from packages.shared.config import get_settings
|
|
|
|
app = create_app(get_settings())
|
|
|
|
class FakeProvider:
|
|
name = "deepseek"
|
|
default_model = "deepseek-v4-flash"
|
|
|
|
async def complete(self, request: Any) -> ProviderResponse:
|
|
return ProviderResponse(
|
|
text="建议白衬衫配西裤。",
|
|
model="deepseek-v4-flash",
|
|
usage=Usage(tokens_in=800, tokens_out=120, tokens_cached=600),
|
|
)
|
|
|
|
async def aclose(self) -> None:
|
|
return None
|
|
|
|
transport = httpx.ASGITransport(app=app)
|
|
async with (
|
|
httpx.AsyncClient(transport=transport, base_url="http://test") as http,
|
|
app.router.lifespan_context(app),
|
|
):
|
|
# 替换掉真实 provider：集成用例验证配额与计量链路，不该花钱也不该受网络影响
|
|
app.state.llm_gateway._providers["deepseek"] = FakeProvider()
|
|
yield http
|
|
|
|
|
|
async def test_chat_slice_reserves_commits_and_records_cost(client: Any) -> None:
|
|
token_resp = await client.post(
|
|
"/api/v1/auth/dev-token", json={"device_key": f"it-{uuid.uuid4().hex[:8]}"}
|
|
)
|
|
assert token_resp.json()["code"] == 0
|
|
headers = {"Authorization": f"Bearer {token_resp.json()['data']['access_token']}"}
|
|
|
|
before = (await client.get("/api/v1/quota", headers=headers)).json()["data"]
|
|
|
|
chat = await client.post("/api/v1/agent/chat", json={"message": "面试穿什么"}, headers=headers)
|
|
body = chat.json()
|
|
assert body["code"] == 0
|
|
assert body["data"]["reply"]
|
|
assert body["data"]["prompt_version"] == "v1"
|
|
assert Decimal(body["data"]["usage"]["cost_cents"]) > 0
|
|
|
|
after = (await client.get("/api/v1/quota", headers=headers)).json()["data"]
|
|
assert after["used"] == before["used"] + 1
|
|
|
|
ledger = (await client.get("/api/v1/quota/ledger", headers=headers)).json()["data"]
|
|
assert ledger[0]["tx_type"] == "consume"
|
|
assert ledger[0]["status"] == "committed"
|
|
|
|
|
|
async def test_alias_path_v1_matches_api_v1(client: Any) -> None:
|
|
assert (await client.get("/healthz")).status_code == 200
|
|
token = await client.post("/v1/auth/dev-token", json={"device_key": "alias-check"})
|
|
assert token.json()["code"] == 0
|
|
|
|
|
|
async def test_unauthenticated_requests_get_the_unified_envelope(client: Any) -> None:
|
|
resp = await client.post("/api/v1/agent/chat", json={"message": "hi"})
|
|
assert resp.status_code == 401
|
|
assert resp.json()["code"] == 40100
|