[阶段4.3] 接入自建 AI 网关，修复多模型层的四个真实缺陷
改用甲骨文机上已有的 ai-gateway (129.146.203.203:5100)：它本身就 OpenAI 兼容，内部串联 nvidia/gemini/ollama 并轮换 4 个 Gemini key， 比在客户端自己串联更能吸收单厂商的配额和超时。回包里的 provider 字段透传为 meta.upstream，网关侧发生降级时前端也看得见。 fix(ai): 目录里两个 NVIDIA 模型 id 根本不存在 - qwen/qwen2.5-72b-instruct 和 deepseek-ai/deepseek-r1 是我凭印象写的， 实际 GET /v1/models 里没有，调用一律 404 - 改为该账号清单里确实存在的 nemotron-49b / mistral-large， 并在注释里写明 id 必须取自实时清单、不能猜 fix(ai): 请求被本机代理劫持导致网关不可达 - requests 默认读 HTTP_PROXY/ALL_PROXY，把发往甲骨文公网 IP 的请求 也塞进了 127.0.0.1:7897，120s 后超时 - 按 provider 区分：境外厂商(Gemini/NVIDIA)仍走代理，自建网关直连 (session.trust_env=False) fix(ai): 承诺的按模型裁剪从未实现 - 模块注释写着 payload 按 (模型窗口, 天数预算) 取小者裁剪，但实际是 用全局预算构建一次 prompt 发给链上所有模型；365 天数据对 Gemini 的 1M 窗口无碍，却会撑爆 128k 的模型 - 新增 max_days_for()，在循环内按各模型窗口分别构建 prompt fix(ai): 推理模型的思考过程吃光输出预算 - 网关首选 nemotron-3-ultra-550b 是推理模型，回答前先输出一段 chain-of-thought；默认 1024 tokens 全被思考占用，JSON 还没开始 就被截断 - max_tokens 改为可按 provider 声明，网关条目给 3000 fix(ai): 配置在 import 时被冻结 - DEFAULT_CHAIN/TIMEOUT/DAY_BUDGET 是模块级常量，改环境变量不生效， 且让开发机 .env 泄漏进测试进程（测试会读到真实 key 和链配置） - 改为 default_chain()/default_timeout()/default_day_budget() 按调用读取 - conftest 增加 autouse fixture 清空全部 AI_* 变量，测试不再继承 .env 测试 (184 passed, 1 skipped): - 新增 TestGatewayProvider: 透传 upstream、目标 URL/鉴权头、 token 失效时继续降级 - 新增 TestProxyPolicy: 境外厂商与自建端点的代理策略相反 - 新增 TestPerModelSizing: 128k 模型收到的 prompt 必须小于 1M 模型 - 新增 TestMaxTokens: 推理端点预算大于默认，且真正写进两种 payload - 新增 TestLazyConfig: 改环境变量立即生效 - mock 目标从 requests.post 改为 requests.Session.post 实测: 网关链路可返回合法 JSON，但 nemotron-550B 排队较久（约 160s）， 故 AI_TIMEOUT_SECONDS 默认调到 180。 Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
This commit is contained in:
ericwyuan
@@ -55,14 +55,29 @@ def openai_payload(text):
|
||||
|
||||
@pytest.fixture
|
||||
def keys(monkeypatch):
|
||||
"""Pretend both vendors are configured."""
|
||||
"""Direct vendor keys configured; the gateway stays out of the chain."""
|
||||
monkeypatch.setenv("GEMINI_API_KEY", "test-gemini-key")
|
||||
monkeypatch.setenv("NVIDIA_API_KEY", "test-nvidia-key")
|
||||
monkeypatch.delenv("AI_GATEWAY_TOKEN", raising=False)
|
||||
monkeypatch.delenv("AI_GATEWAY_BASE_URL", raising=False)
|
||||
return True
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def no_keys(monkeypatch):
|
||||
for var in (
|
||||
"GEMINI_API_KEY", "NVIDIA_API_KEY",
|
||||
"AI_GATEWAY_TOKEN", "AI_GATEWAY_BASE_URL",
|
||||
):
|
||||
monkeypatch.delenv(var, raising=False)
|
||||
return True
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def gateway(monkeypatch):
|
||||
"""Only the self-hosted gateway is configured."""
|
||||
monkeypatch.setenv("AI_GATEWAY_TOKEN", "test-gateway-token")
|
||||
monkeypatch.setenv("AI_GATEWAY_BASE_URL", "http://gw.test:5100/v1")
|
||||
monkeypatch.delenv("GEMINI_API_KEY", raising=False)
|
||||
monkeypatch.delenv("NVIDIA_API_KEY", raising=False)
|
||||
return True
|
||||
@@ -191,47 +206,47 @@ class TestGeminiProvider:
|
||||
def test_successful_call(self, keys, monkeypatch):
|
||||
captured = {}
|
||||
|
||||
def fake_post(url, **kwargs):
|
||||
def fake_post(self, url, **kwargs):
|
||||
captured["url"] = url
|
||||
captured["headers"] = kwargs.get("headers", {})
|
||||
captured["json"] = kwargs.get("json")
|
||||
return FakeResponse(200, gemini_payload("hello"))
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
out = ai_svc.CATALOG["gemini-flash"].generate("prompt text")
|
||||
|
||||
assert out == "hello"
|
||||
assert out.text == "hello"
|
||||
assert "gemini-flash-latest:generateContent" in captured["url"]
|
||||
assert captured["headers"]["X-goog-api-key"] == "test-gemini-key"
|
||||
assert captured["json"]["contents"][0]["parts"][0]["text"] == "prompt text"
|
||||
|
||||
def test_http_error_becomes_aierror(self, keys, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
requests, "post", lambda *a, **k: FakeResponse(429, text="rate limited")
|
||||
requests.Session, "post", lambda *a, **k: FakeResponse(429, text="rate limited")
|
||||
)
|
||||
with pytest.raises(ai_svc.AIError, match="429"):
|
||||
ai_svc.CATALOG["gemini-flash"].generate("p")
|
||||
|
||||
def test_timeout_becomes_aierror(self, keys, monkeypatch):
|
||||
def boom(*a, **k):
|
||||
def boom(self, *a, **k):
|
||||
raise requests.Timeout("timed out")
|
||||
|
||||
monkeypatch.setattr(requests, "post", boom)
|
||||
monkeypatch.setattr(requests.Session, "post", boom)
|
||||
with pytest.raises(ai_svc.AIError, match="请求失败"):
|
||||
ai_svc.CATALOG["gemini-flash"].generate("p")
|
||||
|
||||
def test_unexpected_shape_becomes_aierror(self, keys, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
requests, "post", lambda *a, **k: FakeResponse(200, {"unexpected": True})
|
||||
requests.Session, "post", lambda *a, **k: FakeResponse(200, {"unexpected": True})
|
||||
)
|
||||
with pytest.raises(ai_svc.AIError, match="响应格式异常"):
|
||||
ai_svc.CATALOG["gemini-flash"].generate("p")
|
||||
|
||||
def test_missing_key_raises_before_any_request(self, no_keys, monkeypatch):
|
||||
def boom(*a, **k):
|
||||
def boom(self, *a, **k):
|
||||
raise AssertionError("must not issue a request without a key")
|
||||
|
||||
monkeypatch.setattr(requests, "post", boom)
|
||||
monkeypatch.setattr(requests.Session, "post", boom)
|
||||
with pytest.raises(ai_svc.AIError, match="GEMINI_API_KEY"):
|
||||
ai_svc.CATALOG["gemini-flash"].generate("p")
|
||||
|
||||
@@ -240,33 +255,232 @@ class TestOpenAICompatProvider:
|
||||
def test_successful_call(self, keys, monkeypatch):
|
||||
captured = {}
|
||||
|
||||
def fake_post(url, **kwargs):
|
||||
def fake_post(self, url, **kwargs):
|
||||
captured["url"] = url
|
||||
captured["headers"] = kwargs.get("headers", {})
|
||||
captured["json"] = kwargs.get("json")
|
||||
return FakeResponse(200, openai_payload("hi"))
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
out = ai_svc.CATALOG["llama-70b"].generate("prompt text")
|
||||
|
||||
assert out == "hi"
|
||||
assert out.text == "hi"
|
||||
assert out.upstream is None, "stock OpenAI replies carry no provider field"
|
||||
assert captured["url"].endswith("/chat/completions")
|
||||
assert captured["headers"]["Authorization"] == "Bearer test-nvidia-key"
|
||||
assert captured["json"]["model"] == "meta/llama-3.3-70b-instruct"
|
||||
|
||||
def test_http_error_becomes_aierror(self, keys, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
requests, "post", lambda *a, **k: FakeResponse(500, text="boom")
|
||||
requests.Session, "post", lambda *a, **k: FakeResponse(500, text="boom")
|
||||
)
|
||||
with pytest.raises(ai_svc.AIError, match="500"):
|
||||
ai_svc.CATALOG["llama-70b"].generate("p")
|
||||
|
||||
|
||||
class TestGatewayProvider:
|
||||
"""The self-hosted gateway: OpenAI-compatible, plus a `provider` field
|
||||
naming whichever upstream actually served the request."""
|
||||
|
||||
def test_reports_the_upstream_that_answered(self, gateway, monkeypatch):
|
||||
payload = {**openai_payload("hi"), "provider": "nvidia"}
|
||||
monkeypatch.setattr(requests.Session, "post", lambda *a, **k: FakeResponse(200, payload))
|
||||
out = ai_svc.CATALOG["gateway"].generate("p")
|
||||
assert out.text == "hi"
|
||||
assert out.upstream == "nvidia"
|
||||
|
||||
def test_targets_the_configured_base_url(self, gateway, monkeypatch):
|
||||
captured = {}
|
||||
|
||||
def fake_post(self, url, **kwargs):
|
||||
captured["url"] = url
|
||||
captured["headers"] = kwargs.get("headers", {})
|
||||
captured["model"] = (kwargs.get("json") or {}).get("model")
|
||||
return FakeResponse(200, openai_payload("hi"))
|
||||
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
ai_svc.CATALOG["gateway"].generate("p")
|
||||
|
||||
assert captured["url"] == "http://gw.test:5100/v1/chat/completions"
|
||||
assert captured["headers"]["Authorization"] == "Bearer test-gateway-token"
|
||||
assert captured["model"] == "ai-gateway-auto"
|
||||
|
||||
def test_upstream_surfaces_in_generate_meta(self, gateway, monkeypatch):
|
||||
payload = {**openai_payload(VALID_REPLY), "provider": "gemini"}
|
||||
monkeypatch.setattr(requests.Session, "post", lambda *a, **k: FakeResponse(200, payload))
|
||||
_, meta = ai_svc.generate(SUMMARY)
|
||||
assert meta["model"] == "gateway"
|
||||
assert meta["upstream"] == "gemini"
|
||||
|
||||
def test_gateway_401_falls_through(self, monkeypatch):
|
||||
"""A stale gateway token must not strand the request."""
|
||||
monkeypatch.setenv("AI_GATEWAY_TOKEN", "expired")
|
||||
monkeypatch.setenv("AI_GATEWAY_BASE_URL", "http://gw.test:5100/v1")
|
||||
monkeypatch.setenv("GEMINI_API_KEY", "k")
|
||||
|
||||
def fake_post(self, url, **kwargs):
|
||||
if "gw.test" in url:
|
||||
return FakeResponse(401, text="unauthorized")
|
||||
return FakeResponse(200, gemini_payload(VALID_REPLY))
|
||||
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
_, meta = ai_svc.generate(SUMMARY)
|
||||
assert meta["model"] == "gemini-flash"
|
||||
assert meta["fallbackFrom"] == ["gateway"]
|
||||
|
||||
|
||||
# --- proxy handling ---------------------------------------------------------
|
||||
class TestProxyPolicy:
|
||||
"""Overseas vendors may only be reachable through a local proxy, while a
|
||||
self-hosted box on a public IP breaks when forced through one — so the two
|
||||
must not share a policy."""
|
||||
|
||||
def test_hosted_vendors_honour_environment_proxies(self):
|
||||
assert ai_svc.CATALOG["gemini-flash"].use_proxy is True
|
||||
assert ai_svc.CATALOG["llama-70b"].use_proxy is True
|
||||
|
||||
def test_self_hosted_gateway_bypasses_proxies(self):
|
||||
assert ai_svc.CATALOG["gateway"].use_proxy is False
|
||||
|
||||
def test_session_trust_env_follows_the_flag(self):
|
||||
"""Regression: requests picked up ALL_PROXY and routed the gateway
|
||||
call through a local proxy, which timed out after 120s."""
|
||||
assert ai_svc.CATALOG["gateway"]._session().trust_env is False
|
||||
assert ai_svc.CATALOG["gemini-flash"]._session().trust_env is True
|
||||
|
||||
|
||||
# --- output budget ----------------------------------------------------------
|
||||
class TestMaxTokens:
|
||||
def test_default_applies_to_ordinary_models(self):
|
||||
assert ai_svc.CATALOG["gemini-flash"].max_tokens == ai_svc.FALLBACK_MAX_TOKENS
|
||||
|
||||
def test_reasoning_endpoint_declares_a_larger_budget(self):
|
||||
"""Regression: the gateway's primary upstream thinks out loud before
|
||||
answering; at the default cap the trace consumed the whole budget and
|
||||
the reply was truncated before any JSON appeared."""
|
||||
assert ai_svc.CATALOG["gateway"].max_tokens > ai_svc.FALLBACK_MAX_TOKENS
|
||||
|
||||
def test_env_overrides_the_default_but_not_an_explicit_budget(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_MAX_TOKENS", "77")
|
||||
assert ai_svc.CATALOG["gemini-flash"].max_tokens == 77
|
||||
assert ai_svc.CATALOG["gateway"].max_tokens == 3000
|
||||
|
||||
def test_budget_reaches_the_openai_payload(self, gateway, monkeypatch):
|
||||
seen = {}
|
||||
|
||||
def fake_post(self, url, **kwargs):
|
||||
seen["max_tokens"] = kwargs["json"]["max_tokens"]
|
||||
return FakeResponse(200, openai_payload("hi"))
|
||||
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
ai_svc.CATALOG["gateway"].generate("p")
|
||||
assert seen["max_tokens"] == 3000
|
||||
|
||||
def test_budget_reaches_the_gemini_payload(self, keys, monkeypatch):
|
||||
seen = {}
|
||||
|
||||
def fake_post(self, url, **kwargs):
|
||||
seen["cap"] = kwargs["json"]["generationConfig"]["maxOutputTokens"]
|
||||
return FakeResponse(200, gemini_payload("hi"))
|
||||
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
ai_svc.CATALOG["gemini-flash"].generate("p")
|
||||
assert seen["cap"] == ai_svc.FALLBACK_MAX_TOKENS
|
||||
|
||||
|
||||
# --- lazily-read configuration ----------------------------------------------
|
||||
class TestLazyConfig:
|
||||
"""Regression: these were module-level constants, so they froze whatever
|
||||
the environment held at import — hiding config changes and letting a
|
||||
developer's .env leak into the test run."""
|
||||
|
||||
def test_chain_reflects_the_current_environment(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_MODEL_CHAIN", "llama-70b,gemini-flash")
|
||||
assert ai_svc.default_chain() == ["llama-70b", "gemini-flash"]
|
||||
monkeypatch.setenv("AI_MODEL_CHAIN", "gateway")
|
||||
assert ai_svc.default_chain() == ["gateway"]
|
||||
|
||||
def test_timeout_reflects_the_current_environment(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_TIMEOUT_SECONDS", "7")
|
||||
assert ai_svc.default_timeout() == 7.0
|
||||
|
||||
def test_day_budget_reflects_the_current_environment(self, monkeypatch):
|
||||
monkeypatch.setenv("AI_DAY_BUDGET", "42")
|
||||
assert ai_svc.default_day_budget() == 42
|
||||
|
||||
def test_defaults_apply_when_unset(self):
|
||||
assert ai_svc.default_timeout() == ai_svc.FALLBACK_TIMEOUT
|
||||
assert ai_svc.default_day_budget() == ai_svc.FALLBACK_DAY_BUDGET
|
||||
assert ai_svc.default_chain()[0] == "gateway"
|
||||
|
||||
def test_default_flag_tracks_the_chain_head(self, monkeypatch, keys):
|
||||
monkeypatch.setenv("AI_MODEL_CHAIN", "llama-70b,gemini-flash")
|
||||
by_id = {m["id"]: m for m in ai_svc.list_models()}
|
||||
assert by_id["llama-70b"]["default"] is True
|
||||
assert by_id["gemini-flash"]["default"] is False
|
||||
|
||||
|
||||
# --- context sizing ---------------------------------------------------------
|
||||
class TestPerModelSizing:
|
||||
"""Chain members' windows differ by >30x, so the payload is sized per
|
||||
model rather than once for the whole chain."""
|
||||
|
||||
def test_small_window_gets_fewer_days_than_a_large_one(self):
|
||||
# A budget above what 128k can hold, so the window is what binds.
|
||||
budget = 100_000
|
||||
small = ai_svc.max_days_for(ai_svc.CATALOG["llama-70b"], budget) # 128k
|
||||
large = ai_svc.max_days_for(ai_svc.CATALOG["gemini-flash"], budget) # 1M
|
||||
assert small < large
|
||||
|
||||
def test_budget_binds_when_it_is_the_tighter_limit(self):
|
||||
"""At the default 365-day budget every model gets the same 365 days —
|
||||
no window in the catalog is small enough to bind first."""
|
||||
budget = ai_svc.default_day_budget()
|
||||
days = {
|
||||
mid: ai_svc.max_days_for(p, budget) for mid, p in ai_svc.CATALOG.items()
|
||||
}
|
||||
assert set(days.values()) == {budget}
|
||||
|
||||
def test_never_exceeds_the_configured_budget(self):
|
||||
assert ai_svc.max_days_for(ai_svc.CATALOG["gemini-flash"], day_budget=30) == 30
|
||||
|
||||
def test_always_allows_at_least_one_day(self):
|
||||
tiny = ai_svc.OpenAICompatProvider(
|
||||
model_id="tiny", context_window=10,
|
||||
base_url_env="X", default_base_url="http://x", requires_key=False,
|
||||
)
|
||||
assert ai_svc.max_days_for(tiny) >= 1
|
||||
|
||||
def test_each_model_gets_a_prompt_sized_for_itself(self, keys, monkeypatch):
|
||||
"""Regression: one prompt was built for the whole chain, so a payload
|
||||
sized for Gemini's 1M window was also sent to 128k models.
|
||||
|
||||
Needs more days than the 128k window holds (~6.4k) for the trimming to
|
||||
bite, hence the deliberately oversized history.
|
||||
"""
|
||||
history = [{"date": "2026-01-01", "steps": 8000} for _ in range(8000)]
|
||||
sizes = {}
|
||||
|
||||
def fake_post(self, url, **kwargs):
|
||||
if "generativelanguage" in url:
|
||||
sizes["gemini"] = len(kwargs["json"]["contents"][0]["parts"][0]["text"])
|
||||
raise requests.Timeout("force fallback")
|
||||
sizes["nvidia"] = len(kwargs["json"]["messages"][0]["content"])
|
||||
return FakeResponse(200, openai_payload(VALID_REPLY))
|
||||
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
ai_svc.generate(history, day_budget=100_000)
|
||||
|
||||
assert sizes["nvidia"] < sizes["gemini"], (
|
||||
"the 128k model must receive a smaller prompt than the 1M model"
|
||||
)
|
||||
|
||||
|
||||
# --- catalog & chain --------------------------------------------------------
|
||||
class TestCatalog:
|
||||
def test_all_models_listed(self, keys):
|
||||
assert {m["id"] for m in ai_svc.list_models()} == {
|
||||
"gemini-flash", "llama-70b", "qwen-72b", "deepseek-r1"
|
||||
"gateway", "gemini-flash", "llama-70b", "nemotron-49b", "mistral-large"
|
||||
}
|
||||
|
||||
def test_configured_flag_tracks_the_environment(self, no_keys, monkeypatch):
|
||||
@@ -285,15 +499,14 @@ class TestCatalog:
|
||||
|
||||
class TestResolveChain:
|
||||
def test_preferred_model_goes_first(self, keys):
|
||||
assert ai_svc.resolve_chain("qwen-72b")[0] == "qwen-72b"
|
||||
assert ai_svc.resolve_chain("nemotron-49b")[0] == "nemotron-49b"
|
||||
|
||||
def test_chain_has_no_duplicates(self, keys):
|
||||
chain = ai_svc.resolve_chain("gemini-flash")
|
||||
assert len(chain) == len(set(chain))
|
||||
|
||||
def test_unconfigured_models_are_skipped(self, monkeypatch):
|
||||
def test_unconfigured_models_are_skipped(self, no_keys, monkeypatch):
|
||||
monkeypatch.setenv("GEMINI_API_KEY", "k")
|
||||
monkeypatch.delenv("NVIDIA_API_KEY", raising=False)
|
||||
assert ai_svc.resolve_chain() == ["gemini-flash"]
|
||||
|
||||
def test_unknown_model_raises(self, keys):
|
||||
@@ -304,12 +517,18 @@ class TestResolveChain:
|
||||
with pytest.raises(ai_svc.AIError, match="GEMINI_API_KEY"):
|
||||
ai_svc.resolve_chain()
|
||||
|
||||
def test_gateway_needs_both_token_and_base_url(self, no_keys, monkeypatch):
|
||||
monkeypatch.setenv("AI_GATEWAY_TOKEN", "t")
|
||||
assert ai_svc.CATALOG["gateway"].is_configured() is False
|
||||
monkeypatch.setenv("AI_GATEWAY_BASE_URL", "http://gw.test:5100/v1")
|
||||
assert ai_svc.CATALOG["gateway"].is_configured() is True
|
||||
|
||||
|
||||
# --- generate + fallback ----------------------------------------------------
|
||||
class TestGenerate:
|
||||
def test_returns_recommendations_and_meta(self, keys, monkeypatch):
|
||||
monkeypatch.setattr(
|
||||
requests, "post", lambda *a, **k: FakeResponse(200, gemini_payload(VALID_REPLY))
|
||||
requests.Session, "post", lambda *a, **k: FakeResponse(200, gemini_payload(VALID_REPLY))
|
||||
)
|
||||
recs, meta = ai_svc.generate(SUMMARY)
|
||||
assert len(recs) == 2
|
||||
@@ -320,13 +539,13 @@ class TestGenerate:
|
||||
def test_falls_back_to_the_next_model(self, keys, monkeypatch):
|
||||
calls = []
|
||||
|
||||
def fake_post(url, **kwargs):
|
||||
def fake_post(self, url, **kwargs):
|
||||
calls.append(url)
|
||||
if "generativelanguage" in url:
|
||||
raise requests.Timeout("gemini down")
|
||||
return FakeResponse(200, openai_payload(VALID_REPLY))
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
recs, meta = ai_svc.generate(SUMMARY)
|
||||
|
||||
assert len(recs) == 2
|
||||
@@ -335,43 +554,43 @@ class TestGenerate:
|
||||
assert len(calls) == 2
|
||||
|
||||
def test_falls_back_when_a_model_returns_unparseable_text(self, keys, monkeypatch):
|
||||
def fake_post(url, **kwargs):
|
||||
def fake_post(self, url, **kwargs):
|
||||
if "generativelanguage" in url:
|
||||
return FakeResponse(200, gemini_payload("抱歉，我帮不了你。"))
|
||||
return FakeResponse(200, openai_payload(VALID_REPLY))
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
_, meta = ai_svc.generate(SUMMARY)
|
||||
assert meta["model"] == "llama-70b"
|
||||
|
||||
def test_raises_when_every_model_fails(self, keys, monkeypatch):
|
||||
def boom(*a, **k):
|
||||
def boom(self, *a, **k):
|
||||
raise requests.Timeout("all down")
|
||||
|
||||
monkeypatch.setattr(requests, "post", boom)
|
||||
monkeypatch.setattr(requests.Session, "post", boom)
|
||||
with pytest.raises(ai_svc.AIError, match="所有模型均失败"):
|
||||
ai_svc.generate(SUMMARY)
|
||||
|
||||
def test_preferred_model_is_honoured(self, keys, monkeypatch):
|
||||
seen = {}
|
||||
|
||||
def fake_post(url, **kwargs):
|
||||
def fake_post(self, url, **kwargs):
|
||||
seen["model"] = (kwargs.get("json") or {}).get("model")
|
||||
return FakeResponse(200, openai_payload(VALID_REPLY))
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
_, meta = ai_svc.generate(SUMMARY, preferred_model="qwen-72b")
|
||||
assert meta["model"] == "qwen-72b"
|
||||
assert seen["model"] == "qwen/qwen2.5-72b-instruct"
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
_, meta = ai_svc.generate(SUMMARY, preferred_model="nemotron-49b")
|
||||
assert meta["model"] == "nemotron-49b"
|
||||
assert seen["model"] == "nvidia/llama-3.3-nemotron-super-49b-v1.5"
|
||||
|
||||
def test_no_second_call_after_the_first_succeeds(self, keys, monkeypatch):
|
||||
calls = []
|
||||
|
||||
def fake_post(url, **kwargs):
|
||||
def fake_post(self, url, **kwargs):
|
||||
calls.append(url)
|
||||
return FakeResponse(200, gemini_payload(VALID_REPLY))
|
||||
|
||||
monkeypatch.setattr(requests, "post", fake_post)
|
||||
monkeypatch.setattr(requests.Session, "post", fake_post)
|
||||
ai_svc.generate(SUMMARY)
|
||||
assert len(calls) == 1
|
||||
|
||||
@@ -388,7 +607,7 @@ class TestAiRecommendationsService:
|
||||
):
|
||||
seed_health([{"date": "2026-08-20", "steps": 5000}])
|
||||
monkeypatch.setattr(
|
||||
requests, "post", lambda *a, **k: FakeResponse(200, gemini_payload(VALID_REPLY))
|
||||
requests.Session, "post", lambda *a, **k: FakeResponse(200, gemini_payload(VALID_REPLY))
|
||||
)
|
||||
out = analysis_svc.get_ai_recommendations(user["id"])
|
||||
assert out["meta"]["source"] == "ai"
|
||||
@@ -399,10 +618,10 @@ class TestAiRecommendationsService:
|
||||
):
|
||||
seed_health([{"date": "2026-08-20", "steps": 5000}])
|
||||
|
||||
def boom(*a, **k):
|
||||
def boom(self, *a, **k):
|
||||
raise requests.Timeout("down")
|
||||
|
||||
monkeypatch.setattr(requests, "post", boom)
|
||||
monkeypatch.setattr(requests.Session, "post", boom)
|
||||
out = analysis_svc.get_ai_recommendations(user["id"])
|
||||
assert out["meta"]["source"] == "rules"
|
||||
assert "所有模型均失败" in out["meta"]["reason"]
|
||||
@@ -444,12 +663,12 @@ class TestEndpoints:
|
||||
):
|
||||
seed_health([{"date": "2026-08-20", "steps": 5000}])
|
||||
monkeypatch.setattr(
|
||||
requests, "post", lambda *a, **k: FakeResponse(200, openai_payload(VALID_REPLY))
|
||||
requests.Session, "post", lambda *a, **k: FakeResponse(200, openai_payload(VALID_REPLY))
|
||||
)
|
||||
r = client.get(
|
||||
"/api/analysis/ai-recommendations?model=qwen-72b", headers=auth
|
||||
"/api/analysis/ai-recommendations?model=nemotron-49b", headers=auth
|
||||
)
|
||||
assert r.get_json()["meta"]["model"] == "qwen-72b"
|
||||
assert r.get_json()["meta"]["model"] == "nemotron-49b"
|
||||
|
||||
def test_unknown_model_param_degrades_to_rules(
|
||||
self, client, auth, seed_health, keys
|
||||
|
||||
Reference in New Issue
Block a user