82f4ec4910
enable_thinking=False was a no-op for minimax and openai sources: both profiles had empty dicts on each side, so the payload update injected nothing while the caller believed reasoning had been turned off. A downstream project was blocked on exactly this. The root cause is that an empty dict meant two different things -- "no injection needed" and "we do not know how this provider spells it" -- and that a provider-level table cannot express what turned out to be a per-model property. Live testing showed MiniMax-M3 can disable reasoning via reasoning_effort while M2.7 and M2.5 cannot be disabled at all, which two external registries independently confirm. So the shape stays at provider level and a capability table joins it at model level. Unknown, unsupported and no-opinion are now three distinct values, and resolve_thinking is the single place they meet: it raises at assembly time when a model cannot honour the request, warns and injects for unregistered models, and injects silently otherwise. Every registered capability carries the evidence it was derived from. enable_thinking also joins the cache fingerprint, since it now really does change the request body.
682 lines
30 KiB
Python
682 lines
30 KiB
Python
"""config.py 配置聚合测试(设计 §8): 多源命名、键优先级、缺失报错。"""
|
||
|
||
import contextlib
|
||
import dataclasses
|
||
|
||
import pytest
|
||
from loguru import logger
|
||
|
||
from polygateway.client import GatewayClient
|
||
from polygateway.config import EmbeddingSettings, GatewaySettings, OcrSettings
|
||
|
||
_BASE_ENV = {
|
||
"LLM__QWEN__1__BASE_URL": "https://gw-a.example/v1",
|
||
"LLM__QWEN__1__API_KEY": "sk-a",
|
||
"LLM__QWEN__1__MODEL": "qwen-max",
|
||
"LLM__QWEN__1__TIMEOUT_S": "120",
|
||
"LLM_MAX_RETRIES": "3",
|
||
"LLM_RETRY_BASE_DELAY": "2.0",
|
||
"LLM_RETRY_MAX_DELAY": "30.0",
|
||
"LLM_CIRCUIT_BREAKER_THRESHOLD": "5",
|
||
"LLM_CIRCUIT_BREAKER_COOLDOWN": "60",
|
||
"PGW_CACHE_BACKEND": "none",
|
||
"PGW_TELEMETRY_BACKEND": "none",
|
||
}
|
||
|
||
|
||
@contextlib.contextmanager
|
||
def _captured_warnings():
|
||
"""捕获库发出的 WARNING;loguru 不经标准 logging,pytest 的 caplog 抓不到。"""
|
||
messages: list[str] = []
|
||
sink_id = logger.add(messages.append, level="WARNING")
|
||
try:
|
||
yield messages
|
||
finally:
|
||
logger.remove(sink_id)
|
||
|
||
|
||
def _env(**overrides):
|
||
env = dict(_BASE_ENV)
|
||
env.update({k: v for k, v in overrides.items() if v is not None})
|
||
for k, v in overrides.items():
|
||
if v is None:
|
||
env.pop(k, None)
|
||
return env
|
||
|
||
|
||
class TestSourceAggregation:
|
||
def test_single_source_parsed(self):
|
||
s = GatewaySettings.from_env("LLM", env=_env())
|
||
assert len(s.sources) == 1
|
||
src = s.sources[0]
|
||
assert src.name == "qwen_1" and src.provider == "qwen"
|
||
assert src.base_url == "https://gw-a.example/v1" and src.timeout_s == 120.0
|
||
|
||
def test_multi_source_and_optional_fields(self):
|
||
env = _env(
|
||
**{
|
||
"LLM__DEEPSEEK__2__BASE_URL": "https://gw-b.example/v1",
|
||
"LLM__DEEPSEEK__2__API_KEY": "sk-b",
|
||
"LLM__DEEPSEEK__2__MODEL": "deepseek-chat",
|
||
"LLM__DEEPSEEK__2__TIMEOUT_S": "90",
|
||
"LLM__DEEPSEEK__2__RPM": "60",
|
||
"LLM__DEEPSEEK__2__ENABLE_THINKING": "true",
|
||
"LLM__DEEPSEEK__2__MISSING_DONE": "salvage",
|
||
}
|
||
)
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
by_name = {src.name: src for src in s.sources}
|
||
assert set(by_name) == {"qwen_1", "deepseek_2"}
|
||
ds = by_name["deepseek_2"]
|
||
assert ds.rpm == 60 and ds.enable_thinking is True and ds.missing_done == "salvage"
|
||
assert by_name["qwen_1"].enable_thinking is None # 未配置 = 三态 None
|
||
|
||
def test_other_scope_keys_ignored(self):
|
||
env = _env(
|
||
**{
|
||
"OCR__MONKEY__1__BASE_URL": "http://lan/parse",
|
||
"OCR__MONKEY__1__API_KEY": "x",
|
||
"OCR__MONKEY__1__MODEL": "monkey",
|
||
"OCR__MONKEY__1__TIMEOUT_S": "60",
|
||
}
|
||
)
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert len(s.sources) == 1
|
||
|
||
def test_flat_timeout_is_source_default(self):
|
||
env = _env(LLM_TIMEOUT="300", **{"LLM__QWEN__1__TIMEOUT_S": None})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.sources[0].timeout_s == 300.0
|
||
|
||
@pytest.mark.parametrize("missing", ["BASE_URL", "API_KEY", "MODEL"])
|
||
def test_missing_required_source_field_fails(self, missing):
|
||
with pytest.raises(ValueError, match=missing):
|
||
GatewaySettings.from_env("LLM", env=_env(**{f"LLM__QWEN__1__{missing}": None}))
|
||
|
||
def test_unknown_field_fails_loudly(self):
|
||
with pytest.raises(ValueError, match="TEMPRATURE"):
|
||
GatewaySettings.from_env("LLM", env=_env(**{"LLM__QWEN__1__TEMPRATURE": "0.7"}))
|
||
|
||
def test_no_sources_fails(self):
|
||
env = {k: v for k, v in _BASE_ENV.items() if not k.startswith("LLM__")}
|
||
with pytest.raises(ValueError, match="源"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
|
||
class TestExtraBodyParsing:
|
||
"""配置级采样参数的 env 解析(issue #4 Task 2)。"""
|
||
|
||
def test_json_object_parsed(self):
|
||
env = _env(**{"LLM__QWEN__1__EXTRA_BODY": '{"temperature": 0, "seed": 42}'})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.sources[0].extra_body == {"temperature": 0, "seed": 42}
|
||
|
||
def test_absent_defaults_to_empty(self):
|
||
assert GatewaySettings.from_env("LLM", env=_env()).sources[0].extra_body == {}
|
||
|
||
def test_invalid_json_fails_loudly(self):
|
||
env = _env(**{"LLM__QWEN__1__EXTRA_BODY": "{invalid"})
|
||
with pytest.raises(ValueError, match="EXTRA_BODY"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
def test_non_object_json_fails(self):
|
||
"""数组/标量都不是请求体片段,静默接受会让参数悄悄不生效。"""
|
||
env = _env(**{"LLM__QWEN__1__EXTRA_BODY": "[1, 2]"})
|
||
with pytest.raises(ValueError, match="JSON 对象"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
def test_protected_key_rejected_through_assembly(self):
|
||
"""校验确实挂在装配路径上(而非只在 types.py 里孤立存在)。"""
|
||
env = _env(**{"LLM__QWEN__1__EXTRA_BODY": '{"model": "sneaky"}'})
|
||
with pytest.raises(ValueError, match="model"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
|
||
class TestResilienceKeys:
|
||
def test_flat_legacy_keys(self):
|
||
s = GatewaySettings.from_env("LLM", env=_env())
|
||
assert s.retry.max_attempts == 3 and s.retry.backoff_base_s == 2.0
|
||
assert s.breaker.fail_threshold == 5 and s.breaker.cooldown_s == 60.0
|
||
|
||
def test_scope_keys_override_flat(self):
|
||
env = _env(**{"LLM__RETRY__MAX_ATTEMPTS": "7", "LLM__BREAKER__COOLDOWN_S": "15"})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.retry.max_attempts == 7
|
||
assert s.breaker.cooldown_s == 15.0
|
||
assert s.breaker.fail_threshold == 5 # 未覆盖的仍取平铺键
|
||
|
||
def test_missing_retry_config_fails(self):
|
||
with pytest.raises(ValueError, match="MAX_RETRIES|MAX_ATTEMPTS"):
|
||
GatewaySettings.from_env("LLM", env=_env(LLM_MAX_RETRIES=None))
|
||
|
||
def test_probe_ttl_derived_when_absent(self):
|
||
s = GatewaySettings.from_env("LLM", env=_env())
|
||
# 派生规则(M2 补第三项): max(2 × 最大源 timeout, cooldown, 最大源 timeout + 5)
|
||
assert s.breaker.probe_ttl_s == max(2 * 120.0, 60.0, 120.0 + 5)
|
||
s2 = GatewaySettings.from_env("LLM", env=_env(**{"LLM__BREAKER__PROBE_TTL_S": "300"}))
|
||
assert s2.breaker.probe_ttl_s == 300.0
|
||
|
||
def test_probe_ttl_derivation_third_term_wins(self):
|
||
# timeout=4、cooldown=2 → max(8, 2, 9) = 9;守卫 9 ≥ 4+5 恰好成立不报错
|
||
env = _env(
|
||
LLM_CIRCUIT_BREAKER_COOLDOWN="2",
|
||
**{"LLM__QWEN__1__TIMEOUT_S": "4"},
|
||
)
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.breaker.probe_ttl_s == 9.0
|
||
|
||
def test_explicit_probe_ttl_below_guard_rejected(self):
|
||
# 守卫: probe_ttl_s ≥ max(timeout_s) + 5(CHS container 语义,M2 设计 §3)
|
||
with pytest.raises(ValueError, match="probe"):
|
||
GatewaySettings.from_env("LLM", env=_env(**{"LLM__BREAKER__PROBE_TTL_S": "45"}))
|
||
|
||
def test_selector_and_quota_full(self):
|
||
# M2.5: 缺省选源改 health_aware(生产级默认);显式配置者不变
|
||
s = GatewaySettings.from_env("LLM", env=_env())
|
||
assert s.selector == "health_aware" and s.quota_full == "wait"
|
||
assert (
|
||
GatewaySettings.from_env("LLM", env=_env(**{"LLM__SELECTOR": "round_robin"})).selector
|
||
== "round_robin"
|
||
)
|
||
s2 = GatewaySettings.from_env(
|
||
"LLM", env=_env(**{"LLM__SELECTOR": "least_inflight", "LLM__QUOTA_FULL": "fail_fast"})
|
||
)
|
||
assert s2.selector == "least_inflight" and s2.quota_full == "fail_fast"
|
||
with pytest.raises(ValueError):
|
||
GatewaySettings.from_env("LLM", env=_env(**{"LLM__SELECTOR": "random"}))
|
||
|
||
def test_global_limits(self):
|
||
env = _env(**{"LLM__GLOBAL__MAX_CONCURRENCY": "8", "LLM__GLOBAL__RPM": "120"})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.global_limits.max_concurrency == 8 and s.global_limits.rpm == 120
|
||
assert s.global_limits.tpm == 0
|
||
|
||
|
||
class TestAssemblyGuards:
|
||
def test_structured_retries_default_two(self):
|
||
# M2.5 迭代 4: 缺省重问 1→2(instructor 缺省 3 的保守版;P6 阶梯死亡 3.2% 实证)
|
||
s = GatewaySettings.from_env("LLM", env=_env())
|
||
assert s.structured_max_retries == 2
|
||
s2 = GatewaySettings.from_env("LLM", env=_env(PGW_STRUCTURED_MAX_RETRIES="0"))
|
||
assert s2.structured_max_retries == 0
|
||
|
||
def test_negative_structured_retries_rejected_with_env_key(self):
|
||
"""env 层的检查保留是为了报错能点出键名(构造期那道点的是字段名)。"""
|
||
with pytest.raises(ValueError, match="PGW_STRUCTURED_MAX_RETRIES"):
|
||
GatewaySettings.from_env("LLM", env=_env(PGW_STRUCTURED_MAX_RETRIES="-1"))
|
||
|
||
def test_cache_requires_namespace_and_ttl(self):
|
||
env = _env(PGW_CACHE_BACKEND="memory")
|
||
with pytest.raises(ValueError, match="NAMESPACE"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
env2 = _env(PGW_CACHE_BACKEND="memory", PGW_CACHE_NAMESPACE="proj", PGW_CACHE_TTL_S="0")
|
||
with pytest.raises(ValueError, match="TTL"):
|
||
GatewaySettings.from_env("LLM", env=env2)
|
||
env3 = _env(PGW_CACHE_BACKEND="memory", PGW_CACHE_NAMESPACE="proj", PGW_CACHE_TTL_S="3600")
|
||
s = GatewaySettings.from_env("LLM", env=env3)
|
||
assert s.cache_namespace == "proj" and s.cache_ttl_s == 3600
|
||
|
||
def test_redis_cache_requires_url(self):
|
||
env = _env(PGW_CACHE_BACKEND="redis", PGW_CACHE_NAMESPACE="proj", PGW_CACHE_TTL_S="3600")
|
||
with pytest.raises(ValueError, match="REDIS_URL"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
def test_sqlite_telemetry_requires_path(self):
|
||
env = _env(PGW_TELEMETRY_BACKEND="sqlite")
|
||
with pytest.raises(ValueError, match="SQLITE_PATH"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
def test_timeout_must_fit_lease_ttl(self):
|
||
env = _env(PGW_LEASE_TTL_S="60", **{"LLM__QWEN__1__TIMEOUT_S": "120"})
|
||
with pytest.raises(ValueError, match="租约|lease"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
|
||
def test_effective_breaker_threshold_auto_raised(self):
|
||
env = _env(**{"LLM__QWEN__1__MAX_CONCURRENCY": "8"})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
# 有效阈值 = max(配置值 5, 源级并发 8 × 2) = 16(M2.5: 抬升只看源级)
|
||
assert s.breaker.fail_threshold == 16
|
||
|
||
def test_breaker_threshold_not_raised_by_global_concurrency(self):
|
||
# M2.5 病灶 2 回归: 全局并发不再抬升阈值(M2 曾 max(5, 100×2)=200 使熔断失灵)
|
||
env = _env(**{"LLM__GLOBAL__MAX_CONCURRENCY": "100", "LLM__GLOBAL__RPM": "600"})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.breaker.fail_threshold == 5
|
||
|
||
def test_breaker_rate_channel_defaults_and_overrides(self):
|
||
# M2.5 失败率通道参数: 库缺省(韧性参数缺省先例)与显式覆盖
|
||
s = GatewaySettings.from_env("LLM", env=_env())
|
||
assert s.breaker.min_calls == 10
|
||
assert s.breaker.fail_rate == pytest.approx(0.6)
|
||
assert s.breaker.window_s == pytest.approx(60.0)
|
||
assert s.breaker.max_cooldown_s == pytest.approx(300.0) # max(300, cooldown 60)
|
||
env = _env(
|
||
**{
|
||
"LLM__BREAKER__MIN_CALLS": "20",
|
||
"LLM__BREAKER__FAIL_RATE": "0.5",
|
||
"LLM__BREAKER__WINDOW_S": "30",
|
||
"LLM__BREAKER__MAX_COOLDOWN_S": "600",
|
||
"LLM_CIRCUIT_BREAKER_COOLDOWN": "400",
|
||
}
|
||
)
|
||
s2 = GatewaySettings.from_env("LLM", env=env)
|
||
assert s2.breaker.min_calls == 20 and s2.breaker.fail_rate == pytest.approx(0.5)
|
||
assert s2.breaker.window_s == pytest.approx(30.0)
|
||
assert s2.breaker.max_cooldown_s == pytest.approx(600.0)
|
||
|
||
def test_breaker_max_cooldown_floor_follows_cooldown(self):
|
||
# 缺省封顶 = max(300, cooldown): 冷却 400s 时封顶随之 400s
|
||
env = _env(**{"LLM_CIRCUIT_BREAKER_COOLDOWN": "400"})
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.breaker.max_cooldown_s == pytest.approx(400.0)
|
||
|
||
def test_redis_governance_backend_requires_url(self):
|
||
"""M2 解禁 redis 后端: 取 redis 时 REDIS_URL 必在,缺则装配报错。"""
|
||
env = _env(
|
||
PGW_LIMITER_BACKEND="redis",
|
||
PGW_BREAKER_BACKEND="redis",
|
||
REDIS_URL="redis://:pw@10.0.0.1:6379/3",
|
||
)
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.limiter_backend == "redis" and s.breaker_backend == "redis"
|
||
with pytest.raises(ValueError, match="REDIS_URL"):
|
||
GatewaySettings.from_env("LLM", env=_env(PGW_LIMITER_BACKEND="redis"))
|
||
|
||
def test_postgres_telemetry_requires_dsn_and_strips_driver_suffix(self):
|
||
"""M2: telemetry=postgres 需 PGW_TELEMETRY_PG_DSN;SQLAlchemy 风格驱动后缀剥离。"""
|
||
with pytest.raises(ValueError, match="PG_DSN"):
|
||
GatewaySettings.from_env("LLM", env=_env(PGW_TELEMETRY_BACKEND="postgres"))
|
||
env = _env(
|
||
PGW_TELEMETRY_BACKEND="postgres",
|
||
PGW_TELEMETRY_PG_DSN="postgresql+psycopg://u:p@h:5432/polygateway",
|
||
)
|
||
s = GatewaySettings.from_env("LLM", env=env)
|
||
assert s.telemetry_pg_dsn == "postgresql://u:p@h:5432/polygateway"
|
||
env2 = _env(
|
||
PGW_TELEMETRY_BACKEND="postgres",
|
||
PGW_TELEMETRY_PG_DSN="postgresql+asyncpg://u:p@h:5432/polygateway",
|
||
)
|
||
assert (
|
||
GatewaySettings.from_env("LLM", env=env2).telemetry_pg_dsn
|
||
== "postgresql://u:p@h:5432/polygateway"
|
||
)
|
||
|
||
def test_telemetry_backend_whitelist(self):
|
||
with pytest.raises(ValueError, match="TELEMETRY_BACKEND"):
|
||
GatewaySettings.from_env("LLM", env=_env(PGW_TELEMETRY_BACKEND="mysql"))
|
||
|
||
def test_cache_backend_whitelist(self):
|
||
"""对称于上一条: env 层的域检查保留是为了报错能点出键名,得有测试守着。"""
|
||
with pytest.raises(ValueError, match="CACHE_BACKEND"):
|
||
GatewaySettings.from_env("LLM", env=_env(PGW_CACHE_BACKEND="rediss"))
|
||
|
||
def test_pricing_path_optional(self):
|
||
assert GatewaySettings.from_env("LLM", env=_env()).pricing_path is None
|
||
s = GatewaySettings.from_env("LLM", env=_env(PGW_PRICING_PATH="conf/prices.json"))
|
||
assert s.pricing_path == "conf/prices.json"
|
||
|
||
def test_stall_window_must_cover_ttft(self):
|
||
"""守卫: stall_window_s ≥ 最大 ttft_timeout_s(防误判卡死,ARCH §7.3)。"""
|
||
env = _env(
|
||
**{
|
||
"LLM__QWEN__1__TTFT_TIMEOUT_S": "30",
|
||
"LLM__QWEN__1__INTER_TOKEN_TIMEOUT_S": "15",
|
||
"LLM__BACKPRESSURE__STALL_WINDOW_S": "20",
|
||
}
|
||
)
|
||
with pytest.raises(ValueError, match="stall"):
|
||
GatewaySettings.from_env("LLM", env=env)
|
||
env_ok = dict(env)
|
||
env_ok["LLM__BACKPRESSURE__STALL_WINDOW_S"] = "60"
|
||
assert GatewaySettings.from_env("LLM", env=env_ok).backpressure.stall_window_s == 60.0
|
||
|
||
|
||
class TestOcrSettings:
|
||
"""M3 OcrSettings(设计 §3.4): 复用 GatewaySettings,无 OCR 专用键。"""
|
||
|
||
_OCR_ENV = {
|
||
"OCR__MONKEY__1__BASE_URL": "http://10.77.0.20:7866",
|
||
"OCR__MONKEY__1__API_KEY": "none", # 无鉴权占位惯例
|
||
"OCR__MONKEY__1__MODEL": "monkey-ocr",
|
||
"OCR__MONKEY__1__TIMEOUT_S": "120",
|
||
"LLM_MAX_RETRIES": "3",
|
||
"LLM_RETRY_BASE_DELAY": "2.0",
|
||
"LLM_RETRY_MAX_DELAY": "30.0",
|
||
"LLM_CIRCUIT_BREAKER_THRESHOLD": "5",
|
||
"LLM_CIRCUIT_BREAKER_COOLDOWN": "60",
|
||
"PGW_CACHE_BACKEND": "none",
|
||
"PGW_TELEMETRY_BACKEND": "none",
|
||
}
|
||
|
||
def test_minimal_ocr_scope(self):
|
||
from polygateway.config import OcrSettings
|
||
|
||
settings = OcrSettings.from_env("OCR", env=dict(self._OCR_ENV))
|
||
gw = settings.gateway
|
||
assert gw.scope == "ocr" # GatewaySettings 统一小写归一(既有约定)
|
||
assert gw.sources[0].name == "monkey_1"
|
||
assert gw.sources[0].provider == "monkey"
|
||
assert gw.sources[0].trust_env is True
|
||
|
||
def test_scope_resilience_override(self):
|
||
from polygateway.config import OcrSettings
|
||
|
||
env = dict(self._OCR_ENV)
|
||
env["OCR__RETRY__MAX_ATTEMPTS"] = "5"
|
||
env["OCR__MONKEY__1__TRUST_ENV"] = "false"
|
||
settings = OcrSettings.from_env("OCR", env=env)
|
||
assert settings.gateway.retry.max_attempts == 5
|
||
assert settings.gateway.sources[0].trust_env is False
|
||
|
||
def test_missing_base_url_fails(self):
|
||
from polygateway.config import OcrSettings
|
||
|
||
env = {k: v for k, v in self._OCR_ENV.items() if k != "OCR__MONKEY__1__BASE_URL"}
|
||
with pytest.raises(ValueError):
|
||
OcrSettings.from_env("OCR", env=env)
|
||
|
||
|
||
class TestCrossFieldInvariants:
|
||
"""四条跨字段不变量必须在**任何**构造路径上生效(设计 2026-07-29)。
|
||
|
||
这些约束单看一个字段都合法,组合起来才非法,因此 types.py 各子配置的
|
||
__post_init__ 看不见——只能由聚合层 GatewaySettings 把关。守卫若只挂在
|
||
from_env 上,from_settings 这条同等官方的装配路(CLAUDE.md §4.5)就能
|
||
装出违反不变量的配置,类会存在于自己 docstring 声称不可能的状态。
|
||
|
||
每条不变量测两侧: 越界必拒、边界值(恰好相等)必过——收紧的是错的组合,
|
||
不是所有直接构造。
|
||
"""
|
||
|
||
def _base(self, **overrides) -> GatewaySettings:
|
||
return GatewaySettings.from_env("LLM", env=_env(**overrides))
|
||
|
||
def _with_watchdog(self) -> GatewaySettings:
|
||
"""带看门狗的基准: TTFT/inter-token 成对配置才满足 SourceConfig 不变式。"""
|
||
return self._base(
|
||
**{
|
||
"LLM__QWEN__1__TTFT_TIMEOUT_S": "30",
|
||
"LLM__QWEN__1__INTER_TOKEN_TIMEOUT_S": "15",
|
||
"LLM__BACKPRESSURE__STALL_WINDOW_S": "300",
|
||
}
|
||
)
|
||
|
||
# —— 源超时 ≤ permit 租约 TTL(ARCH §7.3: 防租约先于请求过期,并发悄悄超配额)——
|
||
|
||
def test_lease_rejects_timeout_above_ttl_on_direct_construction(self):
|
||
base = self._base() # 源 timeout_s=120
|
||
with pytest.raises(ValueError, match="lease_ttl_s"):
|
||
dataclasses.replace(base, lease_ttl_s=1.0)
|
||
|
||
def test_lease_accepts_timeout_equal_to_ttl(self):
|
||
base = self._base()
|
||
assert dataclasses.replace(base, lease_ttl_s=120.0).lease_ttl_s == 120.0
|
||
|
||
# —— stall 窗口 ≥ 最大源 TTFT(ARCH §7.3: 防正常慢首包被误判卡死掐断)——
|
||
|
||
def test_stall_rejects_window_below_max_ttft_on_direct_construction(self):
|
||
base = self._with_watchdog() # 源 ttft_timeout_s=30
|
||
narrowed = dataclasses.replace(base.backpressure, stall_window_s=20.0)
|
||
with pytest.raises(ValueError, match="stall_window_s"):
|
||
dataclasses.replace(base, backpressure=narrowed)
|
||
|
||
def test_stall_accepts_window_equal_to_max_ttft(self):
|
||
base = self._with_watchdog()
|
||
exact = dataclasses.replace(base.backpressure, stall_window_s=30.0)
|
||
assert dataclasses.replace(base, backpressure=exact).backpressure.stall_window_s == 30.0
|
||
|
||
# —— 探针租约 ≥ 最慢源超时 + 5(M2 设计 §3: 防半开探针在途即被接管)——
|
||
|
||
def test_probe_rejects_ttl_below_floor_on_direct_construction(self):
|
||
base = self._base() # 最慢 timeout_s=120,故下限 125
|
||
shortened = dataclasses.replace(base.breaker, probe_ttl_s=100.0)
|
||
with pytest.raises(ValueError, match="probe_ttl_s"):
|
||
dataclasses.replace(base, breaker=shortened)
|
||
|
||
def test_probe_accepts_ttl_at_floor(self):
|
||
base = self._base()
|
||
at_floor = dataclasses.replace(base.breaker, probe_ttl_s=125.0)
|
||
assert dataclasses.replace(base, breaker=at_floor).breaker.probe_ttl_s == 125.0
|
||
|
||
# —— sources 非空 ——
|
||
|
||
def test_empty_sources_rejected_with_actionable_message(self):
|
||
"""零源装出来的 client 选源必然失败;消息须点明原因,不能泄漏 max() 的内置异常。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError) as exc:
|
||
dataclasses.replace(base, sources=())
|
||
assert "至少一个源" in str(exc.value)
|
||
assert "empty sequence" not in str(exc.value)
|
||
|
||
# —— 装配路径覆盖 ——
|
||
|
||
def test_factory_cannot_receive_invalid_settings(self):
|
||
"""from_settings 这条路吃不到非法配置。
|
||
|
||
异常实际抛在实参求值(构造 settings)那一刻,而不是工厂内部——这正是
|
||
把守卫放构造期换来的性质: 非法实例根本不存在,无需每个工厂各自设防。
|
||
"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="lease_ttl_s"):
|
||
GatewayClient.from_settings(dataclasses.replace(base, lease_ttl_s=1.0))
|
||
|
||
# —— 推理开关的装配守卫(issue #5)——
|
||
|
||
def _thinking_sources(self, provider, model, enable_thinking):
|
||
base = self._base()
|
||
src = dataclasses.replace(
|
||
base.sources[0], provider=provider, model=model, enable_thinking=enable_thinking
|
||
)
|
||
return dataclasses.replace(base, sources=(src,))
|
||
|
||
def test_model_that_cannot_disable_thinking_fails_at_assembly(self):
|
||
"""M2.x 关不掉推理: 配了 false 必须当场炸,而不是装出一个骗人的 client。"""
|
||
settings = self._thinking_sources("minimax", "MiniMax-M2.7", False)
|
||
with pytest.raises(ValueError, match="MiniMax-M2.7"):
|
||
GatewayClient.from_settings(settings)
|
||
|
||
def test_unknown_thinking_shape_fails_at_assembly(self):
|
||
"""provider=openai 是任意兼容厂商的兜底段名,形态未知即报错并指路。"""
|
||
settings = self._thinking_sources("openai", "kimi-k3", False)
|
||
with pytest.raises(ValueError, match="register_provider"):
|
||
GatewayClient.from_settings(settings)
|
||
|
||
def test_supported_combination_assembles(self):
|
||
settings = self._thinking_sources("minimax", "MiniMax-M3", False)
|
||
assert GatewayClient.from_settings(settings) is not None
|
||
|
||
def test_not_taking_a_position_never_trips_the_guard(self):
|
||
"""enable_thinking=None(不干预)对任何 provider 都不该被守卫拦下。"""
|
||
settings = self._thinking_sources("openai", "kimi-k3", None)
|
||
assert GatewayClient.from_settings(settings) is not None
|
||
|
||
def test_ocr_settings_cannot_wrap_invalid_gateway(self):
|
||
"""OcrSettings/EmbeddingSettings 只是包一层 GatewaySettings,自动继承同一把关。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="lease_ttl_s"):
|
||
OcrSettings(gateway=dataclasses.replace(base, lease_ttl_s=1.0))
|
||
|
||
# —— 第二轮(设计 2026-07-30): 后端枚举合法域 ——
|
||
|
||
@pytest.mark.parametrize(
|
||
("field", "bad_value"),
|
||
[
|
||
("limiter_backend", "rediss"),
|
||
("breaker_backend", "sqlite"),
|
||
("cache_backend", "postgres"),
|
||
("telemetry_backend", "redis"),
|
||
("selector", "random"),
|
||
("quota_full", "block"),
|
||
],
|
||
)
|
||
def test_enum_field_rejects_value_outside_domain(self, field, bad_value):
|
||
"""域外取值此前只有 from_env 拦得住,直接构造会落进 _build_* 的 else 分支。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match=field):
|
||
dataclasses.replace(base, **{field: bad_value})
|
||
|
||
# —— 条件必填: 取 redis 的后端必须有 redis_url ——
|
||
|
||
@pytest.mark.parametrize("field", ["limiter_backend", "breaker_backend"])
|
||
def test_redis_backend_requires_redis_url(self, field):
|
||
"""client.py 的 assert settings.redis_url is not None 依赖的正是这条。"""
|
||
base = self._base() # redis_url=None
|
||
with pytest.raises(ValueError, match="redis_url"):
|
||
dataclasses.replace(base, **{field: "redis"})
|
||
|
||
def test_redis_cache_requires_redis_url(self):
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="redis_url"):
|
||
dataclasses.replace(base, cache_backend="redis", cache_namespace="ns", cache_ttl_s=60)
|
||
|
||
# —— 条件必填: 启用缓存必须有命名空间与正 TTL ——
|
||
|
||
def test_cache_requires_namespace(self):
|
||
"""缺命名空间即失去租户隔离,踩"无缓存毒化"铁律。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="cache_namespace"):
|
||
dataclasses.replace(base, cache_backend="memory", cache_ttl_s=60)
|
||
|
||
def test_cache_ttl_must_be_positive(self):
|
||
"""from_env 明令禁止的"永不过期"不能从另一条路进来。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="cache_ttl_s"):
|
||
dataclasses.replace(base, cache_backend="memory", cache_namespace="ns", cache_ttl_s=0)
|
||
|
||
# —— 条件必填: 遥测后端各自的落点 ——
|
||
|
||
def test_sqlite_telemetry_requires_path(self):
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="telemetry_sqlite_path"):
|
||
dataclasses.replace(base, telemetry_backend="sqlite")
|
||
|
||
def test_postgres_telemetry_requires_dsn(self):
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="telemetry_pg_dsn"):
|
||
dataclasses.replace(base, telemetry_backend="postgres")
|
||
|
||
# —— 标量域 ——
|
||
|
||
def test_negative_structured_retries_rejected(self):
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="structured_max_retries"):
|
||
dataclasses.replace(base, structured_max_retries=-1)
|
||
|
||
def test_blank_scope_rejected(self):
|
||
"""空 scope 会污染遥测与缓存命名空间。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="scope"):
|
||
dataclasses.replace(base, scope=" ")
|
||
|
||
# —— 合法组合仍可构造(收紧的是错的那些)——
|
||
|
||
def test_full_redis_stack_constructible(self):
|
||
base = self._base()
|
||
settings = dataclasses.replace(
|
||
base,
|
||
limiter_backend="redis",
|
||
breaker_backend="redis",
|
||
cache_backend="redis",
|
||
cache_namespace="ns",
|
||
cache_ttl_s=60,
|
||
redis_url="redis://127.0.0.1:6379/3",
|
||
)
|
||
assert settings.cache_ttl_s == 60 and settings.redis_url is not None
|
||
|
||
# —— Postgres DSN: 剥 SQLAlchemy 驱动后缀并出声(设计 §5 方案 C)——
|
||
|
||
def test_sqlalchemy_dsn_suffix_stripped_with_warning(self):
|
||
"""asyncpg 不认 `+driver`;库替调用方剥掉,但不静默——日志里看得见。"""
|
||
base = self._base()
|
||
with _captured_warnings() as warnings:
|
||
settings = dataclasses.replace(
|
||
base,
|
||
telemetry_backend="postgres",
|
||
telemetry_pg_dsn="postgresql+asyncpg://u:s3cret@h/db",
|
||
)
|
||
assert settings.telemetry_pg_dsn == "postgresql://u:s3cret@h/db"
|
||
assert any("asyncpg" in m for m in warnings)
|
||
|
||
def test_dsn_warning_does_not_leak_credentials(self):
|
||
"""DSN 带密码,日志只能出现 scheme 段(P5: 敏感信息只走 .env)。"""
|
||
base = self._base()
|
||
with _captured_warnings() as warnings:
|
||
dataclasses.replace(
|
||
base,
|
||
telemetry_backend="postgres",
|
||
telemetry_pg_dsn="postgresql+asyncpg://u:s3cret@h/db",
|
||
)
|
||
assert warnings and not any("s3cret" in m or "@h/db" in m for m in warnings)
|
||
|
||
def test_env_path_strips_dsn_without_warning(self):
|
||
"""env 路已在 _load_pg_dsn 剥过,不该给三项目的历史 DSN 写法刷噪音。"""
|
||
with _captured_warnings() as warnings:
|
||
settings = GatewaySettings.from_env(
|
||
"LLM",
|
||
env=_env(
|
||
PGW_TELEMETRY_BACKEND="postgres",
|
||
PGW_TELEMETRY_PG_DSN="postgresql+asyncpg://u@h/db",
|
||
),
|
||
)
|
||
assert settings.telemetry_pg_dsn == "postgresql://u@h/db"
|
||
assert not warnings
|
||
|
||
# —— 构造期规范化: env 路一直在做的,构造路也要做(否则两条路产出不同的值)——
|
||
|
||
@pytest.mark.parametrize("raw", ["LLM", " llm ", " LLM "])
|
||
def test_scope_normalized_on_direct_construction(self, raw):
|
||
"""scope 直接进 Redis key(pgw:limit:{scope}:…)。
|
||
|
||
大小写不一致会让同一逻辑 scope 的限流/熔断状态分裂到两套命名空间——
|
||
两边各记各的配额与熔断状态,分布式治理静默失效且不报错。
|
||
"""
|
||
base = self._base()
|
||
assert dataclasses.replace(base, scope=raw).scope == "llm"
|
||
|
||
def test_blank_redis_url_normalized_to_none(self):
|
||
"""空串此前只有 env 路归 None,构造路留着它骗过 `is None` 判断。"""
|
||
base = self._base()
|
||
assert dataclasses.replace(base, redis_url="").redis_url is None
|
||
|
||
def test_blank_redis_url_still_blocks_redis_backend(self):
|
||
"""归 None 后必须落进条件必填,而不是放行到 redis 库去抛连接串天书。"""
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="redis_url"):
|
||
dataclasses.replace(base, limiter_backend="redis", redis_url="")
|
||
|
||
def test_blank_pricing_path_normalized_to_none(self):
|
||
base = self._base()
|
||
assert dataclasses.replace(base, pricing_path="").pricing_path is None
|
||
|
||
# —— EmbeddingSettings 自身的字段域(此前只有 from_env 校验)——
|
||
|
||
@pytest.mark.parametrize("bad", [0, -3])
|
||
def test_embedding_settings_rejects_non_positive_batch_size(self, bad):
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="batch_size"):
|
||
EmbeddingSettings(gateway=base, batch_size=bad)
|
||
|
||
def test_embedding_settings_rejects_non_positive_expected_dim(self):
|
||
base = self._base()
|
||
with pytest.raises(ValueError, match="expected_dim"):
|
||
EmbeddingSettings(gateway=base, batch_size=8, expected_dim=0)
|
||
|
||
def test_embedding_settings_accepts_valid_values(self):
|
||
base = self._base()
|
||
settings = EmbeddingSettings(gateway=base, batch_size=8, expected_dim=1024)
|
||
assert settings.batch_size == 8 and settings.expected_dim == 1024
|
||
|
||
# —— 回归护栏: client.py 的 assert 前提确实被保证了 ——
|
||
|
||
def test_factory_accepts_valid_redis_stack(self):
|
||
"""补齐校验后,client.py:262/282/302 的 assert 退回成纯内部不变量声明。"""
|
||
base = self._base()
|
||
settings = dataclasses.replace(
|
||
base,
|
||
limiter_backend="redis",
|
||
breaker_backend="redis",
|
||
redis_url="redis://127.0.0.1:6379/3",
|
||
)
|
||
client = GatewayClient.from_settings(settings)
|
||
assert client is not None
|