feat: accept sampling overlay on chat() and per-source extra_body

Priority is structured injection > per-call overlay > per-source config,
and extra_body now takes part in the cache fingerprint.
This commit is contained in:
2026-07-31 21:17:49 -04:00
parent 152fa264ed
commit 6bb64ca938
4 changed files with 167 additions and 5 deletions
+101
View File
@@ -19,6 +19,7 @@ from polygateway.backends.memory.cache import InMemoryCache
from polygateway.backends.memory.limiter import InMemoryLimiter
from polygateway.sources import RoundRobinSelector
from polygateway.structured.json_repair import JsonRepairStrategy
from polygateway.structured.native_schema import NativeSchemaStrategy
from polygateway.transports.openai_compat import OpenAICompatTransport
from polygateway.types import (
BackpressurePolicy,
@@ -117,6 +118,106 @@ class TestChatEndToEnd:
await client.chat([{"role": "user", "content": "hi"}], structured="json")
class TestSamplingOverlay:
"""调用级采样参数入口(issue #4 Task 3)。"""
def _capturing_client(self, captured, **overrides):
def handler(request):
captured.append(json.loads(request.content))
return _sse()
return _client(handler=handler, **overrides)
async def test_overlay_reaches_request_body(self):
captured = []
async with self._capturing_client(captured) as client:
await client.chat([{"role": "user", "content": "hi"}], overlay={"seed": 42})
assert captured[0]["seed"] == 42
async def test_call_level_beats_config_level(self):
"""优先级: 调用级 > 配置级(设计决策 A)。"""
captured = []
source = _source(extra_body={"temperature": 0, "top_p": 0.9})
async with self._capturing_client(captured, sources=[source]) as client:
await client.chat([{"role": "user", "content": "hi"}], overlay={"temperature": 1})
assert captured[0]["temperature"] == 1 # 调用级覆盖
assert captured[0]["top_p"] == 0.9 # 配置级未被顶掉的键保留
async def test_structured_injection_beats_call_level(self):
"""结构化注入优先级最高: 它关系到响应能否被解析(设计决策 A)。"""
captured = []
client = self._capturing_client(captured, structured_strategy=NativeSchemaStrategy())
async with client:
await client.chat(
[{"role": "user", "content": "hi"}],
structured="json",
overlay={"response_format": {"type": "text"}},
)
assert captured[0]["response_format"] != {"type": "text"}
async def test_protected_key_rejected_before_onion(self):
"""保护键在进洋葱之前就报错,transport 一次都不该被碰到。"""
captured = []
async with self._capturing_client(captured) as client:
with pytest.raises(ValueError, match="stream"):
await client.chat([{"role": "user", "content": "hi"}], overlay={"stream": False})
assert captured == []
async def test_unserializable_value_rejected_before_onion(self):
"""裸 TypeError 会在 CacheMW 的降级 try 之外炸且无遥测(设计决策 B)。"""
captured = []
async with self._capturing_client(captured) as client:
with pytest.raises(ValueError, match="JSON"):
await client.chat(
[{"role": "user", "content": "hi"}], overlay={"temperature": object()}
)
assert captured == []
async def test_caller_dict_mutation_does_not_leak(self):
"""调用方逐次改 seed 复用同一 dict 是预期模式(设计决策 E)。"""
captured = []
caller_overlay = {"seed": 1}
async with self._capturing_client(captured) as client:
await client.chat([{"role": "user", "content": "hi"}], overlay=caller_overlay)
caller_overlay["seed"] = 2
await client.chat([{"role": "user", "content": "hi"}], overlay=caller_overlay)
assert [c["seed"] for c in captured] == [1, 2]
class TestModelFingerprint:
"""配置级采样参数须进缓存身份,否则改 temperature 后仍读旧缓存(决策 C)。"""
def test_empty_extra_body_keeps_legacy_fingerprint(self):
"""全源无 extra_body 时字面量与旧实现逐字相同,不触发存量缓存冷启动。"""
from polygateway.client import build_model_fingerprint
sources = [_source(), _source(name="qwen_2", model="qwen-plus")]
assert build_model_fingerprint(sources) == "qwen-max,qwen-plus"
def test_extra_body_changes_fingerprint(self):
from polygateway.client import build_model_fingerprint
plain = build_model_fingerprint([_source()])
tuned = build_model_fingerprint([_source(extra_body={"temperature": 0})])
assert plain != tuned
assert tuned.startswith("qwen-max|") # 旧字面量仍是前缀,便于人眼辨认
def test_source_rename_does_not_change_fingerprint(self):
"""指纹按 (model, extra_body) 而非源名: 改名不该误触全量冷启动。"""
from polygateway.client import build_model_fingerprint
a = build_model_fingerprint([_source(name="qwen_1", extra_body={"temperature": 0})])
b = build_model_fingerprint([_source(name="renamed", extra_body={"temperature": 0})])
assert a == b
def test_differing_extra_body_across_sources_is_distinguished(self):
from polygateway.client import build_model_fingerprint
a = build_model_fingerprint([_source(extra_body={"temperature": 0})])
b = build_model_fingerprint([_source(extra_body={"temperature": 1})])
assert a != b
class TestFactories:
def test_from_env_assembles(self):
client = GatewayClient.from_env("LLM", env=_ENV)
+21
View File
@@ -445,6 +445,27 @@ class TestRequestShaping:
)
assert seen["response_format"] == {"type": "json_object"}
async def test_extra_body_merged_and_outranked_by_overlay(self):
"""顺序即优先级: thinking profile → extra_body → overlay(issue #4)。"""
seen = {}
def handler(request):
seen.update(json.loads(request.content))
return _sse_stream(_chunk(content="x"), _chunk(usage=_USAGE))
await _complete(
_transport_for(handler),
_source(extra_body={"temperature": 0, "top_p": 0.9}),
overlay={"temperature": 1},
)
assert seen["temperature"] == 1 # 调用级覆盖配置级
assert seen["top_p"] == 0.9 # 未被顶掉的配置级键保留
async def test_extra_body_cannot_break_governed_keys(self):
"""治理键由 payload 骨架拥有;extra_body 的保护键在构造期已被拦下。"""
with pytest.raises(ValueError, match="stream"):
_source(extra_body={"stream": False})
class TestErrorTranslation:
@pytest.mark.parametrize(