feat: add a required first-token event to the transport port
Transport.complete gains the keyword-only first_token_event (no default, per the port convention): streaming sets it on the first delta, the non-streaming path accepts it but never sets it, None means the caller does not observe the first token. All fake/wrapping transports and the three direct call sites follow the signature; the e2e wrapper forwards. Red-green evidence: tests/outputs/137/t1/ (batch A TypeError red, then 147 file tests + 1550 unit tests green).
This commit is contained in:
@@ -1,5 +1,6 @@
|
||||
"""测试侧独立 HTTP 取证装配;无环境自读取或成功 SSE 预读。"""
|
||||
|
||||
import asyncio
|
||||
from collections.abc import AsyncIterator, Iterator, Mapping
|
||||
from contextlib import AsyncExitStack, asynccontextmanager, contextmanager
|
||||
from contextvars import ContextVar
|
||||
@@ -290,6 +291,7 @@ class ObservedTransport:
|
||||
overlay: dict[str, Any],
|
||||
call_id: str,
|
||||
reasoning_effort: Effort | None,
|
||||
first_token_event: asyncio.Event | None,
|
||||
) -> TransportResult:
|
||||
"""与生产端口逐参数同签名。"""
|
||||
with self._capture.attempt_context(call_id):
|
||||
@@ -301,6 +303,7 @@ class ObservedTransport:
|
||||
overlay=overlay,
|
||||
call_id=call_id,
|
||||
reasoning_effort=reasoning_effort,
|
||||
first_token_event=first_token_event,
|
||||
)
|
||||
|
||||
async def embed(
|
||||
|
||||
@@ -75,7 +75,9 @@ class ScriptedTransport:
|
||||
# 取消用例的确定性窗口(同 test_retry FakeTransport): 进入挂起即置位
|
||||
self.entered = asyncio.Event()
|
||||
|
||||
async def complete(self, *, messages, source, stream, overlay, call_id, reasoning_effort):
|
||||
async def complete(
|
||||
self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
|
||||
):
|
||||
self.calls.append(source.name)
|
||||
if self.hang:
|
||||
self.entered.set()
|
||||
|
||||
@@ -210,7 +210,9 @@ class ClockAdvancingTransport:
|
||||
self.clock = clock
|
||||
self.calls = []
|
||||
|
||||
async def complete(self, *, messages, source, stream, overlay, call_id, reasoning_effort):
|
||||
async def complete(
|
||||
self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
|
||||
):
|
||||
self.calls.append((source.name, call_id))
|
||||
advance, action = self.script.pop(0)
|
||||
self.clock.advance(advance)
|
||||
|
||||
@@ -1738,7 +1738,9 @@ class _ClockJumpTransport:
|
||||
self._jump = jump
|
||||
self.calls = []
|
||||
|
||||
async def complete(self, *, messages, source, stream, overlay, call_id, reasoning_effort):
|
||||
async def complete(
|
||||
self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
|
||||
):
|
||||
self.calls.append(call_id)
|
||||
self._clock.advance(self._jump)
|
||||
return _ok()
|
||||
|
||||
@@ -277,6 +277,7 @@ async def _complete(observed, *, call_id="a", stream=False):
|
||||
overlay={},
|
||||
call_id=call_id,
|
||||
reasoning_effort=None,
|
||||
first_token_event=None,
|
||||
)
|
||||
|
||||
|
||||
@@ -1266,6 +1267,7 @@ async def test_structured_first_attempt_requires_exact_initial_messages():
|
||||
overlay={},
|
||||
call_id="first",
|
||||
reasoning_effort=None,
|
||||
first_token_event=None,
|
||||
)
|
||||
event = capture.attempts(session_id="first", parent_call_id="parent")[0].http[0]
|
||||
assert not request_is_valid(event)
|
||||
|
||||
@@ -3,6 +3,7 @@
|
||||
SSE 帧样本按三项目真实网关响应形态二次构造(OpenAI 兼容 chunk 结构)。
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
|
||||
import httpx
|
||||
@@ -79,7 +80,9 @@ def _transport_for(handler, *, registry=None):
|
||||
)
|
||||
|
||||
|
||||
async def _complete(transport, source, *, stream=True, overlay=None, reasoning_effort=None):
|
||||
async def _complete(
|
||||
transport, source, *, stream=True, overlay=None, reasoning_effort=None, first_token_event=None
|
||||
):
|
||||
return await transport.complete(
|
||||
messages=[{"role": "user", "content": "hi"}],
|
||||
source=source,
|
||||
@@ -87,6 +90,7 @@ async def _complete(transport, source, *, stream=True, overlay=None, reasoning_e
|
||||
overlay=overlay or {},
|
||||
call_id="cid-1",
|
||||
reasoning_effort=reasoning_effort,
|
||||
first_token_event=first_token_event,
|
||||
)
|
||||
|
||||
|
||||
@@ -214,6 +218,65 @@ class TestStreamHappyPath:
|
||||
assert await _recorded_cost(result, source) is None
|
||||
|
||||
|
||||
class TestFirstTokenEvent:
|
||||
"""首 token 处置位(1.3.7 对冲 H2): 流式置位、非流式永不置位、None 不观测。"""
|
||||
|
||||
async def test_stream_sets_first_token_event(self):
|
||||
"""流式首 token(内容或思考增量)到达即置位——对冲触发窗的取消信号。"""
|
||||
|
||||
def handler(request):
|
||||
return _sse_stream(
|
||||
_chunk(reasoning="ponder"), _chunk(content="hi"), _chunk(usage=_USAGE)
|
||||
)
|
||||
|
||||
event = asyncio.Event()
|
||||
result = await _complete(_transport_for(handler), _source(), first_token_event=event)
|
||||
assert result.content == "hi"
|
||||
assert event.is_set()
|
||||
|
||||
async def test_non_stream_never_sets_first_token_event(self):
|
||||
"""非流式物理上无中途信号: 即使调用方给了事件,本路径也永不置位。"""
|
||||
|
||||
def handler(request):
|
||||
return httpx.Response(
|
||||
200, json={"choices": [{"message": {"content": "42"}}], "usage": _USAGE}
|
||||
)
|
||||
|
||||
event = asyncio.Event()
|
||||
result = await _complete(
|
||||
_transport_for(handler), _source(), stream=False, first_token_event=event
|
||||
)
|
||||
assert result.content == "42"
|
||||
assert not event.is_set()
|
||||
|
||||
async def test_none_first_token_event_keeps_behavior(self):
|
||||
"""`None` = 调用方不观测首 token(未启用对冲): 行为与旧版逐字相同。"""
|
||||
|
||||
def handler(request):
|
||||
return _sse_stream(_chunk(content="ok"), _chunk(usage=_USAGE))
|
||||
|
||||
result = await _complete(_transport_for(handler), _source(), first_token_event=None)
|
||||
assert result.content == "ok"
|
||||
assert result.ttft_ms is not None
|
||||
|
||||
async def test_first_token_event_is_required_keyword(self):
|
||||
"""端口必填约定: 漏传必须 TypeError——默认值会把"漏传"伪装成"不观测"。"""
|
||||
|
||||
def handler(request):
|
||||
return _sse_stream(_chunk(content="ok"), _chunk(usage=_USAGE))
|
||||
|
||||
transport = _transport_for(handler)
|
||||
with pytest.raises(TypeError):
|
||||
await transport.complete(
|
||||
messages=[{"role": "user", "content": "hi"}],
|
||||
source=_source(),
|
||||
stream=True,
|
||||
overlay={},
|
||||
call_id="cid-1",
|
||||
reasoning_effort=None,
|
||||
)
|
||||
|
||||
|
||||
class TestMissingDoneSemantics:
|
||||
def _no_done_handler(self, request):
|
||||
return _sse_stream(_chunk(content="partial"), _chunk(usage=_USAGE), done=False)
|
||||
|
||||
@@ -72,7 +72,9 @@ class _DummyMw:
|
||||
|
||||
|
||||
class _DummyTransport:
|
||||
async def complete(self, *, messages, source, stream, overlay, call_id, reasoning_effort):
|
||||
async def complete(
|
||||
self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
|
||||
):
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
|
||||
@@ -79,7 +79,9 @@ class FakeTransport:
|
||||
# 取消用例的确定性窗口: 进入 hang 分支即置位, 用例据此取消而非 sleep 猜时长
|
||||
self.entered = asyncio.Event()
|
||||
|
||||
async def complete(self, *, messages, source, stream, overlay, call_id, reasoning_effort):
|
||||
async def complete(
|
||||
self, *, messages, source, stream, overlay, call_id, reasoning_effort, first_token_event
|
||||
):
|
||||
self.calls.append((source.name, call_id))
|
||||
self.efforts.append(reasoning_effort)
|
||||
action = self.script.pop(0)
|
||||
|
||||
@@ -139,6 +139,7 @@ async def test_salvage_override_stays_in_domain(usage):
|
||||
overlay={},
|
||||
call_id="cid",
|
||||
reasoning_effort=None,
|
||||
first_token_event=None,
|
||||
)
|
||||
assert result.usage_source in USAGE_SOURCES
|
||||
|
||||
|
||||
Reference in New Issue
Block a user