fix(webui): merge length recovery stream segments
This commit is contained in:
@@ -534,6 +534,52 @@ class TestToolEventProgress:
|
||||
assert turn_end_msgs[0].content == ""
|
||||
provider.chat_with_retry.assert_not_awaited()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_length_recovery_keeps_one_user_visible_stream(
|
||||
self,
|
||||
tmp_path: Path,
|
||||
) -> None:
|
||||
bus = MessageBus()
|
||||
provider = MagicMock()
|
||||
provider.supports_progress_deltas = True
|
||||
provider.get_default_model.return_value = "test-model"
|
||||
responses = iter([
|
||||
LLMResponse(content="first-", finish_reason="length"),
|
||||
LLMResponse(content="second", finish_reason="stop"),
|
||||
])
|
||||
|
||||
async def chat_stream_with_retry(*, on_content_delta, **kwargs):
|
||||
response = next(responses)
|
||||
await on_content_delta(response.content or "")
|
||||
return response
|
||||
|
||||
provider.chat_stream_with_retry = chat_stream_with_retry
|
||||
provider.chat_with_retry = AsyncMock()
|
||||
loop = AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
|
||||
_attach_webui_runtime_events(loop, bus)
|
||||
loop.tools.get_definitions = MagicMock(return_value=[])
|
||||
loop.consolidator.maybe_consolidate_by_tokens = AsyncMock(return_value=False) # type: ignore[method-assign]
|
||||
|
||||
await loop._dispatch(InboundMessage(
|
||||
channel="websocket",
|
||||
sender_id="u1",
|
||||
chat_id="chat1",
|
||||
content="give a long answer",
|
||||
metadata={"_wants_stream": True},
|
||||
))
|
||||
|
||||
outbound = []
|
||||
while bus.outbound_size > 0:
|
||||
outbound.append(await bus.consume_outbound())
|
||||
|
||||
deltas = [m.event for m in outbound if isinstance(m.event, StreamDeltaEvent)]
|
||||
endings = [m.event for m in outbound if isinstance(m.event, StreamEndEvent)]
|
||||
|
||||
assert [event.content for event in deltas] == ["first-", "second"]
|
||||
assert [event.resuming for event in endings] == [True, False]
|
||||
assert [event.merge_next for event in endings] == [True, False]
|
||||
assert {event.stream_id for event in [*deltas, *endings]} == {deltas[0].stream_id}
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_non_streamed_finalization_is_delivered_as_regular_message(
|
||||
self,
|
||||
|
||||
@@ -151,6 +151,7 @@ async def test_runner_length_recovery_streams_segments_once_and_returns_all_cont
|
||||
provider = MagicMock(spec=LLMProvider)
|
||||
streamed: list[str] = []
|
||||
endings: list[bool] = []
|
||||
merge_next: list[bool] = []
|
||||
responses = iter([
|
||||
LLMResponse(content="first ", finish_reason="length"),
|
||||
LLMResponse(content="second", finish_reason="stop"),
|
||||
@@ -175,6 +176,7 @@ async def test_runner_length_recovery_streams_segments_once_and_returns_all_cont
|
||||
|
||||
async def on_stream_end(self, context: AgentHookContext, *, resuming: bool) -> None:
|
||||
endings.append(resuming)
|
||||
merge_next.append(context.stream_continues_current_message)
|
||||
|
||||
runner = AgentRunner()
|
||||
result = await runner.run(make_run_spec(provider,
|
||||
@@ -189,6 +191,7 @@ async def test_runner_length_recovery_streams_segments_once_and_returns_all_cont
|
||||
assert result.final_content == "first second"
|
||||
assert streamed == ["first ", "second"]
|
||||
assert endings == [True, False]
|
||||
assert merge_next == [True, False]
|
||||
provider.chat_with_retry.assert_not_awaited()
|
||||
|
||||
|
||||
|
||||
@@ -94,7 +94,12 @@ def test_legacy_stream_metadata_flags_create_runtime_events() -> None:
|
||||
channel="websocket",
|
||||
chat_id="chat-1",
|
||||
content="",
|
||||
metadata={"_stream_end": True, "_stream_id": "s1", "_resuming": True},
|
||||
metadata={
|
||||
"_stream_end": True,
|
||||
"_stream_id": "s1",
|
||||
"_resuming": True,
|
||||
"_merge_next": True,
|
||||
},
|
||||
)
|
||||
|
||||
delta_event = outbound_event_from_message(delta)
|
||||
@@ -106,6 +111,7 @@ def test_legacy_stream_metadata_flags_create_runtime_events() -> None:
|
||||
assert isinstance(end_event, StreamEndEvent)
|
||||
assert end_event.stream_id == "s1"
|
||||
assert end_event.resuming is True
|
||||
assert end_event.merge_next is True
|
||||
|
||||
|
||||
def test_legacy_webui_runtime_metadata_flags_create_runtime_events() -> None:
|
||||
@@ -221,7 +227,7 @@ def test_replace_outbound_event_keeps_routing_metadata() -> None:
|
||||
|
||||
updated = replace_outbound_event(
|
||||
msg,
|
||||
StreamEndEvent(stream_id="s1", resuming=True),
|
||||
StreamEndEvent(stream_id="s1", resuming=True, merge_next=True),
|
||||
content="hello world",
|
||||
)
|
||||
|
||||
@@ -230,6 +236,7 @@ def test_replace_outbound_event_keeps_routing_metadata() -> None:
|
||||
assert isinstance(updated.event, StreamEndEvent)
|
||||
assert updated.event.stream_id == "s1"
|
||||
assert updated.event.resuming is True
|
||||
assert updated.event.merge_next is True
|
||||
|
||||
|
||||
def test_streamed_response_event_keeps_final_content_outside_event_payload() -> None:
|
||||
|
||||
@@ -49,6 +49,7 @@ class MockChannel(BaseChannel):
|
||||
stream_id=None,
|
||||
stream_end=False,
|
||||
resuming=False,
|
||||
merge_next=False,
|
||||
):
|
||||
return await self._send_delta_mock(
|
||||
chat_id,
|
||||
@@ -57,6 +58,7 @@ class MockChannel(BaseChannel):
|
||||
stream_id=stream_id,
|
||||
stream_end=stream_end,
|
||||
resuming=resuming,
|
||||
merge_next=merge_next,
|
||||
)
|
||||
|
||||
|
||||
@@ -92,11 +94,17 @@ def _end(
|
||||
chat_id: str = "chat1",
|
||||
stream_id: str | None = None,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
):
|
||||
return outbound_message_for_event(
|
||||
channel="mock",
|
||||
chat_id=chat_id,
|
||||
event=StreamEndEvent(content=content, stream_id=stream_id, resuming=resuming),
|
||||
event=StreamEndEvent(
|
||||
content=content,
|
||||
stream_id=stream_id,
|
||||
resuming=resuming,
|
||||
merge_next=merge_next,
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
@@ -137,6 +145,7 @@ class TestDeltaCoalescing:
|
||||
stream_id=None,
|
||||
stream_end=False,
|
||||
resuming=False,
|
||||
merge_next=False,
|
||||
)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@@ -184,13 +193,19 @@ class TestDeltaCoalescing:
|
||||
@pytest.mark.asyncio
|
||||
async def test_stream_end_terminates_coalescing(self, manager, bus):
|
||||
await bus.publish_outbound(_delta("Hello"))
|
||||
await bus.publish_outbound(_end(" world"))
|
||||
await bus.publish_outbound(_end(
|
||||
" world",
|
||||
resuming=True,
|
||||
merge_next=True,
|
||||
))
|
||||
|
||||
first_msg = await bus.consume_outbound()
|
||||
merged, pending = manager._coalesce_stream_deltas(first_msg)
|
||||
|
||||
assert merged.content == "Hello world"
|
||||
assert isinstance(merged.event, StreamEndEvent)
|
||||
assert merged.event.resuming is True
|
||||
assert merged.event.merge_next is True
|
||||
assert len(pending) == 0
|
||||
|
||||
@pytest.mark.asyncio
|
||||
|
||||
@@ -2818,7 +2818,7 @@ async def test_send_with_retry_no_retry_when_max_is_zero():
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_with_retry_calls_send_delta():
|
||||
"""_send_with_retry should call send_delta for stream delta events."""
|
||||
calls: list[tuple[str, str, str | None, bool, bool]] = []
|
||||
calls: list[tuple[str, str, str | None, bool, bool, bool]] = []
|
||||
|
||||
class _StreamingChannel(BaseChannel):
|
||||
name = "streaming"
|
||||
@@ -2842,8 +2842,9 @@ async def test_send_with_retry_calls_send_delta():
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
calls.append((chat_id, delta, stream_id, stream_end, resuming))
|
||||
calls.append((chat_id, delta, stream_id, stream_end, resuming, merge_next))
|
||||
|
||||
fake_config = SimpleNamespace(
|
||||
channels=ChannelsConfig(send_max_retries=3),
|
||||
@@ -2865,13 +2866,18 @@ async def test_send_with_retry_calls_send_delta():
|
||||
end = outbound_message_for_event(
|
||||
channel="streaming",
|
||||
chat_id="123",
|
||||
event=StreamEndEvent(content="", stream_id="s1", resuming=True),
|
||||
event=StreamEndEvent(
|
||||
content="",
|
||||
stream_id="s1",
|
||||
resuming=True,
|
||||
merge_next=True,
|
||||
),
|
||||
)
|
||||
await mgr._send_with_retry(mgr.channels["streaming"], end)
|
||||
|
||||
assert calls == [
|
||||
("123", "test delta", "s1", False, False),
|
||||
("123", "", "s1", True, True),
|
||||
("123", "test delta", "s1", False, False, False),
|
||||
("123", "", "s1", True, True, True),
|
||||
]
|
||||
|
||||
|
||||
|
||||
@@ -1121,6 +1121,26 @@ def test_replay_keeps_interrupted_pre_tool_text_in_activity() -> None:
|
||||
assert msgs[2]["content"] == "Done. Open index.html to play."
|
||||
|
||||
|
||||
def test_replay_merges_length_recovery_segments_into_one_assistant_message() -> None:
|
||||
msgs = replay_transcript_to_ui_messages([
|
||||
{"event": "delta", "chat_id": "t-stream", "text": "first "},
|
||||
{
|
||||
"event": "stream_end",
|
||||
"chat_id": "t-stream",
|
||||
"text": "first ",
|
||||
"resuming": True,
|
||||
"merge_next": True,
|
||||
},
|
||||
{"event": "delta", "chat_id": "t-stream", "text": "second"},
|
||||
{"event": "stream_end", "chat_id": "t-stream"},
|
||||
{"event": "turn_end", "chat_id": "t-stream"},
|
||||
])
|
||||
|
||||
assert len(msgs) == 1
|
||||
assert msgs[0]["role"] == "assistant"
|
||||
assert msgs[0]["content"] == "first second"
|
||||
|
||||
|
||||
def test_replay_tool_events_dedupes_finish_after_start() -> None:
|
||||
msgs = replay_transcript_to_ui_messages([
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user