fix(webui): merge length recovery stream segments
This commit is contained in:
@@ -25,6 +25,7 @@ class AgentHookContext:
|
||||
tool_events: list[dict[str, str]] = field(default_factory=list)
|
||||
streamed_content: bool = False
|
||||
streamed_reasoning: bool = False
|
||||
stream_continues_current_message: bool = False
|
||||
final_content: str | None = None
|
||||
stop_reason: str | None = None
|
||||
error: str | None = None
|
||||
|
||||
+26
-5
@@ -4,6 +4,7 @@ from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import dataclasses
|
||||
import inspect
|
||||
import os
|
||||
import time
|
||||
from collections.abc import Mapping
|
||||
@@ -860,9 +861,9 @@ class AgentLoop:
|
||||
"""Run the agent iteration loop.
|
||||
|
||||
*on_stream*: called with each content delta during streaming.
|
||||
*on_stream_end(resuming)*: called when a streaming session finishes.
|
||||
``resuming=True`` means tool calls follow (spinner should restart);
|
||||
``resuming=False`` means this is the final response.
|
||||
*on_stream_end(resuming, merge_next)*: called when a streaming session finishes.
|
||||
``resuming=True`` means the active turn continues. ``merge_next=True`` means
|
||||
the next text segment belongs to the same user-visible assistant message.
|
||||
|
||||
Returns (final_content, tools_used, messages, stop_reason, had_injections).
|
||||
"""
|
||||
@@ -1385,6 +1386,19 @@ class AgentLoop:
|
||||
if ctx.on_stream is not None:
|
||||
stream_callback = ctx.on_stream
|
||||
stream_end_callback = ctx.on_stream_end
|
||||
stream_end_accepts_merge_next = False
|
||||
if stream_end_callback is not None:
|
||||
try:
|
||||
stream_end_signature = inspect.signature(stream_end_callback)
|
||||
stream_end_accepts_merge_next = (
|
||||
"merge_next" in stream_end_signature.parameters
|
||||
or any(
|
||||
parameter.kind is inspect.Parameter.VAR_KEYWORD
|
||||
for parameter in stream_end_signature.parameters.values()
|
||||
)
|
||||
)
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
segment_streamed_content = False
|
||||
|
||||
async def _tracked_stream(delta: str) -> None:
|
||||
@@ -1393,12 +1407,19 @@ class AgentLoop:
|
||||
segment_streamed_content = True
|
||||
await stream_callback(delta)
|
||||
|
||||
async def _tracked_stream_end(*, resuming: bool = False) -> None:
|
||||
async def _tracked_stream_end(
|
||||
*,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
nonlocal segment_streamed_content
|
||||
ctx.streamed_content = segment_streamed_content
|
||||
segment_streamed_content = False
|
||||
if stream_end_callback is not None:
|
||||
await stream_end_callback(resuming=resuming)
|
||||
if merge_next and stream_end_accepts_merge_next:
|
||||
await stream_end_callback(resuming=resuming, merge_next=True)
|
||||
else:
|
||||
await stream_end_callback(resuming=resuming)
|
||||
|
||||
ctx.on_stream = _tracked_stream
|
||||
ctx.on_stream_end = _tracked_stream_end
|
||||
|
||||
@@ -85,7 +85,13 @@ class AgentProgressHook(AgentHook):
|
||||
async def on_stream_end(self, context: AgentHookContext, *, resuming: bool) -> None:
|
||||
await self.emit_reasoning_end()
|
||||
if self._on_stream_end:
|
||||
await self._on_stream_end(resuming=resuming)
|
||||
kwargs: dict[str, bool] = {"resuming": resuming}
|
||||
if (
|
||||
context.stream_continues_current_message
|
||||
and self._on_progress_accepts(self._on_stream_end, "merge_next")
|
||||
):
|
||||
kwargs["merge_next"] = True
|
||||
await self._on_stream_end(**kwargs)
|
||||
self._stream_buf = ""
|
||||
self._think_extractor.reset()
|
||||
|
||||
|
||||
@@ -599,6 +599,7 @@ class AgentRunner:
|
||||
_MAX_LENGTH_RECOVERIES,
|
||||
)
|
||||
if hook.wants_streaming():
|
||||
context.stream_continues_current_message = True
|
||||
await hook.on_stream_end(context, resuming=True)
|
||||
messages.append(build_assistant_message(
|
||||
clean,
|
||||
|
||||
@@ -285,7 +285,12 @@ class TurnDelivery:
|
||||
)
|
||||
)
|
||||
|
||||
async def _publish_stream_end(self, *, resuming: bool = False) -> None:
|
||||
async def _publish_stream_end(
|
||||
self,
|
||||
*,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
await self.bus.publish_outbound(
|
||||
outbound_message_for_event(
|
||||
channel=self.delivery_message.channel,
|
||||
@@ -293,8 +298,10 @@ class TurnDelivery:
|
||||
event=StreamEndEvent(
|
||||
stream_id=self._stream_id(),
|
||||
resuming=resuming,
|
||||
merge_next=merge_next,
|
||||
),
|
||||
metadata=self.delivery_message.metadata,
|
||||
)
|
||||
)
|
||||
self._stream_segment += 1
|
||||
if not merge_next:
|
||||
self._stream_segment += 1
|
||||
|
||||
@@ -46,6 +46,7 @@ class StreamEndEvent(OutboundEvent):
|
||||
content: str = ""
|
||||
stream_id: str | None = None
|
||||
resuming: bool = False
|
||||
merge_next: bool = False
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -176,6 +177,7 @@ def _legacy_event_from_metadata(msg: OutboundMessage) -> OutboundEvent | None:
|
||||
content=msg.content,
|
||||
stream_id=_metadata_str(meta, "_stream_id"),
|
||||
resuming=bool(meta.get("_resuming")),
|
||||
merge_next=bool(meta.get("_merge_next")),
|
||||
)
|
||||
if meta.get("_stream_delta"):
|
||||
return StreamDeltaEvent(
|
||||
|
||||
@@ -110,6 +110,7 @@ class BaseChannel(ABC):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
"""Deliver a streaming text chunk.
|
||||
|
||||
@@ -118,6 +119,9 @@ class BaseChannel(ABC):
|
||||
|
||||
Stateful implementations should key buffers by ``stream_id`` rather
|
||||
than only by ``chat_id`` when it is provided.
|
||||
|
||||
``merge_next`` marks a resumable provider boundary whose next text
|
||||
segment belongs to the same user-visible message.
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
@@ -489,6 +489,7 @@ class DiscordChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
"""Progressive Discord delivery: send once, then edit until the stream ends."""
|
||||
client = self._client
|
||||
|
||||
@@ -2216,6 +2216,7 @@ class FeishuChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
"""Progressive streaming via CardKit: create card on first delta, stream-update on subsequent.
|
||||
|
||||
|
||||
@@ -4,6 +4,7 @@ from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import inspect
|
||||
from collections.abc import Callable, Iterable
|
||||
from contextlib import suppress
|
||||
from pathlib import Path
|
||||
@@ -763,13 +764,29 @@ class ChannelManager:
|
||||
msg: OutboundMessage,
|
||||
event: StreamDeltaEvent | StreamEndEvent,
|
||||
) -> None:
|
||||
kwargs: dict[str, Any] = {
|
||||
"stream_id": event.stream_id,
|
||||
"stream_end": isinstance(event, StreamEndEvent),
|
||||
"resuming": event.resuming if isinstance(event, StreamEndEvent) else False,
|
||||
}
|
||||
if isinstance(event, StreamEndEvent) and event.merge_next:
|
||||
try:
|
||||
signature = inspect.signature(channel.send_delta)
|
||||
if (
|
||||
"merge_next" in signature.parameters
|
||||
or any(
|
||||
parameter.kind is inspect.Parameter.VAR_KEYWORD
|
||||
for parameter in signature.parameters.values()
|
||||
)
|
||||
):
|
||||
kwargs["merge_next"] = True
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
await channel.send_delta(
|
||||
msg.chat_id,
|
||||
msg.content,
|
||||
msg.metadata,
|
||||
stream_id=event.stream_id,
|
||||
stream_end=isinstance(event, StreamEndEvent),
|
||||
resuming=event.resuming if isinstance(event, StreamEndEvent) else False,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
@@ -850,6 +867,7 @@ class ChannelManager:
|
||||
final_event = StreamEndEvent(
|
||||
stream_id=next_stream_id,
|
||||
resuming=next_event.resuming,
|
||||
merge_next=next_event.merge_next,
|
||||
)
|
||||
# Stream ended - stop coalescing this stream
|
||||
break
|
||||
|
||||
@@ -598,6 +598,7 @@ class MatrixChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
relates_to = self._build_thread_relates_to(metadata)
|
||||
|
||||
|
||||
@@ -515,6 +515,7 @@ class MattermostChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
if not self._http_client:
|
||||
return
|
||||
|
||||
@@ -923,6 +923,7 @@ class TelegramChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
"""Progressive message editing: send on first delta, edit on subsequent ones."""
|
||||
if not self._app:
|
||||
|
||||
@@ -995,13 +995,18 @@ class WebSocketChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
conns = list(self._subs.get(chat_id, ()))
|
||||
meta = metadata or {}
|
||||
stream_key = (chat_id, str(stream_id or ""))
|
||||
if stream_end:
|
||||
body: dict[str, Any] = {"event": "stream_end", "chat_id": chat_id}
|
||||
buffered = self._stream_text_buffers.pop(stream_key, [])
|
||||
buffered = (
|
||||
self._stream_text_buffers.setdefault(stream_key, [])
|
||||
if merge_next
|
||||
else self._stream_text_buffers.pop(stream_key, [])
|
||||
)
|
||||
if delta:
|
||||
buffered.append(delta)
|
||||
full_text = "".join(buffered)
|
||||
@@ -1019,6 +1024,8 @@ class WebSocketChannel(BaseChannel):
|
||||
body["stream_id"] = stream_id
|
||||
if stream_end and resuming:
|
||||
body["resuming"] = True
|
||||
if stream_end and merge_next:
|
||||
body["merge_next"] = True
|
||||
self._transcripts.prepare_and_append(
|
||||
chat_id,
|
||||
body,
|
||||
|
||||
@@ -1350,6 +1350,39 @@ async def test_send_delta_marks_resuming_stream_end() -> None:
|
||||
assert payload["resuming"] is True
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_delta_keeps_buffer_across_merged_stream_boundary() -> None:
|
||||
bus = MagicMock()
|
||||
channel = WebSocketChannel(
|
||||
{"enabled": True, "allowFrom": ["*"], "streaming": True},
|
||||
bus,
|
||||
gateway=_basic_handler(bus),
|
||||
)
|
||||
mock_ws = AsyncMock()
|
||||
channel._attach(mock_ws, "chat-1")
|
||||
|
||||
await channel.send_delta("chat-1", "first ", stream_id="sid")
|
||||
await channel.send_delta(
|
||||
"chat-1",
|
||||
"",
|
||||
stream_id="sid",
|
||||
stream_end=True,
|
||||
resuming=True,
|
||||
merge_next=True,
|
||||
)
|
||||
await channel.send_delta("chat-1", "second", stream_id="sid")
|
||||
await channel.send_delta("chat-1", "", stream_id="sid", stream_end=True)
|
||||
|
||||
payloads = [json.loads(call.args[0]) for call in mock_ws.send.await_args_list]
|
||||
assert payloads[1]["merge_next"] is True
|
||||
assert payloads[1]["resuming"] is True
|
||||
assert [payload["text"] for payload in payloads if payload["event"] == "delta"] == [
|
||||
"first ",
|
||||
"second",
|
||||
]
|
||||
assert ("chat-1", "sid") not in channel._stream_text_buffers
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_send_delta_stream_end_includes_inline_final_text() -> None:
|
||||
bus = MagicMock()
|
||||
|
||||
@@ -1243,6 +1243,7 @@ class WeixinChannel(BaseChannel):
|
||||
stream_id: str | None = None,
|
||||
stream_end: bool = False,
|
||||
resuming: bool = False,
|
||||
merge_next: bool = False,
|
||||
) -> None:
|
||||
"""Deliver a streamed reply to WeChat.
|
||||
|
||||
|
||||
@@ -1770,6 +1770,7 @@ def replay_transcript_to_ui_messages(
|
||||
buffer_message_id = None
|
||||
buffer_parts = []
|
||||
continue
|
||||
merge_next = rec.get("resuming") is True and rec.get("merge_next") is True
|
||||
final_text = rec.get("text")
|
||||
if isinstance(final_text, str):
|
||||
if buffer_message_id is None:
|
||||
@@ -1794,8 +1795,11 @@ def replay_transcript_to_ui_messages(
|
||||
**_turn_fields(rec, "answer"),
|
||||
}
|
||||
break
|
||||
buffer_message_id = None
|
||||
buffer_parts = []
|
||||
if merge_next:
|
||||
buffer_parts = [final_text]
|
||||
if not merge_next:
|
||||
buffer_message_id = None
|
||||
buffer_parts = []
|
||||
continue
|
||||
|
||||
if ev == "reasoning_delta":
|
||||
|
||||
Reference in New Issue
Block a user