feat(agent): add streaming groundwork for future TUI
Preserve the provider and agent-loop streaming primitives plus the CLI experiment scaffolding so this work can be resumed later without blocking urgent bug fixes on main. Made-with: Cursor
This commit is contained in:
Xubin Ren
Xubin Ren
+50
-15
@@ -212,8 +212,16 @@ class AgentLoop:
|
||||
self,
|
||||
initial_messages: list[dict],
|
||||
on_progress: Callable[..., Awaitable[None]] | None = None,
|
||||
on_stream: Callable[[str], Awaitable[None]] | None = None,
|
||||
on_stream_end: Callable[..., Awaitable[None]] | None = None,
|
||||
) -> tuple[str | None, list[str], list[dict]]:
|
||||
"""Run the agent iteration loop."""
|
||||
"""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.
|
||||
"""
|
||||
messages = initial_messages
|
||||
iteration = 0
|
||||
final_content = None
|
||||
@@ -224,11 +232,20 @@ class AgentLoop:
|
||||
|
||||
tool_defs = self.tools.get_definitions()
|
||||
|
||||
response = await self.provider.chat_with_retry(
|
||||
messages=messages,
|
||||
tools=tool_defs,
|
||||
model=self.model,
|
||||
)
|
||||
if on_stream:
|
||||
response = await self.provider.chat_stream_with_retry(
|
||||
messages=messages,
|
||||
tools=tool_defs,
|
||||
model=self.model,
|
||||
on_content_delta=on_stream,
|
||||
)
|
||||
else:
|
||||
response = await self.provider.chat_with_retry(
|
||||
messages=messages,
|
||||
tools=tool_defs,
|
||||
model=self.model,
|
||||
)
|
||||
|
||||
usage = response.usage or {}
|
||||
self._last_usage = {
|
||||
"prompt_tokens": int(usage.get("prompt_tokens", 0) or 0),
|
||||
@@ -236,10 +253,14 @@ class AgentLoop:
|
||||
}
|
||||
|
||||
if response.has_tool_calls:
|
||||
if on_stream and on_stream_end:
|
||||
await on_stream_end(resuming=True)
|
||||
|
||||
if on_progress:
|
||||
thought = self._strip_think(response.content)
|
||||
if thought:
|
||||
await on_progress(thought)
|
||||
if not on_stream:
|
||||
thought = self._strip_think(response.content)
|
||||
if thought:
|
||||
await on_progress(thought)
|
||||
tool_hint = self._tool_hint(response.tool_calls)
|
||||
tool_hint = self._strip_think(tool_hint)
|
||||
await on_progress(tool_hint, tool_hint=True)
|
||||
@@ -263,9 +284,10 @@ class AgentLoop:
|
||||
messages, tool_call.id, tool_call.name, result
|
||||
)
|
||||
else:
|
||||
if on_stream and on_stream_end:
|
||||
await on_stream_end(resuming=False)
|
||||
|
||||
clean = self._strip_think(response.content)
|
||||
# Don't persist error responses to session history — they can
|
||||
# poison the context and cause permanent 400 loops (#1303).
|
||||
if response.finish_reason == "error":
|
||||
logger.error("LLM returned error: {}", (clean or "")[:200])
|
||||
final_content = clean or "Sorry, I encountered an error calling the AI model."
|
||||
@@ -400,6 +422,8 @@ class AgentLoop:
|
||||
msg: InboundMessage,
|
||||
session_key: str | None = None,
|
||||
on_progress: Callable[[str], Awaitable[None]] | None = None,
|
||||
on_stream: Callable[[str], Awaitable[None]] | None = None,
|
||||
on_stream_end: Callable[..., Awaitable[None]] | None = None,
|
||||
) -> OutboundMessage | None:
|
||||
"""Process a single inbound message and return the response."""
|
||||
# System messages: parse origin from chat_id ("channel:chat_id")
|
||||
@@ -412,7 +436,6 @@ class AgentLoop:
|
||||
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
|
||||
self._set_tool_context(channel, chat_id, msg.metadata.get("message_id"))
|
||||
history = session.get_history(max_messages=0)
|
||||
# Subagent results should be assistant role, other system messages use user role
|
||||
current_role = "assistant" if msg.sender_id == "subagent" else "user"
|
||||
messages = self.context.build_messages(
|
||||
history=history,
|
||||
@@ -486,7 +509,10 @@ class AgentLoop:
|
||||
))
|
||||
|
||||
final_content, _, all_msgs = await self._run_agent_loop(
|
||||
initial_messages, on_progress=on_progress or _bus_progress,
|
||||
initial_messages,
|
||||
on_progress=on_progress or _bus_progress,
|
||||
on_stream=on_stream,
|
||||
on_stream_end=on_stream_end,
|
||||
)
|
||||
|
||||
if final_content is None:
|
||||
@@ -501,9 +527,13 @@ class AgentLoop:
|
||||
|
||||
preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
|
||||
logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
|
||||
|
||||
meta = dict(msg.metadata or {})
|
||||
if on_stream is not None:
|
||||
meta["_streamed"] = True
|
||||
return OutboundMessage(
|
||||
channel=msg.channel, chat_id=msg.chat_id, content=final_content,
|
||||
metadata=msg.metadata or {},
|
||||
metadata=meta,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
@@ -592,8 +622,13 @@ class AgentLoop:
|
||||
channel: str = "cli",
|
||||
chat_id: str = "direct",
|
||||
on_progress: Callable[[str], Awaitable[None]] | None = None,
|
||||
on_stream: Callable[[str], Awaitable[None]] | None = None,
|
||||
on_stream_end: Callable[..., Awaitable[None]] | None = None,
|
||||
) -> OutboundMessage | None:
|
||||
"""Process a message directly and return the outbound payload."""
|
||||
await self._connect_mcp()
|
||||
msg = InboundMessage(channel=channel, sender_id="user", chat_id=chat_id, content=content)
|
||||
return await self._process_message(msg, session_key=session_key, on_progress=on_progress)
|
||||
return await self._process_message(
|
||||
msg, session_key=session_key, on_progress=on_progress,
|
||||
on_stream=on_stream, on_stream_end=on_stream_end,
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user