sync update from LAN repo (source master-yx @ cf505220)

This commit is contained in:
gozeros committed 2026-10-21 15:11:11 +08:00
1 parent e243ec3a46
commit 19d3cb96dc
114 files changed
+14787 -451

No files matched your search

@@ -96,9 +96,11 @@ _BUSY_PATTERNS = (
"稍后重试",
"请稍后重试",
)
_QUOTA_PATTERNS = (
"insufficient_quota",
"quota",
_QUOTA_PATTERNS = (
"insufficient_quota",
"insufficient balance",
"token plan limit",
"quota",
"billing",
"credit",
"payment",
@@ -122,8 +124,10 @@ _AUTH_PATTERNS = (
# error wrapped as `bad_response_status_code`, or a truncated/garbled inference
# response). These are almost always transient inference-side issues and safe
# to retry.
_UPSTREAM_GARBAGE_PATTERNS = (
"bad_response_status_code",
_UPSTREAM_GARBAGE_PATTERNS = (
"openai-compatible upstream application error",
"null value for 'choices'",
"bad_response_status_code",
"bad response status",
"expecting ',' delimiter",
"expecting value",
@@ -5,8 +5,9 @@ Unlike LangChain's stock ``SummarizationMiddleware`` (which runs in
to the checkpoint — wiping the original Q&A from both the model context *and*
the conversation the frontend renders), this middleware compresses the history
**transiently in ``wrap_model_call``**. The full original messages stay in state
(so the UI keeps showing the user's real conversation); only the message list
handed to the model for a single call is replaced with ``[summary, *recent]``.
(so the UI keeps showing the user's real conversation); only the request handed
to the model is replaced with a merged leading system context plus recent
messages.
The generated summary is cached per-thread so we don't pay an extra LLM call on
every model invocation: once a thread is summarized, the cached summary is reused
@@ -39,6 +40,8 @@ from langchain_core.messages import (
from langgraph.config import get_config
from langgraph.runtime import Runtime
from deerflow.models.message_ordering import normalize_model_request_messages
logger = logging.getLogger(__name__)
# Upper bound on the per-thread summary cache so a long-lived process serving
@@ -321,7 +324,14 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
) -> ModelCallResult:
compressed = self._compressed_messages(request)
if compressed is not None:
request = request.override(messages=compressed)
system_message, messages = normalize_model_request_messages(
request.system_message,
compressed,
)
request = request.override(
system_message=system_message,
messages=messages,
)
return handler(request)
@override
@@ -332,7 +342,14 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
) -> ModelCallResult:
compressed = await self._acompressed_messages(request)
if compressed is not None:
request = request.override(messages=compressed)
system_message, messages = normalize_model_request_messages(
request.system_message,
compressed,
)
request = request.override(
system_message=system_message,
messages=messages,
)
return await handler(request)
def _compressed_messages(self, request: ModelRequest) -> list[AnyMessage] | None: