增强 Deep Research 可靠性,并接入 8BF 任务卡片与会商上下文。
修复 MySQL 读写分离下的持久化与 SSE 重连问题,报告完成前先落库;8BF 嵌入页支持 taskId 任务卡与独立意图 metadata;前端统一 createClientId 并更新 runtime 配置。 Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
1 parent
47faa9bcdf
commit
771957429a
36 files changed
+2038
-300
No files matched your search
+162
-112
@@ -27,14 +27,15 @@ from typing import Any, Protocol, override, runtime_checkable
|
||||
from langchain.agents import AgentState
|
||||
from langchain.agents.middleware import SummarizationMiddleware
|
||||
from langchain.agents.middleware.types import ModelCallResult, ModelRequest, ModelResponse
|
||||
from langchain_core.messages import (
|
||||
AIMessage,
|
||||
AnyMessage,
|
||||
SystemMessage,
|
||||
ToolMessage,
|
||||
message_to_dict,
|
||||
messages_from_dict,
|
||||
)
|
||||
from langchain_core.messages import (
|
||||
AIMessage,
|
||||
AnyMessage,
|
||||
HumanMessage,
|
||||
SystemMessage,
|
||||
ToolMessage,
|
||||
message_to_dict,
|
||||
messages_from_dict,
|
||||
)
|
||||
from langgraph.config import get_config
|
||||
from langgraph.runtime import Runtime
|
||||
|
||||
@@ -145,8 +146,8 @@ class _SummaryCacheEntry:
|
||||
|
||||
summarized_ids: frozenset[str]
|
||||
summary_text: str
|
||||
preserved_ids: frozenset[str] = frozenset()
|
||||
preserved_messages: tuple[AnyMessage, ...] = ()
|
||||
preserved_ids: frozenset[str] = frozenset()
|
||||
preserved_messages: tuple[AnyMessage, ...] = ()
|
||||
|
||||
|
||||
# Process-wide summary cache shared across every middleware instance.
|
||||
@@ -160,51 +161,99 @@ class _SummaryCacheEntry:
|
||||
# so only the first threshold crossing (or a genuine re-compaction) pays for an
|
||||
# LLM call. A lock guards the non-atomic LRU eviction against concurrent
|
||||
# threads (subagents / parallel conversations share this process).
|
||||
_GLOBAL_SUMMARY_CACHE: OrderedDict[str, _SummaryCacheEntry] = OrderedDict()
|
||||
_GLOBAL_SUMMARY_CACHE_LOCK = threading.Lock()
|
||||
_STATE_CACHE_KEY = "context_summary_cache"
|
||||
|
||||
|
||||
def _clear_global_summary_cache() -> None:
|
||||
"""Drop every cached summary. Intended for tests/diagnostics only."""
|
||||
with _GLOBAL_SUMMARY_CACHE_LOCK:
|
||||
_GLOBAL_SUMMARY_CACHE.clear()
|
||||
|
||||
|
||||
def _serialize_cache_entry(entry: _SummaryCacheEntry) -> dict[str, Any]:
|
||||
"""Serialize a summary cache entry so it can live in LangGraph state."""
|
||||
return {
|
||||
"version": 1,
|
||||
"summarized_ids": sorted(entry.summarized_ids),
|
||||
"summary_text": entry.summary_text,
|
||||
"preserved_ids": sorted(entry.preserved_ids),
|
||||
"preserved_messages": [message_to_dict(message) for message in entry.preserved_messages],
|
||||
}
|
||||
|
||||
|
||||
def _deserialize_cache_entry(raw: Any) -> _SummaryCacheEntry | None:
|
||||
"""Best-effort restore of a state-backed summary cache entry."""
|
||||
if not isinstance(raw, dict):
|
||||
return None
|
||||
try:
|
||||
summary_text = raw.get("summary_text")
|
||||
if not isinstance(summary_text, str) or not summary_text:
|
||||
return None
|
||||
summarized_ids = raw.get("summarized_ids") or []
|
||||
preserved_ids = raw.get("preserved_ids") or []
|
||||
preserved_messages_raw = raw.get("preserved_messages") or []
|
||||
if not isinstance(summarized_ids, list) or not isinstance(preserved_ids, list) or not isinstance(preserved_messages_raw, list):
|
||||
return None
|
||||
preserved_messages = tuple(messages_from_dict(preserved_messages_raw))
|
||||
return _SummaryCacheEntry(
|
||||
summarized_ids=frozenset(str(item) for item in summarized_ids if item is not None),
|
||||
summary_text=summary_text,
|
||||
preserved_ids=frozenset(str(item) for item in preserved_ids if item is not None),
|
||||
preserved_messages=preserved_messages,
|
||||
)
|
||||
except Exception:
|
||||
logger.debug("summarization: failed to restore state-backed summary cache", exc_info=True)
|
||||
return None
|
||||
_GLOBAL_SUMMARY_CACHE: OrderedDict[str, _SummaryCacheEntry] = OrderedDict()
|
||||
_GLOBAL_SUMMARY_CACHE_LOCK = threading.Lock()
|
||||
_STATE_CACHE_KEY = "context_summary_cache"
|
||||
|
||||
|
||||
def _clear_global_summary_cache() -> None:
|
||||
"""Drop every cached summary. Intended for tests/diagnostics only."""
|
||||
with _GLOBAL_SUMMARY_CACHE_LOCK:
|
||||
_GLOBAL_SUMMARY_CACHE.clear()
|
||||
|
||||
|
||||
def _serialize_cache_entry(entry: _SummaryCacheEntry) -> dict[str, Any]:
|
||||
"""Serialize a summary cache entry so it can live in LangGraph state."""
|
||||
return {
|
||||
"version": 1,
|
||||
"summarized_ids": sorted(entry.summarized_ids),
|
||||
"summary_text": entry.summary_text,
|
||||
"preserved_ids": sorted(entry.preserved_ids),
|
||||
"preserved_messages": [message_to_dict(message) for message in entry.preserved_messages],
|
||||
}
|
||||
|
||||
|
||||
def _deserialize_cache_entry(raw: Any) -> _SummaryCacheEntry | None:
|
||||
"""Best-effort restore of a state-backed summary cache entry."""
|
||||
if not isinstance(raw, dict):
|
||||
return None
|
||||
try:
|
||||
summary_text = raw.get("summary_text")
|
||||
if not isinstance(summary_text, str) or not summary_text:
|
||||
return None
|
||||
summarized_ids = raw.get("summarized_ids") or []
|
||||
preserved_ids = raw.get("preserved_ids") or []
|
||||
preserved_messages_raw = raw.get("preserved_messages") or []
|
||||
if not isinstance(summarized_ids, list) or not isinstance(preserved_ids, list) or not isinstance(preserved_messages_raw, list):
|
||||
return None
|
||||
preserved_messages = tuple(messages_from_dict(preserved_messages_raw))
|
||||
return _SummaryCacheEntry(
|
||||
summarized_ids=frozenset(str(item) for item in summarized_ids if item is not None),
|
||||
summary_text=summary_text,
|
||||
preserved_ids=frozenset(str(item) for item in preserved_ids if item is not None),
|
||||
preserved_messages=preserved_messages,
|
||||
)
|
||||
except Exception:
|
||||
logger.debug("summarization: failed to restore state-backed summary cache", exc_info=True)
|
||||
return None
|
||||
|
||||
|
||||
def _has_nonempty_human_message(message: AnyMessage) -> bool:
|
||||
"""Whether a message is a real, non-empty user turn.
|
||||
|
||||
Some OpenAI-compatible gateways reject a completion request that contains
|
||||
only ``system`` / ``assistant`` / ``tool`` roles. That can legitimately
|
||||
happen after compaction: the active model call is continuing a tool turn,
|
||||
while the user request that started the turn has already moved into the
|
||||
internal summary.
|
||||
"""
|
||||
if not isinstance(message, HumanMessage):
|
||||
return False
|
||||
content = message.content
|
||||
if isinstance(content, str):
|
||||
return bool(content.strip())
|
||||
if isinstance(content, list):
|
||||
return any(bool(block.strip()) if isinstance(block, str) else bool((block.get("text") or block.get("content") or "").strip()) if isinstance(block, dict) else False for block in content)
|
||||
return bool(str(content).strip())
|
||||
|
||||
|
||||
def _ensure_latest_human_message(
|
||||
source_messages: list[AnyMessage],
|
||||
compressed_messages: list[AnyMessage],
|
||||
) -> list[AnyMessage]:
|
||||
"""Keep the latest real user request visible to strict chat gateways.
|
||||
|
||||
The message is inserted after leading system messages, so it neither
|
||||
exposes the internal summary to the UI nor splits an AI tool-call from its
|
||||
following ToolMessages. When there was no user turn in the source at all,
|
||||
do not fabricate one: that is an upstream caller bug and should remain
|
||||
diagnosable rather than silently changing the task.
|
||||
"""
|
||||
if any(_has_nonempty_human_message(message) for message in compressed_messages):
|
||||
return compressed_messages
|
||||
|
||||
latest_human = next(
|
||||
(message for message in reversed(source_messages) if _has_nonempty_human_message(message)),
|
||||
None,
|
||||
)
|
||||
if latest_human is None:
|
||||
logger.warning("summarization: compressed model request has no user message and source history contains none; passing it through unchanged")
|
||||
return compressed_messages
|
||||
|
||||
insert_at = 0
|
||||
while insert_at < len(compressed_messages) and isinstance(compressed_messages[insert_at], SystemMessage):
|
||||
insert_at += 1
|
||||
return [*compressed_messages[:insert_at], latest_human, *compressed_messages[insert_at:]]
|
||||
|
||||
|
||||
class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
@@ -231,8 +280,8 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
# Per-thread cache of the most recent summary: thread_id -> (summarized message ids, summary text).
|
||||
# Points at the *process-wide* cache (not a fresh per-instance dict) so a
|
||||
# summary survives across runs/turns — see ``_GLOBAL_SUMMARY_CACHE``.
|
||||
self._summary_cache: OrderedDict[str, _SummaryCacheEntry] = _GLOBAL_SUMMARY_CACHE
|
||||
self._pending_state_cache_update: dict[str, Any] | None = None
|
||||
self._summary_cache: OrderedDict[str, _SummaryCacheEntry] = _GLOBAL_SUMMARY_CACHE
|
||||
self._pending_state_cache_update: dict[str, Any] | None = None
|
||||
|
||||
@override
|
||||
def before_model(self, state: AgentState, runtime: Runtime) -> dict | None:
|
||||
@@ -248,21 +297,21 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
"""Async counterpart of :meth:`before_model` — also a no-op."""
|
||||
return None
|
||||
|
||||
@override
|
||||
def after_model(self, state: AgentState, runtime: Runtime) -> dict | None:
|
||||
"""Persist the latest reusable summary cache into thread state."""
|
||||
if self._pending_state_cache_update is None:
|
||||
return None
|
||||
update = self._pending_state_cache_update
|
||||
self._pending_state_cache_update = None
|
||||
return {_STATE_CACHE_KEY: update}
|
||||
|
||||
@override
|
||||
async def aafter_model(self, state: AgentState, runtime: Runtime) -> dict | None:
|
||||
"""Async counterpart of :meth:`after_model`."""
|
||||
return self.after_model(state, runtime)
|
||||
|
||||
# ---- wrap_model_call: transient, display-preserving compression ----------
|
||||
@override
|
||||
def after_model(self, state: AgentState, runtime: Runtime) -> dict | None:
|
||||
"""Persist the latest reusable summary cache into thread state."""
|
||||
if self._pending_state_cache_update is None:
|
||||
return None
|
||||
update = self._pending_state_cache_update
|
||||
self._pending_state_cache_update = None
|
||||
return {_STATE_CACHE_KEY: update}
|
||||
|
||||
@override
|
||||
async def aafter_model(self, state: AgentState, runtime: Runtime) -> dict | None:
|
||||
"""Async counterpart of :meth:`after_model`."""
|
||||
return self.after_model(state, runtime)
|
||||
|
||||
# ---- wrap_model_call: transient, display-preserving compression ----------
|
||||
|
||||
@override
|
||||
def wrap_model_call(
|
||||
@@ -376,20 +425,21 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
return None
|
||||
|
||||
thread_id = self._resolve_request_thread_id(request)
|
||||
if thread_id is None:
|
||||
logger.debug("summarization: thread_id unresolved; cross-turn summary cache disabled for this call")
|
||||
cached = self._get_cache_entry(thread_id) if thread_id else None
|
||||
if cached is None:
|
||||
cached = _deserialize_cache_entry(getattr(request, "state", {}).get(_STATE_CACHE_KEY))
|
||||
if cached is not None and thread_id:
|
||||
self._store_cache_entry(thread_id, cached)
|
||||
present_ids = {m.id for m in messages}
|
||||
cache_usable = cached is not None and cached.summarized_ids <= present_ids and cached.preserved_ids <= present_ids
|
||||
if cache_usable:
|
||||
preserved = list(cached.preserved_messages)
|
||||
excluded_ids = cached.summarized_ids | cached.preserved_ids
|
||||
preserved.extend(m for m in messages if m.id not in excluded_ids)
|
||||
effective = [self._summary_message(cached.summary_text), *preserved]
|
||||
if thread_id is None:
|
||||
logger.debug("summarization: thread_id unresolved; cross-turn summary cache disabled for this call")
|
||||
cached = self._get_cache_entry(thread_id) if thread_id else None
|
||||
if cached is None:
|
||||
cached = _deserialize_cache_entry(getattr(request, "state", {}).get(_STATE_CACHE_KEY))
|
||||
if cached is not None and thread_id:
|
||||
self._store_cache_entry(thread_id, cached)
|
||||
present_ids = {m.id for m in messages}
|
||||
cache_usable = cached is not None and cached.summarized_ids <= present_ids and cached.preserved_ids <= present_ids
|
||||
if cache_usable:
|
||||
preserved = list(cached.preserved_messages)
|
||||
excluded_ids = cached.summarized_ids | cached.preserved_ids
|
||||
preserved.extend(m for m in messages if m.id not in excluded_ids)
|
||||
effective = [self._summary_message(cached.summary_text), *preserved]
|
||||
effective = _ensure_latest_human_message(messages, effective)
|
||||
# Decide re-summarization on the *counted* size of the compressed
|
||||
# context only — NOT ``_should_summarize`` — because that folds in the
|
||||
# last AIMessage's reported ``usage_metadata`` (system prompt + tool
|
||||
@@ -400,8 +450,7 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
# Refresh LRU recency and reuse without an LLM call.
|
||||
self._touch_cache_entry(thread_id)
|
||||
logger.info(
|
||||
"summarization: 上下文压缩(复用缓存摘要,无 LLM 调用) context compaction reusing cached summary "
|
||||
"thread=%s full_tokens=%d compressed_tokens=%d preserved_msgs=%d",
|
||||
"summarization: 上下文压缩(复用缓存摘要,无 LLM 调用) context compaction reusing cached summary thread=%s full_tokens=%d compressed_tokens=%d preserved_msgs=%d",
|
||||
thread_id,
|
||||
self.token_counter(messages),
|
||||
self.token_counter(effective),
|
||||
@@ -415,7 +464,7 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
# an "it compacts every turn" report is diagnosable straight from the
|
||||
# backend log: cache=miss → thread_id/key problem; unusable → message-id
|
||||
# instability; stale → preserved genuinely grew back over the trigger.
|
||||
cache_state = "miss" if cached is None else "stale"
|
||||
cache_state = "miss" if cached is None else "stale"
|
||||
logger.info(
|
||||
"summarization: compacting thread=%s cache=%s counted_tokens=%d msgs=%d",
|
||||
thread_id,
|
||||
@@ -452,22 +501,23 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
) -> list[AnyMessage]:
|
||||
"""Assemble the compressed message list and update the per-thread cache."""
|
||||
compressed = [self._summary_message(summary), *preserved]
|
||||
compressed = _ensure_latest_human_message([*messages_to_summarize, *preserved], compressed)
|
||||
|
||||
if thread_id:
|
||||
summarized_ids = frozenset(m.id for m in messages_to_summarize if m.id is not None)
|
||||
preserved_ids = {m.id for m in preserved if m.id is not None}
|
||||
self._store_cache_entry(
|
||||
thread_id,
|
||||
entry := _SummaryCacheEntry(
|
||||
summarized_ids=summarized_ids,
|
||||
summary_text=summary,
|
||||
preserved_ids=frozenset(preserved_ids),
|
||||
preserved_messages=tuple(preserved),
|
||||
),
|
||||
)
|
||||
self._pending_state_cache_update = _serialize_cache_entry(entry)
|
||||
|
||||
return compressed
|
||||
self._store_cache_entry(
|
||||
thread_id,
|
||||
entry := _SummaryCacheEntry(
|
||||
summarized_ids=summarized_ids,
|
||||
summary_text=summary,
|
||||
preserved_ids=frozenset(preserved_ids),
|
||||
preserved_messages=tuple(preserved),
|
||||
),
|
||||
)
|
||||
self._pending_state_cache_update = _serialize_cache_entry(entry)
|
||||
|
||||
return compressed
|
||||
|
||||
def _get_cache_entry(self, thread_id: str) -> _SummaryCacheEntry | None:
|
||||
"""Return the cached entry for ``thread_id`` (thread-safe read)."""
|
||||
@@ -571,7 +621,7 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
return None
|
||||
return _resolve_thread_id(runtime)
|
||||
|
||||
def _summary_message(self, summary: str) -> SystemMessage:
|
||||
def _summary_message(self, summary: str) -> SystemMessage:
|
||||
"""Build the summary message handed to the model.
|
||||
|
||||
It is named ``summary`` and flagged ``hide_from_ui`` defensively. Because
|
||||
@@ -579,21 +629,21 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
|
||||
state), the frontend never receives it — the user keeps seeing the
|
||||
original conversation.
|
||||
"""
|
||||
return SystemMessage(
|
||||
content=(
|
||||
"Internal conversation summary for continuity only. Use it silently "
|
||||
"to answer the user's latest request. Never reveal, quote, mention, "
|
||||
"or describe this summary or the fact that context was compacted.\n\n"
|
||||
"<internal_context_summary>\n"
|
||||
f"{summary}\n"
|
||||
"</internal_context_summary>"
|
||||
),
|
||||
return SystemMessage(
|
||||
content=(
|
||||
"Internal conversation summary for continuity only. Use it silently "
|
||||
"to answer the user's latest request. Never reveal, quote, mention, "
|
||||
"or describe this summary or the fact that context was compacted.\n\n"
|
||||
"<internal_context_summary>\n"
|
||||
f"{summary}\n"
|
||||
"</internal_context_summary>"
|
||||
),
|
||||
name="summary",
|
||||
additional_kwargs={"hide_from_ui": True, "lc_source": "summarization"},
|
||||
)
|
||||
|
||||
@override
|
||||
def _build_new_messages(self, summary: str) -> list[AnyMessage]:
|
||||
def _build_new_messages(self, summary: str) -> list[AnyMessage]:
|
||||
"""Kept for backwards compatibility; delegates to :meth:`_summary_message`."""
|
||||
return [self._summary_message(summary)]
|
||||
|
||||
|
||||
Reference in new issue
Block a user