Merge branch 'master' of http://192.168.0.200/knowledge-base-bj/deerflow-server into dhk-1
# Conflicts: # frontend-web/src/components/workspace/chats/chat-box.tsx # frontend-web/src/pages/StrategyRoutes.tsx # offline-backend-20260512/backend/app/gateway/routers/agents.py
This commit is contained in:
commit
d2f3eba434
81 files changed
+10489
-1653
No files matched your search
+41
-7
@@ -61,6 +61,21 @@ _AUTH_PATTERNS = (
|
||||
"无权",
|
||||
"未授权",
|
||||
)
|
||||
# Upstream model gateway returned a malformed payload (typically a JSON decode
|
||||
# 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",
|
||||
"bad response status",
|
||||
"expecting ',' delimiter",
|
||||
"expecting value",
|
||||
"expecting property name",
|
||||
"unexpected character",
|
||||
"unterminated string",
|
||||
"extra data",
|
||||
"jsondecodeerror",
|
||||
)
|
||||
|
||||
|
||||
class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
|
||||
@@ -139,9 +154,10 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
|
||||
detail = _extract_error_detail(exc)
|
||||
lowered = detail.lower()
|
||||
error_code = _extract_error_code(exc)
|
||||
error_code_lower = str(error_code).lower() if error_code is not None else ""
|
||||
status_code = _extract_status_code(exc)
|
||||
|
||||
if _matches_any(lowered, _QUOTA_PATTERNS) or _matches_any(str(error_code).lower(), _QUOTA_PATTERNS):
|
||||
if _matches_any(lowered, _QUOTA_PATTERNS) or _matches_any(error_code_lower, _QUOTA_PATTERNS):
|
||||
return False, "quota"
|
||||
if _matches_any(lowered, _AUTH_PATTERNS):
|
||||
return False, "auth"
|
||||
@@ -159,6 +175,11 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
|
||||
return True, "transient"
|
||||
if _matches_any(lowered, _BUSY_PATTERNS):
|
||||
return True, "busy"
|
||||
# Treat upstream gateway garbage (malformed JSON, truncated responses)
|
||||
# as a retriable transient — the deterministic char-position errors we
|
||||
# see from vLLM/proxy layers usually clear on a re-roll.
|
||||
if _matches_any(lowered, _UPSTREAM_GARBAGE_PATTERNS) or _matches_any(error_code_lower, _UPSTREAM_GARBAGE_PATTERNS):
|
||||
return True, "upstream"
|
||||
|
||||
return False, "generic"
|
||||
|
||||
@@ -171,21 +192,34 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
|
||||
|
||||
def _build_retry_message(self, attempt: int, wait_ms: int, reason: str) -> str:
|
||||
seconds = max(1, round(wait_ms / 1000))
|
||||
reason_text = "服务繁忙" if reason == "busy" else "网络/连接异常"
|
||||
if reason == "busy":
|
||||
reason_text = "服务繁忙"
|
||||
elif reason == "upstream":
|
||||
reason_text = "上游响应异常"
|
||||
else:
|
||||
reason_text = "网络/连接异常"
|
||||
return f"大模型因{reason_text}调用失败,正在第 {attempt}/{self.retry_max_attempts} 次重试,{seconds} 秒后继续…"
|
||||
|
||||
def _build_circuit_breaker_message(self) -> str:
|
||||
return "大模型因连续多次调用失败已被熔断保护,请稍候再试。"
|
||||
|
||||
def _build_user_message(self, exc: BaseException, reason: str) -> str:
|
||||
detail = _extract_error_detail(exc)
|
||||
def _build_user_message(self, reason: str) -> str:
|
||||
if reason == "quota":
|
||||
return "大模型因账户额度不足、账单异常或使用受限而拒绝请求,请检查模型账户后再试。"
|
||||
if reason == "auth":
|
||||
return "大模型因鉴权失败或无访问权限而拒绝请求,请检查模型的 API Key 与权限配置后再试。"
|
||||
if reason in {"busy", "transient"}:
|
||||
return "大模型因服务繁忙或网络异常,多次重试后仍未恢复,请稍候再继续。"
|
||||
return f"大模型因「{detail}」原因调用失败。"
|
||||
if reason == "upstream":
|
||||
return "大模型当前响应异常(上游模型或网关临时故障),多次重试后仍未恢复,请稍后再试或更换模型。"
|
||||
# NOTE: We intentionally do NOT embed the raw exception detail into the
|
||||
# user-facing message. Raw `Error code: 400 - {...}` strings — especially
|
||||
# Python repr-style dict literals — get persisted as AI messages and then
|
||||
# re-fed to the model on the next turn, where their unescaped quotes /
|
||||
# braces can corrupt the upstream JSON payload and cause deterministic
|
||||
# JSONDecodeError loops. Keep the user message clean; full detail is
|
||||
# already in the backend log via `logger.warning(..., exc_info=exc)`.
|
||||
return "大模型本次调用未能成功完成,请稍后再试或更换模型。"
|
||||
|
||||
def _emit_retry_event(self, attempt: int, wait_ms: int, reason: str) -> None:
|
||||
try:
|
||||
@@ -249,7 +283,7 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
|
||||
)
|
||||
if retriable:
|
||||
self._record_failure()
|
||||
return AIMessage(content=self._build_user_message(exc, reason))
|
||||
return AIMessage(content=self._build_user_message(reason))
|
||||
|
||||
@override
|
||||
async def awrap_model_call(
|
||||
@@ -295,7 +329,7 @@ class LLMErrorHandlingMiddleware(AgentMiddleware[AgentState]):
|
||||
)
|
||||
if retriable:
|
||||
self._record_failure()
|
||||
return AIMessage(content=self._build_user_message(exc, reason))
|
||||
return AIMessage(content=self._build_user_message(reason))
|
||||
|
||||
|
||||
def _matches_any(detail: str, patterns: tuple[str, ...]) -> bool:
|
||||
|
||||
+109
@@ -0,0 +1,109 @@
|
||||
"""Inject stable citation numbering before RAG final answers."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from pathlib import Path
|
||||
from collections.abc import Awaitable, Callable
|
||||
from typing import Any, override
|
||||
|
||||
from langchain.agents import AgentState
|
||||
from langchain.agents.middleware import AgentMiddleware
|
||||
from langchain.agents.middleware.types import ModelCallResult, ModelRequest, ModelResponse
|
||||
from langchain_core.messages import SystemMessage
|
||||
|
||||
from deerflow.runtime.references import build_latest_reference_prompt, build_reference_debug_summary
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
_RAG_DEBUG_LOGGER_NAME = "rag_citation_debug"
|
||||
|
||||
|
||||
def _get_rag_debug_logger() -> logging.Logger:
|
||||
debug_logger = logging.getLogger(_RAG_DEBUG_LOGGER_NAME)
|
||||
if getattr(debug_logger, "_rag_file_configured", False):
|
||||
return debug_logger
|
||||
log_path = Path(os.environ.get("RAG_CITATION_DEBUG_LOG", "logs/rag_citation_debug.log"))
|
||||
if not log_path.is_absolute():
|
||||
log_path = Path.cwd() / log_path
|
||||
log_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
handler = logging.FileHandler(log_path, encoding="utf-8")
|
||||
handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(message)s"))
|
||||
debug_logger.addHandler(handler)
|
||||
debug_logger.setLevel(logging.INFO)
|
||||
debug_logger.propagate = False
|
||||
setattr(debug_logger, "_rag_file_configured", True)
|
||||
setattr(debug_logger, "_rag_file_path", str(log_path))
|
||||
return debug_logger
|
||||
|
||||
|
||||
def _log_rag_debug(message: str, *args: Any) -> None:
|
||||
logger.info(message, *args)
|
||||
_get_rag_debug_logger().info(message, *args)
|
||||
|
||||
|
||||
class RagCitationMiddleware(AgentMiddleware[AgentState]):
|
||||
"""Give the model the same numbered references the frontend will render."""
|
||||
|
||||
@staticmethod
|
||||
def _enabled(request: ModelRequest) -> bool:
|
||||
runtime = getattr(request, "runtime", None)
|
||||
context = getattr(runtime, "context", None) if runtime is not None else None
|
||||
if isinstance(context, dict) and context.get("rag_mode_enabled"):
|
||||
return True
|
||||
config = getattr(runtime, "config", None) if runtime is not None else None
|
||||
if isinstance(config, dict):
|
||||
configurable = config.get("configurable")
|
||||
if isinstance(configurable, dict) and configurable.get("rag_mode_enabled"):
|
||||
return True
|
||||
runtime_context = config.get("context")
|
||||
if isinstance(runtime_context, dict) and runtime_context.get("rag_mode_enabled"):
|
||||
return True
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def _patch(request: ModelRequest) -> ModelRequest | None:
|
||||
if not RagCitationMiddleware._enabled(request):
|
||||
return None
|
||||
messages = list(request.messages)
|
||||
prompt, batch = build_latest_reference_prompt(messages)
|
||||
if not prompt:
|
||||
_log_rag_debug(
|
||||
"middleware reference-prompt enabled=true prompt=false messages=%s",
|
||||
len(messages),
|
||||
)
|
||||
return None
|
||||
summary = build_reference_debug_summary(messages, [batch] if batch else None)
|
||||
_log_rag_debug(
|
||||
"middleware reference-prompt enabled=true prompt=true messages=%s tool_messages=%s "
|
||||
"raw_items=%s normalized_items=%s kept_items=%s latest_batch_sources=%s",
|
||||
summary["messages"],
|
||||
summary["tool_messages"],
|
||||
summary["raw_items"],
|
||||
summary["normalized_items"],
|
||||
summary["kept_items"],
|
||||
len((batch or {}).get("sources") or []),
|
||||
)
|
||||
patched_messages = [
|
||||
*messages,
|
||||
SystemMessage(content=prompt),
|
||||
]
|
||||
return request.override(messages=patched_messages)
|
||||
|
||||
@override
|
||||
def wrap_model_call(
|
||||
self,
|
||||
request: ModelRequest,
|
||||
handler: Callable[[ModelRequest], ModelResponse],
|
||||
) -> ModelCallResult:
|
||||
patched = self._patch(request)
|
||||
return handler(patched or request)
|
||||
|
||||
@override
|
||||
async def awrap_model_call(
|
||||
self,
|
||||
request: ModelRequest,
|
||||
handler: Callable[[ModelRequest], Awaitable[ModelResponse]],
|
||||
) -> ModelCallResult:
|
||||
patched = self._patch(request)
|
||||
return await handler(patched or request)
|
||||
Reference in new issue
Block a user