adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Release/v0.2.3 (#281)

Browse Source 
* feat(app and model): token consumption statistics of the cluster

* fix(web): prompt history remove pageLoading

* fix(prompt): remove hard-coded import of prompt file paths (#279)

* Fix/develop memory bug (#274)

* 遗漏的历史映射

* 遗漏的历史映射

* fix_timeline_memories

* fix(web): update retrieve_type key

* Fix/develop memory bug (#276)

* 遗漏的历史映射

* 遗漏的历史映射

* fix_timeline_memories

* fix_timeline_memories

* write_gragp/bug_fix

* write_gragp/bug_fix

* write_gragp/bug_fix

* chore(celery): disable periodic task scheduling

* fix(prompt): remove hard-coded import of prompt file paths

---------

Co-authored-by: lixinyue11 <94037597+lixinyue11@users.noreply.github.com>
Co-authored-by: zhaoying <yzhao96@best-inc.com>
Co-authored-by: yingzhao <zhaoyingyz@126.com>
Co-authored-by: Ke Sun <kesun5@illinois.edu>

---------

Co-authored-by: Timebomb2018 <18868801967@163.com>
Co-authored-by: Mark <zhuwenhui5566@163.com>
Co-authored-by: zhaoying <yzhao96@best-inc.com>
Co-authored-by: Eternity <61316157+myhMARS@users.noreply.github.com>
Co-authored-by: lixinyue11 <94037597+lixinyue11@users.noreply.github.com>
Co-authored-by: yingzhao <zhaoyingyz@126.com>
This commit is contained in:
Ke Sun
2026-02-03 10:33:39 +08:00
committed by GitHub
parent e919f89caf
commit 940c594066
10 changed files with 191 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
api/app/services/app_chat_service.py
View File

@@ -427,7 +427,11 @@ class AppChatService:
meta_data={
"mode": result.get("mode"),
"elapsed_time": result.get("elapsed_time"),
"sub_results": result.get("sub_results")
"usage": result.get("usage", {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0
})
}
)
@@ -469,6 +473,7 @@ class AppChatService:
yield f"event: start\ndata: {json.dumps({'conversation_id': str(conversation_id)}, ensure_ascii=False)}\n\n"
full_content = ""
total_tokens = 0
# 2. 创建编排器
orchestrator = MultiAgentOrchestrator(self.db, config)
@@ -485,16 +490,26 @@ class AppChatService:
storage_type=storage_type,
user_rag_memory_id=user_rag_memory_id
):
yield event
# 尝试提取内容（用于保存）
if "data:" in event:
try:
data_line = event.split("data: ", 1)[1].strip()
data = json.loads(data_line)
if "content" in data:
full_content += data["content"]
except:
pass
if "sub_usage" in event:
if "data:" in event:
try:
data_line = event.split("data: ", 1)[1].strip()
data = json.loads(data_line)
if "total_tokens" in data:
total_tokens += data["total_tokens"]
except:
pass
else:
yield event
# 尝试提取内容（用于保存）
if "data:" in event:
try:
data_line = event.split("data: ", 1)[1].strip()
data = json.loads(data_line)
if "content" in data:
full_content += data["content"]
except:
pass
elapsed_time = time.time() - start_time
@@ -510,7 +525,12 @@ class AppChatService:
role="assistant",
content=full_content,
meta_data={
"elapsed_time": elapsed_time
"elapsed_time": elapsed_time,
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": total_tokens
}
}
)

7
api/app/services/conversation_service.py
View File

@@ -1,4 +1,5 @@
"""会话服务"""
import os
import uuid
from datetime import datetime, timedelta
from typing import Annotated
@@ -529,12 +530,12 @@ class ConversationService:
takeaways=[],
info_score=0,
)
with open('app/services/prompt/conversation_summary_system.jinja2', 'r', encoding='utf-8') as f:
prompt_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'prompt')
with open(os.path.join(prompt_path, 'conversation_summary_system.jinja2'), 'r', encoding='utf-8') as f:
system_prompt = f.read()
rendered_system_message = Template(system_prompt).render()
with open('app/services/prompt/conversation_summary_user.jinja2', 'r', encoding='utf-8') as f:
with open(os.path.join(prompt_path, 'conversation_summary_user.jinja2'), 'r', encoding='utf-8') as f:
user_prompt = f.read()
rendered_user_message = Template(user_prompt).render(
language=language,

5
api/app/services/draft_run_service.py
View File

@@ -678,6 +678,11 @@ class DraftRunService:
elapsed_time = time.time() - start_time
if sub_agent:
yield self._format_sse_event("sub_usage", {
"total_tokens": total_tokens
})
# 10. 保存会话消息
if not sub_agent and agent_config.memory and agent_config.memory.get("enabled"):
await self._save_conversation_message(

18
api/app/services/handoffs_service.py
View File

@@ -4,7 +4,7 @@ import uuid
from typing import List, Dict, Any, Optional, AsyncGenerator, Annotated
from typing_extensions import TypedDict
from langchain_core.messages import HumanMessage, AIMessage, BaseMessage
from langchain_core.messages import HumanMessage, AIMessage, BaseMessage, AIMessageChunk
from langgraph.graph import StateGraph, START, END
from langgraph.types import Command
from langgraph.checkpoint.memory import MemorySaver
@@ -727,9 +727,12 @@ class HandoffsService:
# 提取响应
response_content = ""
total_tokens = 0
for msg in result.get("messages", []):
if isinstance(msg, AIMessage):
response_content = msg.content
response_meta = msg.response_metadata if hasattr(msg, 'response_metadata') else None
total_tokens = response_meta.get("token_usage", {}).get("total_tokens", 0) if response_meta else 0
break
return {
@@ -737,7 +740,12 @@ class HandoffsService:
"active_agent": result.get("active_agent"),
"response": response_content,
"message_count": len(result.get("messages", [])),
"handoff_count": result.get("handoff_count", 0)
"handoff_count": result.get("handoff_count", 0),
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": total_tokens
}
}
async def chat_stream(
@@ -830,6 +838,12 @@ class HandoffsService:
# 捕获 LLM 结束事件，输出收集到的工具调用
elif kind == "on_chat_model_end":
output_message = event.get("data", {}).get("output", {})
if isinstance(output_message, AIMessageChunk):
response_meta = output_message.response_metadata if hasattr(output_message, 'response_metadata') else None
total_tokens = response_meta.get("token_usage", {}).get("total_tokens",
0) if response_meta else 0
yield f"event: sub_usage\ndata: {json.dumps({"total_tokens": total_tokens}, ensure_ascii=False)}\n\n"
if collected_tool_calls:
# 找到参数最完整的 transfer 工具调用
best_tc = None

20
api/app/services/multi_agent_orchestrator.py
View File

@@ -280,14 +280,22 @@ class MultiAgentOrchestrator:
# 4. 提取子 Agent 的 conversation_id（用于多轮对话）
sub_conversation_id = None
total_tokens = 0
if isinstance(results, dict):
sub_conversation_id = results.get("conversation_id") or results.get("result", {}).get("conversation_id")
# 提取 token 信息
usage = results.get("usage", {}) or results.get("result", {}).get("usage", {})
total_tokens += usage.get("total_tokens", 0)
elif isinstance(results, list) and results:
for item in results:
if "result" in item:
sub_conversation_id = item["result"].get("conversation_id")
if sub_conversation_id:
break
# 累加每个子 Agent 的 token
usage = item.get("usage", {}) or item.get("result", {}).get("usage", {})
total_tokens += usage.get("total_tokens", 0)
logger.info(
"多 Agent 任务完成",
@@ -301,9 +309,15 @@ class MultiAgentOrchestrator:
return {
"message": final_result,
"conversation_id": sub_conversation_id,
"mode": OrchestrationMode.SUPERVISOR,
"elapsed_time": elapsed_time,
"strategy": routing_decision.get("collaboration_strategy", "single"),
"sub_results": results
"sub_results": results,
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": total_tokens
}
}
except Exception as e:
@@ -1552,10 +1566,12 @@ class MultiAgentOrchestrator:
return {
"message": result.get("response", ""),
"conversation_id": result.get("conversation_id"),
"mode": OrchestrationMode.COLLABORATION,
"elapsed_time": elapsed_time,
"strategy": "collaboration",
"active_agent": result.get("active_agent"),
"sub_results": result
"sub_results": result,
"usage": result.get("usage")
}
except Exception as e:

106
api/app/services/multi_agent_service.py
View File

@@ -1,5 +1,6 @@
"""多 Agent 配置管理服务"""
import uuid
import json
from typing import Optional, List, Tuple, Any, Annotated
from fastapi import Depends
@@ -427,6 +428,23 @@ class MultiAgentService:
memory=getattr(request, 'memory', True) # 记忆功能参数
)
await self._save_conversation_message(
conversation_id=request.conversation_id,
user_message=request.message,
assistant_message=result.get("message", ""),
app_id=app_id,
user_id=request.user_id,
meta_data={
"mode": result.get("mode"),
"elapsed_time": result.get("elapsed_time"),
"usage": result.get("usage", {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0
})
}
)
return result
async def run_stream(
@@ -451,11 +469,14 @@ class MultiAgentService:
raise ResourceNotFoundException("多 Agent 配置", str(app_id))
if not config.is_active:
raise BusinessException("多 Agent 配置已禁用", BizCode.RESOURCE_DISABLED)
raise BusinessException("多 Agent 配置已禁用", BizCode.NOT_FOUND)
# 2. 创建编排器
orchestrator = MultiAgentOrchestrator(self.db, config)
full_content = ""
total_tokens = 0
# 3. 流式执行任务
async for event in orchestrator.execute_stream(
message=request.message,
@@ -468,7 +489,88 @@ class MultiAgentService:
storage_type=storage_type,
user_rag_memory_id=user_rag_memory_id
):
yield event
if "sub_usage" in event:
if "data:" in event:
try:
data_line = event.split("data: ", 1)[1].strip()
data = json.loads(data_line)
if "total_tokens" in data:
total_tokens += data["total_tokens"]
except:
pass
else:
yield event
if "data:" in event:
try:
data_line = event.split("data: ", 1)[1].strip()
data = json.loads(data_line)
if "content" in data:
full_content += data["content"]
except:
pass
await self._save_conversation_message(
conversation_id=request.conversation_id,
user_message=request.message,
assistant_message=full_content,
app_id=app_id,
user_id=request.user_id,
meta_data={
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": total_tokens
}
}
)
async def _save_conversation_message(
self,
conversation_id: uuid.UUID,
user_message: str,
assistant_message: str,
meta_data: dict,
app_id: Optional[uuid.UUID] = None,
user_id: Optional[str] = None
) -> None:
"""保存会话消息
Args:
conversation_id: 会话ID
user_message: 用户消息
assistant_message: AI 回复消息
meta_data: 元数据（包括 token 消耗）
app_id: 应用ID
user_id: 用户ID
"""
try:
from app.services.conversation_service import ConversationService
conversation_service = ConversationService(self.db)
conversation_service.add_message(
conversation_id=conversation_id,
role="user",
content=user_message
)
conversation_service.add_message(
conversation_id=conversation_id,
role="assistant",
content=assistant_message,
meta_data=meta_data
)
logger.debug(
"保存多 Agent 会话消息",
extra={
"conversation_id": conversation_id,
"user_message_length": len(user_message),
"assistant_message_length": len(assistant_message)
}
)
except Exception as e:
logger.warning("保存会话消息失败", extra={"error": str(e)})
# def add_sub_agent(
# self,

6
api/app/services/prompt_optimizer_service.py
View File

@@ -1,3 +1,4 @@
import os
import re
import uuid
from typing import Any, AsyncGenerator
@@ -182,11 +183,12 @@ class PromptOptimizerService:
base_url=api_config.api_base
), type=ModelType(model_config.type))
try:
with open('app/services/prompt/prompt_optimizer_system.jinja2', 'r', encoding='utf-8') as f:
prompt_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'prompt')
with open(os.path.join(prompt_path, 'prompt_optimizer_system.jinja2'), 'r', encoding='utf-8') as f:
opt_system_prompt = f.read()
rendered_system_message = Template(opt_system_prompt).render()
with open('app/services/prompt/prompt_optimizer_user.jinja2', 'r', encoding='utf-8') as f:
with open(os.path.join(prompt_path, 'prompt_optimizer_user.jinja2'), 'r', encoding='utf-8') as f:
opt_user_prompt = f.read()
except FileNotFoundError:
raise BusinessException(message="System prompt template not found", code=BizCode.NOT_FOUND)

5
web/src/components/PageScrollList/index.tsx
View File

@@ -26,6 +26,7 @@ interface PageScrollListProps<T, Q = Record<string, unknown>> {
query?: Q;
column?: number;
className?: string;
needLoading?: boolean;
}
const PageScrollList = forwardRef(<T, Q = Record<string, unknown>>({
renderItem,
@@ -33,6 +34,7 @@ const PageScrollList = forwardRef(<T, Q = Record<string, unknown>>({
url,
column = 4,
className = '',
needLoading = true,
}: PageScrollListProps<T, Q>, ref: React.Ref<PageScrollListRef>) => {
useImperativeHandle(ref, () => ({
refresh,
@@ -104,9 +106,10 @@ const PageScrollList = forwardRef(<T, Q = Record<string, unknown>>({
dataLength={data.length}
next={loadMoreData}
hasMore={hasMore}
loader={<PageLoading />}
loader={needLoading ? <PageLoading /> : undefined}
// endMessage={<Divider plain>It is all, nothing more 🤐</Divider>}
scrollableTarget="scrollableDiv"
className='rb:h-full!'
>
{data.length > 0 ? (
<List

3
web/src/styles/index.css
View File

@@ -180,4 +180,7 @@ body {
.x6-node foreignObject > body {
min-height: 100%;
max-height: 100%;
}
#scrollableDiv .infinite-scroll-component__outerdiv {
height: 100%;
}

1
web/src/views/Prompt/History.tsx
View File

@@ -50,6 +50,7 @@ const History: React.FC<{ query: HistoryQuery; edit: (item: HistoryItem) => void
url={getPromptReleaseListUrl}
query={query}
column={3}
needLoading={false}
renderItem={(item) => {
const historyItem = item as unknown as HistoryItem;
return (