Merge remote-tracking branch 'origin/master' into dev/4.11.x

# Conflicts:
#	pyproject.toml
#	uv.lock
#	web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx

src/langbot/pkg/api/http/controller/groups/monitoring.py

@@ -138,6 +138,39 @@ class MonitoringRouterGroup(group.RouterGroup):
                 }
             )
 
+        @self.route('/tool-calls', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def get_tool_calls() -> str:
+            """Get tool call records"""
+            bot_ids = quart.request.args.getlist('botId')
+            pipeline_ids = quart.request.args.getlist('pipelineId')
+            session_ids = quart.request.args.getlist('sessionId')
+            start_time_str = quart.request.args.get('startTime')
+            end_time_str = quart.request.args.get('endTime')
+            limit = int(quart.request.args.get('limit', 100))
+            offset = int(quart.request.args.get('offset', 0))
+
+            start_time = parse_iso_datetime(start_time_str)
+            end_time = parse_iso_datetime(end_time_str)
+
+            tool_calls, total = await self.ap.monitoring_service.get_tool_calls(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                session_ids=session_ids if session_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=offset,
+            )
+
+            return self.success(
+                data={
+                    'tool_calls': tool_calls,
+                    'total': total,
+                    'limit': limit,
+                    'offset': offset,
+                }
+            )
+
         @self.route('/embedding-calls', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
         async def get_embedding_calls() -> str:
             """Get embedding call records"""
@@ -284,6 +317,16 @@ class MonitoringRouterGroup(group.RouterGroup):
                 offset=0,
             )
 
+            # Get tool calls
+            tool_calls, tool_calls_total = await self.ap.monitoring_service.get_tool_calls(
+                bot_ids=bot_ids if bot_ids else None,
+                pipeline_ids=pipeline_ids if pipeline_ids else None,
+                start_time=start_time,
+                end_time=end_time,
+                limit=limit,
+                offset=0,
+            )
+
             # Get sessions
             sessions, sessions_total = await self.ap.monitoring_service.get_sessions(
                 bot_ids=bot_ids if bot_ids else None,
@@ -318,12 +361,14 @@ class MonitoringRouterGroup(group.RouterGroup):
                     'overview': overview,
                     'messages': messages,
                     'llmCalls': llm_calls,
+                    'toolCalls': tool_calls,
                     'embeddingCalls': embedding_calls,
                     'sessions': sessions,
                     'errors': errors,
                     'totalCount': {
                         'messages': messages_total,
                         'llmCalls': llm_calls_total,
+                        'toolCalls': tool_calls_total,
                         'embeddingCalls': embedding_calls_total,
                         'sessions': sessions_total,
                         'errors': errors_total,

src/langbot/pkg/api/http/controller/groups/resources/mcp.py

@@ -29,11 +29,11 @@ class MCPRouterGroup(group.RouterGroup):
                     traceback.print_exc()
                     return self.http_status(500, -1, f'Failed to create MCP server: {str(e)}')
 
-        @self.route('/servers/<server_name>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route(
+            '/servers/<path:server_name>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN
+        )
         async def _(server_name: str) -> str:
             """获取、更新或删除MCP服务器配置"""
-            from urllib.parse import unquote
-
             server_name = unquote(server_name)
 
             server_data = await self.ap.mcp_service.get_mcp_server_by_name(server_name)
@@ -58,17 +58,15 @@ class MCPRouterGroup(group.RouterGroup):
                 except Exception as e:
                     return self.http_status(500, -1, f'Failed to delete MCP server: {str(e)}')
 
-        @self.route('/servers/<server_name>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('/servers/<path:server_name>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _(server_name: str) -> str:
             """测试MCP服务器连接"""
-            from urllib.parse import unquote
-
             server_name = unquote(server_name)
             server_data = await quart.request.json
             task_id = await self.ap.mcp_service.test_mcp_server(server_name=server_name, server_data=server_data)
             return self.success(data={'task_id': task_id})
 
-        @self.route('/servers/<server_name>/resources', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('/servers/<path:server_name>/resources', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
         async def _(server_name: str) -> str:
             """Get resources from an MCP server"""
             server_name = unquote(server_name)
@@ -86,7 +84,9 @@ class MCPRouterGroup(group.RouterGroup):
             except Exception as e:
                 return self.http_status(500, -1, f'Failed to get resources: {str(e)}')
 
-        @self.route('/servers/<server_name>/resource-templates', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route(
+            '/servers/<path:server_name>/resource-templates', methods=['GET'], auth_type=group.AuthType.USER_TOKEN
+        )
         async def _(server_name: str) -> str:
             """Get resource templates from an MCP server"""
             server_name = unquote(server_name)
@@ -96,7 +96,20 @@ class MCPRouterGroup(group.RouterGroup):
             except Exception as e:
                 return self.http_status(500, -1, f'Failed to get resource templates: {str(e)}')
 
-        @self.route('/servers/<server_name>/resources/read', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        @self.route('/servers/<path:server_name>/logs', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(server_name: str) -> str:
+            """Get logs from an MCP server"""
+            server_name = unquote(server_name)
+            try:
+                limit = int(quart.request.args.get('limit', 200))
+            except (TypeError, ValueError):
+                limit = 200
+            limit = min(limit, 500)
+            level = quart.request.args.get('level') or None
+            logs = await self.ap.mcp_service.get_mcp_server_logs(server_name, limit=limit, level=level)
+            return self.success(data={'logs': logs})
+
+        @self.route('/servers/<path:server_name>/resources/read', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _(server_name: str) -> str:
             """Read a resource from an MCP server"""
             server_name = unquote(server_name)

src/langbot/pkg/api/http/service/maintenance.py

@@ -243,6 +243,7 @@ class MaintenanceService:
         tables = {
             'messages': persistence_monitoring.MonitoringMessage.id,
             'llm_calls': persistence_monitoring.MonitoringLLMCall.id,
+            'tool_calls': persistence_monitoring.MonitoringToolCall.id,
             'embedding_calls': persistence_monitoring.MonitoringEmbeddingCall.id,
             'errors': persistence_monitoring.MonitoringError.id,
             'sessions': persistence_monitoring.MonitoringSession.session_id,

src/langbot/pkg/api/http/service/mcp.py

@@ -48,6 +48,17 @@ class MCPService:
             if total_extensions >= max_extensions:
                 raise ValueError(f'Maximum number of extensions ({max_extensions}) reached')
 
+        server_name = str(server_data.get('name') or '').strip()
+        if not server_name:
+            raise ValueError('MCP server name is required')
+        server_data['name'] = server_name
+
+        existing_result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.name == server_name)
+        )
+        if existing_result.first() is not None:
+            raise ValueError(f'MCP server already exists: {server_name}')
+
         server_data['uuid'] = str(uuid.uuid4())
         await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_mcp.MCPServer).values(server_data))
 
@@ -177,10 +188,22 @@ class MCPService:
             persisted_session = runtime_mcp_session
 
             async def _refresh_and_report() -> None:
-                if persisted_session.status == MCPSessionStatus.ERROR:
+                # Testing a persisted server should REUSE its live shared-session
+                # process, not rebuild it. Try a lightweight refresh (a real
+                # list_tools probe over the existing connection) first; only fall
+                # back to a full start() when the session has no live connection
+                # to probe (never connected, or the process is actually gone).
+                needs_start = persisted_session.status == MCPSessionStatus.ERROR or persisted_session.session is None
+                if needs_start:
                     await persisted_session.start()
                 else:
-                    await persisted_session.refresh()
+                    try:
+                        await persisted_session.refresh()
+                    except Exception:
+                        # The live connection was stale/dropped: reconnect once
+                        # (reusing the live managed process where possible) and
+                        # re-probe, instead of reporting a false failure.
+                        await persisted_session.start()
                 # Surface the discovered tools so the config page can render them
                 # even for an already-hosted server.
                 ctx.metadata['runtime_info'] = persisted_session.get_runtime_info_dict()
@@ -221,3 +244,19 @@ class MCPService:
             context=ctx,
         )
         return wrapper.id
+
+    async def get_mcp_server_logs(self, server_name: str, limit: int = 200, level: str | None = None) -> list[dict]:
+        """Get recent log lines captured from the MCP server's stderr."""
+        session = self.ap.tool_mgr.mcp_tool_loader.get_session(server_name)
+        if not session:
+            return []
+
+        # Get logs from the session's buffer
+        logs = list(session._log_buffer)
+
+        # Filter by level if specified
+        if level:
+            logs = [log for log in logs if log.get('level') == level]
+
+        # Return the most recent 'limit' logs
+        return logs[-limit:]

src/langbot/pkg/api/http/service/monitoring.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import uuid
 import datetime
+import json
 import sqlalchemy
 
 from ....core import app
@@ -50,6 +51,12 @@ class MonitoringService:
                 persistence_monitoring.MonitoringLLMCall.timestamp,
                 persistence_monitoring.MonitoringLLMCall.id,
             ),
+            (
+                'monitoring_tool_calls',
+                persistence_monitoring.MonitoringToolCall,
+                persistence_monitoring.MonitoringToolCall.timestamp,
+                persistence_monitoring.MonitoringToolCall.id,
+            ),
             (
                 'monitoring_embedding_calls',
                 persistence_monitoring.MonitoringEmbeddingCall,
@@ -131,6 +138,68 @@ class MonitoringService:
             await autocommit_conn.execute(sqlalchemy.text('PRAGMA wal_checkpoint(TRUNCATE)'))
             await autocommit_conn.execute(sqlalchemy.text('VACUUM'))
 
+    def _serialize_tool_payload(self, payload: object, max_length: int = 20000) -> str | None:
+        """Serialize tool arguments/results for monitoring storage."""
+        if payload is None:
+            return None
+
+        if isinstance(payload, str):
+            text = payload
+        else:
+            try:
+                text = json.dumps(payload, ensure_ascii=False, default=str)
+            except Exception:
+                text = str(payload)
+
+        if len(text) <= max_length:
+            return text
+
+        return f'{text[:max_length]}... [truncated {len(text) - max_length} chars]'
+
+    async def _get_message_for_tool_context(
+        self,
+        message_id: str | None = None,
+        session_id: str | None = None,
+    ):
+        if message_id:
+            result = await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.select(persistence_monitoring.MonitoringMessage).where(
+                    persistence_monitoring.MonitoringMessage.id == message_id
+                )
+            )
+            row = result.first()
+            if row:
+                return row[0]
+
+        if not session_id:
+            return None
+
+        user_query = (
+            sqlalchemy.select(persistence_monitoring.MonitoringMessage)
+            .where(
+                sqlalchemy.and_(
+                    persistence_monitoring.MonitoringMessage.session_id == session_id,
+                    persistence_monitoring.MonitoringMessage.role == 'user',
+                )
+            )
+            .order_by(persistence_monitoring.MonitoringMessage.timestamp.desc())
+            .limit(1)
+        )
+        result = await self.ap.persistence_mgr.execute_async(user_query)
+        row = result.first()
+        if row:
+            return row[0]
+
+        any_query = (
+            sqlalchemy.select(persistence_monitoring.MonitoringMessage)
+            .where(persistence_monitoring.MonitoringMessage.session_id == session_id)
+            .order_by(persistence_monitoring.MonitoringMessage.timestamp.desc())
+            .limit(1)
+        )
+        result = await self.ap.persistence_mgr.execute_async(any_query)
+        row = result.first()
+        return row[0] if row else None
+
     # ========== Recording Methods ==========
 
     async def record_message(
@@ -220,6 +289,57 @@ class MonitoringService:
 
         return call_id
 
+    async def record_tool_call(
+        self,
+        tool_name: str,
+        tool_source: str,
+        duration: int,
+        status: str = 'success',
+        bot_id: str | None = None,
+        bot_name: str | None = None,
+        pipeline_id: str | None = None,
+        pipeline_name: str | None = None,
+        session_id: str | None = None,
+        message_id: str | None = None,
+        arguments: object | None = None,
+        result: object | None = None,
+        error_message: str | None = None,
+    ) -> str:
+        """Record a tool call."""
+        context_message = await self._get_message_for_tool_context(message_id=message_id, session_id=session_id)
+        if context_message:
+            bot_id = bot_id or context_message.bot_id
+            bot_name = bot_name or context_message.bot_name
+            pipeline_id = pipeline_id or context_message.pipeline_id
+            pipeline_name = pipeline_name or context_message.pipeline_name
+            session_id = session_id or context_message.session_id
+            message_id = message_id or context_message.id
+
+        call_id = str(uuid.uuid4())
+        call_data = {
+            'id': call_id,
+            'timestamp': datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
+            'tool_name': tool_name,
+            'tool_source': tool_source,
+            'duration': max(0, duration),
+            'status': status,
+            'bot_id': bot_id or 'unknown',
+            'bot_name': bot_name or 'Unknown',
+            'pipeline_id': pipeline_id or 'unknown',
+            'pipeline_name': pipeline_name or 'Unknown',
+            'session_id': session_id,
+            'message_id': message_id,
+            'arguments': self._serialize_tool_payload(arguments),
+            'result': self._serialize_tool_payload(result),
+            'error_message': self._serialize_tool_payload(error_message),
+        }
+
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.insert(persistence_monitoring.MonitoringToolCall).values(call_data)
+        )
+
+        return call_id
+
     async def record_embedding_call(
         self,
         model_name: str,
@@ -749,6 +869,58 @@ class MonitoringService:
             total,
         )
 
+    async def get_tool_calls(
+        self,
+        bot_ids: list[str] | None = None,
+        pipeline_ids: list[str] | None = None,
+        session_ids: list[str] | None = None,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
+        limit: int = 100,
+        offset: int = 0,
+    ) -> tuple[list[dict], int]:
+        """Get tool calls with filters"""
+        conditions = []
+
+        if bot_ids:
+            conditions.append(persistence_monitoring.MonitoringToolCall.bot_id.in_(bot_ids))
+        if pipeline_ids:
+            conditions.append(persistence_monitoring.MonitoringToolCall.pipeline_id.in_(pipeline_ids))
+        if session_ids:
+            conditions.append(persistence_monitoring.MonitoringToolCall.session_id.in_(session_ids))
+        if start_time:
+            conditions.append(persistence_monitoring.MonitoringToolCall.timestamp >= start_time)
+        if end_time:
+            conditions.append(persistence_monitoring.MonitoringToolCall.timestamp <= end_time)
+
+        count_query = sqlalchemy.select(sqlalchemy.func.count(persistence_monitoring.MonitoringToolCall.id))
+        if conditions:
+            count_query = count_query.where(sqlalchemy.and_(*conditions))
+
+        count_result = await self.ap.persistence_mgr.execute_async(count_query)
+        total = count_result.scalar() or 0
+
+        query = sqlalchemy.select(persistence_monitoring.MonitoringToolCall).order_by(
+            persistence_monitoring.MonitoringToolCall.timestamp.desc()
+        )
+        if conditions:
+            query = query.where(sqlalchemy.and_(*conditions))
+
+        query = query.limit(limit).offset(offset)
+
+        result = await self.ap.persistence_mgr.execute_async(query)
+        tool_calls_rows = result.all()
+
+        return (
+            [
+                self.ap.persistence_mgr.serialize_model(
+                    persistence_monitoring.MonitoringToolCall, row[0] if isinstance(row, tuple) else row
+                )
+                for row in tool_calls_rows
+            ],
+            total,
+        )
+
     async def get_embedding_calls(
         self,
         start_time: datetime.datetime | None = None,
@@ -971,6 +1143,34 @@ class MonitoringService:
             else:
                 error_llm_calls += 1
 
+        # Get tool calls for this session
+        tool_query = (
+            sqlalchemy.select(persistence_monitoring.MonitoringToolCall)
+            .where(persistence_monitoring.MonitoringToolCall.session_id == session_id)
+            .order_by(persistence_monitoring.MonitoringToolCall.timestamp.asc())
+        )
+        tool_result = await self.ap.persistence_mgr.execute_async(tool_query)
+        tool_rows = tool_result.all()
+
+        tool_calls = [
+            self.ap.persistence_mgr.serialize_model(
+                persistence_monitoring.MonitoringToolCall, row[0] if isinstance(row, tuple) else row
+            )
+            for row in tool_rows
+        ]
+
+        total_tool_calls = len(tool_rows)
+        success_tool_calls = 0
+        error_tool_calls = 0
+        total_tool_duration = 0
+        for row in tool_rows:
+            tool_call = row[0] if isinstance(row, tuple) else row
+            total_tool_duration += tool_call.duration
+            if tool_call.status == 'success':
+                success_tool_calls += 1
+            else:
+                error_tool_calls += 1
+
         # Get errors for this session
         error_query = (
             sqlalchemy.select(persistence_monitoring.MonitoringError)
@@ -1014,6 +1214,14 @@ class MonitoringService:
                 'total_tokens': total_tokens,
                 'average_duration_ms': int(total_duration / total_llm_calls) if total_llm_calls > 0 else 0,
             },
+            'tool_calls': tool_calls,
+            'tool_stats': {
+                'total_calls': total_tool_calls,
+                'success_calls': success_tool_calls,
+                'error_calls': error_tool_calls,
+                'total_duration_ms': total_tool_duration,
+                'average_duration_ms': int(total_tool_duration / total_tool_calls) if total_tool_calls > 0 else 0,
+            },
             'errors': errors,
             'session_duration_seconds': session_duration_seconds,
         }

src/langbot/pkg/entity/persistence/monitoring.py

@@ -49,6 +49,28 @@ class MonitoringLLMCall(Base):
     message_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)  # Associated message ID
 
 
+class MonitoringToolCall(Base):
+    """Tool call records"""
+
+    __tablename__ = 'monitoring_tool_calls'
+
+    id = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
+    timestamp = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, index=True)
+    tool_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    tool_source = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # native, plugin, mcp, skill
+    duration = sqlalchemy.Column(sqlalchemy.Integer, nullable=False)  # milliseconds
+    status = sqlalchemy.Column(sqlalchemy.String(50), nullable=False)  # success, error
+    bot_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    bot_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    pipeline_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, index=True)
+    pipeline_name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
+    session_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    message_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True, index=True)
+    arguments = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    result = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+    error_message = sqlalchemy.Column(sqlalchemy.Text, nullable=True)
+
+
 class MonitoringSession(Base):
     """Session tracking records"""
 

src/langbot/pkg/persistence/migrations/dbm026_monitoring_tool_calls.py

@@ -0,0 +1,17 @@
+from langbot.pkg.entity.persistence import monitoring as persistence_monitoring
+from .. import migration
+
+
+@migration.migration_class(26)
+class DBMigrateMonitoringToolCalls(migration.DBMigration):
+    """Add monitoring_tool_calls table"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        async with self.ap.persistence_mgr.get_db_engine().begin() as conn:
+            await conn.run_sync(persistence_monitoring.MonitoringToolCall.__table__.create, checkfirst=True)
+
+    async def downgrade(self):
+        """Downgrade"""
+        async with self.ap.persistence_mgr.get_db_engine().begin() as conn:
+            await conn.run_sync(persistence_monitoring.MonitoringToolCall.__table__.drop, checkfirst=True)

src/langbot/pkg/platform/adapters/aiocqhttp/adapter.py

@@ -21,7 +21,7 @@ class AiocqhttpAdapter(AiocqhttpAPIMixin, abstract_platform_adapter.AbstractPlat
     bot: aiocqhttp.CQHttp = pydantic.Field(exclude=True)
 
     message_converter: AiocqhttpMessageConverter = AiocqhttpMessageConverter()
-    event_converter: AiocqhttpEventConverter = AiocqhttpEventConverter()
+    event_converter: AiocqhttpEventConverter = pydantic.Field(default_factory=AiocqhttpEventConverter)
 
     config: dict
     listeners: dict[

src/langbot/pkg/platform/adapters/aiocqhttp/event_converter.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import asyncio
+import time
 import typing
 
 import aiocqhttp
@@ -10,6 +12,103 @@ from langbot_plugin.api.entities.builtin.platform import entities as platform_en
 from langbot_plugin.api.entities.builtin.platform import events as platform_events
 
 
+_GROUP_NAME_CACHE_TTL_SECONDS = 3600
+_GROUP_NAME_NEGATIVE_CACHE_TTL_SECONDS = 60
+_GROUP_NAME_LOOKUP_TIMEOUT_SECONDS = 2
+_GROUP_MEMBER_INFO_CACHE_TTL_SECONDS = 86400
+_GROUP_MEMBER_INFO_NEGATIVE_CACHE_TTL_SECONDS = 600
+_GROUP_MEMBER_INFO_LOOKUP_TIMEOUT_SECONDS = 2
+
+_group_name_cache: dict[typing.Union[int, str], tuple[str, float]] = {}
+_group_name_negative_cache: dict[typing.Union[int, str], float] = {}
+_group_member_info_cache: dict[tuple[typing.Union[int, str], typing.Union[int, str]], tuple[dict, float]] = {}
+_group_member_info_negative_cache: dict[tuple[typing.Union[int, str], typing.Union[int, str]], float] = {}
+
+
+def _get_field(data: dict, key: str, default: str = '') -> str:
+    value = data.get(key)
+    if value is None:
+        return default
+    return str(value)
+
+
+def _get_group_member_name(sender: dict) -> str:
+    return _get_field(sender, 'card') or _get_field(sender, 'nickname') or _get_field(sender, 'user_id')
+
+
+def _get_group_name_placeholder(group_id: typing.Union[int, str]) -> str:
+    return f'Group {group_id}'
+
+
+async def _get_group_name(group_id: typing.Union[int, str], bot: aiocqhttp.CQHttp | None = None) -> str:
+    now = time.monotonic()
+    if group_id in _group_name_cache:
+        group_name, expires_at = _group_name_cache[group_id]
+        if expires_at > now:
+            return group_name
+        del _group_name_cache[group_id]
+    if group_id in _group_name_negative_cache:
+        expires_at = _group_name_negative_cache[group_id]
+        if expires_at > now:
+            return ''
+        del _group_name_negative_cache[group_id]
+    if bot is None:
+        return ''
+    try:
+        group_info = await asyncio.wait_for(
+            bot.get_group_info(group_id=group_id),
+            timeout=_GROUP_NAME_LOOKUP_TIMEOUT_SECONDS,
+        )
+    except Exception:
+        _group_name_negative_cache[group_id] = now + _GROUP_NAME_NEGATIVE_CACHE_TTL_SECONDS
+        return ''
+    group_name = _get_field(group_info, 'group_name') if isinstance(group_info, dict) else ''
+    if group_name:
+        _group_name_cache[group_id] = (group_name, now + _GROUP_NAME_CACHE_TTL_SECONDS)
+        _group_name_negative_cache.pop(group_id, None)
+    else:
+        _group_name_negative_cache[group_id] = now + _GROUP_NAME_NEGATIVE_CACHE_TTL_SECONDS
+    return group_name
+
+
+async def _get_group_member_info(
+    group_id: typing.Union[int, str],
+    user_id: typing.Union[int, str],
+    bot: aiocqhttp.CQHttp | None = None,
+) -> dict:
+    now = time.monotonic()
+    cache_key = (group_id, user_id)
+    if cache_key in _group_member_info_cache:
+        member_info, expires_at = _group_member_info_cache[cache_key]
+        if expires_at > now:
+            return member_info
+        del _group_member_info_cache[cache_key]
+    if cache_key in _group_member_info_negative_cache:
+        expires_at = _group_member_info_negative_cache[cache_key]
+        if expires_at > now:
+            return {}
+        del _group_member_info_negative_cache[cache_key]
+    if bot is None:
+        return {}
+    try:
+        member_info = await asyncio.wait_for(
+            bot.get_group_member_info(group_id=group_id, user_id=user_id),
+            timeout=_GROUP_MEMBER_INFO_LOOKUP_TIMEOUT_SECONDS,
+        )
+    except Exception:
+        _group_member_info_negative_cache[cache_key] = now + _GROUP_MEMBER_INFO_NEGATIVE_CACHE_TTL_SECONDS
+        return {}
+    if isinstance(member_info, dict) and member_info:
+        _group_member_info_cache[cache_key] = (
+            member_info,
+            now + _GROUP_MEMBER_INFO_CACHE_TTL_SECONDS,
+        )
+        _group_member_info_negative_cache.pop(cache_key, None)
+        return member_info
+    _group_member_info_negative_cache[cache_key] = now + _GROUP_MEMBER_INFO_NEGATIVE_CACHE_TTL_SECONDS
+    return {}
+
+
 class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
     @staticmethod
     async def yiri2target(event: platform_events.Event, bot_account_id: int | str | None = None):
@@ -25,9 +124,9 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
         if event_type == 'message':
             return await AiocqhttpEventConverter.message_to_eba(event, bot)
         if event_type == 'notice':
-            return AiocqhttpEventConverter.notice_to_eba(event, bot_user_id)
+            return await AiocqhttpEventConverter.notice_to_eba(event, bot, bot_user_id)
         if event_type == 'request':
-            return AiocqhttpEventConverter.request_to_eba(event)
+            return await AiocqhttpEventConverter.request_to_eba(event, bot)
         if event_type == 'meta_event':
             return AiocqhttpEventConverter.platform_specific(event, f'meta.{getattr(event, "detail_type", "")}')
         return None
@@ -60,14 +159,14 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
         if message_type == 'group':
             chat_type = platform_entities.ChatType.GROUP
             chat_id = getattr(event, 'group_id', '')
-            group = AiocqhttpEventConverter.group_from_event(event)
+            group = await AiocqhttpEventConverter.group_from_event(event, bot)
 
         return platform_events.MessageReceivedEvent(
             type='message.received',
             adapter_name='aiocqhttp',
             message_id=getattr(event, 'message_id', ''),
             message_chain=message_chain,
-            sender=AiocqhttpEventConverter.user_from_sender(event),
+            sender=await AiocqhttpEventConverter.user_from_sender(event, bot),
             chat_type=chat_type,
             chat_id=chat_id,
             group=group,
@@ -76,8 +175,9 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
         )
 
     @staticmethod
-    def notice_to_eba(
+    async def notice_to_eba(
         event: aiocqhttp.Event,
+        bot: aiocqhttp.CQHttp | None = None,
         bot_user_id: int | str | None = None,
     ) -> platform_events.EBAEvent:
         notice_type = getattr(event, 'notice_type', getattr(event, 'detail_type', ''))
@@ -91,12 +191,14 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 if notice_type == 'group_recall'
                 else platform_entities.ChatType.PRIVATE,
                 chat_id=getattr(event, 'group_id', getattr(event, 'user_id', '')),
-                group=AiocqhttpEventConverter.group_from_event(event) if notice_type == 'group_recall' else None,
+                group=await AiocqhttpEventConverter.group_from_event(event, bot)
+                if notice_type == 'group_recall'
+                else None,
                 timestamp=float(getattr(event, 'time', 0) or 0),
                 source_platform_object=event,
             )
         if notice_type == 'group_increase':
-            group = AiocqhttpEventConverter.group_from_event(event)
+            group = await AiocqhttpEventConverter.group_from_event(event, bot)
             user = AiocqhttpEventConverter.user(getattr(event, 'user_id', ''))
             inviter_id = getattr(event, 'operator_id', None)
             if AiocqhttpEventConverter._is_bot_user(getattr(event, 'user_id', None), bot_user_id, event):
@@ -119,7 +221,7 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 source_platform_object=event,
             )
         if notice_type == 'group_decrease':
-            group = AiocqhttpEventConverter.group_from_event(event)
+            group = await AiocqhttpEventConverter.group_from_event(event, bot)
             operator = AiocqhttpEventConverter.user(getattr(event, 'operator_id', None))
             if AiocqhttpEventConverter._is_bot_user(getattr(event, 'user_id', None), bot_user_id, event):
                 return platform_events.BotRemovedFromGroupEvent(
@@ -141,7 +243,7 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
                 source_platform_object=event,
             )
         if notice_type == 'group_ban':
-            group = AiocqhttpEventConverter.group_from_event(event)
+            group = await AiocqhttpEventConverter.group_from_event(event, bot)
             duration = int(getattr(event, 'duration', 0) or 0)
             operator = AiocqhttpEventConverter.user(getattr(event, 'operator_id', None))
             if AiocqhttpEventConverter._is_bot_user(getattr(event, 'user_id', None), bot_user_id, event):
@@ -179,7 +281,10 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
         return AiocqhttpEventConverter.platform_specific(event, f'notice.{notice_type}')
 
     @staticmethod
-    def request_to_eba(event: aiocqhttp.Event) -> platform_events.EBAEvent:
+    async def request_to_eba(
+        event: aiocqhttp.Event,
+        bot: aiocqhttp.CQHttp | None = None,
+    ) -> platform_events.EBAEvent:
         request_type = getattr(event, 'request_type', getattr(event, 'detail_type', ''))
         if request_type == 'friend':
             return platform_events.FriendRequestReceivedEvent(
@@ -195,7 +300,7 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
             return platform_events.BotInvitedToGroupEvent(
                 type='bot.invited_to_group',
                 adapter_name='aiocqhttp',
-                group=AiocqhttpEventConverter.group_from_event(event),
+                group=await AiocqhttpEventConverter.group_from_event(event, bot),
                 inviter=AiocqhttpEventConverter.user(getattr(event, 'user_id', '')),
                 request_id=getattr(event, 'flag', ''),
                 timestamp=float(getattr(event, 'time', 0) or 0),
@@ -204,13 +309,28 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
         return AiocqhttpEventConverter.platform_specific(event, f'request.{request_type}')
 
     @staticmethod
-    def user_from_sender(event: aiocqhttp.Event) -> platform_entities.User:
+    async def user_from_sender(
+        event: aiocqhttp.Event,
+        bot: aiocqhttp.CQHttp | None = None,
+    ) -> platform_entities.User:
         sender = getattr(event, 'sender', {}) or {}
-        nickname = sender.get('card') or sender.get('nickname') or ''
+        user_id = sender.get('user_id', getattr(event, 'user_id', ''))
+        has_sender_display_name = bool(_get_field(sender, 'card') or _get_field(sender, 'nickname'))
+        nickname = _get_group_member_name(sender)
+        remark = sender.get('remark')
+        if (
+            getattr(event, 'message_type', getattr(event, 'detail_type', 'private')) == 'group'
+            and user_id
+            and (not has_sender_display_name or not remark)
+        ):
+            member_info = await _get_group_member_info(getattr(event, 'group_id', ''), user_id, bot)
+            remark = _get_field(member_info, 'card') or _get_field(member_info, 'remark') or None
+            if not has_sender_display_name:
+                nickname = _get_group_member_name(member_info) or nickname
         return platform_entities.User(
-            id=sender.get('user_id', getattr(event, 'user_id', '')),
+            id=user_id,
             nickname=nickname,
-            remark=sender.get('remark'),
+            remark=remark,
         )
 
     @staticmethod
@@ -220,10 +340,19 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
         return platform_entities.User(id=user_id, nickname=nickname)
 
     @staticmethod
-    def group_from_event(event: aiocqhttp.Event) -> platform_entities.UserGroup:
+    async def group_from_event(
+        event: aiocqhttp.Event,
+        bot: aiocqhttp.CQHttp | None = None,
+    ) -> platform_entities.UserGroup:
+        group_id = getattr(event, 'group_id', '')
+        group_name = getattr(event, 'group_name', '') or ''
+        if group_id and not group_name:
+            group_name = await _get_group_name(group_id, bot)
+        if group_id and not group_name:
+            group_name = _get_group_name_placeholder(group_id)
         return platform_entities.UserGroup(
-            id=getattr(event, 'group_id', ''),
-            name=getattr(event, 'group_name', '') or '',
+            id=group_id,
+            name=group_name,
             member_count=getattr(event, 'member_count', None),
         )
 

src/langbot/pkg/platform/adapters/wecomcs/adapter.py

@@ -101,11 +101,13 @@ class WecomCSAdapter(WecomCSAPIMixin, abstract_platform_adapter.AbstractPlatform
         if target_type not in ('person', 'private'):
             raise NotSupportedError(f'send_message:{target_type}')
 
-        external_userid, open_kfid = parse_private_chat_id(target_id)
+        external_userid, open_kfid = parse_private_chat_id(target_id, self.bot_account_id)
         content_list = await WecomCSMessageConverter.yiri2target(message, self.bot)
         raw_results = []
         for content in content_list:
-            raw_results.append(await self._send_content(open_kfid, external_userid, self._make_outbound_msgid(), content))
+            raw_results.append(
+                await self._send_content(open_kfid, external_userid, self._make_outbound_msgid(), content)
+            )
         return platform_events.MessageResult(raw={'results': raw_results})
 
     async def reply_message(

src/langbot/pkg/platform/adapters/wecomcs/event_converter.py

@@ -17,7 +17,9 @@ class WecomCSEventConverter(abstract_platform_adapter.AbstractEventConverter):
         return getattr(event, 'source_platform_object', None)
 
     @staticmethod
-    async def target2legacy(event: WecomCSEvent, bot: WecomCSClient | None = None) -> platform_events.FriendMessage | None:
+    async def target2legacy(
+        event: WecomCSEvent, bot: WecomCSClient | None = None
+    ) -> platform_events.FriendMessage | None:
         eba_event = await WecomCSEventConverter.target2yiri(event, bot)
         if hasattr(eba_event, 'to_legacy_event'):
             return eba_event.to_legacy_event()
@@ -30,7 +32,9 @@ class WecomCSEventConverter(abstract_platform_adapter.AbstractEventConverter):
         return WecomCSEventConverter.platform_specific(event, f'wecomcs.{event.type or "unknown"}')
 
     @staticmethod
-    async def message_to_eba(event: WecomCSEvent, bot: WecomCSClient | None = None) -> platform_events.MessageReceivedEvent:
+    async def message_to_eba(
+        event: WecomCSEvent, bot: WecomCSClient | None = None
+    ) -> platform_events.MessageReceivedEvent:
         message_chain = await WecomCSMessageConverter.target2yiri(event)
         sender = await WecomCSEventConverter.user_from_event(event, bot)
         return platform_events.MessageReceivedEvent(

src/langbot/pkg/platform/adapters/wecomcs/types.py

@@ -12,8 +12,29 @@ def make_private_chat_id(user_id: str | int | None, open_kfid: str | int | None)
     return f'{user}|{kfid}'
 
 
-def parse_private_chat_id(chat_id: str | int) -> tuple[str, str]:
-    user_id, sep, open_kfid = str(chat_id).partition('|')
-    if not user_id or not sep or not open_kfid:
-        raise ValueError('WeComCS target_id must be formatted as "external_userid|open_kfid"')
+def _strip_legacy_user_prefix(user_id: str) -> str:
+    if user_id.startswith('u'):
+        return user_id[1:]
+    return user_id
+
+
+def _looks_like_open_kfid(value: str) -> bool:
+    return value.startswith(('kf', 'wk', 'open_kfid'))
+
+
+def parse_private_chat_id(chat_id: str | int, default_open_kfid: str | int | None = None) -> tuple[str, str]:
+    raw = str(chat_id)
+    left, sep, right = raw.partition('|')
+    if sep:
+        if _looks_like_open_kfid(left) or right.startswith('u'):
+            open_kfid, user_id = left, right
+        else:
+            user_id, open_kfid = left, right
+    else:
+        user_id = raw
+        open_kfid = str(default_open_kfid or '')
+    user_id = _strip_legacy_user_prefix(str(user_id or ''))
+    open_kfid = str(open_kfid or '')
+    if not user_id or not open_kfid:
+        raise ValueError('WeComCS target_id must include external_userid and open_kfid')
     return user_id, open_kfid

src/langbot/pkg/platform/sources/aiocqhttp.py

@@ -4,6 +4,7 @@ import asyncio
 import traceback
 import datetime
 import json
+import time
 
 import aiocqhttp
 import pydantic
@@ -16,6 +17,14 @@ from ...utils import image
 import langbot_plugin.api.definition.abstract.platform.event_logger as abstract_platform_logger
 
 
+_GROUP_NAME_CACHE_TTL_SECONDS = 3600
+_GROUP_NAME_NEGATIVE_CACHE_TTL_SECONDS = 60
+_GROUP_NAME_LOOKUP_TIMEOUT_SECONDS = 2
+_GROUP_MEMBER_INFO_CACHE_TTL_SECONDS = 86400
+_GROUP_MEMBER_INFO_NEGATIVE_CACHE_TTL_SECONDS = 600
+_GROUP_MEMBER_INFO_LOOKUP_TIMEOUT_SECONDS = 2
+
+
 def _normalize_base64_payload(value: str) -> str:
     if value.startswith('base64://'):
         return value.removeprefix('base64://')
@@ -24,6 +33,21 @@ def _normalize_base64_payload(value: str) -> str:
     return value
 
 
+def _get_field(data: dict, key: str, default: str = '') -> str:
+    value = data.get(key)
+    if value is None:
+        return default
+    return str(value)
+
+
+def _get_group_member_name(sender: dict) -> str:
+    return _get_field(sender, 'card') or _get_field(sender, 'nickname') or _get_field(sender, 'user_id')
+
+
+def _get_group_name_placeholder(group_id: typing.Union[int, str]) -> str:
+    return f'Group {group_id}'
+
+
 class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
     @staticmethod
     async def yiri2target(
@@ -335,16 +359,96 @@ class AiocqhttpMessageConverter(abstract_platform_adapter.AbstractMessageConvert
 
 
 class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
+    def __init__(self):
+        self._group_name_cache: dict[typing.Union[int, str], tuple[str, float]] = {}
+        self._group_name_negative_cache: dict[typing.Union[int, str], float] = {}
+        self._group_member_info_cache: dict[
+            tuple[typing.Union[int, str], typing.Union[int, str]], tuple[dict, float]
+        ] = {}
+        self._group_member_info_negative_cache: dict[tuple[typing.Union[int, str], typing.Union[int, str]], float] = {}
+
     @staticmethod
     async def yiri2target(event: platform_events.MessageEvent, bot_account_id: int):
         return event.source_platform_object
 
-    @staticmethod
-    async def target2yiri(event: aiocqhttp.Event, bot=None):
+    async def _get_group_name(self, group_id: typing.Union[int, str], bot=None) -> str:
+        now = time.monotonic()
+        if group_id in self._group_name_cache:
+            group_name, expires_at = self._group_name_cache[group_id]
+            if expires_at > now:
+                return group_name
+            del self._group_name_cache[group_id]
+        if group_id in self._group_name_negative_cache:
+            expires_at = self._group_name_negative_cache[group_id]
+            if expires_at > now:
+                return ''
+            del self._group_name_negative_cache[group_id]
+        if bot is None:
+            return ''
+        try:
+            group_info = await asyncio.wait_for(
+                bot.get_group_info(group_id=group_id),
+                timeout=_GROUP_NAME_LOOKUP_TIMEOUT_SECONDS,
+            )
+        except Exception:
+            self._group_name_negative_cache[group_id] = now + _GROUP_NAME_NEGATIVE_CACHE_TTL_SECONDS
+            return ''
+        group_name = _get_field(group_info, 'group_name') if isinstance(group_info, dict) else ''
+        if group_name:
+            self._group_name_cache[group_id] = (group_name, now + _GROUP_NAME_CACHE_TTL_SECONDS)
+            self._group_name_negative_cache.pop(group_id, None)
+        else:
+            self._group_name_negative_cache[group_id] = now + _GROUP_NAME_NEGATIVE_CACHE_TTL_SECONDS
+        return group_name
+
+    async def _get_group_member_info(
+        self,
+        group_id: typing.Union[int, str],
+        user_id: typing.Union[int, str],
+        bot=None,
+    ) -> dict:
+        now = time.monotonic()
+        cache_key = (group_id, user_id)
+        if cache_key in self._group_member_info_cache:
+            member_info, expires_at = self._group_member_info_cache[cache_key]
+            if expires_at > now:
+                return member_info
+            del self._group_member_info_cache[cache_key]
+        if cache_key in self._group_member_info_negative_cache:
+            expires_at = self._group_member_info_negative_cache[cache_key]
+            if expires_at > now:
+                return {}
+            del self._group_member_info_negative_cache[cache_key]
+        if bot is None:
+            return {}
+        try:
+            member_info = await asyncio.wait_for(
+                bot.get_group_member_info(group_id=group_id, user_id=user_id),
+                timeout=_GROUP_MEMBER_INFO_LOOKUP_TIMEOUT_SECONDS,
+            )
+        except Exception:
+            self._group_member_info_negative_cache[cache_key] = now + _GROUP_MEMBER_INFO_NEGATIVE_CACHE_TTL_SECONDS
+            return {}
+        if isinstance(member_info, dict) and member_info:
+            self._group_member_info_cache[cache_key] = (
+                member_info,
+                now + _GROUP_MEMBER_INFO_CACHE_TTL_SECONDS,
+            )
+            self._group_member_info_negative_cache.pop(cache_key, None)
+            return member_info
+        self._group_member_info_negative_cache[cache_key] = now + _GROUP_MEMBER_INFO_NEGATIVE_CACHE_TTL_SECONDS
+        return {}
+
+    async def target2yiri(self, event: aiocqhttp.Event, bot=None):
         yiri_chain = await AiocqhttpMessageConverter.target2yiri(event.message, event.message_id, bot)
 
         if event.message_type == 'group':
             permission = 'MEMBER'
+            group_name = await self._get_group_name(event.group_id, bot) or _get_group_name_placeholder(event.group_id)
+            special_title = _get_field(event.sender, 'title')
+            if not special_title:
+                member_info = await self._get_group_member_info(event.group_id, event.sender['user_id'], bot)
+                special_title = _get_field(member_info, 'title')
 
             if 'role' in event.sender:
                 if event.sender['role'] == 'admin':
@@ -354,14 +458,14 @@ class AiocqhttpEventConverter(abstract_platform_adapter.AbstractEventConverter):
             converted_event = platform_events.GroupMessage(
                 sender=platform_entities.GroupMember(
                     id=event.sender['user_id'],  # message_seq 放哪？
-                    member_name=event.sender['nickname'],
+                    member_name=_get_group_member_name(event.sender),
                     permission=permission,
                     group=platform_entities.Group(
                         id=event.group_id,
-                        name=event.sender['nickname'],
+                        name=group_name,
                         permission=platform_entities.Permission.Member,
                     ),
-                    special_title=event.sender['title'] if 'title' in event.sender else '',
+                    special_title=special_title,
                 ),
                 message_chain=yiri_chain,
                 time=event.time,
@@ -385,7 +489,7 @@ class AiocqhttpAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter)
     bot: aiocqhttp.CQHttp = pydantic.Field(exclude=True, default_factory=aiocqhttp.CQHttp)
 
     message_converter: AiocqhttpMessageConverter = AiocqhttpMessageConverter()
-    event_converter: AiocqhttpEventConverter = AiocqhttpEventConverter()
+    event_converter: AiocqhttpEventConverter = pydantic.Field(default_factory=AiocqhttpEventConverter)
 
     on_websocket_connection_event_cache: typing.List[typing.Callable[[aiocqhttp.Event], None]] = []
 

src/langbot/pkg/platform/sources/wecomcs.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 import typing
 import asyncio
 import traceback
+import uuid
 
 import datetime
 import pydantic
@@ -182,7 +183,28 @@ class WecomCSAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 )
 
     async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
-        pass
+        if target_type != 'person':
+            raise ValueError('WeCom customer service only supports sending messages to person targets')
+
+        open_kfid = self.bot_account_id
+        external_userid = target_id
+        if '|' in target_id:
+            open_kfid, external_userid = target_id.split('|', 1)
+        if external_userid.startswith('u'):
+            external_userid = external_userid[1:]
+        if not open_kfid:
+            raise ValueError('WeCom customer service open_kfid is required before sending messages')
+
+        content_list = await WecomMessageConverter.yiri2target(message, self.bot)
+        for content in content_list:
+            msgid = f'langbot_{uuid.uuid4().hex}'
+            if content['type'] == 'text':
+                await self.bot.send_text_msg(
+                    open_kfid=open_kfid,
+                    external_userid=external_userid,
+                    msgid=msgid,
+                    content=content['content'],
+                )
 
     def set_bot_uuid(self, bot_uuid: str):
         """设置 bot UUID（用于生成 webhook URL）"""

src/langbot/pkg/provider/tools/loaders/mcp.py

@@ -25,7 +25,7 @@ from ....core import app
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 from ....entity.persistence import mcp as persistence_mcp
-from .mcp_stdio import BoxStdioSessionRuntime, MCPServerBoxConfig, MCPSessionErrorPhase  # noqa: F401
+from .mcp_stdio import BoxStdioSessionRuntime, MCPServerBoxConfig, MCPSessionErrorPhase, _ColdStartRetry  # noqa: F401
 
 # Synthesized LLM tools for MCP resources (not from server tools/list).
 # Dispatched in MCPLoader.invoke_tool; placeholder func on LLMTool is never used.
@@ -185,6 +185,16 @@ class MCPSessionStatus(enum.Enum):
     ERROR = 'error'
 
 
+class _TransportReconnect(Exception):
+    """Internal signal: the Box stdio WS transport dropped but the managed
+    process is still alive. Triggers a lightweight transport reconnect that
+    reuses the live process, instead of a full process rebuild.
+
+    Reconnect attempts are NOT counted toward the fatal retry budget, so a
+    long-lived session can survive arbitrarily many transient drops.
+    """
+
+
 class RuntimeMCPSession:
     """运行时 MCP 会话"""
 
@@ -254,6 +264,16 @@ class RuntimeMCPSession:
         self._lifecycle_task = None
         self._shutdown_event = asyncio.Event()
         self._ready_event = asyncio.Event()
+        # Set transiently when a WS transport drop should NOT stop the managed
+        # process (it will be re-attached on the next initialize()).
+        self._preserve_managed_process = False
+
+        # Log buffer for capturing stderr from Box managed process (maxlen=500 keeps
+        # recent lines without unbounded memory growth)
+        import collections as _collections
+
+        self._log_buffer: _collections.deque = _collections.deque(maxlen=500)
+        self._last_stderr_text: str = ''
 
         self._box_stdio_runtime = BoxStdioSessionRuntime(self)
         self.box_config = self._box_stdio_runtime.config
@@ -399,11 +419,39 @@ class RuntimeMCPSession:
                     task.cancel()
                 for task in done:
                     if task is monitor_task and not self._shutdown_event.is_set():
+                        # The monitor completed. This is EITHER the managed
+                        # process actually exiting OR just the WS transport
+                        # dropping while the process stays alive in the Box
+                        # runtime. Re-check the real process state so a
+                        # transient transport drop reconnects (reusing the live
+                        # process) instead of tearing the process down and
+                        # running a full rebuild+backoff cycle.
+                        process_still_running = False
+                        try:
+                            process_still_running = await self._box_stdio_runtime._managed_process_is_running()
+                        except Exception:
+                            process_still_running = False
+                        if process_still_running:
+                            self.ap.logger.info(
+                                f'MCP server {self.server_name}: transport dropped but '
+                                f'managed process is still running; reconnecting transport'
+                            )
+                            self.error_phase = MCPSessionErrorPhase.RELAY_CONNECT
+                            # Preserve the live process across the finally-block
+                            # cleanup: only the WS transport should be torn down.
+                            self._preserve_managed_process = True
+                            raise _TransportReconnect('Box managed process transport dropped; reconnecting')
                         self.error_phase = MCPSessionErrorPhase.RUNTIME
                         raise Exception('Box managed process exited unexpectedly')
             else:
                 await self._shutdown_event.wait()
 
+        except _ColdStartRetry:
+            # Cold-start in progress: set the preserve flag BEFORE the finally
+            # block runs so it does not stop the live managed process. The outer
+            # _lifecycle_loop_with_retry will reuse it on the next attempt.
+            self._preserve_managed_process = True
+            raise
         except Exception as e:
             self.status = MCPSessionStatus.ERROR
             self.error_message = str(e)
@@ -424,14 +472,55 @@ class RuntimeMCPSession:
             except Exception as e:
                 self.ap.logger.error(f'Error cleaning up MCP session {self.server_name}: {e}\n{traceback.format_exc()}')
             finally:
-                await self._cleanup_box_stdio_session()
+                # On a transport-only reconnect the managed process is healthy
+                # and will be re-attached on the next initialize(); do NOT stop
+                # it. Any other exit path fully tears the session down.
+                if getattr(self, '_preserve_managed_process', False):
+                    self._preserve_managed_process = False
+                else:
+                    await self._cleanup_box_stdio_session()
 
     async def _lifecycle_loop_with_retry(self):
         """Wrap _lifecycle_loop with retry and exponential backoff."""
-        for attempt in range(self._MAX_RETRIES + 1):
+        attempt = 0
+        while attempt <= self._MAX_RETRIES:
             try:
                 await self._lifecycle_loop()
                 return  # Normal shutdown, don't retry
+            except _TransportReconnect as e:
+                # Transient WS transport drop while the managed process is still
+                # alive. Reconnect promptly WITHOUT consuming the fatal retry
+                # budget and WITHOUT stopping the process — initialize() will
+                # re-attach to the live process. This is what lets a long-lived
+                # stdio MCP survive repeated brief event-loop stalls / pings.
+                if self._shutdown_event.is_set():
+                    return
+                self.ap.logger.info(
+                    f'MCP session {self.server_name}: reconnecting transport ({self._describe_exception(e)})'
+                )
+                self.status = MCPSessionStatus.CONNECTING
+                self.error_message = None
+                self.error_phase = None
+                await asyncio.sleep(1)
+                continue
+            except _ColdStartRetry as e:
+                # The managed process is alive but still cold-starting (e.g.
+                # `npx -y <pkg>` is still installing) and cannot yet answer the
+                # handshake. Reuse the live process and retry the attach WITHOUT
+                # consuming the fatal retry budget or stopping the process, so a
+                # slow cold start is waited out instead of failing. Preserve the
+                # process across the finally-block cleanup.
+                if self._shutdown_event.is_set():
+                    return
+                self._preserve_managed_process = True
+                self.ap.logger.debug(
+                    f'MCP session {self.server_name}: waiting for cold start ({self._describe_exception(e)})'
+                )
+                self.status = MCPSessionStatus.CONNECTING
+                self.error_message = None
+                self.error_phase = None
+                await asyncio.sleep(2)
+                continue
             except Exception as e:
                 self.retry_count = attempt + 1
                 if self._shutdown_event.is_set():
@@ -460,6 +549,7 @@ class RuntimeMCPSession:
                 self.error_message = None
                 self.error_phase = None
                 await asyncio.sleep(delay)
+                attempt += 1
 
     @staticmethod
     def _describe_exception(exc: BaseException) -> str:
@@ -927,11 +1017,14 @@ class RuntimeMCPSession:
         return self._box_stdio_runtime.uses_box_stdio()
 
     def _build_box_session_id(self) -> str:
-        # Transient test sessions get their own isolated Box session so a
-        # failing/short-lived test can never disturb the shared session that
-        # hosts live, already-connected MCP servers.
-        if self.is_transient:
-            return f'mcp-test-{self.server_uuid}'
+        # Both live servers and transient config-page tests share ONE Box
+        # session ('mcp-shared'). A test therefore reuses the already-running
+        # container (and, for an existing server, its live managed process)
+        # instead of paying a full per-test session cold-start + dependency
+        # bootstrap. Isolation between a test and the live servers is provided
+        # at the *process* level: each server/test has its own process_id and a
+        # test only ever stops its own process_id (see cleanup_session), so it
+        # never disturbs another server's process or the shared session itself.
         return 'mcp-shared'
 
     def _rewrite_path(self, path: str, host_path: str | None) -> str:

src/langbot/pkg/provider/tools/loaders/mcp_stdio.py

@@ -6,7 +6,7 @@ import os
 import shutil
 import shlex
 import threading
-from contextlib import suppress
+from contextlib import suppress, AsyncExitStack
 from typing import TYPE_CHECKING, Any
 
 import pydantic
@@ -74,6 +74,35 @@ class MCPServerBoxConfig(pydantic.BaseModel):
     model_config = pydantic.ConfigDict(extra='ignore')
 
 
+_HANDSHAKE_ATTEMPT_TIMEOUT_SEC = 10.0
+
+
+class _TransferredStack:
+    """Adapts an already-populated AsyncExitStack into an async context manager
+    so ownership of its resources can be transferred into another exit stack.
+    Entering is a no-op; exiting closes the wrapped stack (and thus the live WS
+    transport + ClientSession) when the owning session shuts down."""
+
+    def __init__(self, stack: AsyncExitStack):
+        self._stack = stack
+
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, exc_type, exc, tb):
+        await self._stack.aclose()
+        return False
+
+
+class _ColdStartRetry(Exception):
+    """Signal: the managed process is alive but not yet answering the MCP
+    handshake because it is still cold-starting (e.g. `npx -y <pkg>` is still
+    installing). The outer lifecycle retry treats this like a transient
+    reconnect: it reuses the live process and does not count toward the fatal
+    retry budget, so a slow cold start is waited out rather than failing.
+    """
+
+
 class BoxStdioSessionRuntime:
     """Encapsulate Box-backed stdio MCP session orchestration."""
 
@@ -173,28 +202,55 @@ class BoxStdioSessionRuntime:
                     stderr_preview = (result.stderr or '')[:500]
                     raise Exception(f'Dependency install failed (exit code {result.exit_code}): {stderr_preview}')
 
-        try:
-            process_workspace = (
-                self._build_workspace(host_path=host_path, workdir=process_cwd, mount_path=process_cwd)
-                if host_path
-                else workspace
+        # Reuse an already-running managed process instead of rebuilding it.
+        # The Box runtime keeps the managed process alive across a transient
+        # WebSocket transport drop, so on a reconnect we only need to re-attach
+        # the WS below. Rebuilding here would needlessly stop a healthy process
+        # and re-run the (slow, network-touching) dependency bootstrap.
+        if not await self._managed_process_is_running():
+            try:
+                process_workspace = (
+                    self._build_workspace(host_path=host_path, workdir=process_cwd, mount_path=process_cwd)
+                    if host_path
+                    else workspace
+                )
+                payload = process_workspace.build_process_payload(
+                    self.server_config['command'],
+                    self.server_config.get('args', []),
+                    env=self.server_config.get('env', {}),
+                    cwd=process_cwd,
+                )
+                if install_cmd:
+                    payload = self._wrap_process_payload_with_python_env(payload, process_cwd)
+                payload['process_id'] = self.process_id
+                await workspace.box_service.start_managed_process(workspace.session_id, payload)
+            except Exception:
+                self.owner.error_phase = MCPSessionErrorPhase.PROCESS_START
+                raise
+        else:
+            self.ap.logger.info(
+                f'MCP server {self.server_name}: reusing live managed process '
+                f'process_id={self.process_id} (transport reconnect)'
             )
-            payload = process_workspace.build_process_payload(
-                self.server_config['command'],
-                self.server_config.get('args', []),
-                env=self.server_config.get('env', {}),
-                cwd=process_cwd,
-            )
-            if install_cmd:
-                payload = self._wrap_process_payload_with_python_env(payload, process_cwd)
-            payload['process_id'] = self.process_id
-            await workspace.box_service.start_managed_process(workspace.session_id, payload)
-        except Exception:
-            self.owner.error_phase = MCPSessionErrorPhase.PROCESS_START
-            raise
 
+        websocket_url = workspace.get_managed_process_websocket_url(self.process_id)
+
+        # Attach the WS transport + MCP session ONCE, on the owner's exit stack,
+        # in the same task as the serve loop that follows. websocket_client and
+        # ClientSession use anyio task groups whose cancel scope is bound to the
+        # frame/stack that entered them, so they must live on the owner exit
+        # stack (not a deferred/transferred one) or the streams close the moment
+        # initialize() returns and the next request fails with "Connection
+        # closed".
+        #
+        # A slow (`npx -y <pkg>`) cold start makes this single attempt fail
+        # while the process is still alive — the package is still installing and
+        # cannot answer the handshake. We surface that to the outer retry loop
+        # as a _ColdStartRetry: it must NOT stop the process (it is healthy and
+        # will be reused) and must NOT consume the fatal retry budget. The next
+        # attempt re-attaches to the same live process; once it has finished
+        # cold start the handshake succeeds and stays healthy.
         try:
-            websocket_url = workspace.get_managed_process_websocket_url(self.process_id)
             transport = await self.owner.exit_stack.enter_async_context(websocket_client(websocket_url))
             read_stream, write_stream = transport
             self.owner.session = await self.owner.exit_stack.enter_async_context(
@@ -202,12 +258,19 @@ class BoxStdioSessionRuntime:
             )
         except Exception:
             self.owner.error_phase = MCPSessionErrorPhase.RELAY_CONNECT
+            if not await self._managed_process_has_exited():
+                # Process is alive but not yet serving (cold start) — reconnect.
+                raise _ColdStartRetry(f'{self.server_name}: transport not ready during cold start')
             raise
 
         try:
-            await self.owner.session.initialize()
-        except Exception:
+            await asyncio.wait_for(self.owner.session.initialize(), timeout=_HANDSHAKE_ATTEMPT_TIMEOUT_SEC)
+        except Exception as exc:
             self.owner.error_phase = MCPSessionErrorPhase.MCP_INIT
+            if not await self._managed_process_has_exited():
+                raise _ColdStartRetry(
+                    f'{self.server_name}: handshake not ready during cold start ({type(exc).__name__})'
+                )
             raise
 
     async def monitor_process_health(self) -> None:
@@ -234,8 +297,74 @@ class BoxStdioSessionRuntime:
                 )
                 if consecutive_errors >= self.owner._MONITOR_MAX_CONSECUTIVE_ERRORS:
                     return
+
+            # Capture stderr logs from the managed process
+            if isinstance(info, dict):
+                stderr_text = info.get('stderr', '') or info.get('stderr_preview', '')
+            else:
+                stderr_text = getattr(info, 'stderr', '') or getattr(info, 'stderr_preview', '')
+
+            if stderr_text and stderr_text != self.owner._last_stderr_text:
+                # Find new lines not in the previous snapshot
+                old_lines = set(self.owner._last_stderr_text.splitlines()) if self.owner._last_stderr_text else set()
+                new_lines = [l for l in stderr_text.splitlines() if l and l not in old_lines]
+                self.owner._last_stderr_text = stderr_text
+
+                import time as _time
+
+                for line in new_lines:
+                    level = (
+                        'error'
+                        if any(k in line.upper() for k in ('ERROR', 'CRITICAL'))
+                        else 'warning'
+                        if 'WARNING' in line.upper()
+                        else 'debug'
+                        if 'DEBUG' in line.upper()
+                        else 'info'
+                    )
+                    self.owner._log_buffer.append({'ts': _time.time(), 'level': level, 'text': line})
+
             await asyncio.sleep(self.owner._MONITOR_POLL_INTERVAL)
 
+    async def _managed_process_is_running(self) -> bool:
+        """Return True if this server's managed process exists and is running.
+
+        Used to decide whether initialize() must (re)start the process or can
+        simply re-attach the WebSocket transport to a process the Box runtime
+        kept alive across a transient transport drop.
+        """
+        from langbot_plugin.box.models import BoxManagedProcessStatus
+
+        workspace = self._build_workspace()
+        try:
+            info = await workspace.get_managed_process(self.process_id)
+        except Exception:
+            return False
+        status = info.get('status', '') if isinstance(info, dict) else getattr(info, 'status', '')
+        return status in (BoxManagedProcessStatus.RUNNING.value, BoxManagedProcessStatus.RUNNING)
+
+    async def _managed_process_has_exited(self) -> bool:
+        """Return True only if the process is DEFINITIVELY gone (reports EXITED).
+
+        Distinct from ``not _managed_process_is_running()``: a process that has
+        just been spawned may not yet report RUNNING, and a transient query
+        error is not proof of exit. During the cold-start handshake retry we
+        must NOT treat 'not yet running' or 'query failed' as a terminal
+        failure, or we bail out to the outer rebuild path and churn the
+        process (relay then rejects the early re-attach with HTTP 400). Only a
+        successful query that reports EXITED stops the retry loop.
+        """
+        from langbot_plugin.box.models import BoxManagedProcessStatus
+
+        workspace = self._build_workspace()
+        try:
+            info = await workspace.get_managed_process(self.process_id)
+        except Exception:
+            # Unknown — treat as 'still coming up', not exited.
+            return False
+        status = info.get('status', '') if isinstance(info, dict) else getattr(info, 'status', '')
+        return status in (BoxManagedProcessStatus.EXITED.value, BoxManagedProcessStatus.EXITED)
+
     async def _stage_host_path_to_shared_workspace(self, host_path: str) -> str:
         source_path = normalize_host_path(host_path)
         if not source_path:
@@ -342,16 +471,20 @@ class BoxStdioSessionRuntime:
 
         workspace = self._build_workspace(host_path=None)
 
-        # Transient test sessions own their isolated Box session, so tear the
-        # whole session down rather than leaking it. This cannot affect live
-        # servers because they live in the separate shared session.
+        # Transient config-page tests now share the same 'mcp-shared' Box
+        # session as live servers, so we must NOT tear the session down here —
+        # that would kill every other MCP server in the container. A test is
+        # isolated at the process level: it ran under its own process_id, so we
+        # stop only that process, exactly like a live server does below. The
+        # shared session and all other servers' live processes are untouched.
+        # (Staged per-test workspace files are still cleaned up.)
         if getattr(self.owner, 'is_transient', False):
             try:
-                await workspace.cleanup()
+                await workspace.stop_managed_process(self.process_id)
             except Exception as exc:
                 self.ap.logger.warning(
-                    f'MCP server {self.server_name}: failed to delete transient test session '
-                    f'{self.owner._build_box_session_id()}: {type(exc).__name__}: {exc}'
+                    f'MCP server {self.server_name}: failed to stop transient test process '
+                    f'process_id={self.process_id}: {type(exc).__name__}: {exc}'
                 )
             await self._cleanup_staged_workspace()
             return

src/langbot/pkg/provider/tools/toolmgr.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import typing
+import time
 from typing import TYPE_CHECKING
 
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
@@ -175,21 +176,130 @@ class ToolManager:
 
         return tools
 
+    def _get_query_session_id(self, query: pipeline_query.Query) -> str | None:
+        launcher_type = getattr(query, 'launcher_type', None)
+        launcher_id = getattr(query, 'launcher_id', None)
+        if launcher_type is None or launcher_id is None:
+            return None
+
+        launcher_type_value = launcher_type.value if hasattr(launcher_type, 'value') else launcher_type
+        return f'{launcher_type_value}_{launcher_id}'
+
+    async def _record_tool_call(
+        self,
+        *,
+        name: str,
+        source: str,
+        parameters: dict,
+        query: pipeline_query.Query,
+        duration_ms: int,
+        status: str,
+        result: typing.Any = None,
+        error_message: str | None = None,
+    ) -> None:
+        monitoring_service = getattr(self.ap, 'monitoring_service', None)
+        if not monitoring_service:
+            return
+
+        variables = getattr(query, 'variables', {}) or {}
+        message_id = variables.get('_monitoring_message_id') if isinstance(variables, dict) else None
+        bot_name = variables.get('_monitoring_bot_name') if isinstance(variables, dict) else None
+        pipeline_name = variables.get('_monitoring_pipeline_name') if isinstance(variables, dict) else None
+
+        try:
+            await monitoring_service.record_tool_call(
+                tool_name=name,
+                tool_source=source,
+                duration=duration_ms,
+                status=status,
+                bot_id=getattr(query, 'bot_uuid', None),
+                bot_name=bot_name,
+                pipeline_name=pipeline_name,
+                session_id=self._get_query_session_id(query),
+                message_id=message_id,
+                arguments=parameters,
+                result=result,
+                error_message=error_message,
+            )
+        except Exception as e:
+            self.ap.logger.warning(f'Failed to record tool call: {e}')
+
+    async def _invoke_tool_with_monitoring(
+        self,
+        *,
+        source: str,
+        name: str,
+        parameters: dict,
+        query: pipeline_query.Query,
+        invoke: typing.Callable[[], typing.Awaitable[typing.Any]],
+    ) -> typing.Any:
+        start_time = time.perf_counter()
+        try:
+            result = await invoke()
+        except Exception as e:
+            duration_ms = int((time.perf_counter() - start_time) * 1000)
+            await self._record_tool_call(
+                name=name,
+                source=source,
+                parameters=parameters,
+                query=query,
+                duration_ms=duration_ms,
+                status='error',
+                error_message=str(e),
+            )
+            raise
+
+        duration_ms = int((time.perf_counter() - start_time) * 1000)
+        await self._record_tool_call(
+            name=name,
+            source=source,
+            parameters=parameters,
+            query=query,
+            duration_ms=duration_ms,
+            status='success',
+            result=result,
+        )
+        return result
+
     async def execute_func_call(self, name: str, parameters: dict, query: pipeline_query.Query) -> typing.Any:
         from langbot.pkg.telemetry import features as telemetry_features
 
         if await self.native_tool_loader.has_tool(name):
             telemetry_features.increment(query, 'tool_calls', 'native')
-            return await self.native_tool_loader.invoke_tool(name, parameters, query)
+            return await self._invoke_tool_with_monitoring(
+                source='native',
+                name=name,
+                parameters=parameters,
+                query=query,
+                invoke=lambda: self.native_tool_loader.invoke_tool(name, parameters, query),
+            )
         if await self.plugin_tool_loader.has_tool(name):
             telemetry_features.increment(query, 'tool_calls', 'plugin')
-            return await self.plugin_tool_loader.invoke_tool(name, parameters, query)
+            return await self._invoke_tool_with_monitoring(
+                source='plugin',
+                name=name,
+                parameters=parameters,
+                query=query,
+                invoke=lambda: self.plugin_tool_loader.invoke_tool(name, parameters, query),
+            )
         if await self.mcp_tool_loader.has_tool(name):
             telemetry_features.increment(query, 'tool_calls', 'mcp')
-            return await self.mcp_tool_loader.invoke_tool(name, parameters, query)
+            return await self._invoke_tool_with_monitoring(
+                source='mcp',
+                name=name,
+                parameters=parameters,
+                query=query,
+                invoke=lambda: self.mcp_tool_loader.invoke_tool(name, parameters, query),
+            )
         if await self.skill_tool_loader.has_tool(name):
             telemetry_features.increment(query, 'tool_calls', 'skill')
-            return await self.skill_tool_loader.invoke_tool(name, parameters, query)
+            return await self._invoke_tool_with_monitoring(
+                source='skill',
+                name=name,
+                parameters=parameters,
+                query=query,
+                invoke=lambda: self.skill_tool_loader.invoke_tool(name, parameters, query),
+            )
         raise ToolNotFoundError(name)
 
     async def shutdown(self):