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,
         }