⏸ refactor: Improve UX for Parallel Streams (Multi-Convo) (#11096)

* 🌊 feat: Implement multi-conversation feature with added conversation context and payload adjustments

* refactor: Replace isSubmittingFamily with isSubmitting across message components for consistency

* feat: Add loadAddedAgent and processAddedConvo for multi-conversation agent execution

* refactor: Update ContentRender usage to conditionally render PlaceholderRow based on isLast and isSubmitting

* WIP: first pass, sibling index

* feat: Enhance multi-conversation support with agent tracking and display improvements

* refactor: Introduce isEphemeralAgentId utility and update related logic for agent handling

* refactor: Implement createDualMessageContent utility for sibling message display and enhance useStepHandler for added conversations

* refactor: duplicate tools for added agent if ephemeral and primary agent is also ephemeral

* chore: remove deprecated multimessage rendering

* refactor: enhance dual message content creation and agent handling for parallel rendering

* refactor: streamline message rendering and submission handling by removing unused state and optimizing conditional logic

* refactor: adjust content handling in parallel mode to utilize existing content for improved agent display

* refactor: update @librechat/agents dependency to version 3.0.53

* refactor: update @langchain/core and @librechat/agents dependencies to latest versions

* refactor: remove deprecated @langchain/core dependency from package.json

* chore: remove unused SearchToolConfig and GetSourcesParams types from web.ts

* refactor: remove unused message properties from Message component

* refactor: enhance parallel content handling with groupId support in ContentParts and useStepHandler

* refactor: implement parallel content styling in Message, MessageRender, and ContentRender components. use explicit model name

* refactor: improve agent ID handling in createDualMessageContent for dual message display

* refactor: simplify title generation in AddedConvo by removing unused sender and preset logic

* refactor: replace string interpolation with cn utility for className in HoverButtons component

* refactor: enhance agent ID handling by adding suffix management for parallel agents and updating related components

* refactor: enhance column ordering in ContentParts by sorting agents with suffix management

* refactor: update @librechat/agents dependency to version 3.0.55

* feat: implement parallel content rendering with metadata support

- Added `ParallelContentRenderer` and `ParallelColumns` components for rendering messages in parallel based on groupId and agentId.
- Introduced `contentMetadataMap` to store metadata for each content part, allowing efficient parallel content detection.
- Updated `Message` and `ContentRender` components to utilize the new metadata structure for rendering.
- Modified `useStepHandler` to manage content indices and metadata during message processing.
- Enhanced `IJobStore` interface and its implementations to support storing and retrieving content metadata.
- Updated data schemas to include `contentMetadataMap` for messages, enabling multi-agent and parallel execution scenarios.

* refactor: update @librechat/agents dependency to version 3.0.56

* refactor: remove unused EPHEMERAL_AGENT_ID constant and simplify agent ID check

* refactor: enhance multi-agent message processing and primary agent determination

* refactor: implement branch message functionality for parallel responses

* refactor: integrate added conversation retrieval into message editing and regeneration processes

* refactor: remove unused isCard and isMultiMessage props from MessageRender and ContentRender components

* refactor: update @librechat/agents dependency to version 3.0.60

* refactor: replace usage of EPHEMERAL_AGENT_ID constant with isEphemeralAgentId function for improved clarity and consistency

* refactor: standardize agent ID format in tests for consistency

* chore: move addedConvo property to the correct position in payload construction

* refactor: rename agent_id values in loadAgent tests for clarity

* chore: reorder props in ContentParts component for improved readability

* refactor: rename variable 'content' to 'result' for clarity in RedisJobStore tests

* refactor: streamline useMessageActions by removing duplicate handleFeedback assignment

* chore: revert placeholder rendering logic MessageRender and ContentRender components to original

* refactor: implement useContentMetadata hook for optimized content metadata handling

* refactor: remove contentMetadataMap and related logic from the codebase and revert back to agentId/groupId in content parts

- Eliminated contentMetadataMap from various components and services, simplifying the handling of message content.
- Updated functions to directly access agentId and groupId from content parts instead of relying on a separate metadata map.
- Adjusted related hooks and components to reflect the removal of contentMetadataMap, ensuring consistent handling of message content.
- Updated tests and documentation to align with the new structure of message content handling.

* refactor: remove logging from groupParallelContent function to clean up output

* refactor: remove model parameter from TBranchMessageRequest type for simplification

* refactor: enhance branch message creation by stripping metadata for standalone content

* chore: streamline branch message creation by simplifying content filtering and removing unnecessary metadata checks

* refactor: include attachments in branch message creation for improved content handling

* refactor: streamline agent content processing by consolidating primary agent identification and filtering logic

* refactor: simplify multi-agent message processing by creating a dedicated mapping method and enhancing content filtering

* refactor: remove unused parameter from loadEphemeralAgent function for cleaner code

* refactor: update groupId handling in metadata to only set when provided by the server

api/server/cleanup.js

@@ -350,9 +350,6 @@ function disposeClient(client) {
     if (client.agentConfigs) {
       client.agentConfigs = null;
     }
-    if (client.agentIdMap) {
-      client.agentIdMap = null;
-    }
     if (client.artifactPromises) {
       client.artifactPromises = null;
     }

api/server/controllers/agents/client.js

@@ -37,14 +37,13 @@ const {
   EModelEndpoint,
   PermissionTypes,
   isAgentsEndpoint,
-  AgentCapabilities,
+  isEphemeralAgentId,
   bedrockInputSchema,
   removeNullishValues,
 } = require('librechat-data-provider');
 const { spendTokens, spendStructuredTokens } = require('~/models/spendTokens');
 const { encodeAndFormat } = require('~/server/services/Files/images/encode');
 const { createContextHandlers } = require('~/app/clients/prompts');
-const { checkCapability } = require('~/server/services/Config');
 const { getConvoFiles } = require('~/models/Conversation');
 const BaseClient = require('~/app/clients/BaseClient');
 const { getRoleByName } = require('~/models/Role');
@@ -96,59 +95,101 @@ function logToolError(graph, error, toolId) {
   });
 }
 
+/** Regex pattern to match agent ID suffix (____N) */
+const AGENT_SUFFIX_PATTERN = /____(\d+)$/;
+
 /**
- * Applies agent labeling to conversation history when multi-agent patterns are detected.
- * Labels content parts by their originating agent to prevent identity confusion.
+ * Creates a mapMethod for getMessagesForConversation that processes agent content.
+ * - Strips agentId/groupId metadata from all content
+ * - For multi-agent: filters to primary agent content only (no suffix or lowest suffix)
+ * - For multi-agent: applies agent labels to content
  *
- * @param {TMessage[]} orderedMessages - The ordered conversation messages
- * @param {Agent} primaryAgent - The primary agent configuration
- * @param {Map<string, Agent>} agentConfigs - Map of additional agent configurations
- * @returns {TMessage[]} Messages with agent labels applied where appropriate
+ * @param {Agent} primaryAgent - Primary agent configuration
+ * @param {Map<string, Agent>} [agentConfigs] - Additional agent configurations
+ * @returns {(message: TMessage) => TMessage} Map method for processing messages
  */
-function applyAgentLabelsToHistory(orderedMessages, primaryAgent, agentConfigs) {
-  const shouldLabelByAgent = (primaryAgent.edges?.length ?? 0) > 0 || (agentConfigs?.size ?? 0) > 0;
-
-  if (!shouldLabelByAgent) {
-    return orderedMessages;
-  }
-
-  const processedMessages = [];
-
-  for (let i = 0; i < orderedMessages.length; i++) {
-    const message = orderedMessages[i];
-
-    /** @type {Record<string, string>} */
-    const agentNames = { [primaryAgent.id]: primaryAgent.name || 'Assistant' };
+function createMultiAgentMapper(primaryAgent, agentConfigs) {
+  const hasMultipleAgents = (primaryAgent.edges?.length ?? 0) > 0 || (agentConfigs?.size ?? 0) > 0;
 
+  /** @type {Record<string, string> | null} */
+  let agentNames = null;
+  if (hasMultipleAgents) {
+    agentNames = { [primaryAgent.id]: primaryAgent.name || 'Assistant' };
     if (agentConfigs) {
       for (const [agentId, agentConfig] of agentConfigs.entries()) {
         agentNames[agentId] = agentConfig.name || agentConfig.id;
       }
     }
-
-    if (
-      !message.isCreatedByUser &&
-      message.metadata?.agentIdMap &&
-      Array.isArray(message.content)
-    ) {
-      try {
-        const labeledContent = labelContentByAgent(
-          message.content,
-          message.metadata.agentIdMap,
-          agentNames,
-        );
-
-        processedMessages.push({ ...message, content: labeledContent });
-      } catch (error) {
-        logger.error('[AgentClient] Error applying agent labels to message:', error);
-        processedMessages.push(message);
-      }
-    } else {
-      processedMessages.push(message);
-    }
   }
 
-  return processedMessages;
+  return (message) => {
+    if (message.isCreatedByUser || !Array.isArray(message.content)) {
+      return message;
+    }
+
+    // Find primary agent ID (no suffix, or lowest suffix number) - only needed for multi-agent
+    let primaryAgentId = null;
+    let hasAgentMetadata = false;
+
+    if (hasMultipleAgents) {
+      let lowestSuffixIndex = Infinity;
+      for (const part of message.content) {
+        const agentId = part?.agentId;
+        if (!agentId) {
+          continue;
+        }
+        hasAgentMetadata = true;
+
+        const suffixMatch = agentId.match(AGENT_SUFFIX_PATTERN);
+        if (!suffixMatch) {
+          primaryAgentId = agentId;
+          break;
+        }
+        const suffixIndex = parseInt(suffixMatch[1], 10);
+        if (suffixIndex < lowestSuffixIndex) {
+          lowestSuffixIndex = suffixIndex;
+          primaryAgentId = agentId;
+        }
+      }
+    } else {
+      // Single agent: just check if any metadata exists
+      hasAgentMetadata = message.content.some((part) => part?.agentId || part?.groupId);
+    }
+
+    if (!hasAgentMetadata) {
+      return message;
+    }
+
+    try {
+      /** @type {Array<TMessageContentParts>} */
+      const filteredContent = [];
+      /** @type {Record<number, string>} */
+      const agentIdMap = {};
+
+      for (const part of message.content) {
+        const agentId = part?.agentId;
+        // For single agent: include all parts; for multi-agent: filter to primary
+        if (!hasMultipleAgents || !agentId || agentId === primaryAgentId) {
+          const newIndex = filteredContent.length;
+          const { agentId: _a, groupId: _g, ...cleanPart } = part;
+          filteredContent.push(cleanPart);
+          if (agentId && hasMultipleAgents) {
+            agentIdMap[newIndex] = agentId;
+          }
+        }
+      }
+
+      const finalContent =
+        Object.keys(agentIdMap).length > 0 && agentNames
+          ? labelContentByAgent(filteredContent, agentIdMap, agentNames)
+          : filteredContent;
+
+      return { ...message, content: finalContent };
+    } catch (error) {
+      logger.error('[AgentClient] Error processing multi-agent message:', error);
+      return message;
+    }
+  };
 }
 
 class AgentClient extends BaseClient {
@@ -200,8 +241,6 @@ class AgentClient extends BaseClient {
     this.indexTokenCountMap = {};
     /** @type {(messages: BaseMessage[]) => Promise<void>} */
     this.processMemory;
-    /** @type {Record<number, string> | null} */
-    this.agentIdMap = null;
   }
 
   /**
@@ -288,18 +327,13 @@ class AgentClient extends BaseClient {
     { instructions = null, additional_instructions = null },
     opts,
   ) {
-    let orderedMessages = this.constructor.getMessagesForConversation({
+    const orderedMessages = this.constructor.getMessagesForConversation({
       messages,
       parentMessageId,
       summary: this.shouldSummarize,
+      mapMethod: createMultiAgentMapper(this.options.agent, this.agentConfigs),
     });
 
-    orderedMessages = applyAgentLabelsToHistory(
-      orderedMessages,
-      this.options.agent,
-      this.agentConfigs,
-    );
-
     let payload;
     /** @type {number | undefined} */
     let promptTokens;
@@ -551,10 +585,9 @@ class AgentClient extends BaseClient {
         agent: prelimAgent,
         allowedProviders,
         endpointOption: {
-          endpoint:
-            prelimAgent.id !== Constants.EPHEMERAL_AGENT_ID
-              ? EModelEndpoint.agents
-              : memoryConfig.agent?.provider,
+          endpoint: !isEphemeralAgentId(prelimAgent.id)
+            ? EModelEndpoint.agents
+            : memoryConfig.agent?.provider,
         },
       },
       {
@@ -693,9 +726,7 @@ class AgentClient extends BaseClient {
     });
 
     const completion = filterMalformedContentParts(this.contentParts);
-    const metadata = this.agentIdMap ? { agentIdMap: this.agentIdMap } : undefined;
-
-    return { completion, metadata };
+    return { completion };
   }
 
   /**
@@ -891,12 +922,10 @@ class AgentClient extends BaseClient {
        */
       const runAgents = async (messages) => {
         const agents = [this.options.agent];
-        if (
-          this.agentConfigs &&
-          this.agentConfigs.size > 0 &&
-          ((this.options.agent.edges?.length ?? 0) > 0 ||
-            (await checkCapability(this.options.req, AgentCapabilities.chain)))
-        ) {
+        // Include additional agents when:
+        // - agentConfigs has agents (from addedConvo parallel execution or agent handoffs)
+        // - Agents without incoming edges become start nodes and run in parallel automatically
+        if (this.agentConfigs && this.agentConfigs.size > 0) {
           agents.push(...this.agentConfigs.values());
         }
 
@@ -992,24 +1021,6 @@ class AgentClient extends BaseClient {
           );
         });
       }
-
-      try {
-        /** Capture agent ID map if we have edges or multiple agents */
-        const shouldStoreAgentMap =
-          (this.options.agent.edges?.length ?? 0) > 0 || (this.agentConfigs?.size ?? 0) > 0;
-        if (shouldStoreAgentMap && run?.Graph) {
-          const contentPartAgentMap = run.Graph.getContentPartAgentMap();
-          if (contentPartAgentMap && contentPartAgentMap.size > 0) {
-            this.agentIdMap = Object.fromEntries(contentPartAgentMap);
-            logger.debug('[AgentClient] Captured agent ID map:', {
-              totalParts: this.contentParts.length,
-              mappedParts: Object.keys(this.agentIdMap).length,
-            });
-          }
-        }
-      } catch (error) {
-        logger.error('[AgentClient] Error capturing agent ID map:', error);
-      }
     } catch (err) {
       logger.error(
         '[api/server/controllers/agents/client.js #sendCompletion] Operation aborted',

api/server/middleware/accessResources/canAccessAgentFromBody.js

@@ -1,5 +1,10 @@
 const { logger } = require('@librechat/data-schemas');
-const { Constants, isAgentsEndpoint, ResourceType } = require('librechat-data-provider');
+const {
+  Constants,
+  ResourceType,
+  isAgentsEndpoint,
+  isEphemeralAgentId,
+} = require('librechat-data-provider');
 const { canAccessResource } = require('./canAccessResource');
 const { getAgent } = require('~/models/Agent');
 
@@ -13,7 +18,8 @@ const { getAgent } = require('~/models/Agent');
  */
 const resolveAgentIdFromBody = async (agentCustomId) => {
   // Handle ephemeral agents - they don't need permission checks
-  if (agentCustomId === Constants.EPHEMERAL_AGENT_ID) {
+  // Real agent IDs always start with "agent_", so anything else is ephemeral
+  if (isEphemeralAgentId(agentCustomId)) {
     return null; // No permission check needed for ephemeral agents
   }
 
@@ -62,7 +68,8 @@ const canAccessAgentFromBody = (options) => {
       }
 
       // Skip permission checks for ephemeral agents
-      if (agentId === Constants.EPHEMERAL_AGENT_ID) {
+      // Real agent IDs always start with "agent_", so anything else is ephemeral
+      if (isEphemeralAgentId(agentId)) {
         return next();
       }
 

api/server/routes/messages.js

@@ -1,4 +1,5 @@
 const express = require('express');
+const { v4: uuidv4 } = require('uuid');
 const { logger } = require('@librechat/data-schemas');
 const { ContentTypes } = require('librechat-data-provider');
 const { unescapeLaTeX, countTokens } = require('@librechat/api');
@@ -111,6 +112,91 @@ router.get('/', async (req, res) => {
   }
 });
 
+/**
+ * Creates a new branch message from a specific agent's content within a parallel response message.
+ * Filters the original message's content to only include parts attributed to the specified agentId.
+ * Only available for non-user messages with content attributions.
+ *
+ * @route POST /branch
+ * @param {string} req.body.messageId - The ID of the source message
+ * @param {string} req.body.agentId - The agentId to filter content by
+ * @returns {TMessage} The newly created branch message
+ */
+router.post('/branch', async (req, res) => {
+  try {
+    const { messageId, agentId } = req.body;
+    const userId = req.user.id;
+
+    if (!messageId || !agentId) {
+      return res.status(400).json({ error: 'messageId and agentId are required' });
+    }
+
+    const sourceMessage = await getMessage({ user: userId, messageId });
+    if (!sourceMessage) {
+      return res.status(404).json({ error: 'Source message not found' });
+    }
+
+    if (sourceMessage.isCreatedByUser) {
+      return res.status(400).json({ error: 'Cannot branch from user messages' });
+    }
+
+    if (!Array.isArray(sourceMessage.content)) {
+      return res.status(400).json({ error: 'Message does not have content' });
+    }
+
+    const hasAgentMetadata = sourceMessage.content.some((part) => part?.agentId);
+    if (!hasAgentMetadata) {
+      return res
+        .status(400)
+        .json({ error: 'Message does not have parallel content with attributions' });
+    }
+
+    /** @type {Array<import('librechat-data-provider').TMessageContentParts>} */
+    const filteredContent = [];
+    for (const part of sourceMessage.content) {
+      if (part?.agentId === agentId) {
+        const { agentId: _a, groupId: _g, ...cleanPart } = part;
+        filteredContent.push(cleanPart);
+      }
+    }
+
+    if (filteredContent.length === 0) {
+      return res.status(400).json({ error: 'No content found for the specified agentId' });
+    }
+
+    const newMessageId = uuidv4();
+    /** @type {import('librechat-data-provider').TMessage} */
+    const newMessage = {
+      messageId: newMessageId,
+      conversationId: sourceMessage.conversationId,
+      parentMessageId: sourceMessage.parentMessageId,
+      attachments: sourceMessage.attachments,
+      isCreatedByUser: false,
+      model: sourceMessage.model,
+      endpoint: sourceMessage.endpoint,
+      sender: sourceMessage.sender,
+      iconURL: sourceMessage.iconURL,
+      content: filteredContent,
+      unfinished: false,
+      error: false,
+      user: userId,
+    };
+
+    const savedMessage = await saveMessage(req, newMessage, {
+      context: 'POST /api/messages/branch',
+    });
+
+    if (!savedMessage) {
+      return res.status(500).json({ error: 'Failed to save branch message' });
+    }
+
+    res.status(201).json(savedMessage);
+  } catch (error) {
+    logger.error('Error creating branch message:', error);
+    res.status(500).json({ error: 'Internal server error' });
+  }
+});
+
 router.post('/artifact/:messageId', async (req, res) => {
   try {
     const { messageId } = req.params;

api/server/services/Endpoints/agents/addedConvo.js

@@ -0,0 +1,136 @@
+const { logger } = require('@librechat/data-schemas');
+const { initializeAgent, validateAgentModel } = require('@librechat/api');
+const { loadAddedAgent, setGetAgent, ADDED_AGENT_ID } = require('~/models/loadAddedAgent');
+const { getConvoFiles } = require('~/models/Conversation');
+const { getAgent } = require('~/models/Agent');
+const db = require('~/models');
+
+// Initialize the getAgent dependency
+setGetAgent(getAgent);
+
+/**
+ * Process addedConvo for parallel agent execution.
+ * Creates a parallel agent config from an added conversation.
+ *
+ * When an added agent has no incoming edges, it becomes a start node
+ * and runs in parallel with the primary agent automatically.
+ *
+ * Edge cases handled:
+ * - Primary agent has edges (handoffs): Added agent runs in parallel with primary,
+ *   but doesn't participate in the primary's handoff graph
+ * - Primary agent has agent_ids (legacy chain): Added agent runs in parallel with primary,
+ *   but doesn't participate in the chain
+ * - Primary agent has both: Added agent is independent, runs parallel from start
+ *
+ * @param {Object} params
+ * @param {import('express').Request} params.req
+ * @param {import('express').Response} params.res
+ * @param {Object} params.endpointOption - The endpoint option containing addedConvo
+ * @param {Object} params.modelsConfig - The models configuration
+ * @param {Function} params.logViolation - Function to log violations
+ * @param {Function} params.loadTools - Function to load agent tools
+ * @param {Array} params.requestFiles - Request files
+ * @param {string} params.conversationId - The conversation ID
+ * @param {Set} params.allowedProviders - Set of allowed providers
+ * @param {Map} params.agentConfigs - Map of agent configs to add to
+ * @param {string} params.primaryAgentId - The primary agent ID
+ * @param {Object|undefined} params.userMCPAuthMap - User MCP auth map to merge into
+ * @returns {Promise<{userMCPAuthMap: Object|undefined}>} The updated userMCPAuthMap
+ */
+const processAddedConvo = async ({
+  req,
+  res,
+  endpointOption,
+  modelsConfig,
+  logViolation,
+  loadTools,
+  requestFiles,
+  conversationId,
+  allowedProviders,
+  agentConfigs,
+  primaryAgentId,
+  primaryAgent,
+  userMCPAuthMap,
+}) => {
+  const addedConvo = endpointOption.addedConvo;
+  logger.debug('[processAddedConvo] Called with addedConvo:', {
+    hasAddedConvo: addedConvo != null,
+    addedConvoEndpoint: addedConvo?.endpoint,
+    addedConvoModel: addedConvo?.model,
+    addedConvoAgentId: addedConvo?.agent_id,
+  });
+  if (addedConvo == null) {
+    return { userMCPAuthMap };
+  }
+
+  try {
+    const addedAgent = await loadAddedAgent({ req, conversation: addedConvo, primaryAgent });
+    if (!addedAgent) {
+      return { userMCPAuthMap };
+    }
+
+    const addedValidation = await validateAgentModel({
+      req,
+      res,
+      modelsConfig,
+      logViolation,
+      agent: addedAgent,
+    });
+
+    if (!addedValidation.isValid) {
+      logger.warn(
+        `[processAddedConvo] Added agent validation failed: ${addedValidation.error?.message}`,
+      );
+      return { userMCPAuthMap };
+    }
+
+    const addedConfig = await initializeAgent(
+      {
+        req,
+        res,
+        loadTools,
+        requestFiles,
+        conversationId,
+        agent: addedAgent,
+        endpointOption,
+        allowedProviders,
+      },
+      {
+        getConvoFiles,
+        getFiles: db.getFiles,
+        getUserKey: db.getUserKey,
+        updateFilesUsage: db.updateFilesUsage,
+        getUserKeyValues: db.getUserKeyValues,
+        getToolFilesByIds: db.getToolFilesByIds,
+      },
+    );
+
+    if (userMCPAuthMap != null) {
+      Object.assign(userMCPAuthMap, addedConfig.userMCPAuthMap ?? {});
+    } else {
+      userMCPAuthMap = addedConfig.userMCPAuthMap;
+    }
+
+    const addedAgentId = addedConfig.id || ADDED_AGENT_ID;
+    agentConfigs.set(addedAgentId, addedConfig);
+
+    // No edges needed - agent without incoming edges becomes a start node
+    // and runs in parallel with the primary agent automatically.
+    // This is independent of any edges/agent_ids the primary agent has.
+
+    logger.debug(
+      `[processAddedConvo] Added parallel agent: ${addedAgentId} (primary: ${primaryAgentId}, ` +
+        `primary has edges: ${!!endpointOption.edges}, primary has agent_ids: ${!!endpointOption.agent_ids})`,
+    );
+
+    return { userMCPAuthMap };
+  } catch (err) {
+    logger.error('[processAddedConvo] Error processing addedConvo for parallel agent', err);
+    return { userMCPAuthMap };
+  }
+};
+
+module.exports = {
+  processAddedConvo,
+  ADDED_AGENT_ID,
+};

api/server/services/Endpoints/agents/build.js

@@ -15,6 +15,9 @@ const buildOptions = (req, endpoint, parsedBody, endpointType) => {
     return undefined;
   });
 
+  /** @type {import('librechat-data-provider').TConversation | undefined} */
+  const addedConvo = req.body?.addedConvo;
+
   return removeNullishValues({
     spec,
     iconURL,
@@ -23,6 +26,7 @@ const buildOptions = (req, endpoint, parsedBody, endpointType) => {
     endpointType,
     model_parameters,
     agent: agentPromise,
+    addedConvo,
   });
 };
 

api/server/services/Endpoints/agents/initialize.js

@@ -7,10 +7,10 @@ const {
   createSequentialChainEdges,
 } = require('@librechat/api');
 const {
-  Constants,
   EModelEndpoint,
   isAgentsEndpoint,
   getResponseSender,
+  isEphemeralAgentId,
 } = require('librechat-data-provider');
 const {
   createToolEndCallback,
@@ -20,6 +20,7 @@ const { getModelsConfig } = require('~/server/controllers/ModelController');
 const { loadAgentTools } = require('~/server/services/ToolService');
 const AgentClient = require('~/server/controllers/agents/client');
 const { getConvoFiles } = require('~/models/Conversation');
+const { processAddedConvo } = require('./addedConvo');
 const { getAgent } = require('~/models/Agent');
 const { logViolation } = require('~/cache');
 const db = require('~/models');
@@ -233,6 +234,33 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
     edges = edges ? edges.concat(chain) : chain;
   }
 
+  /** Multi-Convo: Process addedConvo for parallel agent execution */
+  const { userMCPAuthMap: updatedMCPAuthMap } = await processAddedConvo({
+    req,
+    res,
+    endpointOption,
+    modelsConfig,
+    logViolation,
+    loadTools,
+    requestFiles,
+    conversationId,
+    allowedProviders,
+    agentConfigs,
+    primaryAgentId: primaryConfig.id,
+    primaryAgent,
+    userMCPAuthMap,
+  });
+
+  if (updatedMCPAuthMap) {
+    userMCPAuthMap = updatedMCPAuthMap;
+  }
+
+  // Ensure edges is an array when we have multiple agents (multi-agent mode)
+  // MultiAgentGraph.categorizeEdges requires edges to be iterable
+  if (agentConfigs.size > 0 && !edges) {
+    edges = [];
+  }
+
   primaryConfig.edges = edges;
 
   let endpointConfig = appConfig.endpoints?.[primaryConfig.endpoint];
@@ -276,10 +304,7 @@ const initializeClient = async ({ req, res, signal, endpointOption }) => {
     endpointType: endpointOption.endpointType,
     resendFiles: primaryConfig.resendFiles ?? true,
     maxContextTokens: primaryConfig.maxContextTokens,
-    endpoint:
-      primaryConfig.id === Constants.EPHEMERAL_AGENT_ID
-        ? primaryConfig.endpoint
-        : EModelEndpoint.agents,
+    endpoint: isEphemeralAgentId(primaryConfig.id) ? primaryConfig.endpoint : EModelEndpoint.agents,
   });
 
   return { client, userMCPAuthMap };

api/server/services/ToolService.js

@@ -9,7 +9,6 @@ const {
 } = require('@librechat/api');
 const {
   Tools,
-  Constants,
   ErrorTypes,
   ContentTypes,
   imageGenTools,
@@ -18,6 +17,7 @@ const {
   ImageVisionTool,
   openapiToFunction,
   AgentCapabilities,
+  isEphemeralAgentId,
   validateActionDomain,
   defaultAgentCapabilities,
   validateAndParseOpenAPISpec,
@@ -393,7 +393,7 @@ async function loadAgentTools({
   const endpointsConfig = await getEndpointsConfig(req);
   let enabledCapabilities = new Set(endpointsConfig?.[EModelEndpoint.agents]?.capabilities ?? []);
   /** Edge case: use defined/fallback capabilities when the "agents" endpoint is not enabled */
-  if (enabledCapabilities.size === 0 && agent.id === Constants.EPHEMERAL_AGENT_ID) {
+  if (enabledCapabilities.size === 0 && isEphemeralAgentId(agent.id)) {
     enabledCapabilities = new Set(
       appConfig.endpoints?.[EModelEndpoint.agents]?.capabilities ?? defaultAgentCapabilities,
     );