LibreChat/api/server/controllers/agents/callbacks.js
Danny Avila 5af1342dbb
🦥 refactor: Event-Driven Lazy Tool Loading (#11588)
* refactor: json schema tools with lazy loading

- Added LocalToolExecutor class for lazy loading and caching of tools during execution.
- Introduced ToolExecutionContext and ToolExecutor interfaces for better type management.
- Created utility functions to generate tool proxies with JSON schema support.
- Added ExtendedJsonSchema type for enhanced schema definitions.
- Updated existing toolkits to utilize the new schema and executor functionalities.
- Introduced a comprehensive tool definitions registry for managing various tool schemas.

chore: update @librechat/agents to version 3.1.2

refactor: enhance tool loading optimization and classification

- Improved the loadAgentToolsOptimized function to utilize a proxy pattern for all tools, enabling deferred execution and reducing overhead.
- Introduced caching for tool instances and refined tool classification logic to streamline tool management.
- Updated the handling of MCP tools to improve logging and error reporting for missing tools in the cache.
- Enhanced the structure of tool definitions to support better classification and integration with existing tools.

refactor: modularize tool loading and enhance optimization

- Moved the loadAgentToolsOptimized function to a new service file for better organization and maintainability.
- Updated the ToolService to utilize the new service for optimized tool loading, improving code clarity.
- Removed legacy tool loading methods and streamlined the tool loading process to enhance performance and reduce complexity.
- Introduced feature flag handling for optimized tool loading, allowing for easier toggling of this functionality.

refactor: replace loadAgentToolsWithFlag with loadAgentTools in tool loader

refactor: enhance MCP tool loading with proxy creation and classification

refactor: optimize MCP tool loading by grouping tools by server

- Introduced a Map to group cached tools by server name, improving the organization of tool data.
- Updated the createMCPProxyTool function to accept server name directly, enhancing clarity.
- Refactored the logic for handling MCP tools, streamlining the process of creating proxy tools for classification.

refactor: enhance MCP tool loading and proxy creation

- Added functionality to retrieve MCP server tools and reinitialize servers if necessary, improving tool availability.
- Updated the tool loading logic to utilize a Map for organizing tools by server, enhancing clarity and performance.
- Refactored the createToolProxy function to ensure a default response format, streamlining tool creation.

refactor: update createToolProxy to ensure consistent response format

- Modified the createToolProxy function to await the executor's execution and validate the result format.
- Ensured that the function returns a default response structure when the result is not an array of two elements, enhancing reliability in tool proxy creation.

refactor: ToolExecutionContext with toolCall property

- Added toolCall property to ToolExecutionContext interface for improved context handling during tool execution.
- Updated LocalToolExecutor to include toolCall in the runnable configuration, allowing for more flexible tool invocation.
- Modified createToolProxy to pass toolCall from the configuration, ensuring consistent context across tool executions.

refactor: enhance event-driven tool execution and logging

- Introduced ToolExecuteOptions for improved handling of event-driven tool execution, allowing for parallel execution of tool calls.
- Updated getDefaultHandlers to include support for ON_TOOL_EXECUTE events, enhancing the flexibility of tool invocation.
- Added detailed logging in LocalToolExecutor to track tool loading and execution metrics, improving observability and debugging capabilities.
- Refactored initializeClient to integrate event-driven tool loading, ensuring compatibility with the new execution model.

chore: update @librechat/agents to version 3.1.21

refactor: remove legacy tool loading and executor components

- Eliminated the loadAgentToolsWithFlag function, simplifying the tool loading process by directly using loadAgentTools.
- Removed the LocalToolExecutor and related executor components to streamline the tool execution architecture.
- Updated ToolService and related files to reflect the removal of deprecated features, enhancing code clarity and maintainability.

refactor: enhance tool classification and definitions handling

- Updated the loadAgentTools function to return toolDefinitions alongside toolRegistry, improving the structure of tool data returned to clients.
- Removed the convertRegistryToDefinitions function from the initialize.js file, simplifying the initialization process.
- Adjusted the buildToolClassification function to ensure toolDefinitions are built and returned simultaneously with the toolRegistry, enhancing efficiency in tool management.
- Updated type definitions in initialize.ts to include toolDefinitions, ensuring consistency across the codebase.

refactor: implement event-driven tool execution handler

- Introduced createToolExecuteHandler function to streamline the handling of ON_TOOL_EXECUTE events, allowing for parallel execution of tool calls.
- Updated getDefaultHandlers to utilize the new handler, simplifying the event-driven architecture.
- Added handlers.ts file to encapsulate tool execution logic, improving code organization and maintainability.
- Enhanced OpenAI handlers to integrate the new tool execution capabilities, ensuring consistent event handling across the application.

refactor: integrate event-driven tool execution options

- Added toolExecuteOptions to support event-driven tool execution in OpenAI and responses controllers, enhancing flexibility in tool handling.
- Updated handlers to utilize createToolExecuteHandler, allowing for streamlined execution of tools during agent interactions.
- Refactored service dependencies to include toolExecuteOptions, ensuring consistent integration across the application.

refactor: enhance tool loading with definitionsOnly parameter

- Updated createToolLoader and loadAgentTools functions to include a definitionsOnly parameter, allowing for the retrieval of only serializable tool definitions in event-driven mode.
- Adjusted related interfaces and documentation to reflect the new parameter, improving clarity and flexibility in tool management.
- Ensured compatibility across various components by integrating the definitionsOnly option in the initialization process.

refactor: improve agent tool presence check in initialization

- Added a check for tool presence using a new hasAgentTools variable, which evaluates both structuredTools and toolDefinitions.
- Updated the conditional logic in the agent initialization process to utilize the hasAgentTools variable, enhancing clarity and maintainability in tool management.

refactor: enhance agent tool extraction to support tool definitions

- Updated the extractMCPServers function to handle both tool instances and serializable tool definitions, improving flexibility in agent tool management.
- Added a new property toolDefinitions to the AgentWithTools type for better integration of event-driven mode.
- Enhanced documentation to clarify the function's capabilities in extracting unique MCP server names from both tools and tool definitions.

refactor: enhance tool classification and registry building

- Added serverName property to ToolDefinition for improved tool identification.
- Introduced buildToolRegistry function to streamline the creation of tool registries based on MCP tool definitions and agent options.
- Updated buildToolClassification to utilize the new registry building logic, ensuring basic definitions are returned even when advanced classification features are not allowed.
- Enhanced documentation and logging for clarity in tool classification processes.

refactor: update @librechat/agents dependency to version 3.1.22

fix: expose loadTools function in ToolService

- Added loadTools function to the exported module in ToolService.js, enhancing the accessibility of tool loading functionality.

chore: remove configurable options from tool execute options in OpenAI controller

refactor: enhance tool loading mechanism to utilize agent-specific context

chore: update @librechat/agents dependency to version 3.1.23

fix: simplify result handling in createToolExecuteHandler

* refactor: loadToolDefinitions for efficient tool loading in event-driven mode

* refactor: replace legacy tool loading with loadToolsForExecution in OpenAI and responses controllers

- Updated OpenAIChatCompletionController and createResponse functions to utilize loadToolsForExecution for improved tool loading.
- Removed deprecated loadToolsLegacy references, streamlining the tool execution process.
- Enhanced tool loading options to include agent-specific context and configurations.

* refactor: enhance tool loading and execution handling

- Introduced loadActionToolsForExecution function to streamline loading of action tools, improving organization and maintainability.
- Updated loadToolsForExecution to handle both regular and action tools, optimizing the tool loading process.
- Added detailed logging for missing tools in createToolExecuteHandler, enhancing error visibility.
- Refactored tool definitions to normalize action tool names, improving consistency in tool management.

* refactor: enhance built-in tool definitions loading

- Updated loadToolDefinitions to include descriptions and parameters from the tool registry for built-in tools, improving the clarity and usability of tool definitions.
- Integrated getToolDefinition to streamline the retrieval of tool metadata, enhancing the overall tool management process.

* feat: add action tool definitions loading to tool service

- Introduced getActionToolDefinitions function to load action tool definitions based on agent ID and tool names, enhancing the tool loading process.
- Updated loadToolDefinitions to integrate action tool definitions, allowing for better management and retrieval of action-specific tools.
- Added comprehensive tests for action tool definitions to ensure correct loading and parameter handling, improving overall reliability and functionality.

* chore: update @librechat/agents dependency to version 3.1.26

* refactor: add toolEndCallback to handle tool execution results

* fix: tool definitions and execution handling

- Introduced native tools (execute_code, file_search, web_search) to the tool service, allowing for better integration and management of these tools.
- Updated isBuiltInTool function to include native tools in the built-in check, improving tool recognition.
- Added comprehensive tests for loading parameters of native tools, ensuring correct functionality and parameter handling.
- Enhanced tool definitions registry to include new agent tool definitions, streamlining tool retrieval and management.

* refactor: enhance tool loading and execution context

- Added toolRegistry to the context for OpenAIChatCompletionController and createResponse functions, improving tool management.
- Updated loadToolsForExecution to utilize toolRegistry for better integration of programmatic tools and tool search functionalities.
- Enhanced the initialization process to include toolRegistry in agent context, streamlining tool access and configuration.
- Refactored tool classification logic to support event-driven execution, ensuring compatibility with new tool definitions.

* chore: add request duration logging to OpenAI and Responses controllers

- Introduced logging for request start and completion times in OpenAIChatCompletionController and createResponse functions.
- Calculated and logged the duration of each request, enhancing observability and performance tracking.
- Improved debugging capabilities by providing detailed logs for both streaming and non-streaming responses.

* chore: update @librechat/agents dependency to version 3.1.27

* refactor: implement buildToolSet function for tool management

- Introduced buildToolSet function to streamline the creation of tool sets from agent configurations, enhancing tool management across various controllers.
- Updated AgentClient, OpenAIChatCompletionController, and createResponse functions to utilize buildToolSet, improving consistency in tool handling.
- Added comprehensive tests for buildToolSet to ensure correct functionality and edge case handling, enhancing overall reliability.

* refactor: update import paths for ToolExecuteOptions and createToolExecuteHandler

* fix: update GoogleSearch.js description for maximum search results

- Changed the default maximum number of search results from 10 to 5 in the Google Search JSON schema description, ensuring accurate documentation of the expected behavior.

* chore: remove deprecated Browser tool and associated assets

- Deleted the Browser tool definition from manifest.json, which included its name, plugin key, description, and authentication configuration.
- Removed the web-browser.svg asset as it is no longer needed following the removal of the Browser tool.

* fix: ensure tool definitions are valid before processing

- Added a check to verify the existence of tool definitions in the registry before accessing their properties, preventing potential runtime errors.
- Updated the loading logic for built-in tool definitions to ensure that only valid definitions are pushed to the built-in tool definitions array.

* fix: extend ExtendedJsonSchema to support 'null' type and nullable enums

- Updated the ExtendedJsonSchema type to include 'null' as a valid type option.
- Modified the enum property to accept an array of values that can include strings, numbers, booleans, and null, enhancing schema flexibility.

* test: add comprehensive tests for tool definitions loading and registry behavior

- Implemented tests to verify the handling of built-in tools without registry definitions, ensuring they are skipped correctly.
- Added tests to confirm that built-in tools include descriptions and parameters in the registry.
- Enhanced tests for action tools, checking for proper inclusion of metadata and handling of tools without parameters in the registry.

* test: add tests for mixed-type and number enum schema handling

- Introduced tests to validate the parsing of mixed-type enum values, including strings, numbers, booleans, and null.
- Added tests for number enum schema values to ensure correct parsing of numeric inputs, enhancing schema validation coverage.

* fix: update mock implementation for @librechat/agents

- Changed the mock for @librechat/agents to spread the actual module's properties, ensuring that all necessary functionalities are preserved in tests.
- This adjustment enhances the accuracy of the tests by reflecting the real structure of the module.

* fix: change max_results type in GoogleSearch schema from number to integer

- Updated the type of max_results in the Google Search JSON schema to 'integer' for better type accuracy and validation consistency.

* fix: update max_results description and type in GoogleSearch schema

- Changed the type of max_results from 'number' to 'integer' for improved type accuracy.
- Updated the description to reflect the new default maximum number of search results, changing it from 10 to 5.

* refactor: remove unused code and improve tool registry handling

- Eliminated outdated comments and conditional logic related to event-driven mode in the ToolService.
- Enhanced the handling of the tool registry by ensuring it is configurable for better integration during tool execution.

* feat: add definitionsOnly option to buildToolClassification for event-driven mode

- Introduced a new parameter, definitionsOnly, to the BuildToolClassificationParams interface to enable a mode that skips tool instance creation.
- Updated the buildToolClassification function to conditionally add tool definitions without instantiating tools when definitionsOnly is true.
- Modified the loadToolDefinitions function to pass definitionsOnly as true, ensuring compatibility with the new feature.

* test: add unit tests for buildToolClassification with definitionsOnly option

- Implemented tests to verify the behavior of buildToolClassification when definitionsOnly is set to true or false.
- Ensured that tool instances are not created when definitionsOnly is true, while still adding necessary tool definitions.
- Confirmed that loadAuthValues is called appropriately based on the definitionsOnly parameter, enhancing test coverage for this new feature.
2026-02-01 08:50:57 -05:00

731 lines
24 KiB
JavaScript

const { nanoid } = require('nanoid');
const { Constants } = require('@librechat/agents');
const { logger } = require('@librechat/data-schemas');
const {
sendEvent,
GenerationJobManager,
writeAttachmentEvent,
createToolExecuteHandler,
} = require('@librechat/api');
const { Tools, StepTypes, FileContext, ErrorTypes } = require('librechat-data-provider');
const {
EnvVar,
Providers,
GraphEvents,
getMessageId,
ToolEndHandler,
handleToolCalls,
ChatModelStreamHandler,
} = require('@librechat/agents');
const { processFileCitations } = require('~/server/services/Files/Citations');
const { processCodeOutput } = require('~/server/services/Files/Code/process');
const { loadAuthValues } = require('~/server/services/Tools/credentials');
const { saveBase64Image } = require('~/server/services/Files/process');
class ModelEndHandler {
/**
* @param {Array<UsageMetadata>} collectedUsage
*/
constructor(collectedUsage) {
if (!Array.isArray(collectedUsage)) {
throw new Error('collectedUsage must be an array');
}
this.collectedUsage = collectedUsage;
}
finalize(errorMessage) {
if (!errorMessage) {
return;
}
throw new Error(errorMessage);
}
/**
* @param {string} event
* @param {ModelEndData | undefined} data
* @param {Record<string, unknown> | undefined} metadata
* @param {StandardGraph} graph
* @returns {Promise<void>}
*/
async handle(event, data, metadata, graph) {
if (!graph || !metadata) {
console.warn(`Graph or metadata not found in ${event} event`);
return;
}
/** @type {string | undefined} */
let errorMessage;
try {
const agentContext = graph.getAgentContext(metadata);
const isGoogle = agentContext.provider === Providers.GOOGLE;
const streamingDisabled = !!agentContext.clientOptions?.disableStreaming;
if (data?.output?.additional_kwargs?.stop_reason === 'refusal') {
const info = { ...data.output.additional_kwargs };
errorMessage = JSON.stringify({
type: ErrorTypes.REFUSAL,
info,
});
logger.debug(`[ModelEndHandler] Model refused to respond`, {
...info,
userId: metadata.user_id,
messageId: metadata.run_id,
conversationId: metadata.thread_id,
});
}
const toolCalls = data?.output?.tool_calls;
let hasUnprocessedToolCalls = false;
if (Array.isArray(toolCalls) && toolCalls.length > 0 && graph?.toolCallStepIds?.has) {
try {
hasUnprocessedToolCalls = toolCalls.some(
(tc) => tc?.id && !graph.toolCallStepIds.has(tc.id),
);
} catch {
hasUnprocessedToolCalls = false;
}
}
if (isGoogle || streamingDisabled || hasUnprocessedToolCalls) {
await handleToolCalls(toolCalls, metadata, graph);
}
const usage = data?.output?.usage_metadata;
if (!usage) {
return this.finalize(errorMessage);
}
const modelName = metadata?.ls_model_name || agentContext.clientOptions?.model;
if (modelName) {
usage.model = modelName;
}
this.collectedUsage.push(usage);
if (!streamingDisabled) {
return this.finalize(errorMessage);
}
if (!data.output.content) {
return this.finalize(errorMessage);
}
const stepKey = graph.getStepKey(metadata);
const message_id = getMessageId(stepKey, graph) ?? '';
if (message_id) {
await graph.dispatchRunStep(stepKey, {
type: StepTypes.MESSAGE_CREATION,
message_creation: {
message_id,
},
});
}
const stepId = graph.getStepIdByKey(stepKey);
const content = data.output.content;
if (typeof content === 'string') {
await graph.dispatchMessageDelta(stepId, {
content: [
{
type: 'text',
text: content,
},
],
});
} else if (content.every((c) => c.type?.startsWith('text'))) {
await graph.dispatchMessageDelta(stepId, {
content,
});
}
} catch (error) {
logger.error('Error handling model end event:', error);
return this.finalize(errorMessage);
}
}
}
/**
* @deprecated Agent Chain helper
* @param {string | undefined} [last_agent_id]
* @param {string | undefined} [langgraph_node]
* @returns {boolean}
*/
function checkIfLastAgent(last_agent_id, langgraph_node) {
if (!last_agent_id || !langgraph_node) {
return false;
}
return langgraph_node?.endsWith(last_agent_id);
}
/**
* Helper to emit events either to res (standard mode) or to job emitter (resumable mode).
* @param {ServerResponse} res - The server response object
* @param {string | null} streamId - The stream ID for resumable mode, or null for standard mode
* @param {Object} eventData - The event data to send
*/
function emitEvent(res, streamId, eventData) {
if (streamId) {
GenerationJobManager.emitChunk(streamId, eventData);
} else {
sendEvent(res, eventData);
}
}
/**
* @typedef {Object} ToolExecuteOptions
* @property {(toolNames: string[]) => Promise<{loadedTools: StructuredTool[]}>} loadTools - Function to load tools by name
* @property {Object} configurable - Configurable context for tool invocation
*/
/**
* Get default handlers for stream events.
* @param {Object} options - The options object.
* @param {ServerResponse} options.res - The server response object.
* @param {ContentAggregator} options.aggregateContent - Content aggregator function.
* @param {ToolEndCallback} options.toolEndCallback - Callback to use when tool ends.
* @param {Array<UsageMetadata>} options.collectedUsage - The list of collected usage metadata.
* @param {string | null} [options.streamId] - The stream ID for resumable mode, or null for standard mode.
* @param {ToolExecuteOptions} [options.toolExecuteOptions] - Options for event-driven tool execution.
* @returns {Record<string, t.EventHandler>} The default handlers.
* @throws {Error} If the request is not found.
*/
function getDefaultHandlers({
res,
aggregateContent,
toolEndCallback,
collectedUsage,
streamId = null,
toolExecuteOptions = null,
}) {
if (!res || !aggregateContent) {
throw new Error(
`[getDefaultHandlers] Missing required options: res: ${!res}, aggregateContent: ${!aggregateContent}`,
);
}
const handlers = {
[GraphEvents.CHAT_MODEL_END]: new ModelEndHandler(collectedUsage),
[GraphEvents.TOOL_END]: new ToolEndHandler(toolEndCallback, logger),
[GraphEvents.CHAT_MODEL_STREAM]: new ChatModelStreamHandler(),
[GraphEvents.ON_RUN_STEP]: {
/**
* Handle ON_RUN_STEP event.
* @param {string} event - The event name.
* @param {StreamEventData} data - The event data.
* @param {GraphRunnableConfig['configurable']} [metadata] The runnable metadata.
*/
handle: (event, data, metadata) => {
if (data?.stepDetails.type === StepTypes.TOOL_CALLS) {
emitEvent(res, streamId, { event, data });
} else if (checkIfLastAgent(metadata?.last_agent_id, metadata?.langgraph_node)) {
emitEvent(res, streamId, { event, data });
} else if (!metadata?.hide_sequential_outputs) {
emitEvent(res, streamId, { event, data });
} else {
const agentName = metadata?.name ?? 'Agent';
const isToolCall = data?.stepDetails.type === StepTypes.TOOL_CALLS;
const action = isToolCall ? 'performing a task...' : 'thinking...';
emitEvent(res, streamId, {
event: 'on_agent_update',
data: {
runId: metadata?.run_id,
message: `${agentName} is ${action}`,
},
});
}
aggregateContent({ event, data });
},
},
[GraphEvents.ON_RUN_STEP_DELTA]: {
/**
* Handle ON_RUN_STEP_DELTA event.
* @param {string} event - The event name.
* @param {StreamEventData} data - The event data.
* @param {GraphRunnableConfig['configurable']} [metadata] The runnable metadata.
*/
handle: (event, data, metadata) => {
if (data?.delta.type === StepTypes.TOOL_CALLS) {
emitEvent(res, streamId, { event, data });
} else if (checkIfLastAgent(metadata?.last_agent_id, metadata?.langgraph_node)) {
emitEvent(res, streamId, { event, data });
} else if (!metadata?.hide_sequential_outputs) {
emitEvent(res, streamId, { event, data });
}
aggregateContent({ event, data });
},
},
[GraphEvents.ON_RUN_STEP_COMPLETED]: {
/**
* Handle ON_RUN_STEP_COMPLETED event.
* @param {string} event - The event name.
* @param {StreamEventData & { result: ToolEndData }} data - The event data.
* @param {GraphRunnableConfig['configurable']} [metadata] The runnable metadata.
*/
handle: (event, data, metadata) => {
if (data?.result != null) {
emitEvent(res, streamId, { event, data });
} else if (checkIfLastAgent(metadata?.last_agent_id, metadata?.langgraph_node)) {
emitEvent(res, streamId, { event, data });
} else if (!metadata?.hide_sequential_outputs) {
emitEvent(res, streamId, { event, data });
}
aggregateContent({ event, data });
},
},
[GraphEvents.ON_MESSAGE_DELTA]: {
/**
* Handle ON_MESSAGE_DELTA event.
* @param {string} event - The event name.
* @param {StreamEventData} data - The event data.
* @param {GraphRunnableConfig['configurable']} [metadata] The runnable metadata.
*/
handle: (event, data, metadata) => {
if (checkIfLastAgent(metadata?.last_agent_id, metadata?.langgraph_node)) {
emitEvent(res, streamId, { event, data });
} else if (!metadata?.hide_sequential_outputs) {
emitEvent(res, streamId, { event, data });
}
aggregateContent({ event, data });
},
},
[GraphEvents.ON_REASONING_DELTA]: {
/**
* Handle ON_REASONING_DELTA event.
* @param {string} event - The event name.
* @param {StreamEventData} data - The event data.
* @param {GraphRunnableConfig['configurable']} [metadata] The runnable metadata.
*/
handle: (event, data, metadata) => {
if (checkIfLastAgent(metadata?.last_agent_id, metadata?.langgraph_node)) {
emitEvent(res, streamId, { event, data });
} else if (!metadata?.hide_sequential_outputs) {
emitEvent(res, streamId, { event, data });
}
aggregateContent({ event, data });
},
},
};
if (toolExecuteOptions) {
handlers[GraphEvents.ON_TOOL_EXECUTE] = createToolExecuteHandler(toolExecuteOptions);
}
return handlers;
}
/**
* Helper to write attachment events either to res or to job emitter.
* @param {ServerResponse} res - The server response object
* @param {string | null} streamId - The stream ID for resumable mode, or null for standard mode
* @param {Object} attachment - The attachment data
*/
function writeAttachment(res, streamId, attachment) {
if (streamId) {
GenerationJobManager.emitChunk(streamId, { event: 'attachment', data: attachment });
} else {
res.write(`event: attachment\ndata: ${JSON.stringify(attachment)}\n\n`);
}
}
/**
*
* @param {Object} params
* @param {ServerRequest} params.req
* @param {ServerResponse} params.res
* @param {Promise<MongoFile | { filename: string; filepath: string; expires: number;} | null>[]} params.artifactPromises
* @param {string | null} [params.streamId] - The stream ID for resumable mode, or null for standard mode.
* @returns {ToolEndCallback} The tool end callback.
*/
function createToolEndCallback({ req, res, artifactPromises, streamId = null }) {
/**
* @type {ToolEndCallback}
*/
return async (data, metadata) => {
const output = data?.output;
if (!output) {
return;
}
if (!output.artifact) {
return;
}
if (output.artifact[Tools.file_search]) {
artifactPromises.push(
(async () => {
const user = req.user;
const attachment = await processFileCitations({
user,
metadata,
appConfig: req.config,
toolArtifact: output.artifact,
toolCallId: output.tool_call_id,
});
if (!attachment) {
return null;
}
if (!streamId && !res.headersSent) {
return attachment;
}
writeAttachment(res, streamId, attachment);
return attachment;
})().catch((error) => {
logger.error('Error processing file citations:', error);
return null;
}),
);
}
if (output.artifact[Tools.ui_resources]) {
artifactPromises.push(
(async () => {
const attachment = {
type: Tools.ui_resources,
messageId: metadata.run_id,
toolCallId: output.tool_call_id,
conversationId: metadata.thread_id,
[Tools.ui_resources]: output.artifact[Tools.ui_resources].data,
};
if (!streamId && !res.headersSent) {
return attachment;
}
writeAttachment(res, streamId, attachment);
return attachment;
})().catch((error) => {
logger.error('Error processing artifact content:', error);
return null;
}),
);
}
if (output.artifact[Tools.web_search]) {
artifactPromises.push(
(async () => {
const attachment = {
type: Tools.web_search,
messageId: metadata.run_id,
toolCallId: output.tool_call_id,
conversationId: metadata.thread_id,
[Tools.web_search]: { ...output.artifact[Tools.web_search] },
};
if (!streamId && !res.headersSent) {
return attachment;
}
writeAttachment(res, streamId, attachment);
return attachment;
})().catch((error) => {
logger.error('Error processing artifact content:', error);
return null;
}),
);
}
if (output.artifact.content) {
/** @type {FormattedContent[]} */
const content = output.artifact.content;
for (let i = 0; i < content.length; i++) {
const part = content[i];
if (!part) {
continue;
}
if (part.type !== 'image_url') {
continue;
}
const { url } = part.image_url;
artifactPromises.push(
(async () => {
const filename = `${output.name}_img_${nanoid()}`;
const file_id = output.artifact.file_ids?.[i];
const file = await saveBase64Image(url, {
req,
file_id,
filename,
endpoint: metadata.provider,
context: FileContext.image_generation,
});
const fileMetadata = Object.assign(file, {
messageId: metadata.run_id,
toolCallId: output.tool_call_id,
conversationId: metadata.thread_id,
});
if (!streamId && !res.headersSent) {
return fileMetadata;
}
if (!fileMetadata) {
return null;
}
writeAttachment(res, streamId, fileMetadata);
return fileMetadata;
})().catch((error) => {
logger.error('Error processing artifact content:', error);
return null;
}),
);
}
return;
}
const isCodeTool =
output.name === Tools.execute_code || output.name === Constants.PROGRAMMATIC_TOOL_CALLING;
if (!isCodeTool) {
return;
}
if (!output.artifact.files) {
return;
}
for (const file of output.artifact.files) {
const { id, name } = file;
artifactPromises.push(
(async () => {
const result = await loadAuthValues({
userId: req.user.id,
authFields: [EnvVar.CODE_API_KEY],
});
const fileMetadata = await processCodeOutput({
req,
id,
name,
apiKey: result[EnvVar.CODE_API_KEY],
messageId: metadata.run_id,
toolCallId: output.tool_call_id,
conversationId: metadata.thread_id,
session_id: output.artifact.session_id,
});
if (!streamId && !res.headersSent) {
return fileMetadata;
}
if (!fileMetadata) {
return null;
}
writeAttachment(res, streamId, fileMetadata);
return fileMetadata;
})().catch((error) => {
logger.error('Error processing code output:', error);
return null;
}),
);
}
};
}
/**
* Helper to write attachment events in Open Responses format (librechat:attachment)
* @param {ServerResponse} res - The server response object
* @param {Object} tracker - The response tracker with sequence number
* @param {Object} attachment - The attachment data
* @param {Object} metadata - Additional metadata (messageId, conversationId)
*/
function writeResponsesAttachment(res, tracker, attachment, metadata) {
const sequenceNumber = tracker.nextSequence();
writeAttachmentEvent(res, sequenceNumber, attachment, {
messageId: metadata.run_id,
conversationId: metadata.thread_id,
});
}
/**
* Creates a tool end callback specifically for the Responses API.
* Emits attachments as `librechat:attachment` events per the Open Responses extension spec.
*
* @param {Object} params
* @param {ServerRequest} params.req
* @param {ServerResponse} params.res
* @param {Object} params.tracker - Response tracker with sequence number
* @param {Promise<MongoFile | { filename: string; filepath: string; expires: number;} | null>[]} params.artifactPromises
* @returns {ToolEndCallback} The tool end callback.
*/
function createResponsesToolEndCallback({ req, res, tracker, artifactPromises }) {
/**
* @type {ToolEndCallback}
*/
return async (data, metadata) => {
const output = data?.output;
if (!output) {
return;
}
if (!output.artifact) {
return;
}
if (output.artifact[Tools.file_search]) {
artifactPromises.push(
(async () => {
const user = req.user;
const attachment = await processFileCitations({
user,
metadata,
appConfig: req.config,
toolArtifact: output.artifact,
toolCallId: output.tool_call_id,
});
if (!attachment) {
return null;
}
// For Responses API, emit attachment during streaming
if (res.headersSent && !res.writableEnded) {
writeResponsesAttachment(res, tracker, attachment, metadata);
}
return attachment;
})().catch((error) => {
logger.error('Error processing file citations:', error);
return null;
}),
);
}
if (output.artifact[Tools.ui_resources]) {
artifactPromises.push(
(async () => {
const attachment = {
type: Tools.ui_resources,
toolCallId: output.tool_call_id,
[Tools.ui_resources]: output.artifact[Tools.ui_resources].data,
};
// For Responses API, always emit attachment during streaming
if (res.headersSent && !res.writableEnded) {
writeResponsesAttachment(res, tracker, attachment, metadata);
}
return attachment;
})().catch((error) => {
logger.error('Error processing artifact content:', error);
return null;
}),
);
}
if (output.artifact[Tools.web_search]) {
artifactPromises.push(
(async () => {
const attachment = {
type: Tools.web_search,
toolCallId: output.tool_call_id,
[Tools.web_search]: { ...output.artifact[Tools.web_search] },
};
// For Responses API, always emit attachment during streaming
if (res.headersSent && !res.writableEnded) {
writeResponsesAttachment(res, tracker, attachment, metadata);
}
return attachment;
})().catch((error) => {
logger.error('Error processing artifact content:', error);
return null;
}),
);
}
if (output.artifact.content) {
/** @type {FormattedContent[]} */
const content = output.artifact.content;
for (let i = 0; i < content.length; i++) {
const part = content[i];
if (!part) {
continue;
}
if (part.type !== 'image_url') {
continue;
}
const { url } = part.image_url;
artifactPromises.push(
(async () => {
const filename = `${output.name}_img_${nanoid()}`;
const file_id = output.artifact.file_ids?.[i];
const file = await saveBase64Image(url, {
req,
file_id,
filename,
endpoint: metadata.provider,
context: FileContext.image_generation,
});
const fileMetadata = Object.assign(file, {
toolCallId: output.tool_call_id,
});
if (!fileMetadata) {
return null;
}
// For Responses API, emit attachment during streaming
if (res.headersSent && !res.writableEnded) {
const attachment = {
file_id: fileMetadata.file_id,
filename: fileMetadata.filename,
type: fileMetadata.type,
url: fileMetadata.filepath,
width: fileMetadata.width,
height: fileMetadata.height,
tool_call_id: output.tool_call_id,
};
writeResponsesAttachment(res, tracker, attachment, metadata);
}
return fileMetadata;
})().catch((error) => {
logger.error('Error processing artifact content:', error);
return null;
}),
);
}
return;
}
const isCodeTool =
output.name === Tools.execute_code || output.name === Constants.PROGRAMMATIC_TOOL_CALLING;
if (!isCodeTool) {
return;
}
if (!output.artifact.files) {
return;
}
for (const file of output.artifact.files) {
const { id, name } = file;
artifactPromises.push(
(async () => {
const result = await loadAuthValues({
userId: req.user.id,
authFields: [EnvVar.CODE_API_KEY],
});
const fileMetadata = await processCodeOutput({
req,
id,
name,
apiKey: result[EnvVar.CODE_API_KEY],
messageId: metadata.run_id,
toolCallId: output.tool_call_id,
conversationId: metadata.thread_id,
session_id: output.artifact.session_id,
});
if (!fileMetadata) {
return null;
}
// For Responses API, emit attachment during streaming
if (res.headersSent && !res.writableEnded) {
const attachment = {
file_id: fileMetadata.file_id,
filename: fileMetadata.filename,
type: fileMetadata.type,
url: fileMetadata.filepath,
width: fileMetadata.width,
height: fileMetadata.height,
tool_call_id: output.tool_call_id,
};
writeResponsesAttachment(res, tracker, attachment, metadata);
}
return fileMetadata;
})().catch((error) => {
logger.error('Error processing code output:', error);
return null;
}),
);
}
};
}
module.exports = {
getDefaultHandlers,
createToolEndCallback,
createResponsesToolEndCallback,
};