LibreChat/packages/api/src/tools/definitions.ts

226 lines
6.8 KiB
TypeScript
Raw Normal View History

🦥 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
/**
* @fileoverview Tool definitions loader for event-driven mode.
* Loads tool definitions without creating tool instances for efficient initialization.
*
* @module packages/api/src/tools/definitions
*/
import { Constants, actionDelimiter } from 'librechat-data-provider';
import type { AgentToolOptions } from 'librechat-data-provider';
import type { LCToolRegistry, JsonSchemaType, LCTool, GenericTool } from '@librechat/agents';
import { buildToolClassification, type ToolDefinition } from './classification';
import { getToolDefinition } from './registry/definitions';
import { resolveJsonSchemaRefs } from '~/mcp/zod';
export interface MCPServerTool {
function?: {
name?: string;
description?: string;
parameters?: JsonSchemaType;
};
}
export type MCPServerTools = Record<string, MCPServerTool>;
export interface LoadToolDefinitionsParams {
/** User ID for MCP server tool lookup */
userId: string;
/** Agent ID for tool classification */
agentId: string;
/** Agent's tool list (tool names/identifiers) */
tools: string[];
/** Agent-specific tool options */
toolOptions?: AgentToolOptions;
/** Whether deferred tools feature is enabled */
deferredToolsEnabled?: boolean;
}
export interface ActionToolDefinition {
name: string;
description?: string;
parameters?: JsonSchemaType;
}
export interface LoadToolDefinitionsDeps {
/** Gets MCP server tools - first checks cache, then initializes server if needed */
getOrFetchMCPServerTools: (userId: string, serverName: string) => Promise<MCPServerTools | null>;
/** Checks if a tool name is a known built-in tool */
isBuiltInTool: (toolName: string) => boolean;
/** Loads auth values for tool search (passed to buildToolClassification) */
loadAuthValues: (params: {
userId: string;
authFields: string[];
}) => Promise<Record<string, string>>;
/** Loads action tool definitions (schemas) from OpenAPI specs */
getActionToolDefinitions?: (
agentId: string,
actionToolNames: string[],
) => Promise<ActionToolDefinition[]>;
}
export interface LoadToolDefinitionsResult {
toolDefinitions: (ToolDefinition | LCTool)[];
toolRegistry: LCToolRegistry;
hasDeferredTools: boolean;
}
const mcpToolPattern = /_mcp_/;
/**
* Loads tool definitions without creating tool instances.
* This is the efficient path for event-driven mode where tools are loaded on-demand.
*/
export async function loadToolDefinitions(
params: LoadToolDefinitionsParams,
deps: LoadToolDefinitionsDeps,
): Promise<LoadToolDefinitionsResult> {
const { userId, agentId, tools, toolOptions = {}, deferredToolsEnabled = false } = params;
const { getOrFetchMCPServerTools, isBuiltInTool, loadAuthValues, getActionToolDefinitions } =
deps;
const emptyResult: LoadToolDefinitionsResult = {
toolDefinitions: [],
toolRegistry: new Map(),
hasDeferredTools: false,
};
if (!tools || tools.length === 0) {
return emptyResult;
}
const mcpServerToolsCache = new Map<string, MCPServerTools>();
const mcpToolDefs: ToolDefinition[] = [];
const builtInToolDefs: ToolDefinition[] = [];
let actionToolDefs: ToolDefinition[] = [];
const actionToolNames: string[] = [];
const mcpAllPattern = `${Constants.mcp_all}${Constants.mcp_delimiter}`;
for (const toolName of tools) {
if (toolName.includes(actionDelimiter)) {
actionToolNames.push(toolName);
continue;
}
if (!mcpToolPattern.test(toolName)) {
if (!isBuiltInTool(toolName)) {
continue;
}
const registryDef = getToolDefinition(toolName);
if (!registryDef) {
continue;
}
builtInToolDefs.push({
name: toolName,
description: registryDef.description,
parameters: registryDef.schema as JsonSchemaType | undefined,
});
continue;
}
const parts = toolName.split(Constants.mcp_delimiter);
const serverName = parts[parts.length - 1];
if (!mcpServerToolsCache.has(serverName)) {
const serverTools = await getOrFetchMCPServerTools(userId, serverName);
mcpServerToolsCache.set(serverName, serverTools || {});
}
const serverTools = mcpServerToolsCache.get(serverName);
if (!serverTools) {
continue;
}
if (toolName.startsWith(mcpAllPattern)) {
for (const [actualToolName, toolDef] of Object.entries(serverTools)) {
if (toolDef?.function) {
mcpToolDefs.push({
name: actualToolName,
description: toolDef.function.description,
parameters: toolDef.function.parameters
? resolveJsonSchemaRefs(toolDef.function.parameters)
: undefined,
serverName,
});
}
}
continue;
}
const toolDef = serverTools[toolName];
if (toolDef?.function) {
mcpToolDefs.push({
name: toolName,
description: toolDef.function.description,
parameters: toolDef.function.parameters
? resolveJsonSchemaRefs(toolDef.function.parameters)
: undefined,
serverName,
});
}
}
if (actionToolNames.length > 0 && getActionToolDefinitions) {
const fetchedActionDefs = await getActionToolDefinitions(agentId, actionToolNames);
actionToolDefs = fetchedActionDefs.map((def) => ({
name: def.name,
description: def.description,
parameters: def.parameters,
}));
}
const loadedTools = mcpToolDefs.map((def) => ({
name: def.name,
description: def.description,
mcp: true as const,
mcpJsonSchema: def.parameters,
})) as unknown as GenericTool[];
const classificationResult = await buildToolClassification({
userId,
agentId,
loadedTools,
loadAuthValues,
deferredToolsEnabled,
definitionsOnly: true,
agentToolOptions: toolOptions,
});
const { toolDefinitions, hasDeferredTools } = classificationResult;
const toolRegistry: LCToolRegistry = classificationResult.toolRegistry ?? new Map();
for (const actionDef of actionToolDefs) {
if (!toolRegistry.has(actionDef.name)) {
toolRegistry.set(actionDef.name, {
name: actionDef.name,
description: actionDef.description,
parameters: actionDef.parameters,
allowed_callers: ['direct'],
});
}
}
for (const builtInDef of builtInToolDefs) {
if (!toolRegistry.has(builtInDef.name)) {
toolRegistry.set(builtInDef.name, {
name: builtInDef.name,
description: builtInDef.description,
parameters: builtInDef.parameters,
allowed_callers: ['direct'],
});
}
}
const allDefinitions: (ToolDefinition | LCTool)[] = [
...toolDefinitions,
...actionToolDefs.filter((d) => !toolDefinitions.some((td) => td.name === d.name)),
...builtInToolDefs.filter((d) => !toolDefinitions.some((td) => td.name === d.name)),
];
return {
toolDefinitions: allDefinitions,
toolRegistry,
hasDeferredTools,
};
}