LibreChat/api/server/services/start/tools.js
Joseph Licata 200098d992
🍌 feat: Gemini Image Generation Tool (Nano Banana) (#10676)
* Added fully functioning Agent Tool supporting Google's Nano Banana

* 🔧 refactor: Update Google credentials handling in GeminiImageGen.js

* Refactored the credentials path to follow a consistent pattern with other Google service integrations, allowing for an environment variable override.
* Updated documentation in README-GeminiNanoBanana.md to reflect the new credentials handling approach and removed references to hardcoded paths.

* 🛠️ refactor: Remove unnecessary whitespace in handleTools.js

* 🔧 feat: Update Gemini Image Generation Tool

- Bump @google/genai package version to ^1.19.0 for improved functionality.
- Refactor GeminiImageGen to createGeminiImageTool for better clarity and consistency.
- Enhance manifest.json for Gemini Image Tools with updated descriptions and icon.
- Add SVG icon for Gemini Image Tools.
- Implement progress tracking for Gemini image generation in the UI.
- Introduce new toolkit and context handling for image generation tools.

This update improves the Gemini image generation capabilities and user experience.

* 🗑️ chore: Remove outdated Gemini image generation PNG and update SVG icon

- Deleted the obsolete PNG file for Gemini image generation.
- Updated the SVG icon with a new design featuring a gradient and shadow effect, enhancing visual appeal and consistency.

* fix: ESLint formatting and unused variable in GeminiImageGen

* fix: Update default model to gemini-2.5-flash-image

*  feat: Enhance Gemini Image Generation Configuration

- Updated .env.example to include new environment variables for Google Cloud region, service account configuration, and Gemini API key options.
- Modified GeminiImageGen.js to support both user-provided API keys and Vertex AI service accounts, improving flexibility in client initialization.
- Updated manifest.json to reflect changes in authentication methods for the Gemini Image Tools.
- Bumped @google/genai package version to 1.19.0 in package-lock.json for compatibility with new features.

* 🔧 fix: Format Default Service Key Path in GeminiImageGen.js

- Adjusted the return statement in getDefaultServiceKeyPath function for improved readability by formatting it across multiple lines. This change enhances code clarity without altering functionality.

*  feat: Enhance Gemini Image Generation with Token Usage Tracking

- Added `recordTokenUsage` function to track token usage for balance management.
- Integrated token recording into the image generation process.
- Updated Gemini image generation tool to accept optional `aspectRatio` and `imageSize` parameters for improved image customization.
- Updated token values for new Gemini models in the transaction model.
- Improved documentation for image generation tool descriptions and parameters.

*  feat: Add new Gemini models for image generation token limits

- Introduced token limits for 'gemini-3-pro-image' and 'gemini-2.5-flash-image' models.
- Updated token values to enhance the Gemini image generation capabilities.

* 🔧 fix: Update Google Service Key Path for Consistency in Initialization (#11001)

* 🔧 refactor: Update GeminiImageGen for improved file handling and path resolution

- Changed the default service key path to use process.cwd() for better compatibility.
- Replaced synchronous file system operations with asynchronous promises for mkdir and writeFile, enhancing performance and error handling.
- Added error handling for credential file access to prevent crashes when the file does not exist.

* 🔧 refactor: Update GeminiImageGen to streamline API key handling

- Refactored API key checks to improve clarity and consistency.
- Removed redundant checks for user-provided keys, enhancing code readability.
- Ensured proper logging for API key usage across different configurations.

* 🔧 fix: Update GeminiImageGen to handle imageSize support conditionally

- Added a check to ensure imageSize is only applied if the gemini model does not include 'gemini-2.5-flash-image', improving compatibility.
- Enhanced the logic for setting imageConfig to prevent potential issues with unsupported configurations.

* 🔧 refactor: Simplify local storage condition in createGeminiImageTool function

* 🔧 feat: Enhance image format handling in GeminiImageGen with conversion support

* 🔧 refactor: Streamline API key initialization in GeminiImageGen

- Simplified the handling of API keys by removing redundant checks for user-provided keys.
- Updated logging to reflect the new priority order for API key usage, enhancing clarity and consistency.
- Improved code readability by consolidating key retrieval logic.

---------

Co-authored-by: Dev Bhanushali <dev.bhanushali@hingehealth.com>
Co-authored-by: Danny Avila <danny@librechat.ai>
2026-01-03 11:26:46 -05:00

133 lines
4.3 KiB
JavaScript

const fs = require('fs');
const path = require('path');
const { Tool } = require('@langchain/core/tools');
const { Calculator } = require('@librechat/agents');
const { logger } = require('@librechat/data-schemas');
const { zodToJsonSchema } = require('zod-to-json-schema');
const { Tools, ImageVisionTool } = require('librechat-data-provider');
const { getToolkitKey, oaiToolkit, ytToolkit, geminiToolkit } = require('@librechat/api');
const { toolkits } = require('~/app/clients/tools/manifest');
/**
* Loads and formats tools from the specified tool directory.
*
* The directory is scanned for JavaScript files, excluding any files in the filter set.
* For each file, it attempts to load the file as a module and instantiate a class, if it's a subclass of `StructuredTool`.
* Each tool instance is then formatted to be compatible with the OpenAI Assistant.
* Additionally, instances of LangChain Tools are included in the result.
*
* @param {object} params - The parameters for the function.
* @param {string} params.directory - The directory path where the tools are located.
* @param {Array<string>} [params.adminFilter=[]] - Array of admin-defined tool keys to exclude from loading.
* @param {Array<string>} [params.adminIncluded=[]] - Array of admin-defined tool keys to include from loading.
* @returns {Record<string, FunctionTool>} An object mapping each tool's plugin key to its instance.
*/
function loadAndFormatTools({ directory, adminFilter = [], adminIncluded = [] }) {
const filter = new Set([...adminFilter]);
const included = new Set(adminIncluded);
const tools = [];
/* Structured Tools Directory */
const files = fs.readdirSync(directory);
if (included.size > 0 && adminFilter.length > 0) {
logger.warn(
'Both `includedTools` and `filteredTools` are defined; `filteredTools` will be ignored.',
);
}
for (const file of files) {
const filePath = path.join(directory, file);
if (!file.endsWith('.js') || (filter.has(file) && included.size === 0)) {
continue;
}
let ToolClass = null;
try {
ToolClass = require(filePath);
} catch (error) {
logger.error(`[loadAndFormatTools] Error loading tool from ${filePath}:`, error);
continue;
}
if (!ToolClass || !(ToolClass.prototype instanceof Tool)) {
continue;
}
let toolInstance = null;
try {
toolInstance = new ToolClass({ override: true });
} catch (error) {
logger.error(
`[loadAndFormatTools] Error initializing \`${file}\` tool; if it requires authentication, is the \`override\` field configured?`,
error,
);
continue;
}
if (!toolInstance) {
continue;
}
if (filter.has(toolInstance.name) && included.size === 0) {
continue;
}
if (included.size > 0 && !included.has(file) && !included.has(toolInstance.name)) {
continue;
}
const formattedTool = formatToOpenAIAssistantTool(toolInstance);
tools.push(formattedTool);
}
const basicToolInstances = [
new Calculator(),
...Object.values(oaiToolkit),
...Object.values(ytToolkit),
...Object.values(geminiToolkit),
];
for (const toolInstance of basicToolInstances) {
const formattedTool = formatToOpenAIAssistantTool(toolInstance);
let toolName = formattedTool[Tools.function].name;
toolName = getToolkitKey({ toolkits, toolName }) ?? toolName;
if (filter.has(toolName) && included.size === 0) {
continue;
}
if (included.size > 0 && !included.has(toolName)) {
continue;
}
tools.push(formattedTool);
}
tools.push(ImageVisionTool);
return tools.reduce((map, tool) => {
map[tool.function.name] = tool;
return map;
}, {});
}
/**
* Formats a `StructuredTool` instance into a format that is compatible
* with OpenAI's ChatCompletionFunctions. It uses the `zodToJsonSchema`
* function to convert the schema of the `StructuredTool` into a JSON
* schema, which is then used as the parameters for the OpenAI function.
*
* @param {StructuredTool} tool - The StructuredTool to format.
* @returns {FunctionTool} The OpenAI Assistant Tool.
*/
function formatToOpenAIAssistantTool(tool) {
return {
type: Tools.function,
[Tools.function]: {
name: tool.name,
description: tool.description,
parameters: zodToJsonSchema(tool.schema),
},
};
}
module.exports = {
loadAndFormatTools,
};