👤 feat: User Placeholder Variables for Custom Endpoint Headers (#7993)

* 🔧 refactor: move `processMCPEnv` from `librechat-data-provider` and move to `@librechat/api`

* 🔧 refactor: Update resolveHeaders import paths

* 🔧 refactor: Enhance resolveHeaders to support user and custom variables

- Updated resolveHeaders function to accept user and custom user variables for placeholder replacement.
- Modified header resolution in multiple client and controller files to utilize the enhanced resolveHeaders functionality.
- Added comprehensive tests for resolveHeaders to ensure correct processing of user and custom variables.

* 🔧 fix: Update user ID placeholder processing in env.ts

* 🔧 fix: Remove arguments passing this.user rather than req.user

- Updated multiple client and controller files to call resolveHeaders without the user parameter

* 🔧 refactor: Enhance processUserPlaceholders to be more readable / less nested

* 🔧 refactor: Update processUserPlaceholders to pass all tests in mpc.spec.ts and env.spec.ts

* chore: remove legacy ChatGPTClient

* chore: remove LLM initialization code

* chore: initial deprecation removal of `gptPlugins`

* chore: remove cohere-ai dependency from package.json and package-lock.json

* chore: update brace-expansion to version 2.0.2 and add license information

* chore: remove PluginsClient test file

* chore: remove legacy

* ci: remove deprecated sendMessage/getCompletion/chatCompletion tests

---------

Co-authored-by: Dustin Healy <54083382+dustinhealy@users.noreply.github.com>

api/server/controllers/agents/llm.js

@@ -1,106 +0,0 @@
-const { HttpsProxyAgent } = require('https-proxy-agent');
-const { resolveHeaders } = require('librechat-data-provider');
-const { createLLM } = require('~/app/clients/llm');
-
-/**
- * Initializes and returns a Language Learning Model (LLM) instance.
- *
- * @param {Object} options - Configuration options for the LLM.
- * @param {string} options.model - The model identifier.
- * @param {string} options.modelName - The specific name of the model.
- * @param {number} options.temperature - The temperature setting for the model.
- * @param {number} options.presence_penalty - The presence penalty for the model.
- * @param {number} options.frequency_penalty - The frequency penalty for the model.
- * @param {number} options.max_tokens - The maximum number of tokens for the model output.
- * @param {boolean} options.streaming - Whether to use streaming for the model output.
- * @param {Object} options.context - The context for the conversation.
- * @param {number} options.tokenBuffer - The token buffer size.
- * @param {number} options.initialMessageCount - The initial message count.
- * @param {string} options.conversationId - The ID of the conversation.
- * @param {string} options.user - The user identifier.
- * @param {string} options.langchainProxy - The langchain proxy URL.
- * @param {boolean} options.useOpenRouter - Whether to use OpenRouter.
- * @param {Object} options.options - Additional options.
- * @param {Object} options.options.headers - Custom headers for the request.
- * @param {string} options.options.proxy - Proxy URL.
- * @param {Object} options.options.req - The request object.
- * @param {Object} options.options.res - The response object.
- * @param {boolean} options.options.debug - Whether to enable debug mode.
- * @param {string} options.apiKey - The API key for authentication.
- * @param {Object} options.azure - Azure-specific configuration.
- * @param {Object} options.abortController - The AbortController instance.
- * @returns {Object} The initialized LLM instance.
- */
-function initializeLLM(options) {
-  const {
-    model,
-    modelName,
-    temperature,
-    presence_penalty,
-    frequency_penalty,
-    max_tokens,
-    streaming,
-    user,
-    langchainProxy,
-    useOpenRouter,
-    options: { headers, proxy },
-    apiKey,
-    azure,
-  } = options;
-
-  const modelOptions = {
-    modelName: modelName || model,
-    temperature,
-    presence_penalty,
-    frequency_penalty,
-    user,
-  };
-
-  if (max_tokens) {
-    modelOptions.max_tokens = max_tokens;
-  }
-
-  const configOptions = {};
-
-  if (langchainProxy) {
-    configOptions.basePath = langchainProxy;
-  }
-
-  if (useOpenRouter) {
-    configOptions.basePath = 'https://openrouter.ai/api/v1';
-    configOptions.baseOptions = {
-      headers: {
-        'HTTP-Referer': 'https://librechat.ai',
-        'X-Title': 'LibreChat',
-      },
-    };
-  }
-
-  if (headers && typeof headers === 'object' && !Array.isArray(headers)) {
-    configOptions.baseOptions = {
-      headers: resolveHeaders({
-        ...headers,
-        ...configOptions?.baseOptions?.headers,
-      }),
-    };
-  }
-
-  if (proxy) {
-    configOptions.httpAgent = new HttpsProxyAgent(proxy);
-    configOptions.httpsAgent = new HttpsProxyAgent(proxy);
-  }
-
-  const llm = createLLM({
-    modelOptions,
-    configOptions,
-    openAIApiKey: apiKey,
-    azure,
-    streaming,
-  });
-
-  return llm;
-}
-
-module.exports = {
-  initializeLLM,
-};