feat: OpenRouter Support & Improve Model Fetching ⇆ (#936)

* chore(ChatGPTClient.js): add support for OpenRouter API
chore(OpenAIClient.js): add support for OpenRouter API

* chore: comment out token debugging

* chore: add back streamResult assignment

* chore: remove double condition/assignment from merging

* refactor(routes/endpoints): -> controller/services logic

* feat: add openrouter model fetching

* chore: remove unused endpointsConfig in cleanupPreset function

* refactor: separate models concern from endpointsConfig

* refactor(data-provider): add TModels type and make TEndpointsConfig adaptible to new endpoint keys

* refactor: complete models endpoint service in data-provider

* refactor: onMutate for refreshToken and login, invalidate models query

* feat: complete models endpoint logic for frontend

* chore: remove requireJwtAuth from /api/endpoints and /api/models as not implemented yet

* fix: endpoint will not be overwritten and instead use active value

* feat: openrouter support for plugins

* chore(EndpointOptionsDialog): remove unused recoil value

* refactor(schemas/parseConvo): add handling of secondaryModels to use first of defined secondary models, which includes last selected one as first, or default to the convo's secondary model value

* refactor: remove hooks from store and move to hooks
refactor(switchToConversation): make switchToConversation use latest recoil state, which is necessary to get the most up-to-date models list, replace wrapper function
refactor(getDefaultConversation): factor out logic into 3 pieces to reduce complexity.

* fix: backend tests

* feat: optimistic update by calling newConvo when models are fetched

* feat: openrouter support for titling convos

* feat: cache models fetch

* chore: add missing dep to AuthContext useEffect

* chore: fix useTimeout types

* chore: delete old getDefaultConvo file

* chore: remove newConvo logic from Root, remove console log from api models caching

* chore: ensure bun is used for building in b:client script

* fix: default endpoint will not default to null on a completely fresh login (no localStorage/cookies)

* chore: add openrouter docs to free_ai_apis.md and .env.example

* chore: remove openrouter console logs

* feat: add debugging env variable for Plugins

docs/install/free_ai_apis.md

@@ -1,8 +1,34 @@
 # Free AI APIs
 
-There are APIs offering free access to AI APIs via reverse proxy, and one of the major players, compatible with LibreChat, is NagaAI.
+There are APIs offering free/free-trial access to AI APIs via reverse proxy.
 
-Feel free to check out the others, but I haven't personally tested them: [Free AI APIs](https://github.com/NovaOSS/free-ai-apis)
+Here is a well-maintained public list of [Free AI APIs](https://github.com/NovaOSS/free-ai-apis) that may or may not be compatible with LibreChat
+
+### [OpenRouter](https://openrouter.ai/) ⇆ (preferred)
+
+While not completely free, you get free trial credits when you [sign up to OpenRouter](https://openrouter.ai/), a legitimate proxy service to a multitude of LLMs, both closed and open source, including:
+- OpenAI models (great if you are barred from their API for whatever reason)
+- Anthropic Claude models (same as above)
+- Meta's Llama models
+- pygmalionai/mythalion-13b
+- and many more open source models. Newer integrations are usually discounted, too!
+
+OpenRouter is so great, I decided to integrate it to the project as a standalone feature.
+
+**Setup:**
+- Signup to [OpenRouter](https://openrouter.ai/) and create a key. You should name it and set a limit as well.
+- Set the environment variable `OPENROUTER_API_KEY` in your .env file to the key you just created.
+- Restart your LibreChat server and use the OpenAI or Plugins endpoints.
+
+**Notes:** 
+- [TODO] **In the future, you will be able to set up OpenRouter from the frontend as well.**
+- This will override the official OpenAI API or your reverse proxy settings for both Plugins and OpenAI.
+- On initial setup, you may need to refresh your page twice to see all their supported models populate automatically.
+- Plugins: Functions Agent works with OpenRouter when using OpenAI models.
+- Plugins: Turn functions off to try plugins with non-OpenAI models (ChatGPT plugins will not work and others may not work as expected).
+- Plugins: Make sure `PLUGINS_USE_AZURE` is not set in your .env file when wanting to use OpenRouter and you have Azure configured.
+
+> ⚠️ OpenRouter is in a category of its own, and is highly recommended over the "free" services below. NagaAI and other 'free' API proxies tend to have intermittent issues, data leaks, and/or problems with the guidelines of the platforms they advertise on. Use the below at your own risk.
 
 ### NagaAI