resolves #3117

* Add handling to resoning models for Generic OpenAI connector
resolves #3177

* linting

fix: fix UserMenu rendered twice on Main page

* wip onboarding translations

* add normalized EN reference for languages

* add zh/zh-tw translations

* Fix translations

resolves #3160

Add in-text citations as well for PPLX token streaming
handle timeouts for stream/buffer hanging

* Enable `num_ctx` to match defined chunk length in ollama embedder

* remove console

connect #3023
Note: depends on user naming the deployment correctly.

* Add tokenizer improvments via Singleton class
linting

* dev build

* Estimation fallback when string exceeds a fixed byte size

* Add notice to tiktoken on backend

* wip agent ui animation

* WIP agent ui revision

* linting

* simplify css

* memoize agent responses

* patch hook memo issue

* dev build

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>

* Add ability to disable default agent skills

* debug build

* remove native llm

* remove node-llama-cpp from dockerfile

* remove unneeded items from dockerfile

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>

* Breakout LaTeX plugin for modification

* backport regular markdown link

Add better data-handling for unknown providers

* wip change workspace llm settings

* allow editing of workspace llm and agent config inside workspace settings

* lint + put back deleted comment

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>

* implement dynamic fetching of togetherai models

* implement caching for togetherai models

* update gitignore for togetherai model caching

* Remove models.json from git tracking

* Remove .cached_at from git tracking

* lint

* revert unneeded change

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>

* bump perplexity models

---------

Co-authored-by: Timothy Carambat <rambat1010@gmail.com>