* Use `@agent` via dev API

* Move EphemeralEventListener to same file as agent

* Refactor api endpoint chat handler to its own function
remove legacy `chatWithWorkspace` and cleanup `index.js`

* Add `sessionId` in dev API to partition chats logically statelessly

remove legacy `chatWithWorkspace` and cleanup `index.js`

support multiple preset prompts in single message

* Add multimodality support

* Add Bedrock, KoboldCpp,LocalAI,and TextWebGenUI multi-modal

* temp dev build

* patch bad import

* noscrolls for windows dnd

* noscrolls for windows dnd

* update README

* update README

* add multimodal check

Add type defs to helpers

fix query mode always responding with refusal message on develop api openai compatible endpoints

* log query refusals to workspace chats but hide in ui

* linting

---------

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

* Improve RAG responses via source backfilling

* Hide irrelevant citations from UI

resolves #1439

* WIP slash presets

* WIP slash command customization CRUD + validations complete

* backend slash command support

* fix permission setting on new slash commands
rework form submit and pattern on frontend

* Add field updates for hooks,
required=true to field
add user<>command constraint to keep them unique
enforce uniquness via teritary uid field on table for multi and non-multi user

* reset migration

---------

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

* if document is pinned, do not give queryRefusalResponse message

* forgot embed.js patch

---------

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

clear chat window on /reset

* Remove restrictions on pinned documents to use more contet

* update comment

* Customize refusal response for `query` mode

* remove border for desktop

* Update all vector dbs to filter duplicate parents

* cleanup

V1 of agent support via built-in `@agent` that can be invoked alongside normal workspace RAG chat.

* Enable per-workspace provider/model combination

* cleanup

* remove resetWorkspaceChatModels and wipeWorkspaceModelPreference to prevent workspace from resetting model

* add space

---------

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

* Enable ability to do full-text query on documents
Show alert modal on first pin for client
Add ability to use pins in stream/chat/embed

* typo and copy update

* simplify spread of context and sources

* refactor stream/chat/embed-stram to be a single execution logic path so that it is easier to maintain and build upon

* no thread in sync chat since only api uses it
adjust import locations

* WIP RLHF works on historical messages

* refactor Actions component

* completed RLHF up and down votes for chats

* add defaults for HistoricalMessage params

* refactor RLHF implmenation
remove forwardRef on history items to prevent rerenders

* remove dup id

* Add rating to CSV output

---------

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

* Implement workspace thread that is compatible with legacy versions

* last touches

* comment on chat qty enforcement

* WIP embedded app

* WIP got response from backend in embedded app

* WIP streaming prints to embedded app

* implemented streaming and tailwind min for styling into embedded app

* WIP embedded app history functional

* load params from script tag into embedded app

* rough in modularization of embed chat
cleanup dev process for easier dev support
move all chat to components
todo: build process
todo: backend support

* remove eslint config

* Implement models and cleanup embed chat endpoints
Improve build process for embed
prod minification and bundle size awareness
WIP

* forgot files

* rename to embed folder

* introduce chat modal styles

* add middleware validations on embed chat

* auto open param and default greeting

* reset chat history

* Admin embed config page

* Admin Embed Chats mgmt page

* update embed

* nonpriv

* more style support
reopen if chat was last opened

* update comments

* remove unused imports

* allow change of workspace for embedconfig

* update failure to lookup message

* update reset script

* update instructions

* Add more styling options
Add sponsor text at bottom
Support dynamic container height
Loading animations

* publish new embed script

* Add back syntax highlighting and keep bundle small via dynamic script build

* add hint

* update readme

* update copy model for snippet with link to styles

---------

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

* create configurable topN per workspace

* Update TopN UI text
Fix fallbacks for all providers
Add SQLite CHECK to TOPN value

* merge with master
Update zilliz provider for variable TopN

---------

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

* add support for mistral api

* update docs to show support for Mistral

* add default temp to all providers, suggest different results per provider

---------

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

* WIP model selection per workspace (migrations and openai saves properly

* revert OpenAiOption

* add support for models per workspace for anthropic, localAi, ollama, openAi, and togetherAi

* remove unneeded comments

* update logic for when LLMProvider is reset, reset Ai provider files with master

* remove frontend/api reset of workspace chat and move logic to updateENV
add postUpdate callbacks to envs

* set preferred model for chat on class instantiation

* remove extra param

* linting

* remove unused var

* refactor chat model selection on workspace

* linting

* add fallback for base path to localai models

---------

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

* Query mode to return no-result when no context found

* update default error for sync chat

* remove unnecessary type conversion

* add Together AI LLM support

* update readme to support together ai

* Patch togetherAI implementation

* add model sorting/option labels by organization for model selection

* linting + add data handling for TogetherAI

* change truthy statement
patch validLLMSelection method

---------

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

resolves #492