refactor: new API & universal load functions (pt. 2) (#1847)

Revert "refactor: new API & universal load functions (#1743)"

refactor: new API & universal load functions (#1743)

feat(reasoning): support end token search across multiple chunks (#1838)

[WIP] - Add the pop-up search (Ctrl/Command + K) to search entire conversation history (#1823)

fix: remove quotes from search query to prevent exact match search (#1834)

fix: catch errors in default model

fix: remove redundant status update in streaming

fix: only import node-llama-cpp if needed and skip for huggingchat image

fix: stop button working properly

fix: make sure document parser is disabled if not required

fix: rm error in retrying when tool calls are not parsed properly

New `InferenceClient` endpoint type (#1813)

fix: build local llama (#1805)

feat: allow storing env variable in DB (#1802)

feat: allow strings in `MODELS` env var (#1791)

refactor: make env imports match the rest of the app in `adminToken.ts`

Enable/Disable reasoning summary using .env (#1760)

Fix system message handling to preserve user-configured system prompts (#1764)

feat: improve port detection on admin cli login

feat: admin CLI login (#1789)

fix: lint

fix: docker image llama.cpp error catching

Add `toolId` to ToolCall and use it in tool results (#1787)

fix: build llama.cpp locally in dockerfile (#1788)

feat: add a local endpoint type for inference directly from chat-ui (#1778)

feat(db): use in memory db when MONGODB_URL not set (#1773)

fix: trigger redeploy

fix: give more buffer to reasoning

fix(preprocessMessages): clarify web search context in final message content

feat: improve task model tool calling (#1755)

fix(endpoints): fix for tool calling on hf inference with openai endpoint type (#1754)

feat(openai): added support for non-streaming o1 (e.g. Azure) models (#1687)

fix: improve tasks performance

feat(model): configure Llama-3.1-8B-Instruct with OpenAI-compatible endpoint

feat(tasks): use tools for tasks if available (#1749)

fix: move FinalAnswer outside of reasoning processing blocks (#1717)

fix: handle no beginToken for token based reasoning models (#1713)

chores(svelte): migration to svelte 5 (#1685)

fix: bedrock prepareMessages parameters (#1686)

feat(chart): use inference proxy (#1688)

feat: add `deepseek-ai/DeepSeek-R1-Distill-Qwen-32B` to HuggingChat config (#1660)

Added currentDate variable to Dynamic Prompt (#1648)

feat(websearch): skip pages that dont return success (#1639)

Anthropic Tool Support (#1594)

add option to send user message as part of request body in assistant … (#1322)

Add support for Amazon Nova (#1629)

fix: disable caching on OpenAI-compatible endpoint type

feat: new tool UI (#1630)

fix: single step in cohere endpoint type (#1632)