feat: UI for advanced reasoning models (#1605)

[feat] Add support for endpoint web sources (#1544)

feat(endpoints): Add conv ID to headers passed to TGI (#1511)

fix: multimodal on TGI endpoint type (#1491)

fix(front): fix delay after end of streaming tokens

fix(websearch): fix `webSearch` flag use for model with tool use (#1480)

fix(assistants): remove websearch from assistant tool options, add websearch in backend logic (#1465)

fix(assistants): only enable websearch on assistants with RAG (#1452)

feat(assistants): use community tools in assistants (#1421)

feat(tools): use gradio ETA for tools (#1411)

fix(tools): make show output button work

fix(stream): add keep alive stream event

fix(tools): show error cause

fix(logs): better error logging

feat(tools): more detailed errors from tools

Community tools (#1250)

fix(env) enable LLM_SUMMARIZATION (#1379)

fix(logs): improve logging

fix(tools): improve json parsing (#1356)

feat(models): Llama 3.1 support (#1355)

fix(env): change env var typo (#1307)

Revert "Request less `max_new_tokens` on tools and reduce `truncate` on CMD R+ (#1292)"

Request less `max_new_tokens` on tools and reduce `truncate` on CMD R+ (#1292)

fix websearch on assistants (#1244)

Trim trailing comma on tool calls (#1229)

feat: skip tools when all disabled (#1205)

Generic tool error msg "Error occurred" (#1193)

Simplify tool error handling (#1168)

Bypass spaces tools rate limit (#1167)

Add metrics for models, tools, websearch (#1186)

Ony call tools if model.tools is true (#1172)

Add error message for tools (#1163)

Function calling (#996)