fix: catch errors more gracefully in reasoning specific calls

fix: set alg in auth if not set by user

feat: explicit config of id token alg (#1567) (#1568)

feat(openai): added support for o1 reasoning models (#1618)

fix: error reporting in tool calling

feat: improve tool calling & add tools to qwen 2.5 72b (#1615)

fix: summary prompt

feat: UI for advanced reasoning models (#1605)

Anthropic PDF Beta Support (#1571)

fix: default auth not properly treated if undefined

feat: aggregate model votes in metrics

fix: remove hf token from tool calling

fix(websearch): block protocols on playwright (#1579)

fix: remove accessToken min length for llama.cpp endpoint

feat(migrations): clean up empty conversations from db (#1561)

Fix/oai parameters 1552 (#1557)

fix: move thumbnail fonts to server side

fix: better websearch quotes

feat: add sources for websearch (#1551)

fix: only show playground button for models that are available

feat: paste long context as plaintext files (#1549)

feat: Add a model config option to disable system prompts (#1539)

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

fix(endpoint): fallback to hf token for openai endpoint type

fix: use custom tool template only for huggingchat

feat: use model id as fallback for finding a tokenizer (#1535)

[fix] Fix typo in Vertex (#1531)

feat(models): add `nvidia/Llama-3.1-Nemotron-70B-Instruct-HF` (#1527)

[vertex] Add PDF/plein texts support (#1520)

feat(security): add cookie samesite & security settings (#1517)

feat: Update featured workflow to allow user to submit featured requests (#1510)

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

feat(tools): Basic tool support for OpenAI models (#1447)

Add support for model version in Vertex AI (#1496)

Fix: Cohere Endpoint - Add Support for Tools (#1490)

fix: multimodal on TGI endpoint type (#1491)

feat: add link to API playground for compatible models (#1488)

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

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

fix(endpoints): make bedrock import optional (#1468)

fix(tools): tool call name must be a valid python variable name (#1466)

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

feat(conv): let user switch models on conversations with deprecated models (#1462)

feat(models): add transferTo property on old models (#1453)

fix(continue): fix continue feature (#1459)

Move Google GenAI API key to env file instead (#1448)

feat: add support for multimodal in Vertex (#1338)

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

Add support for Anthropic models via AWS Bedrock (#1413)

fix(tools): regex validation