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

New `InferenceClient` endpoint type (#1813)

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

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

Anthropic Tool Support (#1594)

feat: new tool UI (#1630)

fix: error reporting in tool calling

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

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

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(tools): show error cause

feat(tools): more detailed errors from tools

Community tools (#1250)

fix(logs): improve logging

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

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

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)

Trim trailing comma on tool calls (#1229)

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)

Add error message for tools (#1163)

Function calling (#996)