feat(markdown): allow video and audio tags (#2037)

fix(mcp): communicate tool errors to LLM to prevent hallucinated success (#2036)

MCP Tool Progress Notifications and MCP SDK bump. (#2030)

fix: improve logs (#2018)

fix(log): use logger (#2016)

Org billing (#1995)

Guard MCP reasoning stream from whitespace <think> blocks

Expand image field support in tool prompts and rules

Refactor file handling for multimodal chat messages

Update image ref resolution to use conversation order

MCP: Image refs (#1987)

run format, lint, and type check

Add user token to OpenAI API requests

mcp: clarify pre-safety empty selection vs safety rejection; trim URLs in isValidUrl to avoid whitespace false negatives

mcp: add detailed console logging for MCP flow and tool listing

Revert "trying a MCP fix"

trying a MCP fix

MCP (#1981)

Add provider info to router metadata in chat messages

Refactor yield object to use shorthand property

Remove unused import and reformat import statement

Remove reasoning

Update title generation prompt and add GitHub link

Abort (#1924)

Refine title generation prompt and logic

Store oauth token in DB + use it when doing API calls (#1885)

fix CI (#1884)

Refactor token parameters to standardize naming across models and generation settings

HuggingChat 2026 (#1875)

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

fix: remove redundant status update in streaming

fix: stop button working properly

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

New `InferenceClient` endpoint type (#1813)

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

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

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

fix: trigger redeploy

fix: give more buffer to reasoning

feat: improve task model tool calling (#1755)

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

fix: improve tasks performance

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)

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

Added currentDate variable to Dynamic Prompt (#1648)

Anthropic Tool Support (#1594)

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