fix CI (#1884)

Refactor token parameters to standardize naming across models and generation settings

Omni multimodality (#1880)

HuggingChat 2026 (#1875)

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

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

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

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: disable caching on OpenAI-compatible endpoint type

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

Fix/oai parameters 1552 (#1557)

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

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

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

fix(openai): do not throw "Generation failed" when finish_reason="length" (#1429)

Generic Multimodal Support Fixed (#1147)

Revert "Generic Multimodal Support" (#1146)

Generic Multimodal Support (#1021)

Extend endpointOai.ts to allow usage of extra sampling parameters (#1032)

Move vars to dynamic, add metrics (#1085)

Expose sampling controls in assistants (#955) (#959)

Make sure preprompt is set on open ai endpoint type (#913)

Allow customising defaultQuery for native Azure OpenAI support (#822)

Conversation trees (#223) (#807)

fix continue button on openai endpoint (#803)

Several QoL contributions (#760)

[JS] use shorthand notation (#711)

Support websearch for openAI chat completion mode (#608)

Add support for passing an API key or any other custom token in the authorization header (#579)

Modular backends & support for openAI & AWS endpoints (#541)