Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models

Inline video preview for dsh-better-sidebar: plays .mp4/.webm/.mov/.mkv/.avi etc. in the sidebar editor with HTTP Range (seeking) support via a dedicated /video host route