Plugins

Session model selector with search: two-stage loose matching (normalised substring first, subsequence as fallback, so glm53 finds GLM-5.3 and ds finds DeepSeek), providers with recent successful calls pinned first, and a reasoning-effort pane that remembers each model's last explicitly chosen effort.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

DeepSeek Harness model selector upgrade: one-level model & reasoning-effort picker with 5 Liang tiers, custom model aliases, and peak/off-peak price countdown.

Splits the composer model selector into a searchable, favorite-marking dropdown and a reasoning-effort slider, with Ctrl+P / Ctrl+T quick-switch shortcuts.