model-selector 13

DeepSeek Harness 的增强模型选择器：单层菜单（搜索 + 分组）+ 底部内联推理强度（Effort）滑杆。

Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.

Peak / off-peak rate badges and switch countdown for DeepSeek Harness — per provider, per model, in the model selector and the composer tool row. Judges each provider by its own time zone and schedule instead of DeepSeek-only hours.

DSH 模型整理插件：输入框的模型下拉改为「供应商分组 + 模型二级折叠菜单」（含推理等级），并在模型设置页提供一个可拖拽的「供应商与模型顺序」浮窗。

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

A richer model-selection popup for DeepSeek Harness: provider-grouped models with descriptions, inline reasoning-effort chips, search and pinned favorites — replaces the composer's default ModelSelect.

Richer model picker for the DeepSeek Harness Web composer: a searchable provider select (with logos, model counts, and key status) above a keyboard-first, fuzzy-searchable model list grouped by provider, with favorites, recents, context-window/vision/reas

DSH 模型整理插件：输入框的模型下拉改为「供应商分组 + 模型二级折叠菜单」（含推理等级），并在模型设置页提供一个可拖拽的「供应商与模型顺序」浮窗。

模型医生：在对话输入区的模型选择菜单里，为每个模型选项追加「连通检测」与「删除」按钮——直接适配 DSH 官方模型菜单（按官方 DOM 契约精确定位，不依赖任何菜单渲染插件），检测直连各网关探测连通性/欠费/额度，删除直接从 llm-pi-ai 配置移除模型（自动备份配置文档）。

DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).

A grouped, searchable replacement for the DSH composer model selector.

将 DSH 聊天框模型选择改为先选择供应商、再选择模型。

Codex-style DeepSeek Harness model and reasoning selector with model-advertised effort levels, DSH-native themes, left-clipped radiation effects, and copy-ready reasoning-effort declaration guidance for custom-provider models.