model 30

Auto-complete missing model display name, context window, max output tokens, and reasoning efforts in the llm-pi-ai settings namespace.

Delegate light subagent tasks to cheaper models: automatic Flash/Pro routing for DeepSeek Harness subagent calls, with /delegate overrides, budget caps, and a routing-ledger panel.

DeepSeek Harness plugin: control which models appear in the model selector — per-model switches, provider-level batch toggles, and search. Hiding a model never touches your provider config or running sessions.

DeepSeek Harness plugin with two default model-and-reasoning shortcuts above the composer and optional Settings customization.

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam

在模型座左侧显示当前模型所属提供商（显示名称优先，回退 Provider ID）。纯运行时装饰，不改动原生页面源码。

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

dsh plugin: switch named model profiles (default model, think level, per-subagent models) interactively via the host ask-user flow — one implementation for the TUI and web surfaces, a clean fast-fail on headless

在模型座左侧显示当前模型所属提供商（显示名称优先，回退 Provider ID）。纯运行时装饰，不改动原生页面源码。

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。

Override the DSH default model via DSH_MODEL env var (format: provider/model). Lets you switch models per invocation without touching settings.yaml.

DeepSeek Harness plugin: keep every model request inside an allowed set per provider, redirect or refuse the rest, and warn when a request would make a llama.cpp router reload models

给模型选择菜单（输入栏模型座位）加一个搜索框，按模型名 / 模型 ID / 描述 / provider 名称过滤。

在 DSH 主对话每条 assistant 回复旁展示该条回复实际使用的 provider / model 徽章（可选附带 reasoning effort）

DSH host plugin: makes /compact use a user-chosen provider/model instead of the session's chat model, configurable in Settings.

Run the same prompt through every model you have, and see the difference without squinting.

DSH host plugin: enforces the subagent-model-selection whitelist for subagent, agent teams, and every other child-Agent creation.

「设置 → 模型调参」页：模型参数（推理档位/上下文/最大输出/输入模态）、「用途」页（标题生成独立路由，替换宿主标题行）、「绘图」页（绘图模型配置 + generate_image 工具 + 直接绘图面板）。v2 合并了原 dsh-plugin-title-model 与 dsh-plugin-image-generation。

DSH model channel manager: roundrobin failover engine (host) + model config view tab (client).

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。

Better subagents for DeepSeek Harness: choose the default subagent model, see each subagent conversation's model in its header, and wait for subagents with a blocking wait_subagents tool instead of sleeping or polling.

Routes each DSH agent request to the least powerful model that can handle it — flash for simple work, pro for complex, vision for images — with a settings page and live composer readout.

模型能力管理：为手写模型设置图片输入与推理强度、线路系统消息角色（可一键继承目录模型的精确能力）。

DSH web plugin: searchable model selector for DeepSeek Harness WebUI

Configurable model-request retry limit for DeepSeek Harness (Settings → General).

Searchable model selector for DeepSeek Harness (DSH) web: a faithful fork of the native model seat (Model/Effort, provider-grouped list, reasoning effort) with a search box at the top of the model list that filters while you type.

DSH 模型收藏插件:收藏的模型置顶显示、同名模型标注 provider、模型/推理等级双按钮、每模型 effort 记忆

模型能力管理：为手写模型设置图片输入与推理强度、线路系统消息角色（可一键继承目录模型的精确能力）。

Annotate every subagent with the model route it actually ran on: a badge line in each parent-catalog row and a readout in a child session's own header.