124 results
Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.
Type-to-search filtering for DeepSeek Harness model selection lists
DeepSeek Harness plugin: LLM model selection & deployment analysis (deployability, VRAM, TTFT, latency, throughput, power for 38 models × 20 GPUs/NPUs)
Filter input for the composer model menu: case-insensitive list filtering with combobox keyboard navigation, rendered with the shipped menu design
dsh web 插件：自动配置模型思考档位与能力，并按 provider+model 记住最后选择的思考档位
Model availability tester panel in the Models settings page: one-click real streaming test per added model with TPS / first-token / elapsed metrics
Expose per-model thinking levels (reasoningEfforts) inside the Models settings card for a custom model API route.
Route selected models through an outbound proxy in DeepSeek Harness, falling back to a direct connection while that proxy is unavailable.
Platform and manufacturer grouped model picker for DeepSeek Harness
DeepSeek Harness plugin: shows model usage, plan quota and account balance in the session header — OpenCode Go plan usage (rolling / weekly / monthly) with the selected model's monthly cap, DeepSeek account balance, and Command Code 5-hour / weekly windows with remaining credits — each only while a matching model is the active selection.
DSH plugin: a virtual model-router provider that aggregates every configured provider and model, routes each request to the model's currently active provider, and ships a settings page for per-model provider ordering and switching.
Run the same prompt through every model you have, and see the difference without squinting.
Visual custom-provider presets and model switching for DeepSeek Harness Web.
Auto-populate and auto-update the list of llm-pi-ai providers' models. Turn the plugin on and off to update on-demand
自定义模型/提供方顺序：模型设置页里拖拽排序，宿主的模型列表按这份顺序返回（写回配置真源，备份去重且只留最近 N 份）
DSH 模型能力配置 UI：在「设置 → 模型」的每个提供方卡片内直接配置每个模型是否为视觉模型、以及可用的思考强度档位。
A grouped, searchable replacement for the DSH composer model selector.
ZCode-style model picker for the DSH web GUI — provider submenus that open upward, reasoning-effort selection, and keyboard navigation. · DSH 的 ZCode 式模型选择器：向上展开的提供方子菜单、推理等级选择与键盘导航。
DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).
DSH web plugin: searchable model selector for DeepSeek Harness WebUI
Native DeepSeek Harness model health monitor with persistent Alive/Dead state, runtime failure verification, scheduled rechecks, and health-sorted searchable model pickers.
为 DeepSeek Harness 提供持久化模型别名、别名选择器和设置页面
Configurable model-request retry limit for DeepSeek Harness (Settings → General).
Model router for DeepSeek Harness: keep a pool of models and every step is routed to one of them with its reasoning effort set — a click-only composer panel, three authorization scopes (a manual pick only counts in the scope that owns it, and effort scope is bound to the one model you choose), task presets with per-model weights, vision routing for image steps, session signals (todo, context pressure, token budget, subagents) and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a tool call made with thinking off.