dsh-ark-plan
Correctly activate DeepSeek v4 flash on the Volcano Ark plan API for DeepSeek Harness: default config injection (ark provider + reasoningEfforts + reasoningEffort=max) plus an ark_plan_doctor self-check tool.
217 results
Correctly activate DeepSeek v4 flash on the Volcano Ark plan API for DeepSeek Harness: default config injection (ark provider + reasoningEfforts + reasoningEffort=max) plus an ark_plan_doctor self-check tool.
Model-facing accurate_vision tool: precise image spatial reasoning via a vision model
Automatically add reasoning-level controls to compatible DSH provider models.
DSH Web UI model seat: 3-level quick slider (low/medium/high, each preconfigured with model + reasoning effort), advanced model/effort picker, modality icons, and per-provider usage/balance display. DSH 模型选择器增强:低中高三档快切滑块 + 高级选择 + 模态图标 + 供应商用量显示。
Configure model input capabilities and reasoning efforts for DeepSeek Harness
An Eason-themed floating desktop pet for the DeepSeek Harness Web UI: 18 Eason-only transparent animations (concert, coding, daily life), session-linked behavior mirroring the agent (thinking→coding, streaming→singing, tools→progress bar, waiting→peeking,
Per-stage model routing for dsh-TUI: let subagents run on a different provider/model/reasoning-effort, configured in /settings (model-switch namespace), status via /model-switch.
DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with toggles, refresh, and a fill report.
DeepSeek Harness 插件:在 Web GUI 中选择模型的推理程度(reasoning effort)。按当前模型的适配器目录展示可选档位(如 Off / High / Max),一键写入会话的模型选择。
Replace the DSH Web reasoning-effort chooser with a compact animated FX slider that scales with effort level.
Codex 风格 6 档性能滑杆:每档绑定模型 + 推理等级,并切换 31 张本地人物背景。 / Codex-style 6-level performance slider for DeepSeek Harness (dsh web).
Adds a search field inside the model picker menu of the composer. Drop-in replacement for the native model seat, sharing the same per-session ModelDirectory so /model popup, the effort selector, and the /model command stay consistent.
Model selection as a three-level cascading menu (Provider -> Series -> Full model) plus thinking-intensity (reasoning effort) selection for the composer model seat.
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness
DSH Web GUI: one-click expand/collapse all reasoning chains and tool chains in the current session (官方 repository-plugin 格式 / official bundle format)
调味技巧
Tolerate OpenAI-compatible model streams that end without a terminal finish_reason so DSH turns complete instead of aborting.
DSH web GUI plugin: auto-expand assistant reasoning (Think rows).
Structured context for DeepSeek Harness: split the conversation into typed sub-contexts (reasoning / tool calls / replies) and index them with a table of contents. 结构化 dsh 上下文:按类型拆分小上下文(思考/工具调用/正式回复),以结构化目录为索引。
Custom DSH task board fork with per-task provider, model, and reasoning-effort pins.
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.
Ultra mode for DeepSeek Harness: a per-session effort tier that pins reasoning to max and activates an orchestration policy section, with a composer ULTRA chip and rainbow border in the web UI
DeepSeek Harness plugin: make the chain of thought open with "We need" instead of "Let me"
Share any DeepSeek Harness session as a self-contained read-only static webpage — timeline, collapsible tool calls & reasoning, default redaction, dual SHA-256 fingerprints, watermark. · 把 DSH 会话一键变成可分享的只读静态网页:单文件 HTML、离线可开、默认脱敏。