dsh-config-form
One settings page for every plugin that opts in: declare fields, get a rendered form
384 results
One settings page for every plugin that opts in: declare fields, get a rendered form
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.
DeepSeek Harness 插件:实时显示本会话 API 用量开销,按 provider token 用量 × 可配置费率计价,输入栏上方成本条。Real-time per-session API cost meter for DeepSeek Harness: prices provider-reported token usage with configurable rates and shows a live cost chip above the composer.
enhance-provider-config
DSH Web client plugin: card-based new-session configuration wizard (immersive step guide) to prevent silent default configurations
Automatic model routing for DeepSeek Harness: a virtual `smart` model classifies every request by difficulty (hard / normal / easy) and by vision need, then delegates to the models you already configured in Settings → Models. 内置智能路由:三级难度 + 视觉自动路由,模型从「设置-模型」已配置模型中选取,虚拟 smart 模型零配置接入。
First-run health check for DeepSeek Harness (dsh): verifies Node/pnpm/dsh toolchain, profile, API key, workspace and registry config, then prints actionable next steps. Zero runtime dependencies, read-only. CLI + agent-callable quickstart tool.
任务完成约束自动化插件:监听 AI 回合结束,检测回复是否含 ✅ 任务完成,按「推送许可」开关自动 commit+push 交付物。带 HTTP API(status/config)与 agent 工具(task_completion_status / task_completion_config)。
DeepSeek Harness 代理配置插件:对外网目标自动走 HTTP/SOCKS 代理(harness 进程内请求与 pnpm/git 子进程都生效),本机/回环/内网直连;带可关闭的启用开关;设置一页持久化到 $DSH_HOME/proxy-config.json。
Advanced model configuration page for DSH WebUI
Allowlisted subagent routing for DeepSeek Harness: the calling agent dynamically chooses a configured model and exact reasoning effort per delegation.
Multi-provider usage monitor for DeepSeek Harness: per-provider balance / token-plan usage card in the sidebar footer (above the Settings button) plus a「用量监控」settings section for per-provider special config (cookies, API keys), persisted in settings.yaml.
DeepSeek Harness plugin: content-routing LLM adapter. Text-only requests go to DeepSeek; requests containing images go to a user-configurable OpenAI-compatible vision provider. Read_image works natively for text-only 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。
Git sync for DeepSeek Harness settings and profile configuration.
Configure model input capabilities and reasoning efforts for DeepSeek Harness
Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes
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.
DeepSeek Harness plugin: configurable keyboard shortcuts (settings UI + input history + approval/plan hotkeys)
Git workspace panel for DSH Web: repo discovery, stage/commit like VS Code Source Control, AI-generated commit messages via configurable rules, history graph and diff preview
Open a workspace directory from the DSH web GUI in a configurable launcher (VS Code / file explorer / Windows Terminal / any CLI).
DSH bundle: WeChat floating-ball bridge (QR login, message relay, ClawBot model config)
DSH Synthwave theme plugin: neon glow hover/focus, translucent panels over image/video background, configurable blur, fontScale root font-size.
Zero-config local vision and realtime audio routing for DeepSeek Harness