@ruihuahe/dsh-codegraph
Question-driven code architecture scenes for DeepSeek Harness
310 results
Question-driven code architecture scenes for DeepSeek Harness
DeepSeek Harness plugin: control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home, powered by the local yeelight-home runtime.
JumpServer asset lookup for DeepSeek Harness: query assets via conversation using AccessKey/SecretKey signed requests
Safe restart execution for DeepSeek Harness: request validation, checkpoint gating, restart locking, graceful shutdown, crash-loop breaking and an external supervisor. It never decides when to restart.
Host-only command safety gate for DeepSeek Harness: blocks recognized dangerous operations and requests DSH approval when a command cannot be inspected.
Conservative per-request reasoning selection for DeepSeek Harness, with no classifier model calls
DeepSeek Harness plugin that captures the raw HTTP request and response bodies of model provider calls, shows the request body as a collapsible size-annotated JSON tree in a Conversation View tab and on a loopback viewer page, and assembles SSE responses back into reasoning, content and tool calls.
Keep DSH tool results cache-prefix safe: truncate a result before it first enters the session surface, and never rewrite a tool result a provider request has already delivered.
Parallel side questions and side conversations for DeepSeek Harness without polluting the main context.
One-time ephemeral webhook tool for DeepSeek Harness (dsh): mint a single-use callback URL, then wake the requesting agent session with the delivered payload.
Per-model custom request headers for DeepSeek Harness: define named header profiles in Settings → Plugins → Plugin configuration, pick one per model in the provider's model catalog, and every call to that model carries those headers.
Plays a Windows system notification sound when the agent opens a question dialog, when it asks for permission, and when a conversation turn ends. DSH 组合包:弹出选项卡时、请求权限时、对话回合结束时播放系统提示音。
Local reverse proxy plugin for DeepSeek Harness that caps images per request to 1, for self-hosted vLLM backends that reject prompts with more than one image
Ask Jev (TypeSafe System One) typed questions from DeepSeek Harness: batch judgements with probabilities, configured per user in Settings.
Per-session-tree budget and burn-rate circuit breaker for DeepSeek Harness: refuses the next model request or delegation when a tree's spend or spend rate crosses a limit.
Webhook notifications for DeepSeek Harness sessions: POST when an approval is requested or a turn ends (ntfy / Bark / generic JSON).
Cap how long one DSH tool call may wait: a global default wait limit in Settings, plus a per-session raise the model can request from the user.
Safe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits.
Ask TypeSafe (Jev) for a structured decision from inside DeepSeek Harness: route, classify, score or verify with typed questions, and get probabilities your code can branch on.
Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由,虚拟 smart 模型零配置接入。
Floating git status pill for DeepSeek Harness: live branch, +/− line changes and a Create PR prompt, rendered over the whole app.
DSH plugin: when an upstream model API request fails, dump the exact raw request body and the raw upstream error response to disk.