dsh-plugin-permission-popup
Corner approval popup: answer pending permission requests from any session while the agent window is away
193 results
Corner approval popup: answer pending permission requests from any session while the agent window is away
Inspect raw LLM requests and responses in DeepSeek Harness Web
Provider-scoped HTTP/HTTPS forward proxy middleware for DeepSeek Harness LLM requests
Configurable auto-approval for DeepSeek Harness: intercepts approval/request and answers allowed-once/rejected by policy (allow-all / allowlist / deny-always), with a full audit log — so the human is only asked when the policy says so.
Processes tab for DeepSeek Harness: a live per-process console (main agent and every subagent) with raw tool requests, responses and timing, installed as one profile bundle.
DeepSeek Harness plugin: transcodes images to a base64-safe format (PNG) before a vision request, fixing gateways like LM Studio that reject non-PNG/JPEG/GIF data URLs with "'url' field must be a base64 encoded image."
Preview and download the exact request frame (system prompt + tools + wire messages) that DeepSeek Harness sends to the model.
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
Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.
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.
Turn approved tracker tickets into review-ready pull requests with DeepSeek Harness.
Authored PR feedback inbox with shared Codex/DSH progress, priorities and read-only GitHub collection.
DeepSeek Harness plugin: a fail-closed URL host and scheme allowlist checked before a request is opened, exposed as assertUrlAllowed and the ssrf_check tool
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
Scoped OpenCode Zen request compatibility for DeepSeek Harness
Host-only command safety gate for DeepSeek Harness: blocks recognized dangerous operations and requests DSH approval when a command cannot be inspected.
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。
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.
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.
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.
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.
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.
Floating git status pill for DeepSeek Harness: live branch, +/− line changes and a Create PR prompt, rendered over the whole app.