dsh-tui-webhook
IM bot notifications for dsh-TUI: push long-turn completion and approval requests to a 飞书/钉钉/企业微信/generic webhook, configured in /settings (webhook namespace), status via /webhook.
190 results
IM bot notifications for dsh-TUI: push long-turn completion and approval requests to a 飞书/钉钉/企业微信/generic webhook, configured in /settings (webhook namespace), status via /webhook.
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.
Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)
DeepSeek Harness plugin: Windows toast notification with sound when a session requests elevation approval — shows which session, why, and what is being elevated
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.
Auto-reject unanswered permission requests with a model-visible timeout notice
DSH web plugin: plays opencode sound effects on task completion/failure/input-request with a native Settings panel (45-sound pack, per-event picker + on/off switch, preview, volume).
DSH plugin: API retry settings page - view and edit each LLM provider's request retry policy (mode, maxRetries) over the settings wire
DSH web client plugin: a per-conversation cost-statistics tab (token usage + estimated cost per model and per request)
Minimal-anchored agent preset for DeepSeek Harness: first request keeps the real Minimal tool pair, promotion unlocks the full Standard catalog with a one-shot background-jobs notice
Sidebar usage monitor for opencode.go and commandcode credits — usage bars plus per-model estimated request counts from the official pricing docs
Automatic review of sandbox escalation requests for DeepSeek Harness, plus an /approve slash command for manually approving auto-denied actions (Codex Guardian-style)
Any DeepSeek Harness session can request a Desktop restart, then the same persisted session is resumed and followup'd with a self-contained mission.
Standard handoff protocol so DSH never restarts itself: a host plugin that files a JSON reset request for an external ops agent (e.g. Hermes) to execute preflight-snapshot → restart → health-check → recover, then delivers the result back to the requesting session.
Provider-scoped HTTP/HTTPS forward proxy middleware for DeepSeek Harness LLM requests
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
Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.
Safe restart execution for DeepSeek Harness: request validation, checkpoint gating, restart locking, graceful shutdown, crash-loop breaking and an external supervisor. It never decides when to restart.
Local reverse proxy plugin for DeepSeek Harness that caps images per request to 1, for self-hosted vLLM backends that reject prompts with more than one image
DSH plugin: inject dynamic/random HTTP request headers (${uuid} templates) into LLM provider requests, e.g. a run-stable x-opencode-session for the opencode-go gateway.
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.