Plugins

Tavily search, extract, map and crawl tools with multi-key rotation, failover on HTTP 401/429/432/433, and a load-balance mode that caps in-flight requests per Tavily account, plus a key and usage card on the Plugins page. The built-in web_search is never replaced.

Host-resident cron engine with a web jobs board and a timer_agent tool: fires real agent sessions on schedule, continuing a pinned session for context or starting fresh ones in a chosen project workspace.

Android real-device debugging workbench for the DSH Web GUI: auto-attached logcat with severity/keyword filters and crash snapshots, live on-device screen casting with remote tap/swipe/text control, memory/proc/frida reverse-engineering toolset, 30 agent tools.

Private loopback DSH Web gateway for Tailscale Serve, Cloudflare Access, and Headscale TCP Serve, with exact principal allowlists and guided fail-closed setup.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Agent2Agent protocol v1.0 for DSH: run a standard A2A server to let other agents call this instance, connect to remote A2A agents as clients, and manage both from a visual settings page.

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Repair DeepSeek Harness sessions that refuse to load, with a sidebar Session surgeon overlay and dry-run repair.

A whip for DeepSeek V4 Pro: it watches the reasoning fingerprint of every thinking block and pulls the model back when it slips from focused "We will / I will" mode into scattered "let me" mode.

Multi-dimensional quality scoring for DeepSeek Harness plugins that scores a repo or npm package across install success, maintenance activity, documentation completeness, security scan, and protocol compliance using real CLI evidence, and produces a JSON or Markdown leaderboard report.

Desktop pet drawn from the official whale outline, for both the desktop app and the web UI: SVG animations and facial expressions follow agent state (thinking, working, done, error, waiting for confirmation), and it can follow other running sessions with a count badge; poke it, drag it, shake it dizzy, squash it against a screen edge, or rub the cursor over its head for a headpat; 7 palettes, 4 sizes, synthesized sounds, light/dark theme sync, and a playable web preview.

Runs isolated install-and-smoke test drives for DSH plugins in throwaway profiles, returning structured pass/fail records and batch matrices without touching your real profile.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

A simple DSH queue panel for editing, removing, steering, reordering, and bulk removal.

Replay sessions on a playable timeline with per-step token usage, audit sensitive operations, estimate cost, view fork lineage, compare sessions, and export standalone HTML replays.

Usage tiers and shareable stats cards: 🐟→🐳 ranks by monthly token burn with a locally-computed estimated percentile, precise pricing for 46 models across 6 vendors (including size-tiered Chinese pricing), backfill of pre-install sessions, and old-vs-new comparison across the 2026-08-17 rate change. Local-only, no telemetry.

Settings page for per-model capabilities: reasoning-effort levels with their wire spellings, input modalities, and token capacities, written as declarations or sparse catalog overrides.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

A floating desktop pet for the DeepSeek Harness Web UI: idle breathing, occasional direction turns, random actions, and screen wandering.

Select browser elements directly during Vibe Coding and send structured visual feedback to the DeepSeek Harness Agent.

Plan review with anchored annotations and structured feedback back to the agent.

Skill pool manager in the Settings sidebar: enable/disable, folder batch import with rename-conflict prompts, state-driven one-click DSH-spec check & auto-fix, system/project scope labels.

Connect multiple Overleaf projects to DSH through OverleafMCP for browsing, analysis, and Git-based file updates.