Plugins

Rules, commands & skills manager for dsh: /rules slash command, settings panel with visual rule editing (add/edit/disable/delete, free-zone support), user-defined custom commands with {input} arguments, skill management, and automatic backup & one-click restore of AGENTS.md.

One-click start/stop button pinned to the window bottom-right corner: restarts DeepSeek Harness in place via a detached helper that relaunches the exact boot invocation (loopback same-origin guarded), with an optional stop-only action.

Plugin compiler with a blueprint registry (scaffold → validate → deploy) exposed as a runtime service, three model tools, and a blueprint-gallery settings page.

Unifies every DSH extensibility seam behind one declarative DSL: a runtime `fabric` service, `fabric_extend`/`fabric_inspect` tools, and a capability-graph settings page.

Windows desktop shortcut for dsh web: launches the server, auto-opens the browser when ready, and stops the service when the Harness window closes.

Skill Manager page in the DSH settings panel: browse system / user / workspace / preset skills, expand a skill to its file tree, view and edit files, import skills from a zip, and export or delete them (system skills read-only).

DingTalk IM channel via Stream-mode WebSocket: each chat drives its own tooled agent; replies stream back as messages, no public callback URL needed.

Long-task orchestration loop: Codex plans/scores/reviews, DeepSeek executes, Kimi supplements (vision acceptance, summarization, cross-check).

Turns the iterate skill into an autonomous closed-loop harness — plan, parallel review, atomic fixes, validate, loop, auto-stop — plus a dry-run review-only mode and a meta-review that audits the report and emits a final review report.

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.

Spec-driven development discipline for dsh: five keel skills (anchor/spec/probe/build/audit), three review tools and six spec templates enforce specs-before-code, assumption verification and scope control.

Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.

Native vision capability extension, using either Zhipu (free) or Qwen-VL (local).

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Model-facing `vision` tool for DeepSeek Harness: describe and OCR image files by calling the free Zhipu GLM vision API directly (glm-4v-flash fallback chain), no external CLI required.

Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.

Independent browser acceptance testing for agent deliverables: JSON spec in, real-Chromium verdict out.

Provides the bili_summary tool: Bilibili video metadata, subtitle timeline, and sharp-based frame capture with built-in error handling and graceful degradation.