Plugins

Per-model capability profiling for DSH: turns local session history into per-model dashboards of session counts, tool usage, error rates, and top error signatures, with time-range filters and multi-model comparison.

Browser-first, LAN-only access to the current DeepSeek Harness Web UI with one-time QR pairing, revocable devices, event-driven diagnostics, and a slot-preserving mobile layout; no companion app, cloud relay, or remote tunnel.

Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon

Generates editable PPTX decks in DSH with a bundled authoring Skill, deterministic PPTD scene checks, native PowerPoint objects, and local PPTD source-project delivery.

Local semantic code search for DeepSeek Harness: fragment-level symbol-aware indexing, offline lexical embeddings or an OpenAI-compatible endpoint, and hybrid vector + BM25 retrieval fused with RRF - three dsh tools plus a sema CLI.

Auto-continue for the dsh web GUI: when a local model hits its output-token cap and the max-tokens notice appears, the plugin automatically queues a short continue message so the reply keeps flowing — dual-source truncation detection, loop protection, and no UI.

Registers a /code-review slash command with five parallel review lenses and per-finding confidence scoring, for both pull requests and local code.

Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.

Use AItelier as a subagent from DeepSeek Harness: generate, edit, run, export and import SkillFlow pipelines. Client only — requires a running AItelier backend (Docker; see README).

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Four dependency-free local git tools (status, diff, log, commit) for DeepSeek Harness operating on the session workspace.

Import local Codex CLI/Desktop, Claude Code CLI, and Claude Desktop conversations into DSH with project grouping, semantic history, and tool activity; bind an existing or replacement workspace and continue with the DSH Agent.

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.

Shows a local image or short video in the current conversation card, with click-to-preview.

Peak-Valley Meter (峰谷电表) — a tiny DeepSeek usage companion: a minimal two-part balance chip above the composer (currency symbol + number, nothing else), official balance refreshed every 5s; click the symbol to open the official top-up page in a new tab; hovering the chip fades in a circular backdrop under the symbol, its left arc flush with the chip's own left edge, and expands a 24h peak/valley timeline (orange=peak, blue=valley, glowing marker at the current local time) so off-peak hours are obvious; independent today-spend metering; a settings panel with 10 muted color presets plus custom valley/peak colors, detailed/minimal styles and readout toggles; all-Chinese UI.

Adds Claude, Gemini, and a local Ollama model to DSH's native model picker, using your existing Claude Code / Antigravity CLI logins instead of a metered API key, with a working reasoning-effort selector for Claude.

Static-only plugin gate and clinic for DSH: audit before install, hash-and-capability lock after install, local fingerprint peer search over GitHub topic:dsh-plugin, and mechanical detox. Never executes the target plugin.

Push vague or rich, user-configurable DSH interaction states to the local Discord client as Rich Presence — real-time, content-free, with a user-editable status list and an optional rich-mode toggle in Settings.

Full-screen lightbox for chat images: click any image to open the full-resolution original with zoom (wheel, buttons, shortcuts), drag panning, prev/next paging, filename caption and download, plus keyboard-arrow and touch-swipe navigation. One "image display control" popover next to the composer collapses every image in the conversation into a thumbnail grid whose column count (1-12) is configurable and remembered, or hides them entirely so the space closes up and restores them later; images are styled in place and no node is ever moved or reparented. The host-side display_image tool takes a local path or directory (TIFF/HEIC transcoded, originals still saved on download), a remote URL, or a keyword search over Bing, Huaban and Sogou that samples loadability before picking a source, re-saves images blocked by hotlink protection and drops dead links after a magic-byte check, returning paste-ready Markdown. It also keeps a system-prompt rule that every delivered image must appear in the reply body as  markdown, because collapsed tool rows are invisible to the reader.

Layered long-term memory MCP server: raw turns → task fragments → daily summaries → topic indexes, local MiniLM 384-dim embeddings or OpenAI-compatible API backend, semantic + Jaccard-fallback search, one-command DSH plugin install.

Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

Windows desktop UI context picker for Codex, DeepSeek Harness, and MCP clients: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, and local OCR, then review and approve Markdown/JSON context before output.

Adds OpenAI Codex (ChatGPT) as a selectable DSH provider via the local Codex App Server.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.