Plugins

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore decisions and a full audit trail, /memory commands, ≤3-claim/1200-char injection per call, no extra model call.

Cross-session task queue with handoff notes: sessions and subagents push, claim, complete and cancel tasks on a shared file-backed queue, and leave a handoff summary for whoever picks up next.

Font switcher for the DSH Web GUI: 99 UI fonts and 31 code fonts with CJK-Latin pairing stacks, instant apply and localStorage persistence.

Activity heatmap in the DSH Web sidebar: GitHub-style grid of daily commits, token usage, and estimated spend, with a today stats line for all-session token totals, cache hit rate, and per-model auto-priced cost.

Desktop pet for the DSH Web UI: sprite-sheet animation, agent state linkage, drag, alarm (daily/one-shot) and pomodoro widgets, skin picker with preview.

Right-edge user-message navigator with an adaptive block layout that fits the available height, plus hover previews, keyboard controls, and click-to-jump navigation.

LAN/remote access for the Web UI: injects a crypto.randomUUID polyfill on plain-HTTP origins so the frontend survives LAN or Tailscale IP direct links.

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

Structured test runner tool (test_run): auto-detect Vitest/Jest/pytest/node:test, run tests, parse failure summaries for the model.

DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.

Two-tier model router for DeepSeek Harness — LLM-Judge routing, multi-model fallback chains, exponential-backoff failover, and task-level orchestration (DSH adaptation of pi-shift-router)

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

view modes for deepseek harness, including Verbose, Normal, Summary Mode

deepseek harness manim数学插件

Bring any file into the conversation — stashed to the workspace and referenced by path; zero type rejection

DeepSeek Harness (dsh) Windows notification plugin: a native toast when the agent stops running (finished / aborted / error / waiting for your choice / session closed), plus a system-tray icon. Pure host-side, zero dependencies, zero build.

DeepSeek Harness diagnostic, repair, and rollback plugin: dsh_doctor (diagnose), dsh_doctor_fix (journaled repair), dsh_doctor_rollback (LIFO undo), plus a Cordis runtime service for dynamic self-healing.

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

DeepSeek Harness plugin: secondary working directories for a project. The agent keeps the primary workspace as cwd, gains equal write/exec permissions on configured secondary directories under workspace-write mode, and is notified of configuration changes

Global skill hub for dsh: aggregates Claude Code, project, and .skill-package skills into ~/.dsh/skills with reference/copy import and slash-menu usage

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers, with OAuth login from the web Settings page

DeepSeek Harness plugin: query AI Monitor balance / usage from local SQLite — cost-aware agent, auto bookkeeping with the AI Monitor proxy.