Plugins

Dedicated read-only Git Graph view beside Chat and Trajectory: commit topology, local/remote/tag refs, HEAD and working-tree status, search, filtering, first-parent mode, refresh, and load more.

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.

Professional translation for DSH: 18 target languages, 4 styles (formal/casual/technical/literal), glossary-controlled terminology, and whole-file translation (README/docs/subtitles) with Markdown/code-block format preservation; powered by DeepSeek via SiliconFlow.

Unofficial Cursor subscription chat: Host-owned CLI session login, a displayed model catalog, and subscription usage rails. Cursor staff treat this class of private-client usage as against ToS.

DeepSeek API usage dashboard for DSH Web: daily cache-hit/miss and output token statistics from session logs, per-model cost estimates, account balance, 7-day trends, and a composer usage summary.

Subscription OAuth login: use ChatGPT/Claude/Grok/Kimi subscription accounts (not API keys) with automatic model discovery.

Command Code Go provider adapter for dsh: scan the Go-plan model catalog dynamically and serve /alpha/generate through the harness LLM seam

Structured, safe Git tool family for DeepSeek Harness: status/diff/log/branch/stage/commit/stash/show/fetch/pull/remote/checkout with a destructive-command guard.

Generated-catalog plugin discovery and npm installation marketplace for DeepSeek Harness

Langfuse observability for DeepSeek Harness: exports session logs as OpenTelemetry traces (GenAI semantic conventions) to Langfuse's OTLP endpoint

Evidence-first operating kit: six read-only tools (capability catalog, staged workflow plans, packaged skill reader, bounded local memory search, repository release audit, release checklist) and five packaged skills - plans and audits, never remote writes.

First-class Git tools for the model: status / diff / log / commit / branch with validated messages and paths - no bare-shell git calls.

Real-compute verification gates: math simplification, logic proofs, regex validation, E-prover FOL, state-machine checks, and code repair, backed by Go-compiled binaries with prebuilt Windows executables.

ADB device & bench operations for DSH: device discovery, structured logcat (background streaming), apk install, file pull/push, and dumpsys performance snapshots.

Aborts a DSH reasoning stream that starts repeating itself instead of letting the turn stall: five rules over the streamed reasoning text (periodic unit, repeated block, repeated line above a share floor, 64-gram density, and a long trailing run of punctuation or whitespace), plus a JSONL fire journal, a Web GUI log panel, and opt-in recovery that retries with a corrective message.

Self-organizing multi-agent clusters with no orchestrator. Real DSH subagents coordinate through a shared append-only log that each agent reads and writes on its own schedule, with no topology and one dispatch per agent; a snapshot mode is also included where the harness freezes each neighbour view into the prompt and drives a ring/mesh/swarm cluster to convergence.

Browse, search and install skills from the public SkillHub catalogue, then enable, disable, update or remove them without leaving Harness. Category chips carry the upstream total for each category; the details drawer has tabs for the file tree, version history, permissions, third-party security-scan results and upstream metrics. An installed skill is written into the harness skill root as an ordinary local skill, and disabling one moves its directory out of that root rather than flagging it.

Layered long-term memory for DeepSeek Harness with automatic model distillation, source-linked encrypted session logs, and guarded compaction.

Model failover and turn keep-alive for DeepSeek Harness: a request that fails with a model error before any visible output falls through the models of the configured provider groups (then the next provider) until one streams; transient failures retry with backoff under a liveness watchdog, a dead turn self-resumes with templated 「继续」 wake-ups, and an optional full-auto mode auto-answers permission, question and plan approvals with every decision appended to an AUTO-MODE.md audit log.

Token usage panel for DeepSeek Harness: a bar above the composer opens billing token totals, trend charts, per-model and per-project breakdowns and a custom date range, read from local session logs of DSH, Codex, Claude Code, Trae and WorkBuddy. With a self-hosted portal URL and an app key it also reports usage events to that portal; with neither configured it collects nothing. It exposes token_usage tools plus a ctx.tokenReport service, and never collects conversation content.

DeepSeek Harness plugin: show a provider + model icon in the sidebar for every session, updated live from the composer model selector with a last-request fallback for history sessions; aggregator routes render the provider logo with a 10px model logo in the corner.

Right-side overlay panel for DSH sessions showing git status, background jobs, skills and MCP usage, artifacts and visited pages, with a commit/push dialog and one-click GitHub publish.

Host-layer Windows toast notifications for DeepSeek Harness: agent turn done, error or interruption, subagent done, and background job done, plus alerts when the model asks you a question or a tool approval is pending. The notification logic runs in the DSH host process, so toasts still arrive with the tab or the browser closed; a Win32 foreground probe suppresses them while you are looking at DSH. Windows only.

DeepSeek Harness LLM adapter for Qoder CN subscriptions, built on the official @qodercn-ai/qodercn-agent-sdk. Reuses the local qoderclicn login, and exposes a fully configurable settings page (per-model context window, session pool, timeouts, model deny l