Plugins

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Exposes OpenCode Zen free models to DeepSeek Harness with no API key, tracking Zen gateway changes.

Agent preset plugin for DeepSeek Harness that triages every request, delegates implementation to an expert, and schedules parallel work through a dependency-DAG taskboard and a file-based message bus before an independent review gate. Ships with only 11 core experts out of the box; more expert teams (Agency agents EN/ZH, classic collections) are one-click downloads from the settings page over dual GitHub/CDN channels with sha256 verification.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Workspace session monitor: aggregates per-session pending/running/completed state into a sidebar footer badge and a floating per-workspace panel, so switching between workspaces never hides a forgotten session; an additive core seam (upstream-seam.patch)

以 dsh-bridge 为根基、融合 remote-gateway 能力的 DSH 远程访问网关：局域网 / Cloudflare 隧道 / 自建隧道之外，新增「公网直连网关」（0.0.0.0 监听 + 自带 HTTPS 自签证书 + 强制登录门禁），解决移动端外网直连操控电脑。

P0–P4 deterministic-first permission gate with permissive tier, learning sedimentation and approval-history UI; hard-deny credentials and protected paths, auto-allow internal read-only tools.

Password-protected HTTPS login gate that lets LAN devices securely access the DeepSeek Harness web UI over the network.

Login gate for the dsh web UI: unauthenticated visitors get a login/register page and the first registrant becomes admin; includes user and role management plus login and access audit logs.

Policy plugin that gates kubectl by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.

DSH GitHub connector: review PRs, triage issues, debug CI, prepare changes (18 tools, gh-first + REST fallback, approval-gated writes).

Sidebar badge and panel that aggregate per-session pending, running, and completed states across workspaces, with one click to open a session.

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.

An approval-gated OME engineering delivery preset with session-isolated lifecycle evidence.

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.

Share the DSH workspace over the local network: phones, tablets and other computers browse, download and upload files via browser with no DSH login. Token gate, path boundary, read-only mode and rate limit. Zero-dependency (node:http).

Text-to-image and image-to-image generation via OpenRouter's unified Image API: configurable model aliases with parameters gated against the live model capability listing, reference-image inputs, a settings card, and inline chat display of results.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

Drive your real logged-in browser through OpenCLI — browser primitives plus 170+ site adapters as deterministic one-shot commands, with in-session adapter authoring, a write-approval gate and a settings management panel.

DSH tools for operating a self-hosted Talebook library: search, download, upload and manage books and audiobooks, manage Legado book sources, and admin operations, with approval-gated writes.

Sidebar badge and panel that aggregate per-session pending, running, and completed states across workspaces, with one click to open a session.