Plugins

Hard break on repeated tool calls: a synchronous ctx.tools.guard gate that counts semantic fingerprints (net/site/sink/cmd/exact) over a per-agent sliding window, ignoring decoy arguments such as description and timeoutMs.

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

Fills in what the official pi-ai adapter leaves out on the Models page: gateway reachability probing with latency, one-click pull of the gateway model catalog with checkbox write-back into settings, DeepSeek balance and provider quota shown in place, the protocol and endpoint each provider is actually wired to, and a model dropdown that lists only what works right now — a dead key, an empty balance or an exhausted quota is hidden until you fix it, and comes back on its own.

Manage the SakuraFrp phone-to-desktop link from the DSH interface - link status, mobile gateway switch, one-time pairing QR code, device revoke and gateway self-heal.

In-place redaction and row-level rollback for session logs, preserving the seq-equals-row-index invariant that makes deleting a middle row corrupt the entire log. Originals are copied to a quarantine sibling before any write, and the reader's own semantics are replayed as a pre-write gate.

Makes the AI default to Mermaid diagrams in development conversations — system prompt guidance, a mermaid_validate syntax-check tool with real-parser validation, and an output gate that auto-fixes or removes broken diagrams. Rendering via dsh-mermaid.

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

DeepSeek Harness 自动审批门控：Flash 模型预判写入/命令是否不可回补，安全自动批准、危险转人工（fail-safe），最小人工介入，含人工审查 UI

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

Zero-credential Outlook automation: 13 tools that drive the local desktop Outlook client via COM — search/read mail, drafts, reply/forward, calendar, address book, rooms, free/busy — plus a sidebar new-mail badge. No Graph API registration, no SMTP passwords; anything that leaves the machine passes a three-layer human approval gate.

Pre-boot health gate and repair for dsh plugin trees: seven static scan rules, fault attribution after failed boots, whitelisted reversible fixes, and a panel with plugin-row management plus a RAG knowledge base of past failures.

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.

会话注入门控：给 DeepSeek Harness (dsh) 加一个会话级上下文裁剪闸门，按会话取消/恢复插件贡献的 skill、tool、系统提示词段落——3 条影子通道、5 条本地路由、零依赖零配置。Per-session injection gate for DeepSeek Harness (dsh): trim skills, tools and prompt sections per session. Zero-config, zero dependencies.

Approval-gated workspace instructions and memory for DeepSeek Harness

Web management panel for Docker on DeepSeek Harness: manages Docker MCP servers (deploy/remove, official catalog search/pull, gateway start-stop-restart, custom deploy) and containers/images (list, start/stop/restart, remove, logs, inspect, interactive terminal, create, pull, build, load) across local CLI and SSH remote targets with one-click switching. Credentials are encrypted with Windows DPAPI, HTTP is loopback-only, and command parameters are whitelist-filtered. Build-free pure ESM; client is zero-dependency.

Multi-agent frugality defense plugin: read-ledger dedup metrics, compaction-immune rules, completion gate, cheap-model review lane.

MaxCompute (ODPS) data analysis plugin for DeepSeek Harness: metadata browsing, cost-gated SQL execution, background jobs and result export.

Shared toolkit for authoring DeepSeek Harness plugins, published as @perrylink/dsh-plugin-kit: a pluggable provider registry seam, fail-closed approval and session-event gates, shared sanitize/pricing/judge modules and a new-plugin skeleton.

Provides a secure reverse proxy, enabling DeepSeek Harness to be accessed remotely and to converse with AI anytime, anywhere.

Prompt enhancer for the DSH web UI with basic/standard/expert modes: standard/expert modes rewrite drafts with project context and recent session history, retry gracefully when gateways reject reasoning-effort settings, and show a before/after review with undo.

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-down with context-growth curves and anomaly flags, global filters with shareable URLs, monthly budget progress with month-end projection, and day/month aggregate fast-path queries (O(days)) with incremental rescan.

DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.