Plugins

Experience memory and reflection for DSH agents: automatically extracts candidate lessons after tasks and recalls user-reviewed lessons in relevant later tasks. Supports source provenance, project-scoped retrieval, conflict handling, usage feedback and expiry review; capture and recall have separate controls, and writing lessons to AGENTS.md requires preview and explicit application. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Performance profiling and LLM cache diagnostics for DeepSeek Harness — context engineering, latency profiling, and cache behavior reports.

Ports poteto's pstack engineering playbooks to DSH, covering planning, review, verification and release workflows.

Work reports for DeepSeek Harness: gathers Git commits and local agent conversations (DeepSeek/Claude/Codex) and renders daily, weekly or monthly reports from your own templates; the agent tool is injected on demand.

Exports the agent loop to GreptimeDB as OpenTelemetry traces, metrics and logs, with seven Grafana dashboards covering token usage, cost, session outcomes and per-turn latency.

Connects DSH Web and qq-bridge to OFM, defaulting to the DeepSeek public pool while preserving reasoning effort and manual model selection; loads the official OFM dependency when absent and reports account-rotation receipts.

Turns a one-line DSH draft into a complete task brief (role / goal / constraints / output format). The engine is a byte-verified port of linshenkx/prompt-optimizer (three modes, 10 templates identical to upstream); history is consent-gated with version chains and structural comparison; every run reports its token usage. Nothing is written back or sent without a click.

Reports which skills each turn invoked (loaded by the model, typed as /name, or none) and manages the local skill directory: install from a pasted repository, folder, SKILL.md or zip address, set a Chinese display name in the skill meta.yaml, and remove a skill while keeping a backup.

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. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

Server card dashboard for DSH: per-host status, CPU, memory, disk and latency, with one-click xterm.js SSH terminals; imports ~/.ssh/config and mounts as a better-sidebar tab or a standalone right drawer.

Register locally-defined custom agents as callable subagents in dsh: the main conversation invokes any agent by name via use_agent, each running as a real dsh subagent with its own persona. Supports breakpoint resume for interrupted runs.

Bring the WorkBuddy accounts signed in on this machine into DSH, managing CN and international accounts separately. Supports automatic failover between accounts, one-click refresh of model catalogs and credits, the CN daily check-in, and a togglable OpenAI-compatible endpoint.

Imports local coding-agent session histories so work can continue in DSH.

Laya typed decisions (`noul` yes/no, `choice`, `score`) as a first-class Cordis service (`ctx.laya`) plus the model-visible `laya_ask` and `laya_plan` tools. The plugin itself installs and downloads nothing: it is a client of a `laya-mcp serve` sidecar you start yourself, and it reports that the sidecar is not running instead of failing obscurely at the first tool call.

Theme plugin — supports dark/light appearance switching, ships 34 preset themes, and supports creating, sharing, and importing custom themes.

TRAE SOLO supplier plugin for dsh-router, ported from traework2api. Provides the traework supplier, a free SOLO chat channel, and reports single-account status to dsh-router core.

Lazy-loading router for MCP servers: auto-discovers compatible MCPs and keeps only a shared router in the tool catalog, revealing a server's schemas when a turn needs them and hiding them again at turn end, so many installed MCPs stop costing context on every request. Falls open to normal visibility on any uncertainty, and the original MCP keeps ownership of execution, permissions and process lifecycle. Also supports explicit lazy connections with warm reuse, bounded reconnection, stdio and Streamable HTTP.

Research data provenance auditor: audits lineage integrity, reproducibility and FAIR principles compliance, outputs provenance audit reports for research integrity and open science.

Geospatial data quality inspector: checks elevation accuracy, topology consistency and coordinate system compliance, outputs weighted quality scoring reports per GB/T 24356-2023.

Financial AML compliance checker: detects large/suspicious transaction thresholds, exemptions and timeliness, outputs auditable AML compliance reports across banking, insurance and securities.

Data asset attestation plugin that generates certification-level data quality reports with evidence chains.

City data AI classification plugin — auto-recommends data classification based on GB/T 47949, supports structured/semi-structured/unstructured data.

Data visualization plugin that generates self-contained HTML reports with five chart types (bar/comparison/pie/radar/flowchart) and two-column layout.

Discovers other DSH instances on the local network by UDP multicast or port scan, lists them in a sidebar panel together with the capabilities each one reports, and dispatches tasks between machines in both directions over the LAN or over an automatically downloaded userspace Tailscale node.