Plugins

Database access for DeepSeek Harness through the DBHub MCP server: configure MySQL, MariaDB, PostgreSQL, SQLite and SQL Server connections per workspace and environment, then let the agent configure, list, query and search SQLite objects through four fixed tools. Passwords and full connection strings are entered in the settings UI and never accepted as tool arguments, so the model only sees metadata such as mysql://host:3306/db; each environment can be read-only (the model may enable it but not clear it) or reached through a manual SSH tunnel. Every call runs its own short-lived dbhub process and dbhub installs itself when missing.

Retrieval and planning toolkit for the BeiShan Besson Minecraft modding tutorials site: 7 tools to search 194 indexed tutorials, plan learning routes, compare version environments, and fetch article text.

Makes the built-in web_fetch tool work when Clash / mihomo runs in TUN mode with fake-ip: it lets the fake-ip address ranges (198.18.0.0/15, fdfe:dcba:9876::/64, 2001:2::/48) past the public-address check that otherwise rejects them, while loopback, private and link-local addresses stay blocked as before. Works with no proxy environment variables and no Clash changes.

Trip-planning agent preset for mainland China that answers in Chinese: queries 12306 train availability, Fliggy and Tuniu flight and hotel prices, and real Amap transit routes, checks closures and weather, and delivers a single offline HTML roadbook with draggable maps, three hotel price tiers and an itemized budget. Ships 9 skills, an environment doctor that walks users through missing API keys, and a patch for the 12306 MCP server; it plans and queries but never books or pays.

核心：信封／签名／握手／幂等／落盘 · Core: envelope, signing, handshake, idempotence, on-disk store

Run one instruction on every online Windows and macOS machine, across networks and regions: a dependency-free relay talks to each machine over outbound connections only (Tailscale, a public VPS behind TLS, or a tunnel), every machine runs the command in its own checkout, and results come back with a commit, a working-tree fingerprint and a command hash so an environment mismatch is reported as unverifiable instead of being mistaken for a different result. Sending work needs its own operator token, separate from the per-machine device token.

让 DeepSeek Harness 以 WSL 子系统作为会话的执行环境：shell、文件读写与命令执行均在子系统内完成，目录选择器与 GUI 终端同样定位到子系统路径，并通过子系统内的 bubblewrap 对命令进行沙箱隔离

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

DeepSeek Harness (DSH) 推理等级自动选择插件：由 Jev System One 模型判断每条消息值多少思考量，按模型声明的等级自动推导档位，上下文信封让「继续」这类追问继承话题深度，低置信度向上取，任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains and env vars for the runtimes each project uses (python venv / node / go) — python & pip always resolve to the project, never silently to system Python.

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

DSH-native uv environment manager: create, sync and run Python virtualenvs from the settings tab, with pip fallback, read-only conda visibility and a dry-run project sync preview.

Adds a net_doctor tool that reports proxy environment, NODE_USE_ENV_PROXY, and reachability of the DeepSeek API and the npm registry, and sets NODE_USE_ENV_PROXY on bash and npm child processes.

Fourth permission preset for dsh: unconfined, GPU-capable sessions (danger-full-access) with per-operation user approval for writes outside the workspace or to protected paths (.git/**, .env*); implemented purely as a bundle over the official tools/pre-execute ask hook, no core edits.

Requirement-driven dsh plugin discovery and environment recipes: plugin_guide matches natural-language needs to a curated plugin directory with reasons and install commands; recipe installs whole setups (通知全家桶, 安全审计套装...) from bundled community bundles with ordered plans.

The judgment layer for DeepSeek Harness plugins: attribute why a plugin silently disappeared, judge a candidate against your exact environment, and keep a capability ledger. Offline, read-only, evidence-first.

Registers one tool, report_health, that answers whether a scheduled report job actually ran. It judges by side effects rather than exit codes: how old the newest report folder is, how many documents it holds, whether more than one report category is present, whether the audit ledger was synced recently, and how long ago the last log was written. Exits nothing, calls no model, and reads only local paths you can override by config or environment variable.

Self-narrative memory in five budgeted segments (800 chars, not a full context): a first-person note the model writes to itself, a profile of you aggregated from approved facts, environment facts kept separate from who you are, heat-ranked conclusions, and habits. Every injected fact is traceable to a fact id and can be retired; the profile can be edited by hand, and self-notes stay plain lines you can clear. Facts fade by use and time without ever changing their credibility. Preference-like lines you say are auto-detected as candidates (never auto-approved), with conflicts kept side by side. Recall over past conversations with citations, an incremental index that only decodes newly appended frames, a pointer-required warm layer, a doctor that says which part is broken, a heartbeat proving injection is alive, and export/import so the whole thing moves to another machine.

Use SSH hosts and WSL distributions as remote DSH workspaces, with environment setup, model configuration porting, and the remote interface embedded locally.

Pipeline for scanned textbooks: OCR at roughly 5x the ONNXRuntime speed (requires Python 3.10+ with pymupdf, rapidocr, openvino and numpy), then a structure report and a per-chapter reading plan before you open the PDF.

Local development facts for Harness: environment and runtime-health probes, git status/diff/log/commit, write-time snapshots with version-by-version restore, and project checks for Node, Python and Go.

Registers Brave as the web_search provider, resolving the API key from the DSH credential store, $DSH_HOME/.credentials.yaml, or the environment. No settings card and no fallback engine: one request to Brave's Web Search API per search.

Registers a QwenWork (千问办公) model provider that reuses the desktop client's local sign-in, runs a loopback OpenAI-compatible bridge on 127.0.0.1, and translates DSH model requests into the ACP-style control-envelope conversation protocol the upstream actually speaks.

A 护航 panel in the session header that switches the local dsh-guard watchdog on or off and shows whether scanning is enabled, whether the guard is alive and when it last scanned; the Python watchdog that does the watching is deployed separately and found through the DSH_GUARD_ROOT environment variable. The watchdog defaults to a Windows checkout (D:\AI\Projects\dsh-guard); set DSH_GUARD_ROOT to point at another directory.