Plugins

Lean and light? See DSH CPU, memory and UI stalls, broken down by plugin, terminal and MCP server, matched against stall times, and copy a diagnostic report. Windows x64 only.

Adds a Restart card to the harness settings: one click hands the restart to the DeepSeek Harness launcher (`Launch-DeepSeekHarness.ps1`), which replaces the running web process, and the page reconnects itself once the new instance answers. Windows only; without that launcher the button reports an error instead of restarting.

Douyin patent and trademark complaint workflow for DeepSeek Harness with a left-sidebar task panel: checks user-supplied links, materials and organization identity in a dedicated browser, records each submission state, queries platform history read-only, and shows local task counts in the sidebar; never discovers targets or submits without explicit authorization.

Local usage ledger that reads this machine's session logs and reports per-day, per-model and per-workspace token consumption, cache hit rate, tool-vs-chat split and estimated cost, with an in-app editor for per-model prices.

DSH-Search-Contrl: a DSH skill/plugin for scoped web search and Chinese daily reports, with a settings GUI for custom search sources, arbitrary topics (not only tech), creator-link scoped search, and one-click rollback.

Audits the skills and plugins you already installed: routes a task description to the tool it needs, flags version drift against the npm registry and runtime faults from host logs, and reports which of a plugin's tools you never call. Registers 9 tools: can, find, status, recommend, check, scan, probe, run and suggest. Runs on Python 3.8+ with no third-party dependencies. Registered tool ids all carry the skill_audit_ prefix, for example skill_audit_can and skill_audit_find.

Windows toast notifications for DeepSeek Harness: approve or reject from the notification while DSH is in the background, with an in-app fallback; foreground only skips the current conversation, while other conversations still notify. Also reports turn completion and errors; subagent sessions stay silent.

QQbot, QQ机器人 — watches chosen QQ groups over OneBot 11, batches messages by a count threshold, summarizes each batch with a model already configured in DSH, and sends the per-group report to chosen friends as a QQ private message. Messages can be filtered by keyword and by sender; ships a settings page, a local web console and a summary archive.

Nudges the main agent of a long-running DSH session to report progress at a configurable interval, with exponential back-off, stuck detection, a per-session Progress tab, and a manual "nudge now" action.

Checks a bid requirement by requirement against a tender requirements pack and reports which requirements appear answered, weakly matched or not located. It reports differences; it does not judge substantive compliance.

Progress tab for the DSH right sidebar: the turn status of the session and the progress long-running tasks reported, in one tab beside the conversation.

Adds a connection-test panel under Settings -> Models: reads the deployment's model catalog and probes each configured model with one minimal chat round-trip (a short "ping" with a small output cap) through the Host LLM service, verifying connectivity with a real request. Each row reports success/failure with the harness failure code (NO_ADAPTER, MISSING_CREDENTIAL, AUTH, RATE_LIMIT, TIMEOUT, ...) plus first-token/total latency; single-model and concurrent test-all (3) are supported. Credentials are resolved inside the Host process and never reach the browser; probes are independent per model behind a same-origin-fenced route with a body-size cap. Pure JS, no build step, MIT.

Forensic analysis of past model-routing decisions. Replays each session, classifies every turn's task complexity from its request shape (deterministic, no LLM), and reports two kinds of waste: an expensive model on cheap work (the difference is measurable), and a cheap model on expensive work that failed on its own merits — where every retry re-sends the whole context, so the downgrade cost more than the upgrade. Distinguishes provider-capacity retries (RATE_LIMIT/TIMEOUT/TRANSPORT) from model failures so it does not cry wolf. Derives routing rules from the evidence, priced against a built-in per-million table.

Registers fifteen slash commands (/idea, /review, /poster, ...) that inject the matching research skill's SKILL.md as a user message, so installed skills run without a marketplace. The skills are not bundled and must already be under ~/.dsh/skills or ~/.agents/skills, otherwise commands report skill not found.

Run a read-only security assessment of a Dameng DM8 database with 60 checks and produce an HTML report with GB/T 22239-2019 control mapping. Needs Java 8+ and a DmJdbcDriver jar you provide yourself.

Panel entry for the official client-plugin hot reload that tells you what actually changed first: it diffs each row rev against the last seen state and reloads only the plugin bundles that changed, keeps whole-graph reloads behind an explicit confirmation (a bare call is refused and reports the affected row count), and reports replay counters so a silent no-op cannot hide.

Read-only panel reporting an instance's plugin bundles, patch inserts, skills, upgrade health and decoupling health.

Self-healing plugin doctor: detects failed DeepSeek Harness plugin rows, disables them automatically after backing up the profile patch, and reports diagnostics via /doctor.

Runs a diff past several reviewers at once — a CLI coding agent such as codex or claude, or a DSH subagent — and merges their separate sections into one report; reviewers and named review modes are configured in the settings UI.

Agent preset for DeepSeek Harness: the standard tool stack plus four working rules written into the persona prompt — a project keeps at most four documents (intro, decisions, change log, current state and next steps), those documents describe only the current state with no AI edit history or superseded decisions, no git commit or push or pull request until the user explicitly asks, and a careful-coding workflow (restate the goal and done-criteria first, surgical diffs, evidence before claiming success) with plain-language reports.

Requires the Codex CLI installed and `codex login` completed. Consult the OpenAI Codex CLI from DeepSeek Harness with three tools: codex_consult runs Codex in a read-only sandbox, inlines evidence files, verifies the served model and reasoning effort from the Codex rollout file, retries disconnected streams, and records quota before and after the call; codex_quota reports the current 5-hour and weekly quota; codex_calls lists recent calls.

Read-only assessment of whether a Dameng DM8 database can be recovered and to which point (LSN or time), across 16 recovery scenarios, with an HTML report. Needs Java 8+ and a Dameng JDBC driver jar (DmJdbcDriver8.jar) that you provide yourself.

Companion sidebar panel for the Kaipu site plugin: shows the built-in advisory team and seat status. Install together with kaipu-platform — seat data comes from the site plugin's gateway endpoints; a standalone install honestly reports "channel not ready". Removable: uninstall it and the site plugin stays fully usable.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy, supervises the local wb2api gateway, and runs a bundled Responses-to-chat-completions bridge so Codex CLI can use the same gateway. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.