Plugins

Pre-install supply-chain checks for DeepSeek Harness plugins: verify the tarball you are about to install matches the source you read, before any code runs.

Permission mode between workspace-write and full access: shell commands are checked by deterministic rules and a subagent review; irreversible or system-level actions require explicit approval.

Checks git commit messages against the 7DGroup convention (Chinese type tags, length and punctuation rules) before committing, as a client-side guard before GitLab pre-receive hooks.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Falsification-driven correction loop for agent sessions: risky work commits an evidence-checkable claim first, deterministic gates verify it, falsified claims force mutually exclusive replacement hypotheses with discriminating experiments, and every event lands in an append-only evidence ledger.

Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run

Toggle, delete, undo-delete, and check/update plugins from the Web settings panel; runtime enable/disable is persisted to the profile.

Plugin insight center: one answer to "哪些值得装" — plugin_guide matches needs to plugins, recipe installs whole environments, plugin_rank scores health (0-100), plugin_audit static-scans a local checkout for security, and plugin_verdict outputs install / caution / research / avoid.

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Test-stability tools: repeatedly run vitest/jest/pytest/node:test suites, classify flaky cases, keep history, maintain a quarantine manifest and health self-check.

Update checker (npm edition): a settings page comparing local and latest versions of @deepseek-ai/dsh and every installed plugin, with a red-dot nav reminder and ready-made update commands.

Update copilot for DeepSeek Harness: one scan covers the DeepSeek Harness core and every profile plugin; explains what changed and how risky each update is, then updates only what you confirm.

Registers a `config_doctor` tool that checks the harness's own configuration for problems that boot silently: fields a patch dropped by whole-config replacement, patches targeting missing entry ids, and tool-name collisions. Read-only.

Boot-time guard that repairs corrupt session logs, preflights plugin composition, vm-checks client artifacts, smoke-tests host apply() and quarantines crash-causing bundles, so a broken plugin can never brick startup.

Automatic type-check diagnostics: after the model edits or creates TS files, runs `tsc --noEmit` in the background (debounced per project) and reports errors via the `code_check` tool — grouped by file with line/column, severity and TS error codes, closing the "edit → check → fix" loop.

Checks npm hourly for newer versions of the installed plugins and asks which ones to upgrade.

Beginner starter pack for DeepSeek Harness: welcome flow, 0→1 learning path, scenario-based plugin recommendations and a self-check checklist, paired with the dsh-handbook-zh Chinese tutorial repo.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Personal toolbox for the dsh web profile with per-feature toggles: task-done desktop notifications, one-click restart, session deletion, plugin enable/disable, update checks, and UI utilities.

Stage-gate governance tools: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks with PASS/BLOCK conclusions.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.

Incremental diff reviewer for DSH: after approving a batch, only new changes since the checkpoint are shown, with a Web review panel and `/review` command that inject feedback back to the agent.

DeepSeek Harness dual-face plugin: a visual plugin manager tab in Web Settings — enable/disable any plugin row, check installed plugins (including official @deepseek-ai/* rows) against the npm registry, update them, repair pristine files, and update the h

Hosted tool server over MCP: invoice and bank-statement extraction with in-code arithmetic checks, ledger reconciliation in integer cents, PDF and table conversion, SQL dialect transpiling, and mainland-China reachability probes run from a China Mobile network vantage point.