Plugins

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Agent governance suite: policy-based tool gating (allow/deny/ask with wildcards and priorities), a structured JSONL audit trail, and per-agent token quotas against the host token meter, with state under $DSH_HOME/gov.

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.

Aborts startup when another live dsh instance holds the same DSH_HOME data directory, preventing the concurrent session-log writes that corrupt transcripts.

S3-compatible backend for the spill seam: oversized tool output goes to object storage (S3, MinIO, R2) with hashed session prefixes and unguessable keys, instead of the agent's local disk.

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

Runs isolated install-and-smoke test drives for DSH plugins in throwaway profiles, returning structured pass/fail records and batch matrices without touching your real profile.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Close and restart controls for DeepSeek Harness Desktop and Web on Windows, in Settings → General.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Evidence-backed Skill self-evolution for DeepSeek Harness: redacted trajectory learning, quarantined proposals, arena validation, canary monitoring, automatic rollback.

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.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

Dependency-topology guard: pre-install conflict prediction and post-install detection of duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services that cause Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".

Verifies that Cordis-managed runtime resources return to baseline after isolated plugin teardown, with deterministic cleanup receipts.

Manage development projects from the DSH web UI in a draggable floating window: add/remove, one-click start/stop/restart, hot-reload restart on file changes, and real-time persistent logs.

Ecosystem trend dashboard (行情面板): snapshot the dsh-plugin topic and the awesome list into local history, then report weekly trends — new plugins, star gainers, category heat, awesome coverage — plus a keyword radar for new plugins and star surges.

Verification toolkit for DSH agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), and read-only URL/npm/GitHub submission-readiness probes.

Two-way TickTick/Dida365 (滴答清单) task sync via the official OAuth Open API: pull tasks across lists, create/update/complete/delete tasks, and one-shot title-deduped sync, with a web settings panel.

System-level desktop notifications: turn-completion and workflow-end banners, plus a modal alert when an approval is needed (macOS osascript / Linux notify-send).

Native Windows system notification (Notification Center toast) when a task completes: goal completion or agent turn end.

DingTalk IM channel via Stream-mode WebSocket: each chat drives its own tooled agent; replies stream back as messages, no public callback URL needed.