Plugins

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.

Automatic secret redaction in tool results: masks API keys, tokens, JWTs, private keys and configured secrets before the model sees them.

Automated approval review: auto-approve read-only tools, auto-deny dangerous commands, fail-closed policy engine.

Static pre-install security auditor for plugin bundles: lifecycle scripts, dynamic execution, credential-exfiltration combos, and patch-layer hazards, with zero dependencies and in-memory tar parsing.

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.

Skill center in the DSH web GUI: browse loaded skills grouped by source (system / project / user / custom / runtime), with create, enable/disable, and delete (moves to .trash) actions.

Gzip compression for /api responses, fixing history-load timeouts over remote/low-bandwidth connections; skips SSE and already-encoded responses.

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.

Reloads an upgraded plugin inside the running dsh process instead of restarting it, and rolls back to the old version when a reload fails.

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.

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

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.

Reuses hooks declared in Claude Code, Codex and opencode configs on dsh, executing shell, webhook, oracle and proxy handlers with zero runtime dependencies.

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.

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