Plugins

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Skills & MCP section in Settings: browse, create, edit and delete skills with live directory watching, toggle loading of any on-disk skill through frontmatter policy keys, register local folders or GitHub repos as extra skill scan roots, edit the MCP server rows in the profile patch, import MCP config from Claude Code or Codex, and install from a curated market of skill repos and MCP servers.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Version management for dsh: inspect the installed version against every npm channel or version line, install or downgrade in one click, stream the install log live (rollback-snapshot copy progress, npm extraction progress, elapsed time), roll back instantly from local snapshots, and automate the cycle with a policy engine (silent auto-update, execution windows, daily checks). Never stops npm mid-install — a wedged run is only stopped after an hour, and a half-committed global tree is detected and repaired from the pre-install snapshot automatically. Confirms before installing a found update, auto-restarts the host after install, and falls back to a mirror when the primary registry is unreachable.

Runtime extension suite for DeepSeek Harness: cross-session mailbox with wake cold-start, agent teams (captain + members + dependency task board + team_wait), subagent spawn policy with escalation approval, task-aware routing preset, plugin market, skill manager and runtime injector.

Allow, ask, or deny DeepSeek Harness tool calls before execution

Adds subagent_route and subagent_fork_route delegation tools where the model itself picks the provider/model route for each child; the deployment only sets the spawn/fork backend, background policy and allowedProviders allowlist, while continuable children and background jobs reuse the official send_message / job_output tools.

DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.

RMB/USD token-billing plugin for DeepSeek Harness (dsh web): official-policy auto pricing with peak/off-peak hours, per-message ledger, account balance, locale-driven currency display. 人民币/美元 token 计费插件

Reusable subagent definitions managed from a Settings page and dispatched through a single delegate_agent tool; ships with a built-in read-only Explorer preset and a nested-delegation policy toggle.

Static bundle form of the DSH plugin-install security gate: reviews cordis_define/cordis_run with a fail-safe policy, plus review/audit tools and a browser approval popup (agree / agree+whitelist / reject; agree+whitelist writes the plugin family into tru

DSH Windows default shell policy plugin: probe git-bash/MSYS2, switch bash/pwsh from the plugin config card, register the bash tool and trim the prompt tool surface. DSH Windows 默认 Shell 策略插件：探测 git-bash，配置面板切换 bash/pwsh，动态注册 bash 工具并裁剪提示词工具面

Runs reproducible DSH profile and patch experiments with guided case authoring, assertions, Web comparison reports, recovery, and policy gates.

Manage the DeepSeek Harness skill catalog from Settings: list what DSH actually resolves, enable or disable a skill by policy without touching its source file, read and edit SKILL.md, and create, import, or permanently delete skills.

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.

Agent-native API client for DeepSeek Harness: Postman-like debugging UI (request tree with context menus and full keyboard navigation, resizable sidebar, layered auto-generated header preview with per-item suppression and constant secret masking), six api_client_* agent tools sharing the same request core, redaction and audit chain with the human UI, Postman Collection v2.1 import with a migration report, environment variables with SecretRef indirection, and a fail-closed SSRF network policy.

Open folders on remote hosts over SSH as Harness workspaces: file tools (read/write/edit/grep/glob) and shell commands run directly on the remote host over SFTP, ripgrep, and ssh2 exec, with no local mirroring, an encrypted multi-host registry, and the local sandbox policy still enforced.

Policy plugin that gates kubectl by kubeconfig context: hard-deny irreversible verbs outside local clusters, ask for the rest.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy。

LLM debug console for DeepSeek Harness: captures the full content of every model call at the llm/stream waterfall (options, stream chunks, usage, wire protocol) and shows it in a DevTools-style docked panel, with shared-prefix context diffing, wire-JSON reconstruction, JSON export and a runtime-tunable capture policy.