플러그인

DeepSeek Harness(dsh)용 자동 모드: 권한 선택기에 Auto 항목을 추가하여 승인 요청을 사람 대신 OpenGuardrails 정책이 처리하도록 하며, 내부에는 OGR 가드 엔진 전체가 탑재되어 있습니다. 핵심 코드 수정 없음.

DeepSeek Harness용 선언적 Claude Code 스타일 권한 규칙: tools/pre-execute 흐름에서 도구 이름, 인자(glob/regex), 워크스페이스 경로 매칭이 가능한 순서 기반 allow/deny/ask 규칙, 전체 세션 로그 감사, HMR 규칙 리로드

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.

DeepSeek Harness(dsh web)용 RMB/USD 토큰 과금 플러그인입니다: 피크/비피크 시간대를 반영한 공식 정책 기반 자동 요금 계산, 메시지별 원장, 계정 잔액, 로케일에 따른 통화 표시를 제공합니다.

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.

에이전틱 AI를 위한 권한 레이어, DeepSeek Harness 플러그인 형태로 제공. TapPass /v1/govern 정책 결정 지점을 통해 모든 도구 호출을 비즈니스 규칙에 따라 통제

위험 작업 정책 검사, 출력 마스킹, 보안 검토 워크플로 추가

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Commitment write-gate for AI coding agents: two-tier (deterministic + LLM judge) pre-execution policy. Engine-agnostic core with a DeepSeek Harness (dsh) adapter.

Egress policy for DeepSeek Harness: a host allowlist on web_fetch and web_search enforced at connect time, audit-mode by default, with OCSF Network Activity records

Adaptive task and risk routing, loop budgets, and progressive tool-result pruning for DeepSeek Harness

Browser-automation tools for DeepSeek Harness (dsh): Chromium via playwright-core behind a security-first navigation policy re-checked on every action

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

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.

Policy-driven Git sync for DSH settings and profile configuration, with secret-aware projections, conflict review, and per-line apply controls.

Trusted office suite for government/enterprise work by Beijing Caizhi Technology (深知可信智能): three skills — trusted consulting (policy/regulation Q&A with citation markers + provenance HTML), trusted search (authoritative policy/standard retrieval with traceable HTML + clean Markdown), and official-document writing (draft/rewrite/Word/red-head delivery); all interfaces go through the dknowc trusted workbench MCP (Bearer auth), products land in the session workspace, one-time key setup persists for later sessions; ships on npm as dknowc-dsh.

Browser operation by accessibility refs: navigate, snapshot the page as a ref tree, act on elements, and wait for conditions; the origin policy follows the session approval stance and is enforced by request interception.

Ecommerce operator workbench: CSV batch preview with marketplace column adapters, reproducible profit/six-dimension scoring, public product-page snapshots, Chinese skills, and a replaceable store-policy KB.

Composer cost chip: prices the current session DeepSeek API spend message-by-message with the official pricing table (incl. the 2026-08-17 peak/off-peak policy); hover for the breakdown, today (DSH) total and account balance. DeepSeek models only.