플러그인

Rapid-refill circuit breaker for DeepSeek Harness automatic compaction. It refuses a compaction that would be futile — the context refilled within fewer than N tool turns M times in a row, which the unbounded step-pressure trigger cannot detect — and instead of burning a summarization call on every step it reports the situation with advice, usually that a single read or tool output was too large. Shows state and re-arms through /compaction-breaker, and injects one prompt section so the model relays it to the user. Covers host-plane sessions through its profile bundle; ordinary sessions need one row replaced inside an agent preset.

Windows-native computer use for DeepSeek Harness: two tools drive and read any desktop app. One batch call runs find, click, type, key, read, wait and screenshot steps in a single engine pass, so a task whose steps are known up front costs one model round trip; reading returns window text rather than an image, and input and capture prefer UI Automation patterns, Win32 messages and offscreen PrintWindow so the user's focus and pointer stay untouched.

Hard stop for runaway turns: blocks repeated identical tool calls and ends the turn when per-turn step or time budgets are exceeded.

DeepSeek Harness의 세션 지시 앵커: 새 세션의 첫 단계에서 자유롭게 구성한 지시 블록을 플러그인 출처 메시지로 주입하고, 요약 컴팩션 후, N턴마다, 또는 계측된 컨텍스트 압력이 임계값을 넘을 때 다시 앵커링합니다. /anchor 명령은 모델 호출 없이 필요할 때 다시 앵커링합니다. 설정 페이지에서는 페이지 단위 프리셋 라이브러리, 주입 순서, 재앵커 소스, 문자 제한을 관리합니다.

Shows the running agent step above the web composer as a Chinese sentence: its step number, the tools it is running, and how long it has been going. A finished step keeps its duration on screen until the next one starts, so a slow step can be identified after the fact.

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.

DeepSeek Harness plugin: drop a hint into a running task and the agent picks it up at its next step — without interrupting it and without polluting the chat history. · 旁路提示：任务执行中插一句话，AI 下一步即刻参考。

Notification sounds for dsh-tui: distinct tones for conversation done / user question, focused vs unfocused terminal, 9 selectable sound groups, master volume 0-150% in 5% steps, settings section, zh/en

Ponytail (lazy-senior-dev) as a mode-switchable, always-on DSH plugin: injects the COMPACT ruleset every step (off empties it) and mirrors the full ruleset + five companions into ~/.dsh/skills. Attribution: github.com/DietrichGebert/ponytail (MIT).

DSH 宿主上的 SBTD workflow 适配器。当前为 T5：注册短中文 sbtd section、进程内会话状态、`sbtd_plan`、`sbtd_review`、`tools/pre-execute` / `agent/pre-step` hooks 门禁，以及从 640-skills 只读同步的 `manuals/`。

在会话工具条挂按钮，点击后开新标签页管理提示词；点【注入】可在当前会话下一次模型 step 前注入 prompt 到 system prompt。

Three-party collaboration protocol for dsh: Step List state machine, five-tier review chain (Gemini/web/Claude Code/dialog/manual), alternatives adjudication, cross-restart resume with heartbeat, and capability persistence.

A rail of four circular buttons in the DSH Web conversation that step to the previous or next user message, or to the top or bottom, paging older history in automatically.

Live subagent progress dock for DeepSeek Harness: folds each child session's events into a subagentProgress projection (turn/step, last tool, latest assistant preview, notify_user updates) and renders a frosted-glass status dock above the parent conversat

Installable DeepSeek Harness Web UI for replaying a completed session step

PowerContext for DeepSeek Harness: WorkBuddy-style project memory and inspectable handoff workflows - bounded context recall before each model step, 19 pc_* tools for memory, handoff, experience and skills, with a Windows server watchdog for resident operation.

Prevents concurrent-write session corruption: takes a per-session advisory lock on session start and every step, so a second dsh process fails loudly instead of writing a duplicate-seq gap; dead owners are taken over automatically.

Configurable chat auto-scroll — paced section-by-section reading with size-proportional pauses, smooth follow, step and hold modes, hotkeys, and per-session open positions.

Plan-and-execute orchestration over ReactLoopAgent — turns a goal into reviewable steps with a web UI plan card.

Always-on-top capybara task reporter for DSH Web — a transparent floating pet that narrates each trajectory step in a speech bubble, names the project it reports for, and alerts you when a task completes while you work elsewhere.

Keeps a local model's context at a size the GPU handles well: measures prefill speed on every request and, before each step, warns or compacts early on a hard token ceiling, an observed time-to-first-token budget, or a predicted cold-prefill budget; /context-budget shows the numbers and the cost of compacting now.

Code management panel for the DSH web UI that handles everyday Git in five steps: ① env check auto-detects git/gh/ssh and one-click installs missing tools (gh mirror download sources speed up installs, Windows included) with check-update; ② SSH ed25519 key generation / connection tests plus one-click 443 config to bypass blocked port 22, with the Gitee personal token configured here; ③ repo status, side-by-side diffs, stage/commit, branch switching, history with revert/cherry-pick, one-click repo creation and push, auto-ignoring >100MB files; ④ lists all repos of your account for one-click clone; ⑤ five-step npm publish wizard. GitHub / Gitee dual-platform, with the UI switching between 中文 and English live.

An agent preset that turns a one-line idea into requirements, tech plan and maintenance baseline — every step is restated and confirmed by you before proceeding. No scenario presets: 73 atomic skills (6 master skills + a verify dispatcher + 66 sub-skills) load by context.

Hover timestamps for DSH web chat nodes — start–end (and duration) on Think, Bash and every tool/step row · 在 web 界面 hover Think/Bash 等会话节点行时显示开始-结束时间与用时的 DeepSeek Harness 插件