플러그인

모델이 생각하는 동안 정적 그리드 또는 회전하는 룰렛 휠에서 1..N을 순서대로 클릭하는 동적 Schulte 그리드 대기 시간 미니 게임

Pi TUI(차등 렌더링 터미널 프레임워크) 프런트엔드: 스트리밍 markdown, 사고 접기, 도구 카드, 슬래시 명령어, 승인/질문 오버레이, 공유 dsh 세션 스토어

DeepSeek Harness 플러그인: OpenAI 호환 엔드포인트의 Qwen3 계열 모델을 위한 요청별 사고 모드 전환(enable_thinking)

Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

The row that is running expands itself and folds back when it settles. A running turn keeps its whole procedure in one height-capped window that scrolls itself; a finished turn merges into the built-in finished header, leaving only the final answer. It works by driving the official disclosure rows rather than drawing its own panel, leaves rows you opened by hand alone, and restores the official settings on uninstall.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

Imports chats captured from chat.deepseek.com by the repo's companion Edge extension (loaded unpacked in Edge) into DeepSeek Harness as new sessions; thinking is saved as a sidecar thinking.md, and trimmed, branched or very long chats also get the full transcript.md.

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

Replaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failures (one extra small judge call per turn), picks the effort from that score, and labels every finished turn with the effort it sent.

Turns scattered thinking notes into a growing constellation of themes, claims, relations and open questions, plus a written synthesis of the argument.

Injects a Chinese-thinking reminder around the system prompt and the per-step runtime snapshot, so the agent reasons in Simplified Chinese instead of drifting back to English as the transcript grows.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

공유 OAuth, Qwen 모델 5종, 사고 예산, 스트리밍, 도구 호출을 지원하는 SAP AI Core 제공자입니다. cn40에서 검증되었습니다.

[LLM] DeepSeek Harness가 magpie 업스트림에서 입력 모달리티와 사고 수준을 동기화하도록 합니다.

DeepSeek Harness 플러그인: 모든 에이전트에게 비공개 reasoning을 간체 중국어로 작성하도록 지시합니다.

Claude Desktop에서 영감을 받은 composer 슬라이더로 클릭, 드래그, 키보드 조작을 통해 모델 추론 강도를 조절합니다.

공식 Antigravity ACP runtime을 포함한 Windows x64 번들입니다. 인증/모델/생각 수준을 선택해 단발 텍스트 작업을 위임합니다. Harness >=0.2.1-rc.3 <0.2.2-0에서 host peers를 사용하며 이후 0.2.1 RC와 안정판 0.2.1도 포함합니다.

composer 기록에서 전체 입력 상태를 복원합니다. 내용, 이미지/파일 첨부, @ 참조, slash command와 사용했던 model, thinking effort, permission, agent preset을 함께 되돌립니다.

세션 헤더의 점 3개 메뉴: 세션 로그 다운로드, 채팅별 transcript를 Normal/Verbose로 전환, Verbose에서 확장할 항목(생각 블록, 도구 호출, 터미널 출력)을 설정합니다.

DSH용 Cohere 모델 provider입니다. 기본은 OpenAI 호환 wire를 사용하고 인용/RAG/사고 예산에는 Cohere 네이티브 v2 경로를 사용합니다. 프록시 없는 직접 wire 어댑터입니다.

라벤더 포인트를 더한 차분한 단색 DSH UI입니다. 시작 및 전환 모션, 사고 워크스페이스, 범위 지정 스킬, 선택적 로컬 음성 및 펫 연결을 제공합니다.