플러그인

콘텐츠 인식 도구 결과 축소기: tools/post-execute 단계에서 13개의 리듀서가 의미를 기준으로 과도한 출력을 축소합니다(실패한 테스트는 유지, diff 컨텍스트는 제거, JSON·CSV는 샘플링, lint 문제는 규칙별 그룹화, 의존성 스택 프레임은 접기, 혼잡 디렉터리는 카운팅). 전체 원본은 로케이터와 함께 디스크에 저장됩니다.

로컬 인증된 AGY CLI용 DSH 모델 프로바이더: Gemini/Claude 모델 검색, 독립 리즈닝 노력, DSH 소유 도구, 경계 컨텍스트 및 도구 결과 처리, Windows 안전 스트리밍. GitHub Issues에 문제 보고: https://github.com/darkings/dsh-agy-provider/issues.

입력창 프롬프트 최적화 도구: 6가지 전략 × 3개 언어와 사용자 지정 지침으로 초안을 다시 작성하고, 목표/할 일/압축 요약/도구 결과와 채팅 컨텍스트를 선택적으로 활용합니다. 확인 대화상자, 최근 5개 기록, 3단계 설정 지속성을 제공합니다.

Eager, tail-heavy, line-aware tool result trimmer plugin: hooks into post-execution pipeline to trim oversized command outputs with smart semantic reducers and ANSI stripping.

Model-driven tool-result archiving for DeepSeek Harness. Results above a configurable size carry a short inline id (\[#a1b2c3d4]); the model archives the ones it no longer needs into the session's own archives/ folder and the context keeps a small recoverable stub with the file path. Originals stay in the append-only session log, so nothing is lost. Ships a settings panel with per-size-bucket recovery stats, thresholds that apply without restart, and a conditional reminder when results are waiting to be archived. Requires dsh-better-sidebar for the statistics panel.

A human-in-the-loop curation workbench inside a DSH session: mark whole turns or single messages to keep verbatim or to summarize, rewrite user, assistant, tool-result and injected-context messages in place without a model call, then compress the marked ranges with model-written summaries or the official /compact. A local JSON backup is written before every write to the session.

Model-driven context compaction for DeepSeek Harness. The agent decides when and what to compress, commits durable session-log replacements, and ships reversible tool-result compression with byte-exact hash retrieval.

DeepSeek Harness Web plugin that keeps image-bearing Tool results visible after Compact transcript folding

Session-header button that previews and downloads the exact request frame DeepSeek Harness sends to the model: the full system prompt, the declared tools array, and the wire message array (system/user/assistant/tool-result) rebuilt from the session log via the same folds the agent loop reads.

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

Data-loss-prevention plugin for DeepSeek Harness: a non-configurable tool guard floor, tool-result redaction, and fail-closed telemetry redaction