플러그인

컨텍스트 인사이트 패널: 모델의 컨텍스트 윈도우 구성과 변화 과정을 확인합니다 — 구성 비율 대 윈도우 크기, 요청별 이력, 압축/주입 이벤트, 메시지별 토큰 통계를 제공합니다.

Profile-wide DSH governance and routing bundle with configurable compaction calls and scoped local semantic memory; compatible with DSH 0.1.0-rc.6 and 0.1.0-rc.7.

DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

DeepSeek Harness용 LLM 없이 동작하는 무손실* 압축 엔진입니다.

DeepSeek Harness 웹 컴포저용 터미널 스타일 입력 히스토리: 엣지 우선 화살표 이동과 정확한 초안/커서 위치 복원, 브라우저 로컬에 저장되는 히스토리, Ctrl+R 역방향 검색, 워크스페이스 범위 회상, 완전히 커스터마이즈 가능한 키 바인딩, 슬라이딩 컨텍스트 인식 기능

claude-code / codex / reasonix / zcode의 대화 기록을 dsh 세션으로 가져옵니다: 워크스페이스 바인딩, 도구 호출 보존, 세션 과대화 방지, zcode 압축 복원을 지원합니다.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

네이티브 LLM 제공업체 비전 브리지: 채팅에 붙여넣은 이미지를 비전 모델(pi-ai/llama.cpp를 통한 Qwen3-VL)이 설명하고, 그 텍스트 설명을 텍스트 전용 DeepSeek에 전달해 답변 생성 — 이미지 수신, 라우팅, 압축 모두 하네스 네이티브 메커니즘으로 처리, LRU 설명 캐시와 503 재시도 포함

Vision toolkit for text-only DeepSeek: model-invokable `vision` tool, wrapper adapters for deepseek/opencode-go (v4 flash/pro), Antigravity IDE quota (default, flash/pro) / any OpenAI-compatible VLM / Gemini / local Ollama channels, evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Deterministic context compaction: prunes conversation atoms in reference-graph topological order with no LLM calls during compaction, and keeps pruned atoms recallable by marker.

Deterministic context-pruning compaction backend for dsh (DeepSeek Harness) — zero-LLM summaries, /dcp command, works out of the box. Design references Opencode-DCP/opencode-dynamic-context-pruning.

Read-only performance diagnostics for DeepSeek Harness: session load (open/restore) timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via the /fas

Visual percentage and token settings for official DeepSeek Harness compaction

File-based self-evolving memory for DeepSeek Harness v2: compression & extraction over official compaction, daily episodic layer, dream consolidation to semantic files (user/agent/memory/dream + project), catalog disclosure injection, no confidence machin

Pure-incremental directive-driven compaction for DeepSeek Harness: /compact-directive <requirement> summarizes the session middle per your requirement, /trim-directive <requirement> trims the whole conversation per your requirement

The pet that grows with your agent: 5 evolution stages earned from real signals (verified rules, completed sessions, tool calls, compactions), agent-state mirroring, and one-click growth share cards. Zero dependencies, 100% local.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.