Plugins

Painel de insights de contexto: veja do que é composta a janela de contexto do modelo e como ela evolui — composição em relação ao tamanho da janela, histórico por requisição, eventos de compressão/injeção e estatísticas de tokens por mensagem.

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.

Motor de compactação sem perdas* e sem uso de LLM para o DeepSeek Harness

Histórico de entrada no estilo terminal para o compositor web do DeepSeek Harness: setas priorizando a borda com restauração exata de rascunho/cursor, histórico persistido localmente no navegador, busca reversa com Ctrl+R, recuperação com escopo por workspace e teclas totalmente configuráveis — além de reconhecimento de contexto deslizante

Importe o histórico de chat do claude-code / codex / reasonix / zcode para sessões do dsh: vinculação de workspace, chamadas de ferramentas preservadas, proteção contra sessões grandes demais e restauração de compactação do zcode.

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

Ponte de visão nativa do provedor LLM: imagens coladas no chat são descritas por um modelo de visão (Qwen3-VL via pi-ai/llama.cpp), e a descrição em texto é enviada ao DeepSeek somente de texto para a resposta — admissão de imagem, roteamento e compactação passam pelos mecanismos nativos do harness, com cache de descrições LRU e nova tentativa em erro 503

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.