Plugins

Retransmissão assíncrona de contexto, resumida por LLM, entre Sessões do DSH e Agent Team Rooms autorizadas, com snapshots instantâneos e resumos agendados

Montagem incremental de arquivos com deduplicação de leitura: intervalos de linhas já montados nunca são reenviados ao modelo, alterações em disco invalidam e remontam, com uma aba de Arquivos Montados e contabilização de economia de tokens

Expõe as capacidades do agente do DeepSeek Harness como um servidor MCP, para que um cliente MCP externo (por exemplo, Hermes) possa comandar o Harness na execução de tarefas de código. Hermes = cérebro, Harness = braços

Adiciona artefatos de especificação, skills, comandos, implementação orientada por objetivos e contexto de progresso das tarefas

Drive Origin scientific plotting from DeepSeek Harness AI chat via MCP: write data, plot line/scatter/column, export PNG/SVG.

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

Sidebar meters for DeepSeek Harness Web: a DeepSeek account balance bar (orange, with a low-balance alarm) and a conversation context-usage bar (blue), rendered above the plugin store with a hover detail popover.

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

DSH plugin: automatic dual-peer Honcho v3 memory, contextual recall, search, reasoning, conclusions, and health diagnostics

MCP & Skill manager: enable/disable MCP servers and skills from a Settings panel to free context in real time; optional AI middle layer (mcp_search/mcp_call) calls disabled servers on demand, with state-based visibility filtering that keeps user-enabled servers visible.

A `search` tool that learns to pick between fast and thorough search strategies using a contextual bandit (Thompson sampling), improving from real usage instead of a fixed heuristic.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

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.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

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

Minimal-compatible first turn for Web root sessions: starts with persistent bash and str_replace_editor, removes automatic workspace and skill context, then restores the selected preset after the first tool call or reply; includes a persistent composer toggle.

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

Ollama Cloud native chat adapter: direct NDJSON translation of the Ollama /api/chat wire format, model discovery with context windows and capabilities, and web search/fetch providers under the ollama-cloud id, plus a Web settings card.

Right-side prompt toolbox panel with 24 built-in deep templates plus user-defined ones, accessible via the /prompt slash trigger and a context-aware floating suggestion card; one-click inserts the selected prompt into the composer.

Camada de execução com reconhecimento de GPU para o DeepSeek Harness: ferramentas gpu_status / gpu_exec / gpu_run_bg, injeção de contexto de GPU por etapa, seleção automática de placa via CUDA_VISIBLE_DEVICES

Skill de compressão de contexto para o DeepSeek Harness — sumarização inteligente de conversas

Memória de persona persistente e de longo prazo para o DeepSeek Harness: armazenamento em MEMORY.md/USER.md, ferramentas memory + memory_search, injeção de contexto por requisição e verificação de segredos. Portado em espírito a partir do pi-hermes-memory

Taxonomia de contexto de chamadas lógicas para o perfil Web do DeepSeek Harness

Um plugin do DeepSeek Harness que integra o claude-mem: consulta, injeção de contexto, salvamento manual e ciclo de vida de sessão via a API HTTP de um worker local do claude-mem