Plugins

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.

Hard-stops further tool calls after a configurable per-session budget is reached.

Composer stats strip for the DSH Web UI: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live timers, subagent-tree merging, DeepSeek account balance, budget alerts, and streaming cost estimation.

Memory Standard Protocol (mm) for DeepSeek Harness: layered MEMORY.md with hard budgets, frozen snapshots, mm:// URI interop, session-log digestion, mem_* tools and a standalone CLI.

Pacote de contabilidade conversacional para dsh: registre despesas/receitas por chat com validação rigorosa de valores e datas em linguagem natural, depois consulte, gere relatórios, exporte CSV/HTML e acompanhe orçamentos mensais em um razão SQLite local.

Contabilidade pessoal para o DeepSeek Harness: registre despesas e receitas (unitárias ou em lote), liste, estatísticas mensais e anuais com tendências, orçamentos com progresso e alertas de estouro, restauração após exclusão lógica e relatórios CSV e HTML autocontidos. Sem dependências, JSON local.

Orçamentos por turno configuráveis para as mutações de arquivo suportadas, limitando arquivos distintos, chamadas de mutação e bytes de payload UTF-8 antes da execução da ferramenta.

Ferramenta image_describe (识图) voltada ao modelo sobre a API compatível com OpenAI do DashScope (qwen3.7-flash), além de uma ponte de colagem: em sessões somente texto, imagens coladas se convertem automaticamente em caminhos de arquivo no envio e são renderizadas de volta na transcrição, para nunca esbarrarem na admissão de imagens. Traga sua própria DASHSCOPE_API_KEY; endpoint/modelo/orçamentos configuráveis, cliente HTTP à prova de redirecionamento e funciona em todos os agent presets.

Memória de longo prazo injetada no início da sessão: preferências/fatos/resumos/conhecimento em escopos global e por projeto, recall com orçamento via `agent/pre-step`, armazenamento JSON durável.

Acompanhamento de uso de tokens e custos com alertas de orçamento diário/de sessão e uma ferramenta usage_report.

Gerenciamento de orçamento de tokens para a árvore de agentes

Track token spend and enforce budgets for every model call your dsh agent makes.

Edit global and project instruction files in DeepSeek Harness settings, with project-chain discovery, byte-budget display, and save-conflict handling.

Hard stop for runaway turns: blocks repeated identical tool calls and ends the turn when per-turn step or time budgets are exceeded.

Read-only enhancer for a file-based long-term memory library (markdown cards in git): a memory_find search tool, a small budgeted memory digest injected into the system prompt, and a settings page with library overview, health-check status and toggles.

Three-mode visible-session advisor plugin for DeepSeek Harness with configurable tool permissions, local-subagent coverage, and task-tree budgets.

Adds per-route context window and compaction threshold fields to the Models settings page and a vendor-aware thinking-effort picker to the composer, writing llm-pi-ai capacities, reasoningEfforts, and a compaction-basic patch row.

DeepSeek Harness plugin: expensive models plan and review, cheap models implement, a program loop keeps the factory inside budget.

CWL — Context Window Lifecycle for DeepSeek Harness: structured context eviction (arXiv:2606.11213). Graduated, deterministic, zero-LLM eviction of exploration/action episodes when context pressure exceeds budget — no summarization lossiness, no hallucina

Injection scheduler for DeepSeek Harness injection planes: cross-plugin sections register/order/account on the official storageDomain, with conflict detection and per-session budget summaries (B10 panel data source).

dsh-plugin: quality-first topic memory for dsh — a topic keeps the starting question, conclusion, impact and dependencies, not the process; local-first git-traced OKF bundle, budgeted LLM-free injection

Cross-session knowledge for DeepSeek Harness: ctx.knowledge service + knowledge_* tools, SQLite FTS5 trigram retrieval (CJK substring) with L1 query expansion. V1.11 contract (write/update/search/list/delete + budget + events + error codes).

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.