플러그인

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.

dsh용 대화형 부기 번들: 엄격한 금액 검증과 자연어 날짜로 채팅을 통해 지출/수입을 기록하고, 로컬 SQLite 장부를 기준으로 조회, 보고서, CSV/HTML 내보내기 및 월별 예산 추적을 수행합니다.

DeepSeek Harness용 개인 가계부: 지출/수입 기록(단건 또는 일괄), 목록, 추세가 있는 월간/연간 통계, 진행률과 초과 경보가 있는 예산, 소프트 삭제 복원, CSV 및 자체 포함 HTML 보고서. 의존성 없음, 로컬 JSON.

지원되는 파일 변경에 대한 턴 단위 설정 가능 예산: 도구 실행 전에 대상 파일 수, 변경 호출 수, UTF-8 페이로드 바이트를 제한합니다.

DashScope OpenAI 호환 API(qwen3.7-flash) 기반의 모델용 image_describe(识图) 도구와 붙여넣기 브리지: 텍스트 전용 세션에서 붙여넣은 이미지가 전송 시 파일 경로로 자동 변환되고 트랜스크립트에 다시 렌더링되어 이미지 허용 단계에서 걸리지 않습니다. DASHSCOPE_API_KEY는 BYOK, 엔드포인트/모델/예산 설정 가능, 리다이렉트 방지 HTTP 클라이언트, 모든 agent preset에서 동작.

세션 시작 시 주입되는 장기 기억: 전역 및 프로젝트별 범위의 선호·사실·요약·지식, `agent/pre-step`을 통한 예산 기반 회상, 영속 JSON 저장소.

일간/세션 예산 알림과 usage_report 도구를 갖춘 토큰 사용량 및 비용 추적.

에이전트 트리 토큰 예산 관리

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.