Plugins

Per-request thinking budgets, a compaction backend, and a settings tab for the local Qwen3.8 line (llama.cpp or NInfer).

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports Claude Code/Codex/Cursor multi-agent sharing. Zero external dependencies.

Pi-style append-only multi-branch session trees: fork or jump to any historical node without deleting history, clone a branch into a new session, and browse the tree in a WebUI panel. Works on stock Harness via graceful degradation.

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

Adds an unofficial Antigravity OAuth-backed LLM route, web search, image generation and editing, video understanding, quota status, and DSH Web settings controls.

dsh · dsh-plugin · deepseek · deepseek-harness · deepseek-harness-plugin · ai-companion · desktop-pet · character-card · local-first · privacy · jingling · 鲸灵

Embedded C/C++ firmware development toolbox: agents and skills covering FreeRTOS, interrupts, NVM storage, Keil MDK, ARMCLANG, HardFault triage, state machines, architecture, and LVGL patterns.

Connects DeepSeek Harness to Multisim MCP for circuit generation, simulation, diagnostics, design optimization, and experiment report export.

Presents DSH Web as a playable, full-screen first-person Minecraft-style voxel interface—not a color-only skin: users walk through a persistent Three.js block world and access native workspaces, sessions, conversations, tools, model selection, permissions, context information, and the composer through in-world facilities and a workbench.

Review agent file changes as a dsh-better-sidebar sidebar tab or chat turn-tail row — line-level diffs and undo.

🌊 Persistent dock & fully-customizable balance/usage panel for DeepSeek Harness — activity heatmap, dual-channel comparison, local-only & privacy-first

MCP server manager for DeepSeek Harness: add, edit, enable/disable, restart and delete MCP servers from Settings → MCP 管理, with JSON export/import, four mcp_manager_* model tools and an HTTP API; install via npx, npm or cross-platform scripts.

Cross-device session sync for DeepSeek Harness — syncs sessions and settings between machines through git.

A study tab with course-map, tutor and blackboard columns that turns markdown files, local folders or GitHub repos into guided courses, with lesson unlocking, mastery tracking, spaced repetition and a tutor-designed course import.

Update management for DeepSeek Harness and its plugins: semver-aware dual-source (npm/GitHub) checks for the main program and every installed plugin, a locale-aware banner (zh/en) listing updatable items, one-click updates (the main program is backed up, integrity-checked and rolled back on failure; plugins install via a temp directory without touching other packages), and a watchdog-guarded restart after updating. The settings page adds per-plugin version lamps, live update progress, and banner/notification toggles.

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.

One-click optimization of a raw instruction into a professional prompt: three output styles, situation-aware role/task/goal profiling, multi-sample selection scored by a model judge, self-iterating learning (session memory + smart defaults + user overrides), /template for 22 sub-scenes with zero model calls, input-box ✨ one-click optimize/undo, prompt_optimize tool, auto-optimize hook, a runtime status page, a settings panel (dsh 0.2.0) and auto-detected zh/en documents.

Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.

IMAP/SMTP email tools (list/read/search/send/folders/attachment/health/watch/mark/reply) with since/until date-range filters, email_mark for read/unread/star/move, email_reply for reply/reply-all/forward with threading headers, QQ/163/126/Sina/Aliyun/Gmail/Outlook/iCloud presets, multi-account support, a send-approval gate, a web settings page and a whale-girl new-mail popup driven by the incremental email_watch checker. Outlook OAuth2 device-code login works out of the box through a built-in community client, and an account can still supply its own clientId instead.

Role-based LLM retry & fallback strategies.