Plugins

Adds a take screenshot tool plus two optional automatic capture points, putting the screen into the conversation as an image block; requires an image-capable model.

Proactive multi-model scheduling plugin: multi-source signal intake with dedup and urgency ranking, a four-way execute/defer/dismiss/ask-user decision engine, DAG plan generation with parallel model execution, quality reflection with automatic retry and model switch, long-term memory for task patterns and lessons, and strategy evolution via genetic algorithms with sandboxed evaluation and canary rollout.

Routes agent requests to configurable default, planner, and subagent models, automatically using the planner role in plan mode, with per-role reasoning effort and Web UI configuration.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

一个可以让ai自动调用VLM(多模态模型)进行视觉分析的dsh插件。A dsh plugin that allows AI to automatically invoke VLMs (multimodal models) for visual analysis.

Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.

Fully local vector memory for DSH: local embeddings, SQLite storage, automatic recall injection, dedup with conflict detection, soft-delete recycle bin, online backup, and optional LLM extraction.

Boot-time watchdog for DSH web: detects broken plugins, disables them persistently so the UI opens, with quarantine audit, automatic probe recovery, and one-click restore.

Auto maintenance and resilience for DeepSeek Harness: startup self-diagnosis, automatic repair of missing directories, scheduled configuration backups with rotation, one-click restore, smart-start port detection, plugin-change self-check with automatic rollback, startup failure rescue, and a health watchdog that restarts a stuck-but-alive instance. Ships as a Cordis plugin plus a standalone CLI.

A self-evolving plugin for DeepSeek Harness: it observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

A settings-panel skin manager that auto-discovers installed Web UI skins, switches between them in one click, and maintains the profile patch automatically.

Real-time token billing for DSH web: official DeepSeek CNY pricing with automatic peak/off-peak switching, hourly price sync from the official site, visual custom model prices, and multi-currency fallback.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Adaptive model routing: per-request complexity classification with automatic provider routing.

HeartFlow (心虫) AGI layer-1 discriminator gate as a DSH plugin: 47-dimension rule-based text checking (heartflow_check tool) plus automatic output supervision at tools/post-execute, fail-closed when engine missing.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Automatically retrieves time-of-use pricing data (with Beijing Time) and notifies users during peak periods to reduce costs.

给每次 AI 对话装一根 Token 保险丝：为每条用户消息设置独立总预算，统一约束输入、缓存、思考与回答。A per-conversation total-token safety fuse for DeepSeek Harness, with a whale slider and automatic reset on the next user message.

Multi-channel notifications for DeepSeek Harness: registers a send_notification tool and a settings page fanning out to NotifyX, WeCom app webhook, WeCom group robot, email (Resend), SMTP, DingTalk, Feishu robot; plus browser notifications and automatic notification on task completion and blocking events.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.