Plugins

Cost tracking priced from an online catalogue (models.dev + OpenRouter, 8000+ models, each call priced at its own instant): a per-turn cost line, a Cost tab attributing spend to tool output / model output / system prompt / commands, budget, monthly forecast, ~166 live-rate currencies, and a bill_stats agent tool.

Automatically folds tool calls into Think-segment groups and collapses each finished turn into a single header showing duration, token, throughput, and cache-hit metrics.

Feynman learning-mode plugin: teach → teach-back → judge → re-explain loop rendered as rich HTML lesson cards (mermaid diagrams + shiki code highlighting).

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

11 shareable workflow skills (handoff, triage, to-spec, to-tickets, wayfinder, teach, wait-what, dsh-mode-routing, ask-matt, overnight-execution, full-throttle) as an installable skill pack.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Maps locally analyzed system audio to music-reactive conversation effects, rhythm-game judgements, score and combo feedback, and optional RGB spectrum bars in DSH Web.

Edit a sent message to rewind and branch the conversation from that turn, switch versions with a counter under the bubble, and browse every branch in a turn-level version tree.

Visual development studio for DSH WebUI plugins with isolated Git worktrees, live official-WebUI previews, source editing, patch inspection, builds, and validation.

Interval heartbeat that wakes each root agent itself (followup injection) to proactively report progress, risks or blockers: busy-safe queuing, no stacking, auto-pauses when no human replies, re-arms on the next user message.

DSH Companion 鲸鱼 Skill/CLI 插件前端（dual-face Cordis 插件）

Turns the user into an RPG protagonist: after each finished user turn a random "adventure" may trigger, drawn from 700+ events across 7 themed pools (sci-fi, fantasy, ancient, anime, novels, wuxia, urban), growing six persistent attributes (strength, intelligence, agility, charisma, luck, vitality) with XP, levels and attribute-weighted story branches, configured via a settings-page UI.

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

Connects WeChat, WeCom, DingTalk, Feishu, Lark, QQ, and Telegram to a local DeepSeek Harness agent, with each IM chat as a separate workspace channel.

Per-event sound notifications: turn completion, approval, question, plan-review, goal-blocked, and task-failure each get their own sound and volume, configurable in the Web UI (built-in synth, mute, or local audio file).

Lets sandboxed agents reach the web through your local proxy: net_fetch fetches pages, net_proxy_status reports proxy status.

Daily RSS/Atom news digest for DSH: built-in channels plus a curated awesome-rsshub-routes catalog and custom feeds (validated on save), aggregated into one "今日值得读" Markdown digest each day and injected into the system prompt; Web GUI settings card and sidebar reader.

Idle session reminder: prompts to archive sessions untouched for N hours, with a snooze window after each refusal, using the official archiveSession API.

Project and session organization with multi-folder groups, attention summaries, grouped chat search, native folder picking, pinning, favorites, ordering, and an archive center.

Move a session to another folder from the Web UI via drag & drop or a menu picker, permanently delete a session with a risk-consent dialog, and AI-rename a session by summarizing the whole conversation (typo-aware). Each action also ships as an agent tool.

DeepSeek Harness (dsh) web plugin: API balance + today's spend widget in the sidebar footer. /api/dsh-usage route + React client bundle, no build step required.

Project-scoped cross-session memory: PROJECT.md snapshot injected into the first user message, a memory_remember tool, and auto-reflection after ReAct tasks; each project keeps its own memory file.

Per-turn USD cost badge in the Web UI: session total in the header and per-turn cost in each message footer, with a hover breakdown.