Plugins

Telegram mobile remote that attaches the phone to a live DeepSeek Harness Web session: workspace-then-session picker (/sessions), /last for the previous Q/A, /model switch, and native Rich Message replies.

Ships a set of /logi commands for project housekeeping: dispatches security, logic-correctness, maintainability, reliability and performance experts to inspect the whole project, then produces one consolidated improvement report.

A single-character agent that lives across QQ (via SnowLuma / OneBot 11), Bilibili and Douyin (the Douyin channel needs an always-on Windows desktop): persona cards with slowly evolving traits, per-person memory with Ebbinghaus decay and correction, a virtual clock driving a daily routine, proactive messages, auto-extracted memories, and a ten-tab settings panel covering retrieval, persona, routine, memory inspection, channels, habits, models and usage. QQ groups are deny-by-default: a group is answered only when it is on the allowlist or allGroups is explicitly switched on, and it still has to @-mention the bot. Private chats answer QQ friends only. Bilibili/Douyin auto-reply is off by default, limited to the owner, allowlist and mutual follows on Bilibili, and to the owner and allowlist on Douyin unless reply-to-everyone is explicitly enabled. Vendors MIT-licensed code from dsh-qq-bridge and dsh-douyin-bridge, credited in-source with their LICENSE files; it does not need either installed alongside.

统计所有经过 DeepSeek Harness 的模型调用：Token 用量、成本核算（含峰谷计价）、首字延迟与输出速度、供应商余额与配额、预算，并按模型/供应商/项目/来源/账号/日期拆分。

Preset workbench for editing per-agent personas, system prompt sections and tool descriptions, selecting tools and skills, previewing request context, and importing or exporting JSON/YAML configurations.

Windows-only plugin that watches the foreground window title, recognizes Bilibili video courses, classifies them by subject, fetches metadata/danmaku/comments, and generates Markdown + Mermaid knowledge maps and Word study manuals (Word output needs a local Python install).

Replaces the chat composer with an editor-style input panel on CodeMirror 6: line numbers, edit + markdown-preview split, a floating window mode and a full-height sidebar tab — one input surface at a time. Drafts ride the official input machine; the official voice-input button is rendered when the host provides one, and the stats row and context meter read the same data as the official dock.

Pending-change review for DeepSeek Harness: every `edit`, `write` and `str_replace_editor` change is collected automatically into the file list, where a single change block, the blocks within a selection, or the whole file can be kept or reverted, and undo/redo is supported. It imports the workspace's version-control changes, shows the diff in a single-column or side-by-side view, and provides a Markdown preview in which changes can also be kept or reverted, in-file search, block jumping and copyable line references; the diff data is stored persistently, so the review continues after a restart.

Attaches a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests, fixing 400 MissingSessionID errors and keeping session affinity and prompt-cache routing intact.

Visual node-based workflow canvas for DSH with sub-agent calls, code execution, branching, loops, scheduling, and workflow import/export.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

Project file explorer in the details column (multi-select, drag-move, upload, download, rename, trash, system-open) with an in-session read-only preview tab for Markdown/HTML/JSON/CSV/notebook/PDF + code highlighting, a live model throughput badge, and a multiline GoalBar.

AI-for-Science research workflow skill for DeepSeek Harness, aimed at researchers and grad students using agentic AI: multi-angle literature review with per-angle files, experiment design with a caveat list, figures and paper reading; each job returns files plus a cross-verification brief for a second model. Zero deps, MIT.

One-stop visual management of DSH Skills & MCP: on-demand MCP loading, in-session hot reload, SKILL & MCP descriptions viewable in the plugin.

A community plugin marketplace for DeepSeek Harness, built to the official plugin spec — browse, search and install 4000+ human-curated community plugins without leaving the app. · DeepSeek Harness 社区插件市场（遵循官方开发规范）：4000+ 人工精选社区插件，每日更新。

Turns the DeepSeek Harness agent into any character: a global cosplay switch, SillyTavern v2 role cards with JSON import/export, a neutral/role thinking-style toggle, and natural-language card authoring via a built-in skill.

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Codex-style turn folding for the DSH Web UI: keeps final answers visible, groups consecutive reasoning and tool activity, and shows configurable live duration, tool-call, and token metrics with multilingual summaries.

Full-featured TUI for DeepSeek Harness: streaming conversation, powerline status bar, real-time think/tool/todo panels, subagent dual-view, theme hot-switch — all as pure cordis plugins with zero upstream patches.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log.

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

Projection-driven live DAG for a Session's subagents and durable workflows: status and navigation, deterministic deep-chain layout, fit/pan canvas controls, and current-session node rearrangement.