Plugins

Header quota badge plus a usage-monitoring tab: live balance/quota remaining and reset countdown per provider, with requests, tokens (input/output/cache-read/cache-write), cache hit rate, estimated cost and average latency tracked per session, provider, model and client, stored locally in SQLite with cross-device import/export.

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.

Plugin marketplace in Settings that targets any local profile, not just the running one: install, update and remove across web, headless and other profiles, with install-script warnings, an installed view that also covers non-catalog profile dependencies, and an automatic DSH restart when the current profile changes.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Xueqiu (Snowball) market panel docked above the composer: A-share/HK/US quotes and indices, watchlist, candlestick K-line with volume, MAs and crosshair tooltip, hot list, search, 7x24 news, plus a draggable mini index badge — no login needed.

Cache-stable progressive tool discovery: a fixed tool_search and tool_dispatch surface on every request, in-memory catalog search, nested dispatch through the Harness pipeline, and a byte-stable native tool list across discovery.

Self-contained literature library for DSH with optional Zotero export: full-text PDF fetching (Unpaywall/arXiv/custom URL templates), loose Crossref-backed search, APA/GB-T 7714/MLA/Chicago citation generation, a side-panel PDF reader with highlights and notes, and AI-assisted Q&A/translation steered into the current conversation.

AI Company Framework: turn one sentence into a multi-agent company — 15 flat Skills (boss/pipeline/role-template/11 roles/generic customer-memory), 7 workflow templates, AgentTeams runtime + activity panel, employee sidebar with per-session isolation, Feishu bot bridge (boss and per-employee bots, group routing, autonomous push, human decision gate, external-contact guide), per-customer SQLite memory with three-layer memory (cross-group merge), /company mode switch; no RAG.

Bring the deepseek.com web/app chat experience to DSH: edit your prompt and regenerate answers in place, with a per-message <i/N> version pager (tree model, stable across conversations).

kimi-tide（月汐）— preset-and-rule model router for DeepSeek Harness（预设+规则驱动的逐步模型路由）：named presets with ordered image/keyword-group rules route each agent step across ANY mounted provider/model (candidate pool = full host catalog enumeration, no whitelist), w

Find DSH plugins across several community catalogs plus live GitHub and npm search, ranked by relevance, trust, freshness and bounded popularity instead of stars alone.

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

Query Chinese Minecraft Wiki (MediaWiki API) and convert raw wiki text into clean AI-readable output — search, page intro, full-page Markdown, and random entry; templates, references, images and cross-language links are stripped before reaching the model.

Modular frontier execution discipline for DSH: evidence-first routing across 26 skills, Manus-style file planning, verification gates, fail-streak recovery, and an interactive web dashboard.

Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.

Authentication gate for the DeepSeek Harness Web UI: the login gate covers pages, /api, /plugins and WebSocket upgrades; PBKDF2 password hashing, HttpOnly SameSite session cookies and IP-based login lockout; invite-code registration; two-factor login with TOTP or passkeys (WebAuthn: several keys per account, phone enrolment by QR, username-less sign-in, and a password or second-factor step-up before any login factor is added or removed); a user-management settings panel (users edit their own profile and manage their own TOTP and passkeys, admins add or remove users, reset passwords, manage invites and clear the passkeys of a lost device); admin-only model and API-key configuration guards; per-user isolation on the REST/list APIs and on the WebSocket event streams; session persistence across restarts; a JSONL audit log; and a fail-closed gateway. Runs on both DSH transport lines (0.1.1-rc.2 legacy and 0.1.2+ modern) with no configuration; passkey login needs a localhost or HTTPS origin because browsers require a secure context.

Move sessions across workspaces by drag-and-drop with true in-place migration; recover orphaned or unregistered sessions; re-point stale workspaces after folder renames. IDs and history stay intact, with per-step backup and rollback.

Move, archive, restore, portable backup/export and import sessions across workspaces in the DeepSeek Harness web UI.

Decentralized multi-device fleet: mDNS LAN discovery, key pairing, and SSH direct execution across networks.

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. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory.

Decentralized multi-device fleet: mDNS LAN discovery, key pairing, and SSH direct execution across networks.

Conversational Grafana operations: inspect live dashboard data across named sources, then make safe, reviewable dashboard changes with approval and version checks.

Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, needs-your-input, and error tones; silent for plain chat, system-level playback (works in background), cross-platform (Windows/macOS/Linux), custom TTS sounds.