Plugins

Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness

Drag or paste files into the Web composer with one image-and-file preview rail; native PNG/JPEG/WebP/GIF keep the image attachment path, while other files reuse a matching local path or stream to Host staging and become @ references only at send time. Includes browser media/PDF and bounded text previews; Office and archives show identity cards, and unsent file entries are page-local.

Thème clair Whale Girl pour l’UI Web DSH. Cette version corrige l’accès Settings, le fond papier des conversations et la barre latérale, et ajoute un contrôle papier propre aux conversations; remappage natif des tokens --dsw-*, couche papier claire, verre/fond réglables. Identité visuelle : 溟月 by 上善无形 → DeepSeek maid ver. by ZipZipPipe. Illustration CC BY-NC-SA 4.0, code MIT.

Onglet Design Studio : les briefs de design deviennent des maquettes html/css/js avec aperçu en direct, sélecteur d'éléments, chat d'agent de design avec revue par vision, préréglages d'identité et export zip.

Deep PTC mode is an open-source agent preset for DeepSeek Harness that keeps the built-in PTC tool surface and replaces the persona with a working contract: a DeepSeek identity and unlimited-token-budget instruction so the model does not skip reads, commands or checks to save tokens; planning by estimated size (internal up to 5 minutes, shown without approval up to 20, approval required beyond); and asking about unclear intent instead of guessing. Waiting is limited in code by wrapping the official shell, job and question tools: foreground commands move to background jobs after 30 s (configurable), a steered user message ends the current wait so the model reads it, foreground pauses over 5 s and long timers in run_code are refused, and questions run in timed mode. A settings card selects the preset executor — Automatic, WSL Bash, Windows PowerShell, native Zsh or native Bash.

Links the current DeepSeek account in DSH to a GitHub identity through the local GitHub CLI, a personal access token, or OAuth device flow, then exposes a scoped github tool for listing repositories and reading, creating, or commenting on issues.

Injects SOUL, IDENTITY, AGENTS, and TOOLS into Claw session prompts. Hard dep (install together or single install fails): dsh-claw-permissions.

Plays a character entrance card beside the composer when you switch model: identity name, six scored axes (intelligence, coding, speed, stability, cost, context), quota hint and a dialogue line. 23 curated cards across 15 providers; models without a curated card fall back to a data card derived from public benchmarks, or a generic card when no benchmark data exists. A web client plugin with no dependencies and no hooks.

Session utilities: Markdown export and dependency-free batch ZIP export, a timeline overlay for jumping between turns, safe session duplication that rewrites internal identity fields, and sidebar right-click menu extension points.

Customize the Harness sidebar name and avatar with a local crop editor.

Embedded identity and payment-governance trust plane for multi-agent cross-border payment workflows.

Douyin patent and trademark complaint workflow for DeepSeek Harness with a left-sidebar task panel: checks user-supplied links, materials and organization identity in a dedicated browser, records each submission state, queries platform history read-only, and shows local task counts in the sidebar; never discovers targets or submits without explicit authorization.

Full-screen ice-and-fire boot intro for DSH: a frost-to-ember boot sequence with typed bilingual logs and a hairline progress line, then Ygritte's five-step identity authorization. Esc skips, Enter or click fast-forwards, and a settings page switches it off/quick/full or replays it; the host half paints the opening frame while the document parses, so the built-in loading card never shows.

Deletes a whole DSH session or one completed turn from the session log: confirmation dialog, live-agent teardown, path and identity checks, pre-rewrite backup, and later turns renumbered.

Adds a Claude Pro/Max OAuth provider with multiple accounts, optional account failover, cached quota reporting, live model catalogs, and quota UI in settings and conversations. Uses the Claude Code client identity; quota reporting uses an experimental endpoint.

Agent persona management, agent memory, edit-and-regenerate for past messages: create and manage agents, each with its own identity, long-term memory, global memory and chat history.

Renders an Agent Teams swimlane canvas above the composer: lead centred with members below, tasks laid out in lanes by longest dependency path, and four SVG connector families drawn as dashed paths (task dependency as a cubic bezier from the upstream card edge to the downstream card edge, lead bus, peer bus, member-to-task tether). Cards are absolutely positioned DOM, connectors are one SVG layer sharing the same geometry constants. Layout constants and path algorithms are ported from cc-haha. Reads the live per-session agentTeam projection (roster, shared tasks, dependency edges, running state) and falls back to the session todo list when the session has no team; team messages are not part of the projection yet, so the communication panel shows an empty state. Body colours come from host theme tokens; the eight member identity colours are the deliberate exception — fixed hues mixed with the theme accent via color-mix, declared as CSS variables because the same values feed an SVG stroke attribute that rejects colour functions. Ships zh/en dictionaries with identical keys.

A social deduction game played against your own model configurations. A table has N seats (six by default, one of them yours) and some of the rest are played by agents bound to different provider, model, temperature, system prompt and disguise settings; you interrogate them and cross-check the answers to work out which seats are not human. Seat identity and each agent model configuration stay hidden in the host state until a seat is judged, then the disguise parameters are revealed. Every round exports a per-seat conversation JSONL plus the judgment record, and the same seed with the same move script replays byte-identical, so runs with different models or disguise strengths can be diffed.

Mount the QianYuan MCP server inside DeepSeek Harness: one config-layer bundle brings 15 agent-record tools (pitfalls, cached results, identity, task board) to mcp__qianyuan__*. No runtime code; reads are anonymous, writes are ed25519-signed.

Watches Feishu (Lark) conversations with your own user identity and forwards new messages as prompts into a chosen DeepSeek Harness session: per-monitor sender filters, @bot-mention bypass and keyword allow/block lists, auto-created pinned target sessions, and cursor-based polling that re-reads messages after a failed delivery.

Git integration for DSH modelled on IDEA's VCS: a git icon beside the permission mode in the composer shows the current branch and the pending-change count, opens a branch switcher on hover and an IDEA-style VCS panel on click (branch tree, commit graph, changes and staging, commit detail, file diff), plus a settings page for commit identity, the git binary and the network flags. Registers no model tools with DSH.

Make the model believe it is inside the Z.ai Code (Zhipu ZCode) agent environment: replaces the harness identity opener and injects a ZCode rules skeleton with a dynamic project section. 让模型认为自己处于智谱 ZCode Agent 环境。

Manage SSH identity keys and per-host ssh config from the web settings page, so git-over-ssh works in headless server mode.

Read-only process identity capability for Agent-authored Relay Monitor Bundles.