Plugins

Render and iterate on Blender scenes from DSH: 16 tools for scene specs, previews, visual review and delivery renders, with immutable revisions and an approval gate.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

An editable diagram canvas in the DSH sidebar plus two agent tools (diagram_read, diagram_apply) that read and edit the workspace in place, using native .drawio files: the canvas opens and saves them losslessly — cells it does not understand are preserved byte-for-byte — and a file-fingerprint revision powers optimistic locking against concurrent edits.

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

Desktop computer-use for DSH: captures the Windows screen into the agent vision channel and drives mouse/keyboard through a Codex-style overlay with Esc abort; auto-detects Windows native or WSL hosts.

Windows computer use forked from computer-user: 13 computer_* tools that read the screen and drive the mouse and keyboard. Image-capable routes get the screenshot as a real image with an exact image-to-screen mapping, so no external OCR; elements return as UI Automation refs so a click lands on the exact control rectangle; Ctrl+Alt+Esc stops every call.

Model picker for the DSH web composer that replaces the model seat: a search-first popup whose left column indexes the suppliers and scrolls the grouped list, with a favorites group pinned at the top, image icons separating native from bridged vision input, and a reasoning-effort panel opened from the right zone of the trigger.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Provisions the kimi-webbridge bridge daemon (auto-install with SHA-256 verification, auto-start) and registers a 25-action skill that drives the user's real browser through the local bridge.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.

Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.

Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in free vision model and automatic rate-limit failover.

Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.

Aperçus d'images intégrés dans la conversation pour les images collées relayées par dsh-tool-vision sur les modèles texte uniquement (clic pour zoomer, les anciens messages reçoivent aussi des aperçus).

Routage de modèles par niveaux pour DeepSeek Harness : niveaux think/build, délégation à la vision (le modèle de vision ne fait que décrire les images ; le modèle de travail agit), génération d'images et garde à fort impact.

Supervision par broker détaché de services de longue durée (serveurs de développement, watchers, API simulées) qui survivent aux tours, aux sessions et aux redémarrages de DSH, avec un onglet Service dans la barre latérale (enregistré via l'API d'extension de better-sidebar) et des outils de modèle service_start/stop/restart/list/logs.

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.

Plugin web pour DeepSeek Harness (DSH) : collez des fichiers dans le composeur, stockage en boîte de réception et vignettes. Le texte passe par read_inbox ; la compréhension d'images nécessite votre propre compétence de vision (image-reader fourni + ARK_API_KEY).

Plugin de routage à deux modèles pour DSH : la conversation principale reste sur DeepSeek, les tâches d'image sont automatiquement dirigées vers le modèle de vision explicitement configuré, puis le résultat de l'analyse revient à DeepSeek pour continuer.

Plugin DeepSeek Harness : une route `deepseek-vision` qui déclare l'entrée d'images et transcrit les images collées via les modèles de vision gratuits Zhipu GLM avant de déléguer à l'adaptateur DeepSeek.

Plugin out-of-tree DeepSeek Harness : donne des yeux à un modèle de codage textuel en routant les images vers une route Qwen-VL (DashScope) via ctx.llm et en retournant du texte.

Plugin settings-pro pour DeepSeek Harness : pont IM (Telegram/WeChat), usage DeepSeek, mémoire cross-restart, animaux de bureau, et pont vision