Plugins

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

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota runway forecast, safe resets, web search, image generation, and Fast mode.

Web search provider for the ctx.web seam that routes the DeepSeek web_search tool through a LiteLLM proxy using the OpenAI Responses API, reusing LITELLM_API_KEY.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Neutralize tool calls with invalid JSON arguments on the wire so one malformed model generation cannot brick a session against strict OpenAI-compatible servers.

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).

Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.

Text-to-video and image-to-video generation via DashScope Wanx, Volcengine Seedance, Google Veo and OpenAI Sora, with tool results saved to the session workspace and a video gallery (grid, lightbox, download, delete) that survives DSH restarts.

Routes the harness through the OpenLLM gateway: a pure-config Cordis patch that adds an `openllm` provider to the in-box pi-ai adapter pointed at the local daemon (`127.0.0.1:8787/v1`, no API key held by dsh) and registers the `openllm mcp` stdio server (openllm, claude-context, supermemory tool groups).

Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)

Manages the default DSH model, provider and model visibility, and optional OpenAI Responses web search.

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.

Text-to-image and image-to-image generation inside DSH through OpenAI-compatible endpoints, with an agent tool, multi-provider fallback, and a side-panel workspace with history.

DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.

DSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models

Audio Copilot for DeepSeek Harness: transcribe audio (ASR) and synthesize speech (TTS) — gives text-only agents ears and a voice. Windows-local SAPI TTS out of the box; OpenAI-compatible ASR/TTS endpoints configurable. Includes an in-composer voice-input

DeepSeek-Harness-Kompatibilitätsplugin für OpenAI-artige Gateways von Drittanbietern: verträgt SSE-Streams, die nach einer vollständigen Antwort geschlossen werden, ohne das [DONE]-Signal zu senden.

OpenAI Codex CLI-Wrapper: Einmal-Ausführung (one-shot exec), Repo-Überprüfung und Sitzungswiederaufnahme mit einer standardmäßig schreibgeschützten Sandbox.

DSH Web Usage Center mit lokaler SQLite-Historie, HUD und Dashboard, Hub-Konto-/Kontingent-Snapshots, benutzerdefinierter Preisgestaltung und Gebührenbuch sowie CSV/JSON-Export, zusätzlich OAuth für Coding-Pläne und ein optionaler Loopback-OpenAI/Anthropic-Gateway.

Multimodales Plugin für DeepSeek Harness: Bilder verstehen und Bilder generieren über konfigurierbare OpenAI-kompatible oder DashScope-Endpunkte.

DIT.ai-Provider-Bundle für DeepSeek Harness: installiert 29 OpenAI-Chat-Completions-Modelle und 10 Anthropic-Messages-Modelle aus einem DIT_API_KEY, mit protokollspezifischer Thinking-Konfiguration.

Chat-Bildanhang-Brücke mit einem view_image-Werkzeug für jedes OpenAI-kompatible VLM (lokales Ollama oder Cloud): eingefügte/abgelegte Bilder werden zu view_image-Pfadmarkern, bevor sie Text-only-DeepSeek-Modelle erreichen.

Modellseitiges image_describe-Werkzeug (识图) über die OpenAI-kompatible DashScope-API (qwen3.7-flash), plus eine Einfüge-Brücke: In Text-only-Sitzungen werden eingefügte Bilder beim Senden automatisch in Dateipfade umgewandelt und im Transkript zurückgerendert, sodass sie nie an der Bildannahme scheitern. Eigenen DASHSCOPE_API_KEY mitbringen; Endpunkt/Modell/Budgets konfigurierbar, redirect-fester HTTP-Client, funktioniert in jedem agent preset.

Bedarfsgesteuertes Sehen für reine Textmodelle von DeepSeek: Bilder hochladen, und das Modell ruft ein view_image-Tool auf, das auf jedem OpenAI-kompatiblen Vision-Endpunkt basiert (standardmäßig Qwen/DashScope).