Plugins

OpenDesign Go provider: 12 subscription models over Chat Completions, the real 5-hour and 7-day quota read from the local OpenDesign app, per-model parameters and switches, and multi-account failover.

Brings the WorkBuddy, Trae and Qoder desktop logins on this machine into DeepSeek Harness as OpenAI-compatible local endpoints, with an account pool, automatic account switching when WorkBuddy is rate limited, and a settings panel.

Trellis-style workflow for DeepSeek Harness: per-turn phase breadcrumbs via agent/pre-step, bundled skill provider, and DSH-native task/phase state with git-cleanliness guardrails.

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 TPS tracked per session, provider, model and client, stored locally in SQLite with cross-device import/export.

SearXNG search and Crawl4AI fetch providers for DeepSeek Harness

Local-first four-bucket Token observability: persistent session/provider/model/day dashboards, trends, budget and anomaly signals, public-rate estimates, safe aggregate exports, and explicit opt-in usage or session-trajectory analysis.

Manage llm-pi-ai providers, API keys and models from one Settings page: add or edit providers, test a model, discover models from an endpoint, and start from 218 provider templates.

Plays Inception Mercury's diffusion (denoising) stream live in the dsh Web UI answer bubble: for routes that support it, the request is re-sent with `diffusing: true` and the real frames are replayed from noise to final text, while only the converged answer reaches the session log. Support is detected per provider/model with a probe that is rejected before any token is generated, a floating per-model toggle turns it on, and attachments, auxiliary calls or unsupported routes fall back to the original adapter. Replaces the assistant-message renderer for all models while enabled.

Unofficial upstream bundle for DeepSeek Harness. CodeBuddy gateway with a runtime-synced model catalogue, per-model reasoning efforts, web search/fetch, image generation and a streaming credential bridge, plus TraeWork CN and Qoder CN subscription channels via local translation gateways and a key-type OpenAI-compatible provider registry, all managed from an accordion settings card.

Media and vision workspace for DeepSeek Harness: image, video and speech generation, image Q&A and element locating, long-image OCR, pixel diff, HTML-screenshot verification and video summarization, with DashScope and OpenAI-compatible providers, model pools and a workbench client.

Self-hosted DSH Web operations panel for safe restart and upgrade, health diagnostics, model-usage statistics and provider quota lookup, backup and session management, task notifications, skill controls, subagent model routing, and Linux permission maintenance.

SearXNG-backed web_search provider for the web seam: free, self-hosted, key-less metasearch through your own instance's JSON API, with a bundled loopback-only docker-compose example.

Connects DeepSeek Harness to OOMOL-managed apps and services, with progressive Connector Action discovery and execution plus an in-app panel for managing Provider connections.

Answers the built-in web_search from a self-hosted RustXNG metasearch instance, downloading and starting that binary on demand and stopping it after an idle timeout; an optional fetch provider also decodes pages whose charset is declared only in <meta>.

Injects an x-session-id HTTP header carrying the harness session id onto every LLM provider request, plus whitelisted gateway fetches during tool execution.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Reusable Agent Team presets for DeepSeek Harness: a Settings page stores named Teams — a captain with its own prompt and tool allow-list, plus members carrying their own provider/model route, reasoning effort, prompt and tools — and a composer control applies one Team to the current Session, installing the captain prompt and registering the spawn_team_member, get_team_preset and update_team_preset tools.

Context window auto-management for DeepSeek Harness: when the window fills up it rolls over to a fresh one with zero summarization model calls, archiving the old window verbatim for line-by-line recall; handoff anchors carry task orientation, working notes survive compaction, and a stale-notes gate warns instead of vouching for outdated notes. The trigger follows the provider budget equation (window - max_tokens) and the real routed model even after a mid-session switch. One-click composer button plus /smart-compact, three-band automatic rollover, mandatory anchor sanitization; works out of the box.

Unofficial upstream bundle for DeepSeek Harness. CodeBuddy gateway with a runtime-synced model catalogue, per-model reasoning efforts, web search/fetch, image generation and a streaming credential bridge, plus TraeWork CN and Qoder CN subscription channels via local translation gateways and a key-type OpenAI-compatible provider registry, all managed from an accordion settings card.

Compliantly use your own Antigravity quota in dsh: bridges your local logged-in official Antigravity CLI (agy) session as the chat and subagent model provider.

Enterprise AI resource platform as a 22-plugin cordis bundle: org/account/role IAM, OIDC provider and App SSO, MCP server management with the platform itself exposed as an MCP server, NAS asset storage, skill hub, agent and app registries, SaaS connector management, enterprise portal data channel, department agent workbench panel, DingTalk group bridging for message and approval push, one-click remote dsh enrollment with tool proxying, usage metering, wallet billing, model gateway, audit with alerts, self-update, and a reviewed third-party plugin marketplace — 70+ ops tools become callable by the dsh agent.

Playwright/CDP web-fetch provider for the built-in web_fetch tool: renders pages in a real browser, denoises them (Readability + DOMPurify) and returns markdown.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.