Plugins

Affichage du solde/de l’utilisation dans le dock du composeur pour DeepSeek, Kimi Coding, OpenCode Go, Zhipu, MiniMax, OpenRouter et OpenAI Codex — par fournisseur, interrogation toutes les 2 s, cache de 5 min.

Bundle Cordis de LoongPort DeepSeek Harness (dsh) et CLI de configuration

Plugin DeepSeek Harness : importe des modèles avec leurs capacités depuis une liste /v1/models compatible OpenAI (extensions de capacité du gateway) et modifie les capacités par modèle (réflexion, vision) sur sa page de paramètres.

Route de fournisseur de vision qui transcrit les images jointes en texte via un modèle configurable (plus de 15 fournisseurs compatibles OpenAI et Anthropic) tandis que DeepSeek continue de répondre.

Pont de vision pour les routes DeepSeek texte seul qui analyse les images jointes et locales via des endpoints configurables OpenAI Responses, Chat Completions ou Anthropic Messages, tout en laissant natives les routes capables d’image.

Boîte à outils de vision pour DeepSeek texte seul : outil `vision` appelable par le modèle, adaptateurs wrappers pour deepseek/opencode-go (v4 flash/pro), quota Antigravity IDE (default, flash/pro) / tout VLM compatible OpenAI / Gemini / canaux Ollama locaux, mémoire de preuves avec réhydratation par compactage, cache de hachage de contenu et panneau client bilingue.

Connectez une passerelle sub2api à DeepSeek Harness : routes multi-fournisseurs compatibles OpenAI (OpenAI / Claude / Grok / Gemini) derrière une seule URL de base, avec découverte des modèles par clé, consultation de l'usage et outils globaux de vision/image.

Utilisez vos abonnements ChatGPT/Codex dans DSH, avec prise en charge de la génération d'images et de la recherche web.

Fournisseur OAuth OpenAI Codex et UI de réglages native pour DeepSeek Harness.

Connecte les agents DeepSeek Harness à des sessions Codex App Server authentifiées.

Plugin ClawBot WeChat personnel pour DeepSeek Harness (DSH) : OpenClaw gère le canal WeChat (connexion par QR code, envoi/réception de messages), DSH gère le cerveau, les deux étant reliés par un protocole compatible OpenAI.

Relie la mémoire, les skills et la configuration d'OpenAI Codex à DeepSeek Harness.

Les images jointes au composeur sont transcrites en texte par un modèle de vision compatible OpenAI avant d'atteindre les modèles DeepSeek texte seul.

只填 Key 的服务商预设：50 家渠道为 DSH 一键写入官方 llm-pi-ai 路由与凭据（插件），并可写入腾讯 WorkBuddy、OpenCode（Key 走其 auth.json）与 cc-switch 的配置（CLI）；核心为纯 JS，可被更多应用的外壳复用。

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

Drive DSH from anything that speaks HTTP: 47 routes (REST + SSE) for workspaces, sessions (create/prompt, live SSE generation, history, stats, todos, cancel, ask-user Q&A), models and the global default model, providers, agent presets, settings namespaces, skills, and workspace files including resumable chunked upload — plus an OpenAI-compatible /chat/completions, a built-in OpenAPI 3.0 spec and an interactive request page. It only injects the host webServer and tools, so it rides on the DSH webserver (default prefix /api/v1) or its own port with optional API-key auth, and it ships a skill that teaches the DSH agent to call the API.

OpenAI-compatible vLLM client (default :8000).

OpenAI-compatible client for llama.cpp / Unsloth Desktop (default :8080).

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.

Registers the imagegen skill on the skill registry, so generating and editing raster images needs no hand-copied files under $DSH_HOME/skills. The agent drives a bundled image_gen.py CLI against any OpenAI-compatible GPT Image endpoint for text-to-image, reference-image editing, and transparent-background cutouts.

Per-reply read-aloud with a multi-provider settings page — MiniMax or any OpenAI-compatible /audio/speech endpoint, with voice, emotion, speed and model selection plus an auto-read toggle.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.