Plugin

Lettura di saldo/utilizzo ancorata al composer per DeepSeek, Kimi Coding, OpenCode Go, Zhipu, MiniMax, OpenRouter e OpenAI Codex — basata su provider, polling di 2 s, cache di 5 min.

Bundle Cordis di LoongPort DeepSeek Harness (dsh) e CLI di configurazione

Plugin DeepSeek Harness: importa modelli con capacità da un elenco /v1/models compatibile con OpenAI (estensioni di capacità del gateway) e modifica le capacità per modello (pensiero, visione) nella pagina delle impostazioni.

Rotta del provider di visione che trascrive le immagini allegate in testo tramite un modello configurabile (oltre 15 fornitori compatibili con OpenAI e Anthropic) mentre DeepSeek continua a rispondere.

Bridge vision per route DeepSeek solo testo che analizza immagini allegate e locali tramite endpoint configurabili OpenAI Responses, Chat Completions o Anthropic Messages, lasciando native le route abilitate alle immagini.

Toolkit vision per DeepSeek solo testo: strumento `vision` invocabile dal modello, adapter wrapper per deepseek/opencode-go (v4 flash/pro), quota Antigravity IDE (default, flash/pro) / qualsiasi VLM compatibile OpenAI / Gemini / canali locali Ollama, memoria delle evidenze con reidratazione da compattazione, cache dell’hash dei contenuti e un pannello client bilingue.

Collega un gateway sub2api a DeepSeek Harness: route multi-provider compatibili OpenAI (OpenAI / Claude / Grok / Gemini) dietro un unico URL di base, con individuazione dei modelli per chiave, consultazione dell'utilizzo e tool globali di visione/immagini.

Usa i tuoi abbonamenti ChatGPT/Codex in DSH, con supporto per la generazione di immagini e la ricerca web.

Provider OAuth di OpenAI Codex e UI di impostazioni nativa per DeepSeek Harness

Collega gli agenti DeepSeek Harness a sessioni autenticate del Codex App Server

Plugin ClawBot per WeChat personale per DeepSeek Harness (DSH): OpenClaw gestisce il canale WeChat (login tramite QR code/invio e ricezione messaggi), DSH funge da cervello, e i due sono collegati tramite un protocollo compatibile con OpenAI

Collega memoria, skill e configurazione di OpenAI Codex a DeepSeek Harness

Le immagini allegate nel composer vengono trascritte in testo da un modello di visione compatibile con OpenAI prima di raggiungere i modelli DeepSeek solo testo

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.