Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription with no API key at all. The picture is shown inline in the conversation; the model rece

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

DSH plugin development as an on-demand agent skill: official docs mirror, version-compatibility matrix, migration seams, measured pitfalls, plus a scaffolder, checker and pack verifier CLI.

Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log

Mobile client for the DeepSeek Harness — use the dsh on your dev machine from your Android or iOS phone, remotely across networks, peer-to-peer over iroh with no server to set up (falls back to a relay that only sees ciphertext)

Free web search & fetch plugin for DeepSeek Harness (dsh) with multi-engine fallback (Tavily, Exa, Brave, Baidu, SearXNG and more)

Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Text-to-speech for DeepSeek Harness: speak agent replies in the Web UI with a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak).

Desktop notifications for DSH Desktop that actually speak: Windows TTS out of the box (zero download), VOICEVOX voice packs optional, a selectable system-sound fallback, and an idle gate that waits for running subagents before saying the turn is done. Inc

Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL

Point-and-shoot screenshot capture for DeepSeek Harness: clipboard watcher + system floating window (comment & key-point, copy/save-doc/save-image) + zero-config OCR through the host's own multimodal model (Tongyi Qianwen fallback) + Obsidian per-day merg

DSH web 插件：通过 DSH v0.1.5-rc.1 原生第三方语言 API（locale.addLanguage + register(ns, locale, dict)）注册 19 种内置语言字典（ja/ko/fr/...），语言直接出现在 DSH 设置页原生 Language 行中切换，未覆盖文案按 fallback 链回退英文。 | DSH web plugin: registers 19 bundled third-language dictionaries (ja/ko/fr/...)