Plugins

Role-based LLM retry & fallback strategies.

Role-based LLM retry & fallback strategies.

Role-based LLM retry/fallback strategy.

Route OpenRouter requests through a configured provider list and quantization cap, injected as provider.only/order with allow_fallbacks, plus provider.quantizations.

Four GitHub workflow skills for PR triage, review feedback, GitHub Actions diagnosis, and safe draft-PR publishing, reusing existing DSH capabilities with gh/git fallbacks.

Adds 20 locales (Traditional Chinese HK/TW, Japanese, Korean, French, German, Spanish, Portuguese, Italian, Russian, Ukrainian, Polish, Dutch, Turkish, Arabic, Hindi, Indonesian, Vietnamese, Thai, Swedish) to the DeepSeek Harness Web UI, with hand-polished translations, runtime fallbacks, and automatic translation of market and third-party text.

QQ 2007-inspired DSH Web skin: 72 native theme tokens, scoped three-pane chrome, original offline art and pixel buddy, an optional synthesized send chime, responsive/accessibility fallbacks, and reversible Settings switches.

Windows desktop observation and control: accessibility tree, screenshots, OCR fallback, mouse and keyboard, with session-scoped approvals and an ESC halt gate. Computer use and desktop automation for DSH, including GUI automation fallbacks.

🌍 Select text, translate in place. A card under your selection in DeepSeek Harness — your own model first, configurable fallbacks behind it.

An Auto toggle next to the model selector that schedules reasoning_effort per request: complexity is scored by a MiniMax/OpenAI-compatible model with a zero-dependency heuristic fallback (fallbacks not cached), effort ladders adapt to each model real effort list (low/high/max, low/high/highx/max/ultra, ...), heavy tool calls upgrade the tier within the same session, the lit button and reply badges show the effort actually used, and every decision plus observed token usage lands in a JSONL ledger. A standalone-button fork of imkingjh999/dsh-adaptive-effort; do not install it and the original in the same profile.

Declarative provider/model fallback chains for the model picker: an ordered root chain plus named pools, failure-code triggered switching, per-model cooldowns, time-slot presets, and subagent role routing. A fork of omdsh-dev/dsh-llm-fallbacks 0.6.5; do not install it alongside that plugin (both use the "llm-fallbacks" profile row id).

Inkstone is a monochrome theme inspired by Obsidian Minimal E-ink, with inverted sidebar interactions, colored Markdown headings and locally installed LXGW WenKai font fallbacks; it preserves native font and appearance preferences and targets DSH 0.2.1-rc.2.

Registers one `ocr` tool for text-only models: it runs the offline script bundled in the repo over a single image or PDF and returns the recognized text — Windows native OCR first, then RapidOCR, then Tesseract. Recognition runs locally with no network request and no API key. Needs Python 3.11 on PATH plus `pip install winocr pillow` (winocr is the preferred engine; RapidOCR and Tesseract are fallbacks). Per-line results for images, per-page results for PDFs.

Add six languages (繁體中文, 日本語, 한국어, Français, Deutsch, Español) to the DeepSeek Harness Web UI language options, with hand-polished per-language translations and automatic fallbacks (Simplified-to-Traditional conversion for zh-TW, English for the others) covering upstream updates and third-party plugins.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR 0.6B 4bit on MLX/Metal by default, SenseVoice and mlx-whisper fallbacks), zero external APIs, launchd self-healing service and an 8-point diagnose script. The bundled skill lets the agent install, configure (Karabiner hotkey wiring, launchd, engine switching) and troubleshoot the whole toolchain for you.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Browse the awesome-dsh-plugin catalog from a dedicated page opened through the DSH left sidebar. Search, filter by category or installed state, and sort by stars, downloads, name or date added. Three tabs show all, installed and updatable plugins, with a separate count when update status cannot be determined. Install into the active Web or Desktop profile using the package manager supplied by DSH, while preserving disabled bundles. Reload the profile through HMR when available, with restart guidance otherwise. Installed state is isolated per profile, installation and reload requests are mutually exclusive, and pagination keeps the submitted search. Expired catalog and installed-state snapshots are served immediately while refreshing in the background. Unversioned npm installs resolve the official registry latest tag to an exact version, and confirm the installed version before reporting success. Registry updates install the exact catalog version; Git updates force source resolution. The catalog is cached locally for one hour, with mirror, CDN and npm fallbacks.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.