Plugin

Budget di pensiero per richiesta, un backend di compattazione e una scheda impostazioni per la linea locale Qwen3.8 (llama.cpp o NInfer).

Casella degli strumenti per lo sviluppo di firmware embedded C/C++: agenti e skill che coprono FreeRTOS, interrupt, archiviazione NVM, Keil MDK, ARMCLANG, triage dei HardFault, macchine a stati, architettura e pattern LVGL.

Forza la compressione del contesto durante l'esecuzione di modelli llama.cpp a basso contesto come Qwen3.8-27B, migliorando l'efficienza del modello e la fluidità d'uso, insieme a prompt di compattazione ben raffinati.

Analisi dei video Bilibili: metadati, trascrizione (fallback ASR tramite Bijian/sherpa-onnx/whisper.cpp), commenti, danmaku e fotogrammi chiave nitidi con descrizioni visive locali opzionali.

Input vocale per la Web UI: dettatura segmentata dalle pause e messaggi vocali, ciascuno con la propria catena di fallback del provider (Deepgram, Groq, HuggingFace, whisper.cpp locale o endpoint compatibile con OpenAI).

Plugin di assistente vocale a mani libere e con priorità locale per DeepSeek Harness (DSH), con riconoscimento e sintesi vocale, comandi vocali e motori locali.

Plugin modello locale per DeepSeek Harness: gestisci modelli GGUF nelle impostazioni, avvio automatico di llama.cpp al primo messaggio e scaricamento automatico dopo 5 minuti di inattività per liberare VRAM.

Plugin di configurazione LSP C/C++ per DeepSeek Harness che usa clangd.

Interpone tre strumenti router (list_capabilities, describe_tool, call_tool) ai server MCP stdio, caricando gli schemi su richiesta invece che in ogni chiamata. Modella ogni risultato con una sequenza deterministica e archivia prima l'originale (retrieve_spill lo recupera); assegna costi in token ai gruppi e può nascondere gruppi integrati per agente. Si collega a un router Python della libreria standard; richiede Python 3.9 o successivo.

DeepSeek Harness (DSH) plugin for llama.cpp docker panel "llamapad" / llamapad 面板的 DeepSeek Harness 插件

Personal dsh preferences: a tunable companion to the official compaction engine (threshold, retention, summarization model/reasoning, turn-end compaction), llama.cpp model import for the Models page, and tab/notification helpers (status-light favicon, bro

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

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Host-side long-task detection for small-context local models: long outputs are scaffolded into a parts skeleton (one part per reply, then assemble), and multi-step work into a PLAN.md ledger with notes/ (plan first, one step per reply). Detection is heuristic and host-side, so it does not depend on the model judging its own limits.

C++ audit skill: detects the target project's actual C++ standard before making any recommendation, then reports findings across RAII and ownership, move semantics, exception safety, performance and memory, containers and algorithms, concurrency, templates and compile-time, standard boundary, and type safety, ABI and interface design, each with a checkpoint, a reason, a bad-to-good example and the minimum standard.

C++ runtime info probe for Windows via CDB: cpp_trace prints variables at multiple breakpoints in one session (replaces hand-written print), cpp_probe dumps the call stack at a conditional breakpoint. Install: dsh plugin --profile web add dsh-cpp-probe.

Re-encodes WebP attachment images to PNG so alpha-channel images load on LLM backends that cannot decode WebP (e.g. llama.cpp).

DeepSeek Harness (dsh) plugin: live local LLM endpoint health in the web rightbar. llama.cpp slots (busy/TTFT/wedged, /metrics) + Ollama MODELS (loaded vs empty). Engine fingerprinted by response shape. Installable dsh.bundle.

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to a local llama.cpp / llama-server gateway.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

Dictate prompts into the DeepSeek Harness Web Client — a microphone in the composer, with swappable transcription: hosted Whisper API, self-hosted server, or a fully offline whisper.cpp binary.