Plugin

Aspetto dei nodi di conversazione per la GUI web di DeepSeek Harness: colori configurabili per categoria e strumento (barra d'accento sinistra + sfondo colorato), oltre a un interruttore per mostrare il ragionamento; rendering puramente frontend, effetto immediato e persistenza nel file delle impostazioni utente DSH.

Leggi il contenuto di un'altra sessione (messaggi, chiamate/risultati degli strumenti, ragionamento) dall'interno di una sessione DSH

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.

Workbench terminale a schermo intero per DeepSeek Harness con un assistente persistente, sessioni di progetto raggruppate per workspace, scorrimento solo della trascrizione e viste strutturate di thinking, strumenti, diff, piani e subagenti.

Plugin per DeepSeek Harness (DSH): un selettore "Lingua di pensiero" in Impostazioni → Generale che indica al modello in quale lingua ragionare (chain of thought) tramite una sezione del system prompt. Zero chiamate extra, zero latenza, 12 lingue

Chat with the DeepSeek web app (chat.deepseek.com) in a native DSH panel — a real browser drives the site on your existing web login, with streaming replies, deep-thinking and smart-search toggles, and image or document attachments. Conversations can be recovered from the web side, exported as Markdown, and distilled or replayed into a harness session, and the agent reaches the same web chat through five tools (dschat_status, dschat_send, dschat_recover, dschat_import, dschat_transfer).

Time-based model routing: a settings panel defines weekday peak and off-peak windows and the provider/model each one uses, the choices are read from the harness registry (API keys and subscription logins alike), and a global switch decides whether that policy sets the model and reasoning effort of every request. The switch is independent per session, each session row carries a light showing its own state, and the settings panel names the model in force right now and why. A day no window matches — every weekend and holiday — uses the primary model of the first plan; the advanced thinking model is a separate axis, used only when a session itself asks for max reasoning.

Realtime token counter beside the deep-thinking indicator in chat, with merged or split input/output display, per-step operation counts, and auto-scaling K/M/G/T units.

Use DeepSeek's web chat inside DSH: real chat history in the leftmost sidebar, a Chat/Work switch beside the agent mode, plus streaming answers, thinking, web search and file uploads.

Replaces the composer model selector with a "model · reasoning level" trigger: a slider across every level a model reports, three switchable modes (the DSH native selector, a gradient particle rail, an energy-charge track), and a per-provider one-click fill for models that declare no reasoning levels.

Allows deepseek harness to think dynamically like human,automatically judge the difficulty of tasks with suitable thinking chain.

Pixel-font "deep seeking" thinking status with an animated DeepSeek blue whale (20 spout frames and 32 tail-wag frames).

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

A lightweight plugin that adds model thinking token statistics to the bottom Dock.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.

Interactive Side-Assistant Dock to ask quick side questions via /btw with real-time thinking status and history pagination without interrupting the active agent loop.

Raises Node's HTTP headers/body timeouts for the whole DSH process (default 30 min, proxy-aware) so Ollama and LM Studio models that stay silent while thinking or generating a large tool call are not cut off at 5 minutes; replaces the node_modules undici patch.

Ask a sidebar assistant about selected assistant text: an ephemeral right-side panel answers from a snapshot of the main conversation's LLM history with streaming Markdown, collapsible thinking and multi-turn follow-ups, without touching the main conversation.

Canale Feishu/Lark che pilota gli agenti DeepSeek Harness dalle chat: schede rich con streaming, pensiero e passaggi degli strumenti in tempo reale, misurazione del costo per turno alle tariffe DeepSeek di punta/fuori punta, schede di approvazione con un tocco, acquisizione di immagini vincolata al modello e onboarding tramite QR senza un endpoint pubblico.

Registra /wrapped, che legge le statistiche della sessione stessa e genera una scheda riassuntiva SVG scura condivisibile — tempo strumenti vs. pensiero, velocità di decodifica e un verdetto sul rapporto strumenti/pensiero.

Durante i lunghi periodi di riflessione dell'agente, pubblica un messaggio di notizia calda o di promemoria direttamente nel flusso della conversazione.