Plugin

Prompt di regole in stile rules.md di Claude Code: attiva file Markdown di regole tramite glob matching dei file che un agente legge o modifica, con supporto per iniezione e ordinamento dei prompt.

Avviso giallo su una riga per un cache miss del prompt dopo la ricostruzione della cache; mostra i token di input non memorizzati nuovamente fatturati, i token trovati nella cache e il TTFT.

Sticker di attività rapide tipo calamita da frigo ancorati sopra il composer: un clic invia un prompt precompilato nella sessione corrente, raggruppati in lungo/breve termine.

Un interrupt button verde accanto alla casella di invio: interrompe silenziosamente un agente in esecuzione, che poi riassume il proprio progresso e chiede nuovi requisiti, con un interrupt prompt personalizzabile.

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

Memoria delle preferenze utente per DeepSeek Harness: profilo utente persistente con strumenti memory_get/memory_update e iniezione nel system prompt

Un plugin meta-agente nativo del modello per DeepSeek Harness: il modello sintetizza a runtime flussi di lavoro specifici per il task a partire da cinque pattern di workflow agentici (concatenazione di prompt, worker paralleli, router, supervisore, ciclo di valutazione) e coordina strumenti e subagent

Deposito LIFO locale dei prompt per sessione, per mettere temporaneamente da parte il testo incompiuto del composer e ripristinarlo in sicurezza in seguito.

Modifica le sezioni del system prompt utente e integrate con anteprima live

Side-by-side model comparison for the DeepSeek Harness Web UI: send one prompt to 2–4 models in sibling sessions forked from the current one, watch the answers stream in columns (tabs on phones) with latency, time to first token, tokens, and cost, then co

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.

Session-aware local notes for DeepSeek Harness: capture notes and page selections in a floating Apple Notes style panel, let the LLM classify topics, auto-inject convention notes into the system prompt, and dispatch todos with recall context to active sessions.

Task-to-skill pairing meta-skill with a laziness ladder for minimal loading, a user-editable routing table, and a quarantine, SkillSpector scan, human-approval install flow.

Adds prompt optimization, cancellation, and undo controls to the DeepSeek Harness composer.

Multi-agent task decomposition, DAG workflow orchestration, and prompt caching optimizer for DeepSeek Harness.

Adds a sparkle button left of the model selector in the composer: it rewrites the draft into a clearer, more complete task brief, replaces it in place with one-click undo, offers five rewrite styles, and greys out while the draft carries file/command chips.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

Custom modes and custom prompts for DeepSeek Harness (dsh): edit a mode's system prompt on the settings page (it takes effect on the next model step), choose its base mode, switch plugins row by row, and keep several assistants side by side.

Forwards an unattended DeepSeek Harness run's tool-call approvals and ask_user_question prompts to Feishu cards on your phone. The desktop GUI answers first — a card is only sent after `delaySeconds` (120 by default) with no answer there — and a phone approval grants `allowed-once`, so no authority accumulates on the phone. One outbound WebSocket long connection to Feishu: no public IP, domain, tunnel or relay.

Session-affinity routing for LLM gateways: injects the session ID into every request sent to NewApi-style gateways so the gateway can pin requests per session and raise prompt-cache hits; takes over the official pi-ai routing on install and restores it on uninstall.

Adds a composer button that optimizes the current prompt or designs the next one from the current session and project context.

Conversation enhancements: a history-input overlay (Alt+Up with workspace/session/global/prompt scopes), recall of unapplied interjected messages, conversation forking with fork-family version switching, and optional auto-resend after forking (off by default).

Tool-health sentinel for DSH: cross-session tool success/latency/error history, chronic-failure warning injected into the system prompt, report tool + /tool-health command + GET /dsh-tool-health/summary.

DeepSeek Harness 输入栏「提示词精炼」插件：✨ 一键把模糊草稿改写为目标/背景/步骤/要求/[假设] 结构化提示词；成本可路由（默认模型可换成便宜的优化模型）、结果缓存、token 用量统计落盘。静态版为功能主体，动态版免安装尝鲜。