Plugins

Ermöglicht der KI, per Streaming generierte TSX-Oberflächen in den Chat oder ein Seitenpanel einzufügen. TSX ist bereits eine native Sprache des Modells, daher ist kein JSON-Schema erforderlich. Flackerfreie Darstellung, Zustandserhalt über Frames ohne erzwungenes Remount und ein Klick in der Karte startet den nächsten Turn. Inline-Ansicht für Streaming, Seiten-Canvas mit stärkerem Agentencharakter. Karten können selbst bash, curl und Modellaufrufe ausführen sowie Dateien lesen und schreiben.

Multithread-Downloader für DeepSeek Harness mit gebündeltem aria2: prüft die Range-Unterstützung des Ziels und nutzt aria2 (4 oder 8 Verbindungen je nach Dateigröße) oder curl.

Windows-PowerShell-5.1-Skill für große GitHub-Release-Assets. Host nur lesend prüfen: Proxy-Ports, System-Proxy/Umgebung, Clash-Verge-Core/-Konfiguration, curl-Version. Vier Wege parallel messen (Proxy, headless Core, Mirrors, direkt), danach kurz zeitbegrenzte Parallelität testen. Per parallelen curl-Byte-Ranges laden; Bytes und SHA256 gegen Digest prüfen. Test unter 100 MB oder ab 3 MB/s je Verbindung überspringen. Autorenmessungen: 6,3× gedrosselt (1.234→7.759 KB/s), 0,72× schnell (5.829→4.175 KB/s). Kein aria2/7z; ändert Proxy nicht, fragt nicht nach Ports/Parallelität. Fehlt es: echte Kandidaten plus `ASSET_NOT_FOUND`, kein Ersatz. Ohne Digest nur Größenprüfung: `DOWNLOAD_SIZE_OK_NO_DIGEST`.

HTTP-/API-Debugging-Toolset: voll kontrollierbare HTTP-Anfragen (Methode/Header/Body/Auth), Parsing von curl-Befehlen und deren Ein-Schritt-Ausführung, Anfragehistorie in der Session mit Side-by-Side-Antwortvergleich, paginierungsbewusste Link-Header und DeepSeek-gebrandete UI-Karten (optional dsh-http-tools-ui).

Keeps bulk output out of the conversation: ctk_execute, ctk_execute_file and ctk_batch_execute run code in a child process and return only the conclusion, ctk_index and ctk_search file long material into a local FTS5 knowledge base built on node:sqlite, and a routing gate refuses curl and wget before they execute. Ships ctk_stats and ctk_doctor plus a settings page with a live context-occupancy panel. No third-party runtime dependencies.

A download-progress indicator for the DSH session header: it reads the background-job roster and parses what downloaders already print — curl --progress-bar, wget, aria2, or a JSON progress file — into a progress ring, animated bars, transfer speed and ETA. Jobs that report nothing show as unknown progress instead of being hidden. A finished file opens with one click, or reveals in the file manager. No third-party plugin required; the package ships zero runtime dependencies.

Device-pairing gateway for DeepSeek Harness: by default it listens on 127.0.0.1:3443 over plain HTTP and reverse-proxies the local dsh at http://127.0.0.1:3080, so a loopback-only install works without any certificate. Production, cross-machine and app pairing require TLS: configure tlsCert/tlsKey plus an https publicUrl (self-signed is fine). A fronting Caddy/Nginx may terminate the public TLS, but the gate itself still needs tlsCert/tlsKey and the proxy must connect back over HTTPS. Features TOTP-authorised QR device pairing, username/password login, sliding sessions with absolute caps, device revocation, a WebUI admin panel and audit log, and a reverse proxy with WebSocket tunnelling. First-run setup is completed in the WebUI wizard. Tests: 171/171 unit tests, 29-step e2e.

Durable cross-session memory plus a fetch ladder that survives hostname-keyed blocking. Four tools: memory_recall, memory_save and memory_stats over a plain-JSON fact store at $DSH_HOME/memory/facts.json, plus resilient_fetch which tries plain fetch, then a same-service alias host (Wikipedia only for now), then curl over IPv6 and IPv4 (needs curl on PATH). No daemon, no npm dependency, no network at import time. (1.3.0 shipped a fifth tool, memory_prune; it was withdrawn in 1.4.0 because adding a tool to a running plugin breaks sessions that were opened before it.)

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Draggable floating card that follows background jobs: a progress bar and percentage parsed from wget/curl/apt/pip output, elapsed time, ETA when present, and the latest output line.

Tavily search and page fetch: tavily_search queries with a rotating pool of up to eight API keys that backs off per key on 401/403/429 so one exhausted account does not take the tool down, and web_fetch retrieves a single page through curl, returning its HTTP status with de-tagged text.

DeepSeek Harness plugin for accurLex Open Platform legal tools