Plugins

Dynamisches Schulte-Gitter-Wartezeit-Minigame: klicke 1..N der Reihe nach auf ein statisches Gitter oder ein rotierendes Roulette-Rad, während das Modell denkt.

Frontend Pi TUI (Terminal-Framework mit differenziellem Rendering): Streaming-Markdown, einklappbares Denken, Tool-Karten, Slash-Befehle, Genehmigungs-/Rückfrage-Overlays, gemeinsamer dsh-Sitzungsspeicher.

DeepSeek-Harness-Plugin: Umschalter für den Denkmodus (enable_thinking) pro Anfrage für Modelle der Qwen3-Familie auf OpenAI-kompatiblen Endpunkten

Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

The row that is running expands itself and folds back when it settles. A running turn keeps its whole procedure in one height-capped window that scrolls itself; a finished turn merges into the built-in finished header, leaving only the final answer. It works by driving the official disclosure rows rather than drawing its own panel, leaves rows you opened by hand alone, and restores the official settings on uninstall.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

Imports chats captured from chat.deepseek.com by the repo's companion Edge extension (loaded unpacked in Edge) into DeepSeek Harness as new sessions; thinking is saved as a sidecar thinking.md, and trimmed, branched or very long chats also get the full transcript.md.

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

Replaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failures (one extra small judge call per turn), picks the effort from that score, and labels every finished turn with the effort it sent.

Turns scattered thinking notes into a growing constellation of themes, claims, relations and open questions, plus a written synthesis of the argument.

Injects a Chinese-thinking reminder around the system prompt and the per-step runtime snapshot, so the agent reasons in Simplified Chinese instead of drifting back to English as the transcript grows.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

SAP-AI-Core-Anbieter mit gemeinsamem OAuth, fünf Qwen-Modelloptionen, Denkbudgets, Streaming und Tool-Aufrufen; auf cn40 validiert.

[LLM] Ermöglicht DSH, Eingabemodalitäten und Denkstufe aus dem magpie-Upstream zu synchronisieren.

DeepSeek-Harness-Plugin: Weist alle Agenten an, ihre private Reasoning-Ausgabe auf vereinfachtem Chinesisch zu verfassen.

Claude-Desktop-inspirierter Composer-Schieberegler für Modell-Reasoning-Stärke mit Klick, Ziehen oder Tastatur.

Windows-x64-Bundle mit enthaltenem offiziellem Antigravity-ACP-Runtime. Delegiert einzelne Textaufgaben mit wählbarer Authentifizierung, Modell und Denkstufe. Nutzt host peers für Harness >=0.2.1-rc.3 <0.2.2-0, einschließlich späterer 0.2.1-RCs und der stabilen 0.2.1.

Der Composer-Verlauf stellt den gesamten Eingabestatus wieder her: Inhalt, Bild-/Dateianhänge, @-Referenzen, Slash-Befehle sowie verwendetes Modell, Reasoning-Stärke, Berechtigung und Agent-Preset.

Drei-Punkte-Menü im Sitzungsheader: Sitzungslog herunterladen, Transkript je Chat zwischen Normal und Verbose umschalten und festlegen, was Verbose erweitert (Denkblöcke, Tool-Aufrufe, Terminalausgabe).

Cohere-Modellprovider für DSH: standardmäßig OpenAI-kompatible Wire-API, Cohere-nativer-v2-Pfad für Zitate/RAG/Denkbudget. Direkter Wire-Adapter ohne Proxy.

Ruhige monochrome DSH-Oberfläche mit Lavendelakzenten, Start- und Wechselanimationen, Denk-Workspace, bereichsbezogenen Skills und optionalen lokalen Sprach- und Haustierverbindungen.