Plugins

Desktop feature aggregate that installs the DSH Web UI collection, dshmarket, Codex Connect, and reasoning-effort controls at pinned versions.

Base aggregate for DeepSeek Harness Desktop features: Web UI collection, plugin market, Codex Connect, and reasoning controls.

Adaptive reasoning slider skin that maps each model's available reasoning efforts onto a 0–30 visual intensity scale, with synchronized portraits, background, and interface colors.

DSH适用的Codex风格的思考强度滑块，以及大肥鱼跑步滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness

Inoffizielles DeepSeek-Harness-LLM-Provider-Plugin für Command Code: Live-Modellkatalog, Unterstützung für Reasoning-Effort, Karte auf der Modelle-Seite. Portiert von pi-commandcode-provider (MIT).

NewAPI (OpenAI-compatible gateway) LLM provider: registers a `newapi` route with chat-only model discovery, auto-fills model parameters (context window, reasoning effort) from models.dev, and adds a Web settings section for the base URL and API key.

Real-time 'We need…' and 'Let me…' reasoning-trajectory keyword stats for the DeepSeek Harness web chat.

compact reasoning and tool activity groups for DeepSeek Harness Web and DeepSeek Harness Desktop.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Regler für den Denkaufwand im Codex-Stil, eingebettet in die Modellauswahl.

Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.

Voice-announce the final reply on Windows (SAPI5 natural voices) and macOS (system voice); skips reasoning and tool calls, one-line npm install.

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.

Ergänzt Drittanbieter-APIs für DeepSeek Harness um Reasoning-Stufen wie Niedrig/Mittel/Hoch und ermöglicht die Modellauswahl für jeden Subagenten-Aufruf.

Fähigkeits-Deklaration je Modell für DeepSeek Harness: Reasoning-Effort-Stufen (Wire-Schreibweisen) plus Anfrage-Modalitäten (Vision) für OpenAI-kompatible Provider. Einstellungsbereich, keine Laufzeit-Harness-Abhängigkeiten, kein YAML.

Codex-style live reasoning and tool-call collapse for the DSH Web chat view.

Enhanced ACP server for DeepSeek Harness: block & reasoning streaming, usage telemetry, model/effort switching, permission presets, session resume/archive, per-session MCP servers, and Zed file/terminal forwarding.

Complete wuyun-liuqi (five-evolutions-six-qi / 五运六气) Traditional Chinese Medicine skill pack as a DeepSeek Harness Cordis plugin: annual and guest-qi calculation, clinical pattern differentiation, and pathogenesis reasoning.

Pause / resume / cancel the in-flight conversation task from the composer area: forced pause interrupts immediately and remembers the interrupted tool, safe pause lands after the tool or reasoning finishes, resume asks for confirmation, and the default pause granularity is configurable in the settings.

Adds models.dev reasoning levels to unconfigured third-party DeepSeek Harness models.

DeepSeek-Harness-(DSH)-Plugin: ein „Denksprache“-Selektor unter Einstellungen → Allgemein, der dem Modell über einen System-Prompt-Abschnitt mitteilt, in welcher Sprache es denken soll (Chain of Thought). Keine zusätzlichen Aufrufe, keine Latenz, 12 Sprachen.

DeepSeek Harness 插件：把「推理等级」(reasoning effort) 档位名翻译成中文，并为接入的自定义第三方模型注入推理等级显示（官方 DSH 默认不注入），所选档位写入出站请求体。

面向 DeepSeek Harness Standard 的 DeepSeek V4 首轮 RL 锚定插件，promotion 后恢复完整能力与 Skill。

Composable working, reasoning, quality, and human-reviewed self-evolution controls for DeepSeek Harness Web.