skymecode/deepseek-harness-for-vscode ↗★ 12
deepseek-harness-for-vscode
DeepSeek Harness VSCode 官方/社区扩展，支持在编辑器中直接配置模型、运行 Agent 并描述任务。
AI 分析
核心用途是在 VSCode 中直接调用 DSH 解决当前项目的开发任务。适合需要将 AI 编码助手深度融入日常 IDE 工作流的开发者。
安裝
此插件尚未提供可驗證的 bundle，或相容性檢查未通過。請先閱讀倉庫說明。 閱讀完整 README ↗
說明文件
閱讀完整 README ↗Configuration
| Setting | Default | Description |
|---|---|---|
deepseekHarness.model | deepseek-v4-flash | Default model for new sessions |
deepseekHarness.reasoningEffort | high | off / high / max |
deepseekHarness.agentPreset | standard | Default Agent Preset for new sessions |
deepseekHarness.provider | deepseek-official | Default source selected from the extension's Connection settings panel |
deepseekHarness.permissionMode | workspace-write | read-only / workspace-write / danger-full-access |
deepseekHarness.autoAttachSelection | true | Automatically attach the active editor selection when sending |
Provider endpoints and write-only credential references are managed through the bundled Harness settings and credentials services. API keys are stored in the extension's private Harness home, are never returned to the webview, and are not written to project-level .vscode/settings.json. Legacy deepseekHarness.apiKey, baseUrl, and providers values are imported once and then removed.
Use the Connection settings panel to add, edit, test, or remove DeepSeek relay sources. Custom sources are registered live through the upstream llm-pi-ai adapter and expose the same Flash/Pro choices in the model panel.
Automatically attached selections are limited to 16 KB and are truncated when necessary. If the same file selection is already embedded manually, the host will not attach it again.