Dsh Claude

Key features

• Native Claude Code conversations — Runs Claude Code as the main agent in a normal DSH conversation instead of wrapping it as a tool or secondary chat.
• Repository and worktree preparation — Lets a user choose a branch before submitting, switch an eligible local branch, or create a dedicated Git worktree and DSH workspace while transferring the current draft and attachments, and removes a worktree's directory automatically once its workspace is deleted and the tree is clean.
• Claude Code settings and Doctor — Adds a Settings panel for runtime diagnostics, supported Claude settings, output style, AI output renderer, session alerts, worktree branch prefix, process limits, and authentication and handshake status.
• Thinking effort — Maps DSH's per-model reasoning effort onto Claude Code's thinking modes — off, low, medium, high (Claude Code's own default), xhigh, max, and ultracode — so the conversation's effort control drives extended thinking directly.
• Models that do not support a mode downgrade silently inside Claude Code