DeepSeek Harness: Building and Extending AI Coding Agents Training Course

Introduction to DeepSeek Harness

• Overview of DeepSeek Harness and its position in the ecosystem
• The "everything is a plugin" design principle
• Web UI, CLI, and headless operating modes

Setup and Initial Execution

• Node.js prerequisites and package installation
• Starting the Web UI using npx
• Building and executing from source code

Model Setup

• Configuring the DeepSeek API key
• Choosing and changing models
• Incorporating OpenAI-compatible endpoints

Workspaces and Sessions

• Selecting and changing workspaces
• The session composer and dialogue flow
• Reading, modifying, and generating files

Executing Coding Tasks

• Summarizing repositories and exploring code
• Running commands and assigning tasks
• Maintaining a structured task plan

Permissions and Sandboxing

• Approval and permission policies
• Restricting file and command access
• Local and remote sandbox backends

Native Tools and Integrations

• Filesystem, terminal, and shell utilities
• Support for the Model Context Protocol
• Integration with the Language Server Protocol

Subagents and Delegation

• Creating and forking subagents
• Product providers for alternative coding agents
• Distributing work across a session

The Cordis Plugin Model

• Plugins as services, events, and effects
• Shared context and lifecycle management
• The absence of a privileged core

Profiles, Bundles, and Configuration

• Profiles and bundle layering
• Adjusting configuration via cordis.patch.yml
• Examining the booted tree

Core Subsystems

• The append-only session log
• Assembly of system prompts and tool schemas
• The agent loop and turn sequence

Events and Extension Points

• Session, agent, and capability events
• Waterfall and interceptor events
• Aligning behavior with extension points

Plugin Development

• Registering services on context keys
• Integrating tools and model adapters
• Distributing and discovering plugins

SDK, Headless Mode, and Automation

• Controlling the harness from external processes
• Using the TypeScript and Python SDKs
• CLI and headless automation