DeepSeek Harness: Building and Extending AI Coding Agents Training Course

Introduction to DeepSeek Harness

• Overview of DeepSeek Harness and its role in the ecosystem
• The "everything is a plugin" design principle
• Web UI, command-line, and headless operational modes

Setup and Initial Execution

• Node.js prerequisites and package management
• Starting the Web interface using npx
• Compiling and running from source code

Model Setup

• Configuring the DeepSeek API key
• Choosing and switching between models
• Integrating OpenAI-compatible endpoints

Workspaces and Session Management

• Selecting and toggling between workspaces
• Managing the session composer and dialogue flow
• Reading, modifying, and creating files

Executing Coding Tasks

• Summarizing repositories and navigating codebases
• Running commands and delegating operations
• Maintaining an organized task plan

Permissions and Sandbox Environment

• Approval workflows and permission policies
• Restricting file and command access
• Utilizing 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

Sub-agents and Delegation

• Creating and forking sub-agents
• Integrating providers for other coding agents
• Distributing tasks across a session

The Cordis Plugin Model

• Plugins as services, events, and effects
• Shared context and lifecycle management
• The rationale behind a non-privileged core

Profiles, Bundles, and Configuration

• Layering profiles and bundles
• Adjusting configuration via cordis.patch.yml
• Reviewing the initialized system tree

Core Subsystems

• The append-only session logging system
• Assembly of system prompts and tool schemas
• The agent loop and turn-based flow

Events and Extension Points

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

Plugin Development

• Registering services via context keys
• Incorporating tools and model adapters
• Publishing and identifying plugins

SDK, Headless Mode, and Automation

• Controlling the harness from external processes
• Utilizing TypeScript and Python SDKs
• Automating tasks via CLI and headless operations