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 core design principle of "everything is a plugin"
• Exploring Web UI, CLI, and headless operational modes

Installation and Initial Setup

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

Model Configuration

• Configuring the DeepSeek API key
• Managing model selection and switching
• Integrating OpenAI-compatible endpoints

Workspaces and Sessions

• Managing workspace selection and switching
• Utilizing the session composer and managing conversation flow
• Interacting with files: reading, editing, and generation

Executing Coding Tasks

• Summarizing repositories and navigating code structures
• Running commands and delegating specific tasks
• Maintaining and updating task plans

Permissions and Sandbox Environment

• Defining approval and permission policies
• Restricting file and command access
• Implementing local and remote sandbox backends

Native Tools and Integrations

• Utilizing filesystem, terminal, and shell tools
• Support for Model Context Protocol
• Integration with Language Server Protocol

Subagents and Task Delegation

• Creating and forking subagents
• Using product providers for external coding agents
• Distributing work across a session

The Cordis Plugin Model

• Understanding plugins as services, events, and effects
• Managing shared context and lifecycle
• The absence of a privileged core

Profiles, Bundles, and Configuration

• Applying profile and bundle layering
• Modifying configuration via cordis.patch.yml
• Reviewing the boot process tree

Core Subsystems

• The append-only session log mechanism
• Assembly of system prompts and tool schemas
• Understanding the agent loop and turn progression

Events and Extension Points

• Handling session, agent, and capability events
• Implementing waterfall and interceptor events
• Aligning behavior with specific extension points

Plugin Development

• Registering services on context keys
• Incorporating tools and model adapters
• Publishing and discovering new plugins

SDK, Headless Mode, and Automation

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