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

Installation and Initial Setup

• Node.js requirements and installing necessary packages
• Starting the Web UI using npx
• Compiling and running from source code

Configuring Models

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

Workspaces and Sessions

• Selecting and toggling between workspaces
• The session composer and managing conversation flow
• Accessing, modifying, and generating files

Executing Coding Tasks

• Summarizing repositories and navigating codebases
• Executing commands and assigning tasks
• Maintaining a structured task plan

Permissions and Sandbox Environment

• 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 Task Delegation

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

The Cordis Plugin Model

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

Profiles, Bundles, and Settings

• Profiles and bundle layering strategies
• Modifying configuration via cordis.patch.yml
• Reviewing the boot sequence tree

Core Subsystems

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

Events and Extension Capabilities

• Events related to sessions, agents, and capabilities
• Waterfall and interceptor event handling
• Aligning behavior with specific extension points

Plugin Development

• Registering services on specific context keys
• Incorporating tools and model adapters
• Releasing and identifying plugins

SDK, Headless Mode, and Automation

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