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 philosophy
• Web UI, CLI, and headless operational modes

Installation and Initial Setup

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

Model Configuration

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

Workspaces and Sessions

• Selecting and navigating between workspaces
• Understanding the session composer and conversation flow
• Reading, editing, and generating files

Executing Coding Tasks

• Summarising repositories and navigating codebases
• Running commands and delegating tasks
• Maintaining and tracking task plans

Permissions and Sandbox

• Managing approval and permission policies
• Restricting file and command access
• Configuring local and remote sandbox backends

Built-in 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
• Utilising product providers for other coding agents
• Delegating work across multiple sessions

The Cordis Plugin Model

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

Profiles, Bundles, and Configuration

• Layering profiles and bundles
• Patching configuration via cordis.patch.yml
• Inspecting the initialised system tree

Core Subsystems

• The append-only session log
• 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 handling
• Aligning behaviour with specific extension points

Plugin Development

• Registering services using context keys
• Implementing custom tools and model adapters
• Publishing and discovering available plugins

SDK, Headless Mode, and Automation

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