DeepSeek Harness: Building and Extending AI Coding Agents Training Course

Overview of DeepSeek Harness

• Defining DeepSeek Harness and its role in the ecosystem
• The "everything is a plugin" design philosophy
• Interfaces: Web UI, CLI, and headless modes

Setup and Initial Launch

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

Model Setup

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

Workspaces and Session Management

• Selecting and changing workspaces
• Using the session composer and managing conversation flow
• Operations for reading, editing, and generating files

Executing Coding Tasks

• Summarizing repositories and navigating codebases
• Executing commands and delegating tasks
• Maintaining and updating the task plan

Permissions and Sandbox Environments

• Defining approval and permission policies
• Restricting access to files and commands
• Managing local and remote sandbox backends

Native Tools and Integrations

• Utilizing filesystem, terminal, and shell utilities
• Supporting the Model Context Protocol
• Integrating 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 Framework

• Viewing plugins as services, events, and effects
• Understanding the shared context and lifecycle
• Why the core remains non-privileged

Profiles, Bundles, and Configuration Management

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

Core System Components

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

Event Handling and Extension Points

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

Plugin Development

• Registering services using context keys
• Incorporating tools and model adapters
• Releasing and discovering plugins

SDK, Headless Mode, and Automation

• Controlling the harness from external processes
• Using the TypeScript and Python SDKs
• Automation via CLI and headless configurations