Add CLAUDE.md with codebase guidance for Claude Code#541
Add CLAUDE.md with codebase guidance for Claude Code#541fmarquezarate-png wants to merge 2 commits intomicrosoft:mainfrom
Conversation
Documents setup commands, env variable requirements, the two provider patterns (AzureAIProjectAgentProvider vs OpenAIChatClient), agent construction flow, tool registration decorators, MCP resumable server architecture, and lesson/translation structure. https://claude.ai/code/session_01CrNVwCz1fsewPiGabLy5m8
|
👋 Thanks for contributing @fmarquezarate-png! We will review the pull request and get back to you soon. |
|
@fmarquezarate-png please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
There was a problem hiding this comment.
Pull request overview
Adds a repository-level CLAUDE.md intended to guide Claude Code when navigating and running this repo’s lesson samples, including setup steps, environment variables, and a high-level architecture summary.
Changes:
- Introduces
CLAUDE.mdwith setup + “how to run” commands for notebooks and key samples. - Documents environment variable expectations across lessons/providers.
- Summarizes agent/provider patterns and the Lesson 11 MCP resumable server architecture.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| | Variable | Required for | | ||
| |---|---| | ||
| | `AZURE_AI_PROJECT_ENDPOINT` | All MAF + AzureAIProjectAgentProvider notebooks | | ||
| | `AZURE_AI_MODEL_DEPLOYMENT_NAME` | All MAF notebooks (e.g. `gpt-4o`) | | ||
| | `AZURE_SEARCH_SERVICE_ENDPOINT` + `AZURE_SEARCH_API_KEY` | Lesson 05 (Agentic RAG) | |
| python 14-microsoft-agent-framework/code-samples/hotel_booking_workflow_sample.py | ||
|
|
||
| # Run the MCP resumable server | ||
| python -m 11-agentic-protocols.code_samples.mcp-agents.server.server --port 8006 |
| python -m venv venv && source venv/bin/activate | ||
| pip install -r requirements.txt | ||
| cp .env.example .env # then fill in values | ||
| az login # notebooks authenticate via AzureCliCredential — no API keys needed |
| | `AZURE_AI_PROJECT_ENDPOINT` | All MAF + AzureAIProjectAgentProvider notebooks | | ||
| | `AZURE_AI_MODEL_DEPLOYMENT_NAME` | All MAF notebooks (e.g. `gpt-4o`) | | ||
| | `AZURE_SEARCH_SERVICE_ENDPOINT` + `AZURE_SEARCH_API_KEY` | Lesson 05 (Agentic RAG) | | ||
| | `GITHUB_TOKEN` | Lessons 06, 08 (GitHub Models) | |
| Agents in this repo are built in three layers: | ||
|
|
||
| ``` | ||
| Instructions (system prompt string) | ||
| → provider.create_agent() / chat_client.create_agent() | ||
| → AgentExecutor (wraps agent, gives it an id) | ||
| → WorkflowBuilder (wires executors into a graph) | ||
| ``` |
|
Thanks for the contribution @fmarquezarate-png please review the Copilot comments and the Contributor License Agreement(CLA) |
Documents setup commands, env variable requirements, the two provider patterns (AzureAIProjectAgentProvider vs OpenAIChatClient), agent construction flow, tool registration decorators, MCP resumable server architecture, and lesson/translation structure.
https://claude.ai/code/session_01CrNVwCz1fsewPiGabLy5m8