-
Notifications
You must be signed in to change notification settings - Fork 19
Add design documents and initialize Claude code #180
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull request overview
This pull request adds comprehensive design documentation to the Agent365-Samples repository, establishing architectural guidelines and usage patterns for sample agents across C#/.NET, Python, and Node.js/TypeScript platforms.
Changes:
- Added repository-wide documentation (CLAUDE.md and docs/design.md) describing initialization flows, message processing patterns, MCP tool integration, authentication strategies, and observability setup
- Added language-specific design guidelines (dotnet/docs/design.md, python/docs/design.md, nodejs/docs/design.md) detailing orchestrator patterns, project structure, dependency injection, configuration, and best practices
- Added sample-specific design documents for 17 different orchestrator implementations across three languages, each with architecture diagrams, component descriptions, message flows, configuration examples, and extension points
Reviewed changes
Copilot reviewed 19 out of 19 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| CLAUDE.md | Developer guidance for Claude Code with repo structure, commands, architecture patterns, auth strategies, configuration, observability, tooling, code quality rules, and documentation standards |
| docs/design.md | Cross-cutting architectural patterns covering agent initialization flow, message processing, MCP tool integration, authentication strategies, observability, notification handling, and graceful degradation |
| dotnet/docs/design.md | .NET design guidelines with ASP.NET Core patterns, dependency injection, configuration management, tool registration, authentication, observability, and streaming support |
| dotnet/agent-framework/sample-agent/docs/design.md | Agent Framework sample design showing weather-focused agent with local tools, MCP integration, streaming responses, dual authentication, and conversation management |
| dotnet/semantic-kernel/sample-agent/docs/design.md | Semantic Kernel sample design demonstrating multi-channel support (Teams/Emulator), notification handling (Email/WPX), installation events, and SK plugin patterns |
| python/docs/design.md | Python design guidelines with async patterns, abstract base classes, generic host server, observability configuration, MCP setup, authentication options, and token caching |
| python/agent-framework/sample-agent/docs/design.md | Python Agent Framework sample showing integration patterns and message processing |
| python/claude/sample-agent/docs/design.md | Claude sample with Anthropic SDK integration, tool use patterns, and MCP tool integration |
| python/crewai/sample_agent/docs/design.md | CrewAI sample demonstrating multi-agent orchestration with crew and task patterns |
| python/google-adk/sample-agent/docs/design.md | Google ADK sample showing Gemini model integration with function calling |
| python/openai/sample-agent/docs/design.md | OpenAI sample with async patterns, MCP servers, observability, and graceful degradation |
| nodejs/docs/design.md | Node.js/TypeScript guidelines with Express patterns, agent application structure, observability integration, and notification handling |
| nodejs/claude/sample-agent/docs/design.md | Claude Node.js sample with tool use loop and MCP tool conversion patterns |
| nodejs/devin/sample-agent/docs/design.md | Devin sample showing code-focused agent capabilities |
| nodejs/langchain/sample-agent/docs/design.md | LangChain sample with chain patterns, agent executor, and memory management |
| nodejs/n8n/sample-agent/docs/design.md | N8N sample demonstrating workflow-based orchestration with webhook triggers |
| nodejs/openai/sample-agent/docs/design.md | OpenAI Node.js sample with InferenceScope usage, notification handling, and MCP tool integration |
| nodejs/perplexity/sample-agent/docs/design.md | Perplexity sample showing search-augmented generation with citation handling |
| nodejs/vercel-sdk/sample-agent/docs/design.md | Vercel AI SDK sample with unified provider interface and streaming responses |
…gent365-Samples into users/johanb/AddDocs
This pull request adds comprehensive documentation to the repository, establishing design and usage guidelines for contributors and users. The new documents outline repository structure, architectural patterns, sample agent flows, configuration, authentication, observability, and extension points for the Microsoft Agent 365 SDK samples across C#/.NET, Python, and Node.js/TypeScript.
Repository-wide documentation and guidelines:
CLAUDE.md, providing detailed repository structure, common development commands, architecture patterns, configuration, observability, security, and documentation standards for all contributors, with a focus on best practices and code quality rules.docs/design.md, describing cross-cutting architectural patterns, message and initialization flows, tool integration (MCP), authentication strategies, observability, notification handling, error handling, and security principles for all sample agents in the repository.Sample-specific documentation:
dotnet/agent-framework/sample-agent/docs/design.md, giving an in-depth design and architecture overview for the .NET Agent Framework sample, including diagrams, component breakdowns, message flow, tool integration, configuration, authentication, observability, and extension points.