agent/agent-framework
2
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: Add BaseAgent implementation for Claude Agent SDK (#3509)

Browse Source 
* Added ClaudeAgent implementation

* Updated streaming logic

* Small updates

* Small update

* Fixes

* Small fix

* Naming improvements

* Updated imports

* Addressed comments

* Updated package versions
This commit is contained in:
Dmytro Struk
2026-01-30 18:11:41 +00:00
committed by GitHub
parent 0fcf075ea7
commit 8b475afe17
39 changed files with 2180 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/getting_started/agents/anthropic/README.md
+25 -3
View File
@@ -2,7 +2,7 @@
This folder contains examples demonstrating how to use Anthropic's Claude models with the Agent Framework.
## Examples
## Anthropic Client Examples
| File | Description |
|------|-------------|
@@ -11,14 +11,36 @@ This folder contains examples demonstrating how to use Anthropic's Claude models
| [`anthropic_skills.py`](anthropic_skills.py) | Illustrates how to use Anthropic-managed Skills with an agent, including the Code Interpreter tool and file generation and saving. |
| [`anthropic_foundry.py`](anthropic_foundry.py) | Example of using Foundry's Anthropic integration with the Agent Framework. |
## Claude Agent Examples
| File | Description |
|------|-------------|
| [`anthropic_claude_basic.py`](anthropic_claude_basic.py) | Basic usage of ClaudeAgent with streaming, non-streaming, and custom tools. |
| [`anthropic_claude_with_tools.py`](anthropic_claude_with_tools.py) | Using built-in tools (Read, Glob, Grep, etc.). |
| [`anthropic_claude_with_shell.py`](anthropic_claude_with_shell.py) | Shell command execution with interactive permission handling. |
| [`anthropic_claude_with_multiple_permissions.py`](anthropic_claude_with_multiple_permissions.py) | Combining multiple tools (Bash, Read, Write) with permission prompts. |
| [`anthropic_claude_with_url.py`](anthropic_claude_with_url.py) | Fetching and processing web content with WebFetch. |
| [`anthropic_claude_with_mcp.py`](anthropic_claude_with_mcp.py) | Local (stdio) and remote (HTTP) MCP server configuration. |
| [`anthropic_claude_with_session.py`](anthropic_claude_with_session.py) | Session management, persistence, and resumption. |
## Environment Variables
Set the following environment variables before running the examples:
### Anthropic Client
- `ANTHROPIC_API_KEY`: Your Anthropic API key (get one from [Anthropic Console](https://console.anthropic.com/))
- `ANTHROPIC_CHAT_MODEL_ID`: The Claude model to use (e.g., `claude-haiku-4-5`, `claude-sonnet-4-5-20250929`)
Or, for Foundry:
### Foundry
- `ANTHROPIC_FOUNDRY_API_KEY`: Your Foundry Anthropic API key
- `ANTHROPIC_FOUNDRY_ENDPOINT`: The endpoint URL for your Foundry Anthropic resource
- `ANTHROPIC_CHAT_MODEL_ID`: The Claude model to use in Foundry (e.g., `claude-haiku-4-5`)
### Claude Agent
- `CLAUDE_AGENT_CLI_PATH`: Path to the Claude Code CLI executable
- `CLAUDE_AGENT_MODEL`: Model to use (sonnet, opus, haiku)
- `CLAUDE_AGENT_CWD`: Working directory for Claude CLI
- `CLAUDE_AGENT_PERMISSION_MODE`: Permission mode (default, acceptEdits, plan, bypassPermissions)
- `CLAUDE_AGENT_MAX_TURNS`: Maximum number of conversation turns
- `CLAUDE_AGENT_MAX_BUDGET_USD`: Maximum budget in USD