Synchronize fork with Anthropic base for minor and patch updates

.github/pull_request_template.md

@@ -0,0 +1,27 @@
+## Description
+<!-- Describe the changes you've made -->
+
+## Quickstart
+- [ ] Computer Use Demo
+- [ ] Customer Support Agent
+- [ ] Financial Data Analyst
+- [ ] N/A
+
+## Type of Change
+- [ ] Bug fix
+- [ ] New feature
+- [ ] Documentation update
+- [ ] Code refactoring
+- [ ] Other (please describe):
+
+## Testing
+<!-- Describe the testing you've done -->
+- [ ] Added/updated unit tests
+- [ ] Tested manually
+- [ ] Verified in development environment
+
+## Screenshots
+<!-- If applicable, add screenshots to help explain your changes -->
+
+## Additional Notes
+<!-- Add any additional context or notes about the changes -->

.github/workflows/tests.yaml

@@ -19,6 +19,8 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - uses: astral-sh/ruff-action@v1
+        with:
+          src: "computer-use-demo"
   pyright:
     runs-on: ubuntu-latest
     defaults:
@@ -36,6 +38,8 @@ jobs:
           pip install -r dev-requirements.txt
       - run: echo "$PWD/.venv/bin" >> $GITHUB_PATH
       - uses: jakebailey/pyright-action@v1
+        with:
+          working-directory: computer-use-demo
   pytest:
     runs-on: ubuntu-latest
     defaults:

CLAUDE.md

@@ -0,0 +1,62 @@
+# Claude Quickstarts Development Guide
+
+## Legal
+
+- When changes are made to files that have a copyright notice add them to that subdirectory's CHANGELOG.md file.
+
+## Computer-Use Demo
+
+### Setup & Development
+
+- **Setup environment**: `./setup.sh`
+- **Build Docker**: `docker build . -t computer-use-demo:local`
+- **Run container**: `docker run -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY -v $(pwd)/computer_use_demo:/home/computeruse/computer_use_demo/ -v $HOME/.anthropic:/home/computeruse/.anthropic -p 5900:5900 -p 8501:8501 -p 6080:6080 -p 8080:8080 -it computer-use-demo:local`
+
+### Testing & Code Quality
+
+- **Lint**: `ruff check .`
+- **Format**: `ruff format .`
+- **Typecheck**: `pyright`
+- **Run tests**: `pytest`
+- **Run single test**: `pytest tests/path_to_test.py::test_name -v`
+
+### Code Style
+
+- **Python**: snake_case for functions/variables, PascalCase for classes
+- **Imports**: Use isort with combine-as-imports
+- **Error handling**: Use custom ToolError for tool errors
+- **Types**: Add type annotations for all parameters and returns
+- **Classes**: Use dataclasses and abstract base classes
+
+## Customer Support Agent
+
+### Setup & Development
+
+- **Install dependencies**: `npm install`
+- **Run dev server**: `npm run dev` (full UI)
+- **UI variants**: `npm run dev:left` (left sidebar), `npm run dev:right` (right sidebar), `npm run dev:chat` (chat only)
+- **Lint**: `npm run lint`
+- **Build**: `npm run build` (full UI), see package.json for variants
+
+### Code Style
+
+- **TypeScript**: Strict mode with proper interfaces
+- **Components**: Function components with React hooks
+- **Formatting**: Follow ESLint Next.js configuration
+- **UI components**: Use shadcn/ui components library
+
+## Financial Data Analyst
+
+### Setup & Development
+
+- **Install dependencies**: `npm install`
+- **Run dev server**: `npm run dev`
+- **Lint**: `npm run lint`
+- **Build**: `npm run build`
+
+### Code Style
+
+- **TypeScript**: Strict mode with proper type definitions
+- **Components**: Function components with type annotations
+- **Visualization**: Use Recharts library for data visualization
+- **State management**: React hooks for state

README.md

@@ -1,10 +1,10 @@
-# Anthropic Quickstarts
+# Claude Quickstarts
 
-Anthropic Quickstarts is a collection of projects designed to help developers quickly get started with building  applications using the Anthropic API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.
+Claude Quickstarts is a collection of projects designed to help developers quickly get started with building  applications using the Claude API. Each quickstart provides a foundation that you can easily build upon and customize for your specific needs.
 
 ## Getting Started
 
-To use these quickstarts, you'll need an Anthropic API key. If you don't have one yet, you can sign up for free at [console.anthropic.com](https://console.anthropic.com).
+To use these quickstarts, you'll need an Claude API key. If you don't have one yet, you can sign up for free at [console.anthropic.com](https://console.anthropic.com).
 
 ## Available Quickstarts
 
@@ -22,31 +22,43 @@ A financial data analyst powered by Claude. This project demonstrates how to lev
 
 ### Computer Use Demo
 
-An environment and tools that Claude can use to control a desktop computer. This project demonstrates how to leverage the computer use capabilities of the the new Claude 3.5 Sonnet model.
+An environment and tools that Claude can use to control a desktop computer. This project demonstrates how to leverage the computer use capabilities of Claude, including support for the latest `computer_use_20251124` tool version with zoom actions.
 
 [Go to Computer Use Demo Quickstart](./computer-use-demo)
 
+### Browser Tools API Demo
+
+A complete reference implementation for browser automation powered by Claude. This project demonstrates how to leverage Claude's browser tools API for web interaction, including navigation, DOM inspection, and form manipulation using Playwright.
+
+[Go to Browser Tools API Demo Quickstart](./browser-tools-api-demo)
+
+### Autonomous Coding Agent
+
+An autonomous coding agent powered by the Claude Agent SDK. This project demonstrates a two-agent pattern (initializer + coding agent) that can build complete applications over multiple sessions, with progress persisted via git and a feature list that the agent works through incrementally.
+
+[Go to Autonomous Coding Agent Quickstart](./autonomous-coding)
+
 ## General Usage
 
 Each quickstart project comes with its own README and setup instructions. Generally, you'll follow these steps:
 
 1. Clone this repository
 2. Navigate to the specific quickstart directory
 3. Install the required dependencies
-4. Set up your Anthropic API key as an environment variable
+4. Set up your Claude API key as an environment variable
 5. Run the quickstart application
 
 ## Explore Further
 
-To deepen your understanding of working with Claude and the Anthropic API, check out these resources:
+To deepen your understanding of working with Claude and the Claude API, check out these resources:
 
-- [Anthropic API Documentation](https://docs.anthropic.com)
-- [Anthropic Cookbook](https://github.com/anthropics/anthropic-cookbook) - A collection of code snippets and guides for common tasks
-- [Anthropic API Fundamentals Course](https://github.com/anthropics/courses/tree/master/anthropic_api_fundamentals)
+- [Claude API Documentation](https://docs.claude.com)
+- [Claude Cookbooks](https://github.com/anthropics/claude-cookbooks) - A collection of code snippets and guides for common tasks
+- [Claude API Fundamentals Course](https://github.com/anthropics/courses/tree/master/anthropic_api_fundamentals)
 
 ## Contributing
 
-We welcome contributions to the Anthropic Quickstarts repository! If you have ideas for new quickstart projects or improvements to existing ones, please open an issue or submit a pull request.
+We welcome contributions to the Claude Quickstarts repository! If you have ideas for new quickstart projects or improvements to existing ones, please open an issue or submit a pull request.
 
 ## Community and Support
 

agents/.gitignore

@@ -0,0 +1,27 @@
+# Python bytecode
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Jupyter Notebook
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# MacOS
+.DS_Store
+
+# Environment variables
+.env
+
+# Virtual environments
+venv/
+env/
+.venv/
+
+# MCP logs
+*.log
+
+# Distribution / packaging
+dist/
+build/
+*.egg-info/

agents/README.md

@@ -0,0 +1,48 @@
+# Agents
+
+A minimal educational implementation of LLM agents using the Claude API.
+
+> **Note:** This is NOT an SDK, but a reference implementation of key concepts
+
+## Overview & Core Components
+
+This repo demonstrates how to [build effective agents](https://www.anthropic.com/engineering/building-effective-agents) with the Claude API. It shows how sophisticated AI behaviors can emerge from a simple foundation: LLMs using tools in a loop. This implementation is not prescriptive - the core logic is <300 lines of code and deliberately lacks production features. Feel free to translate these patterns to your language and production stack ([Claude Code](https://docs.claude.com/en/docs/agents-and-tools/claude-code/overview) can help!)
+
+It contains three components:
+
+- `agent.py`: Manages Claude API interactions and tool execution
+- `tools/`: Tool implementations (both native and MCP tools)
+- `utils/`: Utilities for message history and MCP server connections
+
+## Usage
+
+```python
+from agents.agent import Agent
+from agents.tools.think import ThinkTool
+
+# Create an agent with both local tools and MCP server tools
+agent = Agent(
+    name="MyAgent",
+    system="You are a helpful assistant.",
+    tools=[ThinkTool()],  # Local tools
+    mcp_servers=[
+        {
+            "type": "stdio",
+            "command": "python",
+            "args": ["-m", "mcp_server"],
+        },
+    ]
+)
+
+# Run the agent
+response = agent.run("What should I consider when buying a new laptop?")
+```
+
+From this foundation, you can add domain-specific tools, optimize performance, or implement custom response handling. We remain deliberately unopinionated - this backbone simply gets you started with fundamentals.
+
+## Requirements
+
+- Python 3.8+
+- Claude API key (set as `ANTHROPIC_API_KEY` environment variable)
+- `anthropic` Python library
+- `mcp` Python library

agents/__init__.py

@@ -0,0 +1,6 @@
+"""Core agent implementations."""
+
+from .agent import Agent, ModelConfig
+from .tools.base import Tool
+
+__all__ = ["Agent", "ModelConfig", "Tool"]