v0.1.2 (#21)

* docs(readme): add logo, title, badges, links to other repos (#13)

* feat: upgrade to Claude Sonnet 4 model (#14)

- Updated default model from claude-3-7-sonnet to claude-sonnet-4-20250514-v1:0
- Updated model_id in .prompt, README.md, and model_utils.py
- Adjusted max_tokens to 32768 for Sonnet 4 compatibility
- Updated documentation references to reflect latest model capabilities

This upgrade provides enhanced reasoning capabilities and performance improvements.

* feat: add missing tools to strands.py (#15)

Adds the following tools that were missing from the imports:

- cron: Crontab management and job scheduling
- current_time: Current time utilities
- file_read: File reading capabilities
- rich_interface: Rich console interface components

Also reorganizes the tools list alphabetically and removes
duplicate load_tool entry for better maintainability.

Note: Excludes memory tool to avoid bringing in a dependency on Bedrock Knowledgebases.

* Fix AttributeError: 'dict' object has no attribute 'merge' in BedrockModel (#11)

- Add type conversion for boto_client_config from dict to BotocoreConfig
- Import BotocoreConfig class to handle configuration parsing
- Fixes issue where JSON config parsing creates dict instead of BotocoreConfig object
- Resolves 'AttributeError: dict object has no attribute merge' during model initialization

* fix(readme): use logo that changes color automatically depending on user's color preference scheme (#16)

* feat(tools): add file_write, memory, slack, speak, stop + remove rich_interface (#19)

* feat(tools): add file_write, memory, slack, speak, stop + remove rich_interface

* docs(readme): update list of tools + remove nested agent capabilities section

* fix: correctly handle keyboard interrupts + stop spinners on error (#12)

* v0.1.2

---------

Co-authored-by: Josh Samuel <[email protected]>

Author: awsarron

.prompt

@@ -182,7 +182,7 @@ from botocore.config import Config
 
 # Configure Bedrock model with maximum capabilities
 model = BedrockModel(
-    model_id="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+    model_id="us.anthropic.claude-sonnet-4-20250514-v1:0",
     max_tokens=int(os.getenv("STRANDS_MAX_TOKENS", "64000")),  # Maximized token output
     boto_client_config=Config(
         read_timeout=900,  # 15 min timeout for long operations
@@ -378,9 +378,9 @@ export STRANDS_SYSTEM_PROMPT="Your custom prompt here"
    - Create agents that can collaborate through shared interfaces
 
 6. **Maximizing Bedrock Performance**
-   - Use Claude 3.7 Sonnet for best reasoning capabilities
+   - Use the latest Claude Sonnet model available for best reasoning capabilities
    - Configure extended timeouts for complex reasoning tasks
    - Enable thinking capability with appropriate token budget
    - Use maximal output tokens to handle complex tool responses
 
-I'm here to help you build self-extending agents that continuously evolve their capabilities through autonomous tool creation. Let's build something extraordinary together!
+I'm here to help you build self-extending agents that continuously evolve their capabilities through autonomous tool creation. Let's build something extraordinary together!

README.md

@@ -1,4 +1,36 @@
-# Strands Agent Builder
+<div align="center">
+  <div>
+    <a href="https://strandsagents.com">
+      <img src="https://strandsagents.com/latest/assets/logo-auto.svg" alt="Strands Agents" width="55px" height="105px">
+    </a>
+  </div>
+
+  <h1>
+    Strands Agent Builder
+  </h1>
+
+  <h2>
+    A model-driven approach to building AI agents in just a few lines of code.
+  </h2>
+
+  <div align="center">
+    <a href="https://github.com/strands-agents/agent-builder/graphs/commit-activity"><img alt="GitHub commit activity" src="https://img.shields.io/github/commit-activity/m/strands-agents/agent-builder"/></a>
+    <a href="https://github.com/strands-agents/agent-builder/issues"><img alt="GitHub open issues" src="https://img.shields.io/github/issues/strands-agents/agent-builder"/></a>
+    <a href="https://github.com/strands-agents/agent-builder/pulls"><img alt="GitHub open pull requests" src="https://img.shields.io/github/issues-pr/strands-agents/agent-builder"/></a>
+    <a href="https://github.com/strands-agents/agent-builder/blob/main/LICENSE"><img alt="License" src="https://img.shields.io/github/license/strands-agents/agent-builder"/></a>
+    <a href="https://pypi.org/project/strands-agents-builder/"><img alt="PyPI version" src="https://img.shields.io/pypi/v/strands-agents-builder"/></a>
+    <a href="https://python.org"><img alt="Python versions" src="https://img.shields.io/pypi/pyversions/strands-agents-builder"/></a>
+  </div>
+  
+  <p>
+    <a href="https://strandsagents.com/">Documentation</a>
+    ◆ <a href="https://github.com/strands-agents/samples">Samples</a>
+    ◆ <a href="https://github.com/strands-agents/sdk-python">Python SDK</a>
+    ◆ <a href="https://github.com/strands-agents/tools">Tools</a>
+    ◆ <a href="https://github.com/strands-agents/agent-builder">Agent Builder</a>
+    ◆ <a href="https://github.com/strands-agents/mcp-server">MCP Server</a>
+  </p>
+</div>
 
 An interactive Strands agent toolkit designed to help you build, test, and extend your own custom AI agents and tools. With the Strands Agent Builder, you can create specialized agents, develop custom tools, and compose complex AI workflows—all from your terminal.
 
@@ -38,18 +70,33 @@ strands --kb YOUR_KB_ID "Load my previous calculator tool and enhance it with sc
 
 Strands comes with a comprehensive set of built-in tools:
 
-- **shell**: Run command-line operations with interactive support
-- **editor**: View and edit files with syntax highlighting
-- **http_request**: Make API calls with authentication support
-- **python_repl**: Execute Python code interactively
-- **calculator**: Perform mathematical operations powered by SymPy
-- **retrieve**: Query knowledge bases for relevant information
-- **store_in_kb**: Save content to knowledge bases for future reference
-- **load_tool**: Dynamically load additional tools at runtime
+- **agent_graph**: Create and manage graphs of agents
+- **calculator**: Perform mathematical operations
+- **cron**: Task scheduling with cron jobs
+- **current_time**: Get the current date and time
+- **editor**: File editing operations like line edits, search, and undo
 - **environment**: Manage environment variables
-- **strands**: Create nested agent instances with specialized capabilities
-- **dialog**: Create interactive dialog interfaces
-- **use_aws**: Make AWS API calls through boto3
+- **generate_image**: Create AI generated images with Amazon Bedrock
+- **http_request**: Make API calls, fetch web data, and call local HTTP servers
+- **image_reader**: Process and analyze images
+- **journal**: Create structured tasks and logs for agents to manage and work from
+- **load_tool**: Dynamically load more tools at runtime
+- **memory**: Agent memory persistence in Amazon Bedrock Knowledge Bases
+- **nova_reels**: Create AI generated videos with Nova Reels on Amazon Bedrock
+- **python_repl**: Run Python code
+- **retrieve**: Semantically retrieve data from Amazon Bedrock Knowledge Bases for RAG, memory, and other purposes
+- **shell**: Execute shell commands
+- **slack**: Slack integration with real-time events, API access, and message sending
+- **speak**: Generate speech from text using macOS say command or Amazon Polly
+- **stop**: Force stop the agent event loop
+- **store_in_kb**: Save content to knowledge bases for future reference
+- **strand**: Create nested agent instances with specialized capabilities
+- **swarm**: Coordinate multiple AI agents in a swarm / network of agents
+- **think**: Perform deep thinking by creating parallel branches of agentic reasoning
+- **use_aws**: Interact with AWS services
+- **use_llm**: Run a new AI event loop with custom prompts
+- **welcome**: Manage the Strands Agent Builder welcome text
+- **workflow**: Orchestrate sequenced workflows
 
 ## Knowledge Base Integration
 
@@ -70,26 +117,6 @@ Features:
 - 🛠️ Ability to iteratively improve tools across sessions
 - 🔍 Find and extend tools built in previous sessions
 
-## Nested Agent Capabilities
-
-Use the `strands` tool to prototype and test specialized sub-agents with their own tools and system prompts:
-
-```python
-# Create a specialized data analysis agent
-agent.tool.strand(
-    query="Build and test a data analysis agent",
-    tool_names=["python_repl", "editor", "http_request"],
-    system_prompt="You're an AI specialized in data analysis. Your task is to build tools for data processing and visualization."
-)
-
-# Create a tool-building agent focused on web automation
-agent.tool.strand(
-    query="Create a set of web automation tools for browser testing",
-    tool_names=["editor", "python_repl", "shell"],
-    system_prompt="You're an expert in creating web automation tools. Your specialty is developing reliable browser testing utilities."
-)
-```
-
 ## Model Configuration
 
 ### Optimized Defaults
@@ -98,8 +125,8 @@ Strands comes with optimized, maxed-out configuration settings for the Bedrock m
 
 ```json
 {
-    "model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
-    "max_tokens": 64000,
+    "model_id": "us.anthropic.claude-sonnet-4-20250514-v1:0",
+    "max_tokens": 32767,
     "boto_client_config": {
         "read_timeout": 900,
         "connect_timeout": 900,
@@ -118,8 +145,8 @@ Strands comes with optimized, maxed-out configuration settings for the Bedrock m
 ```
 
 These settings provide:
-- Claude 3.7 Sonnet (latest high-performance model)
-- Maximum token output (64,000 tokens)
+- Claude Sonnet 4 (latest high-performance model)
+- Maximum token output (32,768 tokens)
 - Extended timeouts (15 minutes) for complex operations
 - Automatic retries with adaptive backoff
 - Enabled thinking capability with 2,048 token budget for recursive reasoning
@@ -176,22 +203,29 @@ export STRANDS_SYSTEM_PROMPT="You are a Python expert."
 echo "You are a security expert." > .prompt
 ```
 
-## Contributing
+## Exit
 
-```bash
-git clone https://github.com/strands-agents/agent-builder.git ~/.agent-builder
-cd ~/.agent-builder
-python3 -m venv venv && source venv/bin/activate
-pip3 install -e .
-pip3 install -e ".[test]"
-
-# Run tests
-hatch run test         # Run all tests with verbose coverage output
-hatch run test -k test_pattern  # Run specific tests matching a pattern
-```
+Type `exit`, `quit`, or press `Ctrl+C`/`Ctrl+D`
 
-Testing is managed through hatch scripting in pyproject.toml.
+## Contributing ❤️
 
-## Exit
+We welcome contributions! See our [Contributing Guide](CONTRIBUTING.md) for details on:
+- Reporting bugs & features
+- Development setup
+- Contributing via Pull Requests
+- Code of Conduct
+- Reporting of security issues
 
-Type `exit`, `quit`, or press `Ctrl+C`/`Ctrl+D`
+## License
+
+This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.
+
+## Security
+
+See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.
+
+## ⚠️ Preview Status
+
+Strands Agents is currently in public preview. During this period:
+- APIs may change as we refine the SDK
+- We welcome feedback and contributions

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "strands-agents-builder"
-version = "0.1.1"
+version = "0.1.2"
 description = "An example Strands agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools."
 readme = "README.md"
 requires-python = ">=3.10"

src/strands_agents_builder/models/bedrock.py

@@ -1,5 +1,6 @@
 """Create instance of SDK's Bedrock model provider."""
 
+from botocore.config import Config as BotocoreConfig
 from strands.models import BedrockModel
 from strands.types.models import Model
 from typing_extensions import Unpack
@@ -14,5 +15,8 @@ def instance(**model_config: Unpack[BedrockModel.BedrockConfig]) -> Model:
     Returns:
         Bedrock model provider.
     """
+    # Handle conversion of boto_client_config from dict to BotocoreConfig
+    if "boto_client_config" in model_config and isinstance(model_config["boto_client_config"], dict):
+        model_config["boto_client_config"] = BotocoreConfig(**model_config["boto_client_config"])
 
     return BedrockModel(**model_config)

src/strands_agents_builder/strands.py

@@ -13,17 +13,25 @@
 from strands_tools import (
     agent_graph,
     calculator,
+    cron,
+    current_time,
     editor,
     environment,
+    file_read,
+    file_write,
     generate_image,
     http_request,
     image_reader,
     journal,
     load_tool,
+    memory,
     nova_reels,
     python_repl,
     retrieve,
     shell,
+    slack,
+    speak,
+    stop,
     swarm,
     think,
     use_aws,
@@ -37,7 +45,7 @@
 from strands_agents_builder.utils.kb_utils import load_system_prompt, store_conversation_in_kb
 from strands_agents_builder.utils.welcome_utils import render_goodbye_message, render_welcome_message
 
-# Custom tools, handlers, utils
+# Custom tools
 from tools import (
     store_in_kb,
     strand,
@@ -80,24 +88,31 @@ def main():
     system_prompt = load_system_prompt()
 
     tools = [
-        shell,
+        agent_graph,
+        calculator,
+        cron,
+        current_time,
         editor,
+        environment,
+        file_read,
+        file_write,
+        generate_image,
         http_request,
+        image_reader,
+        journal,
+        load_tool,
+        memory,
+        nova_reels,
         python_repl,
-        calculator,
         retrieve,
+        shell,
+        slack,
+        speak,
+        stop,
+        swarm,
+        think,
         use_aws,
-        load_tool,
-        environment,
         use_llm,
-        think,
-        load_tool,
-        journal,
-        image_reader,
-        generate_image,
-        nova_reels,
-        agent_graph,
-        swarm,
         workflow,
         # Strands tools
         store_in_kb,
@@ -133,7 +148,7 @@ def main():
             render_welcome_message(welcome_text)
         while True:
             try:
-                user_input = get_user_input("\n~ ")
+                user_input = get_user_input("\n~ ", default="", keyboard_interrupt_return_default=False)
                 if user_input.lower() in ["exit", "quit"]:
                     render_goodbye_message()
                     break
@@ -177,6 +192,7 @@ def main():
                 render_goodbye_message()
                 break
             except Exception as e:
+                callback_handler(force_stop=True)  # Stop spinners
                 print(f"\nError: {str(e)}")
 
 

src/strands_agents_builder/utils/model_utils.py

@@ -11,8 +11,8 @@
 
 # Default model configuration
 DEFAULT_MODEL_CONFIG = {
-    "model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
-    "max_tokens": int(os.getenv("STRANDS_MAX_TOKENS", "64000")),
+    "model_id": "us.anthropic.claude-sonnet-4-20250514-v1:0",
+    "max_tokens": int(os.getenv("STRANDS_MAX_TOKENS", "32768")),
     "boto_client_config": Config(
         read_timeout=900,
         connect_timeout=900,

tests/test_strands.py

@@ -41,6 +41,9 @@ def test_interactive_mode(
         # Verify welcome message was rendered
         mock_welcome_message.assert_called_once()
 
+        # Verify user input was called with the correct parameters
+        mock_user_input.assert_called_with("\n~ ", default="", keyboard_interrupt_return_default=False)
+
         # Verify user input was processed
         mock_agent.assert_called_with("test query", system_prompt=mock.ANY)
 
@@ -107,7 +110,7 @@ def test_empty_input(
     ):
         """Test handling of empty input"""
         # Setup mocks - empty input followed by exit
-        mock_user_input.side_effect = ["", "exit"]
+        mock_user_input.side_effect = ["", "   ", "\t", "exit"]
 
         # Mock sys.argv
         monkeypatch.setattr(sys, "argv", ["strands"])
@@ -167,7 +170,8 @@ def test_eof_error_exception(self, mock_goodbye, mock_agent, mock_input):
     @mock.patch.object(strands, "get_user_input")
     @mock.patch.object(strands, "Agent")
     @mock.patch.object(strands, "print")
-    def test_general_exception_handling(self, mock_print, mock_agent, mock_input):
+    @mock.patch.object(strands, "callback_handler")
+    def test_general_exception_handling(self, mock_callback_handler, mock_print, mock_agent, mock_input):
         """Test handling of general exceptions in interactive mode"""
         # Setup mocks
         mock_agent_instance = mock.MagicMock()
@@ -187,6 +191,9 @@ def test_general_exception_handling(self, mock_print, mock_agent, mock_input):
         # Verify error was printed
         mock_print.assert_any_call("\nError: Test error")
 
+        # Verify callback_handler was called to stop spinners
+        mock_callback_handler.assert_called_once_with(force_stop=True)
+
 
 class TestCommandLine:
     """Test cases for command line mode functionality"""