bedrock-agentcore-starter-toolkit 0.1.7__tar.gz → 0.1.9__tar.gz

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/CHANGELOG.md

@@ -1,8 +1,32 @@
 # Changelog
 
+## [0.1.9] - 2025-09-07
+
+### Changes
+
+- fix: resolve regex escape sequence warnings (#151) (70d7381)
+- feat(gateway): handle existing policies gracefully in _attach_policy (#140) (f372b99)
+- chore: bump version to 0.1.8 (#150) (1421e48)
+
+### Dependencies
+- Updated to bedrock-agentcore SDK v0.1.3
+
+## [0.1.8] - 2025-09-02
+
+### Changes
+
+- chore/cb latency optimization (#146) (3523bfa)
+- chore(deps): update mkdocstrings-python requirement (#133) (8b8afb5)
+- Release vv0.1.7 (b473e38)
+
 ## [0.1.7] - 2025-08-28
 
-Enhanced execution role permissions - Added relevant permissions for Runtime, Memory and Identity services to auto-created execution role (#132)
+- Enhanced execution role permissions - Added relevant permissions for Runtime, Memory and Identity services to auto-created execution role (#132)
+- Windows compatibility fix - Resolved file handle issue on Windows systems by properly closing NameTemporaryFile, fixing deployment failures with "process cannot access the file" errors (#106)
+- Corrected managed policy name from AmazonBedrockAgentCoreFullAccess to BedrockAgentCoreFullAccess (#124)
+- S3 permissions - Added missing S3 permissions documentation for bucket creation and lifecycle configuration (#124)
+- Fixed IaC reference - Corrected typo in Infrastructure as Code reference (#124)
+- Other documentation enhancements for clarity and completeness
 
 ## [0.1.6] - 2025-08-11
 

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bedrock-agentcore-starter-toolkit
-Version: 0.1.7
+Version: 0.1.9
 Summary: A starter toolkit for using Bedrock AgentCore
 Project-URL: Homepage, https://github.com/aws/bedrock-agentcore-starter-toolkit
 Project-URL: Bug Tracker, https://github.com/aws/bedrock-agentcore-starter-toolkit/issues
@@ -22,7 +22,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Requires-Dist: autopep8>=2.3.2
-Requires-Dist: bedrock-agentcore>=0.1.2
+Requires-Dist: bedrock-agentcore>=0.1.3
 Requires-Dist: boto3>=1.39.7
 Requires-Dist: botocore>=1.39.7
 Requires-Dist: docstring-parser<1.0,>=0.15
@@ -67,7 +67,7 @@ Description-Content-Type: text/markdown
   <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html">Documentation</a>
     ◆ <a href="https://github.com/awslabs/amazon-bedrock-agentcore-samples">Samples</a>
     ◆ <a href="https://discord.gg/bedrockagentcore-preview">Discord</a>
-    ◆ <a href="https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agentcore-control.html">Setup Python SDK</a>
+    ◆ <a href="https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agentcore-control.html">Boto3 Python SDK</a>
     ◆ <a href="https://github.com/aws/bedrock-agentcore-sdk-python">Runtime Python SDK</a>
     ◆ <a href="https://github.com/aws/bedrock-agentcore-starter-toolkit">Starter Toolkit</a>
 
@@ -82,38 +82,43 @@ Amazon Bedrock AgentCore includes the following modular Services that you can us
 ## 🚀 Amazon Bedrock AgentCore Runtime
 AgentCore Runtime is a secure, serverless runtime purpose-built for deploying and scaling dynamic AI agents and tools using any open-source framework including LangGraph, CrewAI, and Strands Agents, any protocol, and any model. Runtime was built to work for agentic workloads with industry-leading extended runtime support, fast cold starts, true session isolation, built-in identity, and support for multi-modal payloads. Developers can focus on innovation while Amazon Bedrock AgentCore Runtime handles infrastructure and security -- accelerating time-to-market
 
-**[Runtime Quick Start](documentation/docs/user-guide/runtime/quickstart.md)**
+**[Runtime Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/runtime/quickstart.html)**
 
 ## 🧠 Amazon Bedrock AgentCore Memory
 AgentCore Memory makes it easy for developers to build context aware agents by eliminating complex memory infrastructure management while providing full control over what the AI agent remembers. Memory provides industry-leading accuracy along with support for both short-term memory for multi-turn conversations and long-term memory that can be shared across agents and sessions.
 
-**[Memory Quick Start](documentation/docs/user-guide/memory/quickstart.md)**
+**[Memory Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/memory/quickstart.html)**
 
 ## 🔗 Amazon Bedrock AgentCore Gateway
 Amazon Bedrock AgentCore Gateway acts as a managed Model Context Protocol (MCP) server that converts APIs and Lambda functions into MCP tools that agents can use. Gateway manages the complexity of OAuth ingress authorization and secure egress credential exchange, making standing up remote MCP servers easier and more secure. Gateway also offers composition and built-in semantic search over tools, enabling developers to scale their agents to use hundreds or thousands of tools.
 
-**[Gateway Quick Start](documentation/docs/user-guide/gateway/quickstart.md)**
+**[Gateway Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/gateway/quickstart.html)**
 
 ## 💻 Amazon Bedrock AgentCore Code Interpreter
 AgentCore Code Interpreter tool enables agents to securely execute code in isolated sandbox environments. It offers advanced configuration support and seamless integration with popular frameworks. Developers can build powerful agents for complex workflows and data analysis while meeting enterprise security requirements.
 
-**[Code Interpreter Quick Start](documentation/docs/user-guide/builtin-tools/quickstart-code-interpreter.md)**
+**[Code Interpreter Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/builtin-tools/quickstart-code-interpreter.html)**
 
 
 ## 🌐 Amazon Bedrock AgentCore Browser
 AgentCore Browser tool provides a fast, secure, cloud-based browser runtime to enable AI agents to interact with websites at scale. It provides enterprise-grade security, comprehensive observability features, and automatically scales— all without infrastructure management overhead.
 
-**[Browser Quick Start](documentation/docs/user-guide/builtin-tools/quickstart-browser.md)**
+**[Browser Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/builtin-tools/quickstart-browser.html)**
 
 ## 📊 Amazon Bedrock AgentCore Observability
 AgentCore Observability helps developers trace, debug, and monitor agent performance in production through unified operational dashboards. With support for OpenTelemetry compatible telemetry and detailed visualizations of each step of the agent workflow, AgentCore enables developers to easily gain visibility into agent behavior and maintain quality standards at scale.
 
-**[Observability Quick Start](documentation/docs/user-guide/observability/quickstart.md)**
+**[Observability Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/observability/quickstart.html)**
 
 ## 🔐 Amazon Bedrock AgentCore Identity
 AgentCore Identity provides a secure, scalable agent identity and access management capability accelerating AI agent development. It is compatible with existing identity providers, eliminating needs for user migration or rebuilding authentication flows. AgentCore Identity's helps to minimize consent fatigue with a secure token vault and allows you to build streamlined AI agent experiences. Just-enough access and secure permission delegation allow agents to securely access AWS resources and third-party tools and services.
 
-**[Identity Quick Start](documentation/docs/user-guide/identity/quickstart.md)**
+**[Identity Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/identity/quickstart.html)**
+
+## 🔐 Import Amazon Bedrock Agents to Bedrock AgentCore
+AgentCore Import-Agent enables seamless migration of existing Amazon Bedrock Agents to LangChain/LangGraph or Strands frameworks while automatically integrating AgentCore primitives like Memory, Code Interpreter, and Gateway. Developers can migrate agents in minutes with full feature parity and deploy directly to AgentCore Runtime for serverless operation.
+
+**[Import Agent Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/import-agent/quickstart.html)**
 
 
 ## ⚠️ Preview Status

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/README.md

@@ -20,7 +20,7 @@
   <a href="https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html">Documentation</a>
     ◆ <a href="https://github.com/awslabs/amazon-bedrock-agentcore-samples">Samples</a>
     ◆ <a href="https://discord.gg/bedrockagentcore-preview">Discord</a>
-    ◆ <a href="https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agentcore-control.html">Setup Python SDK</a>
+    ◆ <a href="https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/bedrock-agentcore-control.html">Boto3 Python SDK</a>
     ◆ <a href="https://github.com/aws/bedrock-agentcore-sdk-python">Runtime Python SDK</a>
     ◆ <a href="https://github.com/aws/bedrock-agentcore-starter-toolkit">Starter Toolkit</a>
 
@@ -35,38 +35,43 @@ Amazon Bedrock AgentCore includes the following modular Services that you can us
 ## 🚀 Amazon Bedrock AgentCore Runtime
 AgentCore Runtime is a secure, serverless runtime purpose-built for deploying and scaling dynamic AI agents and tools using any open-source framework including LangGraph, CrewAI, and Strands Agents, any protocol, and any model. Runtime was built to work for agentic workloads with industry-leading extended runtime support, fast cold starts, true session isolation, built-in identity, and support for multi-modal payloads. Developers can focus on innovation while Amazon Bedrock AgentCore Runtime handles infrastructure and security -- accelerating time-to-market
 
-**[Runtime Quick Start](documentation/docs/user-guide/runtime/quickstart.md)**
+**[Runtime Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/runtime/quickstart.html)**
 
 ## 🧠 Amazon Bedrock AgentCore Memory
 AgentCore Memory makes it easy for developers to build context aware agents by eliminating complex memory infrastructure management while providing full control over what the AI agent remembers. Memory provides industry-leading accuracy along with support for both short-term memory for multi-turn conversations and long-term memory that can be shared across agents and sessions.
 
-**[Memory Quick Start](documentation/docs/user-guide/memory/quickstart.md)**
+**[Memory Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/memory/quickstart.html)**
 
 ## 🔗 Amazon Bedrock AgentCore Gateway
 Amazon Bedrock AgentCore Gateway acts as a managed Model Context Protocol (MCP) server that converts APIs and Lambda functions into MCP tools that agents can use. Gateway manages the complexity of OAuth ingress authorization and secure egress credential exchange, making standing up remote MCP servers easier and more secure. Gateway also offers composition and built-in semantic search over tools, enabling developers to scale their agents to use hundreds or thousands of tools.
 
-**[Gateway Quick Start](documentation/docs/user-guide/gateway/quickstart.md)**
+**[Gateway Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/gateway/quickstart.html)**
 
 ## 💻 Amazon Bedrock AgentCore Code Interpreter
 AgentCore Code Interpreter tool enables agents to securely execute code in isolated sandbox environments. It offers advanced configuration support and seamless integration with popular frameworks. Developers can build powerful agents for complex workflows and data analysis while meeting enterprise security requirements.
 
-**[Code Interpreter Quick Start](documentation/docs/user-guide/builtin-tools/quickstart-code-interpreter.md)**
+**[Code Interpreter Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/builtin-tools/quickstart-code-interpreter.html)**
 
 
 ## 🌐 Amazon Bedrock AgentCore Browser
 AgentCore Browser tool provides a fast, secure, cloud-based browser runtime to enable AI agents to interact with websites at scale. It provides enterprise-grade security, comprehensive observability features, and automatically scales— all without infrastructure management overhead.
 
-**[Browser Quick Start](documentation/docs/user-guide/builtin-tools/quickstart-browser.md)**
+**[Browser Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/builtin-tools/quickstart-browser.html)**
 
 ## 📊 Amazon Bedrock AgentCore Observability
 AgentCore Observability helps developers trace, debug, and monitor agent performance in production through unified operational dashboards. With support for OpenTelemetry compatible telemetry and detailed visualizations of each step of the agent workflow, AgentCore enables developers to easily gain visibility into agent behavior and maintain quality standards at scale.
 
-**[Observability Quick Start](documentation/docs/user-guide/observability/quickstart.md)**
+**[Observability Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/observability/quickstart.html)**
 
 ## 🔐 Amazon Bedrock AgentCore Identity
 AgentCore Identity provides a secure, scalable agent identity and access management capability accelerating AI agent development. It is compatible with existing identity providers, eliminating needs for user migration or rebuilding authentication flows. AgentCore Identity's helps to minimize consent fatigue with a secure token vault and allows you to build streamlined AI agent experiences. Just-enough access and secure permission delegation allow agents to securely access AWS resources and third-party tools and services.
 
-**[Identity Quick Start](documentation/docs/user-guide/identity/quickstart.md)**
+**[Identity Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/identity/quickstart.html)**
+
+## 🔐 Import Amazon Bedrock Agents to Bedrock AgentCore
+AgentCore Import-Agent enables seamless migration of existing Amazon Bedrock Agents to LangChain/LangGraph or Strands frameworks while automatically integrating AgentCore primitives like Memory, Code Interpreter, and Gateway. Developers can migrate agents in minutes with full feature parity and deploy directly to AgentCore Runtime for serverless operation.
+
+**[Import Agent Quick Start](https://aws.github.io/bedrock-agentcore-starter-toolkit/user-guide/import-agent/quickstart.html)**
 
 
 ## ⚠️ Preview Status

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/documentation/docs/user-guide/gateway/quickstart.md

@@ -11,7 +11,7 @@ In the quick start guide you will learn how to set up a Gateway and integrate it
 
 ⚠️ Before starting, make sure you have:
 
-- **AWS Account** with credentials configured (`aws configure`). 
+- **AWS Account** with credentials configured (`aws configure`).
 - **Python 3.10+** installed.
 - **Access to** Anthropic's Sonnet 3.7 (or another model) for running the demo agent below.
 
@@ -40,7 +40,7 @@ client.logger.setLevel(logging.DEBUG)
 ```
 
 ### Creating an OAuth Authorization Server
-🔒 Gateways are secured by OAuth authorization servers which ensure that only allowed users can access your Gateway. Let's create an OAuth authorization server to use with this Gateway. If you already have an OAuth authorization server, you can skip this step. 
+🔒 Gateways are secured by OAuth authorization servers which ensure that only allowed users can access your Gateway. Let's create an OAuth authorization server to use with this Gateway. If you already have an OAuth authorization server, you can skip this step.
 ```python
 # create cognito authorizer
 cognito_response = client.create_oauth_authorizer_with_cognito("TestGateway")
@@ -53,7 +53,7 @@ cognito_response = client.create_oauth_authorizer_with_cognito("TestGateway")
 gateway = client.create_mcp_gateway(
     # the name of the Gateway - if you don't set one, one will be generated.
     name=None,
-    # the role arn that the Gateway will use - if you don't set one, one will be created. 
+    # the role arn that the Gateway will use - if you don't set one, one will be created.
     # NOTE: if you are using your own role make sure it has a trust policy that trusts bedrock-agentcore.amazonaws.com
     role_arn=None,
     # the OAuth authorization server details. If you are providing your own authorization server, then pass an input of the following form: {"customJWTAuthorizer": {"allowedClients": ["<INSERT CLIENT ID>"], "discoveryUrl": "<INSERT DISCOVERY URL">}}
@@ -63,7 +63,7 @@ gateway = client.create_mcp_gateway(
 )
 ```
 
-Now that we have a Gateway set up let's add a target. Targets can be Lambda functions, Open API schemas, or Smithy schemas (another type of API schema). Each Gateway can have multiple targets and each target can have many APIs. 
+Now that we have a Gateway set up let's add a target. Targets can be Lambda functions, Open API schemas, or Smithy schemas (another type of API schema). Each Gateway can have multiple targets and each target can have many APIs.
 
 ### Adding Lambda Targets
 
@@ -90,7 +90,7 @@ lambda_target = client.create_mcp_gateway_target(
 <summary>
 <strong> ➡️ Adding a custom Lambda</strong>
 </summary>
-Each Lambda target needs a schema defining the tools that the Lambda function implements. Your agent will see this schema and will send requests to your Lambda function in this format. You can decide how to implement the code for these tools in your Lambda. 
+Each Lambda target needs a schema defining the tools that the Lambda function implements. Your agent will see this schema and will send requests to your Lambda function in this format. You can decide how to implement the code for these tools in your Lambda.
 
 The schema has the following structure. **⚠️ Note don't forget to fill in the lambdaArn with your function ARN**
 
@@ -201,14 +201,14 @@ def lambda_handler(event, context):
 access_token = client.get_access_token_for_cognito(cognito_response["client_info"])
 ```
 
-🗒️ Copy and paste the below code to set up a simple agent that we can use to test out the Gateway. Note AgentCore Gateway can integrate with any Agent that uses MCP including agents / code not running on AWS. 
+🗒️ Copy and paste the below code to set up a simple agent that we can use to test out the Gateway. Note AgentCore Gateway can integrate with any Agent that uses MCP including agents / code not running on AWS.
 
 ```python
 from strands import Agent
 import logging
 from strands.models import BedrockModel
 from strands.tools.mcp.mcp_client import MCPClient
-from mcp.client.streamable_http import streamablehttp_client 
+from mcp.client.streamable_http import streamablehttp_client
 import os
 
 def create_streamable_http_transport(mcp_url: str, access_token: str):
@@ -224,7 +224,7 @@ def get_full_tools_list(client):
         if tmp_tools.pagination_token is None:
             more_tools = False
         else:
-            more_tools = True 
+            more_tools = True
             pagination_token = tmp_tools.pagination_token
     return tools
 
@@ -233,9 +233,9 @@ def run_agent(mcp_url: str, access_token: str, bedrock_model_id: str):
         inference_profile_id=bedrock_model_id,
         streaming=True,
     )
-     
+
     mcp_client = MCPClient(lambda: create_streamable_http_transport(mcp_url, access_token))
-     
+
     with mcp_client:
         tools = get_full_tools_list(mcp_client)
         print(f"Found the following tools: {[tool.tool_name for tool in tools]}")
@@ -265,7 +265,7 @@ If you're excited and want to learn more about Gateways and the other Target typ
 
 ### Adding OpenAPI Targets
 
-Let's add an OpenAPI target. This code uses the OpenAPI schema for a NASA API that provides Mars weather information. You can get an API key sent to your email in a minute by filling out the form here: https://api.nasa.gov/. 
+Let's add an OpenAPI target. This code uses the OpenAPI schema for a NASA API that provides Mars weather information. You can get an API key sent to your email in a minute by filling out the form here: https://api.nasa.gov/.
 
 **Open API Spec for NASA Mars weather API**
 <div style="max-height: 200px; overflow: auto;">
@@ -551,7 +551,7 @@ Alternatively if you have an API that uses OAuth, set the `credentials` field to
   }
 }
 ```
-There are other supported `oauth_2_provider` types including Microsoft, GitHub, Google, Salesforce, and Slack. For information on the structure of those provider configs see the [identity documentation](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/identity-idps.html). 
+There are other supported `oauth_2_provider` types including Microsoft, GitHub, Google, Salesforce, and Slack. For information on the structure of those provider configs see the [identity documentation](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/identity-idps.html).
 </details>
 
 ### Adding Smithy API Model Targets
@@ -604,10 +604,10 @@ While the Starter Toolkit makes it easy to get started, the Boto3 Python client
 ### Setup
 
 Instantiate the client
-```python 
+```python
 import boto3
 
-boto_client = boto3.client("bedrock-agentcore-control", 
+boto_client = boto3.client("bedrock-agentcore-control",
                            region_name="us-east-1")
 ```
 
@@ -648,17 +648,17 @@ create_gw_request = {
     "clientToken": "string", # optional - used for idempotency
     "roleArn": "string", # required - execution role arn that Gateway will use when interacting with AWS resources
     "protocolType": "string", # required - must be MCP
-    "protocolConfiguration": { # optional 
+    "protocolConfiguration": { # optional
         "mcp": {
             "supportedVersions": ["enum_string"], # optional - e.g. 2025-06-18
             "instructions": "string", # optional - instructions for agents using this MCP server
             "searchType": "enum_string" # optional - must be SEMANTIC if specified. This enables the tool search tool
         }
     },
-    "authorizerType": "string", # required - must be CUSTOM_JWT  
+    "authorizerType": "string", # required - must be CUSTOM_JWT
     "authorizerConfiguration": { # required - the configuration for your authorizer
         "customJWTAuthorizer": { # required the custom JWT authorizer setup
-            "allowedAudience": [], # optional 
+            "allowedAudience": [], # optional
             "allowedClients": [], # optional
             "discoveryUrl": "string" # required - the URL of the authorization server
         },
@@ -677,7 +677,7 @@ example_create_gw_request = {
     "protocolType": "MCP",
     "authorizerType": "CUSTOM_JWT",
     "authorizerConfiguration":  {
-        "customJWTAuthorizer": {  
+        "customJWTAuthorizer": {
             "discoveryUrl": "<INSERT DISCOVERY URL e.g. https://cognito-idp.{region}.amazonaws.com/{user_pool_id}/.well-known/openid-configuration>",
             "allowedClients": ["<INSERT CLIENT ID>"]
         }
@@ -701,17 +701,17 @@ update_gw_request = {
     "description": "string", # optional - description of your gateway
     "roleArn": "string", # required - execution role arn that Gateway will use when interacting with AWS resources
     "protocolType": "string", # required - must be MCP
-    "protocolConfiguration": { # optional 
+    "protocolConfiguration": { # optional
         "mcp": {
             "supportedVersions": ["enum_string"], # optional - e.g. 2025-06-18
             "instructions": "string", # optional - instructions for agents using this MCP server
             "searchType": "enum_string" # optional - must be SEMANTIC if specified. This enables the tool search tool
         }
     },
-    "authorizerType": "string", # required - must be CUSTOM_JWT  
+    "authorizerType": "string", # required - must be CUSTOM_JWT
     "authorizerConfiguration": { # required - the configuration for your authorizer
         "customJWTAuthorizer": { # required the custom JWT authorizer setup
-            "allowedAudience": [], # optional 
+            "allowedAudience": [], # optional
             "allowedClients": [], # optional
             "discoveryUrl": "string" # required - the URL of the authorization server
         },
@@ -730,7 +730,7 @@ example_update_gw_request = {
     "protocolType": "MCP",
     "authorizerType": "CUSTOM_JWT",
     "authorizerConfiguration":  {
-        "customJWTAuthorizer": {  
+        "customJWTAuthorizer": {
             "discoveryUrl": "<INSERT DISCOVERY URL e.g. https://cognito-idp.{region}.amazonaws.com/{user_pool_id}/.well-known/openid-configuration>",
             "allowedClients": ["<INSERT CLIENT ID>"]
         }
@@ -774,7 +774,7 @@ create_target_request = {
             },
             "lambda": {
                 "lambdaArn": "string",
-                "toolSchema": { # union - choose one of either s3 or inlinePayload 
+                "toolSchema": { # union - choose one of either s3 or inlinePayload
                     "s3": {
                         "uri": "string",
                         "bucketOwnerAccountId": "string"
@@ -865,7 +865,7 @@ update_target_request = {
             },
             "lambda": {
                 "lambdaArn": "string",
-                "toolSchema": { # union - choose one of either s3 or inlinePayload 
+                "toolSchema": { # union - choose one of either s3 or inlinePayload
                     "s3": {
                         "uri": "string",
                         "bucketOwnerAccountId": "string"
@@ -946,4 +946,3 @@ delete_target_response = boto_client.delete_gateway_target(
 )
 ```
 </details>
-

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/documentation/docs/user-guide/observability/quickstart.md

@@ -30,19 +30,19 @@ AgentCore Observability offers two ways to configure monitoring to match differe
 
 ## Enabling Observability for AgentCore-Hosted Agents
 
-AgentCore Runtime-hosted agents are deployed and executed directly within the AgentCore environment, providing automatic instrumentation with minimal configuration. This approach offers the fastest path to deployment and is ideal for rapid development and testing. 
+AgentCore Runtime-hosted agents are deployed and executed directly within the AgentCore environment, providing automatic instrumentation with minimal configuration. This approach offers the fastest path to deployment and is ideal for rapid development and testing.
 
 For a complete example please refer to this [notebook](https://github.com/awslabs/amazon-bedrock-agentcore-samples/blob/main/01-tutorials/06-AgentCore-observability/01-Agentcore-runtime-hosted/runtime_with_strands_and_bedrock_models.ipynb)
 
 ### Step 1 : Create your Agent, shown below is an example with Strands Agents SDK:
 
-To enable OTEL exporting, please note to install [Strands Agents](https://strandsagents.com/latest/) with otel extra dependencies: 
+To enable OTEL exporting, please note to install [Strands Agents](https://strandsagents.com/latest/) with otel extra dependencies:
 
-```bash 
+```bash
 pip install 'strands-agents[otel]'
 ```
 
-Highlighted below are the steps to host a strands agent on AgentCore Runtime to get started: 
+Highlighted below are the steps to host a strands agent on AgentCore Runtime to get started:
 
 ```python
 ##  Save this as strands_claude.py
@@ -55,7 +55,7 @@ from strands.models import BedrockModel
 
 app = BedrockAgentCoreApp()
 
-# Create a custom tool 
+# Create a custom tool
 @tool
 def weather():
     """ Get weather """ # Dummy implementation
@@ -88,9 +88,9 @@ if __name__ == "__main__":
 
 ### Step 2 : Deploy and invoke your Agent on AgentCore Runtime
 
-Now that you created an agent ready to be hosted on AgentCore runtime, you can easily deploy it using the `bedrock_agentcore_starter_toolkit` package as shown below : 
+Now that you created an agent ready to be hosted on AgentCore runtime, you can easily deploy it using the `bedrock_agentcore_starter_toolkit` package as shown below :
 
-```python 
+```python
 from bedrock_agentcore_starter_toolkit import Runtime
 from boto3.session import Session
 boto_session = Session()
@@ -99,7 +99,7 @@ region = boto_session.region_name
 agentcore_runtime = Runtime()
 agent_name = "strands_claude_getting_started"
 response = agentcore_runtime.configure(
-    entrypoint="strands_claude.py", # file created in Step 1  
+    entrypoint="strands_claude.py", # file created in Step 1
     auto_create_execution_role=True,
     auto_create_ecr=True,
     requirements_file="requirements.txt", # ensure aws-opentelemetry-distro exists along with your libraries required to run your agent
@@ -111,7 +111,7 @@ launch_result = agentcore_runtime.launch()
 launch_result
 ```
 
-In these simple steps you deployed your strands agent on runtime with the Bedrock agentcore starter toolkit that automaticcally instruments your agent invocation using Open Telemetry. Now, you can invoke your agent using the command shown below and see the Traces, sessions and metrics on GenAI Obsrvability dashboard on Amazon Cloudwatch. 
+In these simple steps you deployed your strands agent on runtime with the Bedrock agentcore starter toolkit that automaticcally instruments your agent invocation using Open Telemetry. Now, you can invoke your agent using the command shown below and see the Traces, sessions and metrics on GenAI Obsrvability dashboard on Amazon Cloudwatch.
 
 ```python
 invoke_response = agentcore_runtime.invoke({"prompt": "How is the weather now?"})
@@ -120,7 +120,7 @@ invoke_response
 
 ## Enabling Observability for Non-AgentCore-Hosted Agents
 
-For agents running outside of the AgentCore runtime, deliver the same monitoring capabilities for agents deployed on your own infrastructure, allowing consistent observability regardless of where your agents run. Additionally, you would need to  follow the steps below to configure the environment variables needed to observe your agents. 
+For agents running outside of the AgentCore runtime, deliver the same monitoring capabilities for agents deployed on your own infrastructure, allowing consistent observability regardless of where your agents run. Additionally, you would need to  follow the steps below to configure the environment variables needed to observe your agents.
 
 For a complete example please refer to this [notebook](https://github.com/awslabs/amazon-bedrock-agentcore-samples/blob/main/01-tutorials/06-AgentCore-observability/02-Agent-not-hosted-on-runtime/Strands/Strands_Observability.ipynb)
 
@@ -134,7 +134,7 @@ export AWS_ACCESS_KEY_ID=<access key id>
 export AWS_SECRET_ACCESS_KEY=<secret key>
 ```
 
-### Step 2: Configure CloudWatch logging: 
+### Step 2: Configure CloudWatch logging:
 
 Create a log group and log stream for your agent in Amazon CloudWatch which you can use to configure below environment variables.
 
@@ -142,18 +142,18 @@ Create a log group and log stream for your agent in Amazon CloudWatch which you
 
 ```bash
 export AGENT_OBSERVABILITY_ENABLED=true # Activates the ADOT pipeline
-export OTEL_PYTHON_DISTRO=aws_distro # Uses AWS Distro for OpenTelemetry 
+export OTEL_PYTHON_DISTRO=aws_distro # Uses AWS Distro for OpenTelemetry
 export OTEL_PYTHON_CONFIGURATOR=aws_configurator # Sets AWS configurator for ADOT SDK
 export OTEL_EXPORTER_OTLP_PROTOCOL=http/protobuf # Configures export protocol
 export  OTEL_EXPORTER_OTLP_LOGS_HEADERS=x-aws-log-group=<YOUR-LOG-GROUP>,x-aws-log-stream=<YOUR-LOG-STREAM>,x-aws- metric-namespace=<YOUR-NAMESPACE>
-# Directs logs to CloudWatch groups 
+# Directs logs to CloudWatch groups
 export OTEL_RESOURCE_ATTRIBUTES=service.name=<YOUR-AGENT-NAME> # Identifies your agent in observability data
 ```
 
 Replace `<YOUR-AGENT-NAME>` with a unique name to identify this agent in the GenAI Observability dashboard and logs.
 
 
-### Step 4: Create an agent locally 
+### Step 4: Create an agent locally
 
 ```python
 # Create agent.py -  Strands agent that is a weather assistant
@@ -199,7 +199,7 @@ With aws-opetelemetry-distro in your requirements.txt, `opentelemetry-instrument
 - Send traces to CloudWatch
 - Enable you to visualize the agent's decision-making process in the GenAI Observability dashboard
 
-```bash 
+```bash
 opentelemetry-instrument python agent.py
 ```
 
@@ -222,14 +222,14 @@ opentelemetry-instrument python strands_travel_agent_with_session.py --session-i
 
 After implementing observability, you can view the collected data in CloudWatch:
 
-## Bedrock AgentCore Overview on GenAI Observability dashboard 
+## Bedrock AgentCore Overview on GenAI Observability dashboard
 
 1. Open the [GenAI Observability on CloudWatch console](https://console.aws.amazon.com/cloudwatch/home#gen-ai-observability)
 2. You are able to view the data related to model invocations and agents on Bedrock AgentCore on the dashboard.
-3. In the Bedrock Agentcore tab you are able to see Agents View, Sessions View and Traces View. 
+3. In the Bedrock Agentcore tab you are able to see Agents View, Sessions View and Traces View.
 4. Agents View lists all your Agents that are on and not on runtime, you can also click on the agent and view further details like runtime metrics, sessions and traces specific to an agent.
 5. In the Sessions View tab, you can navigate across all the sessions associated with agents.
-6. In the Trace View tab, you can look into the traces and span information for agents. Also explore the trace trajectory and timeline by clicking on a trace. 
+6. In the Trace View tab, you can look into the traces and span information for agents. Also explore the trace trajectory and timeline by clicking on a trace.
 
 
 ### View Logs in CloudWatch

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/documentation/docs/user-guide/runtime/permissions.md

@@ -243,7 +243,7 @@ The toolkit uses AWS CodeBuild for ARM64 container builds, especially useful in
 The Runtime Execution Role is an IAM role that AgentCore Runtime assumes to run an agent. Replace the following:
 
 - `region` with the AWS Region that you are using
-- `accountId` with your AWS account ID  
+- `accountId` with your AWS account ID
 - `agentName` with the name of your agent. You'll need to decide the agent name before creating the role and AgentCore Runtime.
 
 ### Permissions Policy

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "bedrock-agentcore-starter-toolkit"
-version = "0.1.7"
+version = "0.1.9"
 description = "A starter toolkit for using Bedrock AgentCore"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -28,7 +28,7 @@ classifiers = [
 dependencies = [
     "boto3>=1.39.7",
     "botocore>=1.39.7",
-    "bedrock-agentcore>=0.1.2",
+    "bedrock-agentcore>=0.1.3",
     "docstring_parser>=0.15,<1.0",
     "httpx>=0.28.1",
     "jinja2>=3.1.6",
@@ -165,5 +165,5 @@ dev = [
     "mkdocs~=1.6.1",
     "mkdocs-macros-plugin~=1.3.7",
     "mkdocs-material~=9.6.12",
-    "mkdocstrings-python~=1.16.10",
+    "mkdocstrings-python>=1.16.10,<1.18.0",
 ]

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/src/bedrock_agentcore_starter_toolkit/cli/cli.py

@@ -16,7 +16,6 @@ setup_toolkit_logging(mode="cli")
 app.command("invoke")(invoke)
 app.command("status")(status)
 app.command("launch")(launch)
-app.command("import-agent")(import_agent)
 app.add_typer(configure_app)
 
 # gateway
@@ -24,6 +23,9 @@ app.command("create_mcp_gateway")(create_mcp_gateway)
 app.command("create_mcp_gateway_target")(create_mcp_gateway_target)
 app.add_typer(gateway_app, name="gateway")
 
+# import-agent
+app.command("import-agent")(import_agent)
+
 
 def main():
     """Entry point for the CLI application."""

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/src/bedrock_agentcore_starter_toolkit/operations/gateway/client.py

@@ -84,7 +84,7 @@ class GatewayClient:
             "protocolType": "MCP",
             "authorizerType": "CUSTOM_JWT",
             "authorizerConfiguration": authorizer_config,
-            "exceptionLevel": "DEBUG"
+            "exceptionLevel": "DEBUG",
         }
         if enable_semantic_search:
             create_request["protocolConfiguration"] = {"mcp": {"searchType": "SEMANTIC"}}

{bedrock_agentcore_starter_toolkit-0.1.7 → bedrock_agentcore_starter_toolkit-0.1.9}/src/bedrock_agentcore_starter_toolkit/operations/gateway/create_role.py

@@ -73,18 +73,59 @@ def _attach_policy(
     :param policy_name: the policy name (if not using a policy_arn).
     :return:
     """
-    if policy_arn and policy_document:
-        raise Exception("Cannot specify both policy arn and policy document.")
+    # Check for invalid combinations of parameters
+    if policy_arn:
+        if policy_document or policy_name:
+            raise Exception("Cannot specify both policy arn and policy document/name")
+    elif not (policy_document and policy_name):
+        raise Exception("Must specify both policy document and policy name, or just a policy arn")
+
     try:
-        if policy_arn:
-            iam_client.attach_role_policy(RoleName=role_name, PolicyArn=policy_arn)
-        elif policy_document and policy_name:
-            policy = iam_client.create_policy(
-                PolicyName=policy_name,
-                PolicyDocument=policy_document,
-            )
-            iam_client.attach_role_policy(RoleName=role_name, PolicyArn=policy["Policy"]["Arn"])
-        else:
-            raise Exception("Must specify both policy document and policy name or just a policy arn")
+        if policy_document and policy_name:
+            policy_arn = _try_create_policy(iam_client, policy_name, policy_document)
+        iam_client.attach_role_policy(RoleName=role_name, PolicyArn=policy_arn)
     except ClientError as e:
         raise RuntimeError(f"Failed to attach AgentCore policy: {e}") from e
+    
+def _try_create_policy(
+    iam_client: BaseClient, 
+    policy_name: str, 
+    policy_document: str
+) -> str:
+    """Try to create a new policy, or return the arn if the policy already exists.
+
+    :param iam_client: the IAM client to use.
+    :param policy_name: the name of the policy to create.
+    :param policy_document: the policy document to create.
+    :return: the arn of the policy.
+    """
+    try:
+        policy = iam_client.create_policy(
+            PolicyName=policy_name,
+            PolicyDocument=policy_document,
+        )
+        return policy["Policy"]["Arn"]
+    except ClientError as e:
+        if e.response["Error"]["Code"] == "EntityAlreadyExists":
+            return _get_existing_policy_arn(iam_client, policy_name)
+        else:
+            raise e
+        
+def _get_existing_policy_arn(
+    iam_client: BaseClient, 
+    policy_name: str
+) -> str:
+    """Get the arn of an existing policy.
+
+    :param iam_client: the IAM client to use.
+    :param policy_name: the name of the policy to get.
+    :return: the arn of the policy.
+    """
+    paginator = iam_client.get_paginator("list_policies")
+    try:
+        for page in paginator.paginate(Scope="Local"):
+            for policy in page["Policies"]:
+                if policy["PolicyName"] == policy_name:
+                    return policy["Arn"]
+    except ClientError as e:
+        raise RuntimeError(f"Failed to get existing policy arn: {e}") from e