AWS bedrock-agentcore documentation change
Summary
Formatting and structural changes including typographical fixes (e.g., straight quotes to curly quotes), restructuring of numbered lists, reformatting of the shared responsibility model table, and minor text corrections.
Security assessment
The changes are primarily typographical and structural, with no mention of a specific security vulnerability, weakness, or incident. The shared responsibility model section is reformatted but does not introduce new security information. The note about file permissions (644/755) is reformatted but not changed in substance.
Diff
diff --git a/bedrock-agentcore/latest/devguide/runtime-get-started-code-deploy.md b/bedrock-agentcore/latest/devguide/runtime-get-started-code-deploy.md index 0249a3cfb..8bd1fb31f 100644 --- a//bedrock-agentcore/latest/devguide/runtime-get-started-code-deploy.md +++ b//bedrock-agentcore/latest/devguide/runtime-get-started-code-deploy.md @@ -11 +11 @@ Direct code deployment enables you to bring your Python-based agent to Amazon Be -To create your deployment package as .zip file archive, you can use [AgentCore CLI](https://github.com/aws/agentcore-cli) or follow the steps in the _Custom zip + boto3_ tab below, or any other .zip file utility such as [7zip](https://www.7-zip.org/download.html). The examples shown in the following sections assume you're using a command-line `zip` tool in a Linux or MacOS environment. To use the same commands in Windows, you can [install the Windows Subsystem for Linux](https://docs.microsoft.com/en-us/windows/wsl/install-win10) to get a Windows-integrated version of Ubuntu and Bash. +To create your deployment package as .zip file archive, you can use [AgentCore CLI](https://github.com/aws/agentcore-cli) or follow the steps in the _Custom zip + boto3_ tab below, or any other .zip file utility such as [7zip](https://www.7-zip.org/download.html) . The examples shown in the following sections assume you’re using a command-line `zip` tool in a Linux or MacOS environment. To use the same commands in Windows, you can [install the Windows Subsystem for Linux](https://docs.microsoft.com/en-us/windows/wsl/install-win10) to get a Windows-integrated version of Ubuntu and Bash. @@ -44 +44 @@ Before you start, make sure you have: - * [**Uv**](https://docs.astral.sh/uv/getting-started/installation/) **installed** and [**Python 3.10+**](https://docs.astral.sh/uv/guides/install-python/) installed + * [Uv](https://docs.astral.sh/uv/getting-started/installation/) **installed** and [Python 3.10+](https://docs.astral.sh/uv/guides/install-python/) installed @@ -135 +135 @@ Test your agent by opening another terminal window and enter the following comma -**Success:** You should see a response like `{"result": "Hello! I'm here to help..."}`. In the terminal window that's running the agent, enter `Ctrl+C` to stop the agent. +**Success:** You should see a response like `{"result": "Hello! I’m here to help…"}` . In the terminal window that’s running the agent, enter `Ctrl+C` to stop the agent. @@ -144,0 +145,2 @@ Deploy your agent using one of the following methods: +###### Example + @@ -148 +150 @@ AgentCore CLI -The following steps will be required to deploy an agent to AgentCore Runtime, refer to [Get started with the AgentCore CLI](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-get-started-cli.html), for detailed steps. If Uv is available, the AgentCore CLI will recommend direct code deployment. Otherwise it will default to container deployment type. + 1. The following steps will be required to deploy an agent to AgentCore Runtime, refer to [Get started with the AgentCore CLI](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-get-started-cli.html) , for detailed steps. If Uv is available, the AgentCore CLI will recommend direct code deployment. Otherwise it will default to container deployment type. @@ -155,2 +156 @@ Once you have your agent set up using `agentcore create`, use the `deploy` comma -Let's prompt the agent to tell a joke! - +Let’s prompt the agent to tell a joke! @@ -162 +162 @@ The first deployment takes time to install dependencies but subsequent updates t -###### Configuration management +**Configuration management** @@ -171 +174 @@ Interactive -Run `agentcore` to open the TUI, then select **deploy**. The deploy screen shows real-time progress as it validates your project, synthesizes CloudFormation, and provisions AWS resources: + 1. Run `agentcore` to open the TUI, then select **deploy** . The deploy screen shows real-time progress as it validates your project, synthesizes CloudFormation, and provisions AWS resources: @@ -177 +179,0 @@ After deployment completes, use `agentcore invoke` to test your agent. -Custom zip + boto3 @@ -180 +182,2 @@ Custom zip + boto3 -To download a wheel that's compatible with AgentCore Runtime, you use the uv pip `--python-platform` option. AgentCore Runtime only supports **arm64** instruction set architecture, run the following command. Replace `--python 3.x` with the version of the Python runtime you are using. + +Custom zip + boto3 @@ -182,0 +186,2 @@ To download a wheel that's compatible with AgentCore Runtime, you use the uv pip + 1. To download a wheel that’s compatible with AgentCore Runtime, you use the uv pip `--python-platform` option. AgentCore Runtime only supports **arm64** instruction set architecture, run the following command. Replace `--python 3.x` with the version of the Python runtime you are using. + @@ -206,10 +209 @@ After you have created your .zip deployment package, you can use it to create a - 1. The maximum size for a .zip deployment package for AgentCore Runtime is 250 MB (zipped) and 750 MB (unzipped). Note that this limit applies to the combined size of all the files you upload. - - 2. The AgentCore Runtime needs permission to read the files in your deployment package. In Linux permissions octal notation, AgentCore Runtime needs 644 permissions for non-executable files (rw-r—r--) and 755 permissions (rwxr-xr-x) for directories and executable files. - - 3. In Linux and MacOS, use the `chmod` command to change file permissions on files and directories in your deployment package. For example, to give a non-executable file the correct permissions, run the following command, `chmod 644 <filepath>`. To change file permissions in Windows, see [Set, View, Change, or Remove Permissions on an Object](https://learn.microsoft.com/en-us/previous-versions/windows/it-pro/windows-server-2008-R2-and-2008/cc731667\(v=ws.10\)) in the Microsoft Windows documentation. - - 1. If you don't grant AgentCore Runtime the permissions it needs to access directories in your deployment package, AgentCore Runtime sets the permissions for those directories to 755 (rwxr-xr-x). - - - +. The maximum size for a .zip deployment package for AgentCore Runtime is 250 MB (zipped) and 750 MB (unzipped). Note that this limit applies to the combined size of all the files you upload. . The AgentCore Runtime needs permission to read the files in your deployment package. In Linux permissions octal notation, AgentCore Runtime needs 644 permissions for non-executable files (rw-r—r--) and 755 permissions (rwxr-xr-x) for directories and executable files. . In Linux and MacOS, use the `chmod` command to change file permissions on files and directories in your deployment package. For example, to give a non-executable file the correct permissions, run the following command, `chmod 644 <filepath>` . To change file permissions in Windows, see [Set, View, Change, or Remove Permissions on an Object](https://learn.microsoft.com/en-us/previous-versions/windows/it-pro/windows-server-2008-R2-and-2008/cc731667\(v=ws.10\)) in the Microsoft Windows documentation. + .. If you don’t grant AgentCore Runtime the permissions it needs to access directories in your deployment package, AgentCore Runtime sets the permissions for those directories to 755 (rwxr-xr-x). @@ -267 +263 @@ console -You can deploy your agent using the Amazon Bedrock AgentCore console with managed runtime support. The console provides an intuitive interface for uploading ZIP files and configuring agent settings. + 1. You can deploy your agent using the Amazon Bedrock AgentCore console with managed runtime support. The console provides an intuitive interface for uploading ZIP files and configuring agent settings. @@ -271 +267 @@ To deploy using the console, first create your deployment package following the -###### Create agent through console +**Create agent through console** @@ -275 +271 @@ To create your agent: - 1. From the Agents home page, click **Host Agent** + 2. From the Agents home page, click **Host Agent** @@ -277 +273 @@ To create your agent: - 2. Choose your source selection: + 3. Choose your source selection: @@ -285 +281 @@ To create your agent: - 3. Configure your agent settings: + 4. Configure your agent settings: @@ -295,3 +291 @@ To create your agent: - 4. Click **Create Agent** to deploy - - + 5. Click **Create Agent** to deploy @@ -299,2 +293 @@ To create your agent: - -###### Create endpoint +**Create endpoint** @@ -304 +297 @@ Click **Create Endpoint** to create a new endpoint for your agent. The endpoint -###### Test endpoint +**Test endpoint** @@ -308 +301 @@ Select an endpoint and click **Test Endpoint** to navigate to the Playground/San -###### Execution role requirements +**Execution role requirements** @@ -316 +312 @@ Stop your runtime session, update, or cleanup your agent using one of the follow -AgentCore CLI +###### Example @@ -317,0 +314 @@ AgentCore CLI +AgentCore CLI @@ -319 +315,0 @@ AgentCore CLI -To update previously deployed AgentCore Runtime, execute: @@ -320,0 +317 @@ To update previously deployed AgentCore Runtime, execute: + 1. To update previously deployed AgentCore Runtime, execute: @@ -332 +327,0 @@ To delete all resources related to a AgentCore Runtime, first remove all resourc -boto3 @@ -335 +330,2 @@ boto3 -Following boto3 code will update an AgentCore Runtime. + +boto3 @@ -337,0 +334,2 @@ Following boto3 code will update an AgentCore Runtime. + 1. Following boto3 code will update an AgentCore Runtime. + @@ -417 +416 @@ console -###### Update agent + 1. ====== Update agent @@ -421 +420 @@ From the Agent details page, click **Update hosting** to create a new version wi -###### Update endpoint +**Update endpoint** @@ -425 +424 @@ Select an endpoint from the Endpoints table and click **Edit** to update the des -###### Delete endpoint +**Delete endpoint** @@ -427 +426 @@ Select an endpoint from the Endpoints table and click **Edit** to update the des -Select an endpoint and click **Delete**. You'll need to type "delete" to confirm the deletion. +Select an endpoint and click **Delete** . You’ll need to type "delete" to confirm the deletion. @@ -429 +428 @@ Select an endpoint and click **Delete**. You'll need to type "delete" to confirm -###### Delete agent +**Delete agent** @@ -444 +446 @@ Amazon Bedrock AgentCore Runtime with direct code deployment uses a shared respo -If you're using [container images to deploy your agents](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/getting-started-custom.html), then AgentCore Runtime is responsible to patch only compute kernel. In this case, you're responsible for rebuilding your agent's container image from the latest secure image and redeploying the container image. +If you’re using [container images to deploy your agents](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/getting-started-custom.html) , then AgentCore Runtime is responsible to patch only compute kernel. In this case, you’re responsible for rebuilding your agent’s container image from the latest secure image and redeploying the container image. @@ -448 +450 @@ This is summarized in the following table: -Shared responsibility model Deployment mode | AgentCore Runtime's responsibility | Your responsibility +Deployment mode | AgentCore Runtime’s responsibility | Your responsibility @@ -450,20 +452,2 @@ Shared responsibility model Deployment mode | AgentCore Runtime's responsibility -Direct deploy mode | - - 1. Publish new language runtime version containing the latest patches for language runtime. - 2. Apply language runtime patches to existing AgentCore Runtime direct deploy. - -| - - 1. Update your agent code, including dependencies, to address any security vulnerabilities. - - -Container image | - - 1. Automatically patch underlying compute OS kernel with latest version. - -| - - 1. Update your agent code, including dependencies, to address any security vulnerabilities. - 2. Regularly re-build and re-deploy your container image using the latest base image. - - +Direct deploy mode | Publish new language runtime version containing the latest patches for language runtime. Apply language runtime patches to existing AgentCore Runtime direct deploy. | Update your agent code, including dependencies, to address any security vulnerabilities. +Container image | Automatically patch underlying compute OS kernel with latest version. | Update your agent code, including dependencies, to address any security vulnerabilities. Regularly re-build and re-deploy your container image using the latest base image. @@ -475 +459 @@ AgentCore Runtime keeps each direct code deploy runtime up to date with security -For direct deploy runtimes, AgentCore Runtime applies runtime updates automatically. With automatic runtime updates, AgentCore Runtime takes on the operational burden of patching the runtime versions. For most customers, this should be a safe choice as only language runtime patches will be automatically applied and customers are responsible to bring and managed their code dependencies. Currently AgentCore Runtime doesn't support changing this automated patching behavior. +For direct deploy runtimes, AgentCore Runtime applies runtime updates automatically. With automatic runtime updates, AgentCore Runtime takes on the operational burden of patching the runtime versions. For most customers, this should be a safe choice as only language runtime patches will be automatically applied and customers are responsible to bring and managed their code dependencies. Currently AgentCore Runtime doesn’t support changing this automated patching behavior. @@ -479 +463 @@ AgentCore Runtime strives to provide runtime updates that are backward compatibl -The following table lists the supported AgentCore Runtime direct code deploy language runtimes and projected deprecation dates. After a language environment is deprecated, you're still able to create and update functions for a limited period. The table provides the currently forecasted dates for runtime deprecation, based on our [Runtime deprecation policy](https://docs.aws.amazon.com/lambda/latest/dg/lambda-runtimes.html#runtime-support-policy). These dates are provided for planning purposes and are subject to change. +The following table lists the supported AgentCore Runtime direct code deploy language runtimes and projected deprecation dates. After a language environment is deprecated, you’re still able to create and update functions for a limited period. The table provides the currently forecasted dates for runtime deprecation, based on our [Runtime deprecation policy](https://docs.aws.amazon.com/lambda/latest/dg/lambda-runtimes.html#runtime-support-policy) . These dates are provided for planning purposes and are subject to change. @@ -481 +465 @@ The following table lists the supported AgentCore Runtime direct code deploy lan -Supported runtimes # | Name | Identifier | Operating system | Deprecation date | Block function update +# | Name | Identifier | Operating system | Deprecation date | Block function update @@ -489 +473 @@ Supported runtimes # | Name | Identifier | Operating system | Deprecation date | -#### Language environment deprecation policy +==== Language environment deprecation policy @@ -497 +481 @@ After a runtime is deprecated, AWS may no longer apply security patches or updat -AgentCore Runtime occasionally delays deprecation of a AgentCore Runtime direct code deploy programming language runtime for a limited period beyond the end of support date of the language version that the runtime supports. During this period, AgentCore Runtime only applies security patches to the runtime OS. AgentCore Runtime doesn't apply security patches to programming language runtimes after they reach their end of support date. +AgentCore Runtime occasionally delays deprecation of a AgentCore Runtime direct code deploy programming language runtime for a limited period beyond the end of support date of the language version that the runtime supports. During this period, AgentCore Runtime only applies security patches to the runtime OS. AgentCore Runtime doesn’t apply security patches to programming language runtimes after they reach their end of support date. @@ -539 +523 @@ You can also add dependencies in a separate folder inside your .zip package. For -We recommend that you don't include `__pycache__` folders in your agent's deployment package. Python bytecode that's compiled on a build machine with a different architecture or operating system might not be compatible with the AgentCore Runtime execution environment. +We recommend that you don’t include ` _pycache_ ` folders in your agent’s deployment package. Python bytecode that’s compiled on a build machine with a different architecture or operating system might not be compatible with the AgentCore Runtime execution environment. @@ -541 +525 @@ We recommend that you don't include `__pycache__` folders in your agent's deploy -If your function uses only pure Python packages and modules, you can use the `uv pip install` command to install your dependencies on any local build machine and create your .zip file. Many popular Python libraries, including NumPy and Pandas, are not pure Python and contain code written in C or C++. When you add libraries containing C/C++ code to your deployment package, you must build your package correctly to make it compatible with the AgentCore Runtime execution environment. +If your function uses only pure Python packages and modules, you can use the `uv pip install` command to install your dependencies on any local build machine and create your .zip file. Many popular Python libraries, including NumPy and Pandas, are not pure Python and contain code written in C or C. When you add libraries containing C/C code to your deployment package, you must build your package correctly to make it compatible with the AgentCore Runtime execution environment. @@ -616 +600 @@ Common issues and solutions when getting started with Amazon Bedrock AgentCore d -**Why this happens:** The uploaded ZIP file contains binaries compiled for wrong architecture (ARM64 vs x86_64), incompatible Python version, or incorrect package structure that doesn't match AgentCore Runtime requirements. +**Why this happens:** The uploaded ZIP file contains binaries compiled for wrong architecture (ARM64 vs x86_64), incompatible Python version, or incorrect package structure that doesn’t match AgentCore Runtime requirements.