docs: Serverless Workers on AgentCore Runtime - #5289
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
📖 Docs PR preview links
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4f8ea81475
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| | AWS Lambda | Temporal assumes an IAM role in your AWS account to invoke a Lambda function. | | ||
| | GCP Cloud Run | Temporal scales a Cloud Run [Worker Pool](https://cloud.google.com/run/docs/resource-model#worker-pools) through the Cloud Run admin API. A Worker Pool is its own Cloud Run resource type, distinct from a Service or a Job. | | ||
| | Provider | Description | | ||
| | ------------------------------ | ----------- | |
There was a problem hiding this comment.
Adding AgentCore as the third provider here leaves docs/evaluate/features/serverless-workers/index.mdx describing and listing only AWS Lambda and GCP Cloud Run in its introduction, lifecycle comparison, supported-provider table, and SDK table; this page’s autoscaling index at lines 151-154 also still links only those two providers. Update those summaries and tables so readers entering through the Evaluate page or autoscaling section can discover the new AgentCore support.
AGENTS.md reference: AGENTS.md:L237-L243
Useful? React with 👍 / 👎.
| capacity, it invokes an AgentCore Runtime endpoint. The Runtime starts a Worker, which connects to the Temporal Service | ||
| and polls its Task Queue. | ||
|
|
||
| ## How Temporal and AgentCore work together {/* #how-temporal-and-agentcore-work-together */} |
There was a problem hiding this comment.
@bchav i expect we will use this table in customer calls, so it would be good to add more detail on some of the agent core features that the harness can control today, like Memory and code interpreter, where the ID can be orchestrated from the harness and decoupled from the runtime session ID, and therefore not affected by our current worker <> runtime session affinity issues.
lets meet to bottom out on the technical aspects of this to ensure we are not missing any value prop today.
…less-workers # Conflicts: # docs/develop/python/workers/serverless-workers/index.mdx # docs/encyclopedia/workers/serverless-workers/index.mdx # docs/evaluate/features/serverless-workers/index.mdx # docs/production-deployment/worker-deployments/serverless-workers/index.mdx
…s' into docs/agentcore-serverless-workers # Conflicts: # docs/production-deployment/worker-deployments/serverless-workers/index.mdx
| @@ -0,0 +1,280 @@ | |||
| --- | |||
| id: agentcore | |||
| title: Serverless Workers on Amazon Bedrock AgentCore Runtime - Python SDK | |||
There was a problem hiding this comment.
| title: Serverless Workers on Amazon Bedrock AgentCore Runtime - Python SDK | |
| title: Serverless Workers on Amazon Bedrock AgentCore Runtime |
There was a problem hiding this comment.
It's fine in light mode, but I was wondering if we have a light version of this too.
3 participants
What changed
Validation
yarn buildvale --config .vale-ci.inion all changed documentation filesyarn check:orphansThe full-repository link check also ran. It encountered unrelated existing external-link and JavaScript parser failures. The new page internal links and anchors pass.