docs(sensei): clarify Bedrock ambient identity only applies on AWS - #15889
Merged
Conversation
The AI Model Settings page says to leave the AWS keys blank to use the engine's ambient identity, but that only yields credentials when the Sensei engine runs inside AWS with an attached role. Spell out the per-runtime story (EKS IRSA/Pod Identity, ECS task role, EC2 instance profile — incl. the IMDSv2 hop-limit=2 gotcha for containers, Lambda), and add a callout that on-prem / non-AWS deployments (non-EKS k8s, Docker Compose in a data center) have no ambient identity and must enter static keys. Companion to the dojo-pro AI Model Settings change.
blakeaowens
approved these changes
Sep 9, 2026
devGregA
approved these changes
Sep 9, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
[sc-15209]
Description
Clarify the Amazon Bedrock "ambient AWS identity" guidance on the Sensei → AI Model Settings docs page.
The page tells operators to leave the AWS keys blank to use the engine's ambient identity, but that only yields credentials when the Sensei engine actually runs inside AWS with an attached role. This makes the per-runtime story explicit and adds a callout for on-prem / non-AWS deployments, so a self-hosted operator isn't left thinking Bedrock will "just work" without keys.
What changed (
docs/content/sensei/ai_model_settings.md)1blocks a metadata request from inside a container, so it must be set to2.Docs-only. Renders as plain Markdown (a blockquote callout — no custom shortcode), companion to the Pro AI Model Settings change that surfaces the same guidance in the UI.
🤖 Generated with Claude Code