feat(sdk): recommend vetted Bedrock models by default in Workflow Insight#720
Merged
Conversation
…ight
Surfaces a curated set of Bedrock models as suggestions in the Settings model
picker, shown by default before/without fetching the full account list, so users
land on a model that reliably handles the extension's query-generation task.
- New RECOMMENDED_BEDROCK_MODELS list (Claude Sonnet 5 [default], Sonnet 4.5,
Haiku 4.5, Opus 4.5, and Amazon Nova Pro), each with a short description.
- The Bedrock Model ID Autosuggest now shows a "Recommended" group by default;
clicking "List available models" adds an "All available in your account"
group with the recommended entries pinned on top. Free-text entry still works.
- Helper text updated to explain the recommended-by-default behavior.
Curation is evidence-based: the models were benchmarked on the real agent-mode
task ("count of executions grouped by productName and customerName in execution
input") against real data on BOTH the Aurora (PostgreSQL) and S3/Athena (Trino)
destinations. The listed models discovered the correct JSON keys and produced
correct multi-dimension grouped SQL in both dialects. Models that only did well
on one dialect (e.g. Mistral Pixtral Large — correct on Aurora but produced no
aggregation on Athena) or couldn't drive the tool loop (DeepSeek R1, Llama 3.3)
were intentionally excluded from the defaults.
Webview typecheck + build pass.
SilanHe
approved these changes
Jul 15, 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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Surfaces a curated set of Bedrock models as suggestions in the Settings model picker, shown by default before/without fetching the full account list, so users land on a model that reliably handles the extension's query-generation task.
Curation is evidence-based: the models were benchmarked on the real agent-mode task ("count of executions grouped by productName and customerName in execution input") against real data on BOTH the Aurora (PostgreSQL) and S3/Athena (Trino) destinations. The listed models discovered the correct JSON keys and produced correct multi-dimension grouped SQL in both dialects. Models that only did well on one dialect (e.g. Mistral Pixtral Large — correct on Aurora but produced no aggregation on Athena) or couldn't drive the tool loop (DeepSeek R1, Llama 3.3) were intentionally excluded from the defaults.