Skip to content

Improve troubleshooting execution steering guide#161

Merged
bchampp merged 3 commits intoaws:mainfrom
vishalsatam:feature/improve-troubleshooting-steering
May 6, 2026
Merged

Improve troubleshooting execution steering guide#161
bchampp merged 3 commits intoaws:mainfrom
vishalsatam:feature/improve-troubleshooting-steering

Conversation

@vishalsatam
Copy link
Copy Markdown
Contributor

@vishalsatam vishalsatam commented May 6, 2026

Summary

Improves the troubleshooting-executions steering file with:

  • Expanded trigger keywords in POWER.md for better routing
  • ARN-based workflow instead of separate function name + execution ID
  • Console link generation for visual debugging
  • Structured output format with clear diagnosis summaries
  • Additional usage examples covering failure scenarios
  • Better error handling guidance (execution not found, permissions)

Testing

Verified changes are limited to the two steering files. No code changes.
Attached the prompts used to test this. check this comment

Expand trigger keywords in POWER.md for better routing to the
troubleshooting guide. Rewrite troubleshooting-executions.md with
clearer diagnostic steps, ARN-based workflow, console link generation,
structured output format, and additional usage examples.
@vishalsatam vishalsatam force-pushed the feature/improve-troubleshooting-steering branch from 02fb759 to 6260c96 Compare May 6, 2026 22:22
@vishalsatam
Copy link
Copy Markdown
Contributor Author

Testing prompts
test-execution-not-found.md
test-happy-path.md

Comment thread aws-lambda-durable-functions-power/steering/troubleshooting-executions.md Outdated
@bchampp
Copy link
Copy Markdown
Member

bchampp commented May 6, 2026

Comment thread aws-lambda-durable-functions-power/steering/troubleshooting-executions.md Outdated

3. If the command fails:
- Execution not found: Tell the user the execution ID may be incorrect or the execution may have been purged. Ask them to verify the ARN.
- Permissions/network error: Suggest checking IAM permissions (lambda:GetDurableExecutionHistory)
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggestion:

Permissions/network error: check that your caller identity has ambda:GetDurableExecutionHistory on the function ARN. This is not part of AWSLambdaBasicDurableExecutionRolePolicy."

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a good point - general note, do we clarify anywhere in the power about the permission model? I think it might be useful to have some context about permissions you need within the lambda loop (e.g. checkpoint, get state - included in AWSLambdaBasicDurableExecutionRolePolicy), and permissions outside of the loop (like this one).

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'll add "Permissions/network error: check that your caller identity has ambda:GetDurableExecutionHistory on the function ARN."

don't think we need to mention "AWSLambdaBasicDurableExecutionRolePolicy" since the user could be signed in with any role.

@yaythomas
Copy link
Copy Markdown
Contributor

Add steps to fetch the log group and query logs filtered by invocation
ID and execution name when execution history alone is insufficient to
determine root cause.
Add step 0 to resolve function alias to version and list executions
when user provides function name instead of full ARN. Also add STOPPED
status and improve permissions error guidance.
@vishalsatam
Copy link
Copy Markdown
Contributor Author

Test prompt with cloudwatch logs
test-happy-path-with-cw-logs.md

@vishalsatam vishalsatam requested review from bchampp and yaythomas May 6, 2026 23:43
@bchampp bchampp merged commit ee24b16 into aws:main May 6, 2026
vishalsatam added a commit to vishalsatam/agent-plugins that referenced this pull request May 7, 2026
Backport changes from aws/aws-durable-execution-docs#161 to the
agent-plugins repo. Improvements include:
- ARN-based workflow instead of separate function name + execution ID
- Alias resolution and list executions step
- Console link generation for visual debugging
- Structured output format with clear diagnosis summaries
- CloudWatch Logs querying when execution history is insufficient
- Additional usage examples covering failure scenarios
- Better error handling guidance (execution not found, permissions)
- Expanded trigger keywords in SKILL.md for better routing

Closes aws/aws-durable-execution-docs#162
vishalsatam added a commit to vishalsatam/agent-plugins that referenced this pull request May 7, 2026
Backport changes from aws/aws-durable-execution-docs#161 to the
agent-plugins repo. Improvements include:
- ARN-based workflow instead of separate function name + execution ID
- Alias resolution and list executions step
- Console link generation for visual debugging
- Structured output format with clear diagnosis summaries
- CloudWatch Logs querying when execution history is insufficient
- Additional usage examples covering failure scenarios
- Better error handling guidance (execution not found, permissions)
- Expanded trigger keywords in SKILL.md for better routing

Closes aws/aws-durable-execution-docs#162
vishalsatam added a commit to vishalsatam/agent-plugins that referenced this pull request May 7, 2026
Backport changes from aws/aws-durable-execution-docs#161 to the
agent-plugins repo. Improvements include:
- ARN-based workflow instead of separate function name + execution ID
- Alias resolution and list executions step
- Console link generation for visual debugging
- Structured output format with clear diagnosis summaries
- CloudWatch Logs querying when execution history is insufficient
- Additional usage examples covering failure scenarios
- Better error handling guidance (execution not found, permissions)
- Expanded trigger keywords in SKILL.md for better routing

Closes aws/aws-durable-execution-docs#162
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants