Auto-generate sanitized step for issue/discussion/PR/comment contexts#16378
Merged
Auto-generate sanitized step for issue/discussion/PR/comment contexts#16378
Conversation
- Add hasContentContext() to detect workflows triggered by issue/discussion/PR/comment events - Update needsTextOutput logic to check both explicit usage and content context - Add comprehensive tests for context detection - Add integration tests verifying sanitized step is added for content-triggered workflows Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Review logic to add sanitized step for contexts
Auto-generate sanitized step for issue/discussion/PR/comment contexts
Feb 17, 2026
pelikhan
reviewed
Feb 17, 2026
- Update hasContentContext() to detect slash_command triggers - Update hasContentContext() to detect labeled activity types on issues/PRs/discussions - Add test coverage for slash_command and labeled triggers - Verify workflows with these triggers get sanitized step automatically Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Contributor
Author
|
Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details. Warning Firewall rules blocked me from connecting to one or more addresses (expand for details)I tried to connect to the following addresses, but was blocked by firewall rules:
If you need me to access, download, or install something from one of these locations, you can either:
|
…ed.outputs - Update detectTextOutputUsage to look for steps.sanitized.outputs.* instead - Update test workflows to use steps.sanitized.outputs.text directly - Update comments to reflect that users should use steps.sanitized.outputs.* - Keep transformation logic for backward compatibility with existing workflows - All tests passing with new reference pattern Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot stopped work on behalf of
pelikhan due to an error
February 17, 2026 16:13
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates the sanitized step generation logic to automatically add the step when workflows are triggered by content events (issues, discussions, PRs, comments), regardless of explicit usage. It also transitions the API from needs.activation.outputs.* to steps.sanitized.outputs.* while maintaining backward compatibility.
Changes:
- Added
hasContentContext()function to detect workflows triggered by content events (issues, PRs, discussions, comments, slash commands, labeled events) - Updated sanitized step generation to activate when either explicitly used OR triggered by content events
- Migrated API references from
needs.activation.outputs.*tosteps.sanitized.outputs.*across test files - Added comprehensive test coverage for context detection and auto-insertion behavior
Reviewed changes
Copilot reviewed 18 out of 18 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| pkg/workflow/compiler_orchestrator_tools.go | Added hasContentContext() detection and updated detectTextOutputUsage() to check for steps.sanitized.outputs.* |
| pkg/workflow/compiler_activation_jobs.go | Updated comments to clarify new API pattern |
| pkg/workflow/expression_extraction.go | Updated comments to indicate transformation is for backward compatibility |
| pkg/workflow/compute_text_lazy_test.go | Added tests for hasContentContext() and context-based insertion |
| Multiple test files | Updated test cases to use steps.sanitized.outputs.* pattern |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
|
@copilot keep working |
Contributor
Author
|
Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details. Warning Firewall rules blocked me from connecting to one or more addresses (expand for details)I tried to connect to the following addresses, but was blocked by firewall rules:
If you need me to access, download, or install something from one of these locations, you can either:
|
…zed steps - Updated multiple workflow files to include outputs for body, text, and title from the sanitized step. - Introduced a new step to compute the current body text using the compute_text action in each workflow. - Ensured that the workflows maintain permissions for issues and pull requests.
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
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.
Completed: Fix sanitized step generation for issue/discussion/PR/comment contexts
Summary
Successfully implemented automatic sanitized step generation for workflows triggered by content events. The sanitized step now automatically provides text/title/body outputs for:
✅ Direct content events: issues, pull_request, pull_request_target, issue_comment, pull_request_review_comment, pull_request_review, discussion, discussion_comment
✅ Slash command triggers: workflows using
on: slash_command:✅ Labeled activity types: workflows triggered by labeled/unlabeled on issues, PRs, or discussions
API Transition
New API (recommended):
Analyze this: "${{ steps.sanitized.outputs.text }}"Legacy API (backward compatible):
Analyze this: "${{ needs.activation.outputs.text }}"Automatically transformed to steps.sanitized.outputs.text
Test Results
✅ 18 unit tests for hasContentContext (all trigger types)
✅ 7 unit tests for detectTextOutputUsage
✅ 6 integration tests for workflow compilation
✅ All existing tests passing
✅ Build successful
✅ Manual verification complete
Files Changed
All commits are clean, tests pass, and the implementation is fully backward compatible.
Original prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.