feat: add bug-assess agentic workflow#3023
Open
mnriem wants to merge 5 commits into
Open
Conversation
Add a gh-aw agentic workflow that triggers when an issue is labeled `bug-assess`. It assesses the report against the codebase (symptom, suspected code paths, verdict, severity, remediation) and posts the full assessment.md as an issue comment, led by a one-line valid?/priority summary. It also applies severity / needs-reproduction / invalid triage labels. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new gh-aw “bug-assess” agentic workflow that runs on issues:labeled and (via compiled job conditions) activates only when the bug-assess label is applied, then produces a written bug assessment and applies triage labels.
Changes:
- Introduces
.github/workflows/bug-assess.mddefining the assessment prompt, tool allowlist, and safe-outputs constraints for comments/labels. - Adds the compiled workflow
.github/workflows/bug-assess.lock.ymlgenerated bygh aw compile.
Show a summary per file
| File | Description |
|---|---|
| .github/workflows/bug-assess.md | New gh-aw workflow source: instructions for reading the issue, assessing, and emitting a single comment + up to 2 labels. |
| .github/workflows/bug-assess.lock.yml | Compiled GitHub Actions workflow implementing the agent run, safe-outputs handling, and label-gated activation. |
Copilot's findings
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 2/2 changed files
- Comments generated: 1
Set safe-outputs.noop.report-as-issue: false so noop runs on failures/timeouts no longer create extra report issues, keeping outputs limited to the issue comment and triage labels. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Reword the Triggering Conditions paragraph to reflect that the issues:labeled trigger fires for any label and the bug-assess filtering happens via a job-level condition, not at the trigger. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Add a 65,000-char comment-size limit instruction with explicit truncation marking so large reports don't fail the safe-outputs validator. - Clarify the read-only guardrail: scratch files allowed under $RUNNER_TEMP, never write into the working tree or commit/push. - Align the one-line summary verdict vocabulary (Invalid) with the canonical 'invalid' verdict and Step 8 label rules. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Use 'severity' instead of 'priority' in the Step 7 one-line summary to match Step 5, the Severity header field, and the severity-* labels. - Clarify the read-only guardrail: comment + labels are the intended outputs on success, while the gh-aw harness may separately emit failure-report artifacts/issues when a run errors or times out. - Recompile with gh-aw v0.78.1 so the gh-aw-actions/setup pin matches the repo's other workflow lock files and actions-lock.json. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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.
What
Adds a gh-aw agentic workflow that automatically assesses bug reports.
.github/workflows/bug-assess.md— workflow source.github/workflows/bug-assess.lock.yml— compiled GitHub Actions YAML (gh aw compile)How it works
bug-assesslabel is added to an issue (enforced via a job conditiongithub.event.label.name == 'bug-assess'). Bot actors are skipped.grep/find, judges merit and severity, and proposes a remediation — based on the project's bug-assessment prompt, adapted to the issue context.assessment.mdas a single issue comment, led by a one-line summary (valid? + priority) so the verdict is visible at a glance.needs-reproduction/invalidlabel.Safety
Notes
gh aw compile; edit the.mdand recompile rather than editing the.lock.ymldirectly.bug-assesslabel (and the optionalseverity-*/needs-reproduction/invalidlabels) existing in the repo.