chore: expand pr to issue tracing for impact report mapped outcomes#39620
Conversation
Co-authored-by: mnkiefer <8320933+mnkiefer@users.noreply.github.com>
Co-authored-by: mnkiefer <8320933+mnkiefer@users.noreply.github.com>
|
@copilot Recompile workflows |
There was a problem hiding this comment.
⚠️ Not ready to approve
The updated workflows/scripts introduce avoidable failure and injection risks (unvalidated limit input and unsafe $GITHUB_OUTPUT writes) that should be addressed before approval.
Pull request overview
This pull request improves the Objective Impact Efficiency Report dataset generation so PR→issue tracing captures GitHub-native closing references and covers a wider PR sample window, reducing undercounting of mapped outcomes.
Changes:
- Increased PR dataset coverage by making the PR list limit configurable via
OBJECTIVE_IMPACT_PR_LIST_LIMIT(default5000). - Expanded linked-issue derivation to merge
closingIssuesReferences(GraphQL/gh pr list --json) with existing body regex detection, with deduplication. - Updated compiled workflow/runtime plumbing (Objective Impact lock workflow) and hardened output recording in
agentics-maintenance.yml.
File summaries
| File | Description |
|---|---|
scripts/prepare-objective-impact-report-dataset.sh |
Expands PR→issue linkage extraction and increases PR sampling via a configurable limit. |
.github/workflows/objective-impact-report.lock.yml |
Updates compiled workflow steps for MCP/safe-outputs startup configuration. |
.github/workflows/agentics-maintenance.yml |
Adjusts how workflow inputs are written to $GITHUB_OUTPUT via env indirection. |
Copilot's findings
- Files reviewed: 3/3 changed files
- Comments generated: 4
Note
Your feedback helps us improve the quality of this feature.
Please use 👍 or 👎 to tell us whether this assessment is correct.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Ran |
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
|
@copilot Revert changes to |
Co-authored-by: mnkiefer <8320933+mnkiefer@users.noreply.github.com>
|
@copilot Recompile workflow |
Ran |
|
@copilot Recompile workflow and check tests |
Co-authored-by: mnkiefer <8320933+mnkiefer@users.noreply.github.com>
Recompiled in the latest commit — 249 workflows compiled (0 errors), lock files updated (mcpg bumped to v0.3.26). All tests pass. |
Impact Efficiency Report was undercounting accepted mapped outcomes because PR root-issue tracing only captured a subset of closing references and operated on a small PR sample. This change broadens linkage extraction and increases dataset coverage so mapped outcome counts reflect actual traced work.
Root cause
Closes/Fixes/Resolves #Nbody parsing, missing canonical PR closing references.500) truncated the analysis window in active repos.Changes
closingIssuesReferencesto both merged and closed-unmerged PR dataset queries.closingIssuesReferences)linked_issue_numbers.OBJECTIVE_IMPACT_PR_LIST_LIMIT(default5000) for broader, configurable coverage.Behavioral impact