Repository navigation
perf(pr-management): run mentor, reviewer-routing and pre-first-pr-check rules as code - #1583
Merged
potiuk merged 1 commit intoOct 10, 2026
Conversation
potiuk
added
family:pr-management
github-actions
Bot
added
family:setup
potiuk
added this pull request to stack #1586
October 10, 2026 09:23
potiuk
force-pushed
the
perf/pr-mgmt-9-mentor-routing-prefirst
branch
2 times, most recently
from
October 10, 2026 10:18
be6c377 to
686e63c
Compare
…eck rules as code Three smaller skills, the same treatment, one file per classification: - pr-management-mentor: config validation, the hand-off triggers in priority order, maintainer engagement, the out-of-scope prefilter and the deterministic tone rules run in `pr-management mentor assess | render | tone-check | log`; the agent picks the intervention where it is ambiguous and writes the words. The hand-off is posted normally — the mention guard allows the configured maintainer team for it. - reviewer-routing: input validation, roster parsing, path-to-area mapping, familiarity from GitHub data (no local clone), review load (the `review-requested:@<handle>` query was wrong), scoring, overload and backup rules, a new CODEOWNERS signal, and the proposal text run in `pr-management reviewer-routing preflight | propose`. The contradictory overload rules settle on: an overloaded member is never the primary, and is a backup only when no one else is eligible. - pre-first-pr-check: the read-only git inspection and categories A (SPDX header, licence from `project.md`), B2, B3 (attribution resolved like the agent-guard), C and D, and the readiness signal run in `pr-management pre-first-pr check | report`; the agent judges commit mood, AI assistance, wording and injection. The model-graded cases for the now-scripted logic become pytest cases named after each case; the judgement cases stay model evals. Generated-by: Claude Opus 5 Claude-Session: https://claude.ai/code/session_01GTPsZ5aEE5bUVYqp47Dpvv
potiuk
force-pushed
the
perf/pr-mgmt-9-mentor-routing-prefirst
branch
from
October 10, 2026 11:16
686e63c to
a642448
Compare
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
1 participant
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.
Summary
Three smaller skills get the same treatment, with one file per classification:
pr-management mentor assess | render | tone-check | log. The agent picks the intervention where it is ambiguous and writes the words. The hand-off is posted normally; the mention guard allows the configured maintainer team for it.pr-management reviewer-routing preflight | propose.review-requested:@<handle>load query was wrong; fixed.project.md), B2, B3 (attribution resolved like agent-guard), C and D, and the readiness signal run inpr-management pre-first-pr check | report. The agent judges commit mood, AI assistance, wording and injection.Type of change
Test plan
prek run --all-filespassestools/pr-managementpytest / ruff / mypyjudgement.jsonthe model writes (B1 / B3 / D / E) rather than category statuses, which are scripted now.Was generative AI tooling used to co-author this PR?
Generated-by:.🤖 Generated with Claude Code
https://claude.ai/code/session_01GTPsZ5aEE5bUVYqp47Dpvv