Skip to content

[WIP] Add domain-specialist review agents for pre-push code review#16702

Open
jhadvig wants to merge 1 commit into
openshift:mainfrom
jhadvig:review_agent
Open

[WIP] Add domain-specialist review agents for pre-push code review#16702
jhadvig wants to merge 1 commit into
openshift:mainfrom
jhadvig:review_agent

Conversation

@jhadvig

@jhadvig jhadvig commented Jul 2, 2026

Copy link
Copy Markdown
Member

Summary

  • Adds three Claude Code agent types (.claude/agents/) for domain-specific code review:
    • plugin-api-guardian — reviews SDK changes for breaking API impact, changelog compliance, deprecation cycles, and documentation quality
    • go-backend-reviewer — reviews Go backend changes for correctness, security, idiomatic patterns, and test coverage
    • frontend-reviewer — reviews React/TypeScript changes for patterns compliance, i18n, PatternFly 6 usage, K8s resource handling, and test coverage
  • Rewrites the /pre-push-review skill to use these agents instead of the previous CodeRabbit + monolithic Claude approach, reducing review time from 7-30 minutes to seconds

Details

Each agent is a specialist that only reviews files in its domain. The main agent triages the diff, spawns relevant agents in parallel, and synthesizes their findings into a unified report.

Agent Domain Files
plugin-api-guardian Dynamic plugin SDK frontend/packages/console-dynamic-plugin-sdk/**
frontend-reviewer Frontend code frontend/** (excluding SDK)
go-backend-reviewer Go backend pkg/**, cmd/**, *.go

The simplified /pre-push-review flow:

  1. Gather diff and classify changed files by domain
  2. Spawn only relevant domain agents in parallel
  3. Synthesize findings and add cross-domain observations
  4. Report with severity-ranked issues

Screenshots / Recordings

N/A — this is a tooling/DX change with no UI impact.

Test plan

  • Run /pre-push-review on a branch with mixed frontend + backend changes and verify both agents spawn
  • Run /pre-push-review on a frontend-only branch and verify only the frontend agent spawns
  • Run /pre-push-review --staged and verify it reviews only staged changes
  • Verify agent findings are correctly synthesized into the unified report

🤖 Generated with Claude Code

Introduces three Claude Code agent types for domain-specific code
review: plugin-api-guardian (SDK breaking changes, changelogs),
go-backend-reviewer (Go correctness, security, patterns), and
frontend-reviewer (React, i18n, PatternFly, K8s resource handling).

Rewrites the pre-push-review skill to use these agents instead of
the CodeRabbit + monolithic Claude review approach, reducing review
time from 7-30 minutes to seconds.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@openshift-ci openshift-ci Bot added the do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. label Jul 2, 2026
@coderabbitai

coderabbitai Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Repository: openshift/coderabbit/.coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: ec13d4fd-04cc-4ecf-aca9-ab842018d9a6

📥 Commits

Reviewing files that changed from the base of the PR and between 7707540 and f0d4334.

📒 Files selected for processing (4)
  • .claude/agents/frontend-reviewer.md
  • .claude/agents/go-backend-reviewer.md
  • .claude/agents/plugin-api-guardian.md
  • .claude/skills/pre-push-review/SKILL.md
👮 Files not reviewed due to content moderation or server errors (4)
  • .claude/agents/go-backend-reviewer.md
  • .claude/agents/plugin-api-guardian.md
  • .claude/agents/frontend-reviewer.md
  • .claude/skills/pre-push-review/SKILL.md

Warning

Walkthrough skipped

File diffs could not be summarized.

🚥 Pre-merge checks | ❌ 10

❌ Failed checks (10 inconclusive)

Check name Status Explanation Resolution
Stable And Deterministic Test Names ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Test Structure And Quality ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Microshift Test Compatibility ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Single Node Openshift (Sno) Test Compatibility ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Topology-Aware Scheduling Compatibility ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Ote Binary Stdout Contract ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Ipv6 And Disconnected Network Test Compatibility ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
No-Weak-Crypto ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
Container-Privileges ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
No-Sensitive-Data-In-Logs ❓ Inconclusive Custom check execution failed before a final verdict was produced. Retry the review run. If this persists, inspect pre-merge custom-check logs for infrastructure or agent runtime failures.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands.

@openshift-ci openshift-ci Bot requested review from rhamilto and spadgett July 2, 2026 12:24
@openshift-ci

openshift-ci Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: jhadvig

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Details Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@openshift-ci openshift-ci Bot added the approved Indicates a PR has been approved by an approver from all required OWNERS files. label Jul 2, 2026
@openshift-ci

openshift-ci Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

@jhadvig: all tests passed!

Full PR test history. Your PR dashboard.

Details

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

approved Indicates a PR has been approved by an approver from all required OWNERS files. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant