fix(base-cluster/deadMansSwitch): fix alertmanager healthchecks URL

[cwrau]

Summary by CodeRabbit

• Bug Fixes

  • Improved health check resource cleanup to ensure monitoring resources are consistently removed regardless of configuration state

• Chores

  • Updated health check naming convention and standardized identifiers across monitoring components
  • Modified alertmanager webhook configuration to use unified health check naming format across all monitoring systems

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses an issue with the Alertmanager healthchecks URL by standardizing the naming convention for dead man's switch checks across various Kubernetes configurations. The changes ensure that both scheduling and monitoring healthcheck URLs are consistently formatted, improving the reliability of the monitoring system and preventing potential misconfigurations. Additionally, the unregistration process for these checks has been made more robust.

Highlights

• Standardized Healthcheck URLs: Updated the healthcheck URL generation logic across cronjob and Alertmanager configurations to ensure consistent naming, specifically for scheduling and monitoring checks.
• Improved Dead Man's Switch Unregistration: Enhanced the unregistration script for the dead man's switch by ensuring the monitoring check deletion is always attempted and fails gracefully, regardless of Prometheus enablement.

Changelog

• charts/base-cluster/templates/monitoring/deadMansSwitch/cronjob.yaml
  • Updated the hc-ping.com URL to use the base-cluster.deadMansSwitch.checkName template for consistent naming of the scheduling check.
• charts/base-cluster/templates/monitoring/deadMansSwitch/unregister.yaml
  • Removed the conditional if .Values.monitoring.prometheus.enabled block around the deleteCheck "$checkName-monitoring" command.
  • Added || true to the deleteCheck "$checkName-monitoring" command to ensure the script continues execution even if the deletion fails.
• charts/base-cluster/templates/monitoring/kube-prometheus-stack/_alertmanager-config.yaml
  • Modified the hc-ping.com webhook URL to explicitly append -monitoring to the check name, aligning it with the intended monitoring check.

Activity

• No specific activity has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[coderabbitai]

Warning

Rate limit exceeded

@cwrau has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 17 minutes and 43 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: e271b453-2c84-43e0-8b1d-2b83bc0c0ce2

📥 Commits

Reviewing files that changed from the base of the PR and between 9cd529d and 7772579.

📒 Files selected for processing (3)

• charts/base-cluster/templates/monitoring/deadMansSwitch/cronjob.yaml
• charts/base-cluster/templates/monitoring/deadMansSwitch/unregister.yaml
• charts/base-cluster/templates/monitoring/kube-prometheus-stack/_alertmanager-config.yaml

📝 Walkthrough

Walkthrough

This pull request updates health check naming conventions across monitoring templates in the base-cluster Helm chart. The changes introduce a consistent "-monitoring" suffix pattern for alertmanager health checks and simplify the deletion logic to always attempt removing monitoring checks regardless of Prometheus enablement status.

Changes

Cohort / File(s)	Summary
Health Check Naming Conventions charts/base-cluster/templates/monitoring/deadMansSwitch/cronjob.yaml, charts/base-cluster/templates/monitoring/deadMansSwitch/unregister.yaml, charts/base-cluster/templates/monitoring/kube-prometheus-stack/_alertmanager-config.yaml	Updates health check URL paths to use standardized check names with "-monitoring" suffix appended to the check name variable in three locations. Additionally, changes the unregister script to unconditionally attempt deletion of monitoring health checks with error suppression, removing the previous Prometheus enablement condition.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Suggested labels

base-cluster

Suggested reviewers

• tasches
• marvinWolff
• teutonet-bot

Poem

🐰 The health checks now align so fine,
With "-monitoring" appended to each line,
The watchdog cronjobs sing in perfect key,
While alertmanager checks dance wild and free! 🔔✨

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the main change: fixing the alertmanager healthchecks URL in the dead man's switch monitoring configuration by adding the missing '-monitoring' suffix.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch fix/base-cluster/add-missing-monitoring-suffix

📝 Coding Plan

• Generate coding plan for human review comments

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[gemini-code-assist]

Code Review

This pull request aims to fix the health check URLs for the dead man's switch. The changes in cronjob.yaml and _alertmanager-config.yaml correctly align the check names, using a helper for consistency and adding the -monitoring suffix for the alertmanager check. However, the change in unregister.yaml has a critical issue. While it correctly attempts to make the cleanup process more robust by always trying to delete the monitoring check, it calls the deleteCheck function which is currently broken due to a typo in a variable name. The addition of || true will silence the error, leading to the cleanup job succeeding without actually deleting the health check. I've added a specific comment with more details.

[Copilot]

Pull request overview

Updates the base-cluster Helm chart’s Dead Man’s Switch / Healthchecks integration to use consistent check slugs, ensuring Alertmanager pings the intended “monitoring” check.

Changes:

• Fix Alertmanager’s Healthchecks ping URL to target the *-monitoring check slug.
• Align the scheduling CronJob ping URL to use the shared deadMansSwitch.checkName helper.
• Make the pre-delete unregister job attempt deletion of the monitoring check unconditionally (and tolerate failures).

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
charts/base-cluster/templates/monitoring/kube-prometheus-stack/_alertmanager-config.yaml	Adjusts Alertmanager webhook ping URL to use the -monitoring check slug.
charts/base-cluster/templates/monitoring/deadMansSwitch/cronjob.yaml	Uses the shared check-name helper when constructing the scheduling ping URL.
charts/base-cluster/templates/monitoring/deadMansSwitch/unregister.yaml	Changes unregister behavior to always attempt monitoring check deletion and ignore failures.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You can also share your feedback on Copilot code review. Take the survey.