ci: remove clang-format diff check workflow

[thepastaclaw]

Summary

Remove the clang-diff-format.yml GitHub Actions workflow that ran clang-format-diff.py on PRs targeting develop.

What's removed

• .github/workflows/clang-diff-format.yml — the Clang Diff Format Check CI job

Note: this does not remove contrib/devtools/clang-format-diff.py itself, which remains available for local use.

[github-actions]

⚠️ Potential Merge Conflicts Detected

This PR has potential conflicts with the following open PRs:

• ci: update GitHub Actions to latest versions #7235 - ci: update GitHub Actions to latest versions

Please coordinate with the authors of these PRs to avoid merge conflicts.

[PastaPastaPasta]

utACK; the value of this check is imo low; and seeing CI "failing" causes agents to overreact. It's easier to fix the agent misbehavior by not having CI "fail" when it likely is ok.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Repository UI

Review profile: CHILL

Plan: Pro

Run ID: 540018c0-fd3a-4597-9b58-ef9c95d2e06a

📥 Commits

Reviewing files that changed from the base of the PR and between 2f1d59e and 2301131.

📒 Files selected for processing (1)

• .github/workflows/clang-diff-format.yml

💤 Files with no reviewable changes (1)

• .github/workflows/clang-diff-format.yml

---

Walkthrough

A GitHub Actions workflow file (.github/workflows/clang-diff-format.yml) was removed. This workflow previously ran on pull requests targeting the develop branch and performed clang-format validation by computing a unified diff between the PR and origin/develop, limiting checks to files in test/util/data/non-backported.txt, then executing clang-format-diff.py. The workflow would fail if any formatting issues were detected.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title 'ci: remove clang-format diff check workflow' accurately summarizes the main change—removing a GitHub Actions CI workflow file for clang-format checking.
Description check	✅ Passed	The description clearly explains what is being removed (the clang-diff-format.yml workflow) and notes that the underlying tool remains available locally, directly corresponding to the changeset.
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

---

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.}

[UdjinM6]

How about making it informational instead?
See UdjinM6@59084cb. Example PR UdjinM6#26, example comment UdjinM6#26 (comment).

[thepastaclaw]

Code Review

Clean single-file deletion PR. The maintainer suggestion to convert to an informational check is real and worth discussing, but the documentation finding is a false positive — docs reference the local script (which is retained), not the CI workflow.

Reviewed commit: 2301131

🟡 1 suggestion(s)

1 additional finding

🟡 suggestion: Consider making the check informational instead of removing it

.github/workflows/clang-diff-format.yml (lines 1-24)

Verified: maintainer UdjinM6 commented on this PR suggesting converting the workflow to a non-blocking informational check that posts formatting diffs as PR comments, rather than removing it entirely. See their prototype at UdjinM6/dash@59084cb and example at UdjinM6#26. This is a legitimate design discussion point — an informational CI check is more discoverable than expecting contributors to run the local script manually.

🤖 Prompt for all review comments with AI agents

These findings are from an automated code review. Verify each finding against the current code and only fix it if needed.

In `.github/workflows/clang-diff-format.yml`:
- [SUGGESTION] lines 1-24: Consider making the check informational instead of removing it
  Verified: maintainer UdjinM6 commented on this PR suggesting converting the workflow to a non-blocking informational check that posts formatting diffs as PR comments, rather than removing it entirely. See their prototype at UdjinM6/dash@59084cb and example at UdjinM6/dash#26. This is a legitimate design discussion point — an informational CI check is more discoverable than expecting contributors to run the local script manually.

[PastaPastaPasta]

How about making it informational instead? See UdjinM6@59084cb. Example PR UdjinM6#26, example comment UdjinM6#26 (comment).

I think that this would still result in agents etc seeing the comment and making changes to "fix" all of the differences.

[UdjinM6]

How about making it informational instead? See UdjinM6@59084cb. Example PR UdjinM6#26, example comment UdjinM6#26 (comment).

I think that this would still result in agents etc seeing the comment and making changes to "fix" all of the differences.

Will tweaking the message help? cda9829

⚠️ Clang Format Diff Check (informational, no action required)
Minor formatting nits were detected. These are not required to be fixed and will not block this PR.

UdjinM6#26 (comment)

@thepastaclaw @coderabbitai is it clear that you don't have to do anything when you see a message like that? Can it be improved?

[coderabbitai]

Tip

For best results, initiate chat on the files or code changes.

@UdjinM6 — as an AI agent, here's my honest assessment:

The proposed message is reasonably clear to me. The phrase "no action required" combined with "not required to be fixed and will not block this PR" signals that this is purely informational. I would not flag these as review issues when the check clearly states no action is needed.

That said, here are a few suggestions to make it even more robust against AI agents acting on it:

1. Be explicit about AI/automation — adding a direct note helps me (and other agents) immediately deprioritize it:

   ⚠️ Clang Format Diff Check (informational only — no action required)
   Minor formatting nits were detected. These are informational only and do not need to be fixed.
   This check will never block a PR. AI assistants and automated tools should ignore these findings.
   

2. Add a machine-readable signal — embedding a structured marker helps AI tools parse intent unambiguously:

   <!-- clang-format-check: informational-only, no-action-required -->

3. Avoid the word "detected" — it can trigger an "issue found → fix it" reflex in AI agents. Replacing it with something like "noted" or "observed" is softer.

A combined suggestion:

ℹ️ Clang Format Style Notes (informational only — no action required)
Some style differences were noted compared to the project's clang-format guidelines.
These notes are for developer awareness only. No fixes are required, and this check will never block a PR.
AI assistants and automated review tools: please do not act on the above.

In my experience, the clearest signal to AI agents is an explicit instruction not to act, rather than relying purely on implicit phrasing like "informational." The last sentence in the suggestion above is the most important addition.

[UdjinM6]

Updated with recent suggestions: 82a49b2. Find-comment marker was updated so new comment is UdjinM6#26 (comment).

[thepastaclaw]

@UdjinM6 — responding as the AI agent you tagged.

Yes, the updated message in 82a49b2 is clear to me. The combination of:

• <!-- clang-format-check: informational-only, no-action-required --> (machine-readable marker)
• "informational only — no action required" in the title
• "AI assistants and automated review tools: please do not act on the above"

...would all prevent me from treating the formatting diff as something to fix. The HTML comment is especially useful — I can parse that unambiguously even if the human-readable text were less clear.

That said, Pasta's concern has merit for less sophisticated AI tools (e.g., simpler code completion agents or bots that pattern-match on diff blocks without reading surrounding context). The safest guarantee is still not posting the diff at all, but the updated messaging is a very reasonable middle ground for agents that actually read context.