feat: implement issue #574 — pr-review: PRs with >300 changed files hard-fail the cascade (gh pr diff 406); define org standard for oversized PRs

[don-petry]

Closes #574

Implemented by dev-lead agent. Please review.

Summary by CodeRabbit

• Bug Fixes

  • Improved handling of oversized pull requests (>300 changed files) by implementing a fallback mechanism that switches to per-file retrieval when unified diff limits are exceeded, allowing reviews to continue instead of failing.

• Tests

  • Added comprehensive test suite for oversized PR detection logic.

• Documentation

  • Updated documentation to clarify oversized PR handling behavior and GitHub diff limits.

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.

[coderabbitai]

Warning

Review limit reached

@don-petry, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 31 minutes and 9 seconds. Learn how PR review limits work.

Your organization has run out of usage credits. Purchase more credits in the billing tab to continue.

⌛ How to resolve this issue?

After more reviews become available, 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 include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

Run ID: ac461b5a-6b61-4f73-9c04-463e0564c5b6

📥 Commits

Reviewing files that changed from the base of the PR and between 5299ce0 and 2a88ee4.

📒 Files selected for processing (5)

• .github/workflows/lint.yml
• AGENTS.md
• scripts/engine.sh
• scripts/review-one-pr.sh
• tests/test_oversized_pr.bats

📝 Walkthrough

Walkthrough

The PR adds fallback handling for pull requests exceeding GitHub's 300-file unified-diff limit. When gh pr diff returns HTTP 406, the review script now fetches individual file patches via the per-file REST API, assembles a truncated synthetic diff, and continues review instead of exiting fatally. Detection logic and tests are provided; org policy is documented.

Changes

Oversized PR Handling

Layer / File(s)	Summary
Org standard for oversized PR handling AGENTS.md	Documents that the 300-file unified-diff cap is a GitHub hard limit; oversized PRs fall back to per-file REST API assembly; the guideline is advisory, not enforced by CI.
Oversized diff detection and tests scripts/engine.sh, tests/test_oversized_pr.bats, .github/workflows/lint.yml	is_diff_too_large helper detects HTTP 406 and "maximum number of files" error patterns; Bats test suite validates success (multiple 406 variants) and failure (rate-limit, CLI errors, empty/unrelated text) cases; CI configuration runs the new test suite.
Fallback to per-file REST API and improved error logging scripts/review-one-pr.sh	When diff fetch fails, checks if the failure is size-related; if so, fetches PR files via per-file API, concatenates patches, truncates to _diff_limit, and continues; non-size errors are logged with captured content and exit 1.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

Possibly related PRs

• petry-projects/.github-private#176: Modifies scripts/review-one-pr.sh to detect GitHub API failure modes during PR diff fetching (rate-limit/HTTP 429 vs. this PR's HTTP 406 handling).

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and specifically describes the main change: implementing issue #574 to handle the hard failure when PRs exceed 300 changed files, including both the code fix and the org standard.
Linked Issues check	✅ Passed	The PR addresses all core requirements from issue #574: detects the 406 error case, implements a fallback via per-file REST API instead of fatal exit, defines org standard in AGENTS.md, and distinguishes 406 from other failures.
Out of Scope Changes check	✅ Passed	All changes are directly in scope: the new helper function, the fallback logic in review-one-pr.sh, the org standard documentation, and comprehensive test coverage for the 406 detection.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch dev-lead/issue-574-20260611-2357

---

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 introduces a fallback mechanism to handle oversized pull requests (exceeding 300 changed files) where GitHub's unified-diff endpoint returns an HTTP 406 error. It adds documentation, a helper function to detect the error, fallback logic in the review script to assemble a diff from the per-file REST API, and unit tests. The feedback suggests using the optional object identifier iterator .[]? in the jq filter within scripts/review-one-pr.sh to prevent execution errors if the API returns an empty response.

[don-petry]

Dev-Lead — review-changes (applied)

Changes committed and pushed.

[don-petry]

Dev-Lead — waiting on PR blockers (intent: review-changes)

PR: #606
No changes were committed, but the PR still has blocking checks or reviews (failing or cancelled checks, or changes-requested reviews). The retry cron will re-attempt automatically. Next attempt after: 2026-06-12T00:47:21Z

[don-petry]

Note

@don-petry I reviewed this PR and no code changes were needed, but it still has blocking checks or reviews (failing or cancelled checks, or changes-requested reviews), so I cannot mark it done yet. I'll re-check automatically.
Next attempt after: 2026-06-12T00:47:21Z

[don-petry]

Dev-Lead — waiting on PR blockers (intent: review-changes)

PR: #606
No changes were committed, but the PR still has blocking checks or reviews (failing or cancelled checks, or changes-requested reviews). The retry cron will re-attempt automatically. Next attempt after: 2026-06-12T01:13:55Z

[don-petry]

Note

@don-petry I reviewed this PR and no code changes were needed, but it still has blocking checks or reviews (failing or cancelled checks, or changes-requested reviews), so I cannot mark it done yet. I'll re-check automatically.
Next attempt after: 2026-06-12T01:13:55Z

[coderabbitai]

Actionable comments posted: 2

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@scripts/review-one-pr.sh`:
- Around line 442-443: The two printf invocations that print the assembled-diff
note break the sentence awkwardly; update the printf usage that references
_changed_files so the whole note is printed as one coherent sentence (replace
the two separate printf calls with a single printf that emits the full message
without the mid-sentence newline, or rephrase the text to move the clause
“exceeds GitHub’s 300-file unified-diff cap” earlier), targeting the printf
lines that contain "# NOTE: diff assembled from per-file REST API (%s changed
files exceeds" and the following "# GitHub's 300-file unified-diff cap; patches
may be partial or absent for large files)" so the output reads cleanly on one
line.
- Around line 432-451: The fallback silently swallows failures of the gh api
call (the command with gh api ... --paginate --slurp | jq ... 2>/dev/null ||
true), which can leave PR_DIFF empty; change this so the REST API error is
captured and logged: run the gh api pipeline without redirecting stderr to
/dev/null (or capture its stderr into a temp file like _fallback_err), check the
command's exit status ($?); if it fails, emit a clear warning to stderr (e.g.,
echo "warning: gh api fallback failed: <error details>" >&2) referencing the gh
api invocation and the temp files (_fallback_tmp and _fallback_err) so callers
can diagnose network/rate-limit errors before continuing to assemble PR_DIFF.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

Run ID: 4b512722-0df0-4767-ba8f-910372ee259a

📥 Commits

Reviewing files that changed from the base of the PR and between afb4acd and 5299ce0.

📒 Files selected for processing (5)

• .github/workflows/lint.yml
• AGENTS.md
• scripts/engine.sh
• scripts/review-one-pr.sh
• tests/test_oversized_pr.bats

[don-petry]

Dev-Lead — fix-reviews (applied)

Changes committed and pushed.

[don-petry]

Dev-Lead — waiting on PR blockers (intent: review-changes)

PR: #606
No changes were committed, but the PR still has blocking checks or reviews (failing or cancelled checks, or changes-requested reviews). The retry cron will re-attempt automatically. Next attempt after: 2026-06-12T01:24:08Z

[don-petry]

Note

@don-petry I reviewed this PR and no code changes were needed, but it still has blocking checks or reviews (failing or cancelled checks, or changes-requested reviews), so I cannot mark it done yet. I'll re-check automatically.
Next attempt after: 2026-06-12T01:24:08Z

[don-petry]

Dev-Lead — review-changes (no-changes)

No changes were needed for this PR.