Improve error handling, add tests, and migrate code review to issues

[him0]

Summary

• Improve error handling in processBranch() for fast-forward update, branch deletion, and checkout operations
• Replace fmt.Sscanf with strconv.Atoi for commit count parsing with explicit error handling
• Add unit tests for colorizeOutput, getCommitDifference, and getDefaultBranch
• Address CodeRabbit review feedback:
  • Replace fragile branchOut[:len(branchOut)-1] with strings.TrimSpace for safe newline handling
  • Save/restore global colorFlag in TestColorizeOutput to prevent flaky tests
  • Remove dead exact field from test struct (was always true)
  • Add comments documenting os.Chdir parallel test safety constraint
• Remove CODE_REVIEW.md and migrate all findings to individual GitHub issues (Return values of runGitSilent are ignored in processBranch #5-exitWithError calls os.Exit(1) directly, preventing deferred cleanup #15)

Closes #5
Closes #6
Closes #7

Test plan

• All tests pass with go test ./... -v

[coderabbitai]

Warning

Rate limit exceeded

@him0 has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 15 minutes and 39 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.

Walkthrough

Add error handling around git fast-forward, checkout and branch deletion operations; replace fmt.Sscanf parsing with strconv.Atoi for commit counts; add tests (colorizeOutput, getCommitDifference, getDefaultBranch) and a test repo helper.

Changes

Cohort / File(s)	Summary
Core logic & parsing main.go	Added strconv import; replaced fmt.Sscanf parsing with strconv.Atoi and explicit error returns; capture and handle update errors for fast-forward updates; guard checkout and branch deletion with error handling and warnings; adjusted printed messages based on success/failure.
Tests main_test.go	New test file: TestColorizeOutput, TestGetCommitDifference, TestGetDefaultBranch, and setupTestRepo helper to create temporary git repos and remotes. Uses a Remote struct in tests.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

• Add code review findings for gh-sync #3: Implements related error-handling fixes, parsing switch to strconv.Atoi, and introduces test coverage similar to this PR.

🚥 Pre-merge checks | ✅ 1 | ❌ 2

❌ Failed checks (1 warning, 1 inconclusive)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 16.67% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.
Title check	❓ Inconclusive	The PR title mentions 'improve error handling and add tests' which aligns with the actual changes, but includes 'migrate code review to issues' which is not reflected in the file changes provided.	Verify whether 'migrate code review to issues' is part of the actual changes. If not, revise the title to focus on error handling improvements and test additions only.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.

_{✏️ 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 claude/code-review-high-priority-AlBUx

---

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.}

[coderabbitai]

Actionable comments posted: 1

🤖 Fix all issues with AI agents

In `@main_test.go`:
- Around line 81-87: Replace the fragile manual newline stripping when computing
defaultBranch by using strings.TrimSpace on branchOut instead of
branchOut[:len(branchOut)-1]; update the code that runs git rev-parse
(variables: cmd, branchOut, defaultBranch) to set defaultBranch := "refs/heads/"
+ strings.TrimSpace(string(branchOut)) and add "strings" to the import block so
empty or platform-specific line endings are handled safely.

🧹 Nitpick comments (3)

main_test.go (3)

25-33: Global colorFlag is mutated without being restored.

If test ordering changes or new tests depend on colorFlag, this will cause flaky failures. Save and restore the original value.

Proposed fix

 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
+			oldFlag := colorFlag
+			defer func() { colorFlag = oldFlag }()
 			colorFlag = tt.flag
 			got := colorizeOutput()

---

11-16: The exact field is always true — it's dead logic.

Every test case sets exact: true, so the guard if tt.exact && on line 29 is never false. Either remove the field and simplify the check, or add a case that actually uses exact: false.

---

61-68: os.Chdir mutates process-global state, making these tests unsafe for parallel execution.

This is a known Go testing pitfall. If t.Parallel() is ever added, tests will interfere with each other. Since getCommitDifference shells out to git (which uses the working directory), there's no easy workaround, but consider adding a comment documenting this constraint, or using t.Setenv-style guards if Go 1.24+ t.Chdir is available.