local-review-harness/internal/git/git.go

// Package git wraps the subprocess `git` calls the harness needs.
// Every call gracefully degrades: a non-git directory returns
// HasGit=false rather than an error, so the pipeline can mark the
// git phase degraded without halting.
package git

import (
	"context"
	"fmt"
	"os/exec"
	"path/filepath"
	"strings"
	"time"
)

// Info is the git metadata bundle for repo-intake.
type Info struct {
	HasGit        bool   `json:"has_git"`
	CurrentBranch string `json:"current_branch,omitempty"`
	LatestCommit  string `json:"latest_commit,omitempty"`
	Status        string `json:"status,omitempty"` // raw `git status -s` output
	Errors        []string `json:"errors,omitempty"`
}

// Inspect runs the read-only git probes. Times out after 5s per call
// so a hung git process can't stall the pipeline. Never mutates the
// target repo.
func Inspect(ctx context.Context, repoPath string) Info {
	out := Info{}
	abs, _ := filepath.Abs(repoPath)
	gitDir := filepath.Join(abs, ".git")
	if _, err := exec.LookPath("git"); err != nil {
		out.Errors = append(out.Errors, "git binary not in PATH")
		return out
	}

	// `.git` may be a file (worktree pointer) or a dir. `git rev-parse`
	// is the canonical "is this a repo?" probe.
	cctx, cancel := context.WithTimeout(ctx, 5*time.Second)
	defer cancel()
	cmd := exec.CommandContext(cctx, "git", "-C", abs, "rev-parse", "--git-dir")
	if err := cmd.Run(); err != nil {
		// Only annotate when .git looked present — otherwise it's just
		// a non-git target, not an error.
		if _, statErr := exec.LookPath("git"); statErr == nil {
			_ = gitDir
		}
		return out
	}
	out.HasGit = true

	out.CurrentBranch = runGit(ctx, abs, "rev-parse", "--abbrev-ref", "HEAD")
	out.LatestCommit = runGit(ctx, abs, "rev-parse", "HEAD")
	out.Status = runGit(ctx, abs, "status", "-s")
	return out
}

func runGit(ctx context.Context, dir string, args ...string) string {
	cctx, cancel := context.WithTimeout(ctx, 5*time.Second)
	defer cancel()
	full := append([]string{"-C", dir}, args...)
	out, err := exec.CommandContext(cctx, "git", full...).Output()
	if err != nil {
		return ""
	}
	return strings.TrimSpace(string(out))
}

// ChangedFiles returns the set of repo-relative paths the diff
// subcommand should scan. Includes (in priority order):
//   - unstaged changes (`git diff --name-only`)
//   - staged changes (`git diff --cached --name-only`)
//   - branch diff against base (`git diff --name-only base..HEAD`)
//
// base is auto-detected: prefer "main" then "master" then HEAD~1.
// Returns dedup'd, stable-ordered list. Empty list when there's
// nothing to review (clean tree, no commits ahead of base).
func ChangedFiles(ctx context.Context, repoPath string) ([]string, error) {
	if _, err := exec.LookPath("git"); err != nil {
		return nil, fmt.Errorf("git not in PATH")
	}
	abs, _ := filepath.Abs(repoPath)
	cctx, cancel := context.WithTimeout(ctx, 10*time.Second)
	defer cancel()
	if err := exec.CommandContext(cctx, "git", "-C", abs, "rev-parse", "--git-dir").Run(); err != nil {
		return nil, fmt.Errorf("not a git repository: %s", repoPath)
	}

	seen := map[string]bool{}
	var out []string
	add := func(s string) {
		s = strings.TrimSpace(s)
		if s == "" || seen[s] {
			return
		}
		seen[s] = true
		out = append(out, s)
	}

	// Unstaged
	for _, line := range strings.Split(runGit(ctx, abs, "diff", "--name-only"), "\n") {
		add(line)
	}
	// Staged
	for _, line := range strings.Split(runGit(ctx, abs, "diff", "--cached", "--name-only"), "\n") {
		add(line)
	}
	// vs base — try main, master, then HEAD~1
	for _, base := range []string{"main", "master"} {
		if runGit(ctx, abs, "rev-parse", "--verify", base) != "" {
			for _, line := range strings.Split(runGit(ctx, abs, "diff", "--name-only", base+"...HEAD"), "\n") {
				add(line)
			}
			break
		}
	}

	return out, nil
}

// fmt + filepath are already imported indirectly; this var keeps
// the import list clean if those packages get unused after a refactor.
var _ = fmt.Sprintf
var _ = filepath.Join