huskies: merge 1013

crates/source-map-gen/src/main.rs

@@ -5,8 +5,13 @@
 //! Exits with code 1 and prints LLM-friendly directions when public items are
 //! missing doc comments. Exits 0 (silently) when all changed files are fully
 //! documented or when there are no relevant changes to check.
+//!
+//! The file set is derived from all worktree states: committed changes since
+//! `base`, staged changes, unstaged changes, and untracked files. This ensures
+//! the result is independent of git index state.
 
 use source_map_gen::{CheckResult, check_files_ratcheted};
+use std::collections::HashSet;
 use std::path::{Path, PathBuf};
 use std::process::Command;
 
@@ -17,29 +22,7 @@ fn main() {
 
     let worktree_path = Path::new(&worktree);
 
-    let output = match Command::new("git")
-        .args(["diff", "--name-only", &format!("{base}...HEAD")])
-        .current_dir(worktree_path)
-        .output()
-    {
-        Ok(o) => o,
-        Err(e) => {
-            eprintln!("source-map-check: git diff failed: {e}");
-            std::process::exit(1);
-        }
-    };
-
-    if !output.status.success() {
-        // Base branch not found or other git error — skip the check gracefully.
-        return;
-    }
-
-    let changed: Vec<PathBuf> = String::from_utf8_lossy(&output.stdout)
-        .lines()
-        .filter(|l| !l.is_empty())
-        .map(|l| worktree_path.join(l))
-        .filter(|p| p.exists())
-        .collect();
+    let changed = collect_changed_files(worktree_path, &base);
 
     if changed.is_empty() {
         return;
@@ -64,6 +47,64 @@ fn main() {
     }
 }
 
+/// Collect all files that differ from `base` in any git state: committed, staged,
+/// unstaged, or untracked. Returns deduplicated absolute paths that exist on disk.
+fn collect_changed_files(worktree_path: &Path, base: &str) -> Vec<PathBuf> {
+    let mut names: HashSet<String> = HashSet::new();
+
+    // Committed changes since base (three-dot diff handles divergent histories).
+    run_git_name_list(
+        worktree_path,
+        &["diff", "--name-only", &format!("{base}...HEAD")],
+        &mut names,
+    );
+
+    // Staged changes not yet committed.
+    run_git_name_list(
+        worktree_path,
+        &["diff", "--name-only", "--cached"],
+        &mut names,
+    );
+
+    // Unstaged changes to tracked files.
+    run_git_name_list(worktree_path, &["diff", "--name-only"], &mut names);
+
+    // Untracked files (new files not yet added to the index).
+    run_git_name_list(
+        worktree_path,
+        &["ls-files", "--others", "--exclude-standard"],
+        &mut names,
+    );
+
+    names
+        .into_iter()
+        .map(|l| worktree_path.join(l))
+        .filter(|p| p.exists())
+        .collect()
+}
+
+/// Run a git command and collect each non-empty output line into `out`.
+///
+/// Silently ignores git errors so a missing base branch or a fresh repo without
+/// any commits does not abort the check.
+fn run_git_name_list(worktree_path: &Path, args: &[&str], out: &mut HashSet<String>) {
+    let Ok(output) = Command::new("git")
+        .args(args)
+        .current_dir(worktree_path)
+        .output()
+    else {
+        return;
+    };
+    if !output.status.success() {
+        return;
+    }
+    for line in String::from_utf8_lossy(&output.stdout).lines() {
+        if !line.is_empty() {
+            out.insert(line.to_string());
+        }
+    }
+}
+
 /// Parse a flag value from an argument list (e.g. `--flag value`).
 fn parse_arg(args: &[String], flag: &str) -> Option<String> {
     args.windows(2).find(|w| w[0] == flag).map(|w| w[1].clone())