fix: pre-landing review fixes (pass 5)

The pack's blob list is the copied index's blobs that HEAD's tree lacks,
so an intent-to-add entry's empty blob and the stages of an unmerged entry
travel too (the HEAD-only diff list dropped both); gitlinks still skip.
The live-checkout test adds an intent-to-add entry, which the VM fsck
assertion covers.

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

scripts/ubicloud/ubi-runner.sh

@@ -627,15 +627,16 @@ cmd_pack() {
     done < <(git -C "$gitdir" config --local --null --get-regexp '^(remote|branch)\.' 2>/dev/null || true)
     # The checkout's index rides along so the VM's status matches, except a
     # split index, whose shared half lives only in the original git dir. The
-    # blobs staged against HEAD are behind no ref, so they travel as a pack of
+    # index's blobs that HEAD's tree lacks (staged, intent-to-add, the stages
+    # of an unmerged entry) are behind no ref, so they travel as a pack of
     # their own; without them the VM's write-tree (gstack-wtree) cannot read a
     # staged file.
     if [ "$(git -C "$src" config --bool core.splitIndex 2>/dev/null)" != true ]; then
       cp "$(cd "$src" && cd "$(dirname "$(git rev-parse --git-path index)")" && pwd)/index" "$tmp/.git/index"
       # Read the copy, not the live index, so the pack matches it; a gitlink's
       # sha (mode 160000) is a submodule commit this object store lacks.
-      GIT_INDEX_FILE="$tmp/.git/index" git -C "$src" diff --cached --raw --no-abbrev HEAD \
-        | awk '$2 != "160000" && $4 !~ /^0+$/ {print $4}' \
+      GIT_INDEX_FILE="$tmp/.git/index" git -C "$src" ls-files -s | awk '$1 != "160000" {print $2}' | sort -u \
+        | comm -23 - <(git -C "$src" ls-tree -r HEAD | awk '{print $3}' | sort -u) \
         | git -C "$src" pack-objects -q --stdout \
         | git -C "$tmp/.git" unpack-objects -q \
         || die "pack: could not snapshot the staged blobs of $src"

test/ubicloud-runner.test.ts

@@ -315,7 +315,7 @@ test('pack ships a linked worktree with a self-contained .git on the checked-out
     const d = mkdtempSync(join(tmpdir(), 'ubi-pack-live-'));
     try {
       const sh = (cmd: string, cwd: string) => { const r = Bun.spawnSync(['bash', '-c', cmd], { cwd, timeout: 60_000, env: { ...process.env, GIT_AUTHOR_NAME: 't', GIT_AUTHOR_EMAIL: 't@t', GIT_COMMITTER_NAME: 't', GIT_COMMITTER_EMAIL: 't@t' } }); expect(r.exitCode, r.stderr.toString()).toBe(0); return r.stdout.toString(); };
-      sh('git init -q --bare origin.git && git clone -q origin.git src 2>/dev/null && cd src && echo a > a && git add a && git commit -qm one && git push -q origin HEAD:main && echo b > b && git add b && git commit -qm two && git push -q origin HEAD:main && git checkout -q --detach && echo c > c && echo s > staged && git add staged', d);
+      sh('git init -q --bare origin.git && git clone -q origin.git src 2>/dev/null && cd src && echo a > a && git add a && git commit -qm one && git push -q origin HEAD:main && echo b > b && git add b && git commit -qm two && git push -q origin HEAD:main && git checkout -q --detach && echo c > c && echo s > staged && git add staged && echo i > inta && git add -N inta', d);
       const src = join(d, 'src');
       const pack = `bash ${JSON.stringify(join(DIR, 'ubi-runner.sh'))} pack .`;
       // Twenty seconds of index.lock, worktree and ref churn in the checkout while pack runs three times.
@@ -328,8 +328,8 @@ test('pack ships a linked worktree with a self-contained .git on the checked-out
       expect(lstatSync(join(vm, '.git')).isDirectory()).toBe(true);
       const head = sh('git rev-parse HEAD', src).trim();
       expect(sh('git rev-parse HEAD && git rev-parse --abbrev-ref HEAD && git rev-parse origin/main && git config --get remote.origin.url && git status --short', vm).split('\n').filter(Boolean))
-        .toEqual([head, `detached-${head.slice(0, 12)}`, head, join(d, 'origin.git'), 'A  staged', '?? c']);
-      // The staged blob is behind no ref; the snapshot carries it, so the VM can read and write-tree it.
+        .toEqual([head, `detached-${head.slice(0, 12)}`, head, join(d, 'origin.git'), ' A inta', 'A  staged', '?? c']);
+      // The staged blob and the intent-to-add entry's empty blob are behind no ref; the snapshot carries them, so the VM can read and write-tree them.
       expect(sh('git fsck --no-progress 2>&1; git diff --cached --name-only', vm).trim()).toBe('staged');
       const wtree = (cwd: string) => sh(`bash ${JSON.stringify(join(ROOT, 'bin/gstack-wtree'))}`, cwd).trim();
       expect(wtree(vm)).toBe(wtree(src));