feat(library): seed bundled starter content into the library on first run (#743)

Ship a public-domain Für Elise (keys) feedpak as starter content so a fresh
install isn't an empty library. server._seed_builtin_starter_content() copies
bundled packs into DLC_DIR/starter/ exactly once, guarded by a marker in
CONFIG_DIR — unlike the always-reseeding diagnostic seed, a user who deletes
the starter song does not get it back. `starter/` is deliberately outside the
diagnostics/tutorials library carve-out so the song surfaces as a normal
library entry.

Extract the shared symlink-safe, mtime-aware copy loop into
_copy_builtin_packs() and route both the diagnostic and starter seeds through
it (diagnostic behavior unchanged; existing tests green).

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

server.py

@@ -8,6 +8,7 @@ import logging
 import math
 import os
 import secrets
+import stat
 import sys
 import tempfile
 import shutil
@@ -5576,13 +5577,217 @@ def _get_progression_content() -> dict:
     return _progression_content
 
 
+def _copy_builtin_packs(
+    root: Path,
+    dest_dir: Path,
+    sources: list[tuple[str, str]],
+    label: str,
+    update_existing: bool = True,
+) -> int:
+    """Symlink-safe, mtime-aware copy of bundled packs into ``dest_dir``.
+
+    ``sources`` is a list of ``(dest_name, rel_source)`` pairs; each source is
+    resolved under ``root`` (the repo root in dev, ``resources/feedBack`` when
+    bundled). A pack is copied when its destination is missing. Never deletes
+    user files; refuses to follow a symlinked seed directory or destination and
+    refuses to clobber a non-regular destination (any would let a copy escape
+    ``dest_dir`` or destroy user data). Logs and continues on error. ``label``
+    prefixes every log line.
+
+    ``update_existing`` controls what happens when a *regular* destination file
+    already exists: when True (diagnostic seed) a bundle copy newer than the
+    destination refreshes it; when False (one-time starter content) an existing
+    file is always left as-is so the user's copy is never overwritten.
+
+    Returns the number of ``sources`` that are present at their destination
+    afterwards (freshly seeded, refreshed, or already current) — so callers can
+    tell whether every pack made it. A skip (missing source, symlink/non-regular
+    refusal, copy error) does not count.
+    """
+    # Refuse a symlinked seed directory: mkdir(exist_ok=True) would accept it
+    # and copies would land at the link target, outside the DLC tree. The
+    # per-file symlink guard below cannot catch this.
+    if dest_dir.is_symlink():
+        log.warning("%s: %s is a symlink, skipping all seeding", label, dest_dir.name)
+        return 0
+    dest_dir.mkdir(parents=True, exist_ok=True)
+
+    # Pin the seed directory by an O_NOFOLLOW fd so a symlink swapped in for
+    # dest_dir *after* the check above cannot redirect the per-file stat /
+    # temp-create / replace outside the DLC tree (parent-directory TOCTOU).
+    # os.replace accepts dir_fd on POSIX even though it isn't listed in
+    # os.supports_dir_fd, so gate on os.rename (the reliable proxy); platforms
+    # without dir_fd/O_NOFOLLOW (e.g. Windows) fall back to path-based ops.
+    dir_fd = None
+    if (
+        hasattr(os, "O_NOFOLLOW")
+        and hasattr(os, "O_DIRECTORY")
+        and os.open in os.supports_dir_fd
+        and os.rename in os.supports_dir_fd
+    ):
+        try:
+            dir_fd = os.open(dest_dir, os.O_RDONLY | os.O_NOFOLLOW | os.O_DIRECTORY)
+        except OSError as exc:
+            log.warning("%s: cannot open seed dir %s: %s", label, dest_dir, exc)
+            return 0
+
+    try:
+        present = 0
+        for dest_name, rel_source in sources:
+            source = root / rel_source
+            if not source.is_file():
+                log.warning("%s: source missing, skipping %s (%s)", label, dest_name, source)
+                continue
+
+            # lstat the destination without following symlinks. Pinned by dir_fd
+            # this resolves within the real seed dir, immune to a parent swap.
+            try:
+                if dir_fd is not None:
+                    dstat = os.lstat(dest_name, dir_fd=dir_fd)
+                else:
+                    dstat = os.lstat(dest_dir / dest_name)
+                dest_exists = True
+                dest_islink = stat.S_ISLNK(dstat.st_mode)
+            except FileNotFoundError:
+                dest_exists = False
+                dest_islink = False
+            except OSError as exc:
+                log.warning("%s: cannot stat %s: %s", label, dest_name, exc)
+                continue
+
+            # Refuse to seed through a symlink at the destination name.
+            if dest_islink:
+                log.warning("%s: destination is a symlink, skipping %s", label, dest_name)
+                continue
+
+            # A non-regular destination (directory, fifo, …) the user placed
+            # there: never clobber it, and never count it as present — otherwise
+            # a one-time seed would mark itself done without a real pack on disk.
+            if dest_exists and not stat.S_ISREG(dstat.st_mode):
+                log.warning("%s: destination is not a regular file, skipping %s", label, dest_name)
+                continue
+
+            if dest_exists:
+                # A regular file is already there. One-time seeds (starter
+                # content) must never overwrite the user's copy; refreshing
+                # seeds (diagnostics) replace it only when the bundle is newer.
+                if not update_existing:
+                    log.info("%s: already present %s", label, dest_name)
+                    present += 1
+                    continue
+                try:
+                    src_mtime = source.stat().st_mtime
+                except OSError as exc:
+                    log.warning("%s: cannot stat source %s: %s", label, source, exc)
+                    continue
+                if src_mtime <= dstat.st_mtime:
+                    log.info("%s: already present %s", label, dest_name)
+                    present += 1
+                    continue
+                action = "updated"
+            else:
+                action = "seeded"
+
+            if _write_builtin_pack(source, dest_dir, dest_name, dir_fd):
+                present += 1
+                log.info("%s: %s %s -> %s", label, action, source.name, dest_name)
+            else:
+                log.warning("%s: failed to copy %s -> %s/%s", label, source, dest_dir.name, dest_name)
+
+        return present
+    finally:
+        if dir_fd is not None:
+            os.close(dir_fd)
+
+
+def _write_builtin_pack(
+    source: Path,
+    dest_dir: Path,
+    dest_name: str,
+    dir_fd: int | None,
+) -> bool:
+    """Atomically write ``source`` to ``dest_name`` inside ``dest_dir``.
+
+    Writes to a temp file then ``os.replace()``s onto the final name so a
+    symlink raced in at the destination is overwritten (rename semantics), not
+    followed, and a crash never leaves a half-written pack. When ``dir_fd`` is
+    given, every step is anchored to that fd (O_NOFOLLOW temp create + dir_fd
+    replace), closing the parent-directory TOCTOU; otherwise falls back to
+    path-based temp+replace. Returns True on success. Never raises.
+    """
+    # Unique per-attempt name (O_EXCL create) so a crash that orphans a temp
+    # can't permanently block later seeds via an EEXIST collision.
+    tmp_name = f".seed-{dest_name}.{os.getpid()}.{secrets.token_hex(4)}.tmp"
+    try:
+        src_stat = source.stat()
+    except OSError as exc:
+        log.debug("builtin pack: cannot stat source %s: %s", source, exc)
+        return False
+    if dir_fd is not None:
+        tmp_fd = None
+        try:
+            tmp_fd = os.open(
+                tmp_name,
+                os.O_CREAT | os.O_EXCL | os.O_WRONLY | os.O_NOFOLLOW,
+                0o644,
+                dir_fd=dir_fd,
+            )
+            with open(source, "rb") as sf, os.fdopen(tmp_fd, "wb") as tf:
+                tmp_fd = None  # fdopen now owns the descriptor
+                shutil.copyfileobj(sf, tf)
+            os.replace(tmp_name, dest_name, src_dir_fd=dir_fd, dst_dir_fd=dir_fd)
+            # Preserve the bundle mtime (copyfileobj doesn't) so the mtime-based
+            # refresh check matches the shutil.copy2 fallback path. Best-effort.
+            try:
+                os.utime(
+                    dest_name,
+                    ns=(src_stat.st_atime_ns, src_stat.st_mtime_ns),
+                    dir_fd=dir_fd,
+                    follow_symlinks=False,
+                )
+            except OSError as exc:
+                log.debug("builtin pack: could not set mtime on %s: %s", dest_name, exc)
+            return True
+        except OSError as exc:
+            log.debug("builtin pack write (dir_fd) failed for %s: %s", dest_name, exc)
+            if tmp_fd is not None:
+                try:
+                    os.close(tmp_fd)
+                except OSError:
+                    pass
+            try:
+                os.unlink(tmp_name, dir_fd=dir_fd)
+            except OSError:
+                pass
+            return False
+
+    tmp = None
+    try:
+        fd, tmp = tempfile.mkstemp(dir=dest_dir, prefix=".seed-", suffix=".tmp")
+        os.close(fd)
+        shutil.copy2(source, tmp)
+        os.replace(tmp, dest_dir / dest_name)
+        tmp = None
+        return True
+    except OSError as exc:
+        log.debug("builtin pack write failed for %s: %s", dest_name, exc)
+        return False
+    finally:
+        if tmp is not None:
+            try:
+                os.unlink(tmp)
+            except OSError:
+                pass
+
+
 def _seed_builtin_diagnostic_sloppaks(dlc: Path | None = None) -> None:
     """Copy bundled diagnostic sloppaks into DLC before library scan.
 
     Creates ``DLC_DIR/diagnostics-builtin/`` and copies each bundled sloppak
     when the destination is missing or older than the repo/bundle source.
     Never deletes user files or touches manually copied paths (e.g.
-    ``diagnostics-test/``). Logs and continues on missing source or copy errors.
+    ``diagnostics-test/``). Re-seeds whenever the destination is missing so the
+    diagnostic target is always available. Logs and continues on errors.
     """
     try:
         if dlc is None:
@@ -5590,86 +5795,100 @@ def _seed_builtin_diagnostic_sloppaks(dlc: Path | None = None) -> None:
         if dlc is None:
             log.debug("Builtin diagnostic seed: no DLC folder configured, skipping")
             return
-
+        _copy_builtin_packs(
-        root = _feedBack_server_root()
+            _feedBack_server_root(),
-        dest_dir = dlc / _BUILTIN_DIAGNOSTIC_SUBDIR
+            dlc / _BUILTIN_DIAGNOSTIC_SUBDIR,
-        # Refuse a symlinked seed directory: mkdir(exist_ok=True) would accept
+            _BUILTIN_DIAGNOSTIC_SOURCES,
-        # it and copies would land at the link target, outside the DLC tree.
+            "Builtin diagnostic seed",
-        # The per-file is_symlink() guard below cannot catch this.
+        )
-        if dest_dir.is_symlink():
-            log.warning(
-                "Builtin diagnostic seed: %s is a symlink, skipping all seeding",
-                _BUILTIN_DIAGNOSTIC_SUBDIR,
-            )
-            return
-        dest_dir.mkdir(parents=True, exist_ok=True)
-
-        for dest_name, rel_source in _BUILTIN_DIAGNOSTIC_SOURCES:
-            source = root / rel_source
-            dest = dest_dir / dest_name
-
-            if not source.is_file():
-                log.warning(
-                    "Builtin diagnostic seed: source missing, skipping %s (%s)",
-                    dest_name,
-                    source,
-                )
-                continue
-
-            # Refuse to seed through a symlink. is_file()/stat()/copy2 all
-            # follow links, so a symlink planted at the destination would let
-            # the copy redirect outside diagnostics-builtin/ and overwrite an
-            # arbitrary file the server user can write. Skip and warn; never
-            # touch the link or its target.
-            if dest.is_symlink():
-                log.warning(
-                    "Builtin diagnostic seed: destination is a symlink, skipping %s/%s",
-                    _BUILTIN_DIAGNOSTIC_SUBDIR,
-                    dest_name,
-                )
-                continue
-
-            if dest.is_file():
-                try:
-                    if source.stat().st_mtime <= dest.stat().st_mtime:
-                        log.info(
-                            "Builtin diagnostic seed: already present %s/%s",
-                            _BUILTIN_DIAGNOSTIC_SUBDIR,
-                            dest_name,
-                        )
-                        continue
-                    action = "updated"
-                except OSError as exc:
-                    log.warning(
-                        "Builtin diagnostic seed: cannot compare %s and %s: %s",
-                        source,
-                        dest,
-                        exc,
-                    )
-                    continue
-            else:
-                action = "seeded"
-
-            try:
-                shutil.copy2(source, dest)
-                log.info(
-                    "Builtin diagnostic seed: %s %s -> %s/%s",
-                    action,
-                    source.name,
-                    _BUILTIN_DIAGNOSTIC_SUBDIR,
-                    dest_name,
-                )
-            except OSError as exc:
-                log.warning(
-                    "Builtin diagnostic seed: failed to copy %s -> %s: %s",
-                    source,
-                    dest,
-                    exc,
-                )
     except Exception:
         log.warning("Builtin diagnostic seed: unexpected error", exc_info=True)
 
 
+# Starter content: bundled songs copied into ``DLC_DIR/starter/`` exactly ONCE,
+# on first run, as a welcome library so a fresh install isn't empty. Unlike the
+# diagnostic seed this is one-time — guarded by a marker in CONFIG_DIR — so if
+# the user deletes the starter song it stays gone. ``starter/`` is NOT in the
+# library scan carve-out (unlike diagnostics-builtin/ / tutorials-builtin/), so
+# seeded packs surface as ordinary library songs.
+_BUILTIN_STARTER_SUBDIR = "starter"
+_BUILTIN_STARTER_SOURCES: list[tuple[str, str]] = [
+    (
+        "beethoven-fur_elise.feedpak",
+        "content/starter/beethoven-fur_elise.feedpak",
+    ),
+]
+_STARTER_SEED_MARKER = ".starter-content-seeded"
+
+
+def _seed_builtin_starter_content(dlc: Path | None = None) -> None:
+    """Copy bundled starter songs into ``DLC_DIR/starter/`` exactly once.
+
+    Guarded by ``CONFIG_DIR/.starter-content-seeded``: the first run with a DLC
+    folder configured seeds the packs and writes the marker; subsequent runs are
+    no-ops, so a user who deletes the starter song does not get it back on the
+    next launch. Symlink-safe; never deletes user files. Logs, never raises.
+    """
+    try:
+        marker = CONFIG_DIR / _STARTER_SEED_MARKER
+        # Already seeded? The marker is a sentinel: any existing path there
+        # (regular file, or a symlink/dir a user deliberately planted to opt
+        # out) means "done" — lstat so we detect it without following a symlink.
+        # Worst case of a planted marker is simply no starter content, never a
+        # data write; the O_EXCL|O_NOFOLLOW create below refuses to write
+        # *through* a symlink regardless.
+        try:
+            os.lstat(marker)
+            return
+        except FileNotFoundError:
+            pass
+        except OSError as exc:
+            log.warning("Starter content seed: cannot stat marker %s: %s", marker, exc)
+            return
+        if dlc is None:
+            dlc = _get_dlc_dir()
+        if dlc is None:
+            # No DLC yet — leave the marker unwritten so we retry once a
+            # library folder is configured.
+            log.debug("Starter content seed: no DLC folder configured, skipping")
+            return
+        present = _copy_builtin_packs(
+            _feedBack_server_root(),
+            dlc / _BUILTIN_STARTER_SUBDIR,
+            _BUILTIN_STARTER_SOURCES,
+            "Starter content seed",
+            update_existing=False,
+        )
+        # Only mark seeding complete once every starter pack is actually in
+        # place. If a source was missing or a copy failed, leave the marker
+        # unwritten so the next launch retries rather than permanently skipping.
+        if present < len(_BUILTIN_STARTER_SOURCES):
+            log.info(
+                "Starter content seed: %d/%d packs present, will retry next launch",
+                present,
+                len(_BUILTIN_STARTER_SOURCES),
+            )
+            return
+        # Record completion with an exclusive, no-follow create so a planted or
+        # raced symlink at the marker path can't redirect the write outside
+        # CONFIG_DIR. O_EXCL fails (EEXIST) on any existing path including a
+        # symlink, so we never write through one.
+        try:
+            CONFIG_DIR.mkdir(parents=True, exist_ok=True)
+            flags = os.O_CREAT | os.O_EXCL | os.O_WRONLY | getattr(os, "O_NOFOLLOW", 0)
+            fd = os.open(marker, flags, 0o644)
+            try:
+                os.write(fd, b"1\n")
+            finally:
+                os.close(fd)
+        except FileExistsError:
+            pass  # already marked (or a non-regular path is squatting) — fine
+        except OSError as exc:
+            log.warning("Starter content seed: could not write marker %s: %s", marker, exc)
+    except Exception:
+        log.warning("Starter content seed: unexpected error", exc_info=True)
+
+
 def _background_scan():
     """Scan the library and cache song metadata on startup. Uses a process pool to bypass the GIL for CPU-bound metadata parsing.
 
@@ -5690,6 +5909,7 @@ def _background_scan():
         return
 
     _seed_builtin_diagnostic_sloppaks(dlc)
+    _seed_builtin_starter_content(dlc)
 
     # Listing can fail on macOS without Full Disk Access, or on Docker if the
     # path isn't shared. Report the failure explicitly rather than silently

tests/test_builtin_starter_seed.py

@@ -0,0 +1,183 @@
+"""Tests for one-time builtin starter-content seeding into DLC."""
+
+from __future__ import annotations
+
+import importlib
+import sys
+
+import pytest
+
+
+@pytest.fixture()
+def server_mod(tmp_path, monkeypatch, isolate_logging):
+    monkeypatch.setenv("CONFIG_DIR", str(tmp_path / "config"))
+    (tmp_path / "config").mkdir()
+    monkeypatch.delenv("DLC_DIR", raising=False)
+    sys.modules.pop("server", None)
+    mod = importlib.import_module("server")
+    yield mod
+
+
+def _source(server_mod):
+    return (
+        server_mod._feedBack_server_root()
+        / server_mod._BUILTIN_STARTER_SOURCES[0][1]
+    )
+
+
+def _dest(server_mod, dlc):
+    return (
+        dlc
+        / server_mod._BUILTIN_STARTER_SUBDIR
+        / server_mod._BUILTIN_STARTER_SOURCES[0][0]
+    )
+
+
+def test_seed_creates_starter_content_and_marker(tmp_path, server_mod):
+    """First run copies the bundled feedpak into starter/ and writes the marker."""
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    source = _source(server_mod)
+    if not source.is_file():
+        pytest.skip(f"starter source not present in checkout: {source}")
+
+    server_mod._seed_builtin_starter_content(dlc)
+
+    dest = _dest(server_mod, dlc)
+    assert dest.is_file()
+    assert dest.stat().st_size == source.stat().st_size
+    assert (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).is_file()
+
+
+def test_seed_preserves_source_mtime(tmp_path, server_mod):
+    """The seeded pack keeps the bundle's mtime so the diagnostic refresh check
+    (source newer than dest -> update) stays correct across both write paths."""
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    source = _source(server_mod)
+    if not source.is_file():
+        pytest.skip(f"starter source not present in checkout: {source}")
+
+    server_mod._seed_builtin_starter_content(dlc)
+
+    assert _dest(server_mod, dlc).stat().st_mtime_ns == source.stat().st_mtime_ns
+
+
+def test_starter_is_not_carved_out_of_the_library():
+    """`starter/` must NOT collide with the diagnostics/tutorials carve-out —
+    otherwise seeded songs would never appear in the library listing."""
+    assert "starter" not in {"diagnostics-builtin", "tutorials-builtin"}
+
+
+def test_seed_runs_only_once_and_respects_deletion(tmp_path, server_mod):
+    """After the first seed, deleting the song does NOT bring it back: the
+    marker makes starter seeding a one-time welcome."""
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    source = _source(server_mod)
+    if not source.is_file():
+        pytest.skip(f"starter source not present in checkout: {source}")
+
+    server_mod._seed_builtin_starter_content(dlc)
+    dest = _dest(server_mod, dlc)
+    assert dest.is_file()
+
+    # User removes the starter song.
+    dest.unlink()
+
+    # A subsequent launch must not re-seed it.
+    server_mod._seed_builtin_starter_content(dlc)
+    assert not dest.exists()
+
+
+def test_seed_deferred_until_dlc_configured(tmp_path, server_mod):
+    """With no DLC folder, seeding is skipped WITHOUT writing the marker, so it
+    retries once a library folder exists."""
+    source = _source(server_mod)
+    if not source.is_file():
+        pytest.skip(f"starter source not present in checkout: {source}")
+
+    # dlc is None and DLC_DIR unset -> _get_dlc_dir() returns None.
+    server_mod._seed_builtin_starter_content(None)
+    assert not (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).exists()
+
+    # Now a DLC is configured: the deferred seed runs.
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    server_mod._seed_builtin_starter_content(dlc)
+    assert _dest(server_mod, dlc).is_file()
+    assert (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).is_file()
+
+
+def test_seed_refuses_symlinked_seed_directory(tmp_path, server_mod):
+    """A symlinked starter/ dir is refused so copies can't escape the DLC tree."""
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    source = _source(server_mod)
+    if not source.is_file():
+        pytest.skip(f"starter source not present in checkout: {source}")
+
+    outside_dir = tmp_path / "outside"
+    outside_dir.mkdir()
+    (dlc / server_mod._BUILTIN_STARTER_SUBDIR).symlink_to(outside_dir)
+
+    server_mod._seed_builtin_starter_content(dlc)
+
+    assert list(outside_dir.iterdir()) == []
+    # An incomplete seed must NOT write the marker, so a later launch retries.
+    assert not (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).exists()
+
+
+def test_seed_never_overwrites_an_existing_user_file(tmp_path, server_mod):
+    """One-time starter seeding must never replace a user's own file at the
+    destination, even if the bundled pack has a newer mtime."""
+    import os as _os
+
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    dest = _dest(server_mod, dlc)
+    dest.parent.mkdir(parents=True, exist_ok=True)
+    dest.write_bytes(b"user's own edited pack")
+    _os.utime(dest, (1_000_000, 1_000_000))  # far older than the bundled source
+
+    server_mod._seed_builtin_starter_content(dlc)
+
+    assert dest.read_bytes() == b"user's own edited pack"  # untouched
+    # counted as already-present, so the one-time seed considers itself done
+    assert (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).is_file()
+
+
+def test_seed_does_not_mark_when_destination_is_a_directory(tmp_path, server_mod):
+    """A directory sitting at the destination name is neither clobbered nor
+    counted as present, so the marker stays unwritten and seeding retries."""
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    source = _source(server_mod)
+    if not source.is_file():
+        pytest.skip(f"starter source not present in checkout: {source}")
+
+    bogus = _dest(server_mod, dlc)
+    bogus.parent.mkdir(parents=True, exist_ok=True)
+    bogus.mkdir()  # user (or junk) placed a directory where the pack goes
+
+    server_mod._seed_builtin_starter_content(dlc)
+
+    assert bogus.is_dir()  # untouched
+    assert not (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).exists()
+
+
+def test_seed_does_not_mark_when_source_missing(tmp_path, server_mod, monkeypatch):
+    """If a starter source can't be found, the marker stays unwritten and the
+    seed is retried on the next launch (rather than permanently skipped)."""
+    dlc = tmp_path / "dlc"
+    dlc.mkdir()
+    monkeypatch.setattr(
+        server_mod,
+        "_BUILTIN_STARTER_SOURCES",
+        [("missing.feedpak", "content/starter/does-not-exist.feedpak")],
+    )
+
+    server_mod._seed_builtin_starter_content(dlc)
+
+    assert not (dlc / server_mod._BUILTIN_STARTER_SUBDIR / "missing.feedpak").exists()
+    assert not (server_mod.CONFIG_DIR / server_mod._STARTER_SEED_MARKER).exists()