feat(audiobook): recognise .mp4 as an audiobook format (#1264)

## Problem

Some trackers — MyAnonamouse in particular — distribute AAC audiobooks
as per-chapter `.mp4` files. That's the same ISO-BMFF container as
`.m4a`/`.m4b`, just with the generic extension (`ftyp isom`,
audio-only).

Today those releases:
1. show up in Prowlarr search results with **no format chip** — only the
generic "Audiobook" icon, because no format could be inferred;
2. download successfully; then
3. fail post-processing with **"No book files found in download"**,
because `.mp4` isn't in `AUDIOBOOK_FORMATS` (`shelfmark/core/utils.py`).

Real example: MAM #627978, *The Martian* (Andy Weir, 2020 edition) — 142
files `0001 … 0142 Andy Weir (2020) The Martian.mp4` + `cover.jpg`, 305
MB. Every file is a valid AAC-in-MP4 chapter.

Adding `mp4` to `SUPPORTED_AUDIOBOOK_FORMATS` in `settings.json` doesn't
help since the hard-coded tuple is what post-processing scans against.

## Change

- Add `"mp4"` to `AUDIOBOOK_FORMATS` (single source of truth — settings
UI, Prowlarr parsing, IRC parser, archive extraction and post-download
scan all derive from it), with a comment explaining why.
- Add `".mp4"` to the two hand-maintained debrid `_BOOK_EXTENSIONS`
lists (AllDebrid / Real-Debrid) so file selection matches.
- Slot `mp4` into the IRC `AUDIOBOOK_FORMAT_PRIORITY` table right after
`m4a` (same container family).
- Update the documented default in `docs/environment-variables.md`.
- New regression test
`test_audiobook_multifile_mp4_chapters_are_book_files` modelled on the
existing multi-file usenet test.

### Note for existing installs

The legacy-default migration only widens configs that still hold the old
`m4b,mp3` list, so users on the current widened default won't pick up
`mp4` automatically — they'll need to tick it in Settings → Audiobook
formats. New installs get it by default. Happy to extend the migration
if you'd rather it be automatic.

## Testing

- `ruff check` / `ruff format --check`: clean
- `pytest tests/core tests/config tests/irc tests/prowlarr
tests/download -m "not integration and not e2e"`: 2296 passed, new test
+ `test_audiobook_format_consistency.py` all green. The 10 failures in
`test_entrypoint_permissions.py` / `test_orchestrator_stall.py`
reproduce identically on untouched `main` on macOS and are unrelated.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

docs/environment-variables.md

@@ -247,7 +247,7 @@ Seconds since the last WireGuard handshake before the healthcheck bounces the tu
 | `CALIBRE_WEB_URL` | Adds a navigation button to your book library (Calibre-Web Automated, Grimmory, etc). | string | _none_ |
 | `AUDIOBOOK_LIBRARY_URL` | Adds a separate navigation button for your audiobook library (Audiobookshelf, Plex, etc). When both URLs are set, icons are shown instead of text. | string | _none_ |
 | `SUPPORTED_FORMATS` | Book formats to include in search results. ZIP/RAR archives are extracted automatically and book files are used if found. | string (comma-separated) | `epub,mobi,azw3,fb2,djvu,cbz,cbr` |
-| `SUPPORTED_AUDIOBOOK_FORMATS` | Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found. | string (comma-separated) | `m4b,mp3,m4a,flac,ogg,wma,aac,wav,opus,zip,rar` |
+| `SUPPORTED_AUDIOBOOK_FORMATS` | Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found. | string (comma-separated) | `m4b,mp3,m4a,mp4,flac,ogg,wma,aac,wav,opus,zip,rar` |
 | `BOOK_LANGUAGE` | Default language filter for searches. | string (comma-separated) | `en` |
 
 <details>
@@ -296,7 +296,7 @@ Book formats to include in search results. ZIP/RAR archives are extracted automa
 Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found.
 
 - **Type:** string (comma-separated)
-- **Default:** `m4b,mp3,m4a,flac,ogg,wma,aac,wav,opus,zip,rar`
+- **Default:** `m4b,mp3,m4a,mp4,flac,ogg,wma,aac,wav,opus,zip,rar`
 
 #### `BOOK_LANGUAGE`
 

shelfmark/core/utils.py

@@ -122,7 +122,12 @@ def is_audiobook(content_type: str | None) -> bool:
 # had drifted apart: the settings UI only offered m4b/mp3/m4a, which meant a FLAC
 # audiobook could never be enabled, was silently dropped from every search result, and
 # was rejected after download as "format not supported".
-AUDIOBOOK_FORMATS = ("m4b", "mp3", "m4a", "flac", "ogg", "wma", "aac", "wav", "opus")
+#
+# "mp4" is here because some trackers (MyAnonamouse in particular) ship AAC audiobooks
+# as per-chapter .mp4 files - the same ISO-BMFF container as .m4a/.m4b, just with the
+# generic extension. Without it those releases downloaded fine and then failed
+# post-processing with "No book files found in download".
+AUDIOBOOK_FORMATS = ("m4b", "mp3", "m4a", "mp4", "flac", "ogg", "wma", "aac", "wav", "opus")
 
 # Multi-file audiobooks are almost always distributed as an archive. These are containers
 # rather than formats: they are what a *release* looks like, and the formats above are

shelfmark/download/clients/alldebrid.py

@@ -76,6 +76,7 @@ _BOOK_EXTENSIONS = (
     ".m4b",
     ".mobi",
     ".mp3",
+    ".mp4",
     ".ogg",
     ".opus",
     ".pdf",

shelfmark/download/clients/realdebrid.py

@@ -80,6 +80,7 @@ _BOOK_EXTENSIONS = (
     ".m4b",
     ".mobi",
     ".mp3",
+    ".mp4",
     ".ogg",
     ".opus",
     ".pdf",

shelfmark/release_sources/irc/source.py

@@ -428,14 +428,15 @@ class IRCReleaseSource(ReleaseSource):
         "m4b": 0,
         "mp3": 1,
         "m4a": 2,
-        "flac": 3,
-        "opus": 4,
-        "ogg": 5,
-        "aac": 6,
-        "wav": 7,
-        "wma": 8,
-        "rar": 9,
-        "zip": 10,
+        "mp4": 3,
+        "flac": 4,
+        "opus": 5,
+        "ogg": 6,
+        "aac": 7,
+        "wav": 8,
+        "wma": 9,
+        "rar": 10,
+        "zip": 11,
     }
 
     def _convert_to_releases(

tests/core/test_processing_integration.py

@@ -1458,3 +1458,47 @@ def test_external_directory_prefers_files_over_archives_and_keeps_source(
 
     # TMP staging should be cleaned.
     assert list(staging.iterdir()) == []
+
+
+def test_audiobook_multifile_mp4_chapters_are_book_files(tmp_path):
+    """Per-chapter .mp4 audiobooks (as MyAnonamouse ships AAC releases) must be
+    recognised as book files instead of failing with "No book files found"."""
+    from shelfmark.download.postprocess.router import (
+        post_process_download as _post_process_download,
+    )
+
+    source_dir = tmp_path / "downloads" / "Andy Weir (2020) The Martian"
+    source_dir.mkdir(parents=True)
+    for part in (1, 2):
+        (source_dir / f"{part:04d} Andy Weir (2020) The Martian.mp4").write_text(f"audio{part}")
+    (source_dir / "cover.jpg").write_text("jpg")
+
+    ingest = tmp_path / "ingest"
+    ingest.mkdir()
+    task = DownloadTask(
+        task_id="mp4-audio-grouped",
+        source="prowlarr",
+        title="The Martian",
+        author="Andy Weir",
+        format="mp4",
+        content_type="audiobook",
+        search_mode=SearchMode.UNIVERSAL,
+    )
+
+    with patch("shelfmark.core.config.config") as mock_config:
+        mock_config.get = _build_config(
+            ingest,
+            organization="rename_and_group",
+            supported_audiobook_formats=["mp4"],
+        )
+        mock_config.CUSTOM_SCRIPT = None
+
+        result = _post_process_download(source_dir, task, Event(), lambda *_args: None)
+
+    grouped_dir = ingest / "Andy Weir (2020) The Martian"
+    assert result is not None
+    assert Path(result).parent == grouped_dir
+    assert sorted(path.name for path in grouped_dir.glob("*.mp4")) == [
+        "0001 Andy Weir (2020) The Martian.mp4",
+        "0002 Andy Weir (2020) The Martian.mp4",
+    ]