Attachments stored once; nightly clean-up of unused files

Attachments are no longer stored apart from their message (they were kept
twice: base64 inside the raw message and decoded on their own). The indexer
records the MIME part (attachments.part_index, migration 0023); downloads,
zip, inline images, thumbnails and forwarding take it out of the message;
videos stream from a short-lived copy (kept a day, 1 GiB per user). A
background pass on worker start removes the copies stored before, each only
after checking it can be taken out again (spec App. D §D.6 item 1, criterion
corrected to <= 60%).

A nightly job (03:47, after the Trash/Spam purge) removes files nothing
refers to any more — deleted or purged messages, previews of attachments
gone, uploads no draft has used for a week, expired streaming copies. Files
younger than an hour are left alone; a sent message waiting for its Sent copy
is held until its job is done. Account removal keeps files a draft still uses.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

backend/app/indexer/mime.py

@@ -41,6 +41,9 @@ class ParsedAttachment:
     mime_type: str
     content_id: str | None
     payload: bytes
+    # The part's position in ``msg.walk()``: where to find it again in the raw
+    # message, which is the only copy kept (attachments are not stored apart).
+    part_index: int = -1
 
 
 @dataclass
@@ -114,7 +117,7 @@ def _extract_attachments(msg: EmailMessage) -> list[ParsedAttachment]:
     # or inline resource if it has a filename, a Content-ID, or attachment disposition;
     # the body text/plain and text/html parts have none of these and are skipped.
     out: list[ParsedAttachment] = []
-    for part in msg.walk():
+    for index, part in enumerate(msg.walk()):
         if part.is_multipart() or not isinstance(part, EmailMessage):
             continue
         cid = part.get("Content-ID")
@@ -137,13 +140,14 @@ def _extract_attachments(msg: EmailMessage) -> list[ParsedAttachment]:
                 mime_type=part.get_content_type(),
                 content_id=cid.strip("<>") if (inline and cid is not None) else None,
                 payload=payload,
+                part_index=index,
             )
         )
     # An invitation sent only as the text/calendar alternative (Outlook, often) has
     # no file to show: keep it as invite.ics, so the event can be seen, answered
     # and downloaded like a Gmail one. Not when the message attaches its own .ics.
     if not any(a.filename.lower().endswith(".ics") for a in out):
-        for part in msg.walk():
+        for index, part in enumerate(msg.walk()):
             if part.get_content_type() != "text/calendar" or part.get_filename():
                 continue
             payload = part.get_payload(decode=True)
@@ -154,6 +158,7 @@ def _extract_attachments(msg: EmailMessage) -> list[ParsedAttachment]:
                         mime_type="text/calendar",
                         content_id=None,
                         payload=payload,
+                        part_index=index,
                     )
                 )
                 break
@@ -215,3 +220,36 @@ def _parse_email(msg: EmailMessage) -> ParsedEmail:
         html_body=_scrub(html_body) if html_body is not None else None,
         attachments=_extract_attachments(msg),
     )
+
+
+def load_message(
+    raw: bytes | None = None, path: str | os.PathLike[str] | None = None
+) -> EmailMessage:
+    """The parsed tree of a raw message, from memory or straight from its file."""
+    if path is not None:
+        with open(path, "rb") as handle:
+            msg = email.message_from_binary_file(handle, policy=default_policy)
+    else:
+        msg = email.message_from_bytes(raw or b"", policy=default_policy)
+    assert isinstance(msg, EmailMessage)
+    return msg
+
+
+def part_payload(msg: EmailMessage, part_index: int | None, sha256: str) -> bytes | None:
+    """The decoded bytes of the attachment whose content hashes to ``sha256``:
+    the part at ``part_index`` when that is it, else whichever part is (rows
+    stored before the index was kept). None when the message has no such part."""
+    import hashlib
+
+    parts = list(msg.walk())
+    if part_index is not None and 0 <= part_index < len(parts):
+        payload = parts[part_index].get_payload(decode=True)
+        if isinstance(payload, bytes) and hashlib.sha256(payload).hexdigest() == sha256:
+            return payload
+    for part in parts:
+        if part.is_multipart():
+            continue
+        payload = part.get_payload(decode=True)
+        if isinstance(payload, bytes) and hashlib.sha256(payload).hexdigest() == sha256:
+            return payload
+    return None