search: email address search + address-first ranking; inline images; folder i18n; link security

Search (PG backend):
- '@' terms match address substrings (from/to/cc), so a partial email like
  "dyrektor@wfdif" resolves and narrows predictably as you type
- index each address split into parts, so a bare domain/local word ("wfdif")
  finds the address (indexed as one lexeme otherwise); dotted terms fall back to
  an address substring
- rank sender/recipient name+address matches above body/subject-only ones
  (addr_hit tier, then recency); cursor extended to keep keyset pagination correct
- scripts/reindex_address_parts.py backfills address tokens into existing rows

Inline images:
- extract attachments via a full MIME walk instead of shallow iter_attachments(),
  which missed inline images nested in mixed>related>alternative (cid: rendered
  broken); has_attachments counts only real (non-cid) attachments
- scripts/backfill_inline_attachments.py stores previously-missed inline images

Folder-name i18n (SPEC §12 M2):
- accent/punctuation-insensitive, multi-delimiter (/ \ .) special-use inference
  across ~13 languages; curated names (no substring false positives)

Link security (reading panel):
- links never navigate the message iframe: a parent-side click interceptor opens
  http/https in a new tab (noopener) and mailto in the composer (recipient
  pre-filled); all other schemes blocked

Backend 292 tests green, ruff + mypy --strict clean; frontend tsc/eslint/vitest clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01U72FZiF1W1pb8XxyWBTREA

backend/tests/indexer/test_mime.py

@@ -93,6 +93,39 @@ def test_attachment_extracted() -> None:
     assert parsed.attachments[0].payload == b"\x00\x01\x02data"
 
 
+def test_inline_image_nested_in_related_is_extracted() -> None:
+    # Real-world structure: mixed > related > alternative(text, html) + inline image.
+    # iter_attachments() misses the nested image; a full walk must find it so the
+    # cid: reference resolves (regression: broken inline image).
+    from email.mime.image import MIMEImage
+    from email.mime.multipart import MIMEMultipart
+    from email.mime.text import MIMEText
+
+    root = MIMEMultipart("mixed")
+    root["Subject"] = "newsletter"
+    root["From"] = "biuro@kipa.pl"
+    root["To"] = "me@example.com"
+    root["Message-ID"] = "<n@x.com>"
+    related = MIMEMultipart("related")
+    alt = MIMEMultipart("alternative")
+    alt.attach(MIMEText("text version", "plain"))
+    alt.attach(MIMEText('<p>Hi <img src="cid:img001"></p>', "html"))
+    related.attach(alt)
+    img = MIMEImage(b"\x89PNG\r\n\x1a\ndata", "png")
+    img.add_header("Content-ID", "<img001>")
+    img.add_header("Content-Disposition", "inline", filename="image001.png")
+    related.attach(img)
+    root.attach(related)
+
+    parsed = parse_message(root.as_bytes())
+    assert len(parsed.attachments) == 1
+    att = parsed.attachments[0]
+    assert att.content_id == "img001"
+    assert att.mime_type == "image/png"
+    # Inline-only: no attachment chip / paperclip.
+    assert parsed.has_attachments is False
+
+
 def test_missing_message_id_returns_none() -> None:
     msg = EmailMessage()
     msg["Subject"] = "no id"

backend/tests/search/test_search_api.py

@@ -168,6 +168,36 @@ async def test_free_text_full_email_address(seeded: Ctx) -> None:
     assert await _search(seeded, "bob@corp.co") == 1  # prefix while still typing
 
 
+async def test_free_text_email_matches_address_consistently(seeded: Ctx) -> None:
+    # A term with '@' is treated as an address search and matches as a substring
+    # of from/to/cc, so it narrows *predictably* as you type more of the address
+    # (a partial term never returns more than the fuller one).
+    assert await _search(seeded, "bob@") == 1  # local part -> bob only
+    assert await _search(seeded, "bob@corp") == 1
+    assert await _search(seeded, "bob@co") == 1
+    assert await _search(seeded, "@corp.com") == 3  # all three share the domain
+    assert await _search(seeded, "zzz@corp") == 0  # no such sender
+
+
+async def test_address_matches_rank_before_body_matches(ctx: Ctx) -> None:
+    # Older message matches "zebra" only via its sender address; the newer one
+    # matches only in the body. The address/name hit must still come first.
+    await _ingest(ctx, frm="Zebra Corp <hello@zebra.com>", subject="hi", body="nothing here")
+    await _ingest(ctx, frm="Someone <someone@corp.com>", subject="a note", body="the zebra ran")
+    resp = await ctx.client.get("/api/search", params={"q": "zebra"})
+    subjects = [t["thread"]["subject"] for t in resp.json()["threads"]]
+    assert subjects == ["hi", "a note"]  # address hit first, then body-only
+
+
+async def test_free_text_bare_domain_word_matches_address(seeded: Ctx) -> None:
+    # A bare domain/local word finds the address even though Postgres indexes the
+    # whole address as one lexeme — address parts are tokenized at index time.
+    assert await _search(seeded, "corp") == 3  # the domain word -> all three
+    assert await _search(seeded, "carol") == 1  # local part -> carol only
+    # A dotted domain term also matches via the address-substring fallback.
+    assert await _search(seeded, "corp.com") == 3
+
+
 async def test_from_operator(seeded: Ctx) -> None:
     assert await _search(seeded, "from:bob") == 1
     assert await _search(seeded, "from:corp.com") == 3  # all three share the domain

backend/tests/sync/test_folder_names.py

@@ -1,4 +1,4 @@
-"""Folder-name special-use heuristics (SPEC §6.3)."""
+"""Folder-name special-use heuristics (SPEC §6.3 / §12 M2)."""
 
 from __future__ import annotations
 
@@ -10,24 +10,64 @@ from app.sync.folder_names import infer_special_use
 @pytest.mark.parametrize(
     "path,expected",
     [
+        # inbox
         ("INBOX", "inbox"),
         ("inbox", "inbox"),
+        ("INBOX.", "inbox"),  # Dovecot may show a trailing delimiter
+        # English / Outlook / Gmail
         ("Sent", "sent"),
-        ("Wysłane", "sent"),  # Polish
-        ("Elementy wysłane", "sent"),
-        ("Gesendet", "sent"),  # German
+        ("Sent Items", "sent"),
+        ("[Gmail]/Sent Mail", "sent"),
         ("Drafts", "drafts"),
-        ("Robocze", "drafts"),
-        ("Trash", "trash"),
-        ("Kosz", "trash"),  # Polish
-        ("Papierkorb", "trash"),  # German
-        ("Spam", "junk"),
+        ("Deleted Items", "trash"),
+        ("Bin", "trash"),
         ("Junk", "junk"),
+        ("Junk E-mail", "junk"),  # Outlook, punctuation-insensitive
+        ("[Gmail]/Spam", "junk"),
         ("Archive", "archive"),
+        ("[Gmail]/All Mail", "archive"),
+        # Polish (accents)
+        ("Wysłane", "sent"),
+        ("Elementy wysłane", "sent"),
+        ("Robocze", "drafts"),
+        ("Kosz", "trash"),
+        ("Wiadomości-śmieci", "junk"),
         ("Archiwum", "archive"),
-        ("INBOX/Sent", "sent"),  # nested leaf
+        # German
+        ("Gesendet", "sent"),
+        ("Gesendete Elemente", "sent"),
+        ("Entwürfe", "drafts"),
+        ("Papierkorb", "trash"),
+        ("Gelöschte Elemente", "trash"),
+        # French
+        ("Éléments envoyés", "sent"),
+        ("Brouillons", "drafts"),
+        ("Corbeille", "trash"),
+        ("Courrier indésirable", "junk"),
+        # Spanish / Italian / Dutch / Portuguese
+        ("Enviados", "sent"),
+        ("Papelera", "trash"),
+        ("Posta inviata", "sent"),
+        ("Cestino", "trash"),
+        ("Verzonden", "sent"),
+        ("Prullenbak", "trash"),
+        ("Itens enviados", "sent"),
+        ("Lixeira", "trash"),
+        # Russian (Cyrillic)
+        ("Отправленные", "sent"),
+        ("Корзина", "trash"),
+        ("Черновики", "drafts"),
+        ("Спам", "junk"),
+        # delimiters / nesting
+        ("INBOX/Sent", "sent"),
+        ("INBOX.Sent", "sent"),  # Dovecot dot delimiter
+        ("INBOX.Trash", "trash"),
+        # negatives — must not misfire
         ("Work", None),
         ("Random Folder", None),
+        ("Sent to John", None),  # curated names, not substring match
+        ("Newsletter", None),
+        ("Projects/Client", None),
     ],
 )
 def test_infer_special_use(path: str, expected: str | None) -> None: