feat: the extension picks a Discord source's posters from who posts in the channel, stored by id (#4488)

On a Discord channel page the Add panel lists who posted in the newest 200
messages, the creator the server is named for (or owned by) ticked. On a
channel FabledCurator already follows, the chip opens the same list with Save
and Open artist. The list is kept as user ids, so a rename never quietly stops
it matching; the name each was picked under rides beside it for display, and
the Subscriptions dialog shows it.

- DiscordClient.recent_posters + rank_posters (owner / name-matches-server;
  bots never suggested; it suggests, the operator ticks).
- GET/POST /api/extension/discord/posters; quick-add takes discord_authors.

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

backend/app/services/discord_client.py

@@ -75,6 +75,9 @@ _THREADS_BATCH = 25
 # it is honoured when present; 60s is the fallback and the cap.
 _MAX_429_RETRIES = 4
 _429_WAIT_SECONDS = 60.0
+# How far back the poster picker looks: two pages. Enough to see who posts in
+# a channel, few enough to answer while the operator waits (#4488).
+_POSTER_SCAN = 200
 
 # https://discord.com/developers/docs/resources/message#message-object-message-types
 # DEFAULT, REPLY, CHAT_INPUT_COMMAND — the ones that carry user content.
@@ -204,6 +207,55 @@ def has_visual_attachment(message: dict) -> bool:
     )
 
 
+_SQUASH = re.compile(r"[\W_]+", re.UNICODE)
+# Words a server name wraps around its creator's: "Todding's Server",
+# "The Official Todding Discord".
+_SERVER_WORDS = frozenset({"server", "discord", "the", "official", "community", "s"})
+
+
+def _squash(text: str | None) -> str:
+    return _SQUASH.sub("", (text or "").lower())
+
+
+def _server_tokens(server_name: str | None) -> list[str]:
+    name = (server_name or "").lower().replace("'s", " ").replace("\u2019s", " ")
+    words = [w for w in _SQUASH.split(name) if w and w not in _SERVER_WORDS]
+    tokens = [w for w in words if len(w) >= 3]
+    joined = "".join(words)
+    if len(joined) >= 3 and joined not in tokens:
+        tokens.append(joined)
+    return tokens
+
+
+def rank_posters(server_name: str | None, owner_id, posters: list[dict]) -> list[dict]:
+    """Mark who is probably the creator a server is named for, and order the
+    list for picking: suggested first, then by images posted, then messages.
+
+    Two signals, each a reason the picker shows beside the name:
+      - they own the server;
+      - their username or display name matches the server's name, once
+        "'s Server", "Official", "Discord" and punctuation are taken off
+        ("Todding's Server" and "todding").
+    Neither signal alone is proof, which is why this suggests and never
+    decides: the operator ticks the list. Bots are never suggested."""
+    tokens = _server_tokens(server_name)
+    owner = str(owner_id) if owner_id else None
+    ranked = []
+    for p in posters:
+        reasons = []
+        if owner and p.get("id") == owner:
+            reasons.append("owns the server")
+        names = [n for n in (_squash(p.get("username")), _squash(p.get("global_name"))) if len(n) >= 3]
+        if any(t in n or n in t for t in tokens for n in names):
+            reasons.append("name matches the server")
+        ranked.append({**p, "reasons": reasons, "suggested": False})
+    best = max((len(r["reasons"]) for r in ranked if not r.get("bot")), default=0)
+    for r in ranked:
+        r["suggested"] = best > 0 and not r.get("bot") and len(r["reasons"]) == best
+    ranked.sort(key=lambda r: (not r["suggested"], -r.get("images", 0), -r.get("messages", 0)))
+    return ranked
+
+
 @dataclass
 class MediaItem:
     """One file of a Discord message. `filename`/`extension` are gallery-dl's
@@ -611,6 +663,61 @@ class DiscordClient:
                 pass
         return out
 
+    def recent_posters(
+        self, server_id: str | None, channel_id: str, *, max_messages: int = _POSTER_SCAN,
+    ) -> dict:
+        """Who has posted lately in a channel, for picking a source's poster
+        list (#4488): the newest `max_messages` messages, tallied per author.
+        Deliberately shallow — it answers "who posts here", not "who ever did".
+        Every poster comes back with their stable id, which is what the list
+        stores: a username can change on a whim, an id can't."""
+        server: dict = {}
+        if server_id:
+            try:
+                server = self._get(f"/guilds/{server_id}") or {}
+            except DiscordAPIError:
+                server = {}
+        tally: dict[str, dict] = {}
+        before = None
+        seen = 0
+        while seen < max_messages:
+            page = self._get(
+                f"/channels/{channel_id}/messages",
+                {"limit": min(_MESSAGES_BATCH, max_messages - seen), "before": before},
+            )
+            if not isinstance(page, list) or not page:
+                break
+            for message in page:
+                seen += 1
+                if message.get("type") not in MESSAGE_TYPES:
+                    continue
+                author = message.get("author") or {}
+                aid = str(author.get("id") or "")
+                if not aid:
+                    continue
+                row = tally.setdefault(aid, {
+                    "id": aid,
+                    "username": author.get("username"),
+                    "global_name": author.get("global_name"),
+                    "bot": bool(author.get("bot")),
+                    "messages": 0,
+                    "images": 0,
+                })
+                row["messages"] += 1
+                if has_visual_attachment(message):
+                    row["images"] += 1
+            if len(page) < _MESSAGES_BATCH:
+                break
+            before = str(page[-1]["id"])
+        return {
+            "server": server.get("name") or None,
+            "owner_id": str(server["owner_id"]) if server.get("owner_id") else None,
+            "scanned": seen,
+            "posters": rank_posters(
+                server.get("name"), server.get("owner_id"), list(tally.values()),
+            ),
+        }
+
     def verify_auth(self, url: str) -> tuple[bool | None, str]:
         """Is the token valid, and can it see what the source names?"""
         try:

backend/app/services/extension_service.py

@@ -23,6 +23,12 @@ log = logging.getLogger(__name__)
 
 # The probe runs while the chip is drawing; names that take longer are skipped.
 _NAME_LOOKUP_SECONDS = 6.0
+# The poster picker waits on two pages of a channel's messages (#4488).
+_POSTER_LOOKUP_SECONDS = 20.0
+
+# A source's poster list (discord_ingester.AUTHORS_KEY) holds user ids; this
+# keeps the name each id was picked under, for showing the list to a person.
+AUTHOR_LABELS_KEY = "discord_author_labels"
 
 
 class UnknownPlatformError(Exception):
@@ -37,6 +43,15 @@ class UnknownArtistError(Exception):
     """quick-add named an `artist_id` that does not exist."""
 
 
+class PosterLookupError(Exception):
+    """The Discord poster picker couldn't read the channel (no token, no
+    access, not a channel page, or Discord was slow)."""
+
+
+class UnknownSourceError(Exception):
+    """No source follows this Discord channel or its server."""
+
+
 # Mirrored byte-for-byte from extension/lib/platforms.js
 # PLATFORM_ARTIST_PATTERNS. Keep these two copies in sync by hand —
 # reviewers catch drift.
@@ -110,6 +125,7 @@ class ExtensionService:
         artist_id: int | None = None,
         artist_name: str | None = None,
         use_platform_name: bool = False,
+        discord_authors: list[dict] | None = None,
     ) -> dict:
         """Add `url` as a source. `artist_id` connects it to an existing
         artist, `artist_name` to that artist (created if new); with neither,
@@ -119,7 +135,10 @@ class ExtensionService:
         name is canon: a Patreon source added to an existing artist renames
         that artist to the creator's Patreon display name. Name only — the
         slug, and every path keyed off it, never moves (#130). Ignored on every
-        other platform, and when the name can't be read."""
+        other platform, and when the name can't be read.
+
+        `discord_authors` ([{id, name}], #4488) sets a Discord source's poster
+        list in the same step, on a new source or one already there."""
         platform, raw_slug = self._derive(url)
         url = canonical_source_url(platform, url, raw_slug)
         renamed_from = None
@@ -133,6 +152,8 @@ class ExtensionService:
             artist = (await self.session.execute(
                 select(Artist).where(Artist.id == existing.artist_id)
             )).scalar_one()
+            if platform == DISCORD and discord_authors is not None:
+                await self._apply_posters(existing, discord_authors)
             return self._shape(existing, artist, created_source=False, created_artist=False)
 
         if artist_id is not None:
@@ -154,11 +175,98 @@ class ExtensionService:
         source, created_source = await self._find_or_create_source(
             artist_id=artist.id, platform=platform, url=url,
         )
+        if platform == DISCORD and discord_authors is not None:
+            await self._apply_posters(source, discord_authors)
         shaped = self._shape(source, artist, created_source, created_artist)
         if renamed_from is not None:
             shaped["renamed_from"] = renamed_from
         return shaped
 
+    # -- Discord poster picker (#4488) ------------------------------------------
+
+    def _discord_page(self, url: str) -> tuple[str, str]:
+        platform, raw_slug = self._derive(url)
+        if platform != DISCORD:
+            raise InvalidUrlError("not a Discord page")
+        server_id, _, channel_id = raw_slug.partition("/")
+        if not channel_id:
+            raise PosterLookupError("Open a channel to see who posts in it.")
+        return server_id, channel_id
+
+    async def _source_for_page(self, server_id: str, channel_id: str) -> Source | None:
+        """The source this channel's posts land on: the channel's own, else a
+        whole-server source that walks it."""
+        base = f"https://discord.com/channels/{server_id}"
+        return (
+            await self._existing_source(DISCORD, f"{base}/{channel_id}")
+            or await self._existing_source(DISCORD, base)
+        )
+
+    async def discord_posters(self, url: str) -> dict:
+        """Who posts in the channel `url` shows, newest `_POSTER_SCAN`
+        messages deep, with the likely creator marked — and, when a source
+        already follows it, the poster list that source has now."""
+        server_id, channel_id = self._discord_page(url)
+        import asyncio
+
+        from .credential_service import CredentialService
+        from .discord_client import DiscordAPIError, DiscordClient
+        token = None
+        if self._crypto is not None:
+            token = await CredentialService(self.session, self._crypto).get_token(DISCORD)
+        if not token:
+            raise PosterLookupError("No Discord token is saved in FabledCurator.")
+        client = DiscordClient(token, max_retries=0)
+        loop = asyncio.get_running_loop()
+        try:
+            found = await asyncio.wait_for(
+                loop.run_in_executor(None, client.recent_posters, server_id, channel_id),
+                timeout=_POSTER_LOOKUP_SECONDS,
+            )
+        except TimeoutError as exc:
+            raise PosterLookupError("Discord took too long to answer; try again.") from exc
+        except DiscordAPIError as exc:
+            raise PosterLookupError(f"Couldn't read this channel: {exc}") from exc
+        source = await self._source_for_page(server_id, channel_id)
+        co = (source.config_overrides or {}) if source is not None else {}
+        from .discord_ingester import AUTHORS_KEY
+        return {
+            **found,
+            "source_id": source.id if source is not None else None,
+            "selected": list(co.get(AUTHORS_KEY) or []),
+            # So someone on the list who hasn't posted lately still shows by
+            # name, and can be unticked.
+            "selected_labels": dict(co.get(AUTHOR_LABELS_KEY) or {}),
+        }
+
+    async def set_discord_posters(self, url: str, authors: list[dict]) -> dict:
+        """Store the picked posters on the source that follows `url`'s channel."""
+        server_id, channel_id = self._discord_page(url)
+        source = await self._source_for_page(server_id, channel_id)
+        if source is None:
+            raise UnknownSourceError("No source follows this channel yet.")
+        return await self._apply_posters(source, authors)
+
+    async def _apply_posters(self, source: Source, authors: list[dict]) -> dict:
+        """Ids are what the list keys on — a username can change on a whim,
+        an id can't — and the name each was picked under rides beside it for
+        showing the list to a person. An empty pick clears the list, which
+        takes everyone's posts again."""
+        from .discord_ingester import AUTHORS_KEY
+        picked = [a for a in authors if str(a.get("id") or "").strip()]
+        co = dict(source.config_overrides or {})
+        if picked:
+            co[AUTHORS_KEY] = [str(a["id"]).strip() for a in picked]
+            co[AUTHOR_LABELS_KEY] = {
+                str(a["id"]).strip(): str(a.get("name") or a["id"]) for a in picked
+            }
+        else:
+            co.pop(AUTHORS_KEY, None)
+            co.pop(AUTHOR_LABELS_KEY, None)
+        source.config_overrides = co or None
+        await self.session.commit()
+        return {"source_id": source.id, "discord_authors": co.get(AUTHORS_KEY, [])}
+
     async def _adopt_patreon_name(self, artist, raw_slug: str, url: str) -> str | None:
         """Rename `artist` to the Patreon display name; the old name when it
         changed, else None. Unreadable name → no rename, never the handle."""