feat: the extension adds Discord channels to an artist you pick, and its tests gate the XPI (milestone 429)

Server (#4420)
- extension_service gains a Discord pattern (server or channel, jump links,
  ptb/canary; not DMs or threads), mirrored in platforms.js and pinned by
  the shared artist-url-samples.json.
- probe on a Discord URL matches the source by ids under any artist, reports
  a whole-server source as covering the channel, suggests the artist who owns
  another source on the same server, and names server/channel via the stored
  token (best-effort, bounded, no rate-limit waits).
- quick-add takes artist_id / artist_name; Discord URLs are stored canonical.

Extension (#4421, #4422)
- Content script on discord.com; SPA navigation by URL polling (the old
  pushState patch ran in the isolated world and never fired); stale probes
  are dropped.
- Discord chip opens an Add panel: this channel or the whole server, and the
  suggested artist / a search / a new name.
- Popup: sources show artist, platform and state; a Discord token export is
  verified by FC and the result shown. Token capture covers ptb/canary.
- Pure logic in lib/chip.js and lib/popup-format.js, with specs.

CI (#4423)
- extension.yml's lane (web-ext lint, vitest, XPI contents) moves into
  build.yml as extension-test and joins the needs of sign-extension,
  build-web and build-agent. As a separate workflow it gated nothing: a red
  extension suite still signed and shipped the XPI (rule 177).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LVjrnpQjRgHdvq95rASoiR

backend/app/api/extension.py

@@ -19,6 +19,7 @@ from ..models import AppSetting
 from ..services.extension_service import (
     ExtensionService,
     InvalidUrlError,
+    UnknownArtistError,
     UnknownPlatformError,
 )
 from ..services.source_service import KNOWN_PLATFORMS
@@ -87,10 +88,14 @@ async def probe_source():
     url = (request.args.get("url") or "").strip()
     if not url:
         return _bad("invalid_body", detail="url query parameter is required")
+    from .credentials import _get_crypto
+
     async with get_session() as session:
         if not await _ext_key_required(session):
             return _bad("unauthorized", status=401)
-        result = await ExtensionService(session).probe(url)
+        # crypto lets a Discord probe name the server and channel with the
+        # stored token; every other platform ignores it.
+        result = await ExtensionService(session, _get_crypto()).probe(url)
     return jsonify(result)
 
 
@@ -102,6 +107,15 @@ async def quick_add_source():
     url = body.get("url")
     if not isinstance(url, str) or not url.strip():
         return _bad("invalid_body", detail="url is required")
+    # Optional: connect the new source to an existing artist (artist_id) or to
+    # the artist of that name (artist_name). A Discord channel names no
+    # creator, so the extension's Add panel always sends one of them.
+    artist_id = body.get("artist_id")
+    if artist_id is not None and (isinstance(artist_id, bool) or not isinstance(artist_id, int)):
+        return _bad("invalid_body", detail="artist_id must be an integer")
+    artist_name = body.get("artist_name")
+    if artist_name is not None and not isinstance(artist_name, str):
+        return _bad("invalid_body", detail="artist_name must be a string")
 
     from .credentials import _get_crypto
 
@@ -111,7 +125,11 @@ async def quick_add_source():
         try:
             # crypto lets an add resolve the artist's display name via the
             # stored credential (else it falls back to the URL handle). #130.
-            result = await ExtensionService(session, _get_crypto()).quick_add_source(url)
+            result = await ExtensionService(session, _get_crypto()).quick_add_source(
+                url, artist_id=artist_id, artist_name=artist_name,
+            )
+        except UnknownArtistError as exc:
+            return _bad("not_found", detail=str(exc), status=404)
         except UnknownPlatformError as exc:
             return _bad(
                 "unknown_platform",

backend/app/services/discord_client.py

@@ -510,6 +510,24 @@ class DiscordClient:
 
     # -- verify ------------------------------------------------------------
 
+    def describe(self, server_id: str | None, channel_id: str | None) -> dict:
+        """The display names behind a server/channel pair, for the browser
+        extension's Add panel. Best-effort per name: one that can't be read
+        comes back None, and the other is still returned."""
+        out: dict = {"server": None, "channel": None, "parent": None}
+        if server_id:
+            try:
+                out["server"] = (self._get(f"/guilds/{server_id}") or {}).get("name") or None
+            except DiscordAPIError:
+                pass
+        if channel_id:
+            try:
+                meta = self._parse_channel(self._get(f"/channels/{channel_id}"))
+                out["channel"] = meta.get("channel") or None
+            except (DiscordAPIError, AttributeError):
+                pass
+        return out
+
     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

@@ -21,6 +21,9 @@ from .source_service import BACKFILL_MAX_CHUNKS
 
 log = logging.getLogger(__name__)
 
+# The probe runs while the chip is drawing; names that take longer are skipped.
+_NAME_LOOKUP_SECONDS = 6.0
+
 
 class UnknownPlatformError(Exception):
     """URL didn't match any platform pattern."""
@@ -30,6 +33,10 @@ class InvalidUrlError(Exception):
     """URL was empty or missing a scheme."""
 
 
+class UnknownArtistError(Exception):
+    """quick-add named an `artist_id` that does not exist."""
+
+
 # Mirrored byte-for-byte from extension/lib/platforms.js
 # PLATFORM_ARTIST_PATTERNS. Keep these two copies in sync by hand —
 # reviewers catch drift.
@@ -55,8 +62,39 @@ _PLATFORM_PATTERNS: list[tuple[str, re.Pattern[str]]] = [
         r"^https?://(?:www\.)?hentai-foundry\.com/user/(?P<slug>[^/?#]+)",
         re.IGNORECASE,
     )),
+    # A Discord URL names a server or a channel, never a creator, so the slug is
+    # `<server>` or `<server>/<channel>` and the artist is chosen, not derived.
+    # A trailing message id (a jump link) still names its channel. DMs (`@me`)
+    # are not sources; thread links (`/threads/`) are left to the manual form.
+    ("discord", re.compile(
+        r"^https?://(?:www\.|ptb\.|canary\.)?discord\.com/channels/"
+        r"(?P<slug>\d+(?:/\d+)?)(?:/\d+)?/?(?:[?#].*)?$",
+        re.IGNORECASE,
+    )),
 ]
 
+DISCORD = "discord"
+
+
+def canonical_source_url(platform: str, url: str, slug: str) -> str:
+    """The URL a new source is stored under. Discord's is rebuilt from the ids
+    — the form the manual Add form and the ingester use — so a jump link, a
+    ptb/canary host or a trailing slash never makes a second source for the
+    same channel. Every other platform keeps the URL as given."""
+    if platform == DISCORD:
+        return f"https://discord.com/channels/{slug}"
+    return url
+
+
+def _discord_ids(url: str) -> tuple[str | None, str | None] | None:
+    """`(server_id, channel_id)` of a stored Discord source URL, None if it
+    does not parse (a DM or thread link, or an old malformed row)."""
+    from .discord_client import DiscordAPIError, parse_source_url
+    try:
+        return parse_source_url(url)
+    except DiscordAPIError:
+        return None
+
 
 class ExtensionService:
     def __init__(self, session: AsyncSession, crypto=None) -> None:
@@ -65,30 +103,63 @@ class ExtensionService:
         # add-time. None → skip resolution, fall back to the handle.
         self._crypto = crypto
 
-    async def quick_add_source(self, url: str) -> dict:
+    async def quick_add_source(
+        self,
+        url: str,
+        *,
+        artist_id: int | None = None,
+        artist_name: str | 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,
+        the artist is resolved from the platform as before."""
         platform, raw_slug = self._derive(url)
+        url = canonical_source_url(platform, url, raw_slug)
         # Identity by SOURCE handle (#130): an existing (platform, url) source
         # keeps its artist on re-add — even if that artist was since renamed (its
-        # frozen slug no longer matches the current name). Only a genuinely new
-        # source resolves/creates an artist.
-        existing = (await self.session.execute(
-            select(Source).where(Source.platform == platform, Source.url == url)
-        )).scalar_one_or_none()
+        # frozen slug no longer matches the current name), and even when the
+        # add named a different artist. Only a genuinely new source
+        # resolves/creates an artist.
+        existing = await self._existing_source(platform, url)
         if existing is not None:
             artist = (await self.session.execute(
                 select(Artist).where(Artist.id == existing.artist_id)
             )).scalar_one()
             return self._shape(existing, artist, created_source=False, created_artist=False)
 
-        # New source → name the artist properly by resolving the real display
-        # name from the platform (falls back to the URL handle).
-        name = await self._resolve_artist_name(platform, raw_slug, url)
-        artist, created_artist = await self._find_or_create_artist(name)
+        if artist_id is not None:
+            artist = (await self.session.execute(
+                select(Artist).where(Artist.id == artist_id)
+            )).scalar_one_or_none()
+            if artist is None:
+                raise UnknownArtistError(f"no artist with id {artist_id}")
+            created_artist = False
+        else:
+            name = (artist_name or "").strip()
+            if not name:
+                # Name the artist properly by resolving the real display name
+                # from the platform (falls back to the URL handle).
+                name = await self._resolve_artist_name(platform, raw_slug, url)
+            artist, created_artist = await self._find_or_create_artist(name)
         source, created_source = await self._find_or_create_source(
             artist_id=artist.id, platform=platform, url=url,
         )
         return self._shape(source, artist, created_source, created_artist)
 
+    async def _existing_source(self, platform: str, url: str) -> Source | None:
+        """The source this URL already is, whichever artist owns it. Discord
+        compares ids, not strings, so a row stored before canonicalisation (a
+        ptb host, a trailing slash) is still found."""
+        if platform != DISCORD:
+            return (await self.session.execute(
+                select(Source).where(Source.platform == platform, Source.url == url)
+            )).scalars().first()
+        want = _discord_ids(url)
+        rows = (await self.session.execute(
+            select(Source).where(Source.platform == DISCORD).order_by(Source.id)
+        )).scalars().all()
+        return next((s for s in rows if _discord_ids(s.url) == want), None)
+
     @staticmethod
     def _shape(source, artist, created_source: bool, created_artist: bool) -> dict:
         return {
@@ -117,6 +188,11 @@ class ExtensionService:
         platforms (and any failure — no credential, network error) fall back to
         the URL handle, which is already readable.
         The resolvers are sync, so they run in an executor."""
+        if platform == DISCORD:
+            # The server's name: what the operator knows the community as.
+            server_id = raw_slug.split("/", 1)[0]
+            names = await self._discord_names(server_id, None)
+            return names.get("server") or f"Discord {server_id}"
         if self._crypto is None or platform not in ("patreon", "subscribestar"):
             return raw_slug
         import asyncio
@@ -166,6 +242,8 @@ class ExtensionService:
             platform, raw_slug = self._derive(url)
         except (UnknownPlatformError, InvalidUrlError):
             return {"state": "unknown_platform"}
+        if platform == DISCORD:
+            return await self._probe_discord(raw_slug)
 
         slug = slugify(raw_slug)
         artist = (await self.session.execute(
@@ -205,6 +283,106 @@ class ExtensionService:
             },
         }
 
+    async def _probe_discord(self, raw_slug: str) -> dict:
+        """probe for a Discord server or channel. The states mean what they
+        mean elsewhere, but the artist is never read off the URL:
+
+          - source_match: this channel is a source — or the whole server is
+            (`covered_by_server`), which already walks every channel;
+          - artist_match: another source on this server belongs to an artist,
+            the one this channel most likely belongs to too (a suggestion the
+            Add panel preselects, not a decision);
+          - new: nothing on this server yet.
+
+        `discord` carries the ids, both canonical URLs and the display names,
+        read with the stored token; a name that can't be read is None."""
+        server_id, _, channel_id = raw_slug.partition("/")
+        channel_id = channel_id or None
+        rows = (await self.session.execute(
+            select(Source, Artist)
+            .join(Artist, Artist.id == Source.artist_id)
+            .where(Source.platform == DISCORD)
+            .order_by(Source.id)
+        )).all()
+        exact = server_whole = on_server = None
+        for source, artist in rows:
+            ids = _discord_ids(source.url)
+            if ids is None or ids[0] != server_id:
+                continue
+            if ids[1] == channel_id and exact is None:
+                exact = (source, artist)
+            elif ids[1] is None and server_whole is None:
+                server_whole = (source, artist)
+            if on_server is None:
+                on_server = (source, artist)
+
+        names = await self._discord_names(server_id, channel_id)
+        base = f"https://discord.com/channels/{server_id}"
+        result: dict = {
+            "platform": DISCORD,
+            "slug": raw_slug,
+            "discord": {
+                "server_id": server_id,
+                "channel_id": channel_id,
+                "server_name": names.get("server"),
+                "channel_name": names.get("channel"),
+                "server_url": base,
+                "channel_url": f"{base}/{channel_id}" if channel_id else None,
+            },
+        }
+        hit = exact or server_whole
+        if hit is not None:
+            source, artist = hit
+            result.update(
+                state="source_match",
+                artist=self._artist_payload(artist),
+                source=self._source_payload(source),
+                covered_by_server=exact is None,
+            )
+        elif on_server is not None:
+            result.update(state="artist_match", artist=self._artist_payload(on_server[1]))
+        else:
+            result["state"] = "new"
+        return result
+
+    async def _discord_names(self, server_id: str | None, channel_id: str | None) -> dict:
+        """Server/channel display names via the stored Discord token. Never
+        raises and never waits out a rate limit: it runs while the operator
+        looks at a page, so a slow or missing answer just means no names."""
+        if self._crypto is None:
+            return {}
+        import asyncio
+
+        from .credential_service import CredentialService
+        from .discord_client import DiscordClient
+        try:
+            token = await CredentialService(self.session, self._crypto).get_token(DISCORD)
+            if not token:
+                return {}
+            client = DiscordClient(token, max_retries=0)
+            loop = asyncio.get_running_loop()
+            return await asyncio.wait_for(
+                loop.run_in_executor(None, client.describe, server_id, channel_id),
+                timeout=_NAME_LOOKUP_SECONDS,
+            )
+        except Exception as exc:      # names are decoration — never fail the call
+            log.info("Discord name lookup failed: %s", exc)
+            return {}
+
+    @staticmethod
+    def _artist_payload(artist) -> dict:
+        return {"id": artist.id, "name": artist.name, "slug": artist.slug}
+
+    @staticmethod
+    def _source_payload(source) -> dict:
+        return {
+            "id": source.id,
+            "artist_id": source.artist_id,
+            "platform": source.platform,
+            "url": source.url,
+            "enabled": source.enabled,
+        }
+
     def _derive(self, url: str) -> tuple[str, str]:
         if not isinstance(url, str) or not url.strip():
             raise InvalidUrlError("url is empty")