feat: Discord on the native core ingester — client, downloader, ledgers, wiring (milestone 428)

Discord was the last focus platform still on gallery-dl. This adds the native
path, mirrored from gallery-dl 1.32.13's discord extractor:

- discord_client: API v10 with the user token and gallery-dl's request
  profile (dated Firefox UA, Referer). Walks a server, category, forum,
  channel or thread in gallery-dl's order and pages each channel newest-first.
  Files are attachments, then embeds, then forwards, numbered across the
  message. The resume cursor is <channel>:<before>. Text-only messages are
  not posts, since gallery-dl never made them.
- discord_downloader: gallery-dl's on-disk layout, cleaned the way it cleans
  names on Linux (only `/` and control characters change), so existing files
  are skipped_disk rather than fetched again. Sidecars carry identity only.
  The message record keeps gallery-dl's keys, so parse_sidecar,
  derive_post_url and the drop grouping read it unchanged.
- The ledger keys on the attachment id (or a hash of an embed's URL path),
  not the file's position, which an edit can renumber. Migration 0111.
- DiscordIngester: token auth, body canary off (files-only drops are
  normal). Registered as native, verified by token, and serialised
  per-platform, since every source shares one user token.
- ingest_core: optional `skip_feed` client seam (#4413). A tick's early-out
  on a multi-channel source now ends the quiet channel, not the whole walk.
  Clients without the seam behave as before.

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

alembic/versions/0111_discord_native_ledger.py

@@ -0,0 +1,75 @@
+"""Discord native ingester ledgers — seen and dead-letter, per source.
+
+Milestone 428, #4415. Discord moves off gallery-dl onto the native core, which
+keeps its memory of what a source has already fetched in these two tables
+instead of gallery-dl's archive. Same shape as the SubscribeStar pair.
+
+Revision ID: 0111
+Revises: 0110
+Create Date: 2026-09-24
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0111"
+down_revision = "0110"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.create_table(
+        "discord_seen_media",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("source_id", sa.Integer(), nullable=False),
+        sa.Column("filehash", sa.String(length=128), nullable=False),
+        sa.Column("post_id", sa.String(length=64), nullable=True),
+        sa.Column(
+            "seen_at", sa.DateTime(timezone=True),
+            server_default=sa.text("now()"), nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["source_id"], ["source.id"],
+            name=op.f("fk_discord_seen_media_source_id_source"), ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("id", name=op.f("pk_discord_seen_media")),
+        sa.UniqueConstraint("source_id", "filehash", name="uq_discord_seen_media_source_id"),
+    )
+    op.create_index(
+        op.f("ix_discord_seen_media_source_id"), "discord_seen_media", ["source_id"],
+    )
+    op.create_table(
+        "discord_failed_media",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("source_id", sa.Integer(), nullable=False),
+        sa.Column("filehash", sa.String(length=128), nullable=False),
+        sa.Column("attempts", sa.Integer(), server_default="1", nullable=False),
+        sa.Column("last_error", sa.Text(), nullable=True),
+        sa.Column(
+            "first_failed_at", sa.DateTime(timezone=True),
+            server_default=sa.text("now()"), nullable=False,
+        ),
+        sa.Column(
+            "last_failed_at", sa.DateTime(timezone=True),
+            server_default=sa.text("now()"), nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["source_id"], ["source.id"],
+            name=op.f("fk_discord_failed_media_source_id_source"), ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("id", name=op.f("pk_discord_failed_media")),
+        sa.UniqueConstraint(
+            "source_id", "filehash", name="uq_discord_failed_media_source_id",
+        ),
+    )
+    op.create_index(
+        op.f("ix_discord_failed_media_source_id"), "discord_failed_media", ["source_id"],
+    )
+
+
+def downgrade():
+    op.drop_index(op.f("ix_discord_failed_media_source_id"), table_name="discord_failed_media")
+    op.drop_table("discord_failed_media")
+    op.drop_index(op.f("ix_discord_seen_media_source_id"), table_name="discord_seen_media")
+    op.drop_table("discord_seen_media")

backend/app/models/__init__.py

@@ -8,6 +8,8 @@ from .backup_run import BackupRun
 from .base import Base
 from .character_prototype import CcipPrototypeState, CharacterPrototype
 from .credential import Credential
+from .discord_failed_media import DiscordFailedMedia
+from .discord_seen_media import DiscordSeenMedia
 from .download_event import DownloadEvent
 from .external_link import ExternalLink
 from .gpu_job import GpuJob
@@ -56,6 +58,8 @@ __all__ = [
     "BackupRun",
     "Source",
     "Credential",
+    "DiscordFailedMedia",
+    "DiscordSeenMedia",
     "PatreonFailedMedia",
     "PatreonSeenMedia",
     "SubscribeStarFailedMedia",

backend/app/models/discord_failed_media.py

@@ -0,0 +1,36 @@
+"""DiscordFailedMedia — per-source dead-letter ledger of Discord files that
+keep failing to download or validate.
+
+Mirror of SubscribeStarFailedMedia. After `attempts` reaches the dead-letter
+threshold a routine walk skips the file (recovery still retries it); a later
+clean download clears the row. `filehash` is the seen-ledger's key.
+"""
+
+from datetime import datetime
+
+from sqlalchemy import ForeignKey, Integer, String, Text, UniqueConstraint, func
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy.types import DateTime
+
+from .base import Base
+
+
+class DiscordFailedMedia(Base):
+    __tablename__ = "discord_failed_media"
+    __table_args__ = (
+        UniqueConstraint("source_id", "filehash", name="uq_discord_failed_media_source_id"),
+    )
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True)
+    source_id: Mapped[int] = mapped_column(
+        ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
+    )
+    filehash: Mapped[str] = mapped_column(String(128), nullable=False)
+    attempts: Mapped[int] = mapped_column(Integer, nullable=False, default=1, server_default="1")
+    last_error: Mapped[str | None] = mapped_column(Text, nullable=True)
+    first_failed_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )
+    last_failed_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )

backend/app/models/discord_seen_media.py

@@ -0,0 +1,34 @@
+"""DiscordSeenMedia — per-source ledger of Discord files already downloaded.
+
+Mirror of SubscribeStarSeenMedia for the native Discord ingester (milestone
+428). `filehash` holds the ingester's per-file key, `<message_id>:<media_id>`:
+the attachment id, or for an embed a hash of its URL path. Not the file's
+position in the message — an edit that removes a file renumbers the rest
+(see `discord_client.MediaItem`). The message record's own gate is the
+synthetic `message:<id>` key in the same column.
+"""
+
+from datetime import datetime
+
+from sqlalchemy import ForeignKey, Integer, String, UniqueConstraint, func
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy.types import DateTime
+
+from .base import Base
+
+
+class DiscordSeenMedia(Base):
+    __tablename__ = "discord_seen_media"
+    __table_args__ = (
+        UniqueConstraint("source_id", "filehash", name="uq_discord_seen_media_source_id"),
+    )
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True)
+    source_id: Mapped[int] = mapped_column(
+        ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
+    )
+    filehash: Mapped[str] = mapped_column(String(128), nullable=False)
+    post_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    seen_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )

backend/app/services/discord_client.py

@@ -0,0 +1,544 @@
+"""Native Discord read client — the Discord counterpart to subscribestar_client.
+
+Mirrors gallery-dl 1.32.13's `extractor/discord.py` (rule 130: gallery-dl is the
+known-working base), adapted to the native core's client contract
+(`ingest_core` module docstring): `iter_posts` / `extract_media`, plus the
+post-first `post_record_key` and the `post_meta` date the revisit window reads.
+
+What is mirrored exactly, because drift in any of it changes what we fetch or
+where it lands on disk:
+
+  - API v10, `Authorization: <user token>` (a USER token, not a bot token).
+  - gallery-dl's request profile: its date-derived Firefox User-Agent,
+    `Accept: */*`, `Accept-Language`, `Referer: https://discord.com/`.
+  - `GET /channels/{id}/messages?limit=100&before=<last id>`, newest first,
+    stopping on a short page. Message types {0, 19, 21} only.
+  - The walk: a text/news channel's own messages then its threads, a forum's
+    threads, a category's children, a server's text/news/forum channels.
+  - Files: attachments, then embeds of type image/gifv/video (FC configures
+    `embeds: all`, which for files is the same three plus rich/link embeds that
+    carry an image), then forwarded `message_snapshots`, numbered from 1 across
+    the lot — the `num` in `{date}_{message_id}_{num}_{filename}`.
+  - Text: `content`, rich-embed author/title/description/fields/footer, poll.
+
+Two deliberate departures, both about the walk order, neither about content:
+
+  - Threads are walked newest-CREATED first (by id), not by last-message time.
+    A backfill resumes from a checkpointed channel; last-message order shifts
+    between chunks whenever someone posts, which can move an unwalked thread
+    above the resume point and skip it. Creation order only ever grows at the
+    front, where the next tick finds it.
+  - A 403 on a thread or a nested channel skips that feed instead of failing
+    the walk. gallery-dl skips only nested channels; one private thread the
+    token cannot read would otherwise stop every channel after it.
+
+FC runs on a plain-HTTP homelab; nothing here uses a secure-context Web API.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import logging
+import re
+import time
+from collections.abc import Iterator
+from dataclasses import dataclass
+from datetime import date
+from urllib.parse import unquote
+
+import requests
+
+from .native_ingest_common import (
+    NativeAuthError,
+    NativeDriftError,
+    NativeIngestError,
+    retry_after_seconds,
+)
+
+log = logging.getLogger(__name__)
+
+API_ROOT = "https://discord.com/api/v10"
+_ROOT = "https://discord.com"
+
+_TIMEOUT_SECONDS = 60.0
+_MESSAGES_BATCH = 100
+_THREADS_BATCH = 25
+# gallery-dl retries a 429 up to its default 4 retries, waiting
+# `request_interval_429` (60s) between them. Discord's Retry-After is exact, so
+# it is honoured when present; 60s is the fallback and the cap.
+_MAX_429_RETRIES = 4
+_429_WAIT_SECONDS = 60.0
+
+# https://discord.com/developers/docs/resources/message#message-object-message-types
+# DEFAULT, REPLY, CHAT_INPUT_COMMAND — the ones that carry user content.
+MESSAGE_TYPES = frozenset({0, 19, 21})
+# https://discord.com/developers/docs/resources/channel#channel-object-channel-types
+_TEXT = frozenset({0, 5})               # text, announcement: messages + threads
+_DIRECT = frozenset({1, 3, 10, 11, 12})  # DMs and threads: messages only
+_FORUM = frozenset({15, 16})            # forum, media: threads only
+_CATEGORY = 4
+_SERVER_WALK = _TEXT | _FORUM
+_EMBED_TYPES = frozenset({"image", "gifv", "video"})
+
+_URL_RE = re.compile(
+    r"^(?:https?://)?(?:www\.|ptb\.|canary\.)?discord(?:app)?\.com/channels/"
+    r"(?P<server>@me|\d+)(?:/(?:\d+/threads/)?(?P<channel>\d+))?(?P<rest>/.*)?/?$"
+)
+
+
+class DiscordAPIError(NativeIngestError):
+    """Base for native Discord client failures."""
+
+
+class DiscordAuthError(DiscordAPIError, NativeAuthError):
+    """401 (the token is invalid or expired) or a 403 on the channel the
+    source names. The fix is a new token, not a new client."""
+
+
+class DiscordDriftError(DiscordAPIError, NativeDriftError):
+    """A response did not have the shape the walk depends on."""
+
+
+def firefox_user_agent(today: date | None = None) -> str:
+    """gallery-dl's default User-Agent: a Firefox whose version advances every
+    four weeks (`util._ff_ver`, "147 on 2026-01-13"). Computed the same way so
+    the profile keeps matching the gallery-dl this replaced."""
+    ver = ((today or date.today()).toordinal() - 735_513) // 28
+    return (
+        f"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:{ver}.0) "
+        f"Gecko/20100101 Firefox/{ver}.0"
+    )
+
+
+def nameext_from_url(url: str) -> tuple[str, str]:
+    """gallery-dl's `text.nameext_from_url`: the URL's last path segment,
+    unquoted, split at the last dot when the extension is at most 16 chars
+    (lowercased); otherwise the whole name and no extension."""
+    filename = unquote(url.partition("?")[0].rpartition("/")[2])
+    name, _, ext = filename.rpartition(".")
+    if name and len(ext) <= 16:
+        return name, ext.lower()
+    return filename, ""
+
+
+def parse_source_url(url: str) -> tuple[str | None, str | None]:
+    """`(server_id, channel_id)` from a Discord channel/server URL. `server_id`
+    is None for a DM (`@me`); `channel_id` is None for a whole server. Raises
+    DiscordAPIError for anything else, including a link to a single message —
+    a message is not something a source can subscribe to."""
+    m = _URL_RE.match((url or "").strip())
+    if not m or (m.group("rest") or "").strip("/"):
+        raise DiscordAPIError(
+            f"Not a Discord channel or server link: {url!r} "
+            "(expected https://discord.com/channels/<server>[/<channel>])"
+        )
+    server = m.group("server")
+    channel = m.group("channel")
+    if server == "@me":
+        if not channel:
+            raise DiscordAPIError(f"A DM link needs a channel id: {url!r}")
+        return None, channel
+    return server, channel
+
+
+def message_text(message: dict) -> str:
+    """gallery-dl's `extract_message_text`: the body plus the text of rich
+    embeds and polls, newline-joined, empties dropped."""
+    parts = [message.get("content") or ""]
+    for embed in message.get("embeds") or []:
+        if embed.get("type") != "rich":
+            continue
+        parts.append((embed.get("author") or {}).get("name") or "")
+        parts.append(embed.get("title") or "")
+        parts.append(embed.get("description") or "")
+        for fld in embed.get("fields") or []:
+            parts.append(fld.get("name") or "")
+            parts.append(fld.get("value") or "")
+        parts.append((embed.get("footer") or {}).get("text") or "")
+    poll = message.get("poll")
+    if poll:
+        parts.append(((poll.get("question") or {}).get("text")) or "")
+        for answer in poll.get("answers") or []:
+            parts.append(((answer.get("poll_media") or {}).get("text")) or "")
+    return "\n".join(p for p in parts if p)
+
+
+@dataclass
+class MediaItem:
+    """One file of a Discord message. `filename`/`extension` are gallery-dl's
+    split of the URL; `num` is its 1-based position across the message's files,
+    which is what names it on disk.
+
+    `media_id` is what the seen-ledger keys on, and it is deliberately NOT
+    `num`: an edit that removes a file renumbers the ones after it, and a
+    positional key would then call a different file seen. It is the
+    attachment's id, or for an embed (which has none) a hash of its URL path —
+    the query string is a signature that changes on every fetch. `filehash` is
+    always None; nothing in a signed CDN URL is a content hash."""
+
+    url: str
+    filename: str
+    extension: str
+    kind: str
+    post_id: str
+    num: int
+    media_id: str
+    filehash: str | None = None
+
+
+class DiscordClient:
+    """Synchronous Discord API v10 read client for one user token."""
+
+    def __init__(
+        self,
+        token: str | None,
+        *,
+        request_sleep: float = 0.0,
+        max_retries: int = _MAX_429_RETRIES,
+        session: requests.Session | None = None,
+    ):
+        self._session = session or requests.Session()
+        self._session.headers.update({
+            "User-Agent": firefox_user_agent(),
+            "Accept": "*/*",
+            "Accept-Language": "en-US,en;q=0.5",
+            "Referer": _ROOT + "/",
+        })
+        if token:
+            self._session.headers["Authorization"] = token
+        self._token = token
+        self._request_sleep = request_sleep or 0.0
+        self._max_retries = max_retries
+        self._server: dict = {}
+        self._channels: dict[str, dict] = {}
+        self._skip_feed = False
+
+    # -- request -----------------------------------------------------------
+
+    def _get(self, endpoint: str, params: dict | None = None):
+        if not self._token:
+            raise DiscordAuthError("No Discord token is configured for this source")
+        if self._request_sleep > 0:
+            time.sleep(self._request_sleep)
+        url = API_ROOT + endpoint
+        attempt = 0
+        while True:
+            try:
+                resp = self._session.get(url, params=params, timeout=_TIMEOUT_SECONDS)
+            except requests.RequestException as exc:
+                raise DiscordAPIError(f"Discord request failed ({endpoint}): {exc}") from exc
+            if resp.status_code == 429 and attempt < self._max_retries:
+                attempt += 1
+                delay = retry_after_seconds(
+                    resp, attempt, base=_429_WAIT_SECONDS, cap=_429_WAIT_SECONDS,
+                )
+                log.warning(
+                    "Discord 429 (%s) — waiting %.1fs (retry %d/%d)",
+                    endpoint, delay, attempt, self._max_retries,
+                )
+                time.sleep(delay)
+                continue
+            break
+        if resp.status_code == 401:
+            raise DiscordAuthError(
+                "Discord rejected the token (HTTP 401) — it is invalid or has "
+                "expired; copy a fresh one from the browser",
+                status_code=401,
+            )
+        if resp.status_code != 200:
+            raise DiscordAPIError(
+                f"Discord returned HTTP {resp.status_code} ({endpoint})",
+                status_code=resp.status_code,
+                retry_after=_retry_after(resp),
+            )
+        try:
+            return resp.json()
+        except ValueError as exc:
+            raise DiscordDriftError(
+                f"Discord returned non-JSON for {endpoint} ({len(resp.content)} bytes)"
+            ) from exc
+
+    # -- metadata (gallery-dl parse_server / parse_channel) -----------------
+
+    def _load_server(self, server_id: str) -> None:
+        server = self._get(f"/guilds/{server_id}")
+        if not isinstance(server, dict) or "id" not in server:
+            raise DiscordDriftError(f"Discord server {server_id} came back without an id")
+        self._server = {
+            "server": server.get("name") or "",
+            "server_id": str(server["id"]),
+            "owner_id": server.get("owner_id"),
+        }
+        channels = self._get(f"/guilds/{server_id}/channels")
+        if not isinstance(channels, list):
+            raise DiscordDriftError(f"Discord server {server_id} channel list is not a list")
+        # Categories first, so every child can name its parent.
+        for channel in sorted(channels, key=lambda ch: ch.get("type") != _CATEGORY):
+            self._parse_channel(channel)
+
+    def _parse_channel(self, channel: dict) -> dict:
+        parent_id = channel.get("parent_id")
+        meta = {
+            "channel": channel.get("name") or "",
+            "channel_id": str(channel.get("id")),
+            "channel_type": channel.get("type"),
+            "channel_topic": channel.get("topic") or "",
+            "parent_id": parent_id,
+            "is_thread": "thread_metadata" in channel,
+        }
+        parent = self._channels.get(parent_id) if parent_id else None
+        if parent:
+            meta["parent"] = parent["channel"]
+            meta["parent_type"] = parent["channel_type"]
+        if meta["channel_type"] in {1, 3}:
+            recipients = channel.get("recipients") or []
+            meta["channel"] = "DMs"
+            meta["recipients"] = [u.get("username") for u in recipients]
+            meta["recipients_id"] = [u.get("id") for u in recipients]
+        self._channels[meta["channel_id"]] = meta
+        return meta
+
+    def _channel_meta(self, channel_id: str) -> dict:
+        if channel_id not in self._channels:
+            self._parse_channel(self._get(f"/channels/{channel_id}"))
+        return self._channels[channel_id]
+
+    def _threads(self, channel_id: str) -> list[dict]:
+        """Every thread of a channel or forum, newest-created first (see the
+        module docstring for why not last-message order)."""
+        threads: list[dict] = []
+        offset = 0
+        while True:
+            data = self._get(f"/channels/{channel_id}/threads/search", {
+                "sort_by": "last_message_time",
+                "sort_order": "desc",
+                "limit": _THREADS_BATCH,
+                "offset": offset,
+            })
+            batch = (data.get("threads") or []) if isinstance(data, dict) else []
+            threads.extend(batch)
+            if len(batch) < _THREADS_BATCH:
+                break
+            offset += len(batch)
+        threads.sort(key=lambda t: int(t.get("id") or 0), reverse=True)
+        return threads
+
+    # -- the walk ------------------------------------------------------------
+
+    def _feeds(self, channel_id: str, *, safe: bool) -> Iterator[tuple[str, bool]]:
+        """`(channel_id, safe)` for every message feed under `channel_id`, in
+        gallery-dl's order. `safe` feeds are skipped on a 403."""
+        try:
+            ctype = self._channel_meta(channel_id)["channel_type"]
+        except DiscordAPIError as exc:
+            if exc.status_code != 403:
+                raise
+            if not safe:
+                raise DiscordAuthError(
+                    f"The Discord token cannot see channel {channel_id} (HTTP 403)",
+                    status_code=403,
+                ) from exc
+            log.info("Discord: no access to channel %s — skipped", channel_id)
+            return
+        if ctype in _TEXT or ctype in _DIRECT:
+            yield channel_id, safe
+        if ctype in _TEXT or ctype in _FORUM:
+            try:
+                threads = self._threads(channel_id)
+            except DiscordAPIError as exc:
+                if exc.status_code != 403:
+                    raise
+                log.info("Discord: cannot list threads of %s — skipped", channel_id)
+                threads = []
+            for thread in threads:
+                yield self._parse_channel(thread)["channel_id"], True
+        elif ctype == _CATEGORY:
+            for child in list(self._channels.values()):
+                if child.get("parent_id") == channel_id:
+                    yield from self._feeds(child["channel_id"], safe=True)
+        elif ctype not in _DIRECT and not safe:
+            raise DiscordAPIError(
+                f"Discord channel {channel_id} is of type {ctype}, which has no messages"
+            )
+
+    def _source_feeds(self, url: str) -> Iterator[tuple[str, bool]]:
+        server_id, channel_id = parse_source_url(url)
+        self._server, self._channels = {}, {}
+        if server_id is not None:
+            self._load_server(server_id)
+        if channel_id is not None:
+            yield from self._feeds(channel_id, safe=False)
+            return
+        for meta in list(self._channels.values()):
+            if meta["channel_type"] in _SERVER_WALK:
+                yield from self._feeds(meta["channel_id"], safe=True)
+
+    def skip_feed(self) -> None:
+        """Optional core seam (#4413): end the current channel and go on to the
+        next one. A tick's early-out means THIS channel has nothing new, not
+        that the server has nothing new."""
+        self._skip_feed = True
+
+    def iter_posts(
+        self, campaign_id: str, cursor: str | None = None
+    ) -> Iterator[tuple[dict, dict, str | None]]:
+        """Yield `(message, channel_meta, page_cursor)` for every content
+        message the source reaches, channel by channel, each newest first.
+
+        `campaign_id` is the source URL. The cursor is `<channel_id>:<before>`
+        — the channel and the `before` id that fetched the page (empty for a
+        channel's first page) — so a backfill resumes inside the right channel
+        and re-fetches the page it was cut in. A cursor naming a channel the
+        walk no longer reaches (a deleted thread) restarts from the top rather
+        than walking nothing.
+        """
+        resume_channel, _, resume_before = (cursor or "").partition(":")
+        resuming = bool(resume_channel)
+        feeds = list(self._source_feeds(campaign_id)) if resuming else None
+        if feeds is not None and resume_channel not in {cid for cid, _ in feeds}:
+            log.warning(
+                "Discord: resume channel %s is no longer in %s — restarting",
+                resume_channel, campaign_id,
+            )
+            resuming = False
+        for channel_id, safe in feeds if feeds is not None else self._source_feeds(campaign_id):
+            before = None
+            if resuming:
+                if channel_id != resume_channel:
+                    continue
+                resuming = False
+                before = resume_before or None
+            yield from self._iter_channel(channel_id, before, safe=safe)
+
+    def _iter_channel(
+        self, channel_id: str, before: str | None, *, safe: bool
+    ) -> Iterator[tuple[dict, dict, str | None]]:
+        self._skip_feed = False
+        meta = {**self._server, **self._channels.get(channel_id, {})}
+        while True:
+            page_cursor = f"{channel_id}:{before or ''}"
+            try:
+                messages = self._get(
+                    f"/channels/{channel_id}/messages",
+                    {"limit": _MESSAGES_BATCH, "before": before},
+                )
+            except DiscordAPIError as exc:
+                if exc.status_code != 403:
+                    raise
+                if not safe:
+                    raise DiscordAuthError(
+                        f"The Discord token cannot read channel {channel_id} (HTTP 403)",
+                        status_code=403,
+                    ) from exc
+                log.info("Discord: no access to messages of %s — skipped", channel_id)
+                return
+            if not isinstance(messages, list):
+                raise DiscordDriftError(
+                    f"Discord messages of {channel_id} came back as "
+                    f"{type(messages).__name__}, not a list"
+                )
+            for message in messages:
+                if message.get("type") not in MESSAGE_TYPES:
+                    continue
+                message["_meta"] = meta
+                yield message, meta, page_cursor
+                if self._skip_feed:
+                    return
+            if len(messages) < _MESSAGES_BATCH:
+                return
+            before = str(messages[-1]["id"])
+
+    # -- per-message -------------------------------------------------------
+
+    @staticmethod
+    def extract_media(post: dict, included: dict | None = None) -> list[MediaItem]:
+        """gallery-dl's file list for one message: attachments, then the first
+        of video/image/thumbnail `proxy_url` of each file-bearing embed, then
+        the same for every forwarded snapshot; numbered from 1 across them."""
+        mid = str(post.get("id") or "")
+        snapshots = [post] + [
+            (s or {}).get("message") or {}
+            for s in post.get("message_snapshots") or []
+            if ((s or {}).get("message") or {}).get("type", 0) in MESSAGE_TYPES
+        ]
+        found: list[tuple[str, str, str | None]] = []
+        for snap in snapshots:
+            for att in snap.get("attachments") or []:
+                if att.get("url"):
+                    aid = att.get("id")
+                    found.append((att["url"], "attachment", str(aid) if aid else None))
+            for embed in snap.get("embeds") or []:
+                if embed.get("type") not in _EMBED_TYPES:
+                    continue
+                for fld in ("video", "image", "thumbnail"):
+                    url = (embed.get(fld) or {}).get("proxy_url")
+                    if url:
+                        found.append((url, "embed", None))
+                        break
+        items = []
+        for num, (url, kind, fid) in enumerate(found, start=1):
+            name, ext = nameext_from_url(url)
+            if fid is None:
+                path = url.partition("?")[0].encode()
+                fid = "u" + hashlib.sha1(path, usedforsecurity=False).hexdigest()[:32]
+            items.append(MediaItem(
+                url=url, filename=name, extension=ext, kind=kind, post_id=mid,
+                num=num, media_id=fid,
+            ))
+        return items
+
+    @staticmethod
+    def post_meta(post: dict) -> dict:
+        """No title (Discord has none); `date` is the message timestamp, ISO
+        with an offset — what the core's revisit window reads."""
+        return {"title": None, "date": post.get("timestamp")}
+
+    @classmethod
+    def post_record_key(cls, post: dict) -> tuple[str, str] | None:
+        """`(message:<id>, <id>)` — gates the message record through the seen
+        ledger, like `post:<id>` on the other platforms.
+
+        None for a message with no files. gallery-dl wrote a sidecar only
+        beside a file, so a text-only chat line never became a post, and the
+        drop grouping (discord_grouping) is built on that: a channel's chatter
+        recorded as posts would bury the drops it exists to surface."""
+        mid = post.get("id")
+        mid = str(mid) if mid is not None else ""
+        if not mid or not cls.extract_media(post):
+            return None
+        return (f"message:{mid}", mid)
+
+    # -- verify ------------------------------------------------------------
+
+    def verify_auth(self, url: str) -> tuple[bool | None, str]:
+        """Is the token valid, and can it see what the source names?"""
+        try:
+            server_id, channel_id = parse_source_url(url)
+        except DiscordAPIError as exc:
+            return None, str(exc)
+        try:
+            me = self._get("/users/@me")
+            if channel_id is not None:
+                self._get(f"/channels/{channel_id}")
+            elif server_id is not None:
+                self._get(f"/guilds/{server_id}")
+        except DiscordAuthError as exc:
+            return False, f"Discord rejected the token — {exc}"
+        except DiscordAPIError as exc:
+            if exc.status_code in (403, 404):
+                return False, (
+                    "The token is valid, but its account cannot see "
+                    f"{'this channel' if channel_id else 'this server'} "
+                    f"(HTTP {exc.status_code})"
+                )
+            return None, f"Couldn't verify (network/HTTP issue): {exc}"
+        who = (me or {}).get("username") if isinstance(me, dict) else None
+        return True, f"Token valid{f' ({who})' if who else ''} — the source is readable."
+
+
+def _retry_after(resp: requests.Response) -> float | None:
+    hdr = resp.headers.get("Retry-After")
+    try:
+        return float(hdr) if hdr else None
+    except (TypeError, ValueError):
+        return None

backend/app/services/discord_downloader.py

@@ -0,0 +1,210 @@
+"""Native Discord media downloader — the Discord counterpart to
+subscribestar_downloader.
+
+Writes files exactly where gallery-dl wrote them, so a cutover finds every
+existing file on disk (`skipped_disk`) instead of fetching it again:
+
+    <images>/<artist>/discord/<channel>/<YYYYMMDD>_<message_id>_<NN>_<name>.<ext>
+
+That is FC's gallery-dl config (`gallery_dl.DISCORD_DIRECTORY` /
+`DISCORD_FILENAME`) under the per-source base directory
+`<images>/<artist>/<platform>`. The name is cleaned the way gallery-dl cleans it
+on Linux — `/` becomes `_` and control characters are removed, nothing else
+(`path-restrict: auto`, `path-remove` defaults). It is NOT `sanitize_segment`,
+whose Windows set would turn a `:` in a channel or file name into `_` and miss
+the file gallery-dl wrote.
+
+Post-first (rule 120): each file gets a minimal sidecar named like it minus the
+extension (what `find_sidecar` pairs first), and the message itself gets one
+record, `<YYYYMMDD>_<message_id>_post.json`, carrying gallery-dl's metadata keys
+— `message_id` for the post id, `server_id`/`channel_id` for the permalink,
+`message` for the body, `date` — so `parse_sidecar` reads it exactly as it read
+the gallery-dl sidecars. Neither file carries an `id` or `post_id` key: both
+outrank `message_id` in the post-id chain (`platforms.base`).
+
+PURE: no DB; the seen-skip is an injected predicate.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import re
+import time
+from collections.abc import Callable
+from datetime import UTC, datetime
+from pathlib import Path
+
+import requests
+
+from .discord_client import firefox_user_agent, message_text
+from .native_ingest_common import (
+    BaseNativeDownloader,
+    MediaOutcome,
+    PostRecordOutcome,
+    make_session,
+)
+
+log = logging.getLogger(__name__)
+
+PLATFORM = "discord"
+_CONTROL = re.compile("[\x00-\x1f\x7f]")
+# gallery-dl falls back to the response's type for a URL with no extension;
+# we never see the response before naming, and such URLs do not occur for
+# Discord attachments or embed proxies in practice.
+_NO_EXTENSION = "bin"
+
+
+def gdl_clean(segment: str) -> str:
+    """One path segment as gallery-dl writes it on Linux."""
+    return _CONTROL.sub("", segment.replace("/", "_"))
+
+
+def message_date(post: dict) -> datetime | None:
+    raw = post.get("timestamp")
+    if not isinstance(raw, str) or not raw:
+        return None
+    try:
+        dt = datetime.fromisoformat(raw.replace("Z", "+00:00"))
+    except ValueError:
+        return None
+    return (dt if dt.tzinfo else dt.replace(tzinfo=UTC)).astimezone(UTC)
+
+
+def channel_dir(images_root: Path, artist_slug: str, post: dict) -> Path:
+    """gallery-dl's `{channel}` directory; an empty name adds no segment."""
+    base = Path(images_root) / artist_slug / PLATFORM
+    channel = gdl_clean(((post.get("_meta") or {}).get("channel") or "").strip())
+    return base / channel if channel else base
+
+
+def media_stem(post: dict, media) -> str:
+    """`<YYYYMMDD>_<message_id>_<NN>_<name>` — the file's name minus `.<ext>`."""
+    when = message_date(post)
+    day = f"{when:%Y%m%d}" if when else "None"
+    return gdl_clean(f"{day}_{post.get('id')}_{media.num:>02}_{media.filename}")
+
+
+class DiscordDownloader(BaseNativeDownloader):
+    """Download a message's files to gallery-dl's layout. The CDN gets
+    gallery-dl's browser profile and no token — gallery-dl sends the token only
+    to the API, and the CDN URLs are pre-signed."""
+
+    def __init__(
+        self,
+        images_root: Path,
+        cookies_path: str | None = None,
+        *,
+        validate: bool = True,
+        rate_limit: float = 0.0,
+        session: requests.Session | None = None,
+    ):
+        super().__init__(
+            images_root, None, platform=PLATFORM,
+            validate=validate, rate_limit=rate_limit,
+            session=session if session is not None else make_session(None, extra_headers={
+                "User-Agent": firefox_user_agent(),
+                "Accept-Language": "en-US,en;q=0.5",
+                "Referer": "https://discord.com/",
+            }),
+        )
+
+    def download_post(
+        self,
+        post: dict,
+        media_items: list,
+        artist_slug: str,
+        *,
+        is_seen: Callable[[object], bool] = lambda m: False,
+        should_stop: Callable[[], bool] = lambda: False,
+        recapture: bool = False,
+    ) -> list[MediaOutcome]:
+        """Every file of one message; per-file outcomes, one failure isolated."""
+        folder = channel_dir(self.images_root, artist_slug, post)
+        outcomes: list[MediaOutcome] = []
+        for media in media_items:
+            if should_stop():
+                break
+            try:
+                outcomes.append(self._download_one(
+                    post, media, folder, artist_slug, is_seen, recapture=recapture,
+                ))
+            except Exception as exc:  # resilient: isolate one item's failure
+                log.warning(
+                    "Discord media failed (message %s, file %d): %s",
+                    post.get("id"), media.num, exc,
+                )
+                outcomes.append(
+                    MediaOutcome(media=media, status="error", path=None, error=str(exc))
+                )
+        return outcomes
+
+    def _download_one(
+        self,
+        post: dict,
+        media,
+        folder: Path,
+        artist_slug: str,
+        is_seen: Callable[[object], bool],
+        *,
+        recapture: bool = False,
+    ) -> MediaOutcome:
+        seen = is_seen(media)
+        if seen and not recapture:
+            return MediaOutcome(media=media, status="skipped_seen", path=None, error=None)
+        stem = media_stem(post, media)
+        path = folder / f"{stem}.{media.extension or _NO_EXTENSION}"
+        if path.exists():  # tier-2: gallery-dl (or an earlier walk) wrote it
+            return MediaOutcome(media=media, status="skipped_disk", path=path, error=None)
+        if seen:  # recapture never re-fetches a seen file that is gone
+            return MediaOutcome(media=media, status="skipped_seen", path=None, error=None)
+
+        folder.mkdir(parents=True, exist_ok=True)
+        if self._rate_limit > 0:
+            time.sleep(self._rate_limit)
+        out = self._fetch_get(media.url, path)
+        reason, quarantined = self._validate_path(out, artist_slug, media.url)
+        if reason is not None:
+            return MediaOutcome(media=media, status="quarantined", path=quarantined, error=reason)
+        sidecar = {"category": PLATFORM, "message_id": str(post.get("id") or "")}
+        sidecar["source_url"] = media.url
+        (folder / f"{stem}.json").write_text(json.dumps(sidecar, indent=2))
+        return MediaOutcome(media=media, status="downloaded", path=out, error=None)
+
+    def write_post_record(
+        self, post: dict, artist_slug: str, *, revisit: bool = False,
+    ) -> PostRecordOutcome:
+        """The message record — the one writer of a Discord post's body, date
+        and permalink ids. `revisit` re-reads a message already captured (an
+        edit); an empty re-read writes nothing, so it never blanks a body."""
+        mid = str(post.get("id") or "")
+        body = message_text(post)
+        if not mid or (revisit and not body.strip()):
+            return PostRecordOutcome(path=None, post_type=None, title=None, body_chars=0)
+        meta = post.get("_meta") or {}
+        author = post.get("author") or {}
+        record = {
+            "category": PLATFORM,
+            "message_id": mid,
+            "server": meta.get("server"),
+            "server_id": meta.get("server_id"),
+            "channel": meta.get("channel"),
+            "channel_id": meta.get("channel_id") or post.get("channel_id"),
+            "parent": meta.get("parent"),
+            "is_thread": meta.get("is_thread"),
+            "author": author.get("username"),
+            "author_id": author.get("id"),
+            "message": body,
+            "date": post.get("timestamp"),
+        }
+        folder = channel_dir(self.images_root, artist_slug, post)
+        folder.mkdir(parents=True, exist_ok=True)
+        when = message_date(post)
+        day = f"{when:%Y%m%d}" if when else "None"
+        path = folder / f"{day}_{mid}_post.json"
+        path.write_text(json.dumps(
+            {k: v for k, v in record.items() if v is not None}, indent=2,
+        ))
+        return PostRecordOutcome(
+            path=path, post_type=None, title=None, body_chars=len(body),
+        )

backend/app/services/discord_ingester.py

@@ -0,0 +1,85 @@
+"""Native Discord ingester — the Discord ADAPTER over `ingest_core.Ingester`.
+
+Thin counterpart to subscribestar_ingester (milestone 428). The walk's modes,
+both ledgers, cursor checkpointing and the post-first capture live in the core;
+this wires in the Discord client, downloader, ledger models and key.
+
+Two things differ from the cookie platforms:
+
+  - Discord authenticates with a user TOKEN, so `auth_token` is the credential
+    here rather than an argument accepted and ignored.
+  - The body canary is off. It fails a walk whose first 30+ captured posts all
+    came back without text, on the theory that a creator nearly always writes
+    something; a Discord drop is routinely files and nothing else, so on
+    Discord that is an ordinary backfill, not a broken parser.
+
+`campaign_id` is the source URL (a server, channel, thread or category link).
+FC runs on a plain-HTTP homelab; nothing here uses a secure-context Web API.
+"""
+
+from __future__ import annotations
+
+import asyncio
+from collections.abc import Callable
+from pathlib import Path
+
+from ..models import DiscordFailedMedia, DiscordSeenMedia
+from .discord_client import DiscordAPIError, DiscordClient, MediaItem
+from .discord_downloader import DiscordDownloader
+from .ingest_core import Ingester
+
+_LEDGER_KEY_MAX = 128
+
+
+def _ledger_key(media: MediaItem) -> str:
+    """`<message_id>:<media_id>` — stable across edits (see MediaItem)."""
+    return f"{media.post_id}:{media.media_id}"[:_LEDGER_KEY_MAX]
+
+
+class DiscordIngester(Ingester):
+    """Walk a Discord source's channels, download unseen files, return a
+    `DownloadResult`. `client` / `downloader` are injectable for tests."""
+
+    def __init__(
+        self,
+        images_root: Path,
+        cookies_path: str | None,
+        session_factory: Callable[[], object],
+        *,
+        validate: bool = True,
+        rate_limit: float = 0.0,
+        request_sleep: float = 0.0,
+        auth_token: str | None = None,
+        client: DiscordClient | None = None,
+        downloader: DiscordDownloader | None = None,
+    ):
+        del cookies_path  # Discord authenticates by token (uniform signature)
+        self.images_root = Path(images_root)
+        super().__init__(
+            client=client if client is not None else DiscordClient(
+                auth_token, request_sleep=request_sleep,
+            ),
+            downloader=downloader if downloader is not None else DiscordDownloader(
+                self.images_root, validate=validate, rate_limit=rate_limit,
+            ),
+            session_factory=session_factory,
+            seen_model=DiscordSeenMedia,
+            failed_model=DiscordFailedMedia,
+            seen_constraint="uq_discord_seen_media_source_id",
+            failed_constraint="uq_discord_failed_media_source_id",
+            ledger_key=_ledger_key,
+            platform="discord",
+            error_base=DiscordAPIError,
+            drift_label="Discord API",
+            body_canary=False,
+        )
+
+
+async def verify_discord_credential(url: str, auth_token: str | None) -> tuple[bool | None, str]:
+    """The uniform `(ok, message)` probe: is the token valid, and can its
+    account see the channel or server the source names?"""
+    if not auth_token:
+        return False, "No Discord token is saved — add one under Credentials."
+    client = DiscordClient(auth_token)
+    loop = asyncio.get_running_loop()
+    return await loop.run_in_executor(None, client.verify_auth, url)

backend/app/services/download_backends.py

@@ -23,6 +23,7 @@ from __future__ import annotations
 import asyncio
 from pathlib import Path
 
+from .discord_ingester import DiscordIngester
 from .gallery_dl import DownloadResult, ErrorType
 from .ingest_core import DEFAULT_REVISIT_DAYS
 from .patreon_ingester import PatreonIngester
@@ -31,9 +32,13 @@ from .platforms import known_platform_keys
 from .subscribestar_ingester import SubscribeStarIngester
 
 # Platforms whose download + verify go through the native ingester rather than
-# gallery-dl. gallery-dl still serves the rest (hentaifoundry, discord) until
-# they migrate too.
-NATIVE_INGESTER_PLATFORMS = frozenset({"patreon", "subscribestar"})
+# gallery-dl. gallery-dl still serves the rest (hentaifoundry) until it
+# migrates too. Discord joined in milestone 428.
+NATIVE_INGESTER_PLATFORMS = frozenset({"patreon", "subscribestar", "discord"})
+
+# Native platforms whose feed id IS the source URL, so there is nothing to
+# resolve: SubscribeStar's creator page, Discord's server/channel link.
+_URL_IS_FEED = frozenset({"subscribestar", "discord"})
 
 
 def _unsupported_platform_message(platform: str) -> str | None:
@@ -67,6 +72,7 @@ def _native_ingester_cls(platform: str):
     return {
         "patreon": PatreonIngester,
         "subscribestar": SubscribeStarIngester,
+        "discord": DiscordIngester,
     }[platform]
 
 
@@ -126,10 +132,10 @@ async def _resolve_native_campaign_id(
     platform: str, url: str, cookies_path: str | None, overrides: dict,
 ) -> tuple[str | None, str | None]:
     """`(campaign_id, resolved_campaign_id)` for a native source. SubscribeStar's
-    feed id IS the creator URL (no lookup → resolved None). Patreon resolves the
-    campaign id from the vanity URL (resolved non-None when a lookup actually ran,
-    so phase 3 caches it)."""
-    if platform == "subscribestar":
+    and Discord's feed id IS the source URL (no lookup → resolved None). Patreon
+    resolves the campaign id from the vanity URL (resolved non-None when a lookup
+    actually ran, so phase 3 caches it)."""
+    if platform in _URL_IS_FEED:
         return url, None
     return await resolve_campaign_id_for_source(url, cookies_path, overrides)
 
@@ -252,6 +258,10 @@ async def verify_source_credential(
             from .subscribestar_ingester import verify_subscribestar_credential
 
             return await verify_subscribestar_credential(url, cookies_path, config_overrides)
+        if platform == "discord":
+            from .discord_ingester import verify_discord_credential
+
+            return await verify_discord_credential(url, auth_token)
         from .patreon_ingester import verify_patreon_credential
 
         return await verify_patreon_credential(url, cookies_path, config_overrides)

backend/app/services/ingest_core.py

@@ -264,6 +264,14 @@ class Ingester:
         # operator-driven "re-read every body" pass; a horizon there would be a
         # third overlapping answer to a question that has two.
         post_meta = getattr(self.client, "post_meta", None)
+        # #4413: optional client seam for a source that is several feeds walked
+        # one after another (a Discord server: every channel and thread). The
+        # tick early-out means "this feed has nothing new", and without the
+        # seam it ends the WHOLE walk — so the first quiet channel would hide
+        # every channel after it. With it, the early-out asks the client to
+        # move on and the walk continues. Absent → the early-out ends the walk,
+        # exactly as before (Patreon and SubscribeStar are one feed each).
+        skip_feed = getattr(self.client, "skip_feed", None)
         horizon: datetime | None = None
         if mode == "tick" and revisit_days > 0 and post_meta is not None:
             horizon = datetime.now(UTC) - timedelta(days=revisit_days)
@@ -312,6 +320,7 @@ class Ingester:
         reached_bottom = False
         budget_hit = False
         early_out = False
+        feeds_caught_up = 0  # #4413: feeds a tick left early via skip_feed
         stopped = False  # plan #708 B4: operator hit Stop mid-walk
         cancel_armed = False  # latched once we observe a live "running" state
 
@@ -674,9 +683,15 @@ class Ingester:
                     })
 
                 if early_out:
-                    break
+                    if skip_feed is None:
+                        break
+                    skip_feed()
+                    feeds_caught_up += 1
+                    early_out = False
+                    consecutive_seen = 0
             else:
-                reached_bottom = True
+                # A walk that left feeds early did not read to their ends.
+                reached_bottom = not feeds_caught_up
         except self._error_base as exc:
             # The platform's client-error base — _failure_result (adapter)
             # maps it to a typed error.
@@ -724,6 +739,7 @@ class Ingester:
                 f", {revisited} post(s) updated ({revisit_downloads} new file(s))"
                 if revisited else ""
             )
+            + (f", {feeds_caught_up} feed(s) caught up" if feeds_caught_up else "")
             + (", reached end" if reached_bottom else "")
             + (", time-boxed" if budget_hit else "")
         )

backend/app/services/platform_lock.py

@@ -23,8 +23,10 @@ log = logging.getLogger(__name__)
 # Platforms walked one-at-a-time. gallery-dl platforms are intentionally NOT
 # here: each runs as a self-pacing subprocess and they're lower-volume. The
 # native-ingester platforms are serialized (one paced scrape/API walk at a time).
-# Add a platform here to cap it to a single concurrent walk.
-SERIALIZED_PLATFORMS = frozenset({"patreon", "subscribestar"})
+# Add a platform here to cap it to a single concurrent walk. Discord most of
+# all: every source walks on the operator's ONE user token, and parallel walks
+# on a user account are both how its rate limit trips and what gets it flagged.
+SERIALIZED_PLATFORMS = frozenset({"patreon", "subscribestar", "discord"})
 
 _LOCK_PREFIX = "fc:download_lock:"
 

tests/test_discord_client.py

@@ -0,0 +1,339 @@
+"""The native Discord client walks what gallery-dl walked, in its order (#4412).
+
+No network: a fake session answers by endpoint. What these pin is the part of
+gallery-dl's behaviour that decides WHICH files exist and WHAT they are called —
+the channel walk, the file list and its numbering, the name split — because a
+difference there is a re-download or a missed file at cutover, not a style
+choice.
+"""
+
+from __future__ import annotations
+
+from datetime import date
+
+import pytest
+
+from backend.app.services import discord_client as dc
+from backend.app.services.discord_client import (
+    DiscordAPIError,
+    DiscordAuthError,
+    DiscordClient,
+    firefox_user_agent,
+    message_text,
+    nameext_from_url,
+    parse_source_url,
+)
+
+
+class _Resp:
+    def __init__(self, status, body=None, headers=None):
+        self.status_code = status
+        self._body = body
+        self.headers = headers or {}
+        self.content = b"x"
+
+    def json(self):
+        return self._body
+
+
+class _Session:
+    """Answers `GET API_ROOT + endpoint` from a dict. A value may be a list of
+    responses, served in order; a messages entry is keyed by (endpoint, before)."""
+
+    def __init__(self, routes):
+        self.routes = routes
+        self.headers = {}
+        self.calls = []
+
+    def get(self, url, params=None, timeout=None):
+        endpoint = url[len(dc.API_ROOT):]
+        self.calls.append((endpoint, dict(params or {})))
+        key = endpoint
+        if endpoint.endswith("/messages"):
+            key = (endpoint, (params or {}).get("before"))
+        elif endpoint.endswith("/threads/search"):
+            key = (endpoint, (params or {}).get("offset"))
+        answer = self.routes.get(key, _Resp(404, {}))
+        if isinstance(answer, list):
+            return answer.pop(0)
+        return answer
+
+
+def _ok(body):
+    return _Resp(200, body)
+
+
+def _msg(mid, *, content="", attachments=(), embeds=(), **extra):
+    return {
+        "id": str(mid), "type": 0, "content": content,
+        "timestamp": "2026-09-20T12:00:00.000000+00:00",
+        "author": {"id": "7", "username": "artist"},
+        "attachments": list(attachments), "embeds": list(embeds), **extra,
+    }
+
+
+def _client(routes, **kw):
+    return DiscordClient("tok", session=_Session(routes), **kw)
+
+
+def _ids(client, url, cursor=None):
+    return [(m["id"], cur) for m, _meta, cur in client.iter_posts(url, cursor)]
+
+
+# -- pure helpers --------------------------------------------------------------
+
+def test_source_urls():
+    assert parse_source_url("https://discord.com/channels/1/2") == ("1", "2")
+    assert parse_source_url("https://discord.com/channels/1") == ("1", None)
+    assert parse_source_url("https://discord.com/channels/1/2/threads/3") == ("1", "3")
+    assert parse_source_url("https://discord.com/channels/@me/5") == (None, "5")
+    assert parse_source_url("discord.com/channels/1/2/") == ("1", "2")
+
+
+def test_a_message_link_is_not_a_source():
+    with pytest.raises(DiscordAPIError):
+        parse_source_url("https://discord.com/channels/1/2/3")
+    with pytest.raises(DiscordAPIError):
+        parse_source_url("https://example.com/channels/1/2")
+
+
+def test_name_split_matches_gallery_dl():
+    url = "https://cdn.discordapp.com/attachments/1/2/My%20Pic.final.PNG?ex=a&hm=b"
+    assert nameext_from_url(url) == ("My Pic.final", "png")
+    assert nameext_from_url("https://x/y/noext") == ("noext", "")
+    assert nameext_from_url("https://x/y/a." + "b" * 17) == ("a." + "b" * 17, "")
+
+
+def test_user_agent_is_gallery_dls_dated_firefox():
+    """gallery-dl's own comment: "147 on 2026-01-13"."""
+    assert "Firefox/147.0" in firefox_user_agent(date(2026, 1, 13))
+
+
+def test_message_text_takes_rich_embeds_and_polls():
+    m = _msg(1, content="hello", embeds=[
+        {"type": "rich", "author": {"name": "A"}, "title": "T",
+         "fields": [{"name": "f", "value": "v"}], "footer": {"text": "ft"}},
+        {"type": "image", "title": "not text"},
+    ], poll={"question": {"text": "Q?"}, "answers": [{"poll_media": {"text": "yes"}}]})
+    assert message_text(m) == "hello\nA\nT\nf\nv\nft\nQ?\nyes"
+
+
+def test_files_are_attachments_then_embeds_then_snapshots_numbered_across():
+    m = _msg(9, attachments=[{"url": "https://cdn/a/1.png"}], embeds=[
+        {"type": "video", "video": {"proxy_url": "https://media/v.mp4"},
+         "thumbnail": {"proxy_url": "https://media/t.jpg"}},
+        {"type": "image", "thumbnail": {"proxy_url": "https://media/i.webp"}},
+        {"type": "rich", "image": {"proxy_url": "https://media/rich.png"}},
+    ], message_snapshots=[
+        {"message": {"type": 0, "attachments": [{"url": "https://cdn/a/fwd.gif"}],
+                     "embeds": []}},
+        {"message": {"type": 7, "attachments": [{"url": "https://cdn/a/join.png"}]}},
+    ])
+    items = DiscordClient.extract_media(m)
+    assert [(i.num, i.filename, i.extension, i.kind) for i in items] == [
+        (1, "1", "png", "attachment"),
+        (2, "v", "mp4", "embed"),
+        (3, "i", "webp", "embed"),
+        (4, "fwd", "gif", "attachment"),
+    ]
+    assert {i.post_id for i in items} == {"9"}
+
+
+def test_the_ledger_identity_survives_a_renumbering_edit():
+    """Removing the first file renumbers the second; its identity must not move."""
+    a = {"id": "100", "url": "https://cdn/a/1.png?ex=1"}
+    b = {"id": "200", "url": "https://cdn/a/2.png?ex=1"}
+    before = DiscordClient.extract_media(_msg(9, attachments=[a, b]))
+    after = DiscordClient.extract_media(_msg(9, attachments=[b]))
+    assert (before[1].num, after[0].num) == (2, 1)
+    assert before[1].media_id == after[0].media_id == "200"
+
+
+def test_an_embeds_identity_ignores_its_signature():
+    def embed(sig):
+        return {"type": "image", "image": {"proxy_url": f"https://media/p/x.png?ex={sig}"}}
+
+    one = DiscordClient.extract_media(_msg(9, embeds=[embed("a")]))[0].media_id
+    two = DiscordClient.extract_media(_msg(9, embeds=[embed("b")]))[0].media_id
+    assert one == two and len(one) <= 33
+
+
+def test_post_seams():
+    with_file = _msg(5, attachments=[{"url": "https://cdn/a/1.png"}])
+    assert DiscordClient.post_record_key(with_file) == ("message:5", "5")
+    assert DiscordClient.post_record_key({}) is None
+
+
+def test_a_text_only_message_is_not_a_post():
+    """gallery-dl never made one: chat lines would bury the drops."""
+    assert DiscordClient.post_record_key(_msg(6, content="brb")) is None
+    assert DiscordClient.post_meta(_msg(1))["date"].startswith("2026-09-20")
+
+
+# -- the walk --------------------------------------------------------------------
+
+def test_a_channel_pages_newest_first_and_skips_system_messages():
+    page1 = [_msg(i) for i in range(300, 200, -1)]
+    page1[3]["type"] = 7  # a member-join line: not content
+    routes = {
+        "/guilds/1": _ok({"id": "1", "name": "S"}),
+        "/guilds/1/channels": _ok([{"id": "2", "type": 0, "name": "art"}]),
+        ("/channels/2/messages", None): _ok(page1),
+        ("/channels/2/messages", "201"): _ok([_msg(150)]),
+        ("/channels/2/threads/search", 0): _ok({"threads": []}),
+    }
+    got = _ids(_client(routes), "https://discord.com/channels/1/2")
+    assert len(got) == 100  # 99 of page 1 + 1 of page 2
+    assert "297" not in [mid for mid, _ in got]
+    assert got[0] == ("300", "2:")
+    assert got[-1] == ("150", "2:201")
+
+
+def test_messages_carry_server_and_channel_metadata():
+    routes = {
+        "/guilds/1": _ok({"id": "1", "name": "Studio", "owner_id": "9"}),
+        "/guilds/1/channels": _ok([
+            {"id": "4", "type": 4, "name": "Art"},
+            {"id": "2", "type": 0, "name": "drops", "parent_id": "4"},
+        ]),
+        ("/channels/2/messages", None): _ok([_msg(10)]),
+        ("/channels/2/threads/search", 0): _ok({"threads": []}),
+    }
+    [(msg, meta, _)] = list(_client(routes).iter_posts("https://discord.com/channels/1/2"))
+    assert msg["_meta"] is meta
+    assert meta["server"] == "Studio" and meta["server_id"] == "1"
+    assert meta["channel"] == "drops" and meta["channel_id"] == "2"
+    assert meta["parent"] == "Art"
+
+
+def test_a_server_walks_text_then_threads_newest_created_first_and_skips_private():
+    routes = {
+        "/guilds/1": _ok({"id": "1", "name": "S"}),
+        "/guilds/1/channels": _ok([
+            {"id": "2", "type": 0, "name": "text"},
+            {"id": "3", "type": 2, "name": "voice"},
+            {"id": "5", "type": 15, "name": "forum"},
+            {"id": "6", "type": 0, "name": "private"},
+        ]),
+        ("/channels/2/messages", None): _ok([_msg(20)]),
+        ("/channels/2/threads/search", 0): _ok({"threads": [
+            {"id": "21", "type": 11, "name": "old", "parent_id": "2", "thread_metadata": {}},
+            {"id": "22", "type": 11, "name": "new", "parent_id": "2", "thread_metadata": {}},
+        ]}),
+        ("/channels/22/messages", None): _ok([_msg(220)]),
+        ("/channels/21/messages", None): _Resp(403, {}),  # a private thread
+        ("/channels/5/threads/search", 0): _ok({"threads": [
+            {"id": "51", "type": 11, "name": "post", "parent_id": "5", "thread_metadata": {}},
+        ]}),
+        ("/channels/51/messages", None): _ok([_msg(510)]),
+        ("/channels/6/messages", None): _Resp(403, {}),
+        ("/channels/6/threads/search", 0): _Resp(403, {}),
+    }
+    got = [mid for mid, _ in _ids(_client(routes), "https://discord.com/channels/1")]
+    assert got == ["20", "220", "510"]
+
+
+def test_a_resume_cursor_reenters_its_channel_at_its_page():
+    routes = {
+        "/guilds/1": _ok({"id": "1", "name": "S"}),
+        "/guilds/1/channels": _ok([
+            {"id": "2", "type": 0, "name": "a"},
+            {"id": "3", "type": 0, "name": "b"},
+        ]),
+        ("/channels/2/threads/search", 0): _ok({"threads": []}),
+        ("/channels/3/threads/search", 0): _ok({"threads": []}),
+        ("/channels/3/messages", "77"): _ok([_msg(70)]),
+    }
+    client = _client(routes)
+    assert _ids(client, "https://discord.com/channels/1", "3:77") == [("70", "3:77")]
+    fetched = [c for c in client._session.calls if c[0].endswith("/messages")]
+    assert fetched == [("/channels/3/messages", {"limit": 100, "before": "77"})]
+
+
+def test_skip_feed_ends_the_channel_not_the_walk():
+    routes = {
+        "/guilds/1": _ok({"id": "1", "name": "S"}),
+        "/guilds/1/channels": _ok([
+            {"id": "2", "type": 0, "name": "a"},
+            {"id": "3", "type": 0, "name": "b"},
+        ]),
+        ("/channels/2/messages", None): _ok([_msg(29), _msg(28)]),
+        ("/channels/2/threads/search", 0): _ok({"threads": []}),
+        ("/channels/3/messages", None): _ok([_msg(39)]),
+        ("/channels/3/threads/search", 0): _ok({"threads": []}),
+    }
+    client = _client(routes)
+    seen = []
+    for msg, _meta, _cur in client.iter_posts("https://discord.com/channels/1"):
+        seen.append(msg["id"])
+        if msg["id"] == "29":
+            client.skip_feed()
+    assert seen == ["29", "39"]
+
+
+def test_the_named_channel_refusing_the_token_is_an_auth_failure():
+    routes = {
+        "/guilds/1": _ok({"id": "1", "name": "S"}),
+        "/guilds/1/channels": _ok([{"id": "2", "type": 0, "name": "a"}]),
+        ("/channels/2/messages", None): _Resp(403, {}),
+    }
+    with pytest.raises(DiscordAuthError):
+        list(_client(routes).iter_posts("https://discord.com/channels/1/2"))
+
+
+def test_401_is_an_invalid_token():
+    with pytest.raises(DiscordAuthError):
+        list(_client({"/guilds/1": _Resp(401, {})}).iter_posts(
+            "https://discord.com/channels/1"))
+
+
+def test_no_token_fails_before_any_request():
+    client = DiscordClient(None, session=_Session({}))
+    with pytest.raises(DiscordAuthError):
+        list(client.iter_posts("https://discord.com/channels/1"))
+    assert client._session.calls == []
+
+
+def test_429_waits_and_retries(monkeypatch):
+    waits = []
+    monkeypatch.setattr(dc.time, "sleep", waits.append)
+    routes = {"/users/@me": [
+        _Resp(429, {}, {"Retry-After": "1.5"}), _ok({"username": "me"}),
+    ], "/channels/2": _ok({"id": "2", "type": 0})}
+    ok, msg = _client(routes).verify_auth("https://discord.com/channels/1/2")
+    assert ok is True and "me" in msg
+    assert waits == [1.5]
+
+
+def test_verify_tells_a_bad_token_from_a_hidden_channel():
+    bad = _client({"/users/@me": _Resp(401, {})})
+    assert bad.verify_auth("https://discord.com/channels/1/2")[0] is False
+    hidden = _client({"/users/@me": _ok({"username": "me"}),
+                      "/channels/2": _Resp(403, {})})
+    ok, msg = hidden.verify_auth("https://discord.com/channels/1/2")
+    assert ok is False and "cannot see this channel" in msg
+    assert _client({}).verify_auth("https://discord.com/channels/1/2/3")[0] is None
+
+
+def test_the_request_profile_is_gallery_dls():
+    client = _client({})
+    h = client._session.headers
+    assert h["Authorization"] == "tok"
+    assert h["Referer"] == "https://discord.com/"
+    assert h["Accept"] == "*/*"
+    assert h["User-Agent"].startswith("Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:")
+
+
+# -- the adapter ---------------------------------------------------------------
+
+def test_the_adapter_authenticates_with_the_token_and_keys_by_identity(tmp_path):
+    from backend.app.services.discord_ingester import DiscordIngester, _ledger_key
+
+    ing = DiscordIngester(tmp_path, None, session_factory=None, auth_token="tok")
+    assert ing.client._session.headers["Authorization"] == "tok"
+    # A files-only drop is ordinary on Discord, not a broken parser.
+    assert ing._body_canary is False
+    [media] = DiscordClient.extract_media(
+        _msg(9, attachments=[{"id": "300", "url": "https://cdn/a/1.png"}])
+    )
+    assert _ledger_key(media) == "9:300"

tests/test_discord_downloader.py

@@ -0,0 +1,135 @@
+"""The native Discord downloader lands files where gallery-dl did (#4414).
+
+A cutover that names one file differently re-downloads it and imports a
+duplicate, so these pin the path, the name cleaning and the sidecar pairing
+against what gallery-dl's config produces — and that the records it writes read
+back through `parse_sidecar` as the same post the gallery-dl sidecars made.
+"""
+
+from __future__ import annotations
+
+import json
+
+from backend.app.services.discord_client import DiscordClient
+from backend.app.services.discord_downloader import (
+    DiscordDownloader,
+    channel_dir,
+    gdl_clean,
+    media_stem,
+)
+from backend.app.utils.sidecar import find_sidecar, parse_sidecar
+
+_PNG = b"\x89PNG\r\n\x1a\n" + b"\x00" * 16 + b"\x00\x00\x00\x00IEND\xaeB`\x82"
+
+
+class _Resp:
+    status_code = 200
+    headers: dict = {}
+
+    def raise_for_status(self):
+        pass
+
+    def iter_content(self, chunk_size=None):
+        yield _PNG
+
+
+class _Media:
+    def __init__(self):
+        self.calls = []
+
+    def get(self, url, stream=None, timeout=None, headers=None):
+        self.calls.append(url)
+        return _Resp()
+
+
+def _message(**extra):
+    return {
+        "id": "1234", "type": 0, "timestamp": "2026-09-20T23:30:00.000000+00:00",
+        "content": "new set!", "channel_id": "22",
+        "author": {"id": "7", "username": "artist"},
+        "attachments": [{"url": "https://cdn.discordapp.com/attachments/2/3/Red%3AAlt.PNG?ex=1"}],
+        "embeds": [],
+        "_meta": {"server": "Studio", "server_id": "11", "channel": "drops/nsfw",
+                  "channel_id": "22", "is_thread": False},
+        **extra,
+    }
+
+
+def _downloader(tmp_path, session=None):
+    return DiscordDownloader(tmp_path, validate=False, session=session or _Media())
+
+
+def test_names_follow_gallery_dls_pattern_and_linux_cleaning(tmp_path):
+    msg = _message()
+    [media] = DiscordClient.extract_media(msg)
+    assert channel_dir(tmp_path, "art", msg) == tmp_path / "art" / "discord" / "drops_nsfw"
+    # `:` survives: gallery-dl on Linux only replaces `/`.
+    assert media_stem(msg, media) == "20260920_1234_01_Red:Alt"
+    assert gdl_clean("a\x07b/c") == "ab_c"
+
+
+def test_a_channel_with_no_name_adds_no_directory(tmp_path):
+    msg = _message(_meta={"channel": "  "})
+    assert channel_dir(tmp_path, "art", msg) == tmp_path / "art" / "discord"
+
+
+def test_a_file_gallery_dl_already_wrote_is_not_fetched_again(tmp_path):
+    msg = _message()
+    media = DiscordClient.extract_media(msg)
+    existing = tmp_path / "art" / "discord" / "drops_nsfw" / "20260920_1234_01_Red:Alt.png"
+    existing.parent.mkdir(parents=True)
+    existing.write_bytes(_PNG)
+    session = _Media()
+    [out] = _downloader(tmp_path, session).download_post(msg, media, "art")
+    assert out.status == "skipped_disk" and out.path == existing
+    assert session.calls == []
+
+
+def test_a_new_file_gets_a_sidecar_the_importer_pairs_to_its_message(tmp_path):
+    msg = _message()
+    [out] = _downloader(tmp_path).download_post(msg, DiscordClient.extract_media(msg), "art")
+    assert out.status == "downloaded"
+    assert out.path.name == "20260920_1234_01_Red:Alt.png"
+    sidecar = find_sidecar(out.path)
+    assert sidecar is not None
+    data = json.loads(sidecar.read_text())
+    # No `id`/`post_id`: either would outrank message_id as the post id.
+    assert "id" not in data and "post_id" not in data
+    sd = parse_sidecar(data)
+    assert sd.external_post_id == "1234"
+    assert sd.source_url.startswith("https://cdn.discordapp.com/")
+
+
+def test_a_seen_file_is_skipped_without_a_request(tmp_path):
+    msg = _message()
+    session = _Media()
+    [out] = _downloader(tmp_path, session).download_post(
+        msg, DiscordClient.extract_media(msg), "art", is_seen=lambda m: True,
+    )
+    assert out.status == "skipped_seen" and session.calls == []
+
+
+def test_the_message_record_reads_back_as_the_gallery_dl_post(tmp_path):
+    rec = _downloader(tmp_path).write_post_record(_message(), "art")
+    assert rec.path.name == "20260920_1234_post.json"
+    assert rec.body_chars == len("new set!")
+    sd = parse_sidecar(json.loads(rec.path.read_text()))
+    assert sd.platform == "discord"
+    assert sd.external_post_id == "1234"
+    assert sd.post_url == "https://discord.com/channels/11/22/1234"
+    assert sd.description == "new set!"
+    assert sd.post_date.isoformat().startswith("2026-09-20T23:30")
+
+
+def test_the_record_is_not_a_media_sidecar(tmp_path):
+    """It must not pair with any file of the message."""
+    msg = _message()
+    dl = _downloader(tmp_path)
+    [out] = dl.download_post(msg, DiscordClient.extract_media(msg), "art")
+    rec = dl.write_post_record(msg, "art")
+    assert find_sidecar(out.path) != rec.path
+
+
+def test_an_empty_re_read_never_blanks_a_stored_body(tmp_path):
+    rec = _downloader(tmp_path).write_post_record(_message(content=""), "art", revisit=True)
+    assert rec.path is None

tests/test_download_backends.py

@@ -17,7 +17,7 @@ from backend.app.services.gallery_dl import ErrorType
 
 
 def test_native_platforms():
-    for platform in ("patreon", "subscribestar"):
+    for platform in ("patreon", "subscribestar", "discord"):
         assert uses_native_ingester(platform) is True
         assert platform in NATIVE_INGESTER_PLATFORMS
 
@@ -104,8 +104,20 @@ async def test_verifying_a_retired_platform_is_inconclusive_not_rejected():
 def test_gallery_dl_platforms_are_not_native():
     # The platforms still served by gallery-dl must NOT route to the native
     # ingester — guards an accidental over-broad migration.
-    for platform in ("hentaifoundry", "discord"):
-        assert uses_native_ingester(platform) is False
+    assert uses_native_ingester("hentaifoundry") is False
+
+
+@pytest.mark.asyncio
+async def test_discord_verify_without_a_token_is_a_rejection_not_a_request():
+    """Discord authenticates by token (milestone 428); with none saved there is
+    nothing to send, and saying so beats an HTTP 401 from Discord."""
+    ok, message = await verify_source_credential(
+        platform="discord", url="https://discord.com/channels/1/2",
+        artist_slug="someone", config_overrides=None, cookies_path=None,
+        auth_token=None, images_root=Path("/nonexistent"),
+    )
+    assert ok is False
+    assert "token" in message.lower()
 
 
 def test_unknown_platform_is_not_native():

tests/test_patreon_ingester.py

@@ -319,6 +319,64 @@ async def test_tick_early_out_after_threshold(source_id, sync_engine, tmp_path):
     assert client.consumed_posts == 2
 
 
+class _FeedsClient(_FakeClient):
+    """A source that is several feeds walked in turn (a Discord server's
+    channels), with the optional `skip_feed` seam (#4413). `feeds` is a list of
+    `pages` lists, one per feed."""
+
+    def __init__(self, feeds):
+        super().__init__([page for pages in feeds for page in pages])
+        self._feeds = feeds
+        self._skip = False
+        self.skips = 0
+
+    def skip_feed(self):
+        self._skip = True
+        self.skips += 1
+
+    def iter_posts(self, campaign_id, cursor=None):
+        for pages in self._feeds:
+            self._skip = False
+            self._pages = pages
+            for item in super().iter_posts(campaign_id, cursor):
+                yield item
+                if self._skip:
+                    break
+
+
+def _seed_seen_media(sync_engine, source_id, media):
+    factory = sessionmaker(sync_engine, expire_on_commit=False)
+    with factory() as s:
+        for m in media:
+            s.add(PatreonSeenMedia(source_id=source_id, filehash=_ledger_key(m), post_id=m.post_id))
+        s.commit()
+
+
+@pytest.mark.asyncio
+async def test_a_quiet_feed_ends_itself_not_the_walk(source_id, sync_engine, tmp_path):
+    """#4413: a Discord server's first channel is all seen; the tick must still
+    reach the second channel's new file, instead of stopping at the first."""
+    quiet = [_media(f"a{i}", 1) for i in range(1, 5)]
+    _seed_seen_media(sync_engine, source_id, quiet)
+    fresh = _media("b1", 1)
+    client = _FeedsClient([
+        [(None, [(m.post_id, [m]) for m in quiet])],
+        [(None, [("b1", [fresh])])],
+    ])
+    downloader = _FakeDownloader(tmp_path)
+    result = _ingester(sync_engine, tmp_path, client, downloader).run(
+        source_id=source_id, campaign_id="c1", artist_slug="ingest",
+        url="https://patreon.com/ingest", mode="tick", seen_threshold=2,
+    )
+    assert result.success is True
+    assert client.skips == 1
+    # The quiet feed stopped after its 2nd seen post; the next feed was walked.
+    assert client.consumed_posts == 3
+    assert downloader.download_calls == 1
+    assert "1 feed(s) caught up" in result.stdout
+    assert "reached end" not in result.stdout
+
+
 # --- backfill -------------------------------------------------------------
 
 

tests/test_platform_lock.py

@@ -10,7 +10,11 @@ pytestmark = pytest.mark.integration
 def test_non_serialized_platform_has_no_lock():
     # gallery-dl platforms aren't capped — they get no lock at all.
     assert platform_lock("hentaifoundry", ttl_seconds=60) is None
-    assert platform_lock("discord", ttl_seconds=60) is None
+
+
+def test_discord_is_serialized():
+    # Native since milestone 428, and every source shares one user token.
+    assert platform_lock("discord", ttl_seconds=60) is not None
 
 
 def test_subscribestar_is_serialized():