feat: finish the Discord switchover — recapture on every native source, backfills that run, gallery-dl's Discord config retired (milestone 428)

- Recover and Recapture show on every native source. The menu gated them on
  a copied platform list ('patreon', 'subscribestar') that went stale when
  Discord moved over. Sources now carry `native_ingester` from the backend's
  own predicate.
- A running backfill is due on every scheduler tick. Nothing queued a
  backfill's next chunk: each one waited for the source's regular interval,
  so an armed backfill sat idle until the next check (8h at the default) and
  a five-chunk walk took most of two days. The in-flight guard and the
  platform lock keep one chunk at a time. A failing source falls back to its
  backoff, and a stalled or out-of-budget walk stops being due. It also runs
  when the artist has auto-check off, since the operator started it by hand.
- gallery-dl no longer carries Discord: its naming constants, platform
  defaults, sidecar-mirroring postprocessor and token injection are gone.
  The naming test moves to the native downloader and still renders against
  the real gallery-dl sidecar fixture. That is the guard that the files
  gallery-dl wrote are found on disk rather than fetched again.

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

backend/app/services/discord_downloader.py

@@ -6,9 +6,11 @@ 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` /
+That is what FC's gallery-dl config produced (directory `{channel}`, filename
-`DISCORD_FILENAME`) under the per-source base directory
+`{date:%Y%m%d}_{message_id}_{num:>02}_{filename}.{extension}`, under the
-`<images>/<artist>/<platform>`. The name is cleaned the way gallery-dl cleans it
+per-source base directory `<images>/<artist>/<platform>`), retired from that
+config once Discord moved here; tests/test_discord_naming.py pins the match
+against a real gallery-dl sidecar. 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

backend/app/services/gallery_dl.py

@@ -95,48 +95,6 @@ BACKFILL_CHUNK_SECONDS = 600
 _DEFAULT_GDL_TIMEOUT_SECONDS = 870
 
 
-# --- Discord naming ---------------------------------------------------------
-#
-# Derived from a REAL sidecar (operator's instance, 2026-09-13), not from memory
-# of gallery-dl's extractor. What gallery-dl's discord extractor actually emits
-# for an attachment: `channel` is a plain STRING (the channel's name), the
-# message is `message_id`, the attachment's position in it is `num`, and there
-# is NO `id` key at all.
-#
-# The previous patterns asked for `{channel[name]}` and `{id}`. Both render as
-# "None", so every Discord download since the platform was added landed in a
-# directory called `None` as `<date>_None_<original name>`. Worse, the sidecar was
-# named `{filename}.json` — the attachment's ORIGINAL name — which (a) `find_
-# sidecar` can never pair with `<date>_None_<name>.png`, so no Discord file ever
-# got a Post or a post date, and (b) collides: every `image.png` in a channel
-# overwrote the same `image.json`, so the one sidecar that survived described
-# whichever message happened to be written last.
-#
-# The fix names the sidecar EXACTLY like the media minus its extension, so
-# `find_sidecar`'s first candidate (`media.with_suffix(".json")`) is the match
-# and the name is unique per attachment. tests/test_gallery_dl_naming.py renders
-# these patterns against a sanitized copy of the real sidecar, so a key that
-# does not exist fails CI instead of silently becoming "None".
-DISCORD_FILENAME = "{date:%Y%m%d}_{message_id}_{num:>02}_{filename}.{extension}"
-DISCORD_DIRECTORY = ["{channel}"]
-
-
-def sidecar_name_for(media_pattern: str) -> str | None:
-    """The metadata filename pattern that names a sidecar exactly like its media.
-
-    Returns None for a pattern that does not end in `.{extension}`, since then
-    there is no media stem to mirror and the caller must fall back.
-    """
-    suffix = ".{extension}"
-    if not media_pattern.endswith(suffix):
-        return None
-    return media_pattern[: -len(suffix)] + ".json"
-
-
-def metadata_postprocessor(filename: str) -> dict:
-    return {"name": "metadata", "mode": "json", "directory": ".", "filename": filename}
-
-
 def archive_path(images_root: Path) -> Path:
     """gallery-dl's download archive: the record of what it has already fetched.
 
@@ -425,27 +383,16 @@ class GalleryDLService:
     # (services/patreon_ingester.py), not gallery-dl.
     PLATFORM_DEFAULTS = {
         # subscribestar removed — native-ingester platform now (#71); pixiv
-        # removed likewise (#129); deviantart removed at #3069 as a dropped
+        # removed likewise (#129); discord likewise (milestone 428, whose
-        # platform, not a migrated one. The remaining entries are the
+        # downloader keeps this config's on-disk naming); deviantart removed at
-        # gallery-dl platforms not yet migrated.
+        # #3069 as a dropped platform, not a migrated one. HentaiFoundry is the
+        # one platform left here, by the operator's choice not to migrate it.
         "hentaifoundry": {
             "content_types": ["all"],
             "directory": [],
             "filename": "{category}_{index:>03}_{title[:50]}.{extension}",
             "include": "all",
         },
-        "discord": {
-            "content_types": ["all"],
-            "directory": DISCORD_DIRECTORY,
-            "filename": DISCORD_FILENAME,
-            # Overrides the global `{filename}.json` sidecar for this extractor
-            # only — see the Discord naming note above.
-            "postprocessors": [metadata_postprocessor(sidecar_name_for(DISCORD_FILENAME))],
-            "embeds": "all",
-            "stickers": True,
-            "reactions": False,
-            "threads": True,
-        },
     }
 
     def __init__(
@@ -560,17 +507,6 @@ class GalleryDLService:
         if source_config.filename_pattern:
             platform_section["filename"] = source_config.filename_pattern
 
-        # A platform that names its sidecar after its media must keep doing so
-        # under a per-source filename override, or the pairing breaks exactly the
-        # way Discord's did. No metadata wanted means no platform postprocessor
-        # either — the global list was already dropped above.
-        if "postprocessors" in platform_section:
-            mirrored = sidecar_name_for(platform_section.get("filename") or "")
-            if not source_config.save_metadata or mirrored is None:
-                platform_section.pop("postprocessors")
-            else:
-                platform_section["postprocessors"] = [metadata_postprocessor(mirrored)]
-
         platform_section["metadata"] = source_config.save_metadata
 
         return config
@@ -818,9 +754,6 @@ class GalleryDLService:
 
         if cookies_path:
             config["extractor"]["cookies"] = cookies_path
-        if auth_token and platform == "discord":
-            config["extractor"].setdefault("discord", {})
-            config["extractor"]["discord"]["token"] = auth_token
 
         with tempfile.NamedTemporaryFile(
             mode="w", suffix=".json", delete=False, dir=str(self._config_dir),
@@ -1004,8 +937,6 @@ class GalleryDLService:
         config = self._build_config_for_source(platform, source_config, artist_slug)
         if cookies_path:
             config["extractor"]["cookies"] = cookies_path
-        if auth_token and platform == "discord":
-            config["extractor"].setdefault("discord", {})["token"] = auth_token
 
         with tempfile.NamedTemporaryFile(
             mode="w", suffix=".json", delete=False, dir=str(self._config_dir),

backend/app/services/scheduler_service.py

@@ -115,6 +115,32 @@ async def active_platform_cooldowns(session: AsyncSession) -> dict[str, datetime
     return active
 
 
+def backfill_ready(source: Source) -> bool:
+    """A deep walk the operator started, with budget left and no failure
+    backing it off — due NOW rather than at its next scheduled check.
+
+    A backfill runs one time-boxed chunk per download (plan #693), and nothing
+    queued the next chunk: each waited for the source's regular interval. At
+    the 8-hour default a freshly armed backfill sat untouched until the next
+    check (the operator armed one on 2026-09-25 and saw nothing happen) and a
+    five-chunk walk took most of two days. The tick's in-flight guard keeps
+    one chunk at a time per source and the platform lock one walk per
+    platform, so "due every tick" means "next chunk as soon as the last one
+    ends".
+
+    The failure gate is what keeps a broken source from retrying every
+    minute: any failed chunk raises `consecutive_failures`, which drops the
+    source back onto its backed-off interval. A chunk that fails to progress
+    twice marks the walk stalled (download_service), which ends it here too.
+    """
+    co = source.config_overrides or {}
+    return (
+        co.get("_backfill_state") == "running"
+        and (source.backfill_runs_remaining or 0) > 0
+        and not (source.consecutive_failures or 0)
+    )
+
+
 async def select_due_sources(session: AsyncSession) -> list[Source]:
     """Sources where (enabled, artist.auto_check) and now >= last_checked_at + effective_interval.
 
@@ -123,6 +149,9 @@ async def select_due_sources(session: AsyncSession) -> list[Source]:
     cooldown is the preventive half of the burst-prevention pair (per-source
     consecutive_failures backoff handles the offending source itself).
 
+    A running backfill (`backfill_ready`) is due on every tick, and whether
+    or not its artist is on auto-check — the operator started it by hand.
+
     Ordering: last_checked_at ASC NULLS FIRST, then id. Never-checked
     sources go first, then the longest-since-checked, so the most overdue
     sources hit Celery's FIFO download queue first. Anti-starvation: if
@@ -135,7 +164,6 @@ async def select_due_sources(session: AsyncSession) -> list[Source]:
         .options(selectinload(Source.artist))
         .join(Artist, Source.artist_id == Artist.id)
         .where(Source.enabled.is_(True))
-        .where(Artist.auto_check.is_(True))
         .order_by(Source.last_checked_at.asc().nulls_first(), Source.id)
     )).scalars().all()
 
@@ -147,6 +175,11 @@ async def select_due_sources(session: AsyncSession) -> list[Source]:
     for s in rows:
         if s.platform in cooldowns:
             continue
+        if backfill_ready(s):
+            due.append(s)
+            continue
+        if not s.artist.auto_check:
+            continue
         interval = compute_effective_interval(s, s.artist, settings)
         if s.last_checked_at is None:
             due.append(s)
@@ -161,6 +194,8 @@ def compute_next_check_at(
     source: Source, artist: Artist, settings: ImportSettings,
 ) -> datetime | None:
     """Return the projected datetime of the next check, or None if never checked."""
+    if backfill_ready(source):
+        return datetime.now(UTC)
     if source.last_checked_at is None:
         return None
     interval = compute_effective_interval(source, artist, settings)

backend/app/services/source_service.py

@@ -18,6 +18,7 @@ from ..models import (
     Source,
 )
 from .db_helpers import failing_sources_clause
+from .download_backends import uses_native_ingester
 from .gallery_dl import ErrorType
 from .membership_reconcile import KEPT_KEY, STOPPED_KEY
 from .membership_roster import gated_reasons_for_sources
@@ -125,6 +126,11 @@ class SourceRecord:
             "backfill_posts": self.backfill_posts,
             "tier_gated_count": self.tier_gated_count,
             "gated_reason": self.gated_reason,
+            # Recover / recapture exist only on the native ingester. Sent so the
+            # UI asks the backend's own predicate instead of keeping a copy of
+            # the platform list — the copy said "patreon, subscribestar" for a
+            # day after Discord went native (milestone 428).
+            "native_ingester": uses_native_ingester(self.platform),
         }
 
 
@@ -551,8 +557,8 @@ class SourceService:
         whole source); the two flags are mutually exclusive, so arming recapture
         clears bypass_seen. Clears prior cursor/chunk/stall state so it walks
         fresh from the top. The flag is cleared on completion (download_service)
-        and on stop. Recapture is Patreon-only (the native ingester's post-record
+        and on stop. Recapture needs the native ingester's post-record capture,
-        capture); inert elsewhere. The UI gates the action to Patreon sources."""
+        so the UI offers it on native sources only (`native_ingester`)."""
         source = (await self.session.execute(
             select(Source).where(Source.id == source_id)
         )).scalar_one_or_none()

frontend/src/components/subscriptions/SourceActions.vue

@@ -76,10 +76,10 @@ const running = computed(() => props.source.backfill_state === 'running')
 const recovering = computed(() => !!props.source.backfill_bypass_seen)
 const recapturing = computed(() => !!props.source.backfill_recapture)
 // Recover / recapture are native-ingester features (ledger-bypass re-walk and
-// post-text re-grab), available to every native platform — not just Patreon.
+// post-text re-grab), available on every native platform. The backend says
-// Mirrors backend download_backends.NATIVE_INGESTER_PLATFORMS.
+// which those are (`native_ingester`); a copied list here went stale when
-const NATIVE_PLATFORMS = ['patreon', 'subscribestar']
+// Discord moved over.
-const isNative = computed(() => NATIVE_PLATFORMS.includes(props.source.platform))
+const isNative = computed(() => !!props.source.native_ingester)
 </script>
 
 <style scoped>

frontend/src/components/subscriptions/SubscriptionsTab.vue

@@ -679,7 +679,7 @@ async function onRecover(source) {
   }
 }
 
-// #830: arm a recapture walk (Patreon-only) — re-grab every post's body +
+// #830: arm a recapture walk (native platforms) — re-grab every post's body +
 // external links and localize on-disk inline images, without re-downloading
 // media. Reuses the backfill lifecycle/badge; stop via the same Stop control.
 async function onRecapture(source) {

frontend/src/stores/sources.js

@@ -140,7 +140,7 @@ export const useSourcesStore = defineStore('sources', () => {
     _patchSource(body)
     return body
   }
-  // #830: arm a recapture walk (Patreon-only) — re-grab every post's body +
+  // #830: arm a recapture walk (native platforms) — re-grab every post's body +
   // external links and localize on-disk inline images, WITHOUT re-downloading
   // media. Shares the backfill lifecycle/badge; stop via stopBackfill.
   async function recaptureSource(id, artistIdHint = null) {

tests/test_discord_naming.py

@@ -0,0 +1,69 @@
+"""Discord file naming, checked against the metadata gallery-dl really emitted.
+
+Discord moved from gallery-dl to the native downloader in milestone 428. Every
+file gallery-dl wrote is on disk under gallery-dl's naming, and the native
+downloader finds it there — skips it instead of fetching it again — only if it
+builds the SAME name. This file used to pin gallery-dl's patterns (#3999: they
+named keys the extractor never set, and every file landed as
+`None/<date>_None_<name>`); it now pins the native downloader to what those
+patterns produced from the same real metadata.
+
+The fixture keeps the key set and value types of a real attachment sidecar
+from the operator's instance (2026-09-13), with every value invented.
+"""
+
+import json
+from pathlib import Path
+
+from backend.app.services.discord_client import DiscordClient
+from backend.app.services.discord_downloader import channel_dir, media_stem
+from backend.app.utils.sidecar import find_sidecar
+
+_FIXTURE = Path(__file__).parent / "fixtures" / "discord_attachment_sidecar.json"
+
+
+def _message_from_the_fixture():
+    """The API message that produced the fixture's sidecar."""
+    gdl = json.loads(_FIXTURE.read_text())
+    date, time = gdl["date"].split(" ")
+    return {
+        "id": gdl["message_id"],
+        "type": 0,
+        "timestamp": f"{date}T{time}.000000+00:00",
+        "content": gdl["message"],
+        "attachments": [{"id": "500000000000000005", "url": gdl["url"]}],
+        "embeds": [],
+        "_meta": {"channel": gdl["channel"], "channel_id": gdl["channel_id"],
+                  "server": gdl["server"], "server_id": gdl["server_id"]},
+    }
+
+
+def test_the_native_name_is_the_name_gallery_dl_wrote(tmp_path):
+    """gallery-dl's `{date:%Y%m%d}_{message_id}_{num:>02}_{filename}.{extension}`
+    in directory `{channel}`, rendered from the fixture."""
+    msg = _message_from_the_fixture()
+    [media] = DiscordClient.extract_media(msg)
+    assert media_stem(msg, media) + "." + media.extension == (
+        "20240716_300000000000000003_01_image.png"
+    )
+    assert channel_dir(tmp_path, "a", msg) == tmp_path / "a" / "discord" / "nsfw-drops"
+
+
+def test_a_gallery_dl_sidecar_on_disk_still_pairs_with_its_file(tmp_path):
+    """Files gallery-dl wrote keep their full sidecars beside them; the native
+    name must be the stem those sidecars were named after."""
+    msg = _message_from_the_fixture()
+    [media] = DiscordClient.extract_media(msg)
+    stem = media_stem(msg, media)
+    (tmp_path / f"{stem}.png").write_bytes(b"x")
+    (tmp_path / f"{stem}.json").write_text(_FIXTURE.read_text())
+    assert find_sidecar(tmp_path / f"{stem}.png") == tmp_path / f"{stem}.json"
+
+
+def test_two_files_with_the_same_original_name_get_distinct_names():
+    """`image.png` is Discord's default name; two messages must not collide."""
+    one = _message_from_the_fixture()
+    two = {**one, "id": "300000000000000099"}
+    [m1] = DiscordClient.extract_media(one)
+    [m2] = DiscordClient.extract_media(two)
+    assert media_stem(one, m1) != media_stem(two, m2)

tests/test_gallery_dl_naming.py

@@ -1,117 +0,0 @@
-"""gallery-dl naming patterns, rendered against the metadata gallery-dl really emits.
-
-gallery-dl does not fail on a format field that names a key the extractor never
-sets. It renders "None" and carries on. That is how every Discord download
-landed in a `None/` directory as `<date>_None_<name>`: the patterns asked for
-`{channel[name]}` and `{id}`, and the real metadata has a string `channel` and
-`message_id`, with no `id` at all. The mismatch also broke sidecar pairing, so
-no Discord file ever got a Post or a post date.
-
-The fixture keeps the key set and value TYPES of a real attachment sidecar from
-the operator's instance (2026-09-13), with every value invented. Rendering
-through Python's own formatter raises on a missing key or a subscript into a
-string, which is the loud failure gallery-dl does not give.
-"""
-
-import json
-import string
-from datetime import datetime
-from pathlib import Path
-
-import pytest
-
-from backend.app.services.gallery_dl import (
-    DISCORD_DIRECTORY,
-    DISCORD_FILENAME,
-    GalleryDLService,
-    SourceConfig,
-    sidecar_name_for,
-)
-from backend.app.utils.sidecar import find_sidecar
-
-_FIXTURE = Path(__file__).parent / "fixtures" / "discord_attachment_sidecar.json"
-
-
-@pytest.fixture
-def kwdict():
-    data = json.loads(_FIXTURE.read_text())
-    # gallery-dl hands the formatter a datetime; the JSON sidecar stores it as text.
-    data["date"] = datetime.strptime(data["date"], "%Y-%m-%d %H:%M:%S")
-    return data
-
-
-def _render(pattern, kwdict):
-    return string.Formatter().vformat(pattern, (), kwdict)
-
-
-def test_the_discord_filename_renders_from_real_keys(kwdict):
-    name = _render(DISCORD_FILENAME, kwdict)
-    assert "None" not in name
-    assert name == "20240716_300000000000000003_01_image.png"
-
-
-def test_the_discord_directory_renders_from_real_keys(kwdict):
-    assert [_render(p, kwdict) for p in DISCORD_DIRECTORY] == ["nsfw-drops"]
-
-
-@pytest.mark.parametrize(
-    "broken", ["{channel[name]}", "{date:%Y%m%d}_{id}_{filename}.{extension}"],
-)
-def test_the_patterns_that_shipped_would_have_failed_here(kwdict, broken):
-    """Positive control: the two patterns that produced `None/..._None_...`
-    must fail this renderer, or the tests above prove nothing."""
-    with pytest.raises((KeyError, TypeError)):
-        _render(broken, kwdict)
-
-
-def test_the_sidecar_is_named_exactly_like_its_media(kwdict, tmp_path):
-    """So `find_sidecar` pairs them on its first candidate, and two attachments
-    that share an original name (`image.png`) can never share a sidecar."""
-    media = tmp_path / _render(DISCORD_FILENAME, kwdict)
-    sidecar = tmp_path / _render(sidecar_name_for(DISCORD_FILENAME), kwdict)
-    media.write_bytes(b"x")
-    sidecar.write_text("{}")
-    assert find_sidecar(media) == sidecar
-
-
-def test_two_attachments_with_the_same_original_name_get_distinct_sidecars(kwdict):
-    other = {**kwdict, "message_id": "300000000000000099"}
-    pattern = sidecar_name_for(DISCORD_FILENAME)
-    assert _render(pattern, kwdict) != _render(pattern, other)
-
-
-def test_sidecar_name_for_needs_an_extension_suffix():
-    assert sidecar_name_for("{a}_{b}.{extension}") == "{a}_{b}.json"
-    assert sidecar_name_for("{a}_{b}") is None
-
-
-# --- the config gallery-dl is actually given -----------------------------------
-
-
-@pytest.fixture
-def gdl(tmp_path):
-    return GalleryDLService(images_root=tmp_path / "images", validate_files=False)
-
-
-def _discord_section(gdl, **overrides):
-    cfg = gdl._build_config_for_source(
-        platform="discord", source_config=SourceConfig(**overrides), artist_slug="a",
-    )
-    return cfg["extractor"]["discord"]
-
-
-def test_discord_config_carries_the_mirrored_sidecar(gdl):
-    section = _discord_section(gdl)
-    assert section["filename"] == DISCORD_FILENAME
-    assert section["directory"] == DISCORD_DIRECTORY
-    assert section["postprocessors"][0]["filename"] == sidecar_name_for(DISCORD_FILENAME)
-
-
-def test_a_filename_override_keeps_the_sidecar_mirrored(gdl):
-    section = _discord_section(gdl, filename_pattern="{message_id}_{num}.{extension}")
-    assert section["postprocessors"][0]["filename"] == "{message_id}_{num}.json"
-
-
-def test_no_metadata_means_no_discord_postprocessor(gdl):
-    section = _discord_section(gdl, save_metadata=False)
-    assert "postprocessors" not in section

tests/test_scheduler_service.py

@@ -11,6 +11,7 @@ import pytest
 
 from backend.app.models import Artist, ImportSettings, Source
 from backend.app.services.scheduler_service import (
+    backfill_ready,
     compute_effective_interval,
     scheduler_status,
     select_due_sources,
@@ -150,6 +151,67 @@ async def test_select_includes_past_due(db):
     assert any(s.url == "https://sel-past" for s in due)
 
 
+# --- a running backfill is due every tick (2026-09-25) ---------------------
+
+
+def _backfilling(runs=5, failures=0, state="running"):
+    src = _src(failures=failures)
+    src.config_overrides = {"_backfill_state": state}
+    src.backfill_runs_remaining = runs
+    return src
+
+
+def test_a_running_backfill_is_ready():
+    assert backfill_ready(_backfilling()) is True
+
+
+def test_a_backfill_out_of_budget_or_not_running_is_not_ready():
+    assert backfill_ready(_backfilling(runs=0)) is False
+    assert backfill_ready(_backfilling(state="stalled")) is False
+    assert backfill_ready(_src()) is False
+
+
+def test_a_failing_backfill_falls_back_to_its_backoff():
+    """Otherwise a source whose chunks keep erroring would retry every minute."""
+    assert backfill_ready(_backfilling(failures=1)) is False
+
+
+@pytest.mark.asyncio
+async def test_select_runs_a_backfill_now_not_at_its_next_check(db):
+    """Checked a minute ago on an hourly interval: not due, unless backfilling —
+    the next chunk should not wait an interval (the 2026-09-25 armed-and-idle
+    backfill)."""
+    artist = await _seed_artist(db, interval=3600, name="bf-now")
+    for url, overrides, runs in (
+        ("https://bf-running", {"_backfill_state": "running"}, 5),
+        ("https://bf-idle", {}, 0),
+    ):
+        db.add(Source(
+            artist_id=artist.id, platform="patreon", url=url, enabled=True,
+            consecutive_failures=0, config_overrides=overrides,
+            backfill_runs_remaining=runs,
+            last_checked_at=datetime.now(UTC) - timedelta(seconds=60),
+        ))
+    await db.commit()
+    urls = {s.url for s in await select_due_sources(db)}
+    assert "https://bf-running" in urls
+    assert "https://bf-idle" not in urls
+
+
+@pytest.mark.asyncio
+async def test_a_backfill_runs_even_when_its_artist_is_not_auto_checked(db):
+    """The operator started it by hand; auto-check governs the schedule only."""
+    artist = await _seed_artist(db, auto=False, name="bf-noauto")
+    db.add(Source(
+        artist_id=artist.id, platform="patreon", url="https://bf-noauto",
+        enabled=True, consecutive_failures=0,
+        config_overrides={"_backfill_state": "running"}, backfill_runs_remaining=5,
+        last_checked_at=datetime.now(UTC),
+    ))
+    await db.commit()
+    assert any(s.url == "https://bf-noauto" for s in await select_due_sources(db))
+
+
 # --- platform-rate-limit cooldown -----------------------------------------
 
 

tests/test_source_service.py

@@ -34,6 +34,24 @@ async def test_known_platforms_are_the_supported_four(db):
     assert "pixiv" not in KNOWN_PLATFORMS
 
 
+@pytest.mark.asyncio
+async def test_a_source_says_whether_it_is_on_the_native_ingester(db):
+    """The UI offers recover / recapture from this flag rather than a copied
+    platform list — the copy went stale when Discord moved (milestone 428)."""
+    artist = await _artist(db, name="Natty")
+    svc = SourceService(db)
+    discord = await svc.create(
+        artist_id=artist.id, platform="discord",
+        url="https://discord.com/channels/1/2",
+    )
+    hf = await svc.create(
+        artist_id=artist.id, platform="hentaifoundry",
+        url="https://www.hentai-foundry.com/user/Natty",
+    )
+    assert discord.to_dict()["native_ingester"] is True
+    assert hf.to_dict()["native_ingester"] is False
+
+
 @pytest.mark.asyncio
 async def test_create_flips_is_subscription_on_first_source(db):
     artist = await _artist(db)