refactor(subscriptions): remove the dead backfill dry-run preview (#1281)

PreviewDialog.vue was orphaned — nothing mounted it — so the dry-run preview
was unreachable. Rather than wire it up, remove the whole chain: its unique
value (a capped 3-page count of what a backfill would grab) is low, and its
adjacent needs are already covered — auth validation by verify_source_credential,
and actually fetching recent posts by "Check now". Operator decision 2026-07-06.

Removed:
- frontend: PreviewDialog.vue + sources store previewSource()
- backend: POST /api/sources/<id>/preview route, download_backends.preview_source,
  IngestCore.preview() + its now-unused NativeIngestError import
- tests: the 3 ingester preview tests

Nothing else referenced the chain (verified). Shared campaign-resolution and
ledger helpers stay — they're used by run()/verify_source_credential.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM

backend/app/api/sources.py

@@ -230,52 +230,6 @@ async def set_backfill(source_id: int):
     return jsonify(record.to_dict())
 
 
-@sources_bp.route("/<int:source_id>/preview", methods=["POST"])
-async def preview_source_endpoint(source_id: int):
-    """Plan #708 B4: dry-run — count what a backfill WOULD download for a native
-    platform (Patreon today), without downloading. Walks the first few feed pages
-    and counts media not already in the seen/dead ledgers. Returns
-    {total_new, posts_scanned, pages_scanned, has_more, sample[]} or 409 + reason
-    (unresolvable campaign id / auth / drift). 400 for gallery-dl platforms (no
-    cheap dry-run — their verify is a slow --simulate)."""
-    from pathlib import Path
-
-    from ..services.credential_service import CredentialService
-    from ..services.download_backends import preview_source, uses_native_ingester
-    from ..tasks._sync_engine import sync_session_factory
-    from .credentials import _get_crypto
-
-    async with get_session() as session:
-        rec = await SourceService(session).get(source_id)
-        if rec is None:
-            return _bad("not_found", status=404)
-        if not uses_native_ingester(rec.platform):
-            return _bad(
-                "unsupported",
-                detail="Preview is only available for native-ingester platforms.",
-                status=400,
-            )
-        cred = CredentialService(session, _get_crypto())
-        cookies_path = await cred.get_cookies_path(rec.platform)
-        auth_token = await cred.get_token(rec.platform)
-
-    # The walk + ledger reads are sync (run off the request loop); the process
-    # sync engine is the same one the download task uses.
-    result = await preview_source(
-        platform=rec.platform,
-        url=rec.url,
-        source_id=source_id,
-        config_overrides=rec.config_overrides or {},
-        cookies_path=str(cookies_path) if cookies_path else None,
-        images_root=Path("/images"),
-        sync_session_factory=sync_session_factory(),
-        auth_token=auth_token,
-    )
-    if "error" in result:
-        return _bad("preview_failed", detail=result["error"], status=409)
-    return jsonify(result)
-
-
 @sources_bp.route("/<int:source_id>/check", methods=["POST"])
 async def check_source(source_id: int):
     """FC-3c: enqueue a download for this source.

backend/app/services/download_backends.py

@@ -24,7 +24,6 @@ import asyncio
 from pathlib import Path
 
 from .gallery_dl import DownloadResult, ErrorType
-from .native_ingest_common import NativeIngestError
 from .patreon_ingester import PatreonIngester
 from .patreon_resolver import extract_vanity, resolve_campaign_id_for_source
 from .pixiv_client import user_id_from_url
@@ -204,49 +203,6 @@ async def _run_native_ingester(
     return dl_result, resolved_campaign_id
 
 
-async def preview_source(
-    *,
-    platform: str,
-    url: str,
-    source_id: int,
-    config_overrides: dict | None,
-    cookies_path: str | None,
-    images_root: Path,
-    sync_session_factory,
-    auth_token: str | None = None,
-    page_limit: int = 3,
-) -> dict:
-    """Dry-run preview for a native platform (plan #708 B4): resolve the campaign
-    id, then walk a few pages counting media not already seen/dead — no download.
-
-    Returns the preview dict (total_new / posts_scanned / pages_scanned /
-    has_more / sample), or `{"error": msg}` on a resolve / auth / drift failure.
-    Native-only — the caller gates on `uses_native_ingester`.
-    """
-    import asyncio
-
-    campaign_id, _ = await _resolve_native_campaign_id(
-        platform, url, cookies_path, config_overrides or {}
-    )
-    if not campaign_id:
-        return {"error": _campaign_resolution_error(platform, url)}
-    ingester = _native_ingester_cls(platform)(
-        images_root=images_root,
-        cookies_path=cookies_path,
-        session_factory=sync_session_factory,
-        auth_token=auth_token,
-    )
-    loop = asyncio.get_running_loop()
-    try:
-        result = await loop.run_in_executor(
-            None,
-            lambda: ingester.preview(source_id, campaign_id, page_limit=page_limit),
-        )
-    except NativeIngestError as exc:
-        return {"error": f"Couldn't preview: {exc}"}
-    return result
-
-
 async def verify_source_credential(
     *,
     platform: str,

backend/app/services/ingest_core.py

@@ -577,73 +577,6 @@ class Ingester:
             error_type=None, error_message=None,
         )
 
-    # -- preview (dry-run) -------------------------------------------------
-
-    def preview(
-        self,
-        source_id: int,
-        campaign_id: str,
-        *,
-        page_limit: int = 3,
-        sample_size: int = 10,
-    ) -> dict:
-        """Dry-run (plan #708 B4): walk up to `page_limit` pages and count media
-        NOT already in the seen/dead ledgers, WITHOUT downloading anything.
-
-        Read-only — only the seen/dead SELECTs touch the DB (short sessions). Lets
-        an operator gauge "is this source worth a backfill?" cheaply. Returns:
-            {total_new, posts_scanned, pages_scanned, has_more,
-             sample: [{title, date, new}, ...]}  # sample = posts with new media
-        A client-level failure (auth/drift) propagates to the caller.
-        """
-        total_new = 0
-        posts_scanned = 0
-        pages_scanned = 0
-        has_more = False
-        sample: list[dict] = []
-        unset = object()
-        last_page: object = unset
-        # #874: same gated-post gate as run() — the preview must not count
-        # blurred locked-preview media as "new", or it would overstate a gated
-        # source's backlog (preview/apply parity, rule 93).
-        post_is_gated = getattr(self.client, "post_is_gated", None)
-        for post, included, page_cursor in self.client.iter_posts(
-            campaign_id, cursor=None
-        ):
-            if page_cursor != last_page:
-                last_page = page_cursor
-                pages_scanned += 1
-                if pages_scanned > page_limit:
-                    has_more = True
-                    pages_scanned = page_limit
-                    break
-            posts_scanned += 1
-            if post_is_gated and post_is_gated(post):
-                continue
-            media = self.client.extract_media(post, included)
-            if not media:
-                continue
-            keys = [self._ledger_key(m) for m in media]
-            skip = self._seen_keys(source_id, keys) | self._dead_keys(source_id, keys)
-            new_count = sum(1 for m in media if self._ledger_key(m) not in skip)
-            total_new += new_count
-            if new_count > 0 and len(sample) < sample_size:
-                meta = self.client.post_meta(post)
-                sample.append(
-                    {
-                        "title": meta.get("title") or "(untitled)",
-                        "date": meta.get("date"),
-                        "new": new_count,
-                    }
-                )
-        return {
-            "total_new": total_new,
-            "posts_scanned": posts_scanned,
-            "pages_scanned": pages_scanned,
-            "has_more": has_more,
-            "sample": sample,
-        }
-
     # -- failure mapping (adapter overrides) -------------------------------
 
     def _failure_result(self, exc: Exception, _result) -> DownloadResult:

frontend/src/components/subscriptions/PreviewDialog.vue

@@ -1,114 +0,0 @@
-<template>
-  <!-- Plan #708 B4: dry-run preview — what a backfill WOULD download, without
-       downloading. Self-fetches on open; loading / error / empty / result. -->
-  <v-dialog
-    :model-value="modelValue" max-width="520"
-    @update:model-value="$emit('update:modelValue', $event)"
-  >
-    <v-card v-if="source">
-      <CardHeading
-        icon="mdi-eye-outline"
-        :title="`Preview · ${source.artist_name}`"
-      />
-      <v-card-subtitle class="fc-preview__url">{{ source.url }}</v-card-subtitle>
-
-      <v-card-text>
-        <div v-if="loading" class="text-center py-8">
-          <v-progress-circular indeterminate color="accent" />
-          <div class="text-caption mt-3 text-medium-emphasis">Walking the feed…</div>
-        </div>
-
-        <v-alert
-          v-else-if="error" type="error" variant="tonal" density="comfortable"
-        >{{ error }}</v-alert>
-
-        <div v-else-if="result">
-          <div class="text-h5">
-            {{ result.total_new }} new item{{ result.total_new === 1 ? '' : 's' }}
-          </div>
-          <div class="text-body-2 text-medium-emphasis mb-3">
-            in the {{ result.posts_scanned }} most recent
-            post{{ result.posts_scanned === 1 ? '' : 's' }}<span
-              v-if="result.has_more"> · more pages not scanned</span>
-          </div>
-
-          <div
-            v-if="result.total_new === 0"
-            class="text-body-2 text-medium-emphasis"
-          >You’re caught up — nothing new to download.</div>
-
-          <v-list v-else density="compact" class="fc-preview__list" bg-color="transparent">
-            <v-list-item v-for="(row, i) in result.sample" :key="i" class="px-0">
-              <template #prepend>
-                <v-chip
-                  size="x-small" color="info" variant="tonal" label class="mr-3"
-                >+{{ row.new }}</v-chip>
-              </template>
-              <v-list-item-title class="text-body-2">{{ row.title }}</v-list-item-title>
-              <v-list-item-subtitle v-if="row.date" class="text-caption">
-                {{ formatRelative(row.date) }}
-              </v-list-item-subtitle>
-            </v-list-item>
-          </v-list>
-        </div>
-      </v-card-text>
-
-      <v-card-actions>
-        <v-spacer />
-        <v-btn variant="text" @click="$emit('update:modelValue', false)">Close</v-btn>
-        <v-btn
-          v-if="result && result.total_new > 0"
-          color="accent" variant="flat"
-          @click="$emit('backfill', source)"
-        >Start backfill</v-btn>
-      </v-card-actions>
-    </v-card>
-  </v-dialog>
-</template>
-
-<script setup>
-import { ref, watch } from 'vue'
-import { useSourcesStore } from '../../stores/sources.js'
-import { formatRelative } from '../../utils/date.js'
-import CardHeading from '../common/CardHeading.vue'
-
-const props = defineProps({
-  modelValue: { type: Boolean, default: false },
-  source: { type: Object, default: null },
-})
-defineEmits(['update:modelValue', 'backfill'])
-
-const store = useSourcesStore()
-const loading = ref(false)
-const error = ref('')
-const result = ref(null)
-
-watch(
-  () => props.modelValue,
-  async (open) => {
-    if (!open || !props.source) return
-    loading.value = true
-    error.value = ''
-    result.value = null
-    try {
-      result.value = await store.previewSource(props.source.id)
-    } catch (e) {
-      error.value = e?.body?.detail || e?.message || 'Preview failed'
-    } finally {
-      loading.value = false
-    }
-  },
-)
-</script>
-
-<style scoped>
-.fc-preview__url {
-  overflow: hidden;
-  text-overflow: ellipsis;
-  white-space: nowrap;
-}
-.fc-preview__list {
-  max-height: 320px;
-  overflow-y: auto;
-}
-</style>

frontend/src/stores/sources.js

@@ -149,12 +149,6 @@ export const useSourcesStore = defineStore('sources', () => {
     return body
   }
 
-  // Plan #708 B4: dry-run preview — count what a backfill WOULD download
-  // (native platforms), without downloading. Read-only, so no cache invalidate.
-  async function previewSource(id) {
-    return await api.post(`/api/sources/${id}/preview`)
-  }
-
   function sourcesByArtistGrouped() {
     // returns [{artist: {id,name,slug}, sources: [...]}, ...]
     const arr = byArtist.value.get(null) ?? []
@@ -185,7 +179,6 @@ export const useSourcesStore = defineStore('sources', () => {
     stopBackfill,
     recoverSource,
     recaptureSource,
-    previewSource,
     findOrCreateArtist, autocompleteArtist, reassign,
     loadScheduleStatus,
     sourcesByArtistGrouped,

tests/test_patreon_ingester.py

@@ -448,42 +448,6 @@ async def test_backfill_budget_cut_returns_partial_with_progress(
     assert result.cursor == "CUR2"
 
 
-@pytest.mark.asyncio
-async def test_preview_counts_new_media_without_downloading(
-    source_id, sync_engine, tmp_path,
-):
-    """plan #708 B4: preview walks + counts media not already seen/dead, downloads
-    nothing, and samples only posts that have new media."""
-    m1, m2, m3 = _media("p1", 1), _media("p2", 1), _media("p2", 2)
-    # Seed m1 as already-seen → only p2's two media are "new".
-    factory = sessionmaker(sync_engine, expire_on_commit=False)
-    with factory() as s:
-        s.add(PatreonSeenMedia(source_id=source_id, filehash=_ledger_key(m1), post_id="p1"))
-        s.commit()
-    client = _FakeClient([(None, [("p1", [m1]), ("p2", [m2, m3])])])
-    downloader = _FakeDownloader(tmp_path)
-    ing = _ingester(sync_engine, tmp_path, client, downloader)
-
-    result = ing.preview(source_id, "c1")
-    assert result["total_new"] == 2          # p2's m2 + m3 (m1 already seen)
-    assert result["posts_scanned"] == 2
-    assert result["has_more"] is False
-    assert downloader.download_calls == 0     # dry-run — nothing downloaded
-    # The sample lists only posts WITH new media (p2), not the all-seen p1.
-    assert [row["new"] for row in result["sample"]] == [2]
-
-
-@pytest.mark.asyncio
-async def test_preview_page_limit_caps_walk(source_id, sync_engine, tmp_path):
-    """plan #708 B4: preview stops after page_limit pages and flags has_more."""
-    pages = [(f"CUR{i}", [(f"p{i}", [_media(f"p{i}", 1)])]) for i in range(6)]
-    ing = _ingester(sync_engine, tmp_path, _FakeClient(pages), _FakeDownloader(tmp_path))
-    result = ing.preview(source_id, "c1", page_limit=2)
-    assert result["pages_scanned"] == 2
-    assert result["posts_scanned"] == 2   # one post per page, 2 pages
-    assert result["has_more"] is True
-
-
 @pytest.mark.asyncio
 async def test_write_live_progress_updates_running_event(
     source_id, sync_engine, tmp_path, db,
@@ -714,21 +678,6 @@ async def test_gated_post_skipped_entirely_no_media_no_record(
     assert _count_ledger(sync_engine, source_id) == 2
 
 
-@pytest.mark.asyncio
-async def test_preview_excludes_gated_posts(source_id, sync_engine, tmp_path):
-    """#874 preview/apply parity (rule 93): the dry-run must not count a gated
-    post's blurred preview media as new, or it overstates a gated source's
-    backlog."""
-    gm = _media("gated", 1)
-    am = _media("open", 1)
-    client = _FakeClient([(None, [("gated", [gm]), ("open", [am])])], gated={"gated"})
-    ing = _ingester(sync_engine, tmp_path, client, _FakeDownloader(tmp_path))
-
-    preview = ing.preview(source_id, "c1")
-    assert preview["total_new"] == 1                       # only the open post
-    assert [s for s in preview["sample"] if s["title"] == "gated"] == []
-
-
 @pytest.mark.asyncio
 async def test_recapture_does_not_refetch_seen_media_missing_from_disk(
     source_id, sync_engine, tmp_path,