feat(subscriptions): live posts-processed progress on backfill/recovery — #704 step 2
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 22s
CI / backend-lint-and-test (push) Failing after 26s
CI / integration (push) Failing after 3m0s

The running badge only showed the chunk counter; now it shows posts walked
— real walk progress. The ingester already reports posts_processed per
chunk (step 1); the backfill lifecycle accumulates it into
config_overrides._backfill_posts across chunks. SourceRecord exposes
backfill_posts; start_backfill/start_recovery clear it (fresh walk); stop
clears it too. SourceRow/SourceCard badge renders "Recovering · 45 posts"
(falls back to "(N)" chunks before any posts are counted).

Per-chunk accumulation (no mid-walk DB write) — simple and race-free; a
small over-count from each chunk re-walking its resumed page is fine for a
progress indicator.

Tests: lifecycle accumulates posts_processed across chunks; start clears a
prior _backfill_posts and the record exposes it.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-05 23:43:23 -04:00
parent e53f8959af
commit b2e59e7e17
6 changed files with 67 additions and 5 deletions
+7
View File
@@ -515,6 +515,13 @@ class DownloadService:
new_overrides = dict(src.config_overrides or {})
chunks = int(new_overrides.get("_backfill_chunks", 0)) + 1
new_overrides["_backfill_chunks"] = chunks
# plan #704 (#5): accumulate posts-processed across chunks so the badge
# shows live walk progress, not just the chunk count. Cleared on
# (re)start. (Slight over-count: each chunk re-walks the resumed page —
# fine for a progress indicator.)
new_overrides["_backfill_posts"] = int(
new_overrides.get("_backfill_posts", 0)
) + int(getattr(dl_result, "posts_processed", 0) or 0)
completed = (
dl_result.success
+10 -3
View File
@@ -70,6 +70,9 @@ class SourceRecord:
# plan #697: a running deep-walk that bypasses the Patreon seen-ledger
# (recovery) vs. a normal backfill. Lets the badge label it "Recovering".
backfill_bypass_seen: bool
# plan #704: cumulative posts processed across the walk's chunks — live
# progress for the badge.
backfill_posts: int
def to_dict(self) -> dict:
return {
@@ -91,6 +94,7 @@ class SourceRecord:
"backfill_state": self.backfill_state,
"backfill_chunks": self.backfill_chunks,
"backfill_bypass_seen": self.backfill_bypass_seen,
"backfill_posts": self.backfill_posts,
}
@@ -167,6 +171,7 @@ class SourceService:
backfill_state=co.get("_backfill_state"),
backfill_chunks=int(co.get("_backfill_chunks", 0)),
backfill_bypass_seen=bool(co.get("_backfill_bypass_seen")),
backfill_posts=int(co.get("_backfill_posts", 0)),
)
async def _row_to_record(self, source: Source) -> SourceRecord:
@@ -317,7 +322,8 @@ class SourceService:
raise LookupError(f"source id={source_id} not found")
co = dict(source.config_overrides or {})
co["_backfill_state"] = "running"
for k in ("_backfill_cursor", "_backfill_cursor_stalls", "_backfill_chunks"):
for k in ("_backfill_cursor", "_backfill_cursor_stalls", "_backfill_chunks",
"_backfill_posts"):
co.pop(k, None)
source.config_overrides = co
source.backfill_runs_remaining = BACKFILL_MAX_CHUNKS
@@ -345,7 +351,8 @@ class SourceService:
co = dict(source.config_overrides or {})
co["_backfill_state"] = "running"
co["_backfill_bypass_seen"] = True
for k in ("_backfill_cursor", "_backfill_cursor_stalls", "_backfill_chunks"):
for k in ("_backfill_cursor", "_backfill_cursor_stalls", "_backfill_chunks",
"_backfill_posts"):
co.pop(k, None)
source.config_overrides = co
source.backfill_runs_remaining = BACKFILL_MAX_CHUNKS
@@ -362,7 +369,7 @@ class SourceService:
raise LookupError(f"source id={source_id} not found")
co = dict(source.config_overrides or {})
for k in ("_backfill_state", "_backfill_cursor", "_backfill_cursor_stalls",
"_backfill_chunks", "_backfill_bypass_seen"):
"_backfill_chunks", "_backfill_bypass_seen", "_backfill_posts"):
co.pop(k, None)
source.config_overrides = co
source.backfill_runs_remaining = 0
@@ -28,7 +28,9 @@
v-else-if="source.backfill_state === 'running'"
size="x-small" color="info" variant="tonal" label
>{{ source.backfill_bypass_seen ? 'Recovering' : 'Backfilling'
}}{{ source.backfill_chunks ? ` (${source.backfill_chunks})` : '' }}</v-chip>
}}{{ source.backfill_posts
? ` · ${source.backfill_posts} posts`
: (source.backfill_chunks ? ` (${source.backfill_chunks})` : '') }}</v-chip>
<v-chip
v-else-if="source.backfill_state === 'complete'"
size="x-small" color="success" variant="tonal" label
@@ -35,7 +35,9 @@
v-else-if="source.backfill_state === 'running'"
size="x-small" color="info" variant="tonal" label
>{{ source.backfill_bypass_seen ? 'Recovering' : 'Backfilling'
}}{{ source.backfill_chunks ? ` (${source.backfill_chunks})` : '' }}</v-chip>
}}{{ source.backfill_posts
? ` · ${source.backfill_posts} posts`
: (source.backfill_chunks ? ` (${source.backfill_chunks})` : '') }}</v-chip>
<v-chip
v-else-if="source.backfill_state === 'complete'"
size="x-small" color="success" variant="tonal" label
+34
View File
@@ -648,6 +648,40 @@ async def test_backfill_stuck_guard_stalls_after_two_no_advance(
assert "_backfill_cursor" not in co2
@pytest.mark.asyncio
async def test_backfill_accumulates_posts_processed(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""plan #704 (#5): the lifecycle accumulates DownloadResult.posts_processed
into _backfill_posts across chunks for the live progress badge."""
from unittest.mock import MagicMock
from backend.app.services.download_service import DownloadService
_artist, source = seed_artist_and_source
source.config_overrides = {"_backfill_state": "running", "_backfill_posts": 5}
source.backfill_runs_remaining = 5
await db.commit()
svc = DownloadService(
async_session=db, sync_session=db_sync,
gdl=MagicMock(), importer=MagicMock(), cred_service=MagicMock(),
)
ctx = {
"source_id": source.id, "platform": "patreon",
"config_overrides": {"_backfill_state": "running", "_backfill_posts": 5},
"backfill_runs_remaining": 5,
}
await svc._apply_backfill_lifecycle(
ctx, _make_fake_dl_result(success=False, cursor="C1", posts_processed=10),
)
await db.commit()
co = (await db.execute(
select(Source.config_overrides).where(Source.id == source.id)
)).scalar_one()
assert co.get("_backfill_posts") == 15 # 5 (prior) + 10 (this chunk)
@pytest.mark.asyncio
async def test_backfill_timeout_chunk_reclassified_to_ok(
db, db_sync, tmp_path, seed_artist_and_source,
+10
View File
@@ -238,15 +238,25 @@ async def test_start_recovery_arms_bypass_flag(db):
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice",
)
# Simulate a prior walk's posts counter — start must clear it (plan #704).
await db.execute(
Source.__table__.update().where(Source.id == rec.id).values(
config_overrides={"_backfill_posts": 42},
)
)
await db.commit()
updated = await svc.start_recovery(rec.id)
assert updated.backfill_state == "running"
assert updated.backfill_bypass_seen is True
assert updated.backfill_posts == 0 # cleared for a fresh walk
assert updated.backfill_runs_remaining == BACKFILL_MAX_CHUNKS
co = (await db.execute(
select(Source.config_overrides).where(Source.id == rec.id)
)).scalar_one()
assert co.get("_backfill_bypass_seen") is True
assert "_backfill_posts" not in co
# Stop clears the bypass flag too (shared lifecycle).
stopped = await svc.stop_backfill(rec.id)