Merge pull request 'Smarter backfill: time-boxed chunks, run-until-done (plan #693)' (#71) from dev into main
Build images / sign-extension (push) Successful in 3s
CI / lint (push) Successful in 3s
Build images / build-ml (push) Successful in 8s
CI / backend-lint-and-test (push) Successful in 13s
Build images / build-web (push) Successful in 10s
CI / frontend-build (push) Successful in 18s
CI / integration (push) Successful in 2m58s

This commit was merged in pull request #71.
This commit is contained in:
2026-06-05 16:33:06 -04:00
14 changed files with 420 additions and 349 deletions
+13 -14
View File
@@ -122,26 +122,25 @@ async def delete_source(source_id: int):
@sources_bp.route("/<int:source_id>/backfill", methods=["POST"])
async def set_backfill(source_id: int):
"""Plan #544: arm a source for backfill mode for the next N download
runs. Body: `{"runs": int}` (1..10, default 3). Returns the updated
source dict. While backfill_runs_remaining > 0, downloads use
gallery-dl's full-walk config (skip: True + 30-min timeout) instead
of the catch-up default (skip: "exit:20" + 14.5-min timeout)."""
"""Plan #693: start or stop a run-until-done backfill. Body:
`{"action": "start" | "stop"}` (default "start"). 'start' walks the full
post history in time-boxed chunks until it reaches the bottom (then the
source shows 'complete'); 'stop' cancels back to tick mode. Returns the
updated source dict (incl. backfill_state / backfill_chunks)."""
payload = await request.get_json(silent=True) or {}
runs = payload.get("runs", 3)
try:
runs = int(runs)
except (TypeError, ValueError):
return _bad("invalid_runs", detail="runs must be an integer")
action = payload.get("action", "start")
if action not in ("start", "stop"):
return _bad("invalid_action", detail="action must be 'start' or 'stop'")
async with get_session() as session:
try:
record = await SourceService(session).set_backfill_runs(
source_id, runs,
svc = SourceService(session)
record = (
await svc.start_backfill(source_id)
if action == "start"
else await svc.stop_backfill(source_id)
)
except LookupError:
return _bad("not_found", status=404)
except ValueError as exc:
return _bad("invalid_runs", detail=str(exc))
return jsonify(record.to_dict())
+79 -51
View File
@@ -26,8 +26,8 @@ from sqlalchemy.orm import joinedload
from ..models import Artist, DownloadEvent, Source
from .credential_service import CredentialService
from .gallery_dl import (
BACKFILL_CHUNK_SECONDS,
BACKFILL_SKIP_VALUE,
BACKFILL_TIMEOUT_SECONDS,
TICK_SKIP_VALUE,
ErrorType,
GalleryDLService,
@@ -108,23 +108,20 @@ class DownloadService:
self.sync_session.close()
source_config = SourceConfig.from_dict(ctx["config_overrides"] or {})
# alembic 0031 / plan #544: derive skip_value + timeout from the
# source's backfill_runs_remaining counter. When > 0, walk the full
# post history (skip: True + 1170s); when 0, exit gallery-dl after
# 20 contiguous archived items (skip: "exit:20" + the default
# 870s). Operator sets backfill via POST /api/sources/{id}/backfill.
# Backfill mode (plan #693): the source's `_backfill_state == "running"`
# selects a time-boxed deep-walk chunk — skip: True (walk full history)
# + the BACKFILL_CHUNK_SECONDS budget, resuming from the cursor
# checkpoint (plan #689). State is the single source of truth; it stays
# "running" across ticks until the walk reaches the bottom (phase 3
# flips it to "complete"). Otherwise tick mode: exit gallery-dl after
# 20 contiguous archived items (skip: "exit:20" + the default 870s).
# Operator drives this via POST /api/sources/{id}/backfill {action}.
overrides = ctx["config_overrides"] or {}
backfill_remaining = ctx.get("backfill_runs_remaining", 0) or 0
# Cursor-paged backfill (plan #689): a pending checkpoint keeps the
# deep-walk in backfill mode across ticks until it reaches the
# bottom, even after the operator's run budget hits 0 — so one large
# creator (Anduo) finishes without re-triggering. The phase-3
# stuck-guard bounds it. patreon-only: it's the sole platform with a
# resumable gallery-dl cursor.
pending_cursor = overrides.get("_backfill_cursor")
if backfill_remaining > 0 or pending_cursor:
in_backfill = overrides.get("_backfill_state") == "running"
if in_backfill:
skip_value: bool | str = BACKFILL_SKIP_VALUE
source_config.timeout = BACKFILL_TIMEOUT_SECONDS
source_config.timeout = BACKFILL_CHUNK_SECONDS
pending_cursor = overrides.get("_backfill_cursor")
if ctx["platform"] == "patreon" and pending_cursor:
source_config.resume_cursor = pending_cursor
else:
@@ -171,6 +168,24 @@ class DownloadService:
skip_value=skip_value,
)
# A backfill chunk that hit its time-box but made forward progress is
# NORMAL, not a failure — reclassify TIMEOUT → PARTIAL so it reads as
# "ok/progress" (PARTIAL maps to status "ok"), not a red error, and the
# next chunk just resumes from the new cursor (plan #693). A chunk that
# timed out with NO progress stays TIMEOUT and feeds phase 3's
# stall-guard. Leave RATE_LIMITED alone so the platform-cooldown fires.
if in_backfill and dl_result.error_type == ErrorType.TIMEOUT:
new_cursor = parse_last_cursor(dl_result.stdout, dl_result.stderr)
advanced = bool(
(new_cursor and new_cursor != overrides.get("_backfill_cursor"))
or dl_result.files_downloaded > 0
)
if advanced:
dl_result.error_type = ErrorType.PARTIAL
dl_result.error_message = (
f"Backfill chunk: {dl_result.files_downloaded} file(s) — continuing"
)
return await self._phase3_persist(
ctx["event_id"], ctx, dl_result, resolved_campaign_id,
)
@@ -411,35 +426,38 @@ class DownloadService:
return event_id
async def _apply_backfill_lifecycle(self, ctx: dict, dl_result) -> None:
"""Cursor-paged backfill state machine (plan #689).
"""Backfill state machine (plan #693, building on the cursor of #689).
A backfill is "in progress" while backfill_runs_remaining > 0 OR a
checkpoint cursor is stored. Completion is a CLEAN rc=0 finish —
gallery-dl with skip:True exits 0 only after exhausting the
newest→oldest walk; a run cut short by the subprocess budget returns
success=False / return_code=-1 (the TimeoutExpired path), so rc=0 is
an unambiguous "reached the bottom" signal regardless of how many
files this run fetched. (This replaces plan #544's files==0 predicate,
whose audit-2026-06-02 VALIDATION_FAILED guard still holds: those exit
non-zero or carry an error_type, so they are not "completed".)
A backfill runs in time-boxed chunks while
`config_overrides["_backfill_state"] == "running"`. Each chunk:
- COMPLETES the walk → clean rc=0 (gallery-dl with skip:True exits 0
only after exhausting the newest→oldest walk; a chunk cut short by
its time-box returns success=False / rc<0 via TimeoutExpired). On
completion: state="complete", clear the cursor, return to tick mode.
- made PROGRESS (cursor advanced and/or files written) → stay
"running", checkpoint the new cursor, bump the chunk counter, and
spend one of the safety-cap chunks (backfill_runs_remaining). If the
cap is exhausted without finishing → state="stalled".
- made NO progress → increment the stall counter; two strikes →
state="stalled", clear the cursor (a wedged walk can't loop).
For patreon, each non-completing run checkpoints gallery-dl's
last-emitted pagination cursor — even a timed-out run, since its
partial stdout/stderr still carries it — so the next run RESUMES
instead of re-walking from the top. A stuck-guard clears the cursor
after two consecutive runs that fail to advance it, so a wedged walk
can't re-strand forever (cf. download soft-limit ladder).
State is the single source of truth; the cursor lives only inside a
running backfill. config_overrides is reassigned (not mutated in place)
for SQLAlchemy JSON change detection.
"""
overrides = ctx["config_overrides"] or {}
if overrides.get("_backfill_state") != "running":
return # not backfilling — tick mode, nothing to do
old_cursor = overrides.get("_backfill_cursor")
backfill_remaining = ctx.get("backfill_runs_remaining", 0) or 0
if backfill_remaining <= 0 and not old_cursor:
return # tick mode — counter untouched
cap_remaining = ctx.get("backfill_runs_remaining", 0) or 0
src = (await self.async_session.execute(
select(Source).where(Source.id == ctx["source_id"])
)).scalar_one()
new_overrides = dict(src.config_overrides or {})
chunks = int(new_overrides.get("_backfill_chunks", 0)) + 1
new_overrides["_backfill_chunks"] = chunks
completed = (
dl_result.success
@@ -447,33 +465,43 @@ class DownloadService:
and dl_result.return_code == 0
)
if completed:
new_overrides["_backfill_state"] = "complete"
new_overrides.pop("_backfill_cursor", None)
new_overrides.pop("_backfill_cursor_stalls", None)
src.config_overrides = new_overrides
src.backfill_runs_remaining = 0
return
# Non-completing run. Patreon checkpoints + resumes via cursor;
# other platforms have no resumable cursor, so just decrement.
if ctx["platform"] == "patreon":
new_cursor = parse_last_cursor(dl_result.stdout, dl_result.stderr)
if new_cursor and new_cursor != old_cursor:
# Did not finish. Patreon checkpoints + resumes via cursor; other
# platforms have no resumable cursor (every chunk re-walks from the
# top), so they advance only by the download archive growing.
new_cursor = (
parse_last_cursor(dl_result.stdout, dl_result.stderr)
if ctx["platform"] == "patreon" else None
)
advanced = bool(
(new_cursor and new_cursor != old_cursor)
or dl_result.files_downloaded > 0
)
if advanced:
if new_cursor:
new_overrides["_backfill_cursor"] = new_cursor
new_overrides.pop("_backfill_cursor_stalls", None)
cap_remaining = max(0, cap_remaining - 1)
src.backfill_runs_remaining = cap_remaining
if cap_remaining == 0:
# Safety cap hit before reaching the bottom — pause, don't loop.
new_overrides["_backfill_state"] = "stalled"
else:
stalls = int(new_overrides.get("_backfill_cursor_stalls", 0)) + 1
if stalls >= 2:
new_overrides["_backfill_state"] = "stalled"
new_overrides.pop("_backfill_cursor", None)
new_overrides.pop("_backfill_cursor_stalls", None)
else:
stalls = int(new_overrides.get("_backfill_cursor_stalls", 0)) + 1
if stalls >= 2:
# Wedged: give up, drop back to tick mode. The surfaced
# error_type on the event tells the operator why.
new_overrides.pop("_backfill_cursor", None)
new_overrides.pop("_backfill_cursor_stalls", None)
src.config_overrides = new_overrides
src.backfill_runs_remaining = 0
return
new_overrides["_backfill_cursor_stalls"] = stalls
src.config_overrides = new_overrides
src.backfill_runs_remaining = max(0, backfill_remaining - 1)
src.config_overrides = new_overrides
async def _update_source_health(
self, *, source_id: int, status: str, error_message: str | None,
+9 -8
View File
@@ -16,7 +16,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
from ..models import Artist, Source
from ..utils.slug import slugify
from .source_service import NEW_SOURCE_BACKFILL_RUNS
from .source_service import BACKFILL_MAX_CHUNKS
class UnknownPlatformError(Exception):
@@ -205,16 +205,17 @@ class ExtensionService:
return existing, False
sp = await self.session.begin_nested()
try:
# New subscription sources arm a few backfill runs so the
# first ticks walk the full history (otherwise gallery-dl's
# exit:20 short-circuits before the archive is built).
# Mirrors SourceService.create — without it, Firefox quick-
# add on a creator with >20 unsynced posts would surface
# as "check failed" with no diagnosis. Audit 2026-06-02.
# New subscription sources arm run-until-done backfill (plan #693)
# so the first ticks walk the full history (otherwise gallery-dl's
# exit:20 short-circuits before the archive is built). Mirrors
# SourceService.create — without it, Firefox quick-add on a creator
# with >20 unsynced posts would surface as "check failed" with no
# diagnosis. Audit 2026-06-02.
src = Source(
artist_id=artist_id, platform=platform,
url=url, enabled=True,
backfill_runs_remaining=NEW_SOURCE_BACKFILL_RUNS,
config_overrides={"_backfill_state": "running"},
backfill_runs_remaining=BACKFILL_MAX_CHUNKS,
)
self.session.add(src)
await self.session.flush()
+28 -20
View File
@@ -56,25 +56,24 @@ class ErrorType(StrEnum):
# 20 contiguous HEADs is still negligible.
TICK_SKIP_VALUE = "exit:20"
# Backfill mode (operator-triggered deep scan): walk the full history.
# Source.backfill_runs_remaining > 0 selects this mode; the longer
# timeout below absorbs creators with thousands of posts.
# Backfill mode (operator-triggered deep scan): walk the full history,
# one TIME-BOXED CHUNK per run (plan #693). config_overrides["_backfill_state"]
# == "running" selects this mode; the cursor checkpoint (plan #689) lets each
# chunk resume where the last stopped, so the walk advances across chunks
# until gallery-dl exits cleanly (= reached the bottom).
#
# Sits below download_source's Celery soft_time_limit
# (DOWNLOAD_SOFT_TIME_LIMIT=1350, tasks/download.py) with ~180s of
# headroom for phase-3 persist. subprocess.run MUST raise TimeoutExpired
# before Celery raises SoftTimeLimitExceeded — that exception path
# captures partial stdout/stderr and finalizes the event; the soft-limit
# path (until the 2026-06-03 fix) did not. Audit history: 1800 guaranteed
# SIGKILL against the old hard limit (Knuxy #38275); 1170 was then sized
# "30s shy of the hard limit (1200)" but still EXCEEDED the soft limit
# (900), so SoftTimeLimitExceeded preempted TimeoutExpired and every
# backfill stranded empty (Anduo #39912). Raising the Celery soft/hard
# limits to 1350/1500 (tasks/download.py) is what made 1170 safe.
# backfill_runs_remaining=3 still gives ~58 minutes of cumulative walk
# across three runs for prolific creators.
# The chunk budget is deliberately FAR below download_source's Celery
# soft_time_limit (DOWNLOAD_SOFT_TIME_LIMIT=1350, tasks/download.py), not
# "just under" it. Hitting this budget is the NORMAL chunk boundary, not a
# failure: subprocess.run raises TimeoutExpired (which captures partial
# stdout/stderr + the last emitted cursor), and download_service reclassifies
# a chunk that made progress as PARTIAL (status "ok"), not an error. The huge
# headroom means a stuck file or a slow chunk can never let Celery's
# SoftTimeLimitExceeded preempt TimeoutExpired (the failure mode behind Knuxy
# #38275 / Anduo #39912/#40411). Earlier we ran one ~1170s run-to-the-wall
# per arming; that died as a timeout error every time on large catalogs.
BACKFILL_SKIP_VALUE = True
BACKFILL_TIMEOUT_SECONDS = 1170
BACKFILL_CHUNK_SECONDS = 600
# Sits well below download_source's Celery soft_time_limit
@@ -281,7 +280,12 @@ class GalleryDLService:
"skip": True,
"sleep": self._rate_limit,
"sleep-request": max(0.5, self._rate_limit / 4),
"retries": 3,
# 2 (not 3) retries — a stuck CDN host shouldn't burn a whole
# backfill chunk on one file. Anduo #40838 spent ~600s on a
# single image (4 extractor HEAD retries × 30s + 4 downloader
# GET retries × 120s); halving retries + the downloader
# timeout below caps a wedged file at ~1-2 min instead.
"retries": 2,
"timeout": 30.0,
"verify": True,
"postprocessors": [
@@ -296,8 +300,12 @@ class GalleryDLService:
"downloader": {
"part": True,
"part-directory": str(self._config_dir / "temp"),
"retries": 3,
"timeout": 120.0,
# See the extractor retries note above (Anduo #40838): 2
# retries + a 60s read-timeout (was 120) so a stalled
# connection fails fast. 60s is a per-read timeout, not a
# transfer cap — large GIFs that keep streaming are unaffected.
"retries": 2,
"timeout": 60.0,
# Forward Patreon as Referer/Origin to yt-dlp when it
# fetches video manifests. Operator-flagged 2026-06-01
# (DaferQ patreon): video posts hosted on Mux carry a JWT
+56 -25
View File
@@ -64,6 +64,9 @@ class SourceRecord:
consecutive_failures: int
next_check_at: str | None
backfill_runs_remaining: int
# plan #693: derived from config_overrides for the UI badge.
backfill_state: str | None # "running" | "complete" | "stalled" | None (idle)
backfill_chunks: int
def to_dict(self) -> dict:
return {
@@ -82,6 +85,8 @@ class SourceRecord:
"consecutive_failures": self.consecutive_failures,
"next_check_at": self.next_check_at,
"backfill_runs_remaining": self.backfill_runs_remaining,
"backfill_state": self.backfill_state,
"backfill_chunks": self.backfill_chunks,
}
@@ -89,10 +94,13 @@ class SourceRecord:
_EDITABLE = {"enabled", "url", "config_overrides", "check_interval_override", "platform"}
# Plan #544 follow-up: newly created enabled sources pre-arm backfill so
# their first N polls walk gallery-dl's full post history with the longer
# timeout (matches the manual "Deep scan" button's default).
NEW_SOURCE_BACKFILL_RUNS = 3
# Plan #693: backfill safety cap. "Start backfill" (and a newly created
# enabled source) arms a run-until-done walk; this caps how many time-boxed
# chunks it may spend before pausing as "stalled", so a pathological walk that
# never reaches the bottom can't run forever. Generous on purpose — at
# BACKFILL_CHUNK_SECONDS (600s) per chunk this is ~33h of cumulative walk, far
# beyond any real catalog; the cursor stall-guard is the real terminator.
BACKFILL_MAX_CHUNKS = 200
class SourceService:
@@ -135,6 +143,7 @@ class SourceService:
self, source: Source, artist: Artist, settings: ImportSettings,
) -> SourceRecord:
nxt = compute_next_check_at(source, artist, settings)
co = source.config_overrides or {}
return SourceRecord(
id=source.id,
artist_id=source.artist_id,
@@ -151,6 +160,8 @@ class SourceService:
consecutive_failures=source.consecutive_failures or 0,
next_check_at=nxt.isoformat() if nxt else None,
backfill_runs_remaining=source.backfill_runs_remaining or 0,
backfill_state=co.get("_backfill_state"),
backfill_chunks=int(co.get("_backfill_chunks", 0)),
)
async def _row_to_record(self, source: Source) -> SourceRecord:
@@ -212,16 +223,17 @@ class SourceService:
select(func.count(Source.id)).where(Source.artist_id == artist_id)
)).scalar_one()
# Plan #544 follow-up: a freshly added subscription has no archive
# yet, so the first few polls would walk the full post history in
# tick mode and trip exit:20 after ~20 contiguous archive hits —
# except there are none yet, so tick mode would walk forever and
# blow the wall-clock cap. Pre-arm backfill so the initial syncs
# use the longer timeout + skip:True walk. Tick mode resumes once
# the budget is spent or the queue drains.
# Disabled sources (incl. sidecar synthetics, url='sidecar:...')
# are never polled, so leave their counter at 0.
backfill_runs = NEW_SOURCE_BACKFILL_RUNS if enabled else 0
# Plan #693: a freshly added subscription has no archive yet, so it
# should walk its full post history once. Arm run-until-done backfill
# (state="running" + the chunk cap); the time-boxed chunks march to the
# bottom across ticks, then flip to "complete" and tick mode takes over.
# Disabled sources (incl. sidecar synthetics, url='sidecar:...') are
# never polled, so leave them idle.
if enabled:
config_overrides = {**(config_overrides or {}), "_backfill_state": "running"}
backfill_runs = BACKFILL_MAX_CHUNKS
else:
backfill_runs = 0
source = Source(
artist_id=artist_id, platform=platform, url=url,
enabled=enabled, config_overrides=config_overrides,
@@ -286,22 +298,41 @@ class SourceService:
await self.session.commit()
return await self._row_to_record(source)
async def set_backfill_runs(
self, source_id: int, runs: int,
) -> SourceRecord:
"""Plan #544: arm a source for backfill mode. The next `runs`
download runs will use gallery-dl's full-walk config (skip: True
+ 30-min timeout) instead of the catch-up default. Runs must be
1..10 — bigger is rejected to keep the operator from accidentally
setting a runaway budget."""
if not isinstance(runs, int) or runs < 1 or runs > 10:
raise ValueError("runs must be an integer in [1, 10]")
async def start_backfill(self, source_id: int) -> SourceRecord:
"""Plan #693: arm a run-until-done backfill. Sets state="running" and
the chunk cap; download runs then walk the full post history in
time-boxed chunks (skip:True + BACKFILL_CHUNK_SECONDS), resuming from
the cursor each chunk, until gallery-dl reaches the bottom (→ state
"complete") or the cap/stall-guard pauses it (→ "stalled"). Clears any
prior cursor/chunk/stall state so a re-start walks fresh from the top."""
source = (await self.session.execute(
select(Source).where(Source.id == source_id)
)).scalar_one_or_none()
if source is None:
raise LookupError(f"source id={source_id} not found")
source.backfill_runs_remaining = runs
co = dict(source.config_overrides or {})
co["_backfill_state"] = "running"
for k in ("_backfill_cursor", "_backfill_cursor_stalls", "_backfill_chunks"):
co.pop(k, None)
source.config_overrides = co
source.backfill_runs_remaining = BACKFILL_MAX_CHUNKS
await self.session.commit()
return await self._row_to_record(source)
async def stop_backfill(self, source_id: int) -> SourceRecord:
"""Plan #693: cancel an in-progress backfill — back to idle/tick mode.
Clears the running state + cursor/chunk/stall bookkeeping."""
source = (await self.session.execute(
select(Source).where(Source.id == source_id)
)).scalar_one_or_none()
if source is None:
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"):
co.pop(k, None)
source.config_overrides = co
source.backfill_runs_remaining = 0
await self.session.commit()
return await self._row_to_record(source)
+1 -1
View File
@@ -31,7 +31,7 @@ _KEY_PATH = IMAGES_ROOT / "secrets" / "credential_key.b64"
# SoftTimeLimitExceeded in-process, whereas the HARD limit SIGKILLs the
# worker (no chance to finalize). Both gallery-dl subprocess budgets
# (gallery_dl.py: _DEFAULT_GDL_TIMEOUT_SECONDS=870 tick,
# BACKFILL_TIMEOUT_SECONDS=1170 backfill) MUST sit below the soft limit
# BACKFILL_CHUNK_SECONDS=600 per backfill chunk, plan #693) MUST sit below the soft limit
# so subprocess.run raises its own TimeoutExpired first — that path
# captures partial stdout/stderr and finalizes the DownloadEvent. soft is
# max-subprocess (1170) + ~180s phase-3 persist headroom; hard is soft +
@@ -25,9 +25,17 @@
size="x-small" color="error" variant="tonal" label
>{{ source.consecutive_failures }} err</v-chip>
<v-chip
v-else-if="(source.backfill_runs_remaining || 0) > 0"
v-else-if="source.backfill_state === 'running'"
size="x-small" color="info" variant="tonal" label
>backfill ({{ source.backfill_runs_remaining }}×)</v-chip>
>Backfilling{{ source.backfill_chunks ? ` (${source.backfill_chunks})` : '' }}</v-chip>
<v-chip
v-else-if="source.backfill_state === 'complete'"
size="x-small" color="success" variant="tonal" label
>Backfilled</v-chip>
<v-chip
v-else-if="source.backfill_state === 'stalled'"
size="x-small" color="warning" variant="tonal" label
>Stalled</v-chip>
</div>
<div class="fc-source-card__actions">
@@ -40,11 +48,13 @@
</v-btn>
<v-btn
size="x-small" variant="text"
:disabled="(source.backfill_runs_remaining || 0) > 0"
:color="source.backfill_state === 'running' ? 'warning' : undefined"
@click.stop="$emit('backfill', source)"
>
<v-icon>mdi-magnify-scan</v-icon>
<v-tooltip activator="parent" location="top">Deep scan</v-tooltip>
<v-icon>{{ source.backfill_state === 'running' ? 'mdi-stop' : 'mdi-magnify-scan' }}</v-icon>
<v-tooltip activator="parent" location="top">
{{ source.backfill_state === 'running' ? 'Stop backfill' : 'Backfill full history' }}
</v-tooltip>
</v-btn>
<v-btn size="x-small" variant="text" @click.stop="$emit('edit', source)">
<v-icon>mdi-pencil</v-icon>
@@ -32,11 +32,17 @@
size="x-small" color="error" variant="tonal" label
>{{ source.consecutive_failures }}</v-chip>
<v-chip
v-else-if="(source.backfill_runs_remaining || 0) > 0"
v-else-if="source.backfill_state === 'running'"
size="x-small" color="info" variant="tonal" label
>
backfill ({{ source.backfill_runs_remaining }}×)
</v-chip>
>Backfilling{{ source.backfill_chunks ? ` (${source.backfill_chunks})` : '' }}</v-chip>
<v-chip
v-else-if="source.backfill_state === 'complete'"
size="x-small" color="success" variant="tonal" label
>Backfilled</v-chip>
<v-chip
v-else-if="source.backfill_state === 'stalled'"
size="x-small" color="warning" variant="tonal" label
>Stalled</v-chip>
<span v-else class="fc-source-row__zero">0</span>
</td>
<td class="fc-source-row__actions">
@@ -49,13 +55,15 @@
<v-tooltip activator="parent" location="top">Check now</v-tooltip>
</v-btn>
<v-btn
icon="mdi-magnify-scan" size="x-small" variant="text"
:disabled="(source.backfill_runs_remaining || 0) > 0"
size="x-small" variant="text"
:color="source.backfill_state === 'running' ? 'warning' : undefined"
@click.stop="$emit('backfill', source)"
>
<v-icon>mdi-magnify-scan</v-icon>
<v-icon>{{ source.backfill_state === 'running' ? 'mdi-stop' : 'mdi-magnify-scan' }}</v-icon>
<v-tooltip activator="parent" location="top">
Deep scan walk full history for next few runs
{{ source.backfill_state === 'running'
? 'Stop backfill'
: 'Backfill — walk the full post history until complete' }}
</v-tooltip>
</v-btn>
<v-btn
@@ -532,31 +532,23 @@ async function onCheck(source) {
}
}
// Plan #544: arm a source for backfill mode (gallery-dl walks the full
// post history) for the next N download runs. Default 3 — enough budget
// to finish a deep creator without re-prompting the operator across
// timeout boundaries. The chip on the row reflects the remaining count.
// Plan #693: toggle a run-until-done backfill. Starting walks the full post
// history in time-boxed chunks across ticks until it reaches the bottom (the
// row badge tracks progress / completion); stopping cancels back to tick mode.
async function onBackfill(source) {
const raw = globalThis.window?.prompt(
`Deep scan "${source.artist_name} (${source.platform})" — walk full history for the next how many download runs? (110, default 3)`,
'3',
)
if (raw == null) return
const runs = parseInt(raw, 10)
if (!Number.isFinite(runs) || runs < 1 || runs > 10) {
toast({ text: 'Deep scan: runs must be 110', type: 'error' })
return
}
const running = source.backfill_state === 'running'
try {
await store.setBackfill(source.id, runs, source.artist_id)
toast({
text: `Deep scan armed for ${runs} run${runs === 1 ? '' : 's'}`,
type: 'success',
})
if (running) {
await store.stopBackfill(source.id, source.artist_id)
toast({ text: `Backfill stopped for ${source.artist_name}`, type: 'success' })
} else {
await store.startBackfill(source.id, source.artist_id)
toast({ text: `Backfill started for ${source.artist_name}`, type: 'success' })
}
await store.loadAll()
} catch (e) {
toast({
text: `Deep scan failed: ${e?.detail || e?.message || e}`,
text: `Backfill ${running ? 'stop' : 'start'} failed: ${e?.detail || e?.message || e}`,
type: 'error',
})
}
+12 -6
View File
@@ -85,11 +85,16 @@ export const useSourcesStore = defineStore('sources', () => {
}
}
// Plan #544: arm a source for backfill mode. The next `runs` download
// runs (default 3) walk gallery-dl's full post history instead of
// exiting early at the first contiguous archived block.
async function setBackfill(id, runs = 3, artistIdHint = null) {
const body = await api.post(`/api/sources/${id}/backfill`, { body: { runs } })
// Plan #693: start/stop a run-until-done backfill. 'start' walks the full
// post history in time-boxed chunks until it reaches the bottom (then the
// source shows backfill_state 'complete'); 'stop' cancels back to tick mode.
async function startBackfill(id, artistIdHint = null) {
const body = await api.post(`/api/sources/${id}/backfill`, { body: { action: 'start' } })
_invalidate(artistIdHint ?? body.artist_id)
return body
}
async function stopBackfill(id, artistIdHint = null) {
const body = await api.post(`/api/sources/${id}/backfill`, { body: { action: 'stop' } })
_invalidate(artistIdHint ?? body.artist_id)
return body
}
@@ -120,7 +125,8 @@ export const useSourcesStore = defineStore('sources', () => {
loadAll, loadForArtist,
create, update, remove,
checkNow,
setBackfill,
startBackfill,
stopBackfill,
findOrCreateArtist, autocompleteArtist,
loadScheduleStatus,
sourcesByArtistGrouped,
+13 -14
View File
@@ -199,7 +199,7 @@ async def test_list_derives_next_check_at_when_last_checked_set(
@pytest.mark.asyncio
async def test_backfill_endpoint_arms_source(client, artist, db):
async def test_backfill_endpoint_start_and_stop(client, artist, db):
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-backfill", enabled=True,
@@ -208,18 +208,21 @@ async def test_backfill_endpoint_arms_source(client, artist, db):
await db.commit()
sid = src.id
resp = await client.post(f"/api/sources/{sid}/backfill", json={"runs": 5})
resp = await client.post(f"/api/sources/{sid}/backfill", json={"action": "start"})
assert resp.status_code == 200
body = await resp.get_json()
assert body["backfill_runs_remaining"] == 5
assert body["backfill_state"] == "running"
# GET reflects the new state.
# GET reflects the running state.
one = await client.get(f"/api/sources/{sid}")
assert (await one.get_json())["backfill_runs_remaining"] == 5
assert (await one.get_json())["backfill_state"] == "running"
stopped = await client.post(f"/api/sources/{sid}/backfill", json={"action": "stop"})
assert (await stopped.get_json())["backfill_state"] is None
@pytest.mark.asyncio
async def test_backfill_endpoint_defaults_to_three(client, artist, db):
async def test_backfill_endpoint_defaults_to_start(client, artist, db):
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-backfill-default", enabled=True,
@@ -228,26 +231,22 @@ async def test_backfill_endpoint_defaults_to_three(client, artist, db):
await db.commit()
resp = await client.post(f"/api/sources/{src.id}/backfill", json={})
body = await resp.get_json()
assert body["backfill_runs_remaining"] == 3
assert body["backfill_state"] == "running"
@pytest.mark.asyncio
async def test_backfill_endpoint_rejects_out_of_range(client, artist, db):
async def test_backfill_endpoint_rejects_bad_action(client, artist, db):
src = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-backfill-bad", enabled=True,
)
db.add(src)
await db.commit()
bad = await client.post(f"/api/sources/{src.id}/backfill", json={"runs": 0})
bad = await client.post(f"/api/sources/{src.id}/backfill", json={"action": "nope"})
assert bad.status_code == 400
too_big = await client.post(
f"/api/sources/{src.id}/backfill", json={"runs": 99}
)
assert too_big.status_code == 400
@pytest.mark.asyncio
async def test_backfill_endpoint_404_when_source_missing(client):
resp = await client.post("/api/sources/999999/backfill", json={"runs": 3})
resp = await client.post("/api/sources/999999/backfill", json={"action": "start"})
assert resp.status_code == 404
+127 -155
View File
@@ -372,30 +372,16 @@ async def test_finalize_skipped_preserves_failures_clears_error(db):
assert row.last_checked_at is not None
# --- Plan #544: backfill lifecycle + PARTIAL → status=ok -------------------
# --- Plan #693: backfill state machine (time-boxed chunks, run-until-done) ---
@pytest.mark.asyncio
async def test_backfill_decrements_and_checkpoints_cursor(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""A backfill run that did NOT finish the walk (subprocess budget cut it
short → success=False / rc!=0) decrements the run budget AND checkpoints
gallery-dl's last-emitted cursor, so the next run resumes instead of
re-walking from the top (plan #689, Anduo #40411)."""
def _backfill_svc(db, db_sync, tmp_path, result):
"""DownloadService wired with a fake gdl returning `result` + a real
importer (so an empty written_paths just attaches nothing)."""
from backend.app.services.download_service import DownloadService
from backend.app.services.importer import Importer
_artist, source = seed_artist_and_source
source.backfill_runs_remaining = 3
await db.commit()
images_root = tmp_path / "images"
fake_gdl = _fake_gdl_with_result(_make_fake_dl_result(
success=False, written_paths=[], files_downloaded=0,
stderr="[patreon][debug] Cursor: 03:PAGE2:xyz\n",
))
sync_settings = db_sync.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
@@ -404,122 +390,138 @@ async def test_backfill_decrements_and_checkpoints_cursor(
thumbnailer=Thumbnailer(images_root=images_root), settings=sync_settings,
)
cred_service = CredentialService(db, CredentialCrypto(tmp_path / "key.b64", bootstrap_ok=True))
fake_gdl = _fake_gdl_with_result(result)
svc = DownloadService(
async_session=db, sync_session=db_sync,
gdl=fake_gdl, importer=importer, cred_service=cred_service,
)
await svc.download_source(source.id)
remaining, overrides = (await db.execute(
select(Source.backfill_runs_remaining, Source.config_overrides)
.where(Source.id == source.id)
)).one()
assert remaining == 2
assert overrides.get("_backfill_cursor") == "03:PAGE2:xyz"
return svc, fake_gdl
@pytest.mark.asyncio
async def test_backfill_cursor_keeps_backfill_mode_after_budget_drained(
async def test_backfill_chunk_progress_advances_cursor(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""A pending cursor with runs_remaining == 0 still runs in BACKFILL mode
(skip:True + the resume cursor threaded to gallery-dl), so a large walk
finishes across ticks without the operator re-triggering."""
from backend.app.services.download_service import DownloadService
from backend.app.services.gallery_dl import BACKFILL_SKIP_VALUE
from backend.app.services.importer import Importer
"""A running backfill chunk that didn't finish but advanced (new cursor)
stays 'running', checkpoints the cursor, bumps the chunk counter, and
spends one safety-cap chunk."""
_artist, source = seed_artist_and_source
source.backfill_runs_remaining = 0
source.config_overrides = {"_backfill_cursor": "03:RESUME:here"}
source.config_overrides = {"_backfill_state": "running"}
source.backfill_runs_remaining = 5
await db.commit()
fake_gdl = _fake_gdl_with_result(_make_fake_dl_result(
svc, _ = _backfill_svc(db, db_sync, tmp_path, _make_fake_dl_result(
success=False, written_paths=[], files_downloaded=0,
stderr="[patreon][debug] Cursor: 03:PAGE2:xyz\n",
))
await svc.download_source(source.id)
remaining, co = (await db.execute(
select(Source.backfill_runs_remaining, Source.config_overrides)
.where(Source.id == source.id)
)).one()
assert co.get("_backfill_state") == "running"
assert co.get("_backfill_cursor") == "03:PAGE2:xyz"
assert co.get("_backfill_chunks") == 1
assert remaining == 4
@pytest.mark.asyncio
async def test_backfill_state_running_selects_backfill_mode_and_resumes(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""state=='running' drives backfill mode (skip:True + chunk budget) and
threads the stored cursor to gallery-dl as the resume point."""
from backend.app.services.gallery_dl import (
BACKFILL_CHUNK_SECONDS,
BACKFILL_SKIP_VALUE,
)
_artist, source = seed_artist_and_source
source.config_overrides = {"_backfill_state": "running", "_backfill_cursor": "03:RESUME:here"}
source.backfill_runs_remaining = 5
await db.commit()
svc, fake_gdl = _backfill_svc(db, db_sync, tmp_path, _make_fake_dl_result(
success=False, written_paths=[],
stderr="[patreon][debug] Cursor: 03:RESUME2:next\n",
))
sync_settings = db_sync.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
importer = Importer(
session=db_sync, images_root=tmp_path / "images",
import_root=tmp_path / "images",
thumbnailer=Thumbnailer(images_root=tmp_path / "images"),
settings=sync_settings,
)
cred_service = CredentialService(db, CredentialCrypto(tmp_path / "key.b64", bootstrap_ok=True))
svc = DownloadService(
async_session=db, sync_session=db_sync,
gdl=fake_gdl, importer=importer, cred_service=cred_service,
)
await svc.download_source(source.id)
kwargs = fake_gdl.download.call_args.kwargs
assert kwargs["skip_value"] is BACKFILL_SKIP_VALUE
assert kwargs["source_config"].resume_cursor == "03:RESUME:here"
assert kwargs["source_config"].timeout == BACKFILL_CHUNK_SECONDS
overrides = (await db.execute(
co = (await db.execute(
select(Source.config_overrides).where(Source.id == source.id)
)).scalar_one()
assert overrides.get("_backfill_cursor") == "03:RESUME2:next"
assert co.get("_backfill_cursor") == "03:RESUME2:next"
@pytest.mark.asyncio
async def test_backfill_completes_and_clears_cursor(
async def test_backfill_clean_exit_marks_complete(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""A clean rc=0 finish means gallery-dl walked to the bottom — clear the
checkpoint and drop back to tick mode, regardless of files this run."""
from backend.app.services.download_service import DownloadService
from backend.app.services.importer import Importer
"""A clean rc=0 chunk = gallery-dl reached the bottom → state 'complete',
cursor cleared, returns to tick mode."""
_artist, source = seed_artist_and_source
source.backfill_runs_remaining = 2
source.config_overrides = {"_backfill_cursor": "03:NEAR:bottom"}
source.config_overrides = {"_backfill_state": "running", "_backfill_cursor": "03:NEAR:bottom"}
source.backfill_runs_remaining = 5
await db.commit()
fake_gdl = _fake_gdl_with_result(_make_fake_dl_result(
svc, _ = _backfill_svc(db, db_sync, tmp_path, _make_fake_dl_result(
success=True, written_paths=[], files_downloaded=0,
stderr="[patreon][debug] Cursor: 03:LAST:page\n",
))
sync_settings = db_sync.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
importer = Importer(
session=db_sync, images_root=tmp_path / "images",
import_root=tmp_path / "images",
thumbnailer=Thumbnailer(images_root=tmp_path / "images"),
settings=sync_settings,
)
cred_service = CredentialService(db, CredentialCrypto(tmp_path / "key.b64", bootstrap_ok=True))
svc = DownloadService(
async_session=db, sync_session=db_sync,
gdl=fake_gdl, importer=importer, cred_service=cred_service,
)
await svc.download_source(source.id)
remaining, overrides = (await db.execute(
remaining, co = (await db.execute(
select(Source.backfill_runs_remaining, Source.config_overrides)
.where(Source.id == source.id)
)).one()
assert co.get("_backfill_state") == "complete"
assert "_backfill_cursor" not in co
assert remaining == 0
assert "_backfill_cursor" not in (overrides or {})
@pytest.mark.asyncio
async def test_backfill_cursor_stuck_guard_gives_up(
async def test_backfill_cap_exhaustion_stalls(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""If two consecutive non-completing runs fail to advance the cursor,
drop the checkpoint + zero the budget so a wedged walk can't re-strand
forever (cf. download soft-limit ladder)."""
"""A progressing chunk that spends the last safety-cap chunk without
reaching the bottom pauses as 'stalled' (doesn't loop forever)."""
_artist, source = seed_artist_and_source
source.config_overrides = {"_backfill_state": "running"}
source.backfill_runs_remaining = 1
await db.commit()
svc, _ = _backfill_svc(db, db_sync, tmp_path, _make_fake_dl_result(
success=False, written_paths=[],
stderr="[patreon][debug] Cursor: 03:MORE:left\n",
))
await svc.download_source(source.id)
remaining, co = (await db.execute(
select(Source.backfill_runs_remaining, Source.config_overrides)
.where(Source.id == source.id)
)).one()
assert co.get("_backfill_state") == "stalled"
assert remaining == 0
@pytest.mark.asyncio
async def test_backfill_stuck_guard_stalls_after_two_no_advance(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""Two consecutive chunks that fail to advance the cursor → 'stalled',
cursor cleared, so a wedged walk can't re-strand forever."""
from unittest.mock import MagicMock
from backend.app.services.download_service import DownloadService
_artist, source = seed_artist_and_source
source.backfill_runs_remaining = 0
source.config_overrides = {"_backfill_cursor": "stuck"}
source.config_overrides = {"_backfill_state": "running", "_backfill_cursor": "stuck"}
source.backfill_runs_remaining = 5
await db.commit()
svc = DownloadService(
@@ -528,109 +530,79 @@ async def test_backfill_cursor_stuck_guard_gives_up(
)
ctx = {
"source_id": source.id, "platform": "patreon",
"config_overrides": {"_backfill_cursor": "stuck"},
"backfill_runs_remaining": 0,
"config_overrides": {"_backfill_state": "running", "_backfill_cursor": "stuck"},
"backfill_runs_remaining": 5,
}
stuck = _make_fake_dl_result(success=False, stderr="Cursor: stuck\n")
# Run 1: cursor unchanged → 1 stall, checkpoint retained.
await svc._apply_backfill_lifecycle(ctx, stuck)
await db.commit()
overrides = (await db.execute(
co = (await db.execute(
select(Source.config_overrides).where(Source.id == source.id)
)).scalar_one()
assert overrides.get("_backfill_cursor") == "stuck"
assert overrides.get("_backfill_cursor_stalls") == 1
assert co.get("_backfill_state") == "running"
assert co.get("_backfill_cursor_stalls") == 1
# Run 2: still stuck → give up.
ctx["config_overrides"] = dict(overrides)
ctx["config_overrides"] = dict(co)
await svc._apply_backfill_lifecycle(ctx, stuck)
await db.commit()
remaining, overrides2 = (await db.execute(
select(Source.backfill_runs_remaining, Source.config_overrides)
.where(Source.id == source.id)
)).one()
assert remaining == 0
assert "_backfill_cursor" not in (overrides2 or {})
co2 = (await db.execute(
select(Source.config_overrides).where(Source.id == source.id)
)).scalar_one()
assert co2.get("_backfill_state") == "stalled"
assert "_backfill_cursor" not in co2
@pytest.mark.asyncio
async def test_backfill_auto_resets_on_clean_zero_files(
async def test_backfill_timeout_chunk_reclassified_to_ok(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""A clean run (rc=0) that downloaded zero files means the backfill
queue drained — reset to 0 immediately instead of wasting the rest of
the N-run budget on no-op walks."""
from backend.app.services.download_service import DownloadService
from backend.app.services.importer import Importer
"""A backfill chunk that hit its time-box (TIMEOUT) but advanced is
reclassified to PARTIAL → event status 'ok' (progress, not error), and
consecutive_failures is not bumped."""
from backend.app.services.gallery_dl import ErrorType
_artist, source = seed_artist_and_source
source.backfill_runs_remaining = 3
source.config_overrides = {"_backfill_state": "running"}
source.backfill_runs_remaining = 5
await db.commit()
fake_result = _make_fake_dl_result(
success=True, written_paths=[], files_downloaded=0,
)
fake_gdl = _fake_gdl_with_result(fake_result)
svc, _ = _backfill_svc(db, db_sync, tmp_path, _make_fake_dl_result(
success=False, files_downloaded=3,
error_type=ErrorType.TIMEOUT,
error_message="Download timed out",
stderr="[patreon][debug] Cursor: 03:NEXT:page\n",
))
event_id = await svc.download_source(source.id)
sync_settings = db_sync.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
importer = Importer(
session=db_sync, images_root=tmp_path / "images",
import_root=tmp_path / "images",
thumbnailer=Thumbnailer(images_root=tmp_path / "images"),
settings=sync_settings,
)
cred_service = CredentialService(db, CredentialCrypto(tmp_path / "key.b64", bootstrap_ok=True))
svc = DownloadService(
async_session=db, sync_session=db_sync,
gdl=fake_gdl, importer=importer, cred_service=cred_service,
)
await svc.download_source(source.id)
remaining = (await db.execute(
select(Source.backfill_runs_remaining).where(Source.id == source.id)
ev = (await db.execute(
select(DownloadEvent).where(DownloadEvent.id == event_id)
)).scalar_one()
assert remaining == 0
assert ev.status == "ok"
failures = (await db.execute(
select(Source.consecutive_failures).where(Source.id == source.id)
)).scalar_one()
assert failures == 0
@pytest.mark.asyncio
async def test_tick_mode_does_not_touch_backfill_counter(
async def test_tick_mode_when_not_running_leaves_state_untouched(
db, db_sync, tmp_path, seed_artist_and_source,
):
"""When backfill_runs_remaining is already 0, downloads don't go
negative or otherwise mutate the counter."""
from backend.app.services.download_service import DownloadService
from backend.app.services.importer import Importer
"""No _backfill_state → not backfilling; the lifecycle is a no-op and the
counter/state aren't mutated."""
_artist, source = seed_artist_and_source
assert source.backfill_runs_remaining == 0
assert (source.config_overrides or {}).get("_backfill_state") is None
fake_gdl = _fake_gdl_with_result(_make_fake_dl_result(
svc, _ = _backfill_svc(db, db_sync, tmp_path, _make_fake_dl_result(
success=True, written_paths=[], files_downloaded=0,
))
sync_settings = db_sync.execute(
select(ImportSettings).where(ImportSettings.id == 1)
).scalar_one()
importer = Importer(
session=db_sync, images_root=tmp_path / "images",
import_root=tmp_path / "images",
thumbnailer=Thumbnailer(images_root=tmp_path / "images"),
settings=sync_settings,
)
cred_service = CredentialService(db, CredentialCrypto(tmp_path / "key.b64", bootstrap_ok=True))
svc = DownloadService(
async_session=db, sync_session=db_sync,
gdl=fake_gdl, importer=importer, cred_service=cred_service,
)
await svc.download_source(source.id)
remaining = (await db.execute(
select(Source.backfill_runs_remaining).where(Source.id == source.id)
co = (await db.execute(
select(Source.config_overrides).where(Source.id == source.id)
)).scalar_one()
assert remaining == 0
assert (co or {}).get("_backfill_state") is None
@pytest.mark.asyncio
+2 -2
View File
@@ -34,7 +34,7 @@ def test_timeout_ladder_keeps_subprocess_budgets_under_soft_limit():
preempts it. soft must in turn sit below the hard SIGKILL cap."""
from backend.app.services.gallery_dl import (
_DEFAULT_GDL_TIMEOUT_SECONDS,
BACKFILL_TIMEOUT_SECONDS,
BACKFILL_CHUNK_SECONDS,
)
from backend.app.tasks.download import (
DOWNLOAD_HARD_TIME_LIMIT,
@@ -42,7 +42,7 @@ def test_timeout_ladder_keeps_subprocess_budgets_under_soft_limit():
)
assert _DEFAULT_GDL_TIMEOUT_SECONDS < DOWNLOAD_SOFT_TIME_LIMIT
assert BACKFILL_TIMEOUT_SECONDS < DOWNLOAD_SOFT_TIME_LIMIT
assert BACKFILL_CHUNK_SECONDS < DOWNLOAD_SOFT_TIME_LIMIT
assert DOWNLOAD_SOFT_TIME_LIMIT < DOWNLOAD_HARD_TIME_LIMIT
+37 -20
View File
@@ -175,58 +175,75 @@ async def test_list_hides_sidecar_synthetic_anchors(db):
@pytest.mark.asyncio
async def test_set_backfill_runs_arms_source(db):
"""The service method overrides backfill_runs_remaining (regardless of
the auto-arm-on-create starting value) and returns the updated record
so the API can echo it back."""
async def test_start_backfill_arms_run_until_done(db):
"""start_backfill sets state=running + the chunk cap and clears any prior
cursor/chunk state, returning the updated record for the API to echo."""
from backend.app.services.source_service import BACKFILL_MAX_CHUNKS
artist = await _artist(db, "Alice")
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice",
)
updated = await svc.set_backfill_runs(rec.id, 5)
assert updated.backfill_runs_remaining == 5
# Simulate a prior, finished walk leaving stale checkpoint state.
await db.execute(
Source.__table__.update().where(Source.id == rec.id).values(
config_overrides={"_backfill_state": "complete", "_backfill_cursor": "old",
"_backfill_chunks": 7},
)
)
await db.commit()
db_value = (await db.execute(
select(Source.backfill_runs_remaining).where(Source.id == rec.id)
updated = await svc.start_backfill(rec.id)
assert updated.backfill_state == "running"
assert updated.backfill_chunks == 0
assert updated.backfill_runs_remaining == BACKFILL_MAX_CHUNKS
co = (await db.execute(
select(Source.config_overrides).where(Source.id == rec.id)
)).scalar_one()
assert db_value == 5
assert co.get("_backfill_state") == "running"
assert "_backfill_cursor" not in co
@pytest.mark.asyncio
async def test_set_backfill_runs_rejects_out_of_range(db):
async def test_stop_backfill_returns_to_idle(db):
artist = await _artist(db, "Alice")
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice",
)
with pytest.raises(ValueError):
await svc.set_backfill_runs(rec.id, 0)
with pytest.raises(ValueError):
await svc.set_backfill_runs(rec.id, 11)
await svc.start_backfill(rec.id)
updated = await svc.stop_backfill(rec.id)
assert updated.backfill_state is None
assert updated.backfill_runs_remaining == 0
co = (await db.execute(
select(Source.config_overrides).where(Source.id == rec.id)
)).scalar_one()
assert "_backfill_state" not in (co or {})
@pytest.mark.asyncio
async def test_set_backfill_runs_raises_when_source_missing(db):
async def test_start_backfill_raises_when_source_missing(db):
svc = SourceService(db)
with pytest.raises(LookupError):
await svc.set_backfill_runs(99999, 3)
await svc.start_backfill(99999)
@pytest.mark.asyncio
async def test_new_enabled_source_starts_in_backfill_mode(db):
"""Plan #544 follow-up: freshly added enabled sources have no archive
yet, so the first few polls would blow the wall-clock cap in tick
mode. Pre-arm backfill so the initial walks use the longer timeout."""
"""Plan #693: freshly added enabled sources have no archive yet, so they
arm run-until-done backfill — state 'running' — to walk the full history
on the first ticks instead of blowing the wall-clock cap in tick mode."""
artist = await _artist(db, "Alice")
svc = SourceService(db)
rec = await svc.create(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice-new",
)
assert rec.backfill_runs_remaining == 3
assert rec.backfill_state == "running"
@pytest.mark.asyncio