fix: Nightscout API silently truncated multi-day fetches to ~3-4 days
_entries_since/_treatments_since requested a single page via `count`, but Nightscout's /api/v1/entries and /api/v1/treatments ignore a large `count` and cap the response around ~1150/~700 documents regardless of how far back the requested period goes. Every report page relying on fetch_entries_range/fetch_treatments_range (7/14/30/90-day selectors) was silently only getting the most recent ~3-4 days, no matter the selected period. Fixed by paginating with `find[date][$lte]` cursors in a new _paginated_get(), walking back until the requested `since` boundary is reached or the server returns a short/empty page (= genuinely no more data, confirmed by manually paginating against the real instance: entries go back 50+ days, treatments only ~4 days on this install). Also added reporting.completeness_warning(), shared by the interactive pages (via ui_common.render_completeness_warning) and the PDF export, that distinguishes "a structural gap at the start of the period" (data wasn't fetched/available) from "scattered gaps below the clinical AGP coverage threshold" (Danne et al. 2017) — the previous single generic "X% sensor coverage" message read as a CGM/sensor problem even when the real cause was this fetch bug.
This commit is contained in:
+55
-19
@@ -31,6 +31,19 @@ SENSOR_CHANGE_EVENT_TYPES = {"Sensor Change", "Sensor Start"}
|
||||
|
||||
_REQUEST_TIMEOUT = 10
|
||||
|
||||
# Nightscout's /api/v1/entries en /api/v1/treatments negeren een groot
|
||||
# `count`-verzoek: het antwoord wordt hoe dan ook stilzwijgend afgeknipt rond
|
||||
# een paar honderd tot ~1150 documenten, ongeacht hoe ver de opgevraagde
|
||||
# periode teruggaat (waargenomen: count=100000 op entries gaf slechts de
|
||||
# meest recente ~1150 metingen terug — nog geen 4 dagen — terwijl er wel
|
||||
# degelijk weken oudere data in Nightscout beschikbaar bleek te zijn). Eén
|
||||
# verzoek is dus niet genoeg voor meerdaagse rapportages; _paginated_get()
|
||||
# loopt terug in de tijd met `find[date][$lte]`-cursors tot de gevraagde
|
||||
# `since`-grens bereikt is of de server minder dan een volle pagina teruggeeft
|
||||
# (= geen oudere data meer beschikbaar, wat verschilt van "afgeknipt").
|
||||
_PAGE_SIZE = 1000
|
||||
_MAX_PAGES = 150 # 150 000 documenten; ruim boven wat een 90-dagenrapport nodig heeft
|
||||
|
||||
|
||||
class NightscoutConfigError(RuntimeError):
|
||||
"""NIGHTSCOUT_URL ontbreekt of is ongeldig."""
|
||||
@@ -75,15 +88,44 @@ def _get(path: str, params: dict) -> list:
|
||||
return response.json()
|
||||
|
||||
|
||||
def _entries_since(since: datetime, count: int, until: datetime | None = None) -> pd.DataFrame:
|
||||
"""Haal entries op sinds `since` (en optioneel tot `until`), lokaal gefilterd.
|
||||
def _paginated_get(path: str, since: datetime, until: datetime | None = None) -> list:
|
||||
"""Haal alle documenten op tussen `since` en `until` (of tot nu), pagina voor pagina.
|
||||
|
||||
Nightscout geeft resultaten terug in aflopende volgorde; vraag ruim genoeg
|
||||
entries op (CGM meet doorgaans elke 5 min) en filter lokaal op tijd. Dit is
|
||||
robuuster dan server-side find[]-query's, die niet op elke Nightscout-versie
|
||||
identiek werken.
|
||||
Zie de toelichting bij _PAGE_SIZE hierboven voor waarom dit niet één
|
||||
verzoek met een groot `count` kan zijn (BUG: dat leverde bij een
|
||||
meerdaags rapport stilzwijgend alleen de laatste ~3-4 dagen op, ongeacht
|
||||
de gekozen periode). Elke pagina wordt opgevraagd met `find[date][$lte]`
|
||||
net onder de oudste timestamp van de vorige pagina, zodat elk document
|
||||
precies één keer terugkomt. Stopt zodra de oudste timestamp in een pagina
|
||||
op of voorbij `since` ligt, of zodra de server minder dan een volle
|
||||
pagina teruggeeft (dan is er geen oudere data meer, punt).
|
||||
"""
|
||||
data = _get("/api/v1/entries/sgv.json", {"count": count})
|
||||
since_ms = int(since.timestamp() * 1000)
|
||||
cursor_ms = int(until.timestamp() * 1000) if until is not None else None
|
||||
|
||||
results: list = []
|
||||
for _ in range(_MAX_PAGES):
|
||||
params = {"count": _PAGE_SIZE}
|
||||
if cursor_ms is not None:
|
||||
params["find[date][$lte]"] = cursor_ms
|
||||
page = _get(path, params)
|
||||
if not page:
|
||||
break
|
||||
results.extend(page)
|
||||
|
||||
dates = [item["date"] for item in page if "date" in item]
|
||||
if not dates:
|
||||
break
|
||||
oldest_ms = min(dates)
|
||||
if oldest_ms <= since_ms or len(page) < _PAGE_SIZE:
|
||||
break
|
||||
cursor_ms = oldest_ms - 1
|
||||
return results
|
||||
|
||||
|
||||
def _entries_since(since: datetime, until: datetime | None = None) -> pd.DataFrame:
|
||||
"""Haal entries op sinds `since` (en optioneel tot `until`), lokaal gefilterd."""
|
||||
data = _paginated_get("/api/v1/entries/sgv.json", since, until)
|
||||
|
||||
if not data:
|
||||
return pd.DataFrame(columns=["timestamp", "mmol"])
|
||||
@@ -97,9 +139,9 @@ def _entries_since(since: datetime, count: int, until: datetime | None = None) -
|
||||
return df[["timestamp", "mmol"]].sort_values("timestamp").reset_index(drop=True)
|
||||
|
||||
|
||||
def _treatments_since(since: datetime, count: int, until: datetime | None = None) -> pd.DataFrame:
|
||||
def _treatments_since(since: datetime, until: datetime | None = None) -> pd.DataFrame:
|
||||
"""Haal treatments op sinds `since` (en optioneel tot `until`), lokaal gefilterd."""
|
||||
data = _get("/api/v1/treatments.json", {"count": count})
|
||||
data = _paginated_get("/api/v1/treatments.json", since, until)
|
||||
|
||||
if not data:
|
||||
return pd.DataFrame(columns=["timestamp", "eventType", "insulin", "carbs"])
|
||||
@@ -129,8 +171,7 @@ def fetch_entries(hours: int = 24) -> pd.DataFrame:
|
||||
gesorteerd op tijd.
|
||||
"""
|
||||
since = datetime.now(timezone.utc) - timedelta(hours=hours)
|
||||
count = max(300, hours * 15)
|
||||
return _entries_since(since, count)
|
||||
return _entries_since(since)
|
||||
|
||||
|
||||
def fetch_treatments(hours: int = 24) -> pd.DataFrame:
|
||||
@@ -141,8 +182,7 @@ def fetch_treatments(hours: int = 24) -> pd.DataFrame:
|
||||
'insulin' en 'carbs' (de laatste twee NaN waar niet van toepassing).
|
||||
"""
|
||||
since = datetime.now(timezone.utc) - timedelta(hours=hours)
|
||||
count = max(200, hours * 10)
|
||||
return _treatments_since(since, count)
|
||||
return _treatments_since(since)
|
||||
|
||||
|
||||
def fetch_entries_range(start_date: date, end_date: date) -> pd.DataFrame:
|
||||
@@ -154,9 +194,7 @@ def fetch_entries_range(start_date: date, end_date: date) -> pd.DataFrame:
|
||||
"""
|
||||
since = datetime.combine(start_date, time.min, tzinfo=timezone.utc)
|
||||
until = datetime.combine(end_date, time.max, tzinfo=timezone.utc)
|
||||
days = (end_date - start_date).days + 1
|
||||
count = min(days * 300, 100_000) # ruime marge boven 5-min-interval
|
||||
return _entries_since(since, count, until)
|
||||
return _entries_since(since, until)
|
||||
|
||||
|
||||
def fetch_treatments_range(start_date: date, end_date: date) -> pd.DataFrame:
|
||||
@@ -166,6 +204,4 @@ def fetch_treatments_range(start_date: date, end_date: date) -> pd.DataFrame:
|
||||
"""
|
||||
since = datetime.combine(start_date, time.min, tzinfo=timezone.utc)
|
||||
until = datetime.combine(end_date, time.max, tzinfo=timezone.utc)
|
||||
days = (end_date - start_date).days + 1
|
||||
count = min(days * 50, 50_000)
|
||||
return _treatments_since(since, count, until)
|
||||
return _treatments_since(since, until)
|
||||
|
||||
Reference in New Issue
Block a user