feat(tickers): record delisting instead of deleting the symbol
Retiring a symbol meant delete_ticker or bootstrap_universe(prune_missing), both of which cascade through OHLCV, setups and scores. That destroys exactly the history four research documents already apologise for: today's tracked universe projected backward is survivorship-biased, and hard-deleting every delisted name is what causes it. Keeping the rows preserves the option to fix that — it does not fix it, which needs the replay to model a delisting as an exit event. tickers gains delisted_on / delisted_reason (migration 032). NULL means actively traded. The filter is opt-in via ticker_service.active_only rather than folded into a shared getter: the registry and admin views deliberately keep delisted rows so the delisting is visible, and a silent default would undo that. Applied to the live path only — scanner, momentum ranking, scoring, breadth, fundamentals candidates, SEC universe, earnings import, ingestion loops. run_backtest keeps them on purpose. Detection runs off OHLCV staleness, not off the SEC fundamentals import: that importer stalls for days on unrelated Company-Facts gaps and would take detection down with it. On a stale symbol the scheduler asks SEC for a Form 25/25-NSE/15 and retires it only on a hit, so a halt or a rename (SATS->ECHO) keeps the existing warning. The probe waits 3 stale days so a market-data outage cannot turn into one SEC request per symbol per run. Safe to automate because it is reversible: clear_delisted un-retires a false positive, where a delete had already taken the history. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
@@ -25,6 +25,7 @@ from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import ticker_service
|
||||
from app.services.price_service import query_ohlcv
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -112,7 +113,7 @@ def compute_divergence_series(
|
||||
async def _load_universe_closes(
|
||||
db: AsyncSession, symbols: list[str] | None = None
|
||||
) -> dict[str, Series]:
|
||||
stmt = select(Ticker).order_by(Ticker.symbol)
|
||||
stmt = ticker_service.active_only(select(Ticker).order_by(Ticker.symbol))
|
||||
if symbols is not None:
|
||||
stmt = stmt.where(Ticker.symbol.in_(symbols))
|
||||
result = await db.execute(stmt)
|
||||
|
||||
@@ -32,7 +32,7 @@ from app.config import settings
|
||||
from app.database import insert_for_session
|
||||
from app.models.earnings_event import EarningsEvent
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import dolt_client, earnings_alignment
|
||||
from app.services import dolt_client, earnings_alignment, ticker_service
|
||||
from app.services.data_import import ValidationResult
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -289,7 +289,11 @@ class DoltEarningsImporter:
|
||||
# -- helpers -----------------------------------------------------------
|
||||
|
||||
async def _load_universe(self, db) -> dict[str, int]:
|
||||
rows = (await db.execute(select(Ticker.id, Ticker.symbol))).all()
|
||||
rows = (
|
||||
await db.execute(
|
||||
ticker_service.active_only(select(Ticker.id, Ticker.symbol))
|
||||
)
|
||||
).all()
|
||||
return {
|
||||
earnings_alignment.normalise_symbol(symbol): tid
|
||||
for tid, symbol in rows
|
||||
|
||||
@@ -22,6 +22,7 @@ from app.models.fundamental_snapshot import FundamentalSnapshot
|
||||
from app.models.ohlcv import OHLCVRecord
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import fundamentals_derivation as deriv
|
||||
from app.services import ticker_service
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -46,7 +47,11 @@ async def build_candidates(
|
||||
"""Derive current cache candidates using only already-stored data."""
|
||||
today = today or datetime.now(ZoneInfo("America/New_York")).date()
|
||||
tickers = list(
|
||||
(await db.execute(select(Ticker).order_by(Ticker.symbol))).scalars()
|
||||
(
|
||||
await db.execute(
|
||||
ticker_service.active_only(select(Ticker).order_by(Ticker.symbol))
|
||||
)
|
||||
).scalars()
|
||||
)
|
||||
if not tickers:
|
||||
return []
|
||||
|
||||
@@ -18,6 +18,7 @@ from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import ticker_service
|
||||
from app.services.price_service import query_ohlcv
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -169,7 +170,9 @@ async def compute_activation_ranks(db: AsyncSession) -> dict[str, dict[str, floa
|
||||
before scanning; the research backtest ranked each weekly setup-candidate
|
||||
cross-section, so this is the deliberate production approximation.
|
||||
"""
|
||||
result = await db.execute(select(Ticker).order_by(Ticker.symbol))
|
||||
result = await db.execute(
|
||||
ticker_service.active_only(select(Ticker).order_by(Ticker.symbol))
|
||||
)
|
||||
tickers = list(result.scalars().all())
|
||||
|
||||
benchmark_closes = await _load_activation_benchmark(db)
|
||||
|
||||
@@ -31,7 +31,7 @@ from app.services import fundamentals_quality_service, system_event_service
|
||||
from app.services.price_service import query_ohlcv
|
||||
from app.services.qualification import setup_qualifies
|
||||
from app.services.sr_service import detect_gate_target_ladder
|
||||
from app.services import settings_store
|
||||
from app.services import settings_store, ticker_service
|
||||
from app.services.trade_policy import (
|
||||
MANUAL_BOOK,
|
||||
SHADOW_BOOK,
|
||||
@@ -735,7 +735,11 @@ async def scan_all_tickers(
|
||||
# Plain ids/strings, not Ticker instances: the rollbacks below expire any
|
||||
# ORM objects held across them, and touching an expired attribute afterwards
|
||||
# triggers sync lazy-loading, which raises on an AsyncSession.
|
||||
result = await db.execute(select(Ticker.id, Ticker.symbol).order_by(Ticker.symbol))
|
||||
result = await db.execute(
|
||||
ticker_service.active_only(
|
||||
select(Ticker.id, Ticker.symbol).order_by(Ticker.symbol)
|
||||
)
|
||||
)
|
||||
ticker_rows = [(int(ticker_id), symbol) for ticker_id, symbol in result.all()]
|
||||
total = len(ticker_rows)
|
||||
|
||||
|
||||
@@ -20,7 +20,7 @@ from app.database import insert_for_session
|
||||
from app.exceptions import NotFoundError, ValidationError
|
||||
from app.models.score import CompositeScore, DimensionScore
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import settings_store
|
||||
from app.services import settings_store, ticker_service
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -883,7 +883,11 @@ async def get_rankings(db: AsyncSession) -> dict:
|
||||
Returns dict suitable for RankingResponse.
|
||||
"""
|
||||
weights = await _get_weights(db)
|
||||
tickers = (await db.execute(select(Ticker).order_by(Ticker.symbol))).scalars().all()
|
||||
tickers = (
|
||||
await db.execute(
|
||||
ticker_service.active_only(select(Ticker).order_by(Ticker.symbol))
|
||||
)
|
||||
).scalars().all()
|
||||
|
||||
async def _load_scores() -> tuple[dict[int, CompositeScore], dict[int, dict[str, DimensionScore]]]:
|
||||
comps = {
|
||||
@@ -947,7 +951,7 @@ async def update_weights(
|
||||
await _save_weights(db, full_weights)
|
||||
|
||||
# Recompute all composite scores
|
||||
result = await db.execute(select(Ticker))
|
||||
result = await db.execute(ticker_service.active_only(select(Ticker)))
|
||||
tickers = list(result.scalars().all())
|
||||
|
||||
for ticker in tickers:
|
||||
|
||||
@@ -45,6 +45,13 @@ _CA_VERIFY: str | bool = _CA if _CA and Path(_CA).exists() else True
|
||||
|
||||
_FORMS_10 = frozenset({"10-K", "10-Q", "10-K/A", "10-Q/A"})
|
||||
|
||||
# Exchange delisting (25 / 25-NSE) and registration termination (15 family).
|
||||
# Their presence is SEC confirming a security stopped trading — see
|
||||
# ``SecClient.delisting_filing``.
|
||||
_DELISTING_FORMS = frozenset({
|
||||
"25", "25-NSE", "15-12B", "15-12G", "15F-12B", "15F-12G",
|
||||
})
|
||||
|
||||
|
||||
class SecError(ProviderError):
|
||||
"""SEC request failed (403, exhausted 429/5xx, timeout, transport, parse)."""
|
||||
@@ -253,6 +260,34 @@ class SecClient:
|
||||
"filings": filings,
|
||||
}
|
||||
|
||||
async def delisting_filing(self, cik: int | str) -> dict[str, Any] | None:
|
||||
"""Newest exchange-delisting / deregistration filing, or ``None``.
|
||||
|
||||
Form 25/25-NSE strikes a security from listing; Form 15 terminates the
|
||||
registration. Either is SEC confirming the security stopped trading —
|
||||
which is what separates a real delisting from a multi-day halt or a
|
||||
ticker rename, neither of which files one. That precision is the reason
|
||||
this can mark a symbol automatically.
|
||||
|
||||
Reads ``filings.recent`` directly: ``submissions()`` keeps only the
|
||||
10-K/10-Q family, so these forms never survive its parser.
|
||||
"""
|
||||
base = await self.get_json(f"{_DATA}/submissions/CIK{cik10(cik)}.json")
|
||||
arrays = (base.get("filings") or {}).get("recent") or {}
|
||||
forms = arrays.get("form") or []
|
||||
dates = arrays.get("filingDate") or []
|
||||
best: dict[str, Any] | None = None
|
||||
for i, form in enumerate(forms):
|
||||
if form not in _DELISTING_FORMS or i >= len(dates) or not dates[i]:
|
||||
continue
|
||||
try:
|
||||
filed = date.fromisoformat(dates[i])
|
||||
except ValueError:
|
||||
continue
|
||||
if best is None or filed > best["filing_date"]:
|
||||
best = {"form": form, "filing_date": filed}
|
||||
return best
|
||||
|
||||
async def companyfacts(self, cik: int | str) -> dict[str, Any]:
|
||||
"""Raw companyfacts JSON ({cik, entityName, facts})."""
|
||||
return await self.get_json(f"{_DATA}/api/xbrl/companyfacts/CIK{cik10(cik)}.json")
|
||||
|
||||
@@ -24,7 +24,7 @@ from typing import Iterable
|
||||
from sqlalchemy import select, update
|
||||
|
||||
from app.models.ticker import Ticker
|
||||
from app.services import settings_store
|
||||
from app.services import settings_store, ticker_service
|
||||
from app.services.earnings_alignment import normalise_symbol
|
||||
from app.services.sec_client import SecClient
|
||||
|
||||
@@ -55,7 +55,11 @@ async def resolve_ciks(db, client: SecClient) -> ResolvedUniverse:
|
||||
returns the mapping + proposed `tickers.cik` writes; mutates nothing."""
|
||||
ticker_to_cik = await client.company_tickers()
|
||||
overrides = await cik_overrides(db)
|
||||
rows = (await db.execute(select(Ticker.id, Ticker.symbol, Ticker.cik))).all()
|
||||
rows = (
|
||||
await db.execute(
|
||||
ticker_service.active_only(select(Ticker.id, Ticker.symbol, Ticker.cik))
|
||||
)
|
||||
).all()
|
||||
|
||||
result = ResolvedUniverse()
|
||||
for tid, symbol, current_cik in rows:
|
||||
|
||||
@@ -1,13 +1,48 @@
|
||||
"""Ticker Registry service: add, delete, and list tracked tickers."""
|
||||
"""Ticker Registry service: add, delete, list, and retire tracked tickers."""
|
||||
|
||||
import logging
|
||||
import re
|
||||
from datetime import date
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy import select, update
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.exceptions import DuplicateError, NotFoundError, ValidationError
|
||||
from app.models.ticker import Ticker
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Reasons a symbol may be marked delisted, narrowest first.
|
||||
REASON_FORM_25 = "form_25" # SEC Form 25/25-NSE/15 confirmed the exchange exit
|
||||
REASON_MANUAL = "manual" # an operator decided
|
||||
|
||||
# How long a symbol must be without bars before we spend an SEC request asking
|
||||
# whether it delisted. Guards against a market-data outage probing the whole
|
||||
# universe at once; a real delisting is still stale days later.
|
||||
MIN_STALE_DAYS_BEFORE_PROBE = 3
|
||||
|
||||
|
||||
def _sec_client_factory():
|
||||
"""Build the SEC client for a delisting probe (patched in tests).
|
||||
|
||||
Imported lazily so the SEC/httpx stack stays off the import path of every
|
||||
module that only wants ``active_only``.
|
||||
"""
|
||||
from app.services.sec_client import SecClient
|
||||
|
||||
return SecClient()
|
||||
|
||||
|
||||
def active_only(stmt):
|
||||
"""Restrict a Ticker query to symbols that still trade.
|
||||
|
||||
Opt-in on purpose rather than folded into a shared getter: list and admin
|
||||
views deliberately keep delisted rows so the delisting is *visible*, which a
|
||||
silent default would undo. Apply this on the live signal path — scanning,
|
||||
ranking, scoring, breadth, ingestion — and nowhere else.
|
||||
"""
|
||||
return stmt.where(Ticker.delisted_on.is_(None))
|
||||
|
||||
|
||||
async def add_ticker(db: AsyncSession, symbol: str) -> Ticker:
|
||||
"""Add a new ticker after validation.
|
||||
@@ -52,6 +87,121 @@ async def delete_ticker(db: AsyncSession, symbol: str) -> None:
|
||||
|
||||
|
||||
async def list_tickers(db: AsyncSession) -> list[Ticker]:
|
||||
"""Return all tracked tickers sorted alphabetically by symbol."""
|
||||
"""Return all tracked tickers sorted alphabetically by symbol.
|
||||
|
||||
Delisted symbols are included and carry ``delisted_on`` — the registry is
|
||||
where an operator needs to *see* that a symbol retired, not where it should
|
||||
quietly disappear.
|
||||
"""
|
||||
result = await db.execute(select(Ticker).order_by(Ticker.symbol.asc()))
|
||||
return list(result.scalars().all())
|
||||
|
||||
|
||||
async def mark_delisted(
|
||||
db: AsyncSession,
|
||||
symbol: str,
|
||||
*,
|
||||
delisted_on: date,
|
||||
reason: str = REASON_MANUAL,
|
||||
) -> bool:
|
||||
"""Record that a symbol stopped trading. True if this changed anything.
|
||||
|
||||
Idempotent: re-marking an already-delisted symbol is a no-op, so the
|
||||
staleness path can call it on every run without churning the row or
|
||||
re-emitting events.
|
||||
"""
|
||||
normalised = symbol.strip().upper()
|
||||
result = await db.execute(select(Ticker).where(Ticker.symbol == normalised))
|
||||
ticker = result.scalar_one_or_none()
|
||||
if ticker is None:
|
||||
raise NotFoundError(f"Ticker not found: {normalised}")
|
||||
if ticker.delisted_on is not None:
|
||||
return False
|
||||
|
||||
await db.execute(
|
||||
update(Ticker)
|
||||
.where(Ticker.id == ticker.id)
|
||||
.values(delisted_on=delisted_on, delisted_reason=reason)
|
||||
)
|
||||
await db.commit()
|
||||
logger.info(
|
||||
"ticker %s marked delisted on %s (%s)", normalised, delisted_on, reason
|
||||
)
|
||||
return True
|
||||
|
||||
|
||||
async def confirm_delisting(
|
||||
db: AsyncSession,
|
||||
symbol: str,
|
||||
*,
|
||||
last_bar: date | None,
|
||||
today: date | None = None,
|
||||
) -> date | None:
|
||||
"""Ask SEC whether ``symbol`` actually delisted; mark it if so.
|
||||
|
||||
Called when OHLCV goes stale, because "no new bars" alone cannot tell a
|
||||
delisting from a halt or a rename. Returns the effective date when this call
|
||||
marked the symbol, else ``None`` — already-marked and unconfirmed both return
|
||||
``None``, so the caller keeps its existing alert for anything unproven.
|
||||
|
||||
Deliberately driven by staleness rather than by the SEC fundamentals import:
|
||||
that importer stalls for days at a time on unrelated Company-Facts gaps, and
|
||||
detection wired into it would stall with it.
|
||||
|
||||
The probe waits for ``MIN_STALE_DAYS_BEFORE_PROBE``. A delisted symbol stays
|
||||
stale forever, so the delay costs nothing, and it keeps a broad market-data
|
||||
outage — where every tracked symbol reports stale at once — from turning into
|
||||
one SEC request per symbol per run.
|
||||
"""
|
||||
from app.services.sec_client import SecError
|
||||
|
||||
normalised = symbol.strip().upper()
|
||||
result = await db.execute(select(Ticker).where(Ticker.symbol == normalised))
|
||||
ticker = result.scalar_one_or_none()
|
||||
if ticker is None or ticker.delisted_on is not None or not ticker.cik:
|
||||
return None
|
||||
# No bars at all is an ingestion problem, not evidence of a delisting.
|
||||
if last_bar is None:
|
||||
return None
|
||||
if ((today or date.today()) - last_bar).days < MIN_STALE_DAYS_BEFORE_PROBE:
|
||||
return None
|
||||
|
||||
try:
|
||||
async with _sec_client_factory() as client:
|
||||
filing = await client.delisting_filing(ticker.cik)
|
||||
except SecError:
|
||||
# Never let a probe failure escalate a routine staleness warning.
|
||||
logger.warning("delisting probe failed for %s", normalised, exc_info=True)
|
||||
return None
|
||||
|
||||
if filing is None:
|
||||
return None
|
||||
if await mark_delisted(
|
||||
db, normalised, delisted_on=filing["filing_date"], reason=REASON_FORM_25
|
||||
):
|
||||
return filing["filing_date"]
|
||||
return None
|
||||
|
||||
|
||||
async def clear_delisted(db: AsyncSession, symbol: str) -> bool:
|
||||
"""Un-retire a symbol. True if it had been marked.
|
||||
|
||||
The counterpart that makes automatic marking acceptable: a false positive
|
||||
costs one row update, where a delete would have cost the price history.
|
||||
"""
|
||||
normalised = symbol.strip().upper()
|
||||
result = await db.execute(select(Ticker).where(Ticker.symbol == normalised))
|
||||
ticker = result.scalar_one_or_none()
|
||||
if ticker is None:
|
||||
raise NotFoundError(f"Ticker not found: {normalised}")
|
||||
if ticker.delisted_on is None:
|
||||
return False
|
||||
|
||||
await db.execute(
|
||||
update(Ticker)
|
||||
.where(Ticker.id == ticker.id)
|
||||
.values(delisted_on=None, delisted_reason=None)
|
||||
)
|
||||
await db.commit()
|
||||
logger.info("ticker %s un-marked as delisted", normalised)
|
||||
return True
|
||||
|
||||
Reference in New Issue
Block a user