[verified] add frozen research runner and durable paper ledger

This commit is contained in:
Kunthawat Greethong
2026-08-23 14:42:02 +07:00
parent c9932954c2
commit f55ff69c31
19 changed files with 1063 additions and 33 deletions

View File

@@ -17,10 +17,11 @@ from .bot_tourism import BotTourismSource, TourismSourceError
from .event_study import EventStudyError, assess_backtest_readiness
from .paper import PaperLedger
from .prices import PriceSnapshotStore, PriceSourceError
from .research import ResearchRunError, ResearchRunStore, run_tourism_research
from .tourism import compute_tourism_signal
from .vintages import VintageStore, VintageStoreError
APP_VERSION = "0.4.0"
APP_VERSION = "0.5.0"
def _load_default_snapshot() -> dict[str, Any]:
@@ -47,6 +48,7 @@ def create_app(config: dict[str, Any] | None = None) -> Flask:
PAPER_WRITE_TOKEN=os.getenv("PAPER_WRITE_TOKEN", ""),
PAPER_COOKIE_SECURE=os.getenv("PAPER_COOKIE_SECURE", "0") == "1",
PAPER_SESSION_SECONDS=int(os.getenv("PAPER_SESSION_SECONDS", "3600")),
PAPER_LEDGER_PATH=Path(os.getenv("PAPER_LEDGER_PATH", str(data_root / "paper" / "ledger.json"))),
TOURISM_SOURCE=os.getenv("TOURISM_SOURCE", "fixture"),
TOURISM_ADAPTER=None,
TOURISM_DATA_ROOT=Path(os.getenv("TOURISM_DATA_ROOT", str(data_root))),
@@ -55,6 +57,8 @@ def create_app(config: dict[str, Any] | None = None) -> Flask:
VINTAGE_STORE=None,
PRICE_DATA_ROOT=Path(os.getenv("PRICE_DATA_ROOT", str(data_root / "prices"))),
PRICE_STORE=None,
RESEARCH_DATA_ROOT=Path(os.getenv("RESEARCH_DATA_ROOT", str(data_root / "research"))),
RESEARCH_RUN_STORE=None,
SNAPSHOT=_load_default_snapshot(),
)
if config:
@@ -64,6 +68,8 @@ def create_app(config: dict[str, Any] | None = None) -> Flask:
app.extensions["vintage_store"] = vintage_store
price_store = app.config.get("PRICE_STORE") or PriceSnapshotStore(app.config["PRICE_DATA_ROOT"])
app.extensions["price_store"] = price_store
research_run_store = app.config.get("RESEARCH_RUN_STORE") or ResearchRunStore(app.config["RESEARCH_DATA_ROOT"])
app.extensions["research_run_store"] = research_run_store
source_snapshot = app.config["SNAPSHOT"]
source_mode = str(app.config["TOURISM_SOURCE"]).lower()
if source_mode == "bot":
@@ -76,7 +82,10 @@ def create_app(config: dict[str, Any] | None = None) -> Flask:
raise ValueError(f"unsupported TOURISM_SOURCE: {source_mode}")
result = compute_tourism_signal(source_snapshot)
ledger = PaperLedger()
ledger_path = app.config["PAPER_LEDGER_PATH"]
if app.config["TESTING"] and (not config or "PAPER_LEDGER_PATH" not in config):
ledger_path = None
ledger = PaperLedger(ledger_path)
paper_sessions: dict[str, float] = {}
allowed_symbols = {item["symbol"] for item in result["signals"]}
app.extensions["tourism_result"] = result
@@ -176,6 +185,35 @@ def create_app(config: dict[str, Any] | None = None) -> Flask:
def prices_health():
return jsonify(_price_health_payload())
@app.post("/api/v1/research/tourism/run")
def run_tourism_research_endpoint():
payload = request.get_json(silent=True) or {}
if not isinstance(payload, dict):
return jsonify({"error": "JSON object required"}), 400
try:
report = run_tourism_research(
app.extensions["vintage_store"],
app.extensions["price_store"],
app.extensions["research_run_store"],
min_events=payload.get("min_events", 12),
windows=payload.get("windows", (1, 3, 5, 20)),
cost_bps=payload.get("cost_bps", 20.0),
execution_lag_sessions=payload.get("execution_lag_sessions", 1),
)
except (ResearchRunError, TypeError, ValueError) as exc:
return jsonify({"error": str(exc)}), 400
return jsonify(report)
@app.get("/api/v1/research/tourism/latest")
def latest_tourism_research():
try:
report = app.extensions["research_run_store"].latest()
except FileNotFoundError:
return jsonify({"error": "no research runs"}), 404
except ResearchRunError as exc:
return jsonify({"error": str(exc)}), 422
return jsonify(report)
@app.get("/api/v1/data-health")
def data_health():
current = app.extensions["tourism_result"]

View File

@@ -24,12 +24,30 @@ def _parse_date(value: str) -> date:
raise EventStudyError("date must be ISO-8601") from exc
def _canonical_timestamp(value: str) -> str:
try:
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
except (TypeError, ValueError):
return value
if parsed.tzinfo is None:
parsed = parsed.replace(tzinfo=timezone.utc)
return parsed.astimezone(timezone.utc).isoformat()
def assess_backtest_readiness(vintages: Sequence[Mapping[str, Any]], min_events: int = 12) -> dict[str, Any]:
if min_events < 1:
if isinstance(min_events, bool) or min_events < 1:
raise EventStudyError("min_events must be positive")
ids = {str(item.get("vintage_id") or item.get("event_id") or "") for item in vintages}
ids.discard("")
available = len(ids)
independent_keys: set[tuple[str, str, str]] = set()
for item in vintages:
source_id = str(item.get("source_id") or "")
published_at = _canonical_timestamp(str(item.get("published_at") or ""))
if source_id and published_at:
independent_keys.add(("release", source_id, published_at))
continue
identifier = str(item.get("vintage_id") or item.get("event_id") or "")
if identifier:
independent_keys.add(("id", identifier, ""))
available = len(independent_keys)
if available < min_events:
return {
"status": "blocked",
@@ -63,12 +81,18 @@ def _price_map(symbol: str, rows: Sequence[Mapping[str, Any]]) -> dict[date, flo
return dict(sorted(values.items()))
def _window_return(series: dict[date, float], event_date: date, window: int, symbol: str) -> float:
def _window_return(series: dict[date, float], event_date: date, window: int, symbol: str, execution_lag_sessions: int) -> float:
dates = list(series)
anchor_candidates = [index for index, trading_day in enumerate(dates) if trading_day >= event_date]
if not anchor_candidates:
raise EventStudyError(f"missing post-event prices for {symbol}")
anchor = anchor_candidates[0]
first_session = anchor_candidates[0]
if execution_lag_sessions == 0:
anchor = first_session
elif dates[first_session] > event_date:
anchor = first_session + execution_lag_sessions - 1
else:
anchor = first_session + execution_lag_sessions
end = anchor + window
if end >= len(dates):
raise EventStudyError(f"insufficient price history for {symbol} window {window}")
@@ -83,6 +107,7 @@ def run_event_study(
windows: Sequence[int] = (1, 3, 5, 20),
cost_bps: float = 0.0,
min_events: int = 12,
execution_lag_sessions: int = 1,
) -> dict[str, Any]:
"""Calculate weighted post-publication returns from point-in-time events."""
@@ -93,6 +118,9 @@ def run_event_study(
)
if not windows or any(isinstance(window, bool) or int(window) != window or window <= 0 for window in windows):
raise EventStudyError("windows must contain positive integers")
if isinstance(execution_lag_sessions, bool) or int(execution_lag_sessions) != execution_lag_sessions or execution_lag_sessions < 0:
raise EventStudyError("execution_lag_sessions must be a non-negative integer")
execution_lag_sessions = int(execution_lag_sessions)
try:
cost_bps = float(cost_bps)
except (TypeError, ValueError) as exc:
@@ -133,13 +161,13 @@ def run_event_study(
raise EventStudyError(f"invalid target weight for {symbol}")
if symbol not in normalized_prices:
raise EventStudyError(f"missing prices for {symbol}")
gross += weight * _window_return(normalized_prices[symbol], event["event_date"], int(window), symbol)
gross += weight * _window_return(normalized_prices[symbol], event["event_date"], int(window), symbol, execution_lag_sessions)
turnover += abs(weight)
cost = turnover * cost_bps / 10000.0
gross_returns.append(gross)
net_returns.append(gross - cost)
if normalized_benchmark is not None:
benchmark_returns.append(_window_return(normalized_benchmark, event["event_date"], int(window), "benchmark"))
benchmark_returns.append(_window_return(normalized_benchmark, event["event_date"], int(window), "benchmark", execution_lag_sessions))
average_gross = fmean(gross_returns)
average_net = fmean(net_returns)
average_benchmark = fmean(benchmark_returns) if benchmark_returns else None
@@ -152,6 +180,7 @@ def run_event_study(
"active_return": round(average_net - average_benchmark, 8) if average_benchmark is not None else None,
"hit_rate": round(sum(value > 0 for value in net_returns) / len(net_returns), 8),
"cost_bps": cost_bps,
"execution_lag_sessions": execution_lag_sessions,
"event_returns": [round(value, 8) for value in net_returns],
}

View File

@@ -2,14 +2,48 @@
from __future__ import annotations
import json
from copy import deepcopy
from datetime import datetime, timezone
from math import isfinite
from pathlib import Path
from uuid import uuid4
PAPER_LEDGER_SCHEMA_VERSION = 1
class PaperLedgerError(ValueError):
"""Raised when a persistent paper ledger is invalid or unreadable."""
class PaperLedger:
def __init__(self) -> None:
def __init__(self, path: Path | str | None = None) -> None:
self.path = Path(path).resolve() if path else None
self._entries: list[dict] = []
if self.path and self.path.is_file():
self._entries = self._load()
def _load(self) -> list[dict]:
if self.path is None:
raise PaperLedgerError("paper ledger path is not configured")
try:
payload = json.loads(self.path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError) as exc:
raise PaperLedgerError("paper ledger is unreadable") from exc
if not isinstance(payload, dict) or payload.get("schema_version") != PAPER_LEDGER_SCHEMA_VERSION or not isinstance(payload.get("entries"), list):
raise PaperLedgerError("unsupported paper ledger schema")
if not all(isinstance(entry, dict) for entry in payload["entries"]):
raise PaperLedgerError("paper ledger entries are invalid")
return deepcopy(payload["entries"])
def _persist(self, entries: list[dict]) -> None:
if not self.path:
return
self.path.parent.mkdir(parents=True, exist_ok=True)
payload = {"schema_version": PAPER_LEDGER_SCHEMA_VERSION, "entries": entries}
temporary = self.path.with_name(f".{self.path.name}.tmp")
temporary.write_text(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True) + "\n", encoding="utf-8")
temporary.replace(self.path)
def record(self, payload: dict, allowed_symbols: set[str]) -> dict:
symbol = str(payload.get("symbol", "")).strip().upper()
@@ -34,8 +68,10 @@ class PaperLedger:
"assumed_price": assumed_price,
"status": "PAPER_RECORDED",
}
self._entries.append(entry)
return entry
candidate_entries = [*self._entries, entry]
self._persist(candidate_entries)
self._entries = candidate_entries
return deepcopy(entry)
def entries(self) -> list[dict]:
return list(self._entries)
return deepcopy(self._entries)

View File

@@ -230,6 +230,55 @@ class PriceSnapshotStore:
raise PriceSourceError("unsupported price manifest schema")
return manifest
def _snapshot_path(self, snapshot_id: str) -> Path:
if not re.fullmatch(r"[A-Za-z0-9][A-Za-z0-9._-]{0,127}", snapshot_id):
raise PriceSourceError("invalid price snapshot id")
candidate = (self.snapshot_dir / f"{snapshot_id}.json").resolve()
if candidate.parent != self.snapshot_dir.resolve():
raise PriceSourceError("price snapshot path escaped store root")
return candidate
def load_snapshot(self, snapshot_id: str) -> dict[str, Any]:
snapshot_path = self._snapshot_path(snapshot_id)
if not snapshot_path.is_file():
raise FileNotFoundError(snapshot_id)
try:
snapshot = json.loads(snapshot_path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError) as exc:
raise PriceSourceError("price snapshot is unreadable") from exc
source = snapshot.get("source")
if not isinstance(source, dict) or source.get("snapshot_id") != snapshot_id:
raise PriceSourceError("price snapshot identity mismatch")
raw_files = source.get("raw_payload_files")
if not isinstance(raw_files, dict) or not raw_files:
raise PriceSourceError("price snapshot raw payload manifest is missing")
raw_payloads: dict[str, bytes] = {}
raw_root = (self.raw_dir / snapshot_id).resolve()
if raw_root.parent != self.raw_dir.resolve():
raise PriceSourceError("price raw path escaped store root")
for provider_symbol, filename in raw_files.items():
if _raw_filename(str(provider_symbol)) != filename:
raise PriceSourceError("price raw filename mismatch")
raw_path = (raw_root / filename).resolve()
if raw_path.parent != raw_root or not raw_path.is_file():
raise PriceSourceError("price raw payload is missing")
raw_payloads[str(provider_symbol)] = raw_path.read_bytes()
actual_hash = _combined_hash(raw_payloads)
if actual_hash != source.get("raw_payload_hash"):
raise PriceSourceError("price raw payload hash mismatch")
manifest_entry = self.load_manifest().get("snapshots", {}).get(snapshot_id)
if isinstance(manifest_entry, dict) and manifest_entry.get("raw_payload_hash") != actual_hash:
raise PriceSourceError("price manifest hash mismatch")
return snapshot
def list_snapshots(self) -> list[dict[str, Any]]:
entries = list(self.load_manifest().get("snapshots", {}).values())
return sorted(entries, key=lambda item: (str(item.get("retrieved_at", "")), str(item.get("snapshot_id", ""))))
def latest_snapshot_entry(self) -> dict[str, Any] | None:
entries = self.list_snapshots()
return entries[-1] if entries else None
def persist(self, snapshot: dict[str, Any], raw_payloads: Mapping[str, bytes]) -> dict[str, Any]:
source = snapshot.get("source")
if not isinstance(source, dict) or not source.get("snapshot_id"):
@@ -258,8 +307,11 @@ class PriceSnapshotStore:
"period_start": stored_source.get("period_start"),
"period_end": stored_source.get("period_end"),
"raw_payload_hash": raw_hash,
"parser_version": stored_source.get("parser_version"),
"quality": stored_source.get("quality"),
"point_in_time": stored_source.get("point_in_time"),
"adjusted_prices": stored_source.get("adjusted_prices"),
"return_price_field": stored_source.get("return_price_field"),
"symbols": sorted(stored.get("series", {}).keys()),
"snapshot_file": stored_source["snapshot_file"],
}
@@ -299,6 +351,7 @@ def collect_price_snapshot(
"quality": "revised_vendor_history",
"point_in_time": False,
"adjusted_prices": True,
"return_price_field": "close",
"snapshot_id": snapshot_id,
"bar_counts": {symbol: len(series["bars"]) for symbol, series in normalized.items()},
}

296
backend/app/research.py Normal file
View File

@@ -0,0 +1,296 @@
"""Frozen, replayable Tourism research runs.
A run either produces a deterministic event-study result from point-in-time
inputs or persists a blocked report explaining the exact missing gate. It never
falls back to revised vendor history.
"""
from __future__ import annotations
import copy
import hashlib
import json
import math
import re
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Mapping, Sequence
from .event_study import EventStudyError, _canonical_timestamp, assess_backtest_readiness, run_event_study
from .prices import PriceSnapshotStore, PriceSourceError
from .tourism import compute_tourism_signal
from .vintages import VintageStore, VintageStoreError
RUN_SCHEMA_VERSION = 1
_RUN_ID_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9._-]{0,127}")
class ResearchRunError(ValueError):
"""Raised when a research run cannot be safely created or replayed."""
def _canonical_hash(payload: Mapping[str, Any]) -> str:
encoded = json.dumps(payload, ensure_ascii=False, sort_keys=True, separators=(",", ":")).encode("utf-8")
return hashlib.sha256(encoded).hexdigest()
def _atomic_write(path: Path, payload: Mapping[str, Any]) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
temporary = path.with_name(f".{path.name}.tmp")
temporary.write_text(json.dumps(payload, ensure_ascii=False, indent=2, sort_keys=True) + "\n", encoding="utf-8")
temporary.replace(path)
class ResearchRunStore:
"""Immutable JSON reports with a compact run manifest."""
def __init__(self, root: Path | str) -> None:
self.root = Path(root).resolve()
self.report_dir = self.root / "reports"
self.manifest_path = self.root / "manifest.json"
def load_manifest(self) -> dict[str, Any]:
if not self.manifest_path.is_file():
return {"schema_version": RUN_SCHEMA_VERSION, "runs": {}}
try:
manifest = json.loads(self.manifest_path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError) as exc:
raise ResearchRunError("research run manifest is unreadable") from exc
if manifest.get("schema_version") != RUN_SCHEMA_VERSION or not isinstance(manifest.get("runs"), dict):
raise ResearchRunError("unsupported research run manifest schema")
return manifest
def _report_path(self, run_id: str) -> Path:
if not _RUN_ID_RE.fullmatch(run_id):
raise ResearchRunError("invalid research run id")
candidate = (self.report_dir / f"{run_id}.json").resolve()
if candidate.parent != self.report_dir.resolve():
raise ResearchRunError("research report path escaped store root")
return candidate
def load(self, run_id: str) -> dict[str, Any]:
path = self._report_path(run_id)
if not path.is_file():
raise FileNotFoundError(run_id)
try:
report = json.loads(path.read_text(encoding="utf-8"))
except (OSError, json.JSONDecodeError) as exc:
raise ResearchRunError("research report is unreadable") from exc
if report.get("run_id") != run_id or report.get("schema_version") != RUN_SCHEMA_VERSION:
raise ResearchRunError("research report identity mismatch")
return report
def persist(self, report: dict[str, Any]) -> dict[str, Any]:
run_id = str(report.get("run_id", ""))
path = self._report_path(run_id)
manifest = self.load_manifest()
existing = manifest["runs"].get(run_id)
if existing:
stored = self.load(run_id)
if stored != report:
raise ResearchRunError("research run id already contains a different report")
return stored
stored = copy.deepcopy(report)
_atomic_write(path, stored)
manifest["runs"][run_id] = {
"run_id": run_id,
"status": stored.get("status"),
"reason": stored.get("reason"),
"generated_at": stored.get("generated_at"),
"report_file": path.name,
}
_atomic_write(self.manifest_path, manifest)
return stored
def latest(self) -> dict[str, Any]:
entries = list(self.load_manifest().get("runs", {}).values())
if not entries:
raise FileNotFoundError("no research runs")
latest = max(entries, key=lambda item: (str(item.get("generated_at", "")), str(item.get("run_id", ""))))
return self.load(str(latest["run_id"]))
def list_runs(self) -> list[dict[str, Any]]:
entries = list(self.load_manifest().get("runs", {}).values())
return sorted(entries, key=lambda item: (str(item.get("generated_at", "")), str(item.get("run_id", ""))), reverse=True)
def _validate_config(windows: Sequence[int], cost_bps: float, min_events: int, execution_lag_sessions: int) -> tuple[list[int], float, int, int]:
if not windows or any(isinstance(window, bool) or int(window) != window or int(window) <= 0 for window in windows):
raise ResearchRunError("windows must contain positive integers")
try:
parsed_cost = float(cost_bps)
except (TypeError, ValueError) as exc:
raise ResearchRunError("cost_bps must be finite and non-negative") from exc
if not math.isfinite(parsed_cost) or parsed_cost < 0:
raise ResearchRunError("cost_bps must be finite and non-negative")
if isinstance(min_events, bool) or int(min_events) != min_events or int(min_events) < 1:
raise ResearchRunError("min_events must be positive")
if isinstance(execution_lag_sessions, bool) or int(execution_lag_sessions) != execution_lag_sessions or int(execution_lag_sessions) < 0:
raise ResearchRunError("execution_lag_sessions must be a non-negative integer")
return [int(window) for window in windows], parsed_cost, int(min_events), int(execution_lag_sessions)
def _price_gate(price_entry: Mapping[str, Any] | None) -> dict[str, Any]:
if not price_entry:
return {"status": "blocked", "reason": "price_snapshot_missing", "snapshot_count": 0}
if not bool(price_entry.get("point_in_time")):
return {
"status": "blocked",
"reason": "price_series_not_point_in_time",
"snapshot_id": price_entry.get("snapshot_id"),
"quality": price_entry.get("quality"),
"point_in_time": False,
}
return {
"status": "ready",
"reason": None,
"snapshot_id": price_entry.get("snapshot_id"),
"quality": price_entry.get("quality"),
"point_in_time": True,
}
def _revision_key(entry: Mapping[str, Any]) -> tuple[str, str, str]:
source_id = str(entry.get("source_id") or "")
published_at = _canonical_timestamp(str(entry.get("published_at") or ""))
if source_id and published_at:
return ("release", source_id, published_at)
return ("id", str(entry.get("vintage_id") or ""), "")
def _select_independent_vintages(entries: Sequence[Mapping[str, Any]]) -> list[dict[str, Any]]:
selected: dict[tuple[str, str, str], dict[str, Any]] = {}
for raw_entry in entries:
entry = dict(raw_entry)
key = _revision_key(entry)
current = selected.get(key)
candidate_rank = (str(entry.get("first_seen_at", "")), str(entry.get("last_seen_at", "")), str(entry.get("vintage_id", "")))
current_rank = (str(current.get("first_seen_at", "")), str(current.get("last_seen_at", "")), str(current.get("vintage_id", ""))) if current else ("", "", "")
if current is None or candidate_rank > current_rank:
selected[key] = entry
return sorted(selected.values(), key=lambda item: (str(item.get("published_at", "")), str(item.get("vintage_id", ""))))
def _series_rows(series: Mapping[str, Any], price_field: str, symbol: str) -> list[dict[str, Any]]:
bars = series.get("bars")
if not isinstance(bars, list) or not bars:
raise ResearchRunError(f"missing price bars for {symbol}")
rows: list[dict[str, Any]] = []
for bar in bars:
if not isinstance(bar, dict) or price_field not in bar:
raise ResearchRunError(f"price field {price_field} missing for {symbol}")
rows.append({"date": bar.get("date"), "close": bar.get(price_field)})
return rows
def run_tourism_research(
vintage_store: VintageStore,
price_store: PriceSnapshotStore,
run_store: ResearchRunStore,
*,
min_events: int = 12,
windows: Sequence[int] = (1, 3, 5, 20),
cost_bps: float = 20.0,
execution_lag_sessions: int = 1,
) -> dict[str, Any]:
windows, cost_bps, min_events, execution_lag_sessions = _validate_config(windows, cost_bps, min_events, execution_lag_sessions)
try:
vintages = _select_independent_vintages(vintage_store.list_vintages())
price_entry = price_store.latest_snapshot_entry()
except (VintageStoreError, PriceSourceError) as exc:
raise ResearchRunError(str(exc)) from exc
vintage_gate = assess_backtest_readiness(vintages, min_events=min_events)
price_gate = _price_gate(price_entry)
input_vintages = [
{
"vintage_id": entry.get("vintage_id"),
"source_id": entry.get("source_id"),
"as_of": entry.get("as_of"),
"published_at": entry.get("published_at"),
"raw_payload_hash": entry.get("raw_payload_hash"),
"parser_version": entry.get("parser_version"),
"revision_status": entry.get("revision_status"),
}
for entry in vintages
]
input_price = copy.deepcopy(price_entry) if price_entry else None
config = {
"min_events": min_events,
"windows": windows,
"cost_bps": cost_bps,
"execution_lag_sessions": execution_lag_sessions,
}
input_fingerprint = _canonical_hash({"theme": "tourism", "config": config, "vintages": input_vintages, "price_snapshot": input_price})
run_id = f"tourism-run-{input_fingerprint[:16]}"
try:
return run_store.load(run_id)
except FileNotFoundError:
pass
generated_at = datetime.now(timezone.utc).isoformat()
report: dict[str, Any] = {
"schema_version": RUN_SCHEMA_VERSION,
"run_id": run_id,
"theme": "tourism",
"status": "blocked",
"reason": None,
"generated_at": generated_at,
"config": config,
"gates": {"vintages": vintage_gate, "prices": price_gate},
"inputs": {"vintages": input_vintages, "price_snapshot": input_price},
}
if vintage_gate["status"] != "ready":
report["reason"] = vintage_gate["reason"]
return run_store.persist(report)
if price_gate["status"] != "ready":
report["reason"] = price_gate["reason"]
return run_store.persist(report)
if not price_entry:
raise ResearchRunError("price snapshot disappeared after readiness check")
try:
price_snapshot = price_store.load_snapshot(str(price_entry["snapshot_id"]))
except (FileNotFoundError, PriceSourceError) as exc:
report["reason"] = "price_snapshot_unreadable"
report["gates"]["prices"] = {**price_gate, "status": "blocked", "reason": report["reason"], "error": str(exc)}
return run_store.persist(report)
price_source = price_snapshot.get("source", {})
price_field = str(price_source.get("return_price_field", "close"))
series = price_snapshot.get("series")
if not isinstance(series, dict):
report["reason"] = "price_snapshot_invalid"
return run_store.persist(report)
events: list[dict[str, Any]] = []
try:
for entry in vintages:
snapshot = vintage_store.load_snapshot(str(entry["vintage_id"]))
result = compute_tourism_signal(snapshot)
events.append({
"event_id": entry["vintage_id"],
"published_at": snapshot["source"]["published_at"],
"signals": result["signals"],
})
price_rows = {symbol: _series_rows(value, price_field, symbol) for symbol, value in series.items() if symbol != price_snapshot.get("benchmark_symbol")}
benchmark_symbol = price_snapshot.get("benchmark_symbol")
benchmark_rows = _series_rows(series[benchmark_symbol], price_field, str(benchmark_symbol)) if benchmark_symbol else None
result = run_event_study(
events,
price_rows,
benchmark_prices=benchmark_rows,
windows=windows,
cost_bps=cost_bps,
min_events=min_events,
execution_lag_sessions=execution_lag_sessions,
)
except (FileNotFoundError, VintageStoreError, EventStudyError, ResearchRunError, KeyError, TypeError, ValueError) as exc:
report["reason"] = "research_inputs_invalid"
report["error"] = str(exc)
return run_store.persist(report)
report["status"] = "ready"
report["reason"] = None
report["result"] = result
report["input_summary"] = {
"event_count": len(events),
"price_symbols": sorted(price_rows),
"benchmark_symbol": benchmark_symbol,
"return_price_field": price_field,
}
return run_store.persist(report)

View File

@@ -116,7 +116,7 @@ class VintageStore:
existing = manifest["vintages"].get(vintage_id)
same_release = any(
item.get("source_id") == source.get("source_id")
and item.get("published_at") == published_at
and _parse_timestamp(str(item.get("published_at"))) == _parse_timestamp(published_at)
and item.get("vintage_id") != vintage_id
for item in manifest["vintages"].values()
)