You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

653 lines
28 KiB
Python

"""Integration tests for the full backtest pipeline (no DB/HTTP — uses SnapshotStore directly)."""
from __future__ import annotations
import datetime as dt
from pathlib import Path
from zoneinfo import ZoneInfo
import pytest
_UTC = ZoneInfo("UTC")
def _build_synthetic_store() -> object:
"""Build a SnapshotStore with synthetic data for end-to-end testing."""
from libs.backtest.snapshot_store import SnapshotStore
# 5 trading days, 2 symbols
dates = [dt.date(2026, 1, d) for d in [5, 6, 7, 8, 9]]
candidates = {
dt.date(2026, 1, 5): [
{
"event_id": "EVT::001",
"symbol": "AAPL",
"execution_date": dt.date(2026, 1, 5),
"entry_date": "2026-01-05",
"entry_price": 150.0,
"score": 0.85,
"sector": "Technology",
"event_type": "earnings",
"event_timestamp": "2026-01-02T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-02",
"avg_dollar_volume": 5_000_000.0,
"atr_14": 3.0,
},
],
dt.date(2026, 1, 6): [
{
"event_id": "EVT::002",
"symbol": "MSFT",
"execution_date": dt.date(2026, 1, 6),
"entry_date": "2026-01-06",
"entry_price": 300.0,
"score": 0.70,
"sector": "Technology",
"event_type": "guidance",
"event_timestamp": "2026-01-05T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-05",
"avg_dollar_volume": 10_000_000.0,
"atr_14": 5.0,
},
],
}
bars = {
"AAPL": {
dt.date(2026, 1, 5): {"date": dt.date(2026, 1, 5), "open": 150.0, "high": 160.0, "low": 148.0, "close": 158.0, "volume": 1_000_000},
dt.date(2026, 1, 6): {"date": dt.date(2026, 1, 6), "open": 158.0, "high": 170.0, "low": 155.0, "close": 165.0, "volume": 900_000},
dt.date(2026, 1, 7): {"date": dt.date(2026, 1, 7), "open": 165.0, "high": 175.0, "low": 160.0, "close": 170.0, "volume": 800_000},
dt.date(2026, 1, 8): {"date": dt.date(2026, 1, 8), "open": 170.0, "high": 180.0, "low": 165.0, "close": 175.0, "volume": 750_000},
dt.date(2026, 1, 9): {"date": dt.date(2026, 1, 9), "open": 175.0, "high": 185.0, "low": 170.0, "close": 180.0, "volume": 700_000},
},
"MSFT": {
dt.date(2026, 1, 6): {"date": dt.date(2026, 1, 6), "open": 300.0, "high": 305.0, "low": 280.0, "close": 282.0, "volume": 500_000},
dt.date(2026, 1, 7): {"date": dt.date(2026, 1, 7), "open": 282.0, "high": 290.0, "low": 270.0, "close": 272.0, "volume": 480_000},
dt.date(2026, 1, 8): {"date": dt.date(2026, 1, 8), "open": 272.0, "high": 280.0, "low": 260.0, "close": 265.0, "volume": 450_000},
dt.date(2026, 1, 9): {"date": dt.date(2026, 1, 9), "open": 265.0, "high": 270.0, "low": 255.0, "close": 258.0, "volume": 420_000},
},
}
return SnapshotStore(
candidates_by_exec_date=candidates,
bars_by_symbol_date=bars,
)
def _build_multi_engine_store() -> object:
from libs.backtest.snapshot_store import SnapshotStore
candidates = {
dt.date(2026, 1, 7): [
{
"event_id": "EVT::SD::SHORT",
"symbol": "NFLX",
"execution_date": dt.date(2026, 1, 7),
"entry_date": "2026-01-07",
"event_date": "2026-01-06",
"event_close": 400.0,
"entry_price": 399.0,
"score": 0.90,
"sector": "Communication Services",
"event_type": "earnings_release",
"event_timestamp": "2026-01-06T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-06",
"reaction_day_return": -0.12,
"avg_dollar_volume": 8_000_000.0,
"atr_14": 4.0,
},
{
"event_id": "EVT::AC::LONG",
"symbol": "AMD",
"execution_date": dt.date(2026, 1, 7),
"entry_date": "2026-01-07",
"event_date": "2026-01-06",
"event_close": 122.0,
"entry_price": 123.0,
"score": 0.88,
"sector": "Technology",
"event_type": "earnings_release",
"event_timestamp": "2026-01-06T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-07",
"reaction_day_return": 0.14,
"avg_dollar_volume": 9_000_000.0,
"atr_14": 3.0,
},
],
}
bars = {
"NFLX": {
dt.date(2026, 1, 6): {"date": dt.date(2026, 1, 6), "open": 395.0, "high": 405.0, "low": 390.0, "close": 400.0, "volume": 1_200_000},
dt.date(2026, 1, 7): {"date": dt.date(2026, 1, 7), "open": 390.0, "high": 392.0, "low": 380.0, "close": 382.0, "volume": 1_100_000},
dt.date(2026, 1, 8): {"date": dt.date(2026, 1, 8), "open": 382.0, "high": 384.0, "low": 370.0, "close": 372.0, "volume": 1_000_000},
},
"AMD": {
dt.date(2026, 1, 7): {"date": dt.date(2026, 1, 7), "open": 123.0, "high": 130.0, "low": 122.0, "close": 129.0, "volume": 1_500_000},
dt.date(2026, 1, 8): {"date": dt.date(2026, 1, 8), "open": 129.0, "high": 135.0, "low": 128.0, "close": 134.0, "volume": 1_300_000},
dt.date(2026, 1, 9): {"date": dt.date(2026, 1, 9), "open": 134.0, "high": 138.0, "low": 133.0, "close": 137.0, "volume": 1_250_000},
},
}
return SnapshotStore(candidates_by_exec_date=candidates, bars_by_symbol_date=bars)
def _make_config(strategy_engines=None):
from libs.backtest.domain import (
BacktestConfig,
ExecutionConfig,
ReportingConfig,
RiskConfig,
SignalConfig,
UniverseConfig,
)
return BacktestConfig(
strategy_name="test_strategy",
dataset_snapshot_id="test_snapshot",
universe=UniverseConfig(min_price=5.0, min_avg_dollar_volume=100_000),
signal=SignalConfig(score_threshold=0.5, max_candidates_per_day=5),
risk=RiskConfig(
per_trade_risk_pct=0.01,
max_daily_new_risk_pct=0.05,
max_positions=10,
max_positions_per_sector=5,
),
execution=ExecutionConfig(
entry_fill_model="next_open",
exit_fill_model="daily_bar_approximation",
slippage_bps_base=10.0,
commission_per_share=0.005,
same_bar_priority="stop_first_conservative",
max_holding_days=10,
),
reporting=ReportingConfig(
write_trade_blotter=True,
write_equity_curve=True,
write_metrics_summary=True,
generate_plots=False,
),
strategy_engines=strategy_engines or [],
)
@pytest.mark.integration
class TestBacktestRunIntegration:
def test_run_completes(self, tmp_path):
"""Full run completes without error."""
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest
store = _build_synthetic_store()
manifest = ExperimentManifest(
experiment_name="test_exp",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
)
config = _make_config()
runner = BacktestRunner(manifest=manifest, config=config, store=store, initial_equity=100_000.0)
result = runner.run(output_root=tmp_path)
assert result.run_id.startswith("bt_")
assert result.total_trading_days >= 0
assert result.metrics.trade_count >= 0
def test_output_files_created(self, tmp_path):
"""All expected output files are written."""
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest
store = _build_synthetic_store()
manifest = ExperimentManifest(
experiment_name="test_exp",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
)
config = _make_config()
runner = BacktestRunner(manifest=manifest, config=config, store=store, initial_equity=100_000.0)
result = runner.run(output_root=tmp_path)
run_dir = tmp_path / result.run_id
assert run_dir.exists()
assert (run_dir / "metadata.json").exists()
assert (run_dir / "manifest.json").exists()
assert (run_dir / "resolved_config.json").exists()
assert (run_dir / "metrics" / "metrics_summary.json").exists()
assert (run_dir / "plots").exists() # empty dir
def test_equity_curve_has_all_days(self, tmp_path):
"""Equity curve has one entry per candidate date."""
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest
store = _build_synthetic_store()
manifest = ExperimentManifest(
experiment_name="test_exp",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
)
config = _make_config()
runner = BacktestRunner(manifest=manifest, config=config, store=store)
result = runner.run()
# Should have simulated days covering the range (all_trading_days between
# first and last execution date), plus the initial equity state
assert result.total_trading_days >= 2
def test_deterministic_results(self, tmp_path):
"""Two runs with same inputs produce identical metrics."""
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest
manifest = ExperimentManifest(
experiment_name="test_exp",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
)
config = _make_config()
store1 = _build_synthetic_store()
runner1 = BacktestRunner(manifest=manifest, config=config, store=store1)
result1 = runner1.run()
store2 = _build_synthetic_store()
runner2 = BacktestRunner(manifest=manifest, config=config, store=store2)
result2 = runner2.run()
assert result1.metrics.trade_count == result2.metrics.trade_count
assert result1.metrics.win_rate == result2.metrics.win_rate
assert result1.metrics.total_return_pct == result2.metrics.total_return_pct
assert result1.total_candidates_seen == result2.total_candidates_seen
assert result1.total_orders_rejected == result2.total_orders_rejected
def test_no_future_data_used(self, tmp_path):
"""Candidates for day D should not appear in a simulation of day D-1."""
from libs.backtest.snapshot_store import SnapshotStore
candidates = {
dt.date(2026, 1, 5): [
{
"event_id": "EVT::001",
"symbol": "AAPL",
"execution_date": dt.date(2026, 1, 5),
"entry_date": "2026-01-05",
"entry_price": 150.0,
"score": 0.85,
"sector": "Technology",
"event_type": "earnings",
"event_timestamp": "2026-01-02T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-02",
"avg_dollar_volume": 5_000_000.0,
"atr_14": 3.0,
}
],
dt.date(2026, 1, 6): [
{
"event_id": "EVT::FUTURE",
"symbol": "FUTURE_TICKER",
"execution_date": dt.date(2026, 1, 6),
"entry_date": "2026-01-06",
"entry_price": 50.0,
"score": 0.99,
"sector": "Technology",
"event_type": "earnings",
"event_timestamp": "2026-01-05T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-05",
"avg_dollar_volume": 1_000_000.0,
"atr_14": 1.0,
}
],
}
bars = {
"AAPL": {dt.date(2026, 1, 5): {"date": dt.date(2026, 1, 5), "open": 150.0, "high": 160.0, "low": 148.0, "close": 158.0, "volume": 1_000_000}},
"FUTURE_TICKER": {dt.date(2026, 1, 6): {"date": dt.date(2026, 1, 6), "open": 50.0, "high": 55.0, "low": 48.0, "close": 52.0, "volume": 500_000}},
}
store = SnapshotStore(candidates_by_exec_date=candidates, bars_by_symbol_date=bars)
# Querying Jan 5 should NOT return FUTURE_TICKER candidate
rows = store.get_candidates_for_date(dt.date(2026, 1, 5))
symbols = [r["symbol"] for r in rows]
assert "FUTURE_TICKER" not in symbols
assert "AAPL" in symbols
def test_multi_engine_run_writes_per_engine_metrics(self, tmp_path):
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest, StrategyEngineConfig
import json
import pyarrow.parquet as pq
store = _build_multi_engine_store()
manifest = ExperimentManifest(
experiment_name="portfolio_v2",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
strategy_engines=[
StrategyEngineConfig(
engine_id="earnings_same_day_short_v1",
event_types=["earnings_release"],
timing_class="same_day",
direction="short_only",
entry_timing_policy="next_open",
max_holding_days=3,
engine_risk_budget_pct=0.40,
),
StrategyEngineConfig(
engine_id="earnings_after_close_long_v1",
event_types=["earnings_release"],
timing_class="after_close",
direction="long_only",
entry_timing_policy="next_open",
max_holding_days=5,
engine_risk_budget_pct=0.25,
),
StrategyEngineConfig(
engine_id="earnings_after_close_short_v1",
event_types=["earnings_release"],
timing_class="after_close",
direction="short_only",
entry_timing_policy="next_open",
max_holding_days=3,
engine_risk_budget_pct=0.10,
shadow_only=True,
),
],
)
config = _make_config(strategy_engines=manifest.strategy_engines)
runner = BacktestRunner(manifest=manifest, config=config, store=store, initial_equity=100_000.0)
result = runner.run(output_root=tmp_path)
run_dir = tmp_path / result.run_id
per_engine_metrics = run_dir / "metrics" / "per_engine_metrics.json"
attribution_by_engine = run_dir / "metrics" / "attribution_by_engine.csv"
assert per_engine_metrics.exists()
assert attribution_by_engine.exists()
payload = per_engine_metrics.read_text()
assert "earnings_same_day_short_v1" in payload
assert "earnings_after_close_long_v1" in payload
assert "earnings_after_close_short_v1" in payload
assert result.metrics.trade_count >= 1
trade_blotter = pq.read_table(run_dir / "artifacts" / "trade_blotter.parquet").to_pylist()
engine_ids = {row["engine_id"] for row in trade_blotter}
assert "earnings_after_close_short_v1" not in engine_ids
equity_curve = pq.read_table(run_dir / "artifacts" / "daily_equity_curve.parquet").to_pylist()
assert any(float(row["net_exposure"]) < 0 for row in equity_curve if float(row["gross_exposure"]) > 0)
metrics_summary = json.loads((run_dir / "metrics" / "metrics_summary.json").read_text())
assert "avg_gross_exposure_pct" in metrics_summary
assert "avg_net_exposure_pct" in metrics_summary
assert "days_in_market_pct" in metrics_summary
def test_engine_execution_overrides_flow_into_effective_execution_config(self):
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import Candidate, ExperimentManifest, StrategyEngineConfig
store = _build_multi_engine_store()
manifest = ExperimentManifest(
experiment_name="portfolio_exec_overrides",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
strategy_engines=[
StrategyEngineConfig(
engine_id="earnings_same_day_long_trend_v1",
event_types=["earnings_release"],
timing_class="same_day",
direction="long_only",
entry_timing_policy="reaction_close",
max_holding_days=12,
engine_risk_budget_pct=0.25,
target_atr_multiplier_override=2.5,
target_1_fraction_override=0.33,
trailing_model_override="pct_10",
trailing_warmup_days_override=2,
),
],
)
config = _make_config(strategy_engines=manifest.strategy_engines)
runner = BacktestRunner(manifest=manifest, config=config, store=store, initial_equity=100_000.0)
candidate = Candidate(
event_id="EVT::SD::LONG",
symbol="AMD",
issuer_id="ISSUER::AMD",
score=0.92,
sector="Technology",
event_type="earnings_release",
event_timestamp=dt.datetime(2026, 1, 6, 21, 0, tzinfo=_UTC),
event_date=dt.date(2026, 1, 6),
filing_time_bucket="post_market",
timing_class="same_day",
reaction_date=dt.date(2026, 1, 6),
execution_date=dt.date(2026, 1, 6),
entry_price_est=122.0,
avg_dollar_volume=9_000_000.0,
atr_14=3.0,
score_bucket="high",
engine_id="earnings_same_day_long_trend_v1",
entry_timing_policy="reaction_close",
shadow_only=False,
engine_max_holding_days=12,
engine_risk_budget_pct=0.25,
engine_target_atr_multiplier=2.5,
engine_target_1_fraction=0.33,
engine_trailing_model="pct_10",
engine_trailing_warmup_days=2,
trade_direction="long",
)
effective_exec = runner._build_effective_execution_config(candidate)
assert candidate.engine_id == "earnings_same_day_long_trend_v1"
assert effective_exec.max_holding_days == 12
assert effective_exec.target_atr_multiplier == pytest.approx(2.5)
assert effective_exec.target_1_fraction == pytest.approx(0.33)
assert effective_exec.trailing_model == "pct_10"
assert effective_exec.trailing_warmup_days == 2
def test_attention_gate_filters_engine_candidates(self):
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest, StrategyEngineConfig
from libs.backtest.snapshot_store import SnapshotStore
from libs.oracle_client.models import EntityInfo, EventAttentionResponse, NewsFeatures, WikiFeatures
date = dt.date(2026, 1, 7)
store = SnapshotStore(
candidates_by_exec_date={
date: [
{
"event_id": "EVT::ATTN::PASS",
"symbol": "PASS",
"execution_date": date,
"entry_date": "2026-01-07",
"event_date": "2026-01-06",
"event_close": 100.0,
"gap_size": 0.12,
"entry_price": 100.0,
"score": 0.90,
"sector": "Technology",
"event_type": "earnings_release",
"event_timestamp": "2026-01-06T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-06",
"reaction_day_return": -0.12,
"avg_dollar_volume": 8_000_000.0,
"atr_14": 4.0,
},
{
"event_id": "EVT::ATTN::FAIL",
"symbol": "FAIL",
"execution_date": date,
"entry_date": "2026-01-07",
"event_date": "2026-01-06",
"event_close": 101.0,
"gap_size": 0.11,
"entry_price": 101.0,
"score": 0.89,
"sector": "Technology",
"event_type": "earnings_release",
"event_timestamp": "2026-01-06T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-06",
"reaction_day_return": -0.11,
"avg_dollar_volume": 7_500_000.0,
"atr_14": 4.0,
},
]
},
bars_by_symbol_date={
"PASS": {date: {"date": date, "open": 100.0, "high": 100.0, "low": 95.0, "close": 96.0, "volume": 1_000_000}},
"FAIL": {date: {"date": date, "open": 101.0, "high": 102.0, "low": 98.0, "close": 99.0, "volume": 900_000}},
},
)
manifest = ExperimentManifest(
experiment_name="attention_gate_test",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
strategy_engines=[
StrategyEngineConfig(
engine_id="same_day_short_attention",
event_types=["earnings_release"],
timing_class="same_day",
direction="short_only",
attention_min_wiki_spike_10d=1.2,
)
],
)
config = _make_config(strategy_engines=manifest.strategy_engines)
runner = BacktestRunner(manifest=manifest, config=config, store=store)
def _fake_attention(candidate):
spike = 1.5 if candidate.symbol == "PASS" else 0.9
return EventAttentionResponse(
ticker=candidate.symbol,
event_date="2026-01-06",
entity=EntityInfo(
ticker=candidate.symbol,
canonical_name=candidate.symbol,
resolver_confidence=0.9,
),
wiki=WikiFeatures(spike_10d=spike, zscore_20d=1.0),
news=NewsFeatures(),
metadata={},
)
runner._get_event_attention = _fake_attention # type: ignore[method-assign]
selected = runner._select_candidates_for_date(date)
assert [candidate.symbol for candidate in selected] == ["PASS"]
assert selected[0].features["attention_wiki_spike_10d"] == pytest.approx(1.5)
def test_attention_max_gate_allows_missing_payload(self):
from apps.backtester.run import BacktestRunner
from libs.backtest.domain import ExperimentManifest, StrategyEngineConfig
from libs.backtest.snapshot_store import SnapshotStore
date = dt.date(2026, 1, 6)
store = SnapshotStore(
candidates_by_exec_date={
date: [
{
"event_id": "EVT::ATTN::KNOWN",
"symbol": "KNOWN",
"execution_date": date,
"entry_date": "2026-01-06",
"event_date": "2026-01-06",
"event_close": 100.0,
"gap_size": 0.12,
"entry_price": 100.0,
"score": 0.90,
"sector": "Technology",
"event_type": "earnings_release",
"event_timestamp": "2026-01-06T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-06",
"reaction_day_return": 0.15,
"avg_dollar_volume": 8_000_000.0,
"atr_14": 4.0,
},
{
"event_id": "EVT::ATTN::MISSING",
"symbol": "MISSING",
"execution_date": date,
"entry_date": "2026-01-06",
"event_date": "2026-01-06",
"event_close": 101.0,
"gap_size": 0.11,
"entry_price": 101.0,
"score": 0.89,
"sector": "Technology",
"event_type": "earnings_release",
"event_timestamp": "2026-01-06T21:00:00+00:00",
"filing_time_bucket": "post_market",
"reaction_date": "2026-01-06",
"reaction_day_return": 0.14,
"avg_dollar_volume": 7_500_000.0,
"atr_14": 4.0,
},
]
},
bars_by_symbol_date={
"KNOWN": {date: {"date": date, "open": 100.0, "high": 105.0, "low": 99.0, "close": 103.0, "volume": 1_000_000}},
"MISSING": {date: {"date": date, "open": 101.0, "high": 104.0, "low": 100.0, "close": 102.0, "volume": 900_000}},
},
)
manifest = ExperimentManifest(
experiment_name="attention_max_gate_test",
dataset_snapshot_id="test_snapshot",
base_config="configs/backtest/defaults.json",
overrides={},
strategy_engines=[
StrategyEngineConfig(
engine_id="same_day_long_attention_cap",
event_types=["earnings_release"],
timing_class="same_day",
direction="long_only",
entry_timing_policy="reaction_close",
gap_size_min=0.10,
attention_max_wiki_spike_10d=1.5,
)
],
)
config = _make_config(strategy_engines=manifest.strategy_engines)
runner = BacktestRunner(manifest=manifest, config=config, store=store)
def _fake_attention(candidate):
if candidate.symbol == "KNOWN":
from libs.oracle_client.models import EntityInfo, EventAttentionResponse, NewsFeatures, WikiFeatures
return EventAttentionResponse(
ticker=candidate.symbol,
event_date="2026-01-06",
entity=EntityInfo(
ticker=candidate.symbol,
canonical_name=candidate.symbol,
resolver_confidence=0.9,
),
wiki=WikiFeatures(spike_10d=1.4, zscore_20d=0.5),
news=NewsFeatures(),
metadata={},
)
return None
runner._get_event_attention = _fake_attention # type: ignore[method-assign]
selected = runner._select_candidates_for_date(date)
assert [candidate.symbol for candidate in selected] == ["KNOWN", "MISSING"]
assert selected[0].features["attention_wiki_spike_10d"] == pytest.approx(1.4)
assert "attention_wiki_spike_10d" not in selected[1].features