New engines (configurable but not promoted by default):
- libs/backtest/earnings_runup.py: pre-earnings drift entry (T-7 to T-3, attention+volume z-scores)
- libs/backtest/peer_sympathy.py: peer reaction trade after leader earnings, with reaction_close variant
- libs/backtest/vol_breakout_52w.py: 52-week high volume breakout
- libs/backtest/cross_sectional_momentum.py: 12-1 momentum with VIX/SPY-50dma regime filter
Pipeline additions:
- libs/parser/event_type_normalizer.py: normalize Oracle fallback raw vocab to strategy
vocabulary (earnings_result→earnings_release, regulation_fd→guidance_update, etc.).
Wired into apps/pipeline/event_parser/main.py oracle-fallback path.
- libs/labeler/label_generator.py: preserve future entry_dates as label_status='pending'
instead of dropping as 'unavailable'.
- libs/export/snapshot_export.py: include 'pending' labels in snapshot export.
- libs/parser/rule_parser.py: harden 8-K item-code classifier against dirty input strings.
Infrastructure:
- libs/backtest/snapshot_store.py: _PRICE_FEATURE_WARMUP_DAYS 120→400 (needed for
xsmom 12-1 lookback of 273 trading days).
- apps/backtester/run.py + apps/paper_trader/backtest_sim.py: disable auto-refresh
of snapshots (user request — auto-refresh was silently rebuilding snapshots with
current code, making historical backtests irreproducible across DB mutations).
Engine config support:
- libs/backtest/domain.py: add fields for ER/PS/VolBO/xsmom engine configs.
- libs/backtest/execution.py: wire pct-trailing for EarningsRunup.
- libs/backtest/scoring.py: synthetic candidate scoring for new engines.
Configs (POC + sweeps, none promoted as active strategy):
- Phase A-E PEAD baseline comparisons (no PEAD / +ER / +xsmom / +sleeves variants)
- Phase F1-F8 silo allocation sweep (v7.356 + ER/xsmom silos 15-60%)
- xsmom_poc_v1, xsmom_v2_regime_mdd
- v7.356_plus_er_silo_05/10/15/20/25/30 ranges
- earnings_runup_* / peer_sympathy_* / vol_breakout_52w_* POCs
Tests: 16-tests-each for each new engine + event_type_normalizer tests.
Note: backtest reproducibility infrastructure remains broken — see
_backup_2026-05-10/HANDOFF.md for details on the +12,592% reference run that
cannot be reproduced after rebuilds. Followup work needed before trusting any
specific backtest number.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add peer_sympathy_entry_timing_policy ("next_open"|"reaction_close") and
peer_sympathy_leader_filing_time_buckets to StrategyEngineConfig. The
reaction_close variant enters peers at peer's T 16:00 ET close on the
SAME trading day as the leader's print, addressing the v1 hypothesis
failure where T+1 gap had already absorbed the news overnight.
Lookahead defenses tightened for the new branch: cutoff is T 16:00 ET
(_bar_close_timestamp(decision_date)) instead of T+1 09:30 ET; bucket
allow-list excludes AMC filings (which under PEAD's reaction_date=T+1
convention pass the timestamp check but defeat same-session sympathy).
LeaderPrint now carries filing_time_bucket from the runner.
Runner: split _schedule_peer_sympathy_candidates into two phases.
reaction_close fires BEFORE _select_candidates_for_date(date) and emits
into _scheduled_add_ons[date]; next_open keeps the existing tail-of-loop
position emitting into _scheduled_delayed_entries[next_date].
v2 backtest (1052 trading days, midlarge-liquid-long-v1 snapshot):
trades 256→120, return -52.9%→-2.4%, MDD 61.6%→24.5%, SQS 19.6→30.2.
Sample sympathy plays: GOOGL on META +7.7%, AVGO on COHR +6.3%,
SLB on HAL +5.5%, GE on HWM +5.1%. Profit factor 0.977 (one tweak
from breakeven). Verdict: VIABLE BUT WEAK — salvage hypothesis
empirically validated, near breakeven, not promoted yet.
35/35 peer_sympathy unit tests pass (29 pre-existing + 6 new for
reaction_close path).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Adds three new synthetic-Candidate emitter engines parallel to the
existing leader_follower scheduler hook, plus look-ahead defenses
(LookaheadViolationError + per-engine assertions). Each engine is
covered by a standalone PoC config (no PEAD/parking/idle alpha) for
isolation backtests against the midlarge or broad snapshot.
Engines:
EarningsRunup (libs/backtest/earnings_runup.py)
- Trigger: days_to_earnings ∈ [3,7] AND attention_zscore_20d ≥ 1.5
AND dollar_volume_20d_zscore ≥ 1.0 (all evaluated at T-1 close)
- Entry: T+1 next_open. Exit: -4% / +8% / max_holding_days =
days_to_earnings - buffer (forced flat by close before announcement)
- PIT calendar: PointInTimeEarningsCalendar adapter for backtest;
oracle_surprise_prefetch fallback when parquet calendar absent
- PoC verdict (configs/experiments/earnings_runup_poc_v1.json):
119 trades over 1051 days, +37.27% total return, 44.46% MDD,
SQS 45.2 (profitability=55.5, risk=23.5, robustness=50.1).
VIABLE BUT NEEDS WORK — signal exists; standalone risk profile
too aggressive for v7.356 baseline (8.8% MDD on v7.364). Path
forward: per_trade_risk reduction, VIX gate, position cap, or
integrate as PEAD sleeve adjunct (not as standalone replacement).
PeerSympathy (libs/backtest/peer_sympathy.py)
- Trigger: leader passes PEAD filter (earnings_release / guidance_update
/ material_contract) AND leader reaction_close ≥ +5% AND peer 60d
correlation ≥ 0.55 over [T-65, T-5]. Top-2 peers by correlation
from leader_follower_extra_peer_symbols_by_sector + sector ETF
holdings.
- Entry: T+1 next_open on peer. Exit: -3.5% / +6% / max_holding=3 /
peer-earnings blackout
- PoC verdict (configs/experiments/peer_sympathy_poc_v1.json):
256 trades over 1051 days, -52.92% total return, 54.47% MDD,
SQS 19.6 (profitability=0.0, risk=5.4, robustness=100.0).
DEAD. The leader's catalyst is already absorbed by T+1 next_open
— peers gap up overnight before entry. robustness=100 confirms
the negative result is not noise. Salvage paths (not implemented):
reaction_close entry, raised-guidance-only restriction.
- Note: initial run_id was 0 trades due to a select_candidates
filter mismatch (engine.event_types=['peer_sympathy'] dropping
real event_type='earnings_release' rows). The runner adapter
was patched to bypass strategy_engine filtering for leader
selection; the manual peer_sympathy_leader_event_types filter
does the gating.
VolBreakout52w (libs/backtest/vol_breakout_52w.py)
- Trigger: close_T-1 > max(high[T-252:T-2]) AND volume_T-1 ≥
2 × median_volume_20d_T-2 AND ATR_14_T-1/close ∈ [0.015, 0.06].
Entry T next_open, exit -3% / +5% / max_holding=2 / MOC.
- Honest, look-ahead-safe descendant of the retired topgainer v1-v54
family. Five layers of strict-before assertions guard the bar
provider, candidate construction, trigger evaluation, and feature
timestamps. A leaky-provider proof-by-contradiction test
demonstrates the categorical catch.
- PoC verdict (configs/experiments/vol_breakout_52w_poc_v1.json,
broad-liquid universe): 1,332 trades, -87.28% total return,
88.74% MDD, SQS 24.4 (profitability=0.0, robustness=100.0).
DEAD AND HONEST. This is the most important finding of the three
PoCs: the topgainer v1-v54 lineage's headline returns (+267%
Sharpe 13.73 in best variants) were 100% lookahead bug. With
the bug removed, the 52w-high + volume + ATR signal has no real
alpha — the lookahead-corrected -4.3% from prior memory is
confirmed and amplified to -87% on a fuller universe and longer
horizon. Future "revive topgainer" proposals can cite this run
(bt_return_max_long_v1_broad-liquid_20260509042903892342_3bb473d9)
as definitive falsification.
- Pre-open gap guard inactive (no premarket data in broad snapshot).
skip_if_no_gap_data=true; the +4% gap-fade guard would not move
the result given the magnitude.
Shared infrastructure additions:
- libs/backtest/domain.py: LookaheadViolationError class +
StrategyEngineConfig fields (11 EarningsRunup + 11 PeerSympathy
+ 13 VolBreakout52w = 35 new fields)
- apps/backtester/run.py: _BacktestAttentionZscoreAdapter,
_RunnerPeerResolver, _schedule_earnings_runup_candidates,
_schedule_peer_sympathy_candidates,
_schedule_vol_breakout_52w_candidates wired into the daily
scheduler block. PeerSympathy adapter bypasses strategy_engine
filtering on leader selection (manual filter handles gating).
Tests: 21 (EarningsRunup) + 27 (PeerSympathy) + 38 (VolBreakout52w)
= 86 new unit tests, all passing. Broader unit suite: 1392 passed,
2 pre-existing failures unrelated.
Net engine state: EarningsRunup is the only viable new engine class.
PeerSympathy and VolBreakout52w are kept in-tree as falsification
evidence, not as production engines.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Backtester (run.py):
- cash_available = (self._cash + parking_value) * multiplier caused trades to be
approved even when self._cash ≈ 0 (all money in SGOV/QQQ). Trades executed
by deducting from self._cash → negative cash (phantom money).
- Fix: after simulate_entry, if self._cash < actual trade cost and parking exists,
call _liquidate_parking_for_cash(shortfall) before deducting from cash.
- Verified: 2022-2026 backtest with qqqm_low_dd shows 0 cash_negative events.
Live engine (engine.py):
- Add _parking_liquidate_for_event(): frees parking cash to fund event entries.
SGOV (virtual) reduces entry_value in DB; QQQM/QQQ sells real shares via broker.
- Both entry loops (engines mode + flat/reaction_close mode) now attempt parking
liquidation when plan.skip_reason == "insufficient_cash" before giving up.
Also includes prior session work (accumulated since last commit):
- 6 novel parking gate signals: VRP, Market Temperature, Hurst exponent, Rolling
Kurtosis, Return Autocorrelation, SPY-QQQ Correlation (composite risk score v2)
- QQQM parking symbol support (lower expense ratio vs QQQ)
- Snapshot auto-refresh + bar extension cache (pickle) to avoid 10-min re-fetches
- Bar extension clamps to last market-closed date (ET 4PM check)
- fithia2 refresh command; --no-refresh flag for paper backtest
- Paper backtest macro extension beyond last event date (parking-only periods)
- parking_state DB schema: 7 new columns (peak_price, gate_in_sgov,
committed_target, pending_target, pending_days, sgov_entry_value, sold_today)
- Live engine: target confirmation (2-day), top-up drawdown gate, trailing stop,
SGOV interest accrual, full 6-signal gate evaluation
- New PARKING_PRESETS: qqqm_low_dd, composite_v2, vv_24_vrp8, vt_24_t13, etc.
- Web GUI / CLI result parity fix (Oracle URL via get_settings().stock_oracle_url)
- Force-close uses last_exec_date (has bar data); parking liquidates at last_date
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Builds a full synthetic market data pipeline to test strategies against
12 diverse market regimes (bull/bear/crash/chop/rotation/liquidity drought)
that may not exist in historical data. Computes Regime Robustness Score (RRS)
to detect overfitting and environment-specific fragility.
- libs/backtest/scenarios/: price_gen, macro_gen, event_gen, coupling,
store_builder, scenarios (12 pre-built), robustness (RRS)
- apps/scenario/cli.py: `fithia2 scenario-test` with Rich output
- apps/tracker/cli.py: scenario-test command routing
- tests/: 83 unit tests across 3 new test files
- docs/scenario_test.md: usage guide and result interpretation
- docs/research_workflow_and_handoff.md: Step 5.5 scenario test added
Fix: no_signal scenario uses drift=0% (was +10%) for fair signal integrity scoring.
Fix: synthetic candidates now carry macro_vix/macro_hy_spread from macro_by_date
to pass selector engine filters.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Track experiment cycles with SQS scoring (0-100), JSONL journal, and
auto-generated leaderboard to prevent duplicate experiments and enable
data-driven strategy decisions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove 5 non-alpha features (earnings surprise, risk penalty, parse confidence,
direction clarity, LM sentiment) from composite score to eliminate double-counting
with hard gates and noise sources. Redistribute weights to 5 alpha features.
Add default-deny for unknown event types, no-follow-through early exit (D+1),
kill switch log-only mode, macro regime size scaler. Remove SUE gate (Gate 8).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Flip scoring weights so event/document quality is primary signal (55%)
and market confirmation is secondary (35%). Add research mode with
kill-switch cooldown/reset, veto gates for bad events, reduced portfolio
risk, and 4 diagnostic analysis scripts.
Phase A: Research mode kill-switch reset, risk reduction (0.5%/trade,
max 4 positions), bullish-only direction for all event types.
Phase B: 2 new sub-scorers (parse_confidence, direction_clarity),
4 veto gates (oneoff risk, parse confidence, unknown/bearish direction).
Phase C: signal_quality, event_type_decomposition, kill_switch_impact,
concurrent_position analysis scripts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace naive abs(reaction_day_return) fallback with a composite score
from 4 market microstructure features available at entry time:
1. Reaction quality (35%) — moderate positive return (PEAD zone) is
ideal; extreme positives penalized as "priced in"
2. Close strength (30%) — close near session high = buyers won
3. Volume conviction (20%) — 1.2-2x is healthy; >3x is exhaustion
4. Gap quality (15%) — small positive gap = orderly strength
Real data results (14 events, b1868603 snapshot):
- Score filters out 6 of 10 losers (DDOG -11.7%, META -9.1%, etc.)
- With threshold 0.5: return -2.63% → +0.27%, drawdown 4.24% → 0.86%
- Profit factor 0.44 → 1.16 (turns profitable)
- MSFT loss (-8.7%) is macro-driven, not predictable from stock features
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
I Luk Kim