#!/usr/bin/env python3
"""End-of-day whole-market replay.

After the close, pull the day's full active universe (not just the ~20 the live
loop watched), backfill their bars, and run TODAY'S logic (entry filters + ORB +
managed exits) over every qualifying gapper — so you see what the system WOULD
have traded and the P&L, plus a perfect-hindsight line (the biggest catchable
moves) to show what was left on the table. Every run also GROWS the stored
dataset, so the nightly tuner and every verification get more trustworthy.

    PYTHONPATH=. python eod_replay.py            # replay today
    PYTHONPATH=. python eod_replay.py 2026-06-17 # replay a specific date

Schedule after the close (after eod flatten), e.g. cron: 5 16 * * 1-5.
"""
from __future__ import annotations

import os
import sys
from datetime import date, datetime, timezone

from dotenv import load_dotenv

sys.path.insert(0, ".")
load_dotenv()

# config parity with the live loop: DB-backed knobs (config_overrides) beat
# compose env — a bare env would replay under DEFAULT exits (the 4.5x-baseline
# landmine, orderflow-shelf-verdicts 2026-07-17)
from runtime.env_overrides import load as _load_cfg_overrides  # noqa: E402
_load_cfg_overrides()
os.environ.setdefault("STRATEGY_SETUPS", "opening_range_break")

from alpaca_paper.client import AlpacaPaperClient
from alpaca_paper.settings import AlpacaPaperSettings
from config import Config
from research.ingestion.market_data import (
    classify_session,
    ingest_daily_history,
    ingest_live_minute_bars,
    upsert_minute_bars,
)
from research.ingestion.signals import scan_gappers
from research.multi_schema import open_research_db
from research.query import query_avg_daily_volume, query_minute_bars, query_previous_close
from strategy.backtest.engine import BacktestEngine
from strategy.exits import ExitConfig, TRAIL_PRIOR_LOW, parse_profit_tiers
from strategy.models import SetupCriteria
from strategy.population import PopulationConfig, population_reject

# Population is defined ONCE, in strategy/population.py — the SAME gate the live
# loop trades ($2-20 band + gap floor + 35-150% dead band + >=150% squeeze). This
# replaces the stale $1-5 / 3-60% look-ahead screen. Prod thresholds are passed
# explicitly (a bare from_env() shell would disable the gap gate).
_POP = PopulationConfig(min_entry_gap_pct=0.10)
RISK_PCT = float(os.environ.get("TRADING_RISK_PER_TRADE_PCT", "0.01"))


def _daily_gappers(con, sess, universe):
    """Identify today's qualifying gappers from DAILY bars (cheap) so we only
    minute-backfill the handful that matter, not all 100 names. Screens through
    the SHARED live population gate (strategy/population.py) on the OPEN price and
    STATIC open gap — both open-knowable; the old screen used t_close (look-ahead)
    and a hard 60% cap that dropped the >=150% squeezes production re-admits."""
    out = []
    for sym in universe:
        # Bars ON OR BEFORE the session date, newest first — so rows[0] is the
        # session day and rows[1] the prior trading day. Without the `<= sess`
        # bound this pulled the LATEST bar (always the most recent date in the
        # table), so replaying any past date saw rows[0] != sess and skipped
        # EVERY symbol — silently reporting "no qualifying gappers" for all
        # history and making multi-day backtesting impossible.
        rows = con.execute(
            "SELECT trade_date, open, close, volume FROM daily_bars WHERE symbol=? "
            "AND trade_date <= ? ORDER BY trade_date DESC LIMIT 25", [sym, sess]).fetchall()
        if len(rows) < 2 or str(rows[0][0]) != str(sess):
            continue
        t_open, t_vol = float(rows[0][1]), float(rows[0][3])
        prev_close = float(rows[1][2])
        prior = [float(r[3]) for r in rows[1:21]]
        adv = sum(prior) / len(prior) if prior else 0.0
        gap = (t_open / prev_close - 1) if prev_close else 0.0   # FRACTION (population contract)
        rvol = (t_vol / adv) if adv else 0.0
        # OPEN price + open gap are open-knowable; rvol re-admits real >=150% squeezes.
        if population_reject(_POP, gap_pct=gap, price=t_open, volume=None, rvol=rvol) is None:
            out.append(sym)
    return out


def _session_universe(con, client, sess) -> list[str]:
    """Candidate names for a session, from three sources union-ed:

    (a) what the LIVE scanner discovered that day (events) — the top-100
        absolute-volume list misses small-cap gappers entirely: 2026-07-28 the
        replay found 1 gapper on a day the live loop signaled 8 names, because
        MUZ/DAMD/BIYA-class names never crack the most-actives list;
    (b) historical_gappers — the year-scale gapper record, covers dates before
        the live loop existed (backfill path);
    (c) today's most-actives — ONLY for a same-day replay (the API returns the
        CURRENT list; unioning it into a past date would be look-ahead).
    The shared population screen still runs after this — the union only widens
    candidates, it never bypasses the gate."""
    syms: set[str] = set()
    try:
        rows = con.execute(
            "SELECT DISTINCT payload_json::json->>'symbol' FROM events "
            "WHERE event_type = 'symbol_discovered' AND timestamp::date = ?",
            [str(sess)]).fetchall()
        syms |= {r[0] for r in rows if r and r[0]}
    except Exception as exc:  # noqa: BLE001 — events table may not exist in research-only DBs
        print(f"[universe] discovered-symbols lookup skipped: {exc}")
    try:
        rows = con.execute(
            "SELECT DISTINCT symbol FROM historical_gappers WHERE session_date = ?",
            [str(sess)]).fetchall()
        syms |= {r[0] for r in rows if r and r[0]}
    except Exception as exc:  # noqa: BLE001
        print(f"[universe] historical_gappers lookup skipped: {exc}")
    if sess == datetime.now(timezone.utc).date():
        actives = client.get_most_actives(top=100, by="volume")
        syms |= {a["symbol"] for a in actives if a.get("symbol")}
    return sorted(syms)


def _exit_cfg() -> ExitConfig:
    return ExitConfig(
        target_r=float(os.environ.get("TRADING_REWARD_MULTIPLE", "10")),
        trail_mode=os.environ.get("TRADING_EXIT_TRAIL_MODE", TRAIL_PRIOR_LOW),
        trail_after_r=float(os.environ.get("TRADING_EXIT_TRAIL_AFTER_R", "1")),
        profit_lock_tiers=parse_profit_tiers(os.environ.get("TRADING_EXIT_PROFIT_TIERS", "")))


def main(argv=None):
    argv = argv or sys.argv[1:]
    if argv:
        sess = date.fromisoformat(argv[0])
    else:
        sess, _, _, _ = classify_session(datetime.now(timezone.utc))

    con = open_research_db("market")
    client = AlpacaPaperClient(AlpacaPaperSettings.from_env())

    # 1) session universe: scanner-discovered + historical gapper record +
    #    (same-day only) most-actives — see _session_universe
    universe = _session_universe(con, client, sess)
    print(f"=== EOD REPLAY {sess} ===")
    print(f"universe: {len(universe)} candidates (scanner-discovered + "
          f"historical_gappers + same-day most-actives)")

    # 2) cheap DAILY backfill -> screen gappers from daily bars (no need to pull
    #    minute bars for all 100; only the gappers need them)
    ingest_daily_history(con, client, universe, days=30)
    gapper_syms = _daily_gappers(con, sess, universe)
    print(f"daily-screen gappers (shared population gate: ${_POP.price_min:g}-{_POP.price_max:g}, "
          f"gap >={_POP.min_entry_gap_pct:.0%} ex {_POP.gap_dead_band_lo:.0%}-{_POP.gap_dead_band_hi:.0%} "
          f"dead-band, squeeze >={_POP.gap_dead_band_hi:.0%}+rvol{_POP.squeeze_rvol_min:g}): "
          f"{len(gapper_syms)}")

    # 3) minute-backfill ONLY the gappers (fast), then rank them, and grow the
    # dataset. Use the SIP (full-volume) feed so rvol/$-volume in the replay
    # reflect REAL volume — the live IEX feed sees only ~2-5% of it, which was
    # silently corrupting every volume-based backtest conclusion.
    if sess == datetime.now(timezone.utc).date():
        ing = ingest_live_minute_bars(con, client, gapper_syms, lookback_minutes=440,
                                      feed=client.settings.backfill_feed)
        n_rows, n_syms = ing.minute_rows, len(ing.symbols)
    else:
        # historical session: a from-now lookback window would fetch the WRONG
        # day — fetch that session's 04:00-20:00 ET explicitly (premarket incl.)
        from zoneinfo import ZoneInfo
        et = ZoneInfo("America/New_York")
        start = datetime(sess.year, sess.month, sess.day, 4, 0, tzinfo=et)
        end = datetime(sess.year, sess.month, sess.day, 20, 0, tzinfo=et)
        by_sym = client.get_minute_bars(
            gapper_syms, start_iso=start.isoformat(), end_iso=end.isoformat(),
            feed=client.settings.backfill_feed) if gapper_syms else {}
        n_rows, n_syms = 0, 0
        for sym, bars in by_sym.items():
            if bars:
                n_rows += upsert_minute_bars(con, sym, bars,
                                             source_provider="alpaca_sip_backfill")
                n_syms += 1
    print(f"backfilled {n_rows} minute rows ({client.settings.backfill_feed}) "
          f"across {n_syms} gappers\n")
    keep = set(gapper_syms)
    # Population membership was already decided by the shared gate in
    # _daily_gappers; scan_gappers here only computes gap/rvol/vwap for ranking, so
    # pass permissive bounds and let `keep` be the sole authority (this also keeps
    # the >=150% squeeze names the old `gap_pct <= GAP_MAX` cap wrongly dropped).
    gappers = [g for g in scan_gappers(con, sess, min_gap_pct=0.0, min_relative_volume=0.0,
                                       price_min=0.0, price_max=1e9, limit=200)
               if g.symbol in keep]
    if not gappers:
        print("no qualifying gappers today.")
        return

    # 4) run TODAY'S logic over each
    cfg = _exit_cfg()
    eng = BacktestEngine(Config(), target_r=cfg.target_r, warmup_bars=3, eval_every=1,
                         ready_score_pct=55, min_bars=3, exit_config=cfg,
                         # intrabar ORB SETUP criteria (not population) — preserved
                         criteria=SetupCriteria(gap_pct_min=0.05, relative_volume_min=2.0))
    equity = float(client.get_account().get("equity") or 0) or 100000.0
    risk_dollars = equity * RISK_PCT

    trades, hindsight = [], []
    for g in gappers:
        bars = query_minute_bars(con, g.symbol, sess)
        if bars is None or not len(bars):
            continue
        rth = bars[bars["is_regular_hours"] == True].reset_index(drop=True) if "is_regular_hours" in bars.columns else bars  # noqa: E712
        if len(rth):
            run_pct = (float(rth["high"].max()) / float(rth["open"].iloc[0]) - 1) * 100
            hindsight.append((g.symbol, g.gap_pct, run_pct))
        pc = query_previous_close(con, g.symbol, sess)
        adv = query_avg_daily_volume(con, g.symbol, sess)
        for t in eng.run(bars, g.symbol, previous_close=pc, avg_daily_volume=adv).trades:
            trades.append((g.symbol, t))

    # 5) report
    print("--- what TODAY'S logic would have traded ---")
    if trades:
        rs = [t.r_multiple or 0 for _s, t in trades]
        wins = sum(1 for r in rs if r > 0)
        sumR = sum(rs)
        print(f"  trades: {len(trades)}   win: {wins / len(trades) * 100:.0f}%   "
              f"total R: {sumR:+.1f}   est P&L @ ${equity:,.0f} (1% risk): ${sumR * risk_dollars:+,.0f}")
        for sym, t in sorted(trades, key=lambda x: -(x[1].r_multiple or 0))[:8]:
            print(f"    {sym:6} {t.r_multiple:+.2f}R  entry {t.entry_price} -> "
                  f"{t.exit_reason} {t.exit_price}")
    else:
        print("  no trades taken.")

    print("\n--- perfect hindsight (biggest intraday runs from the open) ---")
    for sym, gap, run_pct in sorted(hindsight, key=lambda x: -x[2])[:8]:
        print(f"    {sym:6} gap {gap:+.0f}%  ran +{run_pct:.0f}% intraday")
    captured = sum(r for r in [t.r_multiple or 0 for _s, t in trades]) if trades else 0
    print(f"\n  gappers available: {len(gappers)}  |  traded: {len(set(s for s, _ in trades))}  "
          f"|  captured {captured:+.1f}R of the day's opportunity")


if __name__ == "__main__":
    main()