#!/usr/bin/env python3
"""
backfill_signal_outcomes.py — seed and advance advisory outcomes for every
logged trade setup (not only panel rows), one per advisory event.

Pass A (offline, no network): assign setup_key / advisory_event_id to all
legacy setup rows, mark same-setup re-logs within 60 min as DUPLICATE, and
seed a PENDING outcome on each canonical row that has none. Existing
(panel-seeded) outcomes are never overwritten.

Pass B: advance PENDING rows from the closed-candle streams already stored
in the DB (union across every snapshot of the timeframe — no provider).

Pass C (--reseed-unresolvable): bounded re-seed of continuity-broken rows,
then Pass B again.

Safe beside the live writers: short per-row transactions with a busy
timeout. Read-only preview with --dry-run.

    python scripts/backfill_signal_outcomes.py --dry-run
    python scripts/backfill_signal_outcomes.py
    python scripts/backfill_signal_outcomes.py --reseed-unresolvable
"""
import argparse
import os
import sqlite3
import sys

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

import app_config  # noqa: E402
from signal_log import SignalLogger  # noqa: E402


def _status_counts(con: sqlite3.Connection) -> dict:
    return dict(con.execute(
        "SELECT COALESCE(advisory_outcome_status, 'NULL'), COUNT(*)"
        " FROM signals WHERE setup_json IS NOT NULL AND setup_json != 'null'"
        " GROUP BY 1").fetchall())


def main(argv=None) -> int:
    ap = argparse.ArgumentParser(description=__doc__.splitlines()[1])
    ap.add_argument("--db", default=None, help="defaults to the signal_log.path setting in config.json")
    ap.add_argument("--dry-run", action="store_true")
    ap.add_argument("--reseed-unresolvable", action="store_true")
    ap.add_argument("--symbol", default="XAU/USD")
    args = ap.parse_args(argv)
    path = args.db or app_config.signal_log_path()
    if not os.path.exists(path):
        print(f"no database at {path}")
        return 1
    if args.dry_run:
        con = sqlite3.connect(f"file:{os.path.abspath(path)}?mode=ro", uri=True)
        print("setup rows by outcome status:", _status_counts(con))
        have = {r[1] for r in con.execute("PRAGMA table_info(signals)")}
        if "setup_key" in have:
            n_keyless = con.execute(
                "SELECT COUNT(*) FROM signals WHERE setup_json IS NOT NULL"
                " AND setup_json != 'null' AND setup_key IS NULL").fetchone()[0]
            print(f"setup rows without setup_key: {n_keyless}")
        else:
            print("setup_key column not present yet (schema migrates on"
                  " the first non-dry run)")
        con.close()
        return 0
    lg = SignalLogger(path)
    try:
        print("before:", _status_counts(lg._conn))
        print("pass A (seed/dedup):", lg.backfill_seeds())
        total = 0
        for _ in range(50):
            n = lg.resolve_from_store(args.symbol)
            total += n
            if n == 0:
                break
        print(f"pass B (advance from stored bars): {total} rows changed")
        if args.reseed_unresolvable:
            reseeded = lg.reseed_unresolvable()
            print(f"pass C (re-seed): {len(reseeded)} rows re-seeded")
            for _ in range(50):
                if lg.resolve_from_store(args.symbol) == 0:
                    break
        print("after:", _status_counts(lg._conn))
    finally:
        lg.close()
    return 0


if __name__ == "__main__":
    sys.exit(main())