"""Autonomous sharpening pass: wait for the cross-cluster podcast claims to extract, re-embed, then
re-run the §7.1 backtest. Run in the background; writes logs/backtest2.log for review."""
import sqlite3
import subprocess
import sys
import time

DB = "data/signal.db"
PY = ".venv/bin/python"


def pending_podcast_extract() -> int:
    return sqlite3.connect(DB).execute(
        "SELECT COUNT(*) FROM backfill_jobs WHERE job_type='extract' AND state='pending' "
        "AND target_id LIKE 'pod:%'"
    ).fetchone()[0]


for i in range(60):  # up to ~2h
    p = pending_podcast_extract()
    print(f"[sharpen] iter {i}: podcast extract pending={p}", flush=True)
    if p <= 2:
        break
    time.sleep(120)

print("[sharpen] embedding accumulated claims...", flush=True)
subprocess.run([PY, "-m", "signal_engine", "embed-claims"], stdout=sys.stdout, stderr=subprocess.STDOUT)

print("[sharpen] re-running backtest...", flush=True)
with open("logs/backtest2.log", "w") as f:
    subprocess.run([PY, "-m", "signal_engine", "backtest", "--conviction", "K2023",
                    "--start", "2023-03-01", "--end", "2024-09-01", "--step-days", "90",
                    "--window-days", "90"], stdout=f, stderr=subprocess.STDOUT)
print("[sharpen] DONE — see logs/backtest2.log", flush=True)