import sqlite3
import pandas as pd
import numpy as np

def run_telemetry_drift_audit(
    db_path: str = "data/hiffi_catalog.db",
    max_daily_listener_drop_pct: float = 25.0,
    max_growth_spike_pct: float = 500.0
) -> dict:
    """
    Evaluates cohort telemetry against operational drift thresholds:
      1. Catastrophic Drops (>25% daily decline on high-tier artists).
      2. Anomalous Surges (>500% daily velocity requiring corroboration).
      3. Governance Violations (Hak non-null regressions).
      4. Null Velocity Drift on populated accounts.
    """
    con = sqlite3.connect(db_path)
    query = """
    SELECT 
        r.catalog_rank,
        a.artist_id,
        a.artist_name,
        a.youtube_url,
        a.spotify_url,
        a.instagram_url,
        t.subscribers_count,
        t.spotify_monthly_listeners,
        t.instagram_followers,
        t.daily_view_velocity,
        t.growth_velocity_7d,
        t.momentum_score,
        t.spotify_daily_change
    FROM rankings r
    JOIN artists a ON r.artist_id = a.artist_id
    JOIN telemetry_metrics t ON a.artist_id = t.artist_id
    WHERE r.catalog_rank BETWEEN 1 AND 500
    ORDER BY r.catalog_rank ASC
    """
    df = pd.read_sql_query(query, con)
    con.close()

    anomalies = []
    
    print("=" * 80)
    print("HIFFI AUTOMATED DRIFT & VELOCITY AUDIT")
    print("=" * 80)

    # 1. Governance Drift Check (Hak Tier-1)
    hak = df[df["artist_id"] == "@haknyc"]
    if not hak.empty:
        hak_row = hak.iloc[0]
        if pd.notna(hak_row["spotify_url"]) or pd.notna(hak_row["spotify_monthly_listeners"]) or \
           pd.notna(hak_row["instagram_url"]) or pd.notna(hak_row["instagram_followers"]):
            anomalies.append({
                "artist": "Hak",
                "type": "GOVERNANCE_BREACH",
                "detail": "Hak has non-null values imputed for Spotify/Instagram"
            })

    # 2. Daily Spotify Velocity Drift
    # Calculate % delta: (daily_change / (monthly_listeners - daily_change)) * 100
    active_sp = df[df["spotify_monthly_listeners"].notna() & (df["spotify_monthly_listeners"] > 0)].copy()
    prev_listeners = active_sp["spotify_monthly_listeners"] - active_sp["spotify_daily_change"]
    active_sp["pct_daily_change"] = (active_sp["spotify_daily_change"] / prev_listeners.replace(0, np.nan)) * 100

    severe_drops = active_sp[active_sp["pct_daily_change"] < -max_daily_listener_drop_pct]
    for _, row in severe_drops.iterrows():
        anomalies.append({
            "artist": row["artist_name"],
            "type": "CATASTROPHIC_DROP",
            "detail": f"Daily listener drop of {row['pct_daily_change']:.2f}% (Loss: {int(row['spotify_daily_change'])})"
        })

    anomalous_spikes = active_sp[active_sp["pct_daily_change"] > max_growth_spike_pct]
    for _, row in anomalous_spikes.iterrows():
        anomalies.append({
            "artist": row["artist_name"],
            "type": "UNVERIFIED_SPIKE",
            "detail": f"Daily listener surge of {row['pct_daily_change']:.2f}% (Gain: {int(row['spotify_daily_change'])})"
        })

    # 3. Canonical Schema Drift (Broken URL formats)
    yt_bad = df[~df["youtube_url"].fillna("").str.contains(r"^https://www\.youtube\.com/channel/UC[a-zA-Z0-9_-]{22}$", regex=True)]
    for _, row in yt_bad.iterrows():
        anomalies.append({
            "artist": row["artist_name"],
            "type": "SCHEMA_DRIFT_YOUTUBE",
            "detail": f"Non-canonical YouTube URL: {row['youtube_url']}"
        })

    print(f"Total Cohort Size Audited:           {len(df)}")
    print(f"Total Drift Anomalies Flagged:       {len(anomalies)}")
    
    if anomalies:
        print("\n[CIRCUIT BREAKER TRIGGERED] Anomalies detected:")
        for idx, a in enumerate(anomalies, 1):
            print(f"  {idx}. [{a['type']}] {a['artist']}: {a['detail']}")
        print("\nAction: Synchronization to production aborted.")
        return {"circuit_breaker": "TRIPPED", "anomalies": anomalies}
    else:
        print("[CIRCUIT BREAKER: CLEAR] No drift detected. Telemetry velocities healthy.")
        print("Action: Safe to synchronize with live production API.")
        return {"circuit_breaker": "PASS", "anomalies": []}

if __name__ == "__main__":
    run_telemetry_drift_audit()