"""
Incident generator - randomly samples a production incident scenario.
Each incident has a hidden root cause that the agent must diagnose
from noisy logs and degraded metrics.
"""
from __future__ import annotations
import random
from typing import Dict, List, Any

ROOT_CAUSES: Dict[str, Dict[str, Any]] = {
    "api_timeout": {
        "affected": ["api"],
        "fix_sequence": ["scale_up", "restart_api"],
        "log_hints": ["timeout error", "upstream request failed", "connection refused"],
    },
    "db_connection_leak": {
        "affected": ["db"],
        "fix_sequence": ["restart_db", "scale_up"],
        "log_hints": ["too many connections", "db pool exhausted", "connection refused to db"],
    },
    "cache_miss_storm": {
        "affected": ["cache"],
        "fix_sequence": ["restart_cache", "scale_up"],
        "log_hints": ["cache miss spike", "high backend load", "cache key not found"],
    },
    "memory_leak": {
        "affected": ["api", "db"],
        "fix_sequence": ["restart_api", "restart_db"],
        "log_hints": ["memory usage increasing", "OOM warning", "heap allocation failure"],
    },
}

_NOISE_POOL: List[str] = [
    "disk warning: 78% used",
    "temporary network glitch resolved",
    "unrelated service restarted (metrics-exporter)",
    "certificate renewal scheduled",
    "cron job completed",
    "health check passed for load-balancer",
    "rate limiter triggered on /api/v2/bulk",
]


def generate_incident() -> Dict[str, Any]:
    """Return a fresh incident state dict."""
    cause_key = random.choice(list(ROOT_CAUSES.keys()))
    cause_cfg = ROOT_CAUSES[cause_key]

    services = {s: "healthy" for s in ["api", "db", "cache"]}
    for s in cause_cfg["affected"]:
        services[s] = "degraded"

    logs = _generate_logs(cause_key, cause_cfg["log_hints"])
    metrics = _generate_metrics(cause_key)

    return {
        "services": services,
        "logs": logs,
        "metrics": metrics,
        "root_cause": cause_key,
        "fix_sequence": list(cause_cfg["fix_sequence"]),   # copy
        "resolved": False,
        "fix_progress": 0,
    }

def _generate_logs(cause: str, hints: List[str]) -> List[str]:
    logs = list(hints)

    # 20 % chance of a genuinely misleading entry
    if random.random() < 0.2:
        logs.append("corrupted log entry: [binary garbage]")

    # Always add 2 noise entries
    logs += random.sample(_NOISE_POOL, k=min(2, len(_NOISE_POOL)))
    random.shuffle(logs)
    return logs


def _generate_metrics(cause: str) -> Dict[str, float]:
    base = {
        "api_timeout":        {"latency": 350, "error_rate": 0.55, "cpu": 75},
        "db_connection_leak": {"latency": 280, "error_rate": 0.45, "cpu": 60},
        "cache_miss_storm":   {"latency": 220, "error_rate": 0.35, "cpu": 85},
        "memory_leak":        {"latency": 400, "error_rate": 0.65, "cpu": 92},
    }[cause]

    return {
        "latency":    base["latency"]    + random.randint(-20, 20),
        "error_rate": round(base["error_rate"] + random.uniform(-0.05, 0.05), 3),
        "cpu":        base["cpu"]        + random.randint(-5, 5),
    }