"""Evidence classifier: hypotheses and confirmed observations are distinct."""
import json, sqlite3, time
from pathlib import Path

def diagnose(obs):
    pods=obs.get("pods",{}).get("pods",[])
    events=obs.get("events",{}).get("items",[])
    text=" ".join(e.get("message","") for e in events)
    if any(p.get("phase")=="Pending" for p in pods) and any(e.get("reason")=="FailedScheduling" for e in events):
        if obs.get("deployment",{}).get("selector")=={"lab.invalid/pool":"absent"} and ("selector" in text or "affinity" in text):
            return "selector_mismatch",["pods","events","deployment"]
        if "Insufficient nvidia.com/gpu" in text:return "gpu_insufficient",["pods","events"]
    for pod in pods:
        for c in pod.get("containers",[]):
            last=c.get("lastState",{}).get("terminated",{})
            if last.get("reason")=="OOMKilled" and last.get("exitCode")==137:return "oom_killed",["pods"]
            waiting=c.get("state",{}).get("waiting",{}).get("reason")
            if waiting in ("ErrImagePull","ImagePullBackOff"):return "image_pull_failure",["pods"]
            if waiting=="CrashLoopBackOff" and "logs" in obs:return "restart_backoff",["pods","logs"]
    if "no such host" in str(obs.get("logs",{})):return "dns_lookup_failed",["logs"]
    if obs.get("endpoints",{}).get("service_exists") and not any(e.get("conditions",{}).get("ready") for s in obs["endpoints"]["items"] for e in s.get("endpoints",[])):
        return "no_ready_endpoints",["endpoints"]
    return None,[]

def compact(obs,limit=3500):
    # Keep diagnosis-relevant fields before enforcing a character budget.
    result={}
    for k,v in obs.items():
        if k=="pods":v=[{"phase":p["phase"],"conditions":p.get("conditions",[])[:2],"states":[(c.get("state"),c.get("lastState")) for c in p.get("containers",[])[:2]]} for p in v["pods"][:2]]
        if k=="deployment":v={n:v.get(n) for n in ("uid","selector","generation")}
        result[k]=json.dumps(v,ensure_ascii=False)[:max(100,limit//max(1,len(obs)))]
    return result
def memory(mode,record=None):
    Path("data").mkdir(exist_ok=True)
    with sqlite3.connect("data/cluster-memory.sqlite") as c:
        c.execute("CREATE TABLE IF NOT EXISTS cases(id TEXT PRIMARY KEY,category TEXT,source TEXT,verified REAL)")
        if mode=="save":
            c.execute("INSERT OR REPLACE INTO cases VALUES(?,?,?,?)",(record["id"],record["category"],record["source"],time.time()))
        else:
            return c.execute("SELECT category,source FROM cases WHERE verified>? ORDER BY verified DESC LIMIT 3",(time.time()-86400*30,)).fetchall()