#!/usr/bin/env bash
# radio-usage.sh — per-AP client-USAGE history for a band, from accumulated controller stats
# (ace_stat.stat_daily, ~77d retention). Answers "is this radio actually used?" so you can tell a
# truly-idle radio (safe to DISABLE) apart from a lightly-but-genuinely-used one (POWER-DOWN, not off).
#
# Two metrics per AP, because they say different things:
#   avg = time-averaged concurrent users (<radioName>-num_sta_avg) — how busy the radio is on average
#   peak = max station snapshot (<band>-num_sta)                    — did ANY device ever land here
# A radio with avg~0 but peak>0 is NOT unused: it takes occasional bursts (legacy/IoT/roamers). Disabling
# it strands those clients onto a farther AP. Only peak==0 over the window = genuinely unused.
#
# With NEIGHBOR_JSON=<path> (from neighbor-collect.sh NBR_JSON=...), cross the low-usage APs against the
# AP-to-AP SNR matrix to emit a DEFENSIBLE safe-to-disable shortlist: a low-usage AP whose strong
# overlapping neighbor has the headroom to absorb its rare clients. This is the data-backed version of
# the optimize-radios DISABLE gate, driven by real client history instead of the roam graph.
#
# Read-only. Mongo plane (no controller cred), like model-rank/optimize-radios.
# Usage: bash radio-usage.sh <site-name|id> [band=ng|na|6e] [days=30]
#   NEIGHBOR_JSON=<path>  also print the safe-to-disable shortlist
#   LOW_AVG=0.5  NBR_SNR_MIN=30  HEADROOM=4   thresholds (avg-users "low", strong-neighbor SNR, absorb cap)
set -uo pipefail
REPO="$(git rev-parse --show-toplevel 2>/dev/null || echo .)"
UOS="$REPO/.claude/scripts/uos-mongo.sh"; VAULT="$REPO/.claude/scripts/vault.sh"
HOST="${UOS_HOST:-172.16.3.29}"; PORT="${UOS_HTTPS_PORT:-11443}"
SITEARG="${1:?usage: radio-usage.sh <site> [band=ng|na|6e] [days=30] [--ap <name>]}"; shift
BAND="ng"; DAYS="30"; APNAME=""; POS=()
while [ $# -gt 0 ]; do case "$1" in
  --ap) APNAME="${2:?--ap needs an AP name}"; shift 2;;
  *) POS+=("$1"); shift;; esac; done
[ ${#POS[@]} -ge 1 ] && BAND="${POS[0]}"; [ ${#POS[@]} -ge 2 ] && DAYS="${POS[1]}"
case "$BAND" in ng|na|6e) ;; *) echo "[ERROR] band must be ng|na|6e"; exit 1;; esac
if [[ "$SITEARG" =~ ^[0-9a-f]{24}$ ]]; then SITE="$SITEARG"; else
  SITE="$(bash "$UOS" --sites 2>/dev/null | grep -vi 'pq.html' | grep -i "$SITEARG" | awk '{print $1}' | head -1)"; fi
[ -n "$SITE" ] || { echo "[ERROR] site not found: $SITEARG"; exit 1; }
TMP="$(mktemp -d)"; trap 'rm -rf "$TMP"' EXIT

# ============ DEVICE mode: --ap <name> -> which devices used this AP's <band> (recent) + capability ============
if [ -n "$APNAME" ]; then
  echo "[INFO] radio-usage DEVICE history: site=$SITE band=$BAND AP='$APNAME'"
  case "$BAND" in ng) BTOK=BAND_NG;; na) BTOK=BAND_NA;; 6e) BTOK=BAND_6E;; esac
  CU="$(bash "$VAULT" get-field infrastructure/uos-server-network-api-rw credentials.username 2>/dev/null)"
  CP="$(bash "$VAULT" get-field infrastructure/uos-server-network-api-rw credentials.password 2>/dev/null)"
  [ -n "$CU" ] && [ -n "$CP" ] || { echo "[BLOCKED] --ap needs controller cred at infrastructure/uos-server-network-api-rw (for the live BSSID map + current clients)"; exit 2; }
  base="https://$HOST:$PORT"; CJ="$TMP/cj"
  code=$(curl -sk -c "$CJ" -o /dev/null -w '%{http_code}' -X POST "$base/api/auth/login" -H 'Content-Type: application/json' \
    --data-binary "$(python -c 'import json,sys;print(json.dumps({"username":sys.argv[1],"password":sys.argv[2]}))' "$CU" "$CP")")
  [ "$code" = "200" ] || { echo "[ERROR] controller login HTTP $code"; exit 1; }
  SHORT="$(curl -sk -b "$CJ" "$base/proxy/network/api/self/sites" | python -c "import sys,json;[print(s['name']) for s in json.load(sys.stdin).get('data',[]) if s.get('_id')=='$SITE']")"
  [ -n "$SHORT" ] || SHORT="$SITEARG"
  curl -sk -b "$CJ" "$base/proxy/network/api/s/$SHORT/stat/device" -o "$TMP/dev.json"
  curl -sk -b "$CJ" "$base/proxy/network/api/s/$SHORT/stat/sta" -o "$TMP/sta.json"
  RES="$(python - "$TMP/dev.json" "$TMP/sta.json" "$APNAME" "$BAND" "$TMP/bssids.txt" "$TMP/live.tsv" <<'PY'
import sys,json
dev=json.load(open(sys.argv[1])).get('data',[]); sta=json.load(open(sys.argv[2])).get('data',[])
apname=sys.argv[3].lower(); band=sys.argv[4]
ap=next((a for a in dev if a.get('type')=='uap' and (a.get('name','').lower()==apname)),None)
if not ap: print("ERR not-found"); sys.exit(0)
apmac=ap.get('mac')
bss=[v.get('bssid','').lower() for v in (ap.get('vap_table') or []) if v.get('radio')==band and v.get('bssid')]
open(sys.argv[5],'w',newline='\n').write('\n'.join(bss))
live=[s for s in sta if s.get('ap_mac')==apmac and s.get('radio')==band]
open(sys.argv[6],'w',newline='\n').write('\n'.join(f"{s.get('mac')}\t{s.get('signal')}\t{s.get('channel')}\t{(s.get('oui') or '')}" for s in live))
print(f"OK {apmac} bssids={len(bss)} live={len(live)}")
PY
)"
  echo "  [live] $RES"
  case "$RES" in ERR*) echo "[ERROR] AP '$APNAME' not found at this site (check exact name from audit-site/live-stats)"; exit 1;; esac
  BSSID_JS="$(python -c "import sys;print(','.join('\"%s\"'%b for b in open(sys.argv[1]).read().split()))" "$TMP/bssids.txt")"
  # Plane 1: band-aware association events (retention ~1 day) + cross-band capability + ace.user identity
  cat <<JS | bash "$UOS" 2>&1 | grep -viE 'pq.html|post-quantum|store now|server may need' > "$TMP/hist.tsv"
var ace=db.getSiblingDB('ace'), st=db.getSiblingDB('ace_stat'), SITE="$SITE";
var bset={}; [$BSSID_JS].forEach(function(b){bset[String(b).toLowerCase()]=1;});
var hist={};
st.wifi_connectivity_event.find({site_id:SITE,'to_endpoint.band':"$BTOK"}).forEach(function(e){
  var b=((e.to_endpoint&&e.to_endpoint.mac)||'').toLowerCase(); if(!bset[b])return;
  var m=e.client_mac; if(!m)return;
  if(!hist[m])hist[m]={n:0,last:0}; hist[m].n++; if(e.time>hist[m].last)hist[m].last=e.time;
});
var macs=Object.keys(hist), dual={};
if(macs.length){ st.wifi_connectivity_event.find({site_id:SITE,client_mac:{\$in:macs},
    \$or:[{'to_endpoint.band':{\$in:['BAND_NA','BAND_6E']}},{'from_endpoint.band':{\$in:['BAND_NA','BAND_6E']}}]},{client_mac:1}).forEach(function(e){dual[e.client_mac]=1;}); }
macs.forEach(function(m){ var u=ace.user.findOne({site_id:SITE,mac:m})||{};
  print("DEV\t"+m+"\t"+new Date(hist[m].last).toISOString()+"\t"+hist[m].n+"\t"+(dual[m]?'DUAL':'NG-ONLY')+"\t"+((u.hostname||'').replace(/\t/g,' '))+"\t"+(u.oui||'')+"\t"+(u.last_seen?new Date(u.last_seen*1000).toISOString().slice(0,10):''));
});
JS
  python - "$TMP/hist.tsv" "$TMP/live.tsv" "$APNAME" "$BAND" <<'PY'
import sys
hist=[]
for ln in open(sys.argv[1],encoding='utf-8',errors='replace'):
    if not ln.startswith('DEV\t'): continue
    p=ln.rstrip('\n').split('\t')
    while len(p)<8: p.append('')
    hist.append({'mac':p[1],'last':p[2],'n':int(p[3] or 0),'cap':p[4],'host':p[5],'oui':p[6],'seen':p[7]})
live={}
for ln in open(sys.argv[2],encoding='utf-8',errors='replace'):
    q=ln.rstrip('\n').split('\t')
    if len(q)>=2 and q[0]: live[q[0]]={'sig':q[1],'ch':q[2] if len(q)>2 else '','oui':q[3] if len(q)>3 else ''}
ap,band=sys.argv[3],sys.argv[4]
# union: anything in events + anything live-on-now (covers clients present but with no assoc event in window)
allmacs={h['mac'] for h in hist} | set(live)
def pad(s,w): s=str(s); return s+' '*max(0,w-len(s))
print(f"\n==== Devices on '{ap}' {band} ====   (assoc events retained ~1 day; 'on now' from live)")
print(pad("MAC",19)+pad("name/oui",22)+pad("assoc",7)+pad("last_assoc(UTC)",22)+pad("on_now",9)+"capability")
def randomized(mac):
    try: return (int(mac.split(':')[0],16) & 0x02)!=0   # locally-administered bit = randomized (modern phones/laptops)
    except: return False
byh={h['mac']:h for h in hist}
steer=legacy=0
for m in sorted(allmacs, key=lambda x:(-(byh.get(x,{}).get('n',0)))):
    h=byh.get(m,{}); l=live.get(m)
    nm=(h.get('host') or h.get('oui') or (l or {}).get('oui') or '')[:21]
    cap=h.get('cap','')
    if cap=='DUAL': captag='5G-capable (event) -> STEERABLE'; steer+=1
    elif cap=='NG-ONLY': captag='2.4-only (event) -> legacy/IoT?'; legacy+=1
    elif randomized(m): captag='randomized MAC -> modern, likely 5G/STEERABLE'; steer+=1
    else:
        v=(h.get('oui') or (l or {}).get('oui') or m[:8]); captag=f'fixed-OUI {v} -> likely IoT/legacy'; legacy+=1
    onnow = (l['sig']+'dBm') if l else '-'
    print(pad(m,19)+pad(nm,22)+pad(h.get('n','-'),7)+pad(h.get('last','-'),22)+pad(onnow,9)+captag)
print(f"\nSUMMARY: {len(allmacs)} device(s) on {band} for '{ap}'  |  likely-steerable={steer}  likely-legacy/IoT={legacy}  on-now={len(live)}")
print("  capability = DUAL/NG-ONLY from assoc events when present, else inferred from MAC (randomized=modern, fixed-OUI=IoT).")
print("  -> STEERABLE: fix via band-steering / min-RSSI (apply-wlan bandsteer, apply-radio minrssi), not the radio.")
print("  -> legacy/IoT must keep a 2.4 radio in range -> argues AGAINST disabling this radio if any are present.")
print("  [retention] connectivity events are short-lived here; run during/after busy hours for a fuller event-based read.")
PY
  exit 0
fi
# ============ AGGREGATE mode (default) ============
echo "[INFO] radio-usage site=$SITE band=$BAND window=${DAYS}d"

# ---- Mongo: per-AP avg(time-avg users) + peak(station snapshot) over the window. Emits ROW<TAB>... ----
cat <<JS | bash "$UOS" 2>&1 | grep -viE 'pq.html|post-quantum|store now|server may need' > "$TMP/rows.txt"
var ace=db.getSiblingDB('ace'), st=db.getSiblingDB('ace_stat');
var SITE="$SITE", BAND="$BAND", DAYS=$DAYS, since=new Date().getTime()-DAYS*86400000;
var name={}, rname={}, rstate={};
ace.device.find({site_id:SITE,type:'uap'},{mac:1,name:1,radio_table:1}).forEach(function(a){
  name[a.mac]=a.name||a.mac;
  (a.radio_table||[]).forEach(function(r){ if(r.radio==BAND){ rname[a.mac]=r.name; rstate[a.mac]=r.tx_power_mode||'auto'; }});
});
var agg={};
st.stat_daily.find({o:'ap',site_id:SITE,time:{\$gte:since}}).forEach(function(d){
  var ap=d.ap; if(!ap||name[ap]===undefined)return; var nm=rname[ap]; if(!nm)return;
  var av=d[nm+'-num_sta_avg'], pk=d[BAND+'-num_sta'];
  if(!agg[ap])agg[ap]={s:0,sn:0,pk:0,days:0,n:0};
  var a=agg[ap]; if(av!=null){a.s+=av;a.sn++;} if(pk!=null){if(pk>a.pk)a.pk=pk; if(pk>0)a.days++;} a.n++;
});
Object.keys(agg).forEach(function(m){ var a=agg[m];
  var avg=a.sn? (a.s/a.sn):-1;
  print("ROW\t"+name[m]+"\t"+avg.toFixed(3)+"\t"+a.pk+"\t"+a.days+"\t"+a.n+"\t"+(rstate[m]||'?'));
});
JS

# ---- Python: format report + (optional) neighbor-matrix safe-to-disable shortlist ----
LOW_AVG="${LOW_AVG:-0.5}"; NBR_SNR_MIN="${NBR_SNR_MIN:-30}"; HEADROOM="${HEADROOM:-4}"
python - "$TMP/rows.txt" "${NEIGHBOR_JSON:-NONE}" "$LOW_AVG" "$NBR_SNR_MIN" "$HEADROOM" "$BAND" <<'PY'
import sys,json
rows=[]
for ln in open(sys.argv[1],encoding='utf-8',errors='replace'):
    if not ln.startswith('ROW\t'): continue
    _,ap,avg,pk,days,n,st=ln.rstrip('\n').split('\t')
    rows.append({'ap':ap,'avg':float(avg),'pk':int(pk),'days':int(days),'n':int(n),'st':st})
if not rows: print("[WARN] no daily stats in window (retention may be shorter)."); sys.exit(0)
NJ,LOW,SNR,HEAD,BAND=sys.argv[2],float(sys.argv[3]),float(sys.argv[4]),float(sys.argv[5]),sys.argv[6]
rows.sort(key=lambda r:(r['avg'],r['pk']))
idle=[r for r in rows if r['pk']==0]
low=[r for r in rows if r['pk']>0 and 0<=r['avg']<LOW and r['st']!='disabled']
def pad(s,w): s=str(s); return s+' '*max(0,w-len(s))
print(f"\n==== {BAND} USAGE per AP ({len(rows)} APs)  avg=time-avg concurrent users, peak=max snapshot ====")
print(pad("AP",26)+pad("avg_users",11)+pad("peak",7)+pad("days_used/total",18)+"radio")
for r in rows:
    tag=' [IDLE]' if r['pk']==0 else (' [low-use]' if (0<=r['avg']<LOW and r['st']!='disabled') else '')
    print(pad(r['ap'],26)+pad(f"{r['avg']:.2f}",11)+pad(r['pk'],7)+pad(f"{r['days']}/{r['n']}",18)+r['st']+tag)
print(f"\nSUMMARY: {len(idle)} radio(s) NEVER used (peak==0) -> genuinely disable-safe; "
      f"{len(low)} low-avg(<{LOW}) but with real peaks -> POWER-DOWN, not disable (bursts land here).")
if idle:
    print("  never-used: "+", ".join(f"{r['ap']}({r['st']})" for r in idle))

if NJ!='NONE':
    try: M=json.load(open(NJ))
    except Exception as e: print(f"\n[WARN] could not read NEIGHBOR_JSON {NJ}: {e}"); sys.exit(0)
    # union strong neighbors across bands (physical overlap is band-independent)
    avgby={r['ap']:r for r in rows}
    def strong_nbrs(ap):
        out={}
        for b,nb in (M.get(ap) or {}).items():
            for nm,snr in nb.items():
                try: s=float(snr)
                except: continue
                if s>=SNR: out[nm]=max(out.get(nm,-999),s)
        return out
    print(f"\n==== SAFE-TO-DISABLE SHORTLIST (low-use AP + strong neighbor w/ headroom; SNR>={SNR:.0f}) ====")
    found=0
    for r in low+idle:
        if r['st']=='disabled': continue
        nbrs=strong_nbrs(r['ap'])
        # an absorber = active strong neighbor whose avg + this AP's avg stays under HEADROOM
        absorbers=[(nm,avgby[nm]['avg']) for nm in nbrs
                   if nm in avgby and avgby[nm]['st']!='disabled' and (avgby[nm]['avg']+max(r['avg'],0))<=HEAD]
        if absorbers:
            found+=1
            ab=", ".join(f"{nm}(avg {a:.2f})" for nm,a in sorted(absorbers,key=lambda x:x[1])[:3])
            print(f"  {r['ap']}  avg={r['avg']:.2f} peak={r['pk']}  -> covered by: {ab}")
    if not found:
        print("  (none clear the bar — every low-use radio's strong neighbors lack headroom, or no SNR overlap.")
        print("   That CONFIRMS the conservative call: power-down, don't disable.)")
    print(f"\n[note] shortlist = candidates, not orders. Many are each other's absorbers (mutual coverage),")
    print(f"       so only a NON-CONFLICTING SUBSET can be disabled — once you disable one, its neighbors are")
    print(f"       no longer spare. optimize-radios.sh does the greedy conflict-free selection (with the same")
    print(f"       SNR matrix via NEIGHBOR_JSON); use this list to understand WHY. Disable one at a time, watch")
    print(f"       the neighbor absorb the load (live-stats/watch-ap) before+after. Rare bursts WILL reassociate.")
PY
echo ""
echo "[tip] add the SNR matrix for the disable shortlist:"
echo "  NBR=\$(mktemp -u).json; NBR_JSON=\$NBR bash .../neighbor-collect.sh $SITEARG; NEIGHBOR_JSON=\$NBR bash .../radio-usage.sh $SITEARG $BAND $DAYS"