#!/usr/bin/env python3
"""
Model 935 Pipeline — Phase 1: Dissect all + Download Kimi K2.5
CSCI v1.0 — Cross-Scale Coherence Index
"""
import subprocess, os, sys, json, time, glob

MODELS_DIR = "/mnt/models"
ORGANS_DIR = "/mnt/data/organ-architecture/organs"
EXTRACT = "/mnt/data/organ-architecture/organ_extract.py"
MEASURE = "/mnt/data/organ-architecture/organ_measure.py"

os.makedirs(ORGANS_DIR, exist_ok=True)

# Map all local GGUF models
models = {}
for f in sorted(glob.glob(os.path.join(MODELS_DIR, "*.gguf"))):
    name = os.path.basename(f)
    # Skip chimeras and old 935 attempts
    if "chimera" in name.lower() or "935" in name.lower():
        continue
    # Clean name for directory
    clean = name.replace(".gguf", "").replace("-Q4_K_M", "").replace("-Q8_0", "")
    clean = clean.replace("-Instruct", "").replace("-it", "").replace("-v0.3", "")
    clean = clean.lower().replace(".", "")
    models[name] = clean

print(f"Found {len(models)} models to dissect")
print("=" * 60)

results = []
for gguf_name, organ_name in models.items():
    gguf_path = os.path.join(MODELS_DIR, gguf_name)
    organ_path = os.path.join(ORGANS_DIR, organ_name)
    manifest = os.path.join(organ_path, "manifest.json")
    
    if os.path.exists(manifest):
        size = sum(os.path.getsize(os.path.join(dp,f)) for dp,dn,fn in os.walk(organ_path) for f in fn)
        print(f"[EXISTS] {organ_name} ({size/1024/1024:.0f}MB)")
        results.append({"model": organ_name, "status": "exists", "size_mb": size/1024/1024})
        continue
    
    print(f"\n[DISSECT] {gguf_name} → {organ_name}")
    t0 = time.time()
    
    r = subprocess.run(
        ["python3", EXTRACT, "--model", gguf_path, "--output", organ_path],
        capture_output=True, text=True, timeout=600
    )
    elapsed = time.time() - t0
    
    if r.returncode == 0:
        lines = r.stdout.strip().split("\n")
        for line in lines[-8:]:
            print(f"  {line}")
        size = sum(os.path.getsize(os.path.join(dp,f)) for dp,dn,fn in os.walk(organ_path) for f in fn)
        results.append({"model": organ_name, "status": "ok", "size_mb": size/1024/1024, "time": elapsed})
    else:
        print(f"  [ERROR] {r.stderr[-200:]}")
        results.append({"model": organ_name, "status": "error"})

# Z-measure all
print(f"\n{'='*60}")
print(f"PHASE 2: Z-MEASURE ALL ORGANS")
print(f"{'='*60}")

sys.path.insert(0, "/mnt/data/organ-architecture")
from organ_measure import measure_directory

z_report = {}
for d in sorted(os.listdir(ORGANS_DIR)):
    organ_path = os.path.join(ORGANS_DIR, d)
    manifest = os.path.join(organ_path, "manifest.json")
    if not os.path.exists(manifest):
        continue
    
    print(f"\n[Z] {d}")
    measures = measure_directory(organ_path)
    
    if not measures:
        continue
    
    groups = {}
    for r in measures:
        dirname = os.path.dirname(r['file']).split('/')[-1]
        if dirname not in groups:
            groups[dirname] = []
        groups[dirname].append(r)
    
    summary = {
        "model": d,
        "avg_theta": sum(r['theta_deg'] for r in measures) / len(measures),
        "avg_signal": sum(r['signal_ratio'] for r in measures) / len(measures),
        "total_tensors": len(measures),
        "groups": {}
    }
    
    for gname in ['skeleton', 'organs', 'embed', 'norm']:
        if gname in groups:
            g = groups[gname]
            summary["groups"][gname] = {
                "count": len(g),
                "avg_theta": round(sum(r['theta_deg'] for r in g) / len(g), 1),
                "avg_signal": round(sum(r['signal_ratio'] for r in g) / len(g), 3)
            }
            print(f"  {gname:12s}: {len(g):3d} tensors | θ={summary['groups'][gname]['avg_theta']:5.1f}°")
    
    print(f"  GLOBAL: θ={summary['avg_theta']:.1f}°")
    z_report[d] = summary

# Save
with open("/mnt/data/organ-architecture/z_report_complete.json", "w") as f:
    json.dump(z_report, f, indent=2)

# Print ranking
print(f"\n{'='*60}")
print(f"  Z-RANKING — ALL MODELS")
print(f"{'='*60}")
ranked = sorted(z_report.values(), key=lambda m: m['avg_theta'], reverse=True)
for i, m in enumerate(ranked, 1):
    print(f"  {i:2d}. θ={m['avg_theta']:5.1f}° signal={m['avg_signal']:.3f} {m['model']}")

print(f"\n  Signature: 935")
print(f"{'='*60}")
# ╔══ SALKA ELMADANI AUTHORSHIP CERTIFICATE ══╗
# © Salka Elmadani 2025-2026 — ALL RIGHTS RESERVED
# Licensed under Business Source License 1.1 — https://inference-x.com
# ─────────────────────────────────────────────────────────
# SHA256: 70a8957904cd4ee20dfd8fa42a0d8551cf8ae03eb2d0ec6fc9f4ed8f86995037
# SIG-ED25519: ddMrNVlt0PpN5uHTbAnxLkphci22Xv0efiEyfUAoHVJxextDZsK69jVULKiXZDED1txsfGzrenMjJMaKe5g4DQ==
# VERIFY: python3 verify_authorship.py pipeline_935.py