learning cache + true sampling + DSA indexer extraction mode

- Learning cache: expert usage persists in <SNAP>/.coli_usage across sessions
  (atomic save every turn); at startup the hottest experts are auto-pinned in
  RAM with half the expert budget (AUTOPIN=0 disables). The engine gets faster
  the more you use it.
- Sampling: temperature + nucleus (official 1.0/0.95 defaults in chat; TEMP=0
  = greedy). MTP/n-gram speculation stays lossless via rejection sampling
  (accept draft w.p. p(draft); on reject resample with draft banned).
- coli: --temp flag.
- Converter: --indexer mode extracts DSA lightning-indexer weights
  (resumable; needed for future sparse attention beyond 2048 ctx).
- pin_load/stats include the MTP row; usage histogram covers layer 78.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

c/coli

@@ -101,6 +101,7 @@ def env_for(a):
     if a.ngen: e["NGEN"]=str(a.ngen)
     if a.topp: e["TOPP"]=str(a.topp)
     if a.topk: e["TOPK"]=str(a.topk)
+    if a.temp is not None: e["TEMP"]=str(a.temp)   # 0 = greedy; default motore: 1.0 + nucleus 0.95
     return e
 
 class Spinner:
@@ -279,6 +280,7 @@ def main():
     common.add_argument("--model", default=DEF_MODEL); common.add_argument("--ram", type=int, default=0)  # 0 = auto (il motore usa l'88% della RAM disponibile)
     common.add_argument("--cap", type=int, default=8); common.add_argument("--ngen", type=int, default=1024)  # rete di sicurezza: la fine vera la decidono gli stop token
     common.add_argument("--topp", type=float, default=0); common.add_argument("--topk", type=int, default=0)
+    common.add_argument("--temp", type=float, default=None)  # temperatura token (0=greedy, default 1.0+nucleus .95)
     ap=argparse.ArgumentParser(prog="coli", parents=[common], description="colibrì — GLM-5.2 in locale")
     sub=ap.add_subparsers(dest="cmd")
     sub.add_parser("build", parents=[common]); sub.add_parser("info", parents=[common])