prefill progress: engine reports layer N/78 on stderr, coli spinner shows it live

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

c/coli

@@ -106,14 +106,20 @@ def env_for(a):
 
 class Spinner:
     FRAMES=["⠋","⠙","⠹","⠸","⠼","⠴","⠦","⠧","⠇","⠏"]
-    def __init__(self,label): self.label=label; self.stop_evt=threading.Event(); self.t0=time.time(); self.th=None
+    def __init__(self,label,tick=None):
+        self.label=label; self.tick=tick; self.suffix=""
+        self.stop_evt=threading.Event(); self.t0=time.time(); self.th=None
     def start(self):
         if not TTY: return
         def run():
             i=0
             while not self.stop_evt.is_set():
                 el=time.time()-self.t0
-                sys.stdout.write(f"\r  {C.teal}{self.FRAMES[i%10]}{C.r} {C.dim}{self.label} {el:.0f}s{C.r}\033[K")
+                if self.tick and i%8==0:              # ~1 Hz: legge il progresso dal log
+                    try: self.suffix=self.tick() or self.suffix
+                    except Exception: pass
+                suf=f" {C.dgray}· {self.suffix}{C.r}" if self.suffix else ""
+                sys.stdout.write(f"\r  {C.teal}{self.FRAMES[i%10]}{C.r} {C.dim}{self.label} {el:.0f}s{C.r}{suf}\033[K")
                 sys.stdout.flush(); i+=1; time.sleep(0.12)
         self.th=threading.Thread(target=run,daemon=True); self.th.start()
     def stop(self):
@@ -244,7 +250,14 @@ def cmd_chat(a):
             print(f"\n  {C.teal}◆ colibrì{C.r}")
             dec=codecs.getincrementaldecoder("utf-8")("replace")
             state={"first":True}
-            sp2=Spinner("pensa…"); sp2.start()
+            def prefill_tick(path=errlog.name):
+                try:
+                    with open(path) as f:
+                        f.seek(max(0, os.path.getsize(path)-1500)); tail=f.read()
+                    pl=[l for l in tail.splitlines() if l.startswith("[prefill]")]
+                    return pl[-1].replace("[prefill] ","prefill ") if pl else ""
+                except Exception: return ""
+            sp2=Spinner("pensa…", tick=prefill_tick); sp2.start()
             def echo(bs, _dec=dec, _st=state):
                 if _st["first"]:
                     sp2.stop(); _st["first"]=False

c/glm.c

@@ -725,7 +725,13 @@ static void layer_forward(Model *m, Layer *l, int li, float *x, int S, int pos_b
 static void layers_forward(Model *m, float *x, int S, int pos_base){
     Cfg *c=&m->c; int D=c->hidden;
     float *nrm=falloc((int64_t)S*D), *tmp=falloc((int64_t)S*D);
-    for(int i=0;i<c->n_layers;i++) layer_forward(m,&m->L[i],i,x,S,pos_base,nrm,tmp);
+    for(int i=0;i<c->n_layers;i++){
+        /* progresso su stderr per i batch grossi (prefill): il primo byte di risposta
+         * puo' arrivare dopo MINUTI di streaming — al buio sembra un blocco. */
+        if(S>=8 && (i%4==0 || i==c->n_layers-1))
+            fprintf(stderr,"[prefill] layer %d/%d · %d token\n", i+1, c->n_layers, S);
+        layer_forward(m,&m->L[i],i,x,S,pos_base,nrm,tmp);
+    }
     free(nrm); free(tmp);
 }