coli doctor: read-only setup/health diagnostics (path, config, shards, disk, RAM budget, placement) (#33)

* Add read-only coli doctor diagnostics

* Fix doctor JSON output assertion

c/coli

@@ -8,6 +8,7 @@ CLI per far girare GLM-5.2 (744B) in locale, su CPU, in ~15-26 GB di RAM.
   coli run "prompt"         generazione singola
   coli info                 stato: modello, RAM, disco, config
   coli plan                 piano risorse Disk / RAM / VRAM
+  coli doctor               diagnosi installazione e piano di esecuzione
   coli bench [task...]      benchmark di qualità (MMLU/HellaSwag/...)
   coli convert              converte GLM-5.2-FP8 -> int4 (streaming)
   coli build                compila il motore
@@ -334,6 +335,23 @@ def cmd_plan(a):
     print(textwrap.indent(format_plan(plan),"  "))
     print()
 
+def cmd_doctor(a):
+    from doctor import exit_code, format_doctor, run_doctor
+    try:
+        ram,ctx,devices,vram=resource_request(a,os.environ)
+        if ctx<1: raise ValueError("--ctx deve essere positivo")
+        if ram<0: raise ValueError("--ram non puo essere negativo")
+        if vram<0: raise ValueError("--vram non puo essere negativo")
+    except ValueError as error:
+        report={"schema_version":1,"status":"error","model":os.path.abspath(a.model),
+                "checks":[{"id":"config.arguments","status":"fail","summary":str(error)}],
+                "plan":None}
+        print(json.dumps(report,indent=2) if a.json else format_doctor(report))
+        return 2
+    report=run_doctor(a.model,ram,ctx,devices,vram,engine_path=GLM)
+    print(json.dumps(report,indent=2) if a.json else format_doctor(report))
+    return exit_code(report)
+
 def cmd_run(a):
     need_model(a.model)
     prompt=" ".join(a.prompt) if a.prompt else sys.exit('uso: coli run "il tuo prompt"')
@@ -507,6 +525,8 @@ def main():
     sub.add_parser("build", parents=[common]); sub.add_parser("info", parents=[common])
     pp=sub.add_parser("plan",parents=[common])
     pp.add_argument("--json",action="store_true")
+    pd=sub.add_parser("doctor",parents=[common])
+    pd.add_argument("--json",action="store_true",help="emette un report JSON versionato")
     pr=sub.add_parser("run", parents=[common]);  pr.add_argument("prompt", nargs="*")
     sub.add_parser("chat", parents=[common])
     ps=sub.add_parser("serve", parents=[common])
@@ -523,8 +543,11 @@ def main():
     pc.add_argument("--ebits",type=int,default=4); pc.add_argument("--io-bits",type=int,default=8); pc.add_argument("--xbits",type=int,default=0)
     pc.add_argument("--no-mtp",action="store_true",help="salta la testa MTP (niente draft speculativi)")
     a=ap.parse_args()
-    {"build":cmd_build,"info":cmd_info,"plan":cmd_plan,"run":cmd_run,"chat":cmd_chat,"serve":cmd_serve,"bench":cmd_bench,
-     "convert":cmd_convert}.get(a.cmd, lambda _:(banner(),print(__doc__)))(a)
+    handler={"build":cmd_build,"info":cmd_info,"plan":cmd_plan,"doctor":cmd_doctor,
+             "run":cmd_run,"chat":cmd_chat,"serve":cmd_serve,"bench":cmd_bench,
+             "convert":cmd_convert}.get(a.cmd)
+    if handler: sys.exit(handler(a) or 0)
+    banner(); print(__doc__)
 
 if __name__=="__main__":
     signal.signal(signal.SIGINT, signal.default_int_handler)