feat(harness): tht ollama ensure CLI command (hard-fail preflight)

harness/tht/cli/ollama_cmd.py

@@ -5,8 +5,17 @@ error (the caller refuses the session). "Load" = warm the already-installed mode
 """
 from __future__ import annotations
 
+import json
 import subprocess
 import time
+from pathlib import Path
+
+import typer
+
+from tht.cli.config_cmd import CONFIG_OPT
+from tht.cli.schema_cmd import _load_config_or_exit
+
+ollama_app = typer.Typer(help="Ollama (embeddings) -- preflight.")
 
 
 # --- low-level ops (real implementations; injected as fakes in tests) ----------
@@ -118,3 +127,29 @@ def ensure_ollama(
                 "error": f"warm del modello '{emb.model}' fallito: {e}"}
 
     return {"ok": True, "server": server_state, "model": "warmed", "model_name": emb.model}
+
+
+# --- CLI command ----------
+
+
+@ollama_app.command("ensure")
+def ensure_cmd(
+    timeout: int = typer.Option(60, "--timeout", help="Secondi di attesa per l'avvio di Ollama."),
+    no_start: bool = typer.Option(False, "--no-start", help="Non avviare Ollama (solo verifica)."),
+    json_out: bool = typer.Option(False, "--json", help="Emetti JSON puro su stdout."),
+    config: Path = CONFIG_OPT,
+) -> None:
+    """Assicura Ollama attivo + modello di embedding caricato; errore se non possibile."""
+    cfg = _load_config_or_exit(config)
+    result = ensure_ollama(cfg, timeout=timeout, no_start=no_start)
+    if json_out:
+        typer.echo(json.dumps(result, ensure_ascii=False))
+    elif result["ok"]:
+        typer.secho(
+            f"OK: Ollama {result['server']}, modello {result['model_name']} {result['model']}.",
+            fg=typer.colors.GREEN,
+        )
+    else:
+        typer.secho(f"ERRORE [{result['stage']}]: {result['error']}", fg=typer.colors.RED, err=True)
+    if not result["ok"]:
+        raise typer.Exit(code=1)