feat: Ollama und Modell vor dem Start prüfen, kurze Meldung statt Traceback

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

rede_korrigieren.py

@@ -8,6 +8,7 @@ import re
 import shutil
 import sys
 import time
+import urllib.error
 import urllib.request
 
 from aenderungen import REVIEW_MARK, print_summary, report_path, write_report
@@ -17,6 +18,7 @@ from yt_untertitel import YT_DLP, base_language, default_name, original_language
 
 MODEL = "qwen3:32b"
 OLLAMA_URL = "http://127.0.0.1:11434/api/chat"
+OLLAMA_TAGS_URL = "http://127.0.0.1:11434/api/tags"
 
 CHUNK_SIZE = 1200          # Zielgröße eines Abschnitts in Wörtern
 MAX_EXTRA_WORDS = 300      # so weit darf ein Abschnitt bis zum nächsten Satzende wachsen
@@ -237,6 +239,31 @@ def chat_request(payload):
     )
 
 
+def ollama_open(request, timeout=600):
+    """urlopen() for Ollama; a missing server ends the program with a short message."""
+    try:
+        return urllib.request.urlopen(request, timeout=timeout)
+    except urllib.error.HTTPError:
+        raise
+    except urllib.error.URLError as error:
+        raise SystemExit(
+            f"Ollama nicht erreichbar ({error.reason}). Läuft der Dienst? "
+            "Starten mit: sudo systemctl start ollama (oder: ollama serve)"
+        ) from None
+
+
+def check_ollama(model):
+    """Stop early, before any download, if Ollama is down or lacks the model."""
+    with ollama_open(OLLAMA_TAGS_URL, timeout=10) as response:
+        installed = {m.get("name") for m in json.load(response).get("models", [])}
+    wanted = model if ":" in model else f"{model}:latest"
+    if wanted not in installed:
+        raise SystemExit(
+            f"Modell „{model}“ ist in Ollama nicht installiert. "
+            f"Installieren mit: ollama pull {model}"
+        )
+
+
 def correct_chunk(chunk, index, system):
     payload = {
         "model": MODEL,
@@ -263,7 +290,7 @@ def correct_chunk(chunk, index, system):
     words = 0
     result = {}
 
-    with urllib.request.urlopen(request, timeout=600) as response:
+    with ollama_open(request) as response:
         for line in response:
             if not line.strip():
                 continue
@@ -328,7 +355,7 @@ def find_paragraph_starts(sentences, first, system):
             "num_predict": 2048,
         },
     }
-    with urllib.request.urlopen(chat_request(payload), timeout=600) as response:
+    with ollama_open(chat_request(payload)) as response:
         result = json.load(response)
 
     content = result["message"]["content"]
@@ -542,6 +569,7 @@ def main():
     # reuses cached parts of another
     MODEL = args.model
     print(f"Modell: {MODEL}")
+    check_ollama(MODEL)
     raw, target, lang = read_source(args)
     print(f"Sprache der Rede: {lang}")
     parts_dir = target.with_suffix(".parts")