fix(projekt-matching): use response_format json_schema (vLLM 0.22 ignores guided_json)

projekt-matching/projektmatch/llm.py

@@ -123,24 +123,23 @@ z. B. vLLM, TGI, Triton" ab).
 - reason: EIN kurzer deutscher Satz mit der Begründung."""
 
 
-def _post(base, model, messages, body_extra):
-    body = {"model": model, "messages": messages, "temperature": 0.1}
-    body.update(body_extra)
+def _post(base, model, messages, schema):
+    body = {"model": model, "messages": messages, "temperature": 0.1,
+            "response_format": {"type": "json_schema", "json_schema": {
+                "name": "out", "schema": schema}}}
     return requests.post(f"{base.rstrip('/')}/chat/completions", json=body,
                          timeout=1500)
 
 
 def chat_json(base, model, messages, schema):
-    resp = _post(base, model, messages, {"guided_json": schema})
-    if resp.status_code == 400 and "guided_json" in getattr(resp, "text", ""):
-        resp = _post(base, model, messages, {"response_format": {
-            "type": "json_schema",
-            "json_schema": {"name": "out", "schema": schema}}})
+    resp = _post(base, model, messages, schema)
     if resp.status_code != 200:
         raise LlmError(f"vLLM HTTP {resp.status_code}: "
                        f"{getattr(resp, 'text', '')[:300]}")
     content = resp.json()["choices"][0]["message"]["content"] or ""
     content = THINK_RE.sub("", content).strip()
+    if content.startswith("```"):
+        content = re.sub(r"^```[a-z]*\s*|\s*```$", "", content).strip()
     try:
         return json.loads(content)
     except json.JSONDecodeError as exc: