router: Multipart-Parser auf email.parser.BytesParser umgestellt

- Robustes MIME-Parsing mit Standardbibliothek (email.parser.BytesParser)
- Handhabt quoted und unquoted Boundaries (Open-WebUI-Kompatibilität)
- Beliebiges Feldreihenfolge, zusätzliche Header, binäre Payloads
- Regressionstests: dev/test_multipart.py (8 Tests)
- Fix für Open-WebUI HTTP 400 bei POST /v1/audio/transcriptions

router/ai_profile_router.py

@@ -45,6 +45,7 @@ Nur Python-Standardbibliothek. Logging nach stdout (journald).
 from __future__ import annotations
 
 import base64
+import email
 import json
 import logging
 import os
@@ -56,6 +57,8 @@ import threading
 import time
 import uuid
 import http.client
+from email.parser import BytesParser
+from email.policy import compat32
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 
 # ---------------------------------------------------------------------------
@@ -1127,42 +1130,47 @@ class Handler(BaseHTTPRequestHandler):
 
     def _parse_multipart(self, data: bytes, content_type: str
                          ) -> tuple[bytes, str, dict]:
-        """Parst multipart/form-data. Liefert (file_data, filename, fields)."""
-        boundary = None
-        for part in content_type.split(";"):
-            part = part.strip()
-            if part.startswith("boundary="):
-                boundary = part[len("boundary="):]
-                break
-        if not boundary:
-            raise ValueError("Kein Boundary in Content-Type")
+        """Parst multipart/form-data. Liefert (file_data, filename, fields).
+
+        Nutzt email.parser.BytesParser (Standardbibliothek) für robustes
+        MIME-Parsing. Handhabt quoted und unquoted Boundaries, beliebige
+        Feldreihenfolge, zusätzliche Header und binäre Payloads.
+        """
+        # MIME-Message aus rohen Bytes + Content-Type-Header bauen
+        raw = (f"Content-Type: {content_type}\r\n\r\n"
+               ).encode("utf-8") + data
+        msg = BytesParser(policy=compat32).parsebytes(raw)
+        if not msg.is_multipart():
+            raise ValueError("Kein multipart/form-data")
 
-        boundary_bytes = boundary.encode("utf-8")
         file_data = b""
         filename = ""
         fields = {}
 
-        parts = data.split(b"--" + boundary_bytes)
-        for part in parts:
-            if part in (b"", b"--", b"--\r\n", b"\r\n"):
+        for part in msg.get_payload():
+            disposition = part.get("Content-Disposition", "")
+            name = None
+            part_filename = None
+            for kv in disposition.split(";"):
+                kv = kv.strip()
+                if kv.startswith("name="):
+                    name = kv[len("name="):].strip('"')
+                elif kv.startswith("filename="):
+                    part_filename = kv[len("filename="):].strip('"')
+            if name is None:
                 continue
-            if b"\r\n\r\n" not in part:
-                continue
-            header_part, body_part = part.split(b"\r\n\r\n", 1)
-            if body_part.endswith(b"\r\n"):
-                body_part = body_part[:-2]
 
-            header_text = header_part.decode("utf-8", errors="replace")
-            for line in header_text.split("\r\n"):
-                if "name=" in line and "filename=" in line:
-                    for kv in line.split(";"):
-                        kv = kv.strip()
-                        if kv.startswith("filename="):
-                            filename = kv[len("filename="):].strip('"')
-                    file_data = body_part
-                elif "name=" in line:
-                    name = line.split("name=")[1].strip().strip('"')
-                    fields[name] = body_part.decode("utf-8", errors="replace")
+            payload = part.get_payload(decode=True)
+            if payload is None:
+                payload = b""
+
+            if part_filename is not None:
+                # Dateifeld (binär, nicht dekodieren)
+                file_data = payload
+                filename = part_filename or ""
+            else:
+                # Textfeld
+                fields[name] = payload.decode("utf-8", errors="replace")
 
         return file_data, filename, fields