Add container diarization configuration

src/mka/application/config.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import json
 import os
 from dataclasses import dataclass
 from pathlib import Path
@@ -26,6 +27,7 @@ class AppSettings:
     diarization_mode: str = "auto"
     diarization_runtime: str = "native"
     diarization_container_image: str | None = None
+    diarization_container_args: tuple[str, ...] = ()
 
     @classmethod
     def from_environment(cls) -> AppSettings:
@@ -45,6 +47,9 @@ class AppSettings:
             diarization_mode=os.getenv("MKA_DIARIZATION_MODE", "auto"),
             diarization_runtime=os.getenv("MKA_DIARIZATION_RUNTIME", "native"),
             diarization_container_image=os.getenv("MKA_DIARIZATION_CONTAINER_IMAGE"),
+            diarization_container_args=_parse_container_args(
+                os.getenv("MKA_DIARIZATION_CONTAINER_ARGS")
+            ),
         )
 
     def validate_for_processing(self) -> None:
@@ -67,3 +72,29 @@ class AppSettings:
             raise ConfigurationError(
                 "MKA_DIARIZATION_CONTAINER_IMAGE is required for container runtime."
             )
+        if any(
+            not isinstance(argument, str) or not argument
+            for argument in self.diarization_container_args
+        ):
+            raise ConfigurationError(
+                "MKA_DIARIZATION_CONTAINER_ARGS must contain only non-empty strings."
+            )
+
+
+def _parse_container_args(value: str | None) -> tuple[str, ...]:
+    """Parse an ordered JSON array of opaque container command arguments."""
+    if value is None or not value.strip():
+        return ()
+    try:
+        parsed = json.loads(value)
+    except json.JSONDecodeError as exc:
+        raise ConfigurationError(
+            "MKA_DIARIZATION_CONTAINER_ARGS must be a JSON array of strings."
+        ) from exc
+    if not isinstance(parsed, list) or any(
+        not isinstance(argument, str) or not argument for argument in parsed
+    ):
+        raise ConfigurationError(
+            "MKA_DIARIZATION_CONTAINER_ARGS must be a JSON array of non-empty strings."
+        )
+    return tuple(parsed)