Add Streamlit meeting assistant MVP

src/mka/application/config.py

@@ -0,0 +1,69 @@
+"""Environment-backed configuration for the Meeting Assistant application."""
+
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+from pathlib import Path
+
+
+class ConfigurationError(ValueError):
+    """Raised when required processing configuration is unavailable."""
+
+
+@dataclass(frozen=True)
+class AppSettings:
+    """Machine-specific Meeting Lab settings kept outside the UI."""
+
+    data_root: Path
+    whisper_model: Path | None
+    whisper_executable: str = "whisper-cli"
+    ffmpeg_executable: str = "ffmpeg"
+    protocol_model: str = "qwen3.8:27B"
+    ollama_endpoint: str = "http://127.0.0.1:11434"
+    language: str = "de"
+    threads: str | int = "auto"
+    diarization_mode: str = "auto"
+    diarization_runtime: str = "native"
+    diarization_container_image: str | None = None
+
+    @classmethod
+    def from_environment(cls) -> AppSettings:
+        """Load settings from MKA_* environment variables."""
+        whisper_model = os.getenv("MKA_WHISPER_MODEL")
+        threads = os.getenv("MKA_WHISPER_THREADS", "auto")
+        parsed_threads: str | int = int(threads) if threads.isdigit() else threads
+        return cls(
+            data_root=Path(os.getenv("MKA_DATA_ROOT", "data/meetings")),
+            whisper_model=Path(whisper_model) if whisper_model else None,
+            whisper_executable=os.getenv("MKA_WHISPER_EXECUTABLE", "whisper-cli"),
+            ffmpeg_executable=os.getenv("MKA_FFMPEG_EXECUTABLE", "ffmpeg"),
+            protocol_model=os.getenv("MKA_PROTOCOL_MODEL", "qwen3.8:27B"),
+            ollama_endpoint=os.getenv("MKA_OLLAMA_ENDPOINT", "http://127.0.0.1:11434"),
+            language=os.getenv("MKA_LANGUAGE", "de"),
+            threads=parsed_threads,
+            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"),
+        )
+
+    def validate_for_processing(self) -> None:
+        """Validate settings needed before a Meeting Lab run starts."""
+        if self.whisper_model is None:
+            raise ConfigurationError("MKA_WHISPER_MODEL is not configured.")
+        if not self.whisper_model.is_file():
+            raise ConfigurationError(
+                f"Configured Whisper model does not exist: {self.whisper_model}"
+            )
+        if not self.whisper_executable.strip():
+            raise ConfigurationError("MKA_WHISPER_EXECUTABLE must not be empty.")
+        if not self.ffmpeg_executable.strip():
+            raise ConfigurationError("MKA_FFMPEG_EXECUTABLE must not be empty.")
+        if self.diarization_mode not in {"auto", "cpu", "gpu"}:
+            raise ConfigurationError("MKA_DIARIZATION_MODE must be one of: auto, cpu, gpu.")
+        if self.diarization_runtime not in {"native", "container"}:
+            raise ConfigurationError("MKA_DIARIZATION_RUNTIME must be native or container.")
+        if self.diarization_runtime == "container" and not self.diarization_container_image:
+            raise ConfigurationError(
+                "MKA_DIARIZATION_CONTAINER_IMAGE is required for container runtime."
+            )