chunker and ui

core/schema/models/jobs.py

@@ -1,13 +1,14 @@
 """
-TranscodeJob Schema Definition
+Job Schema Definitions
 
-Source of truth for job data model.
+Source of truth for job data models.
+TranscodeJob and ChunkJob share common lifecycle fields by convention.
 """
 
 from dataclasses import dataclass, field
 from datetime import datetime
 from enum import Enum
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional
 from uuid import UUID
 
 
@@ -77,3 +78,56 @@ class TranscodeJob:
         return self.preset_id is None and (
             self.trim_start is not None or self.trim_end is not None
         )
+
+
+class ChunkJobStatus(str, Enum):
+    """Status of a chunk pipeline job."""
+
+    PENDING = "pending"
+    CHUNKING = "chunking"
+    PROCESSING = "processing"
+    COLLECTING = "collecting"
+    COMPLETED = "completed"
+    FAILED = "failed"
+    CANCELLED = "cancelled"
+
+
+@dataclass
+class ChunkJob:
+    """
+    A chunk pipeline job — splits a media file into chunks and processes them
+    through a concurrent worker pool.
+    """
+
+    id: UUID
+
+    # Input
+    source_asset_id: UUID
+
+    # Configuration
+    chunk_duration: float = 10.0  # seconds
+    num_workers: int = 4
+    max_retries: int = 3
+    processor_type: str = "ffmpeg"  # "ffmpeg", "checksum", "simulated_decode", "composite"
+
+    # Status & Progress
+    status: ChunkJobStatus = ChunkJobStatus.PENDING
+    progress: float = 0.0  # 0.0 to 100.0
+    total_chunks: int = 0
+    processed_chunks: int = 0
+    failed_chunks: int = 0
+    retry_count: int = 0
+    error_message: Optional[str] = None
+
+    # Result stats
+    throughput_mbps: Optional[float] = None
+    elapsed_seconds: Optional[float] = None
+
+    # Worker tracking
+    celery_task_id: Optional[str] = None
+    priority: int = 0  # Lower = higher priority
+
+    # Timestamps
+    created_at: Optional[datetime] = None
+    started_at: Optional[datetime] = None
+    completed_at: Optional[datetime] = None