phase 3

core/db/models.py

@@ -0,0 +1,156 @@
+"""
+SQLModel Table Models - GENERATED FILE
+
+Do not edit directly. Regenerate using modelgen.
+"""
+
+from datetime import datetime
+from enum import Enum
+from typing import Any, Dict, List, Optional
+from uuid import UUID, uuid4
+
+from sqlmodel import SQLModel, Field, Column
+from sqlalchemy import JSON
+
+class AssetStatus(str, Enum):
+    PENDING = "pending"
+    READY = "ready"
+    ERROR = "error"
+
+class JobStatus(str, Enum):
+    PENDING = "pending"
+    RUNNING = "running"
+    PAUSED = "paused"
+    COMPLETED = "completed"
+    FAILED = "failed"
+    CANCELLED = "cancelled"
+
+class RunType(str, Enum):
+    INITIAL = "initial"
+    REPLAY = "replay"
+    RETRY = "retry"
+
+class BrandSource(str, Enum):
+    OCR = "ocr"
+    VLM = "local_vlm"
+    CLOUD = "cloud_llm"
+    MANUAL = "manual"
+
+class SourceType(str, Enum):
+    CHUNK_JOB = "chunk_job"
+    UPLOAD = "upload"
+    DEVICE = "device"
+    STREAM = "stream"
+
+class MediaAsset(SQLModel, table=True):
+    """A video/audio file registered in the system."""
+    __tablename__ = "media_assets"
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    filename: str
+    file_path: str
+    status: AssetStatus = "pending"
+    error_message: Optional[str] = None
+    file_size: Optional[int] = None
+    duration: Optional[float] = None
+    video_codec: Optional[str] = None
+    audio_codec: Optional[str] = None
+    width: Optional[int] = None
+    height: Optional[int] = None
+    framerate: Optional[float] = None
+    bitrate: Optional[int] = None
+    properties: Dict[str, Any] = Field(default_factory=dict, sa_column=Column(JSON, nullable=False, server_default='{}'))
+    comments: str = ""
+    tags: List[str] = Field(default_factory=list, sa_column=Column(JSON, nullable=False, server_default='[]'))
+    created_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+    updated_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+
+class TranscodePreset(SQLModel, table=True):
+    """A reusable transcoding configuration (like Handbrake presets)."""
+    __tablename__ = "transcode_presets"
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    name: str
+    description: str = ""
+    is_builtin: bool = False
+    container: str = "mp4"
+    video_codec: str = "libx264"
+    video_bitrate: Optional[str] = None
+    video_crf: Optional[int] = None
+    video_preset: Optional[str] = None
+    resolution: Optional[str] = None
+    framerate: Optional[float] = None
+    audio_codec: str = "aac"
+    audio_bitrate: Optional[str] = None
+    audio_channels: Optional[int] = None
+    audio_samplerate: Optional[int] = None
+    extra_args: List[str] = Field(default_factory=list, sa_column=Column(JSON, nullable=False, server_default='[]'))
+    created_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+    updated_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+
+class Job(SQLModel, table=True):
+    """A pipeline job."""
+    __tablename__ = "jobs"
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    source_asset_id: UUID = Field(index=True)
+    video_path: str
+    profile_name: str = "soccer_broadcast"
+    parent_id: Optional[UUID] = None
+    run_type: RunType = "initial"
+    config_overrides: Dict[str, Any] = Field(default_factory=dict, sa_column=Column(JSON, nullable=False, server_default='{}'))
+    status: JobStatus = "pending"
+    current_stage: Optional[str] = None
+    progress: float = 0.0
+    error_message: Optional[str] = None
+    total_detections: int = 0
+    brands_found: int = 0
+    cloud_llm_calls: int = 0
+    estimated_cost_usd: float = 0.0
+    celery_task_id: Optional[str] = None
+    priority: int = 0
+    created_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+    started_at: Optional[datetime] = None
+    completed_at: Optional[datetime] = None
+
+class Timeline(SQLModel, table=True):
+    """The frame sequence from a source video."""
+    __tablename__ = "timelines"
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    source_asset_id: Optional[UUID] = Field(default=None, index=True)
+    source_video: str = ""
+    profile_name: str = ""
+    fps: float = 2.0
+    frames_prefix: str = ""
+    frames_manifest: Dict[str, Any] = Field(default_factory=dict, sa_column=Column(JSON, nullable=False, server_default='{}'))
+    frames_meta: List[str] = Field(default_factory=list, sa_column=Column(JSON, nullable=False, server_default='[]'))
+    created_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+
+class Checkpoint(SQLModel, table=True):
+    """A snapshot of pipeline state on a timeline."""
+    __tablename__ = "checkpoints"
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    timeline_id: UUID
+    parent_id: Optional[UUID] = None
+    stage_outputs: Dict[str, Any] = Field(default_factory=dict, sa_column=Column(JSON, nullable=False, server_default='{}'))
+    config_overrides: Dict[str, Any] = Field(default_factory=dict, sa_column=Column(JSON, nullable=False, server_default='{}'))
+    stats: Dict[str, Any] = Field(default_factory=dict, sa_column=Column(JSON, nullable=False, server_default='{}'))
+    is_scenario: bool = False
+    scenario_label: str = ""
+    created_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+
+class Brand(SQLModel, table=True):
+    """A brand discovered or registered in the system."""
+    __tablename__ = "brands"
+
+    id: UUID = Field(default_factory=uuid4, primary_key=True)
+    canonical_name: str = Field(index=True)
+    aliases: List[str] = Field(default_factory=list, sa_column=Column(JSON, nullable=False, server_default='[]'))
+    source: BrandSource = "ocr"
+    confirmed: bool = False
+    airings: List[str] = Field(default_factory=list, sa_column=Column(JSON, nullable=False, server_default='[]'))
+    total_airings: int = 0
+    created_at: Optional[datetime] = Field(default_factory=datetime.utcnow)
+    updated_at: Optional[datetime] = Field(default_factory=datetime.utcnow)

core/schema/models/detect.py

@@ -94,6 +94,9 @@ class StatsUpdate:
     cloud_llm_calls: int = 0
     processing_time_seconds: float = 0.0
     estimated_cloud_cost_usd: float = 0.0
+    run_id: Optional[str] = None
+    parent_job_id: Optional[str] = None
+    run_type: str = "initial"
 
 
 @dataclass