After story 1

db/schema.sql

@@ -0,0 +1,122 @@
+--
+-- VideoDetect Database Schema
+-- Version: 1.0.0
+-- Created: 2026-08-03
+--
+
+-- Create database (if not exists)
+CREATE DATABASE IF NOT EXISTS videodetect
+  CHARACTER SET utf8mb4
+  COLLATE utf8mb4_unicode_ci;
+
+USE videodetect;
+
+-- -----------------------------------------------------
+-- Table: videos
+-- Stores metadata for each video file in the corpus
+-- -----------------------------------------------------
+CREATE TABLE IF NOT EXISTS videos (
+    id BIGINT AUTO_INCREMENT PRIMARY KEY,
+    file_path VARCHAR(2048) NOT NULL,
+    file_hash CHAR(64) NOT NULL COMMENT 'SHA-256 hash of file',
+    resolution_w INT DEFAULT NULL,
+    resolution_h INT DEFAULT NULL,
+    codec VARCHAR(50) DEFAULT NULL,
+    duration FLOAT DEFAULT NULL COMMENT 'Duration in seconds',
+    status ENUM('NEW', 'PENDING', 'PROCESSING', 'COMPLETED', 'UNSCANNABLE', 'ERROR')
+        NOT NULL DEFAULT 'NEW' COMMENT 'Processing status',
+    last_scan_time DATETIME DEFAULT NULL,
+    last_processed_time DATETIME DEFAULT NULL,
+    confidence_score FLOAT DEFAULT NULL COMMENT 'Video-level confidence score',
+    routing_decision ENUM('MATCH', 'REVIEW', 'SKIP') DEFAULT NULL COMMENT 'Routing decision',
+    model_version VARCHAR(50) DEFAULT NULL COMMENT 'Model version used for processing',
+    frame_count INT DEFAULT NULL COMMENT 'Number of frames sampled',
+    error_message TEXT DEFAULT NULL,
+    created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    updated_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
+
+    UNIQUE KEY uk_file_hash (file_hash),
+    INDEX idx_videos_status (status),
+    INDEX idx_videos_last_scan (last_scan_time),
+    INDEX idx_videos_status_last_scan (status, last_scan_time),
+    INDEX idx_videos_file_path (file_path(255))
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci;
+
+-- -----------------------------------------------------
+-- Table: processing_logs
+-- Audit trail for each video processing job
+-- -----------------------------------------------------
+CREATE TABLE IF NOT EXISTS processing_logs (
+    id BIGINT AUTO_INCREMENT PRIMARY KEY,
+    video_id BIGINT NOT NULL,
+    model_version VARCHAR(50) NOT NULL,
+    frame_count INT NOT NULL DEFAULT 0,
+    confidence_score FLOAT DEFAULT NULL,
+    confidence_scores JSON DEFAULT NULL COMMENT 'Frame-level confidence scores',
+    routing_decision ENUM('MATCH', 'REVIEW', 'SKIP') NOT NULL,
+    processed_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    error_message TEXT DEFAULT NULL,
+    FOREIGN KEY (video_id) REFERENCES videos(id) ON DELETE CASCADE,
+    INDEX idx_processing_logs_video (video_id),
+    INDEX idx_processing_logs_processed_at (processed_at),
+    INDEX idx_processing_logs_routing (routing_decision)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci;
+
+-- -----------------------------------------------------
+-- Table: models
+-- Model registry tracking all deployed and archived models
+-- -----------------------------------------------------
+CREATE TABLE IF NOT EXISTS models (
+    version VARCHAR(50) PRIMARY KEY,
+    status ENUM('ACTIVE', 'CANDIDATE', 'ARCHIVED') NOT NULL DEFAULT 'CANDIDATE',
+    path VARCHAR(2048) NOT NULL,
+    calibration_temp FLOAT DEFAULT NULL COMMENT 'Temperature scaling parameter',
+    f1_score FLOAT DEFAULT NULL COMMENT 'F1 score on validation set',
+    ece_score FLOAT DEFAULT NULL COMMENT 'Expected Calibration Error',
+    deployed_at DATETIME DEFAULT NULL,
+    created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    INDEX idx_models_status (status)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci;
+
+-- -----------------------------------------------------
+-- Table: review_queue
+-- Videos awaiting manual annotation
+-- -----------------------------------------------------
+CREATE TABLE IF NOT EXISTS review_queue (
+    id BIGINT AUTO_INCREMENT PRIMARY KEY,
+    video_id BIGINT NOT NULL,
+    confidence_score FLOAT NOT NULL,
+    routing_decision ENUM('REVIEW') NOT NULL DEFAULT 'REVIEW',
+    annotated BOOLEAN NOT NULL DEFAULT FALSE,
+    ground_truth BOOLEAN DEFAULT NULL COMMENT 'True label from annotator',
+    annotated_at DATETIME DEFAULT NULL,
+    notes TEXT DEFAULT NULL,
+    created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+    FOREIGN KEY (video_id) REFERENCES videos(id) ON DELETE CASCADE,
+    INDEX idx_review_queue_annotated (annotated),
+    INDEX idx_review_queue_created (created_at)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci;
+
+-- -----------------------------------------------------
+-- Table: scan_history
+-- Tracks directory scan operations for incremental sync
+-- -----------------------------------------------------
+CREATE TABLE IF NOT EXISTS scan_history (
+    id BIGINT AUTO_INCREMENT PRIMARY KEY,
+    scan_start DATETIME NOT NULL,
+    scan_end DATETIME DEFAULT NULL,
+    files_discovered INT DEFAULT 0,
+    files_new INT DEFAULT 0,
+    files_modified INT DEFAULT 0,
+    files_removed INT DEFAULT 0,
+    files_unscannable INT DEFAULT 0,
+    duration_seconds FLOAT DEFAULT NULL,
+    status ENUM('RUNNING', 'COMPLETED', 'FAILED') NOT NULL DEFAULT 'RUNNING',
+    error_message TEXT DEFAULT NULL
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_unicode_ci;
+
+-- -----------------------------------------------------
+-- Insert default model entry
+-- -----------------------------------------------------
+INSERT IGNORE INTO models (version, status, path, calibration_temp, created_at)
+VALUES ('v0.0.0-placeholder', 'ACTIVE', '/models/placeholder', 1.0, NOW());