feat(ocr): Add docTR OCR engine with metrics infrastructure

Add docTR as primary OCR engine with 2-tier sequential processing,
OCR metrics tracking, and simplified engine selection.

Features:
- docTR OCR engine with light+medium preprocessing tiers
- doctr_plus mode with early exit optimization (~65% fast path)
- OCR metrics dashboard with per-engine statistics
- User OCR preference persistence
- Parallel worker pool for OCR processing
- Cross-validation for extraction quality

Engine options: tesseract, doctr, doctr_plus (recommended), paddleocr

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/modules/data_entry/migrations/versions/20251231_add_ocr_settings_metrics.py

@@ -0,0 +1,74 @@
+"""Add OCR settings and metrics tables.
+
+Revision ID: add_ocr_settings_metrics
+Revises: 20251230_add_needs_manual_review
+Create Date: 2025-12-31
+
+This migration adds:
+- user_ocr_preferences: Store user's preferred OCR engine
+- ocr_job_metrics: Store OCR job processing metrics for analytics
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# Revision identifiers
+revision = 'add_ocr_settings_metrics'
+down_revision = '20251230_add_needs_manual_review'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    """Create OCR settings and metrics tables."""
+
+    # Create user_ocr_preferences table
+    op.create_table(
+        'user_ocr_preferences',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('username', sa.String(length=100), nullable=False),
+        sa.Column('preferred_engine', sa.String(length=20), nullable=False, server_default='doctr_plus'),
+        sa.Column('created_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.Column('updated_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index('ix_user_ocr_preferences_username', 'user_ocr_preferences', ['username'], unique=True)
+
+    # Create ocr_job_metrics table
+    op.create_table(
+        'ocr_job_metrics',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('job_id', sa.String(length=50), nullable=False),
+        sa.Column('username', sa.String(length=100), nullable=False),
+        sa.Column('company_id', sa.Integer(), nullable=True),
+        sa.Column('engine_requested', sa.String(length=20), nullable=False),
+        sa.Column('engine_used', sa.String(length=50), nullable=False),
+        sa.Column('processing_time_ms', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('file_size_bytes', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('file_type', sa.String(length=50), nullable=False, server_default='image/jpeg'),
+        sa.Column('success', sa.Boolean(), nullable=False, server_default='1'),
+        sa.Column('error_message', sa.String(length=500), nullable=True),
+        sa.Column('overall_confidence', sa.Float(), nullable=False, server_default='0.0'),
+        sa.Column('fields_extracted', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('needs_manual_review', sa.Boolean(), nullable=True),
+        sa.Column('validation_warnings_count', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('validation_errors_count', sa.Integer(), nullable=False, server_default='0'),
+        sa.Column('created_at', sa.DateTime(), nullable=False, server_default=sa.func.now()),
+        sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index('ix_ocr_job_metrics_job_id', 'ocr_job_metrics', ['job_id'], unique=True)
+    op.create_index('ix_ocr_job_metrics_username', 'ocr_job_metrics', ['username'], unique=False)
+    op.create_index('ix_ocr_job_metrics_company_id', 'ocr_job_metrics', ['company_id'], unique=False)
+    op.create_index('ix_ocr_job_metrics_created_at', 'ocr_job_metrics', ['created_at'], unique=False)
+
+
+def downgrade() -> None:
+    """Drop OCR settings and metrics tables."""
+    op.drop_index('ix_ocr_job_metrics_created_at', table_name='ocr_job_metrics')
+    op.drop_index('ix_ocr_job_metrics_company_id', table_name='ocr_job_metrics')
+    op.drop_index('ix_ocr_job_metrics_username', table_name='ocr_job_metrics')
+    op.drop_index('ix_ocr_job_metrics_job_id', table_name='ocr_job_metrics')
+    op.drop_table('ocr_job_metrics')
+
+    op.drop_index('ix_user_ocr_preferences_username', table_name='user_ocr_preferences')
+    op.drop_table('user_ocr_preferences')

backend/modules/data_entry/migrations/versions/20251231_add_original_filename_to_metrics.py

@@ -0,0 +1,30 @@
+"""Add original_filename to ocr_job_metrics.
+
+Revision ID: add_original_filename_to_metrics
+Revises: add_ocr_settings_metrics
+Create Date: 2025-12-31
+
+Adds original_filename column to track the uploaded filename.
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# Revision identifiers
+revision = 'add_original_filename_to_metrics'
+down_revision = 'add_ocr_settings_metrics'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    """Add original_filename column to ocr_job_metrics."""
+    op.add_column(
+        'ocr_job_metrics',
+        sa.Column('original_filename', sa.String(length=255), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    """Remove original_filename column."""
+    op.drop_column('ocr_job_metrics', 'original_filename')