chore: snapshot current project updates

src/vlm/cli.py

@@ -4,6 +4,7 @@ This module provides the main CLI entry point using Click framework.
 It implements global options (--config, --log-level) and error handling.
 """
 
+import json
 import sys
 import traceback
 from pathlib import Path
@@ -192,11 +193,9 @@ def parse(ctx: CLIContext, input: Path, output: Path, inventory: Optional[Path])
         vlm parse --input my_inventory.csv           # Custom input
         vlm parse --output parsed_identities.json    # Custom output
     """
-    import csv
-    import json
     from datetime import datetime, timezone
     from vlm.parser import parse_movie, parse_series
-    from vlm.io import load_inventory_csv
+    from vlm.io import load_inventory_csv, save_identities_json
 
     config = ctx.config
     logger = ctx.logger
@@ -215,23 +214,16 @@ def parse(ctx: CLIContext, input: Path, output: Path, inventory: Optional[Path])
 
         click.echo()
 
-        # Load inventory from CSV
-        video_files = []
-        with open(input, 'r', encoding='utf-8') as csvfile:
-            # Skip comment lines
-            lines = []
-            for line in csvfile:
-                if not line.startswith('#'):
-                    lines.append(line)
-
-            # Parse CSV
-            reader = csv.DictReader(lines)
-            for row in reader:
-                video_files.append({
-                    'path': row['path'],
-                    'filename': row['filename'],
-                    'category': row['category']
-                })
+        # Load inventory via unified I/O layer
+        inventory_files = load_inventory_csv(input)
+        video_files = [
+            {
+                'path': str(vf.path),
+                'filename': vf.filename,
+                'category': vf.category,
+            }
+            for vf in inventory_files
+        ]
 
         click.echo(f"Loaded {len(video_files)} files from inventory")
         click.echo()
@@ -360,9 +352,8 @@ def parse(ctx: CLIContext, input: Path, output: Path, inventory: Optional[Path])
             'other': other_files
         }
         
-        # Write JSON file with pretty formatting
-        with open(output, 'w', encoding='utf-8') as jsonfile:
-            json.dump(identities_data, jsonfile, indent=2, ensure_ascii=False)
+        # Write JSON via unified I/O layer
+        save_identities_json(identities_data, output)
         
         click.echo(f"Parsed identities saved successfully!")
         
@@ -373,11 +364,6 @@ def parse(ctx: CLIContext, input: Path, output: Path, inventory: Optional[Path])
         logger.error(f"Input file not found: {input}")
         sys.exit(1)
     
-    except csv.Error as e:
-        click.echo(f"Error: Failed to parse CSV file: {e}", err=True)
-        logger.error(f"CSV parsing failed: {e}", exc_info=True)
-        sys.exit(1)
-    
     except Exception as e:
         click.echo(f"Error during parsing: {e}", err=True)
         logger.error(f"Parse failed: {e}", exc_info=True)
@@ -685,6 +671,101 @@ def plan(ctx: CLIContext, input: Path, output: Path, analysis: Path | None):
         sys.exit(1)
 
 
+@main.command(name="review-plan")
+@click.option(
+    '--input',
+    type=click.Path(exists=True, path_type=Path),
+    default=Path('plan.json'),
+    help='Path to execution plan JSON file (default: plan.json)'
+)
+@click.option(
+    '--output',
+    type=click.Path(path_type=Path),
+    default=Path('plan_manual_review.csv'),
+    help='Path to save manual review CSV (default: plan_manual_review.csv)'
+)
+@click.option(
+    '--season-threshold',
+    type=int,
+    default=20,
+    show_default=True,
+    help='Flag operations with season >= this value as high risk'
+)
+@click.option(
+    '--episode-threshold',
+    type=int,
+    default=40,
+    show_default=True,
+    help='Flag operations with episode >= this value as high risk'
+)
+@pass_context
+def review_plan_cmd(
+    ctx: CLIContext,
+    input: Path,
+    output: Path,
+    season_threshold: int,
+    episode_threshold: int,
+):
+    """Review a plan and export high-risk operations for manual confirmation."""
+    from vlm.planner import load_plan
+    from vlm.plan_review import review_plan, save_review_csv
+
+    logger = ctx.logger
+
+    try:
+        if season_threshold < 1 or episode_threshold < 1:
+            click.echo("Error: thresholds must be >= 1", err=True)
+            sys.exit(1)
+
+        click.echo(f"Loading plan: {input}")
+        execution_plan = load_plan(input)
+        rows, counters = review_plan(
+            execution_plan,
+            season_threshold=season_threshold,
+            episode_threshold=episode_threshold,
+        )
+
+        save_review_csv(rows, output)
+
+        click.echo()
+        click.echo("Plan review summary:")
+        click.echo(f"  Total operations: {counters['total_operations']}")
+        click.echo(f"  High-risk operations: {counters['high_risk_operations']}")
+        click.echo(f"  manual_review: {counters['manual_review']}")
+        click.echo(f"  sample_source: {counters['sample_source']}")
+        click.echo(f"  high_season: {counters['high_season']}")
+        click.echo(f"  high_episode: {counters['high_episode']}")
+        click.echo(f"  conflicts: {counters['conflicts']}")
+        click.echo()
+        click.echo(f"Saved manual review CSV to: {output}")
+
+        if rows:
+            click.echo("Top review samples:")
+            for row in rows[:5]:
+                click.echo(
+                    f"  - [{row['index']}] {row['operation_type']} {Path(row['source_path']).name} ({row['risk_flags']})"
+                )
+
+        logger.info(
+            "Plan review completed: total=%s high_risk=%s output=%s",
+            counters["total_operations"],
+            counters["high_risk_operations"],
+            output,
+        )
+    except FileNotFoundError:
+        click.echo(f"Error: Plan file not found: {input}", err=True)
+        logger.error(f"Plan file not found: {input}")
+        sys.exit(1)
+    except json.JSONDecodeError as e:
+        click.echo(f"Error: Failed to parse plan JSON: {e}", err=True)
+        logger.error(f"Plan review JSON parsing failed: {e}", exc_info=True)
+        sys.exit(1)
+    except Exception as e:
+        click.echo(f"Error during plan review: {e}", err=True)
+        logger.error(f"Plan review failed: {e}", exc_info=True)
+        sys.exit(1)
+
+
 @main.command()
 @click.option(
     '--plan',
@@ -698,19 +779,32 @@ def plan(ctx: CLIContext, input: Path, output: Path, analysis: Path | None):
     default=False,
     help='Actually execute operations (default is dry-run)'
 )
+@click.option(
+    '--yes',
+    is_flag=True,
+    default=False,
+    help='Skip confirmation prompt (auto-approve)'
+)
+@click.option(
+    '--verbose-ops',
+    is_flag=True,
+    default=False,
+    help='Print per-operation dry-run logs at INFO level'
+)
 @pass_context
-def execute(ctx: CLIContext, plan: Path, confirm: bool):
+def execute(ctx: CLIContext, plan: Path, confirm: bool, yes: bool, verbose_ops: bool):
     """Execute plan (defaults to dry-run, requires --confirm).
-    
+
     Executes file operations from a plan. Defaults to dry-run mode which
     simulates operations without making changes. Use --confirm to actually
     execute operations.
-    
+
     Example:
-    
+
         vlm execute                      # Dry-run with plan.json
         vlm execute --plan my_plan.json  # Dry-run with custom plan
-        vlm execute --confirm            # Actually execute operations
+        vlm execute --confirm            # Actually execute operations (with prompt)
+        vlm execute --confirm --yes      # Execute without confirmation prompt
     """
     from vlm.planner import load_plan
     from vlm.executor import ExecutionEngine
@@ -754,16 +848,29 @@ def execute(ctx: CLIContext, plan: Path, confirm: bool):
             click.echo("⚠️  EXECUTE MODE - Files will be modified!")
             click.echo("   This operation cannot be undone without rollback")
             click.echo()
-            if not click.confirm("Are you sure you want to proceed?"):
-                click.echo("Execution cancelled.")
-                return
+            if not yes:
+                if not click.confirm("Are you sure you want to proceed?"):
+                    click.echo("Execution cancelled.")
+                    return
+            else:
+                click.echo("Auto-approved via --yes flag")
         
         click.echo()
         click.echo(f"Executing {len(execution_plan.operations)} operations...")
         click.echo()
         
+        # Load state manager to update file statuses during execution
+        from vlm.state import StateManager
+        state_path = Path.home() / ".vlm" / "state.json"
+        state_manager = StateManager(state_path)
+
         # Create execution engine and execute plan
-        engine = ExecutionEngine(logger=logger, config=config)
+        engine = ExecutionEngine(
+            logger=logger, 
+            config=config, 
+            verbose_operations=verbose_ops,
+            state_manager=state_manager
+        )
         results, summary, rollback_log = engine.execute_plan(
             execution_plan,
             mode=mode,
@@ -1237,10 +1344,8 @@ def report_inventory(ctx: CLIContext, format: str, input: Path, output: Optional
         vlm report inventory --format csv           # CSV format to console
         vlm report inventory --format json --output inventory_report.json
     """
-    import csv
-    from datetime import datetime, timezone
     from vlm.reports import generate_inventory_report
-    from vlm.models import VideoFile
+    from vlm.io import load_inventory_csv
     
     config = ctx.config
     logger = ctx.logger
@@ -1249,40 +1354,7 @@ def report_inventory(ctx: CLIContext, format: str, input: Path, output: Optional
         # Load inventory from CSV
         click.echo(f"Loading inventory from: {input}")
         
-        video_files = []
-        with open(input, 'r', encoding='utf-8') as csvfile:
-            # Skip comment lines
-            lines = []
-            for line in csvfile:
-                if not line.startswith('#'):
-                    lines.append(line)
-            
-            # Parse CSV
-            reader = csv.DictReader(lines)
-            for row in reader:
-                # Parse timestamp
-                modified_timestamp = datetime.fromisoformat(row['modified_timestamp'])
-                if modified_timestamp.tzinfo is None:
-                    modified_timestamp = modified_timestamp.replace(tzinfo=timezone.utc)
-                
-                # Parse optional fields
-                resolution = row.get('resolution') if row.get('resolution') else None
-                codec = row.get('codec') if row.get('codec') else None
-                duration_seconds = float(row['duration_seconds']) if row.get('duration_seconds') else None
-                bitrate_kbps = int(row['bitrate_kbps']) if row.get('bitrate_kbps') else None
-                
-                video_file = VideoFile(
-                    path=Path(row['path']),
-                    filename=row['filename'],
-                    size_bytes=int(row['size_bytes']),
-                    modified_timestamp=modified_timestamp,
-                    category=row['category'],
-                    resolution=resolution,
-                    codec=codec,
-                    duration_seconds=duration_seconds,
-                    bitrate_kbps=bitrate_kbps
-                )
-                video_files.append(video_file)
+        video_files = load_inventory_csv(input)
         
         click.echo(f"Loaded {len(video_files)} files")
         click.echo()
@@ -1313,11 +1385,6 @@ def report_inventory(ctx: CLIContext, format: str, input: Path, output: Optional
         logger.error(f"Input file not found: {input}")
         sys.exit(1)
     
-    except csv.Error as e:
-        click.echo(f"Error: Failed to parse CSV file: {e}", err=True)
-        logger.error(f"CSV parsing failed: {e}", exc_info=True)
-        sys.exit(1)
-    
     except Exception as e:
         click.echo(f"Error generating inventory report: {e}", err=True)
         logger.error(f"Inventory report generation failed: {e}", exc_info=True)
@@ -1362,10 +1429,10 @@ def report_completeness(ctx: CLIContext, format: str, input: Path, output: Optio
         vlm report completeness --plan plan.json   # Include plan content summary
         vlm report completeness --format text --output completeness.txt
     """
-    import json
     from vlm.reports import generate_completeness_report
     from vlm.models import SeasonCompleteness
     from vlm.planner import load_plan
+    from vlm.io import load_analysis_json
 
     config = ctx.config
     logger = ctx.logger
@@ -1382,8 +1449,7 @@ def report_completeness(ctx: CLIContext, format: str, input: Path, output: Optio
         # Load analysis from JSON
         click.echo(f"Loading analysis from: {input}")
         
-        with open(input, 'r', encoding='utf-8') as jsonfile:
-            analysis_data = json.load(jsonfile)
+        analysis_data = load_analysis_json(input)
         
         # Extract completeness data
         completeness_list = analysis_data.get('completeness', [])
@@ -1476,11 +1542,11 @@ def report_duplicates(ctx: CLIContext, format: str, input: Path, output: Optiona
         vlm report duplicates --plan plan.json     # Include plan content summary
         vlm report duplicates --format text --output duplicates.txt
     """
-    import json
     from vlm.reports import generate_duplicate_report
     from vlm.models import DuplicateGroup, MovieIdentity, SeriesIdentity, VideoFile
     from vlm.planner import load_plan
     from datetime import datetime, timezone
+    from vlm.io import load_analysis_json
     
     config = ctx.config
     logger = ctx.logger
@@ -1497,8 +1563,7 @@ def report_duplicates(ctx: CLIContext, format: str, input: Path, output: Optiona
         # Load analysis from JSON
         click.echo(f"Loading analysis from: {input}")
         
-        with open(input, 'r', encoding='utf-8') as jsonfile:
-            analysis_data = json.load(jsonfile)
+        analysis_data = load_analysis_json(input)
         
         # Extract duplicates data
         duplicates_list = analysis_data.get('duplicates', [])
@@ -1527,19 +1592,24 @@ def report_duplicates(ctx: CLIContext, format: str, input: Path, output: Optiona
                     original_filename=""
                 )
             
-            # Reconstruct VideoFile objects from file paths
+            quality_by_path = {
+                str(item.get("path", "")): item for item in d.get("quality_comparison", [])
+            }
+
+            # Reconstruct VideoFile objects from file paths and preserve size metadata
             files = []
             for file_path in d['files']:
+                quality = quality_by_path.get(str(file_path), {})
                 files.append(VideoFile(
                     path=Path(file_path),
                     filename=Path(file_path).name,
-                    size_bytes=0,
+                    size_bytes=int(quality.get("size_bytes", 0) or 0),
                     modified_timestamp=datetime.now(timezone.utc),
                     category="",
-                    resolution=None,
-                    codec=None,
-                    duration_seconds=None,
-                    bitrate_kbps=None
+                    resolution=quality.get("resolution"),
+                    codec=quality.get("codec"),
+                    duration_seconds=quality.get("duration_seconds"),
+                    bitrate_kbps=quality.get("bitrate_kbps"),
                 ))
             
             duplicate_groups.append(DuplicateGroup(
@@ -1612,10 +1682,8 @@ def report_summary(ctx: CLIContext, input: Path, output: Optional[Path]):
         vlm report summary                          # Print to console
         vlm report summary --output summary.txt     # Save to file
     """
-    import csv
-    from datetime import datetime, timezone
     from vlm.reports import generate_summary_report
-    from vlm.models import VideoFile
+    from vlm.io import load_inventory_csv
     
     config = ctx.config
     logger = ctx.logger
@@ -1624,40 +1692,7 @@ def report_summary(ctx: CLIContext, input: Path, output: Optional[Path]):
         # Load inventory from CSV
         click.echo(f"Loading inventory from: {input}")
         
-        video_files = []
-        with open(input, 'r', encoding='utf-8') as csvfile:
-            # Skip comment lines
-            lines = []
-            for line in csvfile:
-                if not line.startswith('#'):
-                    lines.append(line)
-            
-            # Parse CSV
-            reader = csv.DictReader(lines)
-            for row in reader:
-                # Parse timestamp
-                modified_timestamp = datetime.fromisoformat(row['modified_timestamp'])
-                if modified_timestamp.tzinfo is None:
-                    modified_timestamp = modified_timestamp.replace(tzinfo=timezone.utc)
-                
-                # Parse optional fields
-                resolution = row.get('resolution') if row.get('resolution') else None
-                codec = row.get('codec') if row.get('codec') else None
-                duration_seconds = float(row['duration_seconds']) if row.get('duration_seconds') else None
-                bitrate_kbps = int(row['bitrate_kbps']) if row.get('bitrate_kbps') else None
-                
-                video_file = VideoFile(
-                    path=Path(row['path']),
-                    filename=row['filename'],
-                    size_bytes=int(row['size_bytes']),
-                    modified_timestamp=modified_timestamp,
-                    category=row['category'],
-                    resolution=resolution,
-                    codec=codec,
-                    duration_seconds=duration_seconds,
-                    bitrate_kbps=bitrate_kbps
-                )
-                video_files.append(video_file)
+        video_files = load_inventory_csv(input)
         
         click.echo(f"Loaded {len(video_files)} files")
         click.echo()
@@ -1685,11 +1720,6 @@ def report_summary(ctx: CLIContext, input: Path, output: Optional[Path]):
         logger.error(f"Input file not found: {input}")
         sys.exit(1)
     
-    except csv.Error as e:
-        click.echo(f"Error: Failed to parse CSV file: {e}", err=True)
-        logger.error(f"CSV parsing failed: {e}", exc_info=True)
-        sys.exit(1)
-    
     except Exception as e:
         click.echo(f"Error generating summary report: {e}", err=True)
         logger.error(f"Summary report generation failed: {e}", exc_info=True)