Consolidate versioned source evidence across investigation results

scripts/measure_investigation_context.py

@@ -5,25 +5,18 @@ import json
 
 from viano_bug_analysis.analysis.investigation_prompt import build_prompt
 from viano_bug_analysis.analysis.investigation_view import working_view, thin_view
+from viano_bug_analysis.analysis.investigation_consolidation import consolidated_view, restore_view
 from viano_bug_analysis.case.contracts import read_json
 from viano_bug_analysis.package import PackageReader
 
 
 def restore_tables(view):
-    for entry in view['evidence'].values():
-        for capture in entry['content'].get('items', []):
-            result = capture.get('result', {})
-            table = result.get('items')
-            if not isinstance(table, dict):
-                continue
-            if table.get('encoding') == 'source_line_table_v1':
-                result['items'] = [{**table['common'], **dict(zip(table['columns'], row))} for row in table['rows']]
-            elif table.get('encoding') == 'database_row_table_v1':
-                result['items'] = [{**table['common'], 'row': dict(zip(table['columns'], row))} for row in table['rows']]
-    return view
+    return restore_view(view)
 
 
-def measure(path):
+def measure(path, target_version='investigation_project_v6'):
+    if target_version not in {'investigation_project_v5', 'investigation_project_v6'}:
+        raise ValueError('Unsupported model view version')
     records = []
     with PackageReader(path) as reader:
         for ref in sorted(reader.files):
@@ -34,21 +27,27 @@ def measure(path):
                 continue
             old = build_prompt(context)
             projected = copy.deepcopy(context)
-            projected['prompt_version'] = 'investigation_project_v5'
+            projected['prompt_version'] = target_version
             new = build_prompt(projected)
             old_view = working_view(projected)
-            new_view = thin_view(projected)
+            new_view = consolidated_view(projected) if target_version == 'investigation_project_v6' else thin_view(projected)
             if json.dumps(restore_tables(copy.deepcopy(new_view)), sort_keys=True) != json.dumps(old_view, sort_keys=True):
                 raise ValueError('Model view roundtrip failed')
             records.append({'context_ref': ref,
                             'old_characters': len(old['messages'][1]['content']),
                             'new_characters': len(new['messages'][1]['content']),
+                            'old_message_characters': sum(len(m['content']) for m in old['messages']),
+                            'new_message_characters': sum(len(m['content']) for m in new['messages']),
                             'old_components': {k: len(json.dumps(v, ensure_ascii=False, separators=(',', ':'))) for k, v in old_view.items()},
                             'new_components': {k: len(json.dumps(v, ensure_ascii=False, separators=(',', ':'))) for k, v in new_view.items()}})
     old = sum(r['old_characters'] for r in records)
     new = sum(r['new_characters'] for r in records)
-    return {'stored_contexts': len(records), 'old_user_characters': old, 'new_user_characters': new,
+    old_messages = sum(r['old_message_characters'] for r in records)
+    new_messages = sum(r['new_message_characters'] for r in records)
+    return {'target_version': target_version, 'stored_contexts': len(records), 'old_user_characters': old, 'new_user_characters': new,
             'reduction_percent': round(100 * (1 - new / old), 2) if old else None,
+            'old_message_characters': old_messages, 'new_message_characters': new_messages,
+            'message_reduction_percent': round(100 * (1 - new_messages / old_messages), 2) if old_messages else None,
             'lossless_roundtrip': True, 'unit': 'characters_not_provider_tokens',
             'scope': 'stored_contexts_not_billed_calls', 'contexts': records}
 
@@ -56,5 +55,6 @@ def measure(path):
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description=__doc__)
     parser.add_argument('package')
+    parser.add_argument('--target-version', choices=['investigation_project_v5', 'investigation_project_v6'], default='investigation_project_v6')
     args = parser.parse_args()
-    print(json.dumps(measure(args.package), indent=2))
+    print(json.dumps(measure(args.package, args.target_version), indent=2))