diff --git a/docs/measurements/redundancy-audit-20261016.json b/docs/measurements/redundancy-audit-20261016.json new file mode 100644 index 0000000..c1e9fc5 --- /dev/null +++ b/docs/measurements/redundancy-audit-20261016.json @@ -0,0 +1,6848 @@ +{ + "measurement": "redundancy_audit_v1", + "units": "bytes, UTF-8, decimal MB/GB", + "limitations": [ + "No paid API calls; no quality or token savings inferred.", + "Categories are disjoint; duplicate, archive-copy and repeated-string measures overlap.", + "Compressed duplicate sizes are an upper bound, not a compatible deletion proposal.", + "Repeated strings are counted within user messages, minimum 80 UTF-8 bytes; references and JSON framing not deducted.", + "Component repetition compares whole canonical top-level values within each prompt version, ignoring order of calls.", + "Saved requests are canonical gateway input, not literal cached HTTP payload." + ], + "packages": [ + { + "path": "C:/Users/User/Documents/Projekte/VianoBugAnalysis/VianoBugAnalysis/service-data/cases/897a914b67a02e6109a6b567e377e43c72b90ab216bfb9d2dc24485a5a55db8d/5da2caa788fe2ce30477305dcfc1e0df557ff3361ce92d2dac951b3267aaaca7/g00000108.zip", + "identity": { + "case_id": "BUG-000020", + "package_id": "trial-BUG-000020", + "package_generation": 108, + "state": "INVESTIGATING_HYPOTHESES" + }, + "zip_bytes": 63220233, + "raw_member_bytes": 63043223, + "compressed_member_bytes": 63043223, + "members": 517, + "zip_compression_methods": { + "0": 517 + }, + "deflate6_estimated_payload_bytes": 20169873, + "deflate6_by_category": { + "original_archives": 6222168, + "original_members": 12117599, + "case": 49916, + "history": 65151, + "analysis": 278210, + "llm_requests": 753715, + "llm_other": 24828, + "analysis_contexts": 627232, + "manifest.json": 31054 + }, + "categories": { + "original_archives": { + "files": 2, + "raw_bytes": 12071240, + "compressed_bytes": 12071240 + }, + "original_members": { + "files": 220, + "raw_bytes": 40117328, + "compressed_bytes": 40117328 + }, + "case": { + "files": 8, + "raw_bytes": 348541, + "compressed_bytes": 348541 + }, + "history": { + "files": 108, + "raw_bytes": 124162, + "compressed_bytes": 124162 + }, + "analysis": { + "files": 116, + "raw_bytes": 1176808, + "compressed_bytes": 1176808 + }, + "llm_requests": { + "files": 21, + "raw_bytes": 5039065, + "compressed_bytes": 5039065 + }, + "llm_other": { + "files": 25, + "raw_bytes": 53088, + "compressed_bytes": 53088 + }, + "analysis_contexts": { + "files": 16, + "raw_bytes": 3985344, + "compressed_bytes": 3985344 + }, + "manifest.json": { + "files": 1, + "raw_bytes": 127647, + "compressed_bytes": 127647 + } + }, + "stored_context_components": { + "case": { + "total_bytes": 2383856, + "unique_value_bytes": 148991, + "repeated_value_bytes": 2234865, + "occurrences": 16 + }, + "evidence": { + "total_bytes": 986105, + "unique_value_bytes": 497315, + "repeated_value_bytes": 488790, + "occurrences": 16 + }, + "previous_result": { + "total_bytes": 192948, + "unique_value_bytes": 148988, + "repeated_value_bytes": 43960, + "occurrences": 16 + }, + "hypotheses": { + "total_bytes": 151170, + "unique_value_bytes": 96460, + "repeated_value_bytes": 54710, + "occurrences": 16 + }, + "tool_schema": { + "total_bytes": 81456, + "unique_value_bytes": 5091, + "repeated_value_bytes": 76365, + "occurrences": 16 + }, + "interpretation": { + "total_bytes": 40336, + "unique_value_bytes": 2521, + "repeated_value_bytes": 37815, + "occurrences": 16 + }, + "budget": { + "total_bytes": 32876, + "unique_value_bytes": 22005, + "repeated_value_bytes": 10871, + "occurrences": 16 + }, + "budget_policy": { + "total_bytes": 3696, + "unique_value_bytes": 231, + "repeated_value_bytes": 3465, + "occurrences": 16 + }, + "policy": { + "total_bytes": 2448, + "unique_value_bytes": 153, + "repeated_value_bytes": 2295, + "occurrences": 16 + }, + "format": { + "total_bytes": 464, + "unique_value_bytes": 29, + "repeated_value_bytes": 435, + "occurrences": 16 + }, + "previous_rejection": { + "total_bytes": 141, + "unique_value_bytes": 95, + "repeated_value_bytes": 46, + "occurrences": 6 + }, + "selected_hypothesis": { + "total_bytes": 64, + "unique_value_bytes": 12, + "repeated_value_bytes": 52, + "occurrences": 16 + }, + "format_version": { + "total_bytes": 16, + "unique_value_bytes": 1, + "repeated_value_bytes": 15, + "occurrences": 16 + } + }, + "largest_members": [ + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/hits.json", + "raw_bytes": 10174034, + "compressed_bytes": 10174034 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/archive.tar.gz", + "raw_bytes": 8089111, + "compressed_bytes": 8089111 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/source/references.json", + "raw_bytes": 6420610, + "compressed_bytes": 6420610 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/source/historical_sql_references.json", + "raw_bytes": 6393006, + "compressed_bytes": 6393006 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/source/prioritized_references.txt", + "raw_bytes": 6323595, + "compressed_bytes": 6323595 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/source/references.txt", + "raw_bytes": 6323595, + "compressed_bytes": 6323595 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/archive.tar.gz", + "raw_bytes": 3982129, + "compressed_bytes": 3982129 + }, + { + "path": "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/prioritized_hits.json", + "raw_bytes": 2478892, + "compressed_bytes": 2478892 + }, + { + "path": "llm/operations/bbf03137db61614a7898353127aae3d114e56606ca757881038446b590a4cc21/request.json", + "raw_bytes": 418479, + "compressed_bytes": 418479 + }, + { + "path": "llm/operations/380b7dd01cdcda45e7b2199227eccb966d88cb56db9f20193bf85daa46398517/request.json", + "raw_bytes": 405619, + "compressed_bytes": 405619 + }, + { + "path": "llm/operations/d1f0925c8c965af48b7ece664c0ccdaae59563eefb9825b0cc704660eb7a858f/request.json", + "raw_bytes": 405565, + "compressed_bytes": 405565 + }, + { + "path": "analysis/investigation/0001/contexts/H2-0005.json", + "raw_bytes": 384937, + "compressed_bytes": 384937 + } + ], + "exact_duplicate_groups": 8, + "exact_duplicate_raw_bytes": 400233, + "exact_duplicate_compressed_bytes": 400233, + "largest_exact_duplicate_groups": [ + { + "copies": 3, + "raw_duplicate_bytes": 235138, + "compressed_duplicate_bytes": 235138, + "paths": [ + "llm/operations/94f3dcef41675be8227d1ce855d6ab7824cb0c0fb00f3c2cf938da789101dc8f/request.json", + "llm/operations/85c26cc02313cb191d4cd00bce0965c1fa1b7f6065f7f137484f0b764abdd2ca/request.json", + "llm/operations/e2da47e5b60ed940653c6dfedc38b094058362f4914907d4c479ac8d04f8f049/request.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 152247, + "compressed_duplicate_bytes": 152247, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/environment/world_schema_snapshot.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/database/world_schema_snapshot.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 4610, + "compressed_duplicate_bytes": 4610, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/manifest.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/input/wowdiag_manifest.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 3498, + "compressed_duplicate_bytes": 3498, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/source/high_relevance_references.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/source/primary_references.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 2786, + "compressed_duplicate_bytes": 2786, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/candidate_files.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/secondary_candidates.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 1569, + "compressed_duplicate_bytes": 1569, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/input/source_seeds.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/search_seeds.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 281, + "compressed_duplicate_bytes": 281, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/bug/diagnostic_focus.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/input/diagnostic_focus.json" + ] + }, + { + "copies": 53, + "raw_duplicate_bytes": 104, + "compressed_duplicate_bytes": 104, + "paths": [ + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/bug/attachments.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/bug/copied_attachments.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/bug/runtime_spells.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creature_queststarter.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creatures/23486/creature_addon.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creatures/23486/creature_questitem.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creatures/23486/creature_text.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creatures/23486/npc_spellclick_spells.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creatures/23486/npc_vendor.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/creatures/23486/vehicle_template_accessory.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/game_event_gameobject_quest.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/game_event_quest_condition.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/gameobject_questender.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/gameobject_queststarter.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/item_script_names.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/creature_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/disenchant_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/fishing_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/gameobject_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/item_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/mail_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/milling_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/pickpocketing_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/prospecting_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/reference_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/skinning_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32906/sources/spell_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/item_script_names.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/creature_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/disenchant_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/fishing_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/gameobject_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/item_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/mail_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/milling_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/pickpocketing_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/prospecting_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/reference_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/skinning_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/items/32907/sources/spell_loot_template.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/quest_mail_sender.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/database/quest_pool_members.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowdiag/members/BUG-000020-20261008-130429/findings.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/build/relevant_compile_commands.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/database/relationship_map.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/input/ignored_runtime_noise.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/api_context.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/copied_files.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/focus_regions.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/implementation_units.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/primary_implementation_units.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/similar_implementations.json", + "original/vcore/imports/768ba7813ccc3ac656328e895d4abcc8d56822c2976a149a95e99cf91f8bb096/wowsrc/members/WOWSRC-BUG-000020-20261008-130446/source/snippets/index.json" + ] + } + ], + "canonical_json_duplicate_raw_bytes": 400233, + "original_tar_members_also_stored_separately": { + "files": 220, + "raw_bytes": 40117328, + "outer_zip_member_compressed_bytes": 40117328 + }, + "request_count": 21, + "research_repetition": { + "evidence_item_total_bytes": 985513, + "evidence_item_unique_bytes": 148984, + "evidence_item_fields_bytes": { + "content": 797471, + "record": 180866, + "record_ref": 5304 + }, + "source_line_total_bytes": 0, + "source_line_unique_bytes": 0, + "source_line_occurrences": 0, + "source_line_unique_count": 0 + }, + "prompts": { + "case_interpretation_v1": { + "calls": 4, + "message_utf8_bytes": 439124, + "within_call_repeated_strings_ge80_bytes": 36812 + }, + "hypotheses_v1": { + "calls": 1, + "message_utf8_bytes": 112380, + "within_call_repeated_strings_ge80_bytes": 9203 + }, + "investigation_v1": { + "calls": 16, + "message_utf8_bytes": 4122576, + "within_call_repeated_strings_ge80_bytes": 1310292 + } + }, + "system_message_total_bytes": 47267, + "system_message_repeated_bytes": 39195, + "top_level_components": [ + { + "prompt": "investigation_v1", + "field": "input.case", + "total_canonical_bytes": 2383856, + "unique_value_bytes": 148991, + "repeated_value_bytes": 2234865, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "input.evidence", + "total_canonical_bytes": 986105, + "unique_value_bytes": 497315, + "repeated_value_bytes": 488790, + "occurrences": 16 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.sources", + "total_canonical_bytes": 399968, + "unique_value_bytes": 99992, + "repeated_value_bytes": 299976, + "occurrences": 4 + }, + { + "prompt": "investigation_v1", + "field": "input.previous_result", + "total_canonical_bytes": 192948, + "unique_value_bytes": 148988, + "repeated_value_bytes": 43960, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "input.hypotheses", + "total_canonical_bytes": 151170, + "unique_value_bytes": 96460, + "repeated_value_bytes": 54710, + "occurrences": 16 + }, + { + "prompt": "hypotheses_v1", + "field": "input.case_context", + "total_canonical_bytes": 100424, + "unique_value_bytes": 100424, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_v1", + "field": "output_schema", + "total_canonical_bytes": 94320, + "unique_value_bytes": 5895, + "repeated_value_bytes": 88425, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "input.tool_schema", + "total_canonical_bytes": 81456, + "unique_value_bytes": 5091, + "repeated_value_bytes": 76365, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "input.interpretation", + "total_canonical_bytes": 40336, + "unique_value_bytes": 2521, + "repeated_value_bytes": 37815, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "input.budget", + "total_canonical_bytes": 32876, + "unique_value_bytes": 22005, + "repeated_value_bytes": 10871, + "occurrences": 16 + }, + { + "prompt": "case_interpretation_v1", + "field": "output_schema", + "total_canonical_bytes": 7412, + "unique_value_bytes": 1853, + "repeated_value_bytes": 5559, + "occurrences": 4 + }, + { + "prompt": "hypotheses_v1", + "field": "input.interpretation_sources", + "total_canonical_bytes": 3801, + "unique_value_bytes": 3801, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_v1", + "field": "input.budget_policy", + "total_canonical_bytes": 3696, + "unique_value_bytes": 231, + "repeated_value_bytes": 3465, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "input.policy", + "total_canonical_bytes": 2448, + "unique_value_bytes": 153, + "repeated_value_bytes": 2295, + "occurrences": 16 + }, + { + "prompt": "hypotheses_v1", + "field": "output_schema", + "total_canonical_bytes": 1321, + "unique_value_bytes": 1321, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.case", + "total_canonical_bytes": 572, + "unique_value_bytes": 143, + "repeated_value_bytes": 429, + "occurrences": 4 + }, + { + "prompt": "case_interpretation_v1", + "field": "validation_feedback", + "total_canonical_bytes": 467, + "unique_value_bytes": 467, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_v1", + "field": "input.format", + "total_canonical_bytes": 464, + "unique_value_bytes": 29, + "repeated_value_bytes": 435, + "occurrences": 16 + }, + { + "prompt": "investigation_v1", + "field": "task", + "total_canonical_bytes": 384, + "unique_value_bytes": 24, + "repeated_value_bytes": 360, + "occurrences": 16 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.case_sha256", + "total_canonical_bytes": 264, + "unique_value_bytes": 66, + "repeated_value_bytes": 198, + "occurrences": 4 + }, + { + "prompt": "hypotheses_v1", + "field": "input.policy", + "total_canonical_bytes": 150, + "unique_value_bytes": 150, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_v1", + "field": "input.previous_rejection", + "total_canonical_bytes": 141, + "unique_value_bytes": 95, + "repeated_value_bytes": 46, + "occurrences": 6 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.format", + "total_canonical_bytes": 140, + "unique_value_bytes": 35, + "repeated_value_bytes": 105, + "occurrences": 4 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.case_ref", + "total_canonical_bytes": 124, + "unique_value_bytes": 31, + "repeated_value_bytes": 93, + "occurrences": 4 + }, + { + "prompt": "case_interpretation_v1", + "field": "task", + "total_canonical_bytes": 109, + "unique_value_bytes": 46, + "repeated_value_bytes": 63, + "occurrences": 5 + }, + { + "prompt": "hypotheses_v1", + "field": "input.interpretation_sha256", + "total_canonical_bytes": 66, + "unique_value_bytes": 66, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_v1", + "field": "input.selected_hypothesis", + "total_canonical_bytes": 64, + "unique_value_bytes": 12, + "repeated_value_bytes": 52, + "occurrences": 16 + }, + { + "prompt": "hypotheses_v1", + "field": "input.interpretation_ref", + "total_canonical_bytes": 56, + "unique_value_bytes": 56, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.expected_behavior_completeness", + "total_canonical_bytes": 36, + "unique_value_bytes": 9, + "repeated_value_bytes": 27, + "occurrences": 4 + }, + { + "prompt": "hypotheses_v1", + "field": "input.format", + "total_canonical_bytes": 26, + "unique_value_bytes": 26, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.expected_behavior_provenance", + "total_canonical_bytes": 24, + "unique_value_bytes": 6, + "repeated_value_bytes": 18, + "occurrences": 4 + }, + { + "prompt": "hypotheses_v1", + "field": "task", + "total_canonical_bytes": 21, + "unique_value_bytes": 21, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_v1", + "field": "input.format_version", + "total_canonical_bytes": 16, + "unique_value_bytes": 1, + "repeated_value_bytes": 15, + "occurrences": 16 + }, + { + "prompt": "case_interpretation_v1", + "field": "input.format_version", + "total_canonical_bytes": 4, + "unique_value_bytes": 1, + "repeated_value_bytes": 3, + "occurrences": 4 + }, + { + "prompt": "hypotheses_v1", + "field": "input.prior_generations", + "total_canonical_bytes": 2, + "unique_value_bytes": 2, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v1", + "field": "input.format_version", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + } + ], + "json_keys_by_bytes": [ + [ + "sha256", + 95553 + ], + [ + "path", + 57841 + ], + [ + "size", + 57841 + ], + [ + "source_ref", + 46462 + ], + [ + "text_truncated", + 40018 + ], + [ + "role", + 25200 + ], + [ + "text", + 19642 + ], + [ + "case_pointer", + 18300 + ], + [ + "type", + 16828 + ], + [ + "line", + 16478 + ], + [ + "json_pointer", + 15120 + ], + [ + "kind", + 14392 + ], + [ + "additionalProperties", + 12466 + ], + [ + "pattern", + 9410 + ], + [ + "minLength", + 9012 + ] + ], + "calls": [ + { + "ref": "llm/operations/94f3dcef41675be8227d1ce855d6ab7824cb0c0fb00f3c2cf938da789101dc8f/request.json", + "prompt": "case_interpretation_v1", + "message_utf8_bytes": 108805, + "user_repeated_strings_ge80_bytes": 9203, + "json_key_bytes": 18927, + "top_json_keys_by_bytes": [ + [ + "case_pointer", + 3660 + ], + [ + "sha256", + 1971 + ], + [ + "kind", + 1855 + ], + [ + "data", + 1708 + ], + [ + "path", + 1533 + ], + [ + "size", + 1533 + ], + [ + "json_pointer", + 720 + ], + [ + "source_ref", + 676 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/85c26cc02313cb191d4cd00bce0965c1fa1b7f6065f7f137484f0b764abdd2ca/request.json", + "prompt": "case_interpretation_v1", + "message_utf8_bytes": 108805, + "user_repeated_strings_ge80_bytes": 9203, + "json_key_bytes": 18927, + "top_json_keys_by_bytes": [ + [ + "case_pointer", + 3660 + ], + [ + "sha256", + 1971 + ], + [ + "kind", + 1855 + ], + [ + "data", + 1708 + ], + [ + "path", + 1533 + ], + [ + "size", + 1533 + ], + [ + "json_pointer", + 720 + ], + [ + "source_ref", + 676 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/e2da47e5b60ed940653c6dfedc38b094058362f4914907d4c479ac8d04f8f049/request.json", + "prompt": "case_interpretation_v1", + "message_utf8_bytes": 108805, + "user_repeated_strings_ge80_bytes": 9203, + "json_key_bytes": 18927, + "top_json_keys_by_bytes": [ + [ + "case_pointer", + 3660 + ], + [ + "sha256", + 1971 + ], + [ + "kind", + 1855 + ], + [ + "data", + 1708 + ], + [ + "path", + 1533 + ], + [ + "size", + 1533 + ], + [ + "json_pointer", + 720 + ], + [ + "source_ref", + 676 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/2cd36795173fe6d547ff571814187ce1b12b3a7ec6accd4ebd98869d46bad248/request.json", + "prompt": "case_interpretation_v1", + "message_utf8_bytes": 112709, + "user_repeated_strings_ge80_bytes": 9203, + "json_key_bytes": 19057, + "top_json_keys_by_bytes": [ + [ + "case_pointer", + 3660 + ], + [ + "sha256", + 1971 + ], + [ + "kind", + 1855 + ], + [ + "data", + 1708 + ], + [ + "path", + 1533 + ], + [ + "size", + 1533 + ], + [ + "json_pointer", + 720 + ], + [ + "source_ref", + 676 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/request.json", + "prompt": "hypotheses_v1", + "message_utf8_bytes": 112380, + "user_repeated_strings_ge80_bytes": 9203, + "json_key_bytes": 19973, + "top_json_keys_by_bytes": [ + [ + "case_pointer", + 3660 + ], + [ + "sha256", + 1971 + ], + [ + "kind", + 1953 + ], + [ + "data", + 1806 + ], + [ + "path", + 1533 + ], + [ + "size", + 1533 + ], + [ + "json_pointer", + 720 + ], + [ + "source_ref", + 676 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/ca6cdff81de3cbae0492c26802daa287b11bf4fabefad477a9b64f1b6db30112/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 178316, + "user_repeated_strings_ge80_bytes": 50748, + "json_key_bytes": 24902, + "top_json_keys_by_bytes": [ + [ + "sha256", + 4032 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "role", + 1575 + ], + [ + "type", + 1001 + ], + [ + "source_ref", + 780 + ], + [ + "additionalProperties", + 759 + ], + [ + "json_pointer", + 720 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/d844b0d123ece7c9861dbe282539f7879e6e6a21b3d1d4575c6e559fd5044aae/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 178366, + "user_repeated_strings_ge80_bytes": 50748, + "json_key_bytes": 24923, + "top_json_keys_by_bytes": [ + [ + "sha256", + 4032 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "role", + 1575 + ], + [ + "type", + 1001 + ], + [ + "source_ref", + 780 + ], + [ + "additionalProperties", + 759 + ], + [ + "json_pointer", + 720 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/68df285004e1ad76029de7884a6b2c77db165a926dd10c44c34c5cf54472af0e/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 178363, + "user_repeated_strings_ge80_bytes": 50748, + "json_key_bytes": 24923, + "top_json_keys_by_bytes": [ + [ + "sha256", + 4032 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "role", + 1575 + ], + [ + "type", + 1001 + ], + [ + "source_ref", + 780 + ], + [ + "additionalProperties", + 759 + ], + [ + "json_pointer", + 720 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/54ef9b495e10fe49a2ffad5909c89efdbfe7ef7645b601865d12e5223b0651bc/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 178916, + "user_repeated_strings_ge80_bytes": 50748, + "json_key_bytes": 24995, + "top_json_keys_by_bytes": [ + [ + "sha256", + 4032 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "role", + 1575 + ], + [ + "type", + 1001 + ], + [ + "source_ref", + 780 + ], + [ + "additionalProperties", + 759 + ], + [ + "json_pointer", + 720 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 223996, + "user_repeated_strings_ge80_bytes": 69794, + "json_key_bytes": 30757, + "top_json_keys_by_bytes": [ + [ + "sha256", + 4932 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "source_ref", + 2080 + ], + [ + "text_truncated", + 1700 + ], + [ + "role", + 1575 + ], + [ + "type", + 1001 + ], + [ + "text", + 868 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/7b8f9ecd4cb00c7e1d8bbd314d9ab15032701b76a0d5cf4256b895312b03a731/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 224040, + "user_repeated_strings_ge80_bytes": 69794, + "json_key_bytes": 30778, + "top_json_keys_by_bytes": [ + [ + "sha256", + 4932 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "source_ref", + 2080 + ], + [ + "text_truncated", + 1700 + ], + [ + "role", + 1575 + ], + [ + "type", + 1001 + ], + [ + "text", + 868 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/a4ed5334e4125ed14bcbca18629a561513bba48ef92afecc570c14d9e90e05cc/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 272324, + "user_repeated_strings_ge80_bytes": 90764, + "json_key_bytes": 37098, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5868 + ], + [ + "text_truncated", + 3468 + ], + [ + "source_ref", + 3432 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "text", + 1603 + ], + [ + "role", + 1575 + ], + [ + "line", + 1428 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/b7f2e84e7ce1ab15fea771e71ef5c71f3321d1b419eefa7f3f69f110b5c356c6/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 237523, + "user_repeated_strings_ge80_bytes": 73581, + "json_key_bytes": 33077, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5094 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "source_ref", + 2314 + ], + [ + "text_truncated", + 2006 + ], + [ + "role", + 1575 + ], + [ + "text", + 1008 + ], + [ + "type", + 1001 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/315f7926815c1671b537fb3e66cab04a5c6fae6211162461c0bd9de7aaaf48ae/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 237567, + "user_repeated_strings_ge80_bytes": 73581, + "json_key_bytes": 33098, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5094 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "source_ref", + 2314 + ], + [ + "text_truncated", + 2006 + ], + [ + "role", + 1575 + ], + [ + "text", + 1008 + ], + [ + "type", + 1001 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/23e886f4a2c5eeadfea37a9114a2282780ab8a12c14b970fdcc26da184fc793b/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 244878, + "user_repeated_strings_ge80_bytes": 75290, + "json_key_bytes": 34274, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5202 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "source_ref", + 2470 + ], + [ + "text_truncated", + 2210 + ], + [ + "role", + 1575 + ], + [ + "text", + 1099 + ], + [ + "type", + 1001 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/1704c36027e9e7cb8b3d1ec6c6ce478bbf9541e4a8d6a85ebe0c63fbb951d4ca/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 245627, + "user_repeated_strings_ge80_bytes": 74773, + "json_key_bytes": 34599, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5166 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "source_ref", + 2418 + ], + [ + "text_truncated", + 2142 + ], + [ + "role", + 1575 + ], + [ + "text", + 1078 + ], + [ + "type", + 1001 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/90894bde812875d10dcc9a11218c864322aa1f10e8f2c0ee7db07eaa21a4a687/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 285023, + "user_repeated_strings_ge80_bytes": 88807, + "json_key_bytes": 39800, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5958 + ], + [ + "text_truncated", + 3638 + ], + [ + "source_ref", + 3562 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "text", + 1701 + ], + [ + "role", + 1575 + ], + [ + "line", + 1498 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/db5a590ab945f036b4703f8ddcf783cdcf7f28e6cf9d9dfcff02dfdce55bc98b/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 285073, + "user_repeated_strings_ge80_bytes": 88807, + "json_key_bytes": 39821, + "top_json_keys_by_bytes": [ + [ + "sha256", + 5958 + ], + [ + "text_truncated", + 3638 + ], + [ + "source_ref", + 3562 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "text", + 1701 + ], + [ + "role", + 1575 + ], + [ + "line", + 1498 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/d1f0925c8c965af48b7ece664c0ccdaae59563eefb9825b0cc704660eb7a858f/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 379500, + "user_repeated_strings_ge80_bytes": 125927, + "json_key_bytes": 47993, + "top_json_keys_by_bytes": [ + [ + "sha256", + 7254 + ], + [ + "text_truncated", + 6086 + ], + [ + "source_ref", + 5434 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "text", + 2716 + ], + [ + "line", + 2506 + ], + [ + "role", + 1575 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/380b7dd01cdcda45e7b2199227eccb966d88cb56db9f20193bf85daa46398517/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 379550, + "user_repeated_strings_ge80_bytes": 125927, + "json_key_bytes": 48014, + "top_json_keys_by_bytes": [ + [ + "sha256", + 7254 + ], + [ + "text_truncated", + 6086 + ], + [ + "source_ref", + 5434 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "text", + 2716 + ], + [ + "line", + 2506 + ], + [ + "role", + 1575 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/bbf03137db61614a7898353127aae3d114e56606ca757881038446b590a4cc21/request.json", + "prompt": "investigation_v1", + "message_utf8_bytes": 393514, + "user_repeated_strings_ge80_bytes": 150255, + "json_key_bytes": 45805, + "top_json_keys_by_bytes": [ + [ + "sha256", + 6858 + ], + [ + "text_truncated", + 5338 + ], + [ + "source_ref", + 4862 + ], + [ + "path", + 3136 + ], + [ + "size", + 3136 + ], + [ + "text", + 2415 + ], + [ + "line", + 2198 + ], + [ + "role", + 1575 + ] + ], + "stable_partition": null + } + ] + }, + { + "path": "C:/Users/User/Documents/Projekte/VianoBugAnalysis/VianoBugAnalysis/service-data/trials/bug17-selected-context-20261016/cases/ee545dc4fba1e7d80fe28afa53898e02427d7114493f62d3eb771d670253282d/d836e740f8ddbede715b4ba6085ed7d8016366973cfb44992e88f087ef3f2b82/g00000124.zip", + "identity": { + "case_id": "BUG-000017", + "package_id": "trial-selected-context-BUG-000017-20261016", + "package_generation": 124, + "state": "INVESTIGATING_HYPOTHESES" + }, + "zip_bytes": 34612272, + "raw_member_bytes": 34420170, + "compressed_member_bytes": 34420170, + "members": 576, + "zip_compression_methods": { + "0": 576 + }, + "deflate6_estimated_payload_bytes": 9972063, + "deflate6_by_category": { + "original_archives": 2837937, + "original_members": 5285067, + "case": 63394, + "history": 75429, + "research": 9939, + "analysis": 373190, + "llm_requests": 294858, + "llm_other": 20946, + "analysis_contexts": 975618, + "manifest.json": 35685 + }, + "categories": { + "original_archives": { + "files": 2, + "raw_bytes": 5223946, + "compressed_bytes": 5223946 + }, + "original_members": { + "files": 225, + "raw_bytes": 18575957, + "compressed_bytes": 18575957 + }, + "case": { + "files": 8, + "raw_bytes": 406269, + "compressed_bytes": 406269 + }, + "history": { + "files": 124, + "raw_bytes": 141223, + "compressed_bytes": 141223 + }, + "research": { + "files": 9, + "raw_bytes": 68290, + "compressed_bytes": 68290 + }, + "analysis": { + "files": 151, + "raw_bytes": 1662479, + "compressed_bytes": 1662479 + }, + "llm_requests": { + "files": 20, + "raw_bytes": 1462603, + "compressed_bytes": 1462603 + }, + "llm_other": { + "files": 20, + "raw_bytes": 44489, + "compressed_bytes": 44489 + }, + "analysis_contexts": { + "files": 16, + "raw_bytes": 6695441, + "compressed_bytes": 6695441 + }, + "manifest.json": { + "files": 1, + "raw_bytes": 139473, + "compressed_bytes": 139473 + } + }, + "stored_context_components": { + "case": { + "total_bytes": 2815504, + "unique_value_bytes": 175969, + "repeated_value_bytes": 2639535, + "occurrences": 16 + }, + "case_sources": { + "total_bytes": 2053168, + "unique_value_bytes": 128323, + "repeated_value_bytes": 1924845, + "occurrences": 16 + }, + "evidence": { + "total_bytes": 1033572, + "unique_value_bytes": 654554, + "repeated_value_bytes": 379018, + "occurrences": 16 + }, + "hypotheses": { + "total_bytes": 177460, + "unique_value_bytes": 177460, + "repeated_value_bytes": 0, + "occurrences": 16 + }, + "tool_schema": { + "total_bytes": 170064, + "unique_value_bytes": 10629, + "repeated_value_bytes": 159435, + "occurrences": 16 + }, + "interpretation": { + "total_bytes": 69008, + "unique_value_bytes": 4313, + "repeated_value_bytes": 64695, + "occurrences": 16 + }, + "previous_result": { + "total_bytes": 68163, + "unique_value_bytes": 68135, + "repeated_value_bytes": 28, + "occurrences": 16 + }, + "budget": { + "total_bytes": 55069, + "unique_value_bytes": 45325, + "repeated_value_bytes": 9744, + "occurrences": 16 + }, + "budget_policy": { + "total_bytes": 3696, + "unique_value_bytes": 231, + "repeated_value_bytes": 3465, + "occurrences": 16 + }, + "policy": { + "total_bytes": 2800, + "unique_value_bytes": 175, + "repeated_value_bytes": 2625, + "occurrences": 16 + }, + "early_review": { + "total_bytes": 624, + "unique_value_bytes": 39, + "repeated_value_bytes": 585, + "occurrences": 16 + }, + "format": { + "total_bytes": 464, + "unique_value_bytes": 29, + "repeated_value_bytes": 435, + "occurrences": 16 + }, + "prompt_version": { + "total_bytes": 416, + "unique_value_bytes": 26, + "repeated_value_bytes": 390, + "occurrences": 16 + }, + "recalled_evidence": { + "total_bytes": 87, + "unique_value_bytes": 45, + "repeated_value_bytes": 42, + "occurrences": 16 + }, + "selected_hypothesis": { + "total_bytes": 64, + "unique_value_bytes": 12, + "repeated_value_bytes": 52, + "occurrences": 16 + }, + "format_version": { + "total_bytes": 16, + "unique_value_bytes": 1, + "repeated_value_bytes": 15, + "occurrences": 16 + } + }, + "largest_members": [ + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/hits.json", + "raw_bytes": 5014733, + "compressed_bytes": 5014733 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/archive.tar.gz", + "raw_bytes": 3071876, + "compressed_bytes": 3071876 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/references.json", + "raw_bytes": 2502119, + "compressed_bytes": 2502119 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/prioritized_references.txt", + "raw_bytes": 2415907, + "compressed_bytes": 2415907 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/references.txt", + "raw_bytes": 2415907, + "compressed_bytes": 2415907 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/historical_sql_references.json", + "raw_bytes": 2356795, + "compressed_bytes": 2356795 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/archive.tar.gz", + "raw_bytes": 2152070, + "compressed_bytes": 2152070 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/prioritized_hits.json", + "raw_bytes": 1483066, + "compressed_bytes": 1483066 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0014.json", + "raw_bytes": 473357, + "compressed_bytes": 473357 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0012.json", + "raw_bytes": 434808, + "compressed_bytes": 434808 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0013.json", + "raw_bytes": 433638, + "compressed_bytes": 433638 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0008.json", + "raw_bytes": 431601, + "compressed_bytes": 431601 + } + ], + "exact_duplicate_groups": 8, + "exact_duplicate_raw_bytes": 184749, + "exact_duplicate_compressed_bytes": 184749, + "largest_exact_duplicate_groups": [ + { + "copies": 2, + "raw_duplicate_bytes": 152247, + "compressed_duplicate_bytes": 152247, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/environment/world_schema_snapshot.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/database/world_schema_snapshot.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 19560, + "compressed_duplicate_bytes": 19560, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/development_files/src/server/scripts/EasternKingdoms/arathi_highlands.cpp", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/files/src/server/scripts/EasternKingdoms/arathi_highlands.cpp" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 5172, + "compressed_duplicate_bytes": 5172, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/high_relevance_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/primary_references.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 4236, + "compressed_duplicate_bytes": 4236, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/manifest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/wowdiag_manifest.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 2112, + "compressed_duplicate_bytes": 2112, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/snippets/02_arathi_highlands.cpp_614-671.txt", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/snippets/03_arathi_highlands.cpp_614-671.txt" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 1079, + "compressed_duplicate_bytes": 1079, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/source_seeds.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/search_seeds.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 281, + "compressed_duplicate_bytes": 281, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/diagnostic_focus.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/diagnostic_focus.json" + ] + }, + { + "copies": 32, + "raw_duplicate_bytes": 62, + "compressed_duplicate_bytes": 62, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/attachments.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/copied_attachments.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/runtime_spells.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/creature_addon.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/creature_questitem.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/npc_spellclick_spells.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/npc_vendor.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/smart_script_numeric_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/smart_scripts.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/vehicle_template_accessory.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/creature_addon.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/creature_questitem.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/creature_text.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/npc_spellclick_spells.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/npc_vendor.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/smart_script_numeric_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/smart_scripts.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/vehicle_template_accessory.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_creature_quest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_gameobject_quest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_quest_condition.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_seasonal_questrelation.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/gameobject_questender.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/gameobject_queststarter.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_mail_sender.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_objective_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_offer_reward.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_pool_members.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/findings/quest_fulfillment_paths.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/build/relevant_compile_commands.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/database/relationship_map.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/ignored_runtime_noise.json" + ] + } + ], + "canonical_json_duplicate_raw_bytes": 163077, + "original_tar_members_also_stored_separately": { + "files": 225, + "raw_bytes": 18575957, + "outer_zip_member_compressed_bytes": 18575957 + }, + "request_count": 20, + "research_repetition": { + "evidence_item_total_bytes": 71251, + "evidence_item_unique_bytes": 24776, + "evidence_item_fields_bytes": { + "content": 25835, + "record": 39482, + "record_ref": 4386 + }, + "source_line_total_bytes": 52233, + "source_line_unique_bytes": 8097, + "source_line_occurrences": 1753, + "source_line_unique_count": 275 + }, + "prompts": { + "entity_resolution_plan_v4": { + "calls": 1, + "message_utf8_bytes": 47132, + "within_call_repeated_strings_ge80_bytes": 10756 + }, + "entity_resolution_assessment_v4": { + "calls": 1, + "message_utf8_bytes": 48812, + "within_call_repeated_strings_ge80_bytes": 10756 + }, + "case_interpretation_resolved_v8": { + "calls": 1, + "message_utf8_bytes": 36599, + "within_call_repeated_strings_ge80_bytes": 0 + }, + "hypotheses_v4": { + "calls": 1, + "message_utf8_bytes": 35734, + "within_call_repeated_strings_ge80_bytes": 0 + }, + "investigation_project_v9": { + "calls": 16, + "message_utf8_bytes": 1001028, + "within_call_repeated_strings_ge80_bytes": 3888 + } + }, + "system_message_total_bytes": 134293, + "system_message_repeated_bytes": 104880, + "top_level_components": [ + { + "prompt": "investigation_project_v9", + "field": "input.sources", + "total_canonical_bytes": 314480, + "unique_value_bytes": 58965, + "repeated_value_bytes": 255515, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "output_schema", + "total_canonical_bytes": 145232, + "unique_value_bytes": 9077, + "repeated_value_bytes": 136155, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.evidence", + "total_canonical_bytes": 71741, + "unique_value_bytes": 51589, + "repeated_value_bytes": 20152, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.interpretation", + "total_canonical_bytes": 69008, + "unique_value_bytes": 4313, + "repeated_value_bytes": 64695, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.shared_sources", + "total_canonical_bytes": 62113, + "unique_value_bytes": 29269, + "repeated_value_bytes": 32844, + "occurrences": 15 + }, + { + "prompt": "investigation_project_v9", + "field": "input.hypotheses", + "total_canonical_bytes": 60446, + "unique_value_bytes": 60446, + "repeated_value_bytes": 0, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.unread_sources", + "total_canonical_bytes": 53184, + "unique_value_bytes": 6648, + "repeated_value_bytes": 46536, + "occurrences": 16 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "context", + "total_canonical_bytes": 41015, + "unique_value_bytes": 41015, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "context", + "total_canonical_bytes": 41015, + "unique_value_bytes": 41015, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "input.unread_inventory_scope", + "total_canonical_bytes": 30192, + "unique_value_bytes": 1887, + "repeated_value_bytes": 28305, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.evidence_index", + "total_canonical_bytes": 28558, + "unique_value_bytes": 23112, + "repeated_value_bytes": 5446, + "occurrences": 16 + }, + { + "prompt": "hypotheses_v4", + "field": "input.data", + "total_canonical_bytes": 25676, + "unique_value_bytes": 25676, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.data", + "total_canonical_bytes": 20504, + "unique_value_bytes": 20504, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "input.budget", + "total_canonical_bytes": 16316, + "unique_value_bytes": 14420, + "repeated_value_bytes": 1896, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.tool_schema", + "total_canonical_bytes": 11376, + "unique_value_bytes": 2133, + "repeated_value_bytes": 9243, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.shared_metadata", + "total_canonical_bytes": 9184, + "unique_value_bytes": 1722, + "repeated_value_bytes": 7462, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.budget_policy", + "total_canonical_bytes": 3696, + "unique_value_bytes": 231, + "repeated_value_bytes": 3465, + "occurrences": 16 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "output_schema", + "total_canonical_bytes": 3003, + "unique_value_bytes": 3003, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "input.case", + "total_canonical_bytes": 2848, + "unique_value_bytes": 178, + "repeated_value_bytes": 2670, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.policy", + "total_canonical_bytes": 2800, + "unique_value_bytes": 175, + "repeated_value_bytes": 2625, + "occurrences": 16 + }, + { + "prompt": "hypotheses_v4", + "field": "output_schema", + "total_canonical_bytes": 1321, + "unique_value_bytes": 1321, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.shared", + "total_canonical_bytes": 1311, + "unique_value_bytes": 1311, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.shared", + "total_canonical_bytes": 1311, + "unique_value_bytes": 1311, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "output_schema", + "total_canonical_bytes": 1214, + "unique_value_bytes": 1214, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.shapes", + "total_canonical_bytes": 1004, + "unique_value_bytes": 1004, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.shapes", + "total_canonical_bytes": 1004, + "unique_value_bytes": 1004, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "captures", + "total_canonical_bytes": 934, + "unique_value_bytes": 934, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "output_schema", + "total_canonical_bytes": 682, + "unique_value_bytes": 682, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "input.early_review", + "total_canonical_bytes": 624, + "unique_value_bytes": 39, + "repeated_value_bytes": 585, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.format", + "total_canonical_bytes": 464, + "unique_value_bytes": 29, + "repeated_value_bytes": 435, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.prompt_version", + "total_canonical_bytes": 416, + "unique_value_bytes": 26, + "repeated_value_bytes": 390, + "occurrences": 16 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "identity_guidance", + "total_canonical_bytes": 400, + "unique_value_bytes": 400, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "identity_guidance", + "total_canonical_bytes": 400, + "unique_value_bytes": 400, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "task", + "total_canonical_bytes": 384, + "unique_value_bytes": 24, + "repeated_value_bytes": 360, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v9", + "field": "input.previous_result", + "total_canonical_bytes": 368, + "unique_value_bytes": 340, + "repeated_value_bytes": 28, + "occurrences": 16 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "plan", + "total_canonical_bytes": 106, + "unique_value_bytes": 106, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "catalogs", + "total_canonical_bytes": 99, + "unique_value_bytes": 99, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "catalogs", + "total_canonical_bytes": 99, + "unique_value_bytes": 99, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "input.selected_hypothesis", + "total_canonical_bytes": 64, + "unique_value_bytes": 12, + "repeated_value_bytes": 52, + "occurrences": 16 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "task", + "total_canonical_bytes": 30, + "unique_value_bytes": 30, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "task", + "total_canonical_bytes": 24, + "unique_value_bytes": 24, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "task", + "total_canonical_bytes": 21, + "unique_value_bytes": 21, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "task", + "total_canonical_bytes": 21, + "unique_value_bytes": 21, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.encoding", + "total_canonical_bytes": 16, + "unique_value_bytes": 16, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.encoding", + "total_canonical_bytes": 16, + "unique_value_bytes": 16, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v9", + "field": "input.format_version", + "total_canonical_bytes": 16, + "unique_value_bytes": 1, + "repeated_value_bytes": 15, + "occurrences": 16 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "candidates", + "total_canonical_bytes": 2, + "unique_value_bytes": 2, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "max_searches", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "max_searches", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + } + ], + "json_keys_by_bytes": [ + [ + "kind", + 20076 + ], + [ + "type", + 13524 + ], + [ + "additionalProperties", + 10948 + ], + [ + "observed_at", + 9884 + ], + [ + "data", + 9856 + ], + [ + "provenance", + 9776 + ], + [ + "source_ids", + 9763 + ], + [ + "source_ref", + 8411 + ], + [ + "json_pointer", + 7710 + ], + [ + "author", + 6354 + ], + [ + "properties", + 6032 + ], + [ + "origin", + 5589 + ], + [ + "pattern", + 5490 + ], + [ + "text", + 5411 + ], + [ + "value", + 5080 + ] + ], + "calls": [ + { + "ref": "llm/operations/6c0a36f93bea41b87241a30769bd92bb6dc387869b46d3a013ec595cfc7e9548/request.json", + "prompt": "entity_resolution_plan_v4", + "message_utf8_bytes": 47132, + "user_repeated_strings_ge80_bytes": 10756, + "json_key_bytes": 11923, + "top_json_keys_by_bytes": [ + [ + "json_pointer", + 1305 + ], + [ + "source_ref", + 1196 + ], + [ + "kind", + 693 + ], + [ + "case_pointer", + 690 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 481 + ], + [ + "origin", + 396 + ], + [ + "author", + 351 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/88adb8b462df2c473b421f617b086dd65351532f28e81a7a1052e1f24da87dea/request.json", + "prompt": "entity_resolution_assessment_v4", + "message_utf8_bytes": 48812, + "user_repeated_strings_ge80_bytes": 10756, + "json_key_bytes": 12560, + "top_json_keys_by_bytes": [ + [ + "json_pointer", + 1305 + ], + [ + "source_ref", + 1196 + ], + [ + "kind", + 707 + ], + [ + "case_pointer", + 690 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 481 + ], + [ + "origin", + 405 + ], + [ + "author", + 351 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/request.json", + "prompt": "case_interpretation_resolved_v8", + "message_utf8_bytes": 36599, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 7348, + "top_json_keys_by_bytes": [ + [ + "$record", + 1300 + ], + [ + "$ref", + 455 + ], + [ + "metadata_ref", + 360 + ], + [ + "kind", + 294 + ], + [ + "data", + 280 + ], + [ + "type", + 238 + ], + [ + "source_ref", + 156 + ], + [ + "provenance", + 143 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/request.json", + "prompt": "hypotheses_v4", + "message_utf8_bytes": 35734, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 7626, + "top_json_keys_by_bytes": [ + [ + "$record", + 1300 + ], + [ + "kind", + 434 + ], + [ + "data", + 420 + ], + [ + "$ref", + 385 + ], + [ + "metadata_ref", + 360 + ], + [ + "source_ids", + 273 + ], + [ + "text", + 161 + ], + [ + "source_ref", + 156 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/ca6cdff81de3cbae0492c26802daa287b11bf4fabefad477a9b64f1b6db30112/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 51324, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 17113, + "top_json_keys_by_bytes": [ + [ + "kind", + 1015 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "properties", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 41812, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/54ef9b495e10fe49a2ffad5909c89efdbfe7ef7645b601865d12e5223b0651bc/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 55203, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 17970, + "top_json_keys_by_bytes": [ + [ + "kind", + 1036 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "properties", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 46247, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 59516, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 18647, + "top_json_keys_by_bytes": [ + [ + "kind", + 1057 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "properties", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 51073, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/c619a7901de5674f54e8371759fba596a7746f67d62499b198780813912e5c31/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 62683, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 19455, + "top_json_keys_by_bytes": [ + [ + "kind", + 1085 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 54631, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/b5de43dfa1122fa86decfa538047ee813621839eded8ed15356d341f3439e383/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 62833, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 19712, + "top_json_keys_by_bytes": [ + [ + "kind", + 1099 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 54799, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/6849c974442865e5ca3e8f146ef4520c275f2e37a25fb7caa498f17089ed6dc1/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 62424, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 20097, + "top_json_keys_by_bytes": [ + [ + "kind", + 1113 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 54399, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/475d5f458554c35131f24fc92fb2e762c69a8d9c6d4ab9d6426fbd72e6303af3/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 62644, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 20127, + "top_json_keys_by_bytes": [ + [ + "kind", + 1127 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "properties", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 54648, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/8f58f73379896f4edda417f564668be151dea6f1dd75d1872c8aeb64d0cef5ce/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 63652, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 20059, + "top_json_keys_by_bytes": [ + [ + "kind", + 1127 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 55783, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/9d94a56f71b21f01a9b59e1f935e199a9e59dd72e2ab77b517fb5e2b1bdd864e/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 63579, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 20541, + "top_json_keys_by_bytes": [ + [ + "kind", + 1141 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 55759, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/ba23de00b87dde357a659990150f6c36eef21e4cff573f4b4ee4be6dd16c2446/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 64386, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 20644, + "top_json_keys_by_bytes": [ + [ + "kind", + 1155 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "properties", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 56658, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/e9ebe331ccfea690913e97129c6c8906760fc14e445eafa01a30924eb040ed4e/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 64735, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 20480, + "top_json_keys_by_bytes": [ + [ + "kind", + 1155 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 57057, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/1380b43663a13f859f4340f18311e1da621f0278d65d9db8a816c6468a56e074/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 63893, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 20524, + "top_json_keys_by_bytes": [ + [ + "kind", + 1155 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "properties", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 56106, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/97fd3ebe3705d6e44ef75054ecfa47919ceda5f78610190b01f149d5963f2649/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 64772, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 20480, + "top_json_keys_by_bytes": [ + [ + "kind", + 1155 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 57088, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/9ca4b010c7ebc9e0ae40a106866bbb196dd23366b2e453b50c4a6e629b9f6874/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 64686, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 20986, + "top_json_keys_by_bytes": [ + [ + "kind", + 1169 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 57063, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/224d9f1bd039c45d5d91315d847f421fa0dcdeda31cea6416ffd8b342941b46d/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 67460, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 21112, + "top_json_keys_by_bytes": [ + [ + "kind", + 1176 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 60092, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + }, + { + "ref": "llm/operations/befe1c89171fc467713bb086768810344f2b1cb3f016f3b226a791ad3b1eedc5/request.json", + "prompt": "investigation_project_v9", + "message_utf8_bytes": 67238, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 21251, + "top_json_keys_by_bytes": [ + [ + "kind", + 1183 + ], + [ + "type", + 805 + ], + [ + "additionalProperties", + 667 + ], + [ + "source_ids", + 585 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 18696, + "live_bytes": 59899, + "prefix_hash": "1ac3f7f46bf55dad80f249a52418a6b67a47399601254af7f350999d4b22f889" + } + } + ] + }, + { + "path": "C:/Users/User/Documents/Projekte/VianoBugAnalysis/VianoBugAnalysis/service-data/trials/bug17-cache-required-20261016/cases/ee545dc4fba1e7d80fe28afa53898e02427d7114493f62d3eb771d670253282d/9edf174896e59a269c53da31dbe1847e9b1c9da0affe2d2255bf028c0a163638/g00000110.zip", + "identity": { + "case_id": "BUG-000017", + "package_id": "trial-cache-required-BUG-000017-20261016", + "package_generation": 110, + "state": "BLOCKED" + }, + "zip_bytes": 33607692, + "raw_member_bytes": 33422046, + "compressed_member_bytes": 33422046, + "members": 547, + "zip_compression_methods": { + "0": 547 + }, + "deflate6_estimated_payload_bytes": 9790705, + "deflate6_by_category": { + "original_archives": 2837937, + "original_members": 5285067, + "case": 63394, + "history": 66866, + "research": 9939, + "analysis": 315978, + "llm_requests": 285241, + "llm_other": 24107, + "analysis_contexts": 868424, + "manifest.json": 33752 + }, + "categories": { + "original_archives": { + "files": 2, + "raw_bytes": 5223946, + "compressed_bytes": 5223946 + }, + "original_members": { + "files": 225, + "raw_bytes": 18575957, + "compressed_bytes": 18575957 + }, + "case": { + "files": 8, + "raw_bytes": 406263, + "compressed_bytes": 406263 + }, + "history": { + "files": 110, + "raw_bytes": 125589, + "compressed_bytes": 125589 + }, + "research": { + "files": 9, + "raw_bytes": 68290, + "compressed_bytes": 68290 + }, + "analysis": { + "files": 142, + "raw_bytes": 1455495, + "compressed_bytes": 1455495 + }, + "llm_requests": { + "files": 18, + "raw_bytes": 1408047, + "compressed_bytes": 1408047 + }, + "llm_other": { + "files": 18, + "raw_bytes": 54480, + "compressed_bytes": 54480 + }, + "analysis_contexts": { + "files": 14, + "raw_bytes": 5969812, + "compressed_bytes": 5969812 + }, + "manifest.json": { + "files": 1, + "raw_bytes": 134167, + "compressed_bytes": 134167 + } + }, + "stored_context_components": { + "case": { + "total_bytes": 2463510, + "unique_value_bytes": 175965, + "repeated_value_bytes": 2287545, + "occurrences": 14 + }, + "case_sources": { + "total_bytes": 1815422, + "unique_value_bytes": 129673, + "repeated_value_bytes": 1685749, + "occurrences": 14 + }, + "evidence": { + "total_bytes": 968851, + "unique_value_bytes": 683071, + "repeated_value_bytes": 285780, + "occurrences": 14 + }, + "hypotheses": { + "total_bytes": 151149, + "unique_value_bytes": 111984, + "repeated_value_bytes": 39165, + "occurrences": 14 + }, + "tool_schema": { + "total_bytes": 148806, + "unique_value_bytes": 10629, + "repeated_value_bytes": 138177, + "occurrences": 14 + }, + "previous_result": { + "total_bytes": 79588, + "unique_value_bytes": 68834, + "repeated_value_bytes": 10754, + "occurrences": 14 + }, + "interpretation": { + "total_bytes": 66654, + "unique_value_bytes": 4761, + "repeated_value_bytes": 61893, + "occurrences": 14 + }, + "budget": { + "total_bytes": 49635, + "unique_value_bytes": 31623, + "repeated_value_bytes": 18012, + "occurrences": 14 + }, + "budget_policy": { + "total_bytes": 3234, + "unique_value_bytes": 231, + "repeated_value_bytes": 3003, + "occurrences": 14 + }, + "policy": { + "total_bytes": 2450, + "unique_value_bytes": 175, + "repeated_value_bytes": 2275, + "occurrences": 14 + }, + "early_review": { + "total_bytes": 546, + "unique_value_bytes": 39, + "repeated_value_bytes": 507, + "occurrences": 14 + }, + "format": { + "total_bytes": 406, + "unique_value_bytes": 29, + "repeated_value_bytes": 377, + "occurrences": 14 + }, + "prompt_version": { + "total_bytes": 378, + "unique_value_bytes": 27, + "repeated_value_bytes": 351, + "occurrences": 14 + }, + "previous_rejection": { + "total_bytes": 70, + "unique_value_bytes": 46, + "repeated_value_bytes": 24, + "occurrences": 3 + }, + "selected_hypothesis": { + "total_bytes": 56, + "unique_value_bytes": 12, + "repeated_value_bytes": 44, + "occurrences": 14 + }, + "format_version": { + "total_bytes": 14, + "unique_value_bytes": 1, + "repeated_value_bytes": 13, + "occurrences": 14 + } + }, + "largest_members": [ + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/hits.json", + "raw_bytes": 5014733, + "compressed_bytes": 5014733 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/archive.tar.gz", + "raw_bytes": 3071876, + "compressed_bytes": 3071876 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/references.json", + "raw_bytes": 2502119, + "compressed_bytes": 2502119 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/prioritized_references.txt", + "raw_bytes": 2415907, + "compressed_bytes": 2415907 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/references.txt", + "raw_bytes": 2415907, + "compressed_bytes": 2415907 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/historical_sql_references.json", + "raw_bytes": 2356795, + "compressed_bytes": 2356795 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/archive.tar.gz", + "raw_bytes": 2152070, + "compressed_bytes": 2152070 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/prioritized_hits.json", + "raw_bytes": 1483066, + "compressed_bytes": 1483066 + }, + { + "path": "analysis/investigation/0001/contexts/H2-0009-attempt-0002.json", + "raw_bytes": 456424, + "compressed_bytes": 456424 + }, + { + "path": "analysis/investigation/0001/contexts/H2-0009-attempt-0003.json", + "raw_bytes": 456424, + "compressed_bytes": 456424 + }, + { + "path": "analysis/investigation/0001/contexts/H2-0009-attempt-0001.json", + "raw_bytes": 456422, + "compressed_bytes": 456422 + }, + { + "path": "analysis/investigation/0001/contexts/H2-0009.json", + "raw_bytes": 456376, + "compressed_bytes": 456376 + } + ], + "exact_duplicate_groups": 9, + "exact_duplicate_raw_bytes": 641173, + "exact_duplicate_compressed_bytes": 641173, + "largest_exact_duplicate_groups": [ + { + "copies": 2, + "raw_duplicate_bytes": 456424, + "compressed_duplicate_bytes": 456424, + "paths": [ + "analysis/investigation/0001/contexts/H2-0009-attempt-0002.json", + "analysis/investigation/0001/contexts/H2-0009-attempt-0003.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 152247, + "compressed_duplicate_bytes": 152247, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/environment/world_schema_snapshot.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/database/world_schema_snapshot.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 19560, + "compressed_duplicate_bytes": 19560, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/development_files/src/server/scripts/EasternKingdoms/arathi_highlands.cpp", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/files/src/server/scripts/EasternKingdoms/arathi_highlands.cpp" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 5172, + "compressed_duplicate_bytes": 5172, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/high_relevance_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/primary_references.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 4236, + "compressed_duplicate_bytes": 4236, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/manifest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/wowdiag_manifest.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 2112, + "compressed_duplicate_bytes": 2112, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/snippets/02_arathi_highlands.cpp_614-671.txt", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/snippets/03_arathi_highlands.cpp_614-671.txt" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 1079, + "compressed_duplicate_bytes": 1079, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/source_seeds.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/search_seeds.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 281, + "compressed_duplicate_bytes": 281, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/diagnostic_focus.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/diagnostic_focus.json" + ] + } + ], + "canonical_json_duplicate_raw_bytes": 619501, + "original_tar_members_also_stored_separately": { + "files": 225, + "raw_bytes": 18575957, + "outer_zip_member_compressed_bytes": 18575957 + }, + "request_count": 18, + "research_repetition": { + "evidence_item_total_bytes": 135865, + "evidence_item_unique_bytes": 26574, + "evidence_item_fields_bytes": { + "content": 56815, + "record": 68700, + "record_ref": 7650 + }, + "source_line_total_bytes": 64522, + "source_line_unique_bytes": 6475, + "source_line_occurrences": 2446, + "source_line_unique_count": 244 + }, + "prompts": { + "entity_resolution_plan_v4": { + "calls": 1, + "message_utf8_bytes": 47130, + "within_call_repeated_strings_ge80_bytes": 10756 + }, + "entity_resolution_assessment_v4": { + "calls": 1, + "message_utf8_bytes": 49139, + "within_call_repeated_strings_ge80_bytes": 10756 + }, + "case_interpretation_resolved_v8": { + "calls": 2, + "message_utf8_bytes": 81185, + "within_call_repeated_strings_ge80_bytes": 0 + }, + "hypotheses_v4": { + "calls": 1, + "message_utf8_bytes": 36589, + "within_call_repeated_strings_ge80_bytes": 0 + }, + "investigation_project_v10": { + "calls": 13, + "message_utf8_bytes": 939601, + "within_call_repeated_strings_ge80_bytes": 16912 + } + }, + "system_message_total_bytes": 112915, + "system_message_repeated_bytes": 83852, + "top_level_components": [ + { + "prompt": "investigation_project_v10", + "field": "input.sources", + "total_canonical_bytes": 270777, + "unique_value_bytes": 104145, + "repeated_value_bytes": 166632, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.evidence", + "total_canonical_bytes": 136704, + "unique_value_bytes": 96828, + "repeated_value_bytes": 39876, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "output_schema", + "total_canonical_bytes": 114712, + "unique_value_bytes": 8824, + "repeated_value_bytes": 105888, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.hypotheses", + "total_canonical_bytes": 92409, + "unique_value_bytes": 73369, + "repeated_value_bytes": 19040, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.shared_sources", + "total_canonical_bytes": 71362, + "unique_value_bytes": 28822, + "repeated_value_bytes": 42540, + "occurrences": 12 + }, + { + "prompt": "investigation_project_v10", + "field": "input.interpretation", + "total_canonical_bytes": 61893, + "unique_value_bytes": 4761, + "repeated_value_bytes": 57132, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.unread_sources", + "total_canonical_bytes": 43212, + "unique_value_bytes": 13296, + "repeated_value_bytes": 29916, + "occurrences": 13 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.data", + "total_canonical_bytes": 41524, + "unique_value_bytes": 20762, + "repeated_value_bytes": 20762, + "occurrences": 2 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "context", + "total_canonical_bytes": 41013, + "unique_value_bytes": 41013, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "context", + "total_canonical_bytes": 41013, + "unique_value_bytes": 41013, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.data", + "total_canonical_bytes": 26027, + "unique_value_bytes": 26027, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v10", + "field": "input.unread_inventory_scope", + "total_canonical_bytes": 24531, + "unique_value_bytes": 1887, + "repeated_value_bytes": 22644, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.budget", + "total_canonical_bytes": 13959, + "unique_value_bytes": 11577, + "repeated_value_bytes": 2382, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.tool_schema", + "total_canonical_bytes": 9243, + "unique_value_bytes": 3555, + "repeated_value_bytes": 5688, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.shared_metadata", + "total_canonical_bytes": 7462, + "unique_value_bytes": 2870, + "repeated_value_bytes": 4592, + "occurrences": 13 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "output_schema", + "total_canonical_bytes": 6006, + "unique_value_bytes": 3003, + "repeated_value_bytes": 3003, + "occurrences": 2 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.shared", + "total_canonical_bytes": 3630, + "unique_value_bytes": 1815, + "repeated_value_bytes": 1815, + "occurrences": 2 + }, + { + "prompt": "investigation_project_v10", + "field": "input.budget_policy", + "total_canonical_bytes": 3003, + "unique_value_bytes": 231, + "repeated_value_bytes": 2772, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.case", + "total_canonical_bytes": 2288, + "unique_value_bytes": 176, + "repeated_value_bytes": 2112, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.policy", + "total_canonical_bytes": 2275, + "unique_value_bytes": 175, + "repeated_value_bytes": 2100, + "occurrences": 13 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.shapes", + "total_canonical_bytes": 2008, + "unique_value_bytes": 1004, + "repeated_value_bytes": 1004, + "occurrences": 2 + }, + { + "prompt": "hypotheses_v4", + "field": "input.shared", + "total_canonical_bytes": 1815, + "unique_value_bytes": 1815, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "output_schema", + "total_canonical_bytes": 1321, + "unique_value_bytes": 1321, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "output_schema", + "total_canonical_bytes": 1214, + "unique_value_bytes": 1214, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "captures", + "total_canonical_bytes": 1127, + "unique_value_bytes": 1127, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.shapes", + "total_canonical_bytes": 1004, + "unique_value_bytes": 1004, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "validation_feedback", + "total_canonical_bytes": 772, + "unique_value_bytes": 772, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "output_schema", + "total_canonical_bytes": 682, + "unique_value_bytes": 682, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v10", + "field": "input.early_review", + "total_canonical_bytes": 507, + "unique_value_bytes": 39, + "repeated_value_bytes": 468, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.previous_result", + "total_canonical_bytes": 432, + "unique_value_bytes": 340, + "repeated_value_bytes": 92, + "occurrences": 13 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "identity_guidance", + "total_canonical_bytes": 400, + "unique_value_bytes": 400, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "identity_guidance", + "total_canonical_bytes": 400, + "unique_value_bytes": 400, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v10", + "field": "input.format", + "total_canonical_bytes": 377, + "unique_value_bytes": 29, + "repeated_value_bytes": 348, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.prompt_version", + "total_canonical_bytes": 351, + "unique_value_bytes": 27, + "repeated_value_bytes": 324, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "task", + "total_canonical_bytes": 312, + "unique_value_bytes": 24, + "repeated_value_bytes": 288, + "occurrences": 13 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "candidates", + "total_canonical_bytes": 111, + "unique_value_bytes": 111, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "plan", + "total_canonical_bytes": 102, + "unique_value_bytes": 102, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "catalogs", + "total_canonical_bytes": 99, + "unique_value_bytes": 99, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "catalogs", + "total_canonical_bytes": 99, + "unique_value_bytes": 99, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "task", + "total_canonical_bytes": 67, + "unique_value_bytes": 46, + "repeated_value_bytes": 21, + "occurrences": 3 + }, + { + "prompt": "investigation_project_v10", + "field": "input.selected_hypothesis", + "total_canonical_bytes": 52, + "unique_value_bytes": 12, + "repeated_value_bytes": 40, + "occurrences": 13 + }, + { + "prompt": "investigation_project_v10", + "field": "input.previous_rejection", + "total_canonical_bytes": 46, + "unique_value_bytes": 46, + "repeated_value_bytes": 0, + "occurrences": 2 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.encoding", + "total_canonical_bytes": 32, + "unique_value_bytes": 16, + "repeated_value_bytes": 16, + "occurrences": 2 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "task", + "total_canonical_bytes": 30, + "unique_value_bytes": 30, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "task", + "total_canonical_bytes": 24, + "unique_value_bytes": 24, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "task", + "total_canonical_bytes": 21, + "unique_value_bytes": 21, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.encoding", + "total_canonical_bytes": 16, + "unique_value_bytes": 16, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v10", + "field": "input.format_version", + "total_canonical_bytes": 13, + "unique_value_bytes": 1, + "repeated_value_bytes": 12, + "occurrences": 13 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "max_searches", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "max_searches", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + } + ], + "json_keys_by_bytes": [ + [ + "kind", + 17633 + ], + [ + "type", + 11193 + ], + [ + "additionalProperties", + 8763 + ], + [ + "provenance", + 8736 + ], + [ + "data", + 8547 + ], + [ + "observed_at", + 8274 + ], + [ + "source_ids", + 8268 + ], + [ + "source_ref", + 8034 + ], + [ + "json_pointer", + 6990 + ], + [ + "text", + 5782 + ], + [ + "author", + 5319 + ], + [ + "origin", + 5058 + ], + [ + "properties", + 4888 + ], + [ + "pattern", + 4460 + ], + [ + "value", + 4288 + ] + ], + "calls": [ + { + "ref": "llm/operations/6c0a36f93bea41b87241a30769bd92bb6dc387869b46d3a013ec595cfc7e9548/request.json", + "prompt": "entity_resolution_plan_v4", + "message_utf8_bytes": 47130, + "user_repeated_strings_ge80_bytes": 10756, + "json_key_bytes": 11923, + "top_json_keys_by_bytes": [ + [ + "json_pointer", + 1305 + ], + [ + "source_ref", + 1196 + ], + [ + "kind", + 693 + ], + [ + "case_pointer", + 690 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 481 + ], + [ + "origin", + 396 + ], + [ + "author", + 351 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/88adb8b462df2c473b421f617b086dd65351532f28e81a7a1052e1f24da87dea/request.json", + "prompt": "entity_resolution_assessment_v4", + "message_utf8_bytes": 49139, + "user_repeated_strings_ge80_bytes": 10756, + "json_key_bytes": 12727, + "top_json_keys_by_bytes": [ + [ + "json_pointer", + 1305 + ], + [ + "source_ref", + 1196 + ], + [ + "kind", + 707 + ], + [ + "case_pointer", + 690 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 481 + ], + [ + "origin", + 405 + ], + [ + "author", + 351 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/request.json", + "prompt": "case_interpretation_resolved_v8", + "message_utf8_bytes": 37361, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 7659, + "top_json_keys_by_bytes": [ + [ + "$record", + 1310 + ], + [ + "$ref", + 483 + ], + [ + "metadata_ref", + 360 + ], + [ + "kind", + 294 + ], + [ + "data", + 280 + ], + [ + "type", + 245 + ], + [ + "source_ref", + 169 + ], + [ + "provenance", + 169 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/cdf9fddd5dccf7c6859f2f4c5aa65e46778d6d44e446cf579fa6b6f462b9b85c/request.json", + "prompt": "case_interpretation_resolved_v8", + "message_utf8_bytes": 43824, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 7789, + "top_json_keys_by_bytes": [ + [ + "$record", + 1310 + ], + [ + "$ref", + 483 + ], + [ + "metadata_ref", + 360 + ], + [ + "kind", + 294 + ], + [ + "data", + 280 + ], + [ + "type", + 245 + ], + [ + "source_ref", + 169 + ], + [ + "provenance", + 169 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/request.json", + "prompt": "hypotheses_v4", + "message_utf8_bytes": 36589, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 8000, + "top_json_keys_by_bytes": [ + [ + "$record", + 1310 + ], + [ + "kind", + 441 + ], + [ + "data", + 427 + ], + [ + "$ref", + 420 + ], + [ + "metadata_ref", + 360 + ], + [ + "source_ids", + 286 + ], + [ + "source_ref", + 169 + ], + [ + "provenance", + 169 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/ca6cdff81de3cbae0492c26802daa287b11bf4fabefad477a9b64f1b6db30112/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 52440, + "user_repeated_strings_ge80_bytes": 1042, + "json_key_bytes": 17489, + "top_json_keys_by_bytes": [ + [ + "kind", + 1008 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "author", + 351 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 5195, + "prefix_hash": "e23cc8e74af7c0ae1482335f79e3db8d0d6c5166bb0b0d8f1feacac6efd1996f" + } + }, + { + "ref": "llm/operations/54ef9b495e10fe49a2ffad5909c89efdbfe7ef7645b601865d12e5223b0651bc/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 56761, + "user_repeated_strings_ge80_bytes": 1144, + "json_key_bytes": 18370, + "top_json_keys_by_bytes": [ + [ + "kind", + 1036 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 351 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 10096, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 61401, + "user_repeated_strings_ge80_bytes": 1246, + "json_key_bytes": 19094, + "top_json_keys_by_bytes": [ + [ + "kind", + 1064 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 364 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 15269, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/a4ed5334e4125ed14bcbca18629a561513bba48ef92afecc570c14d9e90e05cc/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 64153, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 19841, + "top_json_keys_by_bytes": [ + [ + "kind", + 1092 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 377 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 18366, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/23e886f4a2c5eeadfea37a9114a2282780ab8a12c14b970fdcc26da184fc793b/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 66334, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 20439, + "top_json_keys_by_bytes": [ + [ + "kind", + 1120 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 390 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 20812, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/90894bde812875d10dcc9a11218c864322aa1f10e8f2c0ee7db07eaa21a4a687/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 70016, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 21078, + "top_json_keys_by_bytes": [ + [ + "kind", + 1148 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 403 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 24917, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/bbf03137db61614a7898353127aae3d114e56606ca757881038446b590a4cc21/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 73209, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 21696, + "top_json_keys_by_bytes": [ + [ + "kind", + 1176 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "source_ref", + 416 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 28494, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/311670121264ec34bfd6740a6fa112f0ff3b174752524ef68a2010f28566be9a/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 75524, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 22263, + "top_json_keys_by_bytes": [ + [ + "kind", + 1204 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "text", + 420 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 31062, + "prefix_hash": "f7fd74b23b362f0279643794be629df321186f3ec2e5a3930991818b90f378e1" + } + }, + { + "ref": "llm/operations/e6bac873bcd787e57693424ba50f3a1e6f2de2f28cb729e8f92e8f99c9b39ec4/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 79578, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 22884, + "top_json_keys_by_bytes": [ + [ + "kind", + 1232 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "text", + 441 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 35531, + "prefix_hash": "d448f69cdc29d32da1128e1895f34d92eb522a400ca0b0d1f280200511eb2a3d" + } + }, + { + "ref": "llm/operations/d77b7bdbdcd1547efeb8874ffb7812c7aadd28c8445dac3a938e37e07b47ac4c/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 82599, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 23505, + "top_json_keys_by_bytes": [ + [ + "kind", + 1260 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "text", + 462 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 38897, + "prefix_hash": "01239ca7a0c10c9d9f963526da97319ae5742a6520466b92259c88af56ac1df1" + } + }, + { + "ref": "llm/operations/c3ea7e68dd04531186c5516a41902ac8aa70355aae154470661dc531f3009d7d/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 85832, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 24126, + "top_json_keys_by_bytes": [ + [ + "kind", + 1288 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "text", + 483 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 42503, + "prefix_hash": "daa5c52fd1895e44b023ebe70070d18633de89ecbc48e0a1bc21482730db0458" + } + }, + { + "ref": "llm/operations/b69100e58a16907aef34da21ce7b897405511def5ae642d961494693af611bd2/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 85876, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 24147, + "top_json_keys_by_bytes": [ + [ + "kind", + 1288 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "text", + 483 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 42553, + "prefix_hash": "daa5c52fd1895e44b023ebe70070d18633de89ecbc48e0a1bc21482730db0458" + } + }, + { + "ref": "llm/operations/048af72d2a0d9a782674ee9f9391140cb15f6e18fd32e44316277b9a79b8bb23/request.json", + "prompt": "investigation_project_v10", + "message_utf8_bytes": 85878, + "user_repeated_strings_ge80_bytes": 1348, + "json_key_bytes": 24147, + "top_json_keys_by_bytes": [ + [ + "kind", + 1288 + ], + [ + "type", + 791 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 598 + ], + [ + "provenance", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "data", + 532 + ], + [ + "text", + 483 + ] + ], + "stable_partition": { + "prefix_bytes": 57360, + "live_bytes": 42555, + "prefix_hash": "daa5c52fd1895e44b023ebe70070d18633de89ecbc48e0a1bc21482730db0458" + } + } + ] + }, + { + "path": "C:/Users/User/Documents/Projekte/VianoBugAnalysis/VianoBugAnalysis/service-data/trials/bug17-stable-case-cache-20261016/cases/ee545dc4fba1e7d80fe28afa53898e02427d7114493f62d3eb771d670253282d/b7d27e7124054a03cdbd09ce73a97016ddea0e126653d20ad02b8674d02393c5/g00000148.zip", + "identity": { + "case_id": "BUG-000017", + "package_id": "trial-stable-case-cache-BUG-000017-20261016", + "package_generation": 148, + "state": "INVESTIGATING_HYPOTHESES" + }, + "zip_bytes": 36556503, + "raw_member_bytes": 36342881, + "compressed_member_bytes": 36342881, + "members": 658, + "zip_compression_methods": { + "0": 658 + }, + "deflate6_estimated_payload_bytes": 10316768, + "deflate6_by_category": { + "original_archives": 2837937, + "original_members": 5285067, + "case": 63403, + "history": 89709, + "research": 9939, + "analysis": 487433, + "llm_requests": 401355, + "llm_other": 25746, + "analysis_contexts": 1075348, + "manifest.json": 40831 + }, + "categories": { + "original_archives": { + "files": 2, + "raw_bytes": 5223946, + "compressed_bytes": 5223946 + }, + "original_members": { + "files": 225, + "raw_bytes": 18575957, + "compressed_bytes": 18575957 + }, + "case": { + "files": 8, + "raw_bytes": 406273, + "compressed_bytes": 406273 + }, + "history": { + "files": 148, + "raw_bytes": 168325, + "compressed_bytes": 168325 + }, + "research": { + "files": 9, + "raw_bytes": 68290, + "compressed_bytes": 68290 + }, + "analysis": { + "files": 206, + "raw_bytes": 2104418, + "compressed_bytes": 2104418 + }, + "llm_requests": { + "files": 21, + "raw_bytes": 1896139, + "compressed_bytes": 1896139 + }, + "llm_other": { + "files": 21, + "raw_bytes": 57285, + "compressed_bytes": 57285 + }, + "analysis_contexts": { + "files": 17, + "raw_bytes": 7686103, + "compressed_bytes": 7686103 + }, + "manifest.json": { + "files": 1, + "raw_bytes": 156145, + "compressed_bytes": 156145 + } + }, + "stored_context_components": { + "case": { + "total_bytes": 2991507, + "unique_value_bytes": 175971, + "repeated_value_bytes": 2815536, + "occurrences": 17 + }, + "case_sources": { + "total_bytes": 2179961, + "unique_value_bytes": 128233, + "repeated_value_bytes": 2051728, + "occurrences": 17 + }, + "evidence": { + "total_bytes": 1578323, + "unique_value_bytes": 1451674, + "repeated_value_bytes": 126649, + "occurrences": 17 + }, + "hypotheses": { + "total_bytes": 228291, + "unique_value_bytes": 211499, + "repeated_value_bytes": 16792, + "occurrences": 17 + }, + "tool_schema": { + "total_bytes": 180693, + "unique_value_bytes": 10629, + "repeated_value_bytes": 170064, + "occurrences": 17 + }, + "previous_result": { + "total_bytes": 90675, + "unique_value_bytes": 84347, + "repeated_value_bytes": 6328, + "occurrences": 17 + }, + "budget": { + "total_bytes": 76749, + "unique_value_bytes": 68540, + "repeated_value_bytes": 8209, + "occurrences": 17 + }, + "interpretation": { + "total_bytes": 63801, + "unique_value_bytes": 3753, + "repeated_value_bytes": 60048, + "occurrences": 17 + }, + "budget_policy": { + "total_bytes": 3927, + "unique_value_bytes": 231, + "repeated_value_bytes": 3696, + "occurrences": 17 + }, + "policy": { + "total_bytes": 2975, + "unique_value_bytes": 175, + "repeated_value_bytes": 2800, + "occurrences": 17 + }, + "early_review": { + "total_bytes": 663, + "unique_value_bytes": 39, + "repeated_value_bytes": 624, + "occurrences": 17 + }, + "format": { + "total_bytes": 493, + "unique_value_bytes": 29, + "repeated_value_bytes": 464, + "occurrences": 17 + }, + "prompt_version": { + "total_bytes": 459, + "unique_value_bytes": 27, + "repeated_value_bytes": 432, + "occurrences": 17 + }, + "selected_hypothesis": { + "total_bytes": 68, + "unique_value_bytes": 16, + "repeated_value_bytes": 52, + "occurrences": 17 + }, + "previous_rejection": { + "total_bytes": 22, + "unique_value_bytes": 22, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + "format_version": { + "total_bytes": 17, + "unique_value_bytes": 1, + "repeated_value_bytes": 16, + "occurrences": 17 + } + }, + "largest_members": [ + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/hits.json", + "raw_bytes": 5014733, + "compressed_bytes": 5014733 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/archive.tar.gz", + "raw_bytes": 3071876, + "compressed_bytes": 3071876 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/references.json", + "raw_bytes": 2502119, + "compressed_bytes": 2502119 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/prioritized_references.txt", + "raw_bytes": 2415907, + "compressed_bytes": 2415907 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/references.txt", + "raw_bytes": 2415907, + "compressed_bytes": 2415907 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/historical_sql_references.json", + "raw_bytes": 2356795, + "compressed_bytes": 2356795 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/archive.tar.gz", + "raw_bytes": 2152070, + "compressed_bytes": 2152070 + }, + { + "path": "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/prioritized_hits.json", + "raw_bytes": 1483066, + "compressed_bytes": 1483066 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0013.json", + "raw_bytes": 512371, + "compressed_bytes": 512371 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0012-attempt-0001.json", + "raw_bytes": 495946, + "compressed_bytes": 495946 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0012.json", + "raw_bytes": 495900, + "compressed_bytes": 495900 + }, + { + "path": "analysis/investigation/0001/contexts/H1-0011.json", + "raw_bytes": 483787, + "compressed_bytes": 483787 + } + ], + "exact_duplicate_groups": 8, + "exact_duplicate_raw_bytes": 184749, + "exact_duplicate_compressed_bytes": 184749, + "largest_exact_duplicate_groups": [ + { + "copies": 2, + "raw_duplicate_bytes": 152247, + "compressed_duplicate_bytes": 152247, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/environment/world_schema_snapshot.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/database/world_schema_snapshot.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 19560, + "compressed_duplicate_bytes": 19560, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/development_files/src/server/scripts/EasternKingdoms/arathi_highlands.cpp", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/files/src/server/scripts/EasternKingdoms/arathi_highlands.cpp" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 5172, + "compressed_duplicate_bytes": 5172, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/high_relevance_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/primary_references.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 4236, + "compressed_duplicate_bytes": 4236, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/manifest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/wowdiag_manifest.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 2112, + "compressed_duplicate_bytes": 2112, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/source/snippets/02_arathi_highlands.cpp_614-671.txt", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/snippets/03_arathi_highlands.cpp_614-671.txt" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 1079, + "compressed_duplicate_bytes": 1079, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/source_seeds.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/source/search_seeds.json" + ] + }, + { + "copies": 2, + "raw_duplicate_bytes": 281, + "compressed_duplicate_bytes": 281, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/diagnostic_focus.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/diagnostic_focus.json" + ] + }, + { + "copies": 32, + "raw_duplicate_bytes": 62, + "compressed_duplicate_bytes": 62, + "paths": [ + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/attachments.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/copied_attachments.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/bug/runtime_spells.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/creature_addon.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/creature_questitem.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/npc_spellclick_spells.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/npc_vendor.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/smart_script_numeric_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/smart_scripts.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2768/vehicle_template_accessory.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/creature_addon.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/creature_questitem.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/creature_text.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/npc_spellclick_spells.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/npc_vendor.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/smart_script_numeric_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/smart_scripts.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/creatures/2774/vehicle_template_accessory.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_creature_quest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_gameobject_quest.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_quest_condition.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/game_event_seasonal_questrelation.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/gameobject_questender.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/gameobject_queststarter.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_mail_sender.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_objective_references.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_offer_reward.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/database/quest_pool_members.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowdiag/members/BUG-000017-20261015-213913/findings/quest_fulfillment_paths.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/build/relevant_compile_commands.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/database/relationship_map.json", + "original/vcore/imports/327b4b7b56043984df4ca619d1d359e9b940062f9aefda3c3594324d9f42d918/wowsrc/members/WOWSRC-BUG-000017-20261015-213934/input/ignored_runtime_noise.json" + ] + } + ], + "canonical_json_duplicate_raw_bytes": 163077, + "original_tar_members_also_stored_separately": { + "files": 225, + "raw_bytes": 18575957, + "outer_zip_member_compressed_bytes": 18575957 + }, + "request_count": 21, + "research_repetition": { + "evidence_item_total_bytes": 218820, + "evidence_item_unique_bytes": 29497, + "evidence_item_fields_bytes": { + "content": 127382, + "record": 72946, + "record_ref": 13668 + }, + "source_line_total_bytes": 92683, + "source_line_unique_bytes": 7997, + "source_line_occurrences": 3352, + "source_line_unique_count": 280 + }, + "prompts": { + "entity_resolution_plan_v4": { + "calls": 1, + "message_utf8_bytes": 47133, + "within_call_repeated_strings_ge80_bytes": 10756 + }, + "entity_resolution_assessment_v4": { + "calls": 1, + "message_utf8_bytes": 48813, + "within_call_repeated_strings_ge80_bytes": 10756 + }, + "case_interpretation_resolved_v8": { + "calls": 1, + "message_utf8_bytes": 36510, + "within_call_repeated_strings_ge80_bytes": 0 + }, + "hypotheses_v4": { + "calls": 1, + "message_utf8_bytes": 35000, + "within_call_repeated_strings_ge80_bytes": 0 + }, + "investigation_project_v11": { + "calls": 17, + "message_utf8_bytes": 1400843, + "within_call_repeated_strings_ge80_bytes": 10538 + } + }, + "system_message_total_bytes": 130524, + "system_message_repeated_bytes": 101744, + "top_level_components": [ + { + "prompt": "investigation_project_v11", + "field": "input.sources", + "total_canonical_bytes": 338215, + "unique_value_bytes": 19895, + "repeated_value_bytes": 318320, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.evidence", + "total_canonical_bytes": 220312, + "unique_value_bytes": 196952, + "repeated_value_bytes": 23360, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.hypotheses", + "total_canonical_bytes": 152118, + "unique_value_bytes": 139772, + "repeated_value_bytes": 12346, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "output_schema", + "total_canonical_bytes": 150008, + "unique_value_bytes": 8824, + "repeated_value_bytes": 141184, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.shared_sources", + "total_canonical_bytes": 105814, + "unique_value_bytes": 52448, + "repeated_value_bytes": 53366, + "occurrences": 16 + }, + { + "prompt": "investigation_project_v11", + "field": "input.shared_metadata", + "total_canonical_bytes": 91535, + "unique_value_bytes": 83312, + "repeated_value_bytes": 8223, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.unread_sources", + "total_canonical_bytes": 79356, + "unique_value_bytes": 4668, + "repeated_value_bytes": 74688, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.interpretation", + "total_canonical_bytes": 63801, + "unique_value_bytes": 3753, + "repeated_value_bytes": 60048, + "occurrences": 17 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "context", + "total_canonical_bytes": 41016, + "unique_value_bytes": 41016, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "context", + "total_canonical_bytes": 41016, + "unique_value_bytes": 41016, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.unread_inventory_scope", + "total_canonical_bytes": 32079, + "unique_value_bytes": 1887, + "repeated_value_bytes": 30192, + "occurrences": 17 + }, + { + "prompt": "hypotheses_v4", + "field": "input.data", + "total_canonical_bytes": 24942, + "unique_value_bytes": 24942, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.budget", + "total_canonical_bytes": 24358, + "unique_value_bytes": 22774, + "repeated_value_bytes": 1584, + "occurrences": 17 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.data", + "total_canonical_bytes": 20415, + "unique_value_bytes": 20415, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.tool_schema", + "total_canonical_bytes": 12563, + "unique_value_bytes": 739, + "repeated_value_bytes": 11824, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.shared_results", + "total_canonical_bytes": 3976, + "unique_value_bytes": 568, + "repeated_value_bytes": 3408, + "occurrences": 14 + }, + { + "prompt": "investigation_project_v11", + "field": "input.budget_policy", + "total_canonical_bytes": 3927, + "unique_value_bytes": 231, + "repeated_value_bytes": 3696, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.case", + "total_canonical_bytes": 3043, + "unique_value_bytes": 179, + "repeated_value_bytes": 2864, + "occurrences": 17 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "output_schema", + "total_canonical_bytes": 3003, + "unique_value_bytes": 3003, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.policy", + "total_canonical_bytes": 2975, + "unique_value_bytes": 175, + "repeated_value_bytes": 2800, + "occurrences": 17 + }, + { + "prompt": "hypotheses_v4", + "field": "output_schema", + "total_canonical_bytes": 1321, + "unique_value_bytes": 1321, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.shared", + "total_canonical_bytes": 1311, + "unique_value_bytes": 1311, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.shared", + "total_canonical_bytes": 1311, + "unique_value_bytes": 1311, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "output_schema", + "total_canonical_bytes": 1214, + "unique_value_bytes": 1214, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.shapes", + "total_canonical_bytes": 1004, + "unique_value_bytes": 1004, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.shapes", + "total_canonical_bytes": 1004, + "unique_value_bytes": 1004, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "captures", + "total_canonical_bytes": 934, + "unique_value_bytes": 934, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "output_schema", + "total_canonical_bytes": 682, + "unique_value_bytes": 682, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.early_review", + "total_canonical_bytes": 663, + "unique_value_bytes": 39, + "repeated_value_bytes": 624, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.previous_result", + "total_canonical_bytes": 562, + "unique_value_bytes": 508, + "repeated_value_bytes": 54, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.format", + "total_canonical_bytes": 493, + "unique_value_bytes": 29, + "repeated_value_bytes": 464, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "input.prompt_version", + "total_canonical_bytes": 459, + "unique_value_bytes": 27, + "repeated_value_bytes": 432, + "occurrences": 17 + }, + { + "prompt": "investigation_project_v11", + "field": "task", + "total_canonical_bytes": 408, + "unique_value_bytes": 24, + "repeated_value_bytes": 384, + "occurrences": 17 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "identity_guidance", + "total_canonical_bytes": 400, + "unique_value_bytes": 400, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "identity_guidance", + "total_canonical_bytes": 400, + "unique_value_bytes": 400, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "plan", + "total_canonical_bytes": 106, + "unique_value_bytes": 106, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "catalogs", + "total_canonical_bytes": 99, + "unique_value_bytes": 99, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "catalogs", + "total_canonical_bytes": 99, + "unique_value_bytes": 99, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.selected_hypothesis", + "total_canonical_bytes": 68, + "unique_value_bytes": 16, + "repeated_value_bytes": 52, + "occurrences": 17 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "task", + "total_canonical_bytes": 30, + "unique_value_bytes": 30, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "task", + "total_canonical_bytes": 24, + "unique_value_bytes": 24, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.previous_rejection", + "total_canonical_bytes": 22, + "unique_value_bytes": 22, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "task", + "total_canonical_bytes": 21, + "unique_value_bytes": 21, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "task", + "total_canonical_bytes": 21, + "unique_value_bytes": 21, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "investigation_project_v11", + "field": "input.format_version", + "total_canonical_bytes": 17, + "unique_value_bytes": 1, + "repeated_value_bytes": 16, + "occurrences": 17 + }, + { + "prompt": "case_interpretation_resolved_v8", + "field": "input.encoding", + "total_canonical_bytes": 16, + "unique_value_bytes": 16, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "hypotheses_v4", + "field": "input.encoding", + "total_canonical_bytes": 16, + "unique_value_bytes": 16, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "candidates", + "total_canonical_bytes": 2, + "unique_value_bytes": 2, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_plan_v4", + "field": "max_searches", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + }, + { + "prompt": "entity_resolution_assessment_v4", + "field": "max_searches", + "total_canonical_bytes": 1, + "unique_value_bytes": 1, + "repeated_value_bytes": 0, + "occurrences": 1 + } + ], + "json_keys_by_bytes": [ + [ + "kind", + 23009 + ], + [ + "type", + 13972 + ], + [ + "additionalProperties", + 11224 + ], + [ + "observed_at", + 10430 + ], + [ + "data", + 10374 + ], + [ + "provenance", + 10309 + ], + [ + "source_ids", + 9880 + ], + [ + "metadata_ref", + 9420 + ], + [ + "source_ref", + 8580 + ], + [ + "text", + 7602 + ], + [ + "json_pointer", + 7260 + ], + [ + "origin", + 7011 + ], + [ + "author", + 6705 + ], + [ + "properties", + 6175 + ], + [ + "pattern", + 5650 + ] + ], + "calls": [ + { + "ref": "llm/operations/6c0a36f93bea41b87241a30769bd92bb6dc387869b46d3a013ec595cfc7e9548/request.json", + "prompt": "entity_resolution_plan_v4", + "message_utf8_bytes": 47133, + "user_repeated_strings_ge80_bytes": 10756, + "json_key_bytes": 11923, + "top_json_keys_by_bytes": [ + [ + "json_pointer", + 1305 + ], + [ + "source_ref", + 1196 + ], + [ + "kind", + 693 + ], + [ + "case_pointer", + 690 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 481 + ], + [ + "origin", + 396 + ], + [ + "author", + 351 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/88adb8b462df2c473b421f617b086dd65351532f28e81a7a1052e1f24da87dea/request.json", + "prompt": "entity_resolution_assessment_v4", + "message_utf8_bytes": 48813, + "user_repeated_strings_ge80_bytes": 10756, + "json_key_bytes": 12560, + "top_json_keys_by_bytes": [ + [ + "json_pointer", + 1305 + ], + [ + "source_ref", + 1196 + ], + [ + "kind", + 707 + ], + [ + "case_pointer", + 690 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 481 + ], + [ + "origin", + 405 + ], + [ + "author", + 351 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/572afccbd4034d9c5485045cb4bb28b61fdd40e48dc8a3fab67cfc17e997cd65/request.json", + "prompt": "case_interpretation_resolved_v8", + "message_utf8_bytes": 36510, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 7348, + "top_json_keys_by_bytes": [ + [ + "$record", + 1300 + ], + [ + "$ref", + 455 + ], + [ + "metadata_ref", + 360 + ], + [ + "kind", + 294 + ], + [ + "data", + 280 + ], + [ + "type", + 238 + ], + [ + "source_ref", + 156 + ], + [ + "provenance", + 143 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/5fa06d3e4f4063a74b5818fdba690a7e1cd8b145506fb7c1d2a5deefc421ef98/request.json", + "prompt": "hypotheses_v4", + "message_utf8_bytes": 35000, + "user_repeated_strings_ge80_bytes": 0, + "json_key_bytes": 7542, + "top_json_keys_by_bytes": [ + [ + "$record", + 1300 + ], + [ + "kind", + 420 + ], + [ + "data", + 406 + ], + [ + "$ref", + 385 + ], + [ + "metadata_ref", + 360 + ], + [ + "source_ids", + 247 + ], + [ + "source_ref", + 156 + ], + [ + "text", + 147 + ] + ], + "stable_partition": null + }, + { + "ref": "llm/operations/ca6cdff81de3cbae0492c26802daa287b11bf4fabefad477a9b64f1b6db30112/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 54135, + "user_repeated_strings_ge80_bytes": 192, + "json_key_bytes": 17731, + "top_json_keys_by_bytes": [ + [ + "kind", + 1008 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "author", + 351 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 6169, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/54ef9b495e10fe49a2ffad5909c89efdbfe7ef7645b601865d12e5223b0651bc/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 58772, + "user_repeated_strings_ge80_bytes": 294, + "json_key_bytes": 18663, + "top_json_keys_by_bytes": [ + [ + "kind", + 1036 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "author", + 351 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 11418, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/71fd77c20b2af9bb2d842927c7a39cc8e1cf3e15541f387a26054fdb1047b6e4/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 63436, + "user_repeated_strings_ge80_bytes": 396, + "json_key_bytes": 19415, + "top_json_keys_by_bytes": [ + [ + "kind", + 1064 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "author", + 351 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 16638, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/6c4a875ef7fa994dd58f974afe21784f6a5077b09d2d1748e7facf3dc8083729/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 65888, + "user_repeated_strings_ge80_bytes": 595, + "json_key_bytes": 20090, + "top_json_keys_by_bytes": [ + [ + "kind", + 1092 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "metadata_ref", + 360 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 19359, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/c619a7901de5674f54e8371759fba596a7746f67d62499b198780813912e5c31/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 70806, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 22089, + "top_json_keys_by_bytes": [ + [ + "kind", + 1120 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "metadata_ref", + 390 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 25148, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/b5de43dfa1122fa86decfa538047ee813621839eded8ed15356d341f3439e383/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 73842, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 22843, + "top_json_keys_by_bytes": [ + [ + "kind", + 1148 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "metadata_ref", + 420 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 28514, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/6849c974442865e5ca3e8f146ef4520c275f2e37a25fb7caa498f17089ed6dc1/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 77785, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 23470, + "top_json_keys_by_bytes": [ + [ + "kind", + 1176 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "metadata_ref", + 450 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 32913, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/475d5f458554c35131f24fc92fb2e762c69a8d9c6d4ab9d6426fbd72e6303af3/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 80230, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 24121, + "top_json_keys_by_bytes": [ + [ + "kind", + 1204 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "metadata_ref", + 480 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 35636, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/8f58f73379896f4edda417f564668be151dea6f1dd75d1872c8aeb64d0cef5ce/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 83442, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 24793, + "top_json_keys_by_bytes": [ + [ + "kind", + 1232 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ], + [ + "metadata_ref", + 510 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 39188, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/9d94a56f71b21f01a9b59e1f935e199a9e59dd72e2ab77b517fb5e2b1bdd864e/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 86998, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 25442, + "top_json_keys_by_bytes": [ + [ + "kind", + 1260 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "metadata_ref", + 540 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 43110, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/ba23de00b87dde357a659990150f6c36eef21e4cff573f4b4ee4be6dd16c2446/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 90310, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 26114, + "top_json_keys_by_bytes": [ + [ + "kind", + 1288 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "metadata_ref", + 570 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 46776, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/e9ebe331ccfea690913e97129c6c8906760fc14e445eafa01a30924eb040ed4e/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 93077, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 26926, + "top_json_keys_by_bytes": [ + [ + "kind", + 1316 + ], + [ + "type", + 784 + ], + [ + "additionalProperties", + 644 + ], + [ + "metadata_ref", + 615 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 49876, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/1380b43663a13f859f4340f18311e1da621f0278d65d9db8a816c6468a56e074/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 96183, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 27625, + "top_json_keys_by_bytes": [ + [ + "kind", + 1344 + ], + [ + "type", + 784 + ], + [ + "metadata_ref", + 645 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 53309, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/97fd3ebe3705d6e44ef75054ecfa47919ceda5f78610190b01f149d5963f2649/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 98736, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 28298, + "top_json_keys_by_bytes": [ + [ + "kind", + 1372 + ], + [ + "type", + 784 + ], + [ + "metadata_ref", + 675 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 56150, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/9ca4b010c7ebc9e0ae40a106866bbb196dd23366b2e453b50c4a6e629b9f6874/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 101062, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 28965, + "top_json_keys_by_bytes": [ + [ + "kind", + 1400 + ], + [ + "type", + 784 + ], + [ + "metadata_ref", + 705 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 58786, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/1ee80d0e9b0de9dfb8c8b92cf67de5db6007c769b0b5fe9b0e676f7f6f758b1e/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 101106, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 28986, + "top_json_keys_by_bytes": [ + [ + "kind", + 1400 + ], + [ + "type", + 784 + ], + [ + "metadata_ref", + 705 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "data", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 58836, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + }, + { + "ref": "llm/operations/224d9f1bd039c45d5d91315d847f421fa0dcdeda31cea6416ffd8b342941b46d/request.json", + "prompt": "investigation_project_v11", + "message_utf8_bytes": 105035, + "user_repeated_strings_ge80_bytes": 697, + "json_key_bytes": 29842, + "top_json_keys_by_bytes": [ + [ + "kind", + 1435 + ], + [ + "type", + 784 + ], + [ + "metadata_ref", + 750 + ], + [ + "additionalProperties", + 644 + ], + [ + "source_ids", + 559 + ], + [ + "observed_at", + 546 + ], + [ + "provenance", + 533 + ], + [ + "text", + 532 + ] + ], + "stable_partition": { + "prefix_bytes": 58078, + "live_bytes": 63206, + "prefix_hash": "97b35f43b83473e5331f848b4ad8b55deaad55367926885751f67d73cf9d70f1" + } + } + ] + } + ] +} diff --git a/docs/redundancy-audit-20261016.md b/docs/redundancy-audit-20261016.md new file mode 100644 index 0000000..9049817 --- /dev/null +++ b/docs/redundancy-audit-20261016.md @@ -0,0 +1,160 @@ +# Redundanzbilanz vom 16.10.2026 + +## Umfang und Methode + +Vier erhaltene, durch PackageReader validierte Case-Pakete untersucht: Bug 20 g108 +(alter investigation_v1-Stand) und Bug 17 g124 (v9), g110 (v10), g148 (v11). +Keines ist ein abgeschlossenes OUTPUT_READY-Paket. Der neueste Stand dient als +Hauptbeispiel; ältere Versionen sind keine gleichwertigen Qualitätsbenchmarks. +Keine LLM-Aufrufe, kein Umbau oder Löschen von Paketinhalt. + +Reproduzierbares Werkzeug: `scripts/redundancy_audit.py`, Aufruf mit einem oder +mehreren Paketpfaden und `--output `. +Aggregierte Messdaten ohne Quelltext-/Promptinhalte: +`measurements/redundancy-audit-20261016.json`. +Messstand: Code nach fa1a0ab, historische Pakete und Prompts unverändert. +Alle MB/KB/GB dezimal, alle Textmessungen UTF-8-Bytes, keine Tokenzählung. + +## 1. Paketgröße und fehlende Kompression + +| Paket | Dateien | ZIP auf Platte | DEFLATE-6-Payload, simuliert | +|---|---:|---:|---:| +| Bug 20 g108 | 517 | 63,22 MB | 20,17 MB | +| Bug 17 g124 | 576 | 34,61 MB | 9,97 MB | +| Bug 17 g110 | 547 | 33,61 MB | 9,79 MB | +| Bug 17 g148 | 658 | 36,56 MB | 10,32 MB | + +**Alle ZIP-Einträge verwenden ZIP_STORED, also keine ZIP-Kompression.** Die +Simulation komprimiert jeden Eintrag separat mit raw DEFLATE, Stufe 6, und prüft +für jeden Eintrag die byteidentische Dekompression. ZIP-Header/Verzeichnis kommen +zur simulierten Payload hinzu. Beim jüngsten Paket ergeben sich damit ungefähr +10,53 MB statt 36,56 MB, rund 71 % weniger Speicher. Dies ist keine Änderung am +Format oder am Inhalt und reduziert keine LLM-Tokens. Laufzeitkosten und die +Writer-/Sicherheitsprüfungen wären bei einer Implementierung zu testen. + +## 2. Zusammensetzung des neuesten Pakets + +| Inhalt Bug 17 g148 | Bytes in MB | Anteil an 36,34 MB Dateiinhalten | +|---|---:|---:| +| Entpackte Originaldateien | 18,576 | 51,1 % | +| Ursprüngliche TAR.GZ-Archive | 5,224 | 14,4 % | +| Investigation-Kontexte | 7,686 | 21,1 % | +| Weitere Analyseartefakte | 2,104 | 5,8 % | +| Gespeicherte LLM-Requests | 1,896 | 5,2 % | +| Aufbereiteter Case | 0,406 | 1,1 % | +| Sonstiges: Historie, Forschung, LLM-Ergebnisse, Manifest | 0,450 | 1,2 % | + +Die ZIP-Verzeichnis-/Headerdaten ergänzen weitere 0,214 MB. +Die größte einzelne Datei ist das originale wowsrc `source/hits.json` mit +5,015 MB. Weitere große Originaldateien sind Code-/SQL-Referenzsammlungen. +Ihre fachliche Relevanz wurde hier nicht beurteilt. + +### Exakte Duplikate versus doppelte Repräsentationen + +- Byteidentische vollständige Dateien: nur **0,185 MB** zusätzliche Kopien im + neuesten Paket. Reines Deduplizieren ganzer Dateien löst das Hauptproblem nicht. +- **225 entpackte Originaldateien mit 18,576 MB** sind zusätzlich byteidentisch + innerhalb der beiden archivierten TAR.GZ-Dateien vorhanden. Das ist eine + doppelte Repräsentation derselben Originaldaten. Die TAR.GZ-Dateien selbst + belegen 5,224 MB; diese Werte dürfen nicht als zwei unabhängige Einsparungen + addiert werden. Eine neue Referenz-/Lesestrategie wäre nötig, um eine Kopie + wegzulassen. Bestehende Originaldateien dürfen gemäß Architektur nicht gelöscht + werden. Bei neuen Paketen wäre eine bewusste Import-/Formatentscheidung nötig. +- **5,097 MB kanonisch identische Feldwerte** werden allein durch wiederholte + Speicherung von `case`, `case_sources`, `tool_schema` und `interpretation` in + den 17 Investigation-Kontexten zusätzlich abgelegt. Das ist eine Untergrenze + für Kontextredundanz: wachsende Evidenzlisten enthalten weitere wiederholte + Unterobjekte. Neu entworfene Kontexte könnten auf unveränderliche Artefakte + innerhalb desselben Pakets verweisen, statt diese jedes Mal einzubetten. +- Kontext-Snapshot und daraus erzeugter Request speichern teilweise dieselben + Inhalte in verschiedenen Darstellungen. Diese Überlappung ist nachweisbar, + aber hier nicht als zusätzliche unabhängige Einsparsumme quantifiziert. + +## 3. Aktuelle Investigation-Prompts + +17 gespeicherte v11-Requests ergeben **1,401 MB Nachrichteninhalt** (System und +User, ohne äußere JSON-Transporthülle). Die einzelnen Aufrufe wachsen von +54,1 KB auf 105,0 KB. Bei der bestehenden Cache-Partition wächst die separat +gelieferte Live-Darstellung von 6,2 KB auf 63,2 KB; diese Transportmessung enthält +eine andere JSON-Hülle und ist deshalb kein direkter Summand der 1,401 MB. + +### Wiederholung zwischen Aufrufen + +| Komponente | Insgesamt | Unterschiedliche vollständige Werte | Wiederholt | +|---|---:|---:|---:| +| Aufbereitete Quellen `sources` | 338,2 KB | 19,9 KB | 318,3 KB | +| Output-Schema | 150,0 KB | 8,8 KB | 141,2 KB | +| Interpretation | 63,8 KB | 3,8 KB | 60,0 KB | +| Evidenzobjekte, einzeln verglichen | 218,8 KB | 29,5 KB | 189,3 KB | +| Quellcodezeilen in `shared_sources` | 92,7 KB | 8,0 KB | 84,7 KB | + +Evidenzobjekte werden einzeln nach kanonischem JSON verglichen. Quellcodezeilen +werden nach Quellmetadaten, Zeilennummer und Inhalt verglichen, nicht allein nach +Zeilentext. 3.352 Zeilenvorkommen entsprechen 280 unterschiedlichen belegten +Zeilen. Alle Werte enthalten weiterhin die notwendigen unterschiedlichen Daten; +ein Übertragungsprotokoll benötigt zusätzlich IDs/Referenzen und Cache-Verwaltung. + +**Die statischen Wiederholungen sind zum großen Teil bereits durch den stabilen +Fallcache abgedeckt.** Im zugehörigen vorangegangenen Live-Test meldeten alle +17 Investigation-Antworten 19.987 gecachte Eingabetokens. Die gespeicherten +Requests enthalten trotzdem die vollständige kanonische Anfrage für die +Nachvollziehbarkeit. Ihre Größe darf nicht mit erneut ungecacht übertragenen +oder voll berechneten Tokens gleichgesetzt werden. + +Die Evidenz und Codezeilen liegen dagegen in der veränderlichen Live-Darstellung. +Ein weiterer Ansatz ist ein versionierter Recherche-Cache beziehungsweise eine +exakt rekonstruierbare Aufteilung in bereits bekannte und neu hinzugekommene +Belege. Nicht einfach Belege weglassen: Der frühere Versuch mit selektiver +Historie führte zu Nachladeproblemen und wurde ausdrücklich zurückgenommen. + +### Wiederholung innerhalb eines Aufrufs und JSON-Struktur + +Exakt identische längere Stringwerte (ab 80 UTF-8-Bytes) wiederholen sich in den +17 v11-User-Dokumenten zusammen um **10,5 KB**, entsprechend **0,75 %** des +gesamten System-/User-Nachrichteninhalts. Der Wert ist kein vollständiges Maß +aller Redundanz: kurze Codezeilen, ähnliche Texte und überlappende Strukturen +werden nicht als identische lange Strings erkannt. Eine Ersetzung bräuchte +Referenzen und würde weniger als diese Bruttosumme sparen. + +Zum Vergleich: Die alte Bug-20-Investigation v1 enthält 1,310 MB solcher +wiederholter Strings bei 4,123 MB Nachrichteninhalt, rund 31,8 %. Dieser konkrete +Mechanismus wurde in der aktuellen Darstellung also bereits stark reduziert. +Die Fälle/Anzahl der Schritte sind verschieden; daraus folgt kein kontrollierter +Qualitäts- oder Kostenvergleich. + +Allein die JSON-Schlüsselnamen samt Anführungszeichen und Doppelpunkt belegen +bei v11 insgesamt **415,4 KB**, rund 29,7 % des Nachrichteninhalts. Das ist kein +versprochenes Einsparpotenzial von 29,7 %: Schlüssel sind für Bedeutung und +Schema nötig; Kürzungen benötigen ein verständliches gemeinsames Wörterbuch. +Der Wert zeigt aber, dass noch erhebliche Strukturkosten existieren. Beispiele +sind wiederkehrende Fakt-/Quellprovenienz und Evidenz-Records. Innerhalb aller +übermittelten Evidenzobjekte belegen `record` 72,9 KB und `record_ref` 13,7 KB, +während `content` 127,4 KB belegt (zzgl. Schlüssel/Struktur). + +## 4. Konsequenzen und Reihenfolge + +1. **ZIP-Kompression und Aufbewahrung vollständiger Generationen:** großer, + direkt messbarer Speichergewinn ohne Informationsverlust. Die 20-GB-Regel + gilt unabhängig davon weiter. Keine Auswirkung auf API-Tokenkosten. +2. **Gespeicherte Kontexte referenzieren unveränderliche Paketartefakte:** + Fallbasis/Schemas einmal, je Schritt nur Änderungen und Referenzen. Eine + Rekonstruktion muss exakt sein und auch nach Transport/Neustart funktionieren. + Keine Abhängigkeit von einem externen Dienstgedächtnis. +3. **Live-Recherchekontext effizienter übermitteln:** die 189,3 KB wiederholten + Evidenzobjekte und 84,7 KB wiederholten Quellzeilen sind konkrete Ansatzpunkte. + Diese Zahlen und die Strukturkosten überlappen teilweise; nicht addieren. + Zuerst verlustfreie Struktur-/Cache-Ansätze prüfen, erst danach inhaltliche + Auswahl mit nachgewiesener Qualität. Nicht den gesamten bisherigen Befund + erneut durch eine zusätzliche LLM zusammenfassen lassen. +4. **Provenienz für das Modell reduzieren:** doppelt mitgesendete interne + Speicherpfade, ausführliche Records und technische Verwaltungsfelder anhand + ihrer tatsächlich nötigen Funktion prüfen. Die vollständige Provenienz bleibt + in der Akte; Beleg-ID, Quelle, Abfrageumfang und Versionsbezug müssen für die + LLM verständlich bleiben. Das ist eine Designentscheidung, keine bereits + validierte verlustfreie Ersetzung. + +Es gibt aktuell keine belastbare Grundlage, eine Einsparung in Euro für diese +Schritte zu versprechen. Die vier vorhandenen Pakete erklären die Speicher- und +Textredundanz; sie zeigen nicht, welche fachlichen Informationen gefahrlos +entfallen dürfen. Ein nachfolgender Qualitätstest muss diese Frage getrennt +prüfen. An produktivem Verhalten wurde für diese Bilanz nichts geändert. diff --git a/scripts/redundancy_audit.py b/scripts/redundancy_audit.py new file mode 100644 index 0000000..4dfd2dc --- /dev/null +++ b/scripts/redundancy_audit.py @@ -0,0 +1,271 @@ +"""Read-only offline audit; reports aggregate sizes/hashes, never source contents. + +All byte counts use UTF-8 or ZIP directory sizes. Potential savings overlap and +must not be added together. This is a measurement, not a package migration. +""" +import argparse +from collections import Counter, defaultdict +import hashlib +import io +import json +from pathlib import Path +import tarfile +import zipfile +import zlib + +from viano_bug_analysis.package import PackageReader +from viano_bug_analysis.llm.gemini import GeminiProvider + + +def encoded(value): + return json.dumps(value, ensure_ascii=False, sort_keys=True, + separators=(',', ':')).encode('utf-8') + + +def digest(data): + return hashlib.sha256(data).hexdigest() + + +def category(name): + if name.startswith('original/'): + return 'original_archives' if name.endswith('/archive.tar.gz') else 'original_members' + if name.startswith('llm/'): + return 'llm_requests' if name.endswith('/request.json') else 'llm_other' + if '/contexts/' in name: + return 'analysis_contexts' + return name.split('/')[0] + + +def repeated(groups): + result = [] + for entries in groups.values(): + if len(entries) > 1: + result.append({'copies': len(entries), + 'raw_duplicate_bytes': sum(e[1] for e in entries[1:]), + 'compressed_duplicate_bytes': sum(e[2] for e in entries[1:]), + 'paths': [e[0] for e in entries]}) + return sorted(result, key=lambda v: v['raw_duplicate_bytes'], reverse=True) + + +def audit(path): + # Validate through the normal bounded reader before inspecting ZIP metadata. + with PackageReader(path) as reader: + manifest = reader.manifest + files = set(reader.files) + groups = defaultdict(list) + canonical = defaultdict(list) + categories = defaultdict(Counter) + requests = [] + archive_members = Counter() + metadata_fields = Counter() + deflate_estimate = Counter() + compression_methods = Counter() + evidence_items = {} + source_lines = {} + evidence_sizes = Counter() + context_components = defaultdict(lambda: [0, 0, 0]) + context_values = set() + with zipfile.ZipFile(path) as z: + infos = {v.filename: v for v in z.infolist() if not v.is_dir()} + for name, info in infos.items(): + data = z.read(name) + compressor = zlib.compressobj(level=6, wbits=-15) + compressed = compressor.compress(data) + compressor.flush() + assert zlib.decompress(compressed, wbits=-15) == data + deflate_size = len(compressed) + deflate_estimate[category(name)] += deflate_size + compression_methods[str(info.compress_type)] += 1 + cat = categories[category(name)] + cat.update(files=1, raw_bytes=len(data), compressed_bytes=info.compress_size) + groups[digest(data)].append((name, len(data), info.compress_size)) + if name.endswith('/archive.tar.gz'): + prefix = name.removesuffix('archive.tar.gz') + 'members/' + with tarfile.open(fileobj=io.BytesIO(data), mode='r|gz') as tar: + for member in tar: + if not member.isfile(): + continue + target = prefix + member.name + if target in files and member.size == infos[target].file_size: + with tar.extractfile(member) as stream: + same = digest(stream.read(member.size + 1)) == digest(z.read(target)) + if same: + archive_members.update(files=1, raw_bytes=member.size, + outer_zip_member_compressed_bytes=infos[target].compress_size) + if not name.endswith('.json'): + continue + try: + doc = json.loads(data) + except (ValueError, UnicodeError): + continue + canonical[digest(encoded(doc))].append((name, len(data), info.compress_size)) + if category(name) == 'analysis_contexts' and isinstance(doc, dict): + for field, value in doc.items(): + b = encoded(value) + key = (field, digest(b)) + context_components[field][0] += len(b) + context_components[field][2] += 1 + if key not in context_values: + context_components[field][1] += len(b) + context_values.add(key) + if name.startswith('llm/operations/') and name.endswith('/request.json'): + requests.append((name, doc)) + by_prompt = defaultdict(list) + system_groups = Counter() + block_groups = defaultdict(lambda: [0, 0, 0]) + per_call = [] + def leaves(value, at='$'): + if isinstance(value, dict): + for k, v in value.items(): + if isinstance(v, (dict, list)): + yield from leaves(v, at + '.' + k) + elif isinstance(v, str) and len(v.encode('utf-8')) >= 80: + yield at + '.' + k, v + elif isinstance(value, list): + for v in value: + yield from leaves(v, at + '[]') + for name, req in requests: + messages = req.get('messages', []) + msg_bytes = sum(len(m['content'].encode('utf-8')) for m in messages) + systems = [m['content'] for m in messages if m['role'] == 'system'] + for value in systems: + system_groups[(digest(value.encode()), len(value.encode()))] += 1 + user_docs = [] + strings = defaultdict(list) + keys = Counter() + def count_keys(value): + if isinstance(value, dict): + for k, v in value.items(): + keys[k] += len(encoded(k)) + 1 + count_keys(v) + elif isinstance(value, list): + for v in value: + count_keys(v) + for m in messages: + if m['role'] != 'user': + continue + try: + doc = json.loads(m['content']) + except ValueError: + continue + user_docs.append(doc) + view = doc.get('input', {}) if isinstance(doc, dict) else {} + if isinstance(view, dict): + for item in view.get('evidence', {}).values() if isinstance(view.get('evidence'), dict) else []: + evidence_items[digest(encoded(item))] = (evidence_items.get(digest(encoded(item)), (0, len(encoded(item))))[0] + 1, len(encoded(item))) + if isinstance(item, dict): + for field, value in item.items(): + evidence_sizes[field] += len(encoded(value)) + shared = view.get('shared_sources', {}) + for source in shared.values() if isinstance(shared, dict) else []: + if not isinstance(source, dict): + continue + meta = source.get('metadata', {}) + identity = digest(encoded(meta)) + for block in source.get('blocks', []): + for offset, line in enumerate(block.get('lines', [])): + key = (identity, block['start_line'] + offset, digest(encoded(line))) + count, size = source_lines.get(key, (0, len(encoded(line)))) + source_lines[key] = (count + 1, size) + count_keys(doc) + for at, value in leaves(doc): + strings[digest(value.encode())].append((at, len(encoded(value)))) + if isinstance(doc, dict): + for k, v in doc.items(): + items = v.items() if k == 'input' and isinstance(v, dict) else [(k, v)] + for field, item in items: + label = 'input.' + field if k == 'input' else field + b = encoded(item) + key = (req.get('prompt_version'), label, digest(b)) + block_groups[key][0] += 1 + block_groups[key][1] += len(b) + block_groups[key][2] = len(b) + dup_strings = sum(sum(n for _, n in entries[1:]) + for entries in strings.values()) + metadata_fields.update(keys) + partition = None + if req.get('prompt_version', '').startswith('investigation_project_'): + system, prefix, live = GeminiProvider._messages(req, stable_case_context=True) + partition = {'prefix_bytes': len(encoded([system, prefix])), + 'live_bytes': len(encoded(live)), + 'prefix_hash': digest(encoded([system, prefix]))} + row = {'ref': name, 'prompt': req.get('prompt_version'), + 'message_utf8_bytes': msg_bytes, + 'user_repeated_strings_ge80_bytes': dup_strings, + 'json_key_bytes': sum(keys.values()), + 'top_json_keys_by_bytes': keys.most_common(8), + 'stable_partition': partition} + per_call.append(row) + by_prompt[req.get('prompt_version')].append(row) + components = defaultdict(lambda: [0, 0, 0]) + for (prompt, label, _), (count, total, size) in block_groups.items(): + val = components[(prompt, label)] + val[0] += total + val[1] += size + val[2] += count + exact = repeated(groups) + canon = repeated(canonical) + summary = { + 'path': path.as_posix(), + 'identity': {k: manifest[k] for k in ('case_id', 'package_id', 'package_generation', 'state')}, + 'zip_bytes': path.stat().st_size, + 'raw_member_bytes': sum(v.file_size for v in infos.values()), + 'compressed_member_bytes': sum(v.compress_size for v in infos.values()), + 'members': len(infos), + 'zip_compression_methods': dict(compression_methods), + 'deflate6_estimated_payload_bytes': sum(deflate_estimate.values()), + 'deflate6_by_category': dict(deflate_estimate), + 'categories': dict(categories), + 'stored_context_components': {k:{'total_bytes':v[0], 'unique_value_bytes':v[1], + 'repeated_value_bytes':v[0]-v[1], 'occurrences':v[2]} for k,v in sorted(context_components.items(), key=lambda kv:kv[1][0], reverse=True)}, + 'largest_members': [{'path': v.filename, 'raw_bytes': v.file_size, + 'compressed_bytes': v.compress_size} for v in sorted(infos.values(), key=lambda v:v.compress_size, reverse=True)[:12]], + 'exact_duplicate_groups': len(exact), + 'exact_duplicate_raw_bytes': sum(v['raw_duplicate_bytes'] for v in exact), + 'exact_duplicate_compressed_bytes': sum(v['compressed_duplicate_bytes'] for v in exact), + 'largest_exact_duplicate_groups': exact[:8], + 'canonical_json_duplicate_raw_bytes': sum(v['raw_duplicate_bytes'] for v in canon), + 'original_tar_members_also_stored_separately': dict(archive_members), + 'request_count': len(requests), + 'research_repetition': { + 'evidence_item_total_bytes': sum(n*s for n,s in evidence_items.values()), + 'evidence_item_unique_bytes': sum(s for n,s in evidence_items.values()), + 'evidence_item_fields_bytes':dict(evidence_sizes), + 'source_line_total_bytes':sum(n*s for n,s in source_lines.values()), + 'source_line_unique_bytes':sum(s for n,s in source_lines.values()), + 'source_line_occurrences':sum(n for n,s in source_lines.values()), + 'source_line_unique_count':len(source_lines)}, + 'prompts': {p: {'calls':len(rows), 'message_utf8_bytes':sum(r['message_utf8_bytes'] for r in rows), + 'within_call_repeated_strings_ge80_bytes':sum(r['user_repeated_strings_ge80_bytes'] for r in rows)} for p, rows in by_prompt.items()}, + 'system_message_total_bytes':sum(size*count for (_,size),count in system_groups.items()), + 'system_message_repeated_bytes':sum(size*(count-1) for (_,size),count in system_groups.items()), + 'top_level_components': [{'prompt':p,'field':label,'total_canonical_bytes':v[0], + 'unique_value_bytes':v[1], 'repeated_value_bytes':v[0]-v[1], 'occurrences':v[2]} + for (p,label),v in sorted(components.items(), key=lambda kv:kv[1][0], reverse=True)], + 'json_keys_by_bytes':metadata_fields.most_common(15), + 'calls': per_call, + } + assert sum(v['raw_bytes'] for v in categories.values()) == summary['raw_member_bytes'] + assert sum(v['compressed_bytes'] for v in categories.values()) == summary['compressed_member_bytes'] + return summary + + +def main(): + parser = argparse.ArgumentParser(description=__doc__) + parser.add_argument('packages', nargs='+', type=Path) + parser.add_argument('--output', required=True, type=Path) + args = parser.parse_args() + report = {'measurement':'redundancy_audit_v1', 'units':'bytes, UTF-8, decimal MB/GB', + 'limitations': ['No paid API calls; no quality or token savings inferred.', + 'Categories are disjoint; duplicate, archive-copy and repeated-string measures overlap.', + 'Compressed duplicate sizes are an upper bound, not a compatible deletion proposal.', + 'Repeated strings are counted within user messages, minimum 80 UTF-8 bytes; references and JSON framing not deducted.', + 'Component repetition compares whole canonical top-level values within each prompt version, ignoring order of calls.', + 'Saved requests are canonical gateway input, not literal cached HTTP payload.'], + 'packages':[audit(p) for p in args.packages]} + args.output.parent.mkdir(parents=True, exist_ok=True) + args.output.write_text(json.dumps(report, ensure_ascii=False, indent=2)+'\n', encoding='utf-8') + print(json.dumps({'output':str(args.output),'packages':len(report['packages'])})) + + +if __name__ == '__main__': + main()