@ictechgy/context-guard 0.4.10 → 0.4.11

package/docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl

@@ -0,0 +1,24 @@
+{"artifacts_used": 0, "bytes_after": 9450, "bytes_before": 9450, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_01_bugfix", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1715, "output_tokens": 229}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 11.17}
+{"artifacts_used": 1, "bytes_after": 5481, "bytes_before": 9450, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_01_bugfix", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1131, "output_tokens": 210}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.13}
+{"artifacts_used": 0, "bytes_after": 9900, "bytes_before": 9900, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_02_exploration", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1830, "output_tokens": 238}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 11.34}
+{"artifacts_used": 1, "bytes_after": 5742, "bytes_before": 9900, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_02_exploration", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1207, "output_tokens": 218}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.26}
+{"artifacts_used": 0, "bytes_after": 10350, "bytes_before": 10350, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_03_code_review", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1945, "output_tokens": 247}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 11.51}
+{"artifacts_used": 1, "bytes_after": 6003, "bytes_before": 10350, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_03_code_review", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1283, "output_tokens": 227}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.39}
+{"artifacts_used": 0, "bytes_after": 10800, "bytes_before": 10800, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_04_long_log_analysis", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2060, "output_tokens": 256}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 11.68}
+{"artifacts_used": 1, "bytes_after": 6264, "bytes_before": 10800, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_04_long_log_analysis", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1359, "output_tokens": 235}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.52}
+{"artifacts_used": 0, "bytes_after": 11250, "bytes_before": 11250, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_05_migration", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2175, "output_tokens": 265}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 11.85}
+{"artifacts_used": 1, "bytes_after": 6525, "bytes_before": 11250, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_05_migration", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1435, "output_tokens": 243}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.65}
+{"artifacts_used": 0, "bytes_after": 11700, "bytes_before": 11700, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_06_docs", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2290, "output_tokens": 274}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 12.02}
+{"artifacts_used": 1, "bytes_after": 6785, "bytes_before": 11700, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_06_docs", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1511, "output_tokens": 252}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.78}
+{"artifacts_used": 0, "bytes_after": 12150, "bytes_before": 12150, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_07_refactor", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2405, "output_tokens": 283}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 12.19}
+{"artifacts_used": 1, "bytes_after": 7046, "bytes_before": 12150, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_07_refactor", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1587, "output_tokens": 260}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 11.91}
+{"artifacts_used": 0, "bytes_after": 12600, "bytes_before": 12600, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_08_performance", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2520, "output_tokens": 292}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 12.36}
+{"artifacts_used": 1, "bytes_after": 7307, "bytes_before": 12600, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_08_performance", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1663, "output_tokens": 268}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 12.04}
+{"artifacts_used": 0, "bytes_after": 13050, "bytes_before": 13050, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_09_telemetry", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2635, "output_tokens": 301}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 12.53}
+{"artifacts_used": 1, "bytes_after": 7568, "bytes_before": 13050, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_09_telemetry", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1739, "output_tokens": 276}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 12.17}
+{"artifacts_used": 0, "bytes_after": 13500, "bytes_before": 13500, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_10_cache_layout", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2750, "output_tokens": 310}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 12.7}
+{"artifacts_used": 1, "bytes_after": 7829, "bytes_before": 13500, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_10_cache_layout", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1815, "output_tokens": 285}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 12.3}
+{"artifacts_used": 0, "bytes_after": 13950, "bytes_before": 13950, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_11_tool_schema", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2865, "output_tokens": 319}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 12.87}
+{"artifacts_used": 1, "bytes_after": 8090, "bytes_before": 13950, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_11_tool_schema", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1890, "output_tokens": 293}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 12.43}
+{"artifacts_used": 0, "bytes_after": 14400, "bytes_before": 14400, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 0, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_12_artifact_receipt", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 2980, "output_tokens": 328}, "turns": 3, "variant": "baseline_full_context_fixture", "wall_time_seconds": 13.04}
+{"artifacts_used": 1, "bytes_after": 8352, "bytes_before": 14400, "corrections": 0, "cost_measured": false, "cost_usd": 0.0, "effort": "medium", "external_cost_measured": true, "external_cost_usd": 0.0, "external_tokens": 0, "external_tokens_measured": true, "hook_triggers": 1, "model": "sonnet", "notes": "synthetic fixture-only replay row; not provider measured and not public-claim eligible", "primary_tokens_measured": false, "provenance": {"capture_command_or_export_id": "docs/benchmark-fixtures/token-savings-12task.evidence.example.jsonl", "claim_scope": "local_replay_fixture_not_public_claim", "evidence_source_type": "synthetic_fixture"}, "provider_cached_tokens": 0, "provider_cached_tokens_measured": false, "schema_version": "contextguard.bench.run-evidence.v1", "success": true, "task_id": "token_savings_12_artifact_receipt", "tokens": {"cache_creation": 0, "cache_read": 0, "input_tokens": 1966, "output_tokens": 301}, "turns": 2, "variant": "fixture_only_contextguard_advisory_foundations", "wall_time_seconds": 12.56}

package/docs/benchmark-workflow-examples.md

@@ -26,6 +26,7 @@ Use them to decide what evidence a workflow has and what it does **not** prove:
 3. Treat `comparisons[].quality_gate != "pass"` as a warning to inspect failures, correction burden, and unmatched tasks before discussing savings.
 4. Keep byte-proxy, provider-cache, wall-time, and shifted-cost evidence in separate language from provider-measured token/cost claims. Provider-cache telemetry is not independent savings proof.
 5. Keep self-hosted local/model-server latency, memory, and quality metrics in the run-evidence ledger sidecar; do not fold them into hosted API token/cost savings claims unless provider-measured matched-task evidence separately supports that claim.
+6. For deterministic local replay, add `--evidence-jsonl ... --dashboard-md ...`. Synthetic/manual replay evidence regenerates CSV/report/dashboard artifacts, but the report is marked `replay_only_not_public_claim` or `unknown_mixed_csv` unless every report row has complete provider-export provenance. Public hosted savings claims must additionally have `public_claim_readiness.claim_allowed=true`, which requires matched successful tasks, provider-measured token/cost, quality non-inferiority, shifted-cost accounting, explicit confidence/failure notes, and complete provider-export provenance.
 
 ## Safe wording
 
@@ -42,3 +43,5 @@ The `.example.json` fixtures intentionally use full `context-guard-bench-report-
 The self-hosted metrics example is a JSONL run-evidence sidecar, not a full report shape. Its fields are additive ledger evidence only: `latency_ms`, `peak_memory_mb`, and normalized `quality_score` describe local/model-server behavior and leave hosted API report calculations unchanged. Use `context-guard experiments plan self-hosted-metrics-ledger --json ...` only as a dry-run ledger-preview checker for explicit metrics; it does not write the benchmark ledger.
 
 For task/variant starter fixtures rather than full report-shape examples, see [`experimental-benchmark-fixtures.md`](experimental-benchmark-fixtures.md). Those files are fixture-only and synthetic dry-run-only starters until users replace the placeholder prompts and success checks; they are not shipped OCR, visual-token, learned-compression, or output-transform benchmark results, and real claims still require provider-measured matched successful tasks plus failure-rate, correction, and shifted-cost guardrails.
+
+The token-savings 12-task starter also includes [`benchmark-fixtures/token-savings-12task.evidence.example.jsonl`](benchmark-fixtures/token-savings-12task.evidence.example.jsonl) for `context-guard-bench --evidence-jsonl` replay. That file is synthetic local replay evidence, not provider-measured savings proof; use it to validate dashboards and claim-boundary handling before collecting real provider exports.

package/docs/benchmark-workflows/context-pack-byte-proxy.example.json

@@ -1,169 +1,310 @@
 {
-  "schema": "context-guard-bench-report-v1",
   "baseline_variant": "baseline",
+  "caveat": "Proxy byte reductions are reported separately from matched-task token/cost metrics; shifted cost savings require measured primary cost and measured external cost when external tokens are present. Wall time and provider cached-token fields are diagnostic telemetry, not proof of ContextGuard-caused token or cost savings; provider-cache discounts must stay separate from token-reduction claims. Public hosted savings claims must use public_claim_readiness.claim_allowed; unsupported claims are forbidden.",
+  "claim_status": "insufficient_paired_data",
+  "comparisons": [
+    {
+      "baseline_corrections_per_successful_task": 0.0,
+      "baseline_failure_rate": 0.0,
+      "baseline_successful_task_count": 1,
+      "baseline_variant": "baseline",
+      "corrections_delta_per_successful_task": 0.0,
+      "cost_savings_pct_with_shift": null,
+      "failure_rate_delta_pp": 0.0,
+      "matched_successful_task_count": 1,
+      "missing_baseline_success_tasks": [],
+      "paired_corrections_task_count": 1,
+      "paired_cost_task_count": 0,
+      "paired_token_task_count": 0,
+      "paired_wall_time_task_count": 1,
+      "quality_gate": "pass",
+      "token_savings_pct": null,
+      "variant": "context_pack_auto",
+      "variant_corrections_per_successful_task": 0.0,
+      "variant_failure_rate": 0.0,
+      "wall_time_change_pct": -8.333333333333332,
+      "wall_time_delta_seconds_per_successful_task": -1.0
+    }
+  ],
+  "public_claim_readiness": {
+    "blocking_gate_ids": [
+      "matched_successful_tasks",
+      "provider_measured_token_cost",
+      "shifted_cost_accounting",
+      "confidence_failure_notes",
+      "provider_export_provenance"
+    ],
+    "claim_allowed": false,
+    "claim_boundary": {
+      "claim_allowed_field": "public_claim_readiness.claim_allowed",
+      "fixed_percent_savings_claim_without_matched_provider_report_forbidden": true,
+      "hosted_api_cost_savings_claim_without_claim_allowed_forbidden": true,
+      "hosted_api_token_savings_claim_without_claim_allowed_forbidden": true,
+      "id": "public_claim_readiness_authoritative_release_gate",
+      "reason": "Public hosted token/cost savings claims are forbidden unless every readiness gate passes and public_claim_readiness.claim_allowed is true.",
+      "reporting_only": true,
+      "requires_confidence_and_failure_notes": true,
+      "requires_matched_successful_tasks": true,
+      "requires_provider_export_provenance": true,
+      "requires_provider_measured_tokens_and_cost": true,
+      "requires_quality_non_inferiority": true,
+      "requires_shifted_cost_accounting": true,
+      "unsupported_claims_forbidden": true
+    },
+    "gates": [
+      {
+        "evidence": {
+          "comparison_count": 1,
+          "matched_pair_count": 0,
+          "min_matched_successful_task_count": 1.0,
+          "missing_baseline_success_task_count": 0,
+          "variants": [
+            "context_pack_auto"
+          ]
+        },
+        "id": "matched_successful_tasks",
+        "label": "Matched successful tasks",
+        "passed": false,
+        "reason": "missing_or_regressed_matched_successful_tasks",
+        "required": true,
+        "status": "fail"
+      },
+      {
+        "evidence": {
+          "matched_pair_count": 0,
+          "required_fields": [
+            "matched_pair_evidence[*].measurements.baseline.primary_tokens.measured",
+            "matched_pair_evidence[*].measurements.variant.primary_tokens.measured",
+            "matched_pair_evidence[*].measurements.baseline.primary_cost_usd.measured",
+            "matched_pair_evidence[*].measurements.variant.primary_cost_usd.measured"
+          ]
+        },
+        "id": "provider_measured_token_cost",
+        "label": "Provider-measured token and primary cost",
+        "passed": false,
+        "reason": "missing_provider_measured_primary_tokens_or_cost",
+        "required": true,
+        "status": "fail"
+      },
+      {
+        "evidence": {
+          "max_corrections_delta_per_successful_task": 0.0,
+          "max_failure_rate_delta_pp": 0.0,
+          "quality_gates": [
+            "pass"
+          ]
+        },
+        "id": "quality_non_inferiority",
+        "label": "Quality non-inferiority",
+        "passed": true,
+        "reason": "all_quality_gates_pass",
+        "required": true,
+        "status": "pass"
+      },
+      {
+        "evidence": {
+          "matched_pair_count": 0,
+          "required_fields": [
+            "matched_pair_evidence[*].claim_boundary.shifted_cost_claim_allowed",
+            "matched_pair_evidence[*].measurements.baseline.total_cost_with_shift_usd.measured",
+            "matched_pair_evidence[*].measurements.variant.total_cost_with_shift_usd.measured"
+          ]
+        },
+        "id": "shifted_cost_accounting",
+        "label": "Shifted-cost accounting",
+        "passed": false,
+        "reason": "missing_shifted_cost_claim_accounting",
+        "required": true,
+        "status": "fail"
+      },
+      {
+        "evidence": {
+          "comparison_failure_fields_present": true,
+          "explicit_note_count": 0,
+          "failed_row_count": 0,
+          "failed_rows_with_notes": 0,
+          "replay_row_count": 0
+        },
+        "id": "confidence_failure_notes",
+        "label": "Confidence and failure notes",
+        "passed": false,
+        "reason": "missing_explicit_replay_notes_or_failure_evidence",
+        "required": true,
+        "status": "unknown"
+      },
+      {
+        "evidence": {
+          "mixed_csv": false,
+          "provider_names": [],
+          "replay_row_count": 0,
+          "report_row_count": 2,
+          "same_run_complete": false,
+          "source_types": []
+        },
+        "id": "provider_export_provenance",
+        "label": "Provider-export provenance",
+        "passed": false,
+        "reason": "missing_or_mixed_provider_export_provenance",
+        "required": true,
+        "status": "unknown"
+      }
+    ],
+    "generated_from": "matched_pair_evidence_and_replay_provenance",
+    "passed_required_gate_count": 1,
+    "public_claim_eligible_observed": null,
+    "public_claim_status_observed": "csv_provenance_unknown_requires_original_evidence_or_trusted_ledger",
+    "raw_metric_claim_status_observed": "insufficient_paired_data",
+    "reason": "replay_evidence_required_for_public_claim",
+    "required_gate_count": 6,
+    "required_gate_ids": [
+      "matched_successful_tasks",
+      "provider_measured_token_cost",
+      "quality_non_inferiority",
+      "shifted_cost_accounting",
+      "confidence_failure_notes",
+      "provider_export_provenance"
+    ],
+    "schema_version": "contextguard.bench.public-claim-readiness.v1",
+    "status": "csv_provenance_unknown_requires_original_evidence_or_trusted_ledger"
+  },
   "row_count": 2,
+  "schema": "context-guard-bench-report-v1",
   "summary_by_variant": {
     "baseline": {
-      "runs": 1,
-      "successful_runs": 1,
+      "artifacts_used_per_successful_task": 0.0,
+      "artifacts_used_successful": 0,
+      "byte_reduction_ratio": 1.0,
+      "byte_savings_pct": 0.0,
+      "bytes_after_successful": 24000,
+      "bytes_before_successful": 24000,
+      "bytes_saved_per_successful_task": 0.0,
+      "bytes_saved_successful": 0,
+      "compression_strategy": "baseline",
+      "corrections_per_successful_task": 0.0,
+      "corrections_successful": 0,
+      "external_cost_successful_usd": 0.0,
+      "external_cost_unknown_successful": 1,
+      "external_tokens_measured_successful": 0,
+      "external_tokens_per_successful_task": null,
+      "external_tokens_successful": 0,
       "failed_runs": 0,
-      "total_tokens_all_runs": 0,
-      "primary_tokens_measured_runs": 0,
+      "failure_rate": 0.0,
+      "hook_triggers_successful": 0,
+      "is_baseline_strategy": true,
+      "observed_telemetry": {
+        "byte_savings": "observed",
+        "external_tokens": "unavailable",
+        "primary_cost": "unavailable",
+        "provider_cache": "unavailable",
+        "token_proxy": "inferred",
+        "tokens": "unavailable",
+        "wall_time": "observed"
+      },
       "primary_cost_all_runs_usd": 0.0,
       "primary_cost_measured_runs": 0,
-      "wall_time_seconds_all_runs": 12.0,
-      "wall_time_seconds_measured_runs": 1,
+      "primary_cost_measured_successful": 0,
+      "primary_cost_per_successful_task_usd": null,
+      "primary_cost_per_task_including_failures_usd": null,
+      "primary_cost_successful_usd": 0.0,
+      "primary_tokens_measured_runs": 0,
+      "primary_tokens_measured_successful": 0,
       "provider_cached_tokens_all_runs": 0,
       "provider_cached_tokens_measured_runs": 0,
+      "provider_cached_tokens_measured_successful": 0,
+      "provider_cached_tokens_per_successful_task": 0.0,
+      "provider_cached_tokens_per_task_including_failures": 0.0,
+      "provider_cached_tokens_successful": 0,
+      "runs": 1,
+      "successful_runs": 1,
+      "successful_task_count": 1,
+      "task_count": 1,
+      "token_proxy_saved_per_successful_task": 0.0,
+      "token_proxy_saved_successful": 0,
+      "tokens_per_successful_task": null,
+      "tokens_per_task_including_failures": null,
       "total_cost_with_shift_all_runs_usd": 0.0,
       "total_cost_with_shift_measured_runs": 0,
+      "total_cost_with_shift_measured_successful": 0,
+      "total_cost_with_shift_per_successful_task_usd": null,
+      "total_cost_with_shift_per_task_including_failures_usd": null,
+      "total_cost_with_shift_successful_usd": 0.0,
+      "total_tokens_all_runs": 0,
       "total_tokens_successful": 0,
-      "primary_tokens_measured_successful": 0,
-      "primary_cost_successful_usd": 0.0,
-      "primary_cost_measured_successful": 0,
-      "wall_time_seconds_successful": 12.0,
+      "turns_successful": 0,
+      "wall_time_seconds_all_runs": 12.0,
+      "wall_time_seconds_measured_runs": 1,
       "wall_time_seconds_measured_successful": 1,
-      "provider_cached_tokens_successful": 0,
-      "provider_cached_tokens_measured_successful": 0,
+      "wall_time_seconds_per_successful_task": 12.0,
+      "wall_time_seconds_per_task_including_failures": 12.0,
+      "wall_time_seconds_successful": 12.0
+    },
+    "context_pack_auto": {
+      "artifacts_used_per_successful_task": 0.0,
+      "artifacts_used_successful": 0,
+      "byte_reduction_ratio": 0.25,
+      "byte_savings_pct": 75.0,
+      "bytes_after_successful": 6000,
+      "bytes_before_successful": 24000,
+      "bytes_saved_per_successful_task": 18000.0,
+      "bytes_saved_successful": 18000,
+      "compression_strategy": "context_pack_auto",
+      "corrections_per_successful_task": 0.0,
+      "corrections_successful": 0,
       "external_cost_successful_usd": 0.0,
       "external_cost_unknown_successful": 1,
-      "total_cost_with_shift_successful_usd": 0.0,
-      "total_cost_with_shift_measured_successful": 0,
-      "external_tokens_successful": 0,
       "external_tokens_measured_successful": 0,
-      "artifacts_used_successful": 0,
-      "corrections_successful": 0,
-      "bytes_before_successful": 24000,
-      "bytes_after_successful": 24000,
-      "turns_successful": 0,
-      "hook_triggers_successful": 0,
-      "failure_rate": 0.0,
-      "task_count": 1,
-      "successful_task_count": 1,
-      "tokens_per_task_including_failures": null,
-      "wall_time_seconds_per_task_including_failures": 12.0,
-      "provider_cached_tokens_per_task_including_failures": 0.0,
-      "primary_cost_per_task_including_failures_usd": null,
-      "total_cost_with_shift_per_task_including_failures_usd": null,
-      "tokens_per_successful_task": null,
-      "wall_time_seconds_per_successful_task": 12.0,
-      "provider_cached_tokens_per_successful_task": 0.0,
-      "primary_cost_per_successful_task_usd": null,
-      "total_cost_with_shift_per_successful_task_usd": null,
       "external_tokens_per_successful_task": null,
-      "artifacts_used_per_successful_task": 0.0,
-      "corrections_per_successful_task": 0.0,
-      "byte_reduction_ratio": 1.0,
-      "compression_strategy": "baseline",
-      "is_baseline_strategy": true,
-      "bytes_saved_successful": 0,
-      "bytes_saved_per_successful_task": 0.0,
-      "byte_savings_pct": 0.0,
-      "token_proxy_saved_successful": 0,
-      "token_proxy_saved_per_successful_task": 0.0,
+      "external_tokens_successful": 0,
+      "failed_runs": 0,
+      "failure_rate": 0.0,
+      "hook_triggers_successful": 0,
+      "is_baseline_strategy": false,
       "observed_telemetry": {
-        "tokens": "unavailable",
-        "primary_cost": "unavailable",
-        "external_tokens": "unavailable",
         "byte_savings": "observed",
+        "external_tokens": "unavailable",
+        "primary_cost": "unavailable",
+        "provider_cache": "unavailable",
         "token_proxy": "inferred",
-        "wall_time": "observed",
-        "provider_cache": "unavailable"
-      }
-    },
-    "context_pack_auto": {
-      "runs": 1,
-      "successful_runs": 1,
-      "failed_runs": 0,
-      "total_tokens_all_runs": 0,
-      "primary_tokens_measured_runs": 0,
+        "tokens": "unavailable",
+        "wall_time": "observed"
+      },
       "primary_cost_all_runs_usd": 0.0,
       "primary_cost_measured_runs": 0,
-      "wall_time_seconds_all_runs": 11.0,
-      "wall_time_seconds_measured_runs": 1,
+      "primary_cost_measured_successful": 0,
+      "primary_cost_per_successful_task_usd": null,
+      "primary_cost_per_task_including_failures_usd": null,
+      "primary_cost_successful_usd": 0.0,
+      "primary_tokens_measured_runs": 0,
+      "primary_tokens_measured_successful": 0,
       "provider_cached_tokens_all_runs": 0,
       "provider_cached_tokens_measured_runs": 0,
-      "total_cost_with_shift_all_runs_usd": 0.0,
-      "total_cost_with_shift_measured_runs": 0,
-      "total_tokens_successful": 0,
-      "primary_tokens_measured_successful": 0,
-      "primary_cost_successful_usd": 0.0,
-      "primary_cost_measured_successful": 0,
-      "wall_time_seconds_successful": 11.0,
-      "wall_time_seconds_measured_successful": 1,
-      "provider_cached_tokens_successful": 0,
       "provider_cached_tokens_measured_successful": 0,
-      "external_cost_successful_usd": 0.0,
-      "external_cost_unknown_successful": 1,
-      "total_cost_with_shift_successful_usd": 0.0,
-      "total_cost_with_shift_measured_successful": 0,
-      "external_tokens_successful": 0,
-      "external_tokens_measured_successful": 0,
-      "artifacts_used_successful": 0,
-      "corrections_successful": 0,
-      "bytes_before_successful": 24000,
-      "bytes_after_successful": 6000,
-      "turns_successful": 0,
-      "hook_triggers_successful": 0,
-      "failure_rate": 0.0,
-      "task_count": 1,
+      "provider_cached_tokens_per_successful_task": 0.0,
+      "provider_cached_tokens_per_task_including_failures": 0.0,
+      "provider_cached_tokens_successful": 0,
+      "runs": 1,
+      "successful_runs": 1,
       "successful_task_count": 1,
+      "task_count": 1,
+      "token_proxy_saved_per_successful_task": 4500.0,
+      "token_proxy_saved_successful": 4500,
+      "tokens_per_successful_task": null,
       "tokens_per_task_including_failures": null,
-      "wall_time_seconds_per_task_including_failures": 11.0,
-      "provider_cached_tokens_per_task_including_failures": 0.0,
-      "primary_cost_per_task_including_failures_usd": null,
+      "total_cost_with_shift_all_runs_usd": 0.0,
+      "total_cost_with_shift_measured_runs": 0,
+      "total_cost_with_shift_measured_successful": 0,
+      "total_cost_with_shift_per_successful_task_usd": null,
       "total_cost_with_shift_per_task_including_failures_usd": null,
-      "tokens_per_successful_task": null,
+      "total_cost_with_shift_successful_usd": 0.0,
+      "total_tokens_all_runs": 0,
+      "total_tokens_successful": 0,
+      "turns_successful": 0,
+      "wall_time_seconds_all_runs": 11.0,
+      "wall_time_seconds_measured_runs": 1,
+      "wall_time_seconds_measured_successful": 1,
       "wall_time_seconds_per_successful_task": 11.0,
-      "provider_cached_tokens_per_successful_task": 0.0,
-      "primary_cost_per_successful_task_usd": null,
-      "total_cost_with_shift_per_successful_task_usd": null,
-      "external_tokens_per_successful_task": null,
-      "artifacts_used_per_successful_task": 0.0,
-      "corrections_per_successful_task": 0.0,
-      "byte_reduction_ratio": 0.25,
-      "compression_strategy": "context_pack_auto",
-      "is_baseline_strategy": false,
-      "bytes_saved_successful": 18000,
-      "bytes_saved_per_successful_task": 18000.0,
-      "byte_savings_pct": 75.0,
-      "token_proxy_saved_successful": 4500,
-      "token_proxy_saved_per_successful_task": 4500.0,
-      "observed_telemetry": {
-        "tokens": "unavailable",
-        "primary_cost": "unavailable",
-        "external_tokens": "unavailable",
-        "byte_savings": "observed",
-        "token_proxy": "inferred",
-        "wall_time": "observed",
-        "provider_cache": "unavailable"
-      }
-    }
-  },
-  "comparisons": [
-    {
-      "variant": "context_pack_auto",
-      "baseline_variant": "baseline",
-      "quality_gate": "pass",
-      "baseline_failure_rate": 0.0,
-      "variant_failure_rate": 0.0,
-      "failure_rate_delta_pp": 0.0,
-      "matched_successful_task_count": 1,
-      "baseline_successful_task_count": 1,
-      "missing_baseline_success_tasks": [],
-      "baseline_corrections_per_successful_task": 0.0,
-      "variant_corrections_per_successful_task": 0.0,
-      "paired_corrections_task_count": 1,
-      "corrections_delta_per_successful_task": 0.0,
-      "token_savings_pct": null,
-      "paired_token_task_count": 0,
-      "wall_time_delta_seconds_per_successful_task": -1.0,
-      "wall_time_change_pct": -8.333333333333332,
-      "paired_wall_time_task_count": 1,
-      "cost_savings_pct_with_shift": null,
-      "paired_cost_task_count": 0
+      "wall_time_seconds_per_task_including_failures": 11.0,
+      "wall_time_seconds_successful": 11.0
     }
-  ],
-  "claim_status": "insufficient_paired_data",
-  "caveat": "Proxy byte reductions are reported separately from matched-task token/cost metrics; shifted cost savings require measured primary cost and measured external cost when external tokens are present. Wall time and provider cached-token fields are diagnostic telemetry, not proof of ContextGuard-caused token or cost savings; provider-cache discounts must stay separate from token-reduction claims."
+  }
 }