Use compact MCP input advertisements by default while preserving explicit full, canonical validation, output contracts and complete Evidence. Require an explicit selected catalog for runtime identity and honor both profiles in CLI status. Real ripgrep/Zellij SDK tasks, independent ELF oracle, actual client trials, profile parity workflows and CI are recorded in experiments/analysis-efficiency/mcp-input-catalog.md. SDK token estimates improve; actual Codex token savings and general latency/memory gains are not established. Refs #5861 BREAKING CHANGE: MCP input advertisements default to compact. Set REA_MCP_INPUT_SCHEMA_PROFILE=full for complete advertised guidance and nested constraints.
2795 lines
107 KiB
JSON
2795 lines
107 KiB
JSON
{
|
|
"tokenizer": "tiktoken 0.12.0",
|
|
"encoding": "cl100k_base",
|
|
"estimate_scope": "One complete name/description/input-schema catalog, every RPC argument and text reply; raw output-schema transport counted separately. Model usage is separate and is not inferred from estimates.",
|
|
"records": [
|
|
{
|
|
"case": "sdk-before-ripgrep-1",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 235.4114069999996,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2592.4309000000003,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.743873000000349,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.898541000000478,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 28.123798999999963,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4",
|
|
"parent_semantic_sha256": "3561d500cece1ac5d49a02f1594148a9435d60f8f60acbadb9fae392faddcdfa",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 290,
|
|
"text_replies": 3643,
|
|
"whole_task": 204358,
|
|
"raw_catalog_including_output_schemas": 903377
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.68,
|
|
"cpu_seconds": 7.463226,
|
|
"kernel_family_peak_bytes_including_page_cache": 844361728,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "f8e041e2e30ea08e41bbf430b332a258b383f4d0f07056ef8df4d8b98efda148",
|
|
"receipt_sha256": {
|
|
"report.json": "35af0d97fdc737b3cf0b4eef30dd4c09518520f131cd76a6b133e8ac3fbb448d",
|
|
"catalog.json": "3ce5e55f4a50ef8aabdddf4870bc4ac26714ddebdf3e94750ca2292758abb334",
|
|
"transcript.json": "c7f52603df441e06d0faadc5392981c0db9c57f67af8e0f2a2aac77f994d3c7e"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-before-ripgrep-2",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 257.72447999999986,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2322.8260260000006,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 9.450252999999975,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 6.5934720000004745,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 26.677778000000217,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4",
|
|
"parent_semantic_sha256": "3561d500cece1ac5d49a02f1594148a9435d60f8f60acbadb9fae392faddcdfa",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 290,
|
|
"text_replies": 3643,
|
|
"whole_task": 204358,
|
|
"raw_catalog_including_output_schemas": 903377
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.274,
|
|
"cpu_seconds": 7.088849,
|
|
"kernel_family_peak_bytes_including_page_cache": 843403264,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "d33806d029b0f67c526597c9e197afacdd56ee90a7d5377e60c02e234d3f9eca",
|
|
"receipt_sha256": {
|
|
"report.json": "42db03c16208b5c20589b7f9e4539f1882085ec3242ae3e7027e0cb2a75d1a9d",
|
|
"catalog.json": "3ce5e55f4a50ef8aabdddf4870bc4ac26714ddebdf3e94750ca2292758abb334",
|
|
"transcript.json": "4edb4f8c6e61b831c283c185ba08852f3d873e32a33a4ca083f7c90b2c52c207"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-before-ripgrep-3",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 243.4695329999995,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2340.3538100000005,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.340052999999898,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.634870999999293,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 26.305707999999868,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4",
|
|
"parent_semantic_sha256": "3561d500cece1ac5d49a02f1594148a9435d60f8f60acbadb9fae392faddcdfa",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 290,
|
|
"text_replies": 3643,
|
|
"whole_task": 204358,
|
|
"raw_catalog_including_output_schemas": 903377
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.379,
|
|
"cpu_seconds": 7.158899,
|
|
"kernel_family_peak_bytes_including_page_cache": 826548224,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "f34abb42c2858d492ccb25f4bec037844057dcc5f603dd42106e55a4da4d9630",
|
|
"receipt_sha256": {
|
|
"report.json": "e5498fb40e40de7f978e34f6ebfe10ed5927023d80ad78231e4cb314bdcf32c2",
|
|
"catalog.json": "3ce5e55f4a50ef8aabdddf4870bc4ac26714ddebdf3e94750ca2292758abb334",
|
|
"transcript.json": "80fa2110b462a7dd01cd09141ecb11aa44c700f202839a404e28fdc5d7a3dd32"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-before-zellij-1",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 375.22006000000056,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2189.4753340000007,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.186962999999196,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.954241999999795,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 28.99703899999986,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 204278,
|
|
"raw_catalog_including_output_schemas": 903377
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.373,
|
|
"cpu_seconds": 7.162395,
|
|
"kernel_family_peak_bytes_including_page_cache": 900964352,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "363b01b8cf181841670f2e45312d9151c597aefc0e18bb15ee6c15552cb8c4bb",
|
|
"receipt_sha256": {
|
|
"report.json": "afe207da47d41c28c5df489f777d7d9562f5ecf7487ab5467960be526facae76",
|
|
"catalog.json": "3ce5e55f4a50ef8aabdddf4870bc4ac26714ddebdf3e94750ca2292758abb334",
|
|
"transcript.json": "ba1f6eb81dc23463a2adbfced54955432fea3d7a66763067e4ca8372d5332bfc"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-before-zellij-2",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 374.081913,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2330.8751839999995,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 9.464193000000705,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 5.04649100000006,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 32.14282000000003,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 204278,
|
|
"raw_catalog_including_output_schemas": 903377
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.476,
|
|
"cpu_seconds": 7.283478,
|
|
"kernel_family_peak_bytes_including_page_cache": 879722496,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "f1c2de870ea29b529dee910b6628945b85947563b58991708253c9fe3dfe4dac",
|
|
"receipt_sha256": {
|
|
"report.json": "b1ca87533e6542feebbb4b8307d3644b60d9ad16d8d64c12c433eeb75256e5e0",
|
|
"catalog.json": "3ce5e55f4a50ef8aabdddf4870bc4ac26714ddebdf3e94750ca2292758abb334",
|
|
"transcript.json": "d9310a11e615a8f5e14e21c78b7760dd31a3483ee860690805693950302eaf2a"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-before-zellij-3",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 351.87811300000067,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2199.3235750000003,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.399842999999237,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.889250999999604,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 28.207508000000416,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 204278,
|
|
"raw_catalog_including_output_schemas": 903377
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.172,
|
|
"cpu_seconds": 6.994004,
|
|
"kernel_family_peak_bytes_including_page_cache": 874958848,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "ac726fc9c85859ca05c135b0db2a3c01e4e1e727377d5ac45dddb217d4ee9a71",
|
|
"receipt_sha256": {
|
|
"report.json": "210bc416c53ace328a1f20cb31ed22f4033e898dfdbce5162ec08804287adcac",
|
|
"catalog.json": "3ce5e55f4a50ef8aabdddf4870bc4ac26714ddebdf3e94750ca2292758abb334",
|
|
"transcript.json": "a539746139a73d1ec9c2788f0727b10f184834ee3b57e8e9728bf543e88227cb"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-after-ripgrep-1",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 228.0756139999994,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2289.444885,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.025203000000147,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.815392000000429,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 26.27393800000027,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4",
|
|
"parent_semantic_sha256": "3561d500cece1ac5d49a02f1594148a9435d60f8f60acbadb9fae392faddcdfa",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3643,
|
|
"whole_task": 51801,
|
|
"raw_catalog_including_output_schemas": 750623
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.071,
|
|
"cpu_seconds": 6.828902,
|
|
"kernel_family_peak_bytes_including_page_cache": 855105536,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "5bf6f4d1e02769af4dd08880f7a0280eceb8c802431a7527bd85a8b0082675b0",
|
|
"receipt_sha256": {
|
|
"report.json": "002692e86fdc444ecc47ca813e34205b25e9b90a4fe61cc9259a213743a1b338",
|
|
"catalog.json": "002de51700f35ca1e5a5f4fcb5b44892d669810d43c93112cedfb1da487d2764",
|
|
"transcript.json": "ea9e833b197aa31a5828180b1843a58698654bd27ae030eb35f3837c3802d801"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-after-ripgrep-2",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 226.54507000000012,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2451.053623,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.024482999999236,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.942861999999877,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 25.94279700000061,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4",
|
|
"parent_semantic_sha256": "3561d500cece1ac5d49a02f1594148a9435d60f8f60acbadb9fae392faddcdfa",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3643,
|
|
"whole_task": 51801,
|
|
"raw_catalog_including_output_schemas": 750623
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.274,
|
|
"cpu_seconds": 7.056284,
|
|
"kernel_family_peak_bytes_including_page_cache": 847163392,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "3d2d04a472786aae603b38edefb3b951d872fcd5faa24b954d964171d19b316d",
|
|
"receipt_sha256": {
|
|
"report.json": "6fa4253362fd809916a5f4c0313a76dc6440dc597b81ba2d449b177e8f12d4d5",
|
|
"catalog.json": "002de51700f35ca1e5a5f4fcb5b44892d669810d43c93112cedfb1da487d2764",
|
|
"transcript.json": "9a9df6330b19fc69055f12276ebc194779fd841648e0424a0c69f495afd1c810"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-after-ripgrep-3",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 233.24478,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2287.8342869999997,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 7.477762000000439,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.396171999999751,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 24.576046999999562,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4",
|
|
"parent_semantic_sha256": "3561d500cece1ac5d49a02f1594148a9435d60f8f60acbadb9fae392faddcdfa",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3643,
|
|
"whole_task": 51801,
|
|
"raw_catalog_including_output_schemas": 750623
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.274,
|
|
"cpu_seconds": 7.035747,
|
|
"kernel_family_peak_bytes_including_page_cache": 856150016,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "10fdd1496c3c3883872a402424e5f934ae8788d84241442b5d16963097e67e4a",
|
|
"receipt_sha256": {
|
|
"report.json": "cfb0c86691beaa081d971c3f003f0f58a4a741d38565ba03c9be75bdf260f8c1",
|
|
"catalog.json": "002de51700f35ca1e5a5f4fcb5b44892d669810d43c93112cedfb1da487d2764",
|
|
"transcript.json": "8c2aea98f93b5ef5a5701fa7d6b046af651e8613263f031588d605dc150e183b"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-after-zellij-1",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 376.51606899999933,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2252.891488,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 10.003193000000465,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.7563219999992725,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 29.48786899999959,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 51721,
|
|
"raw_catalog_including_output_schemas": 750623
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.374,
|
|
"cpu_seconds": 7.190767,
|
|
"kernel_family_peak_bytes_including_page_cache": 867143680,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "d2834ea461c6cdebd30d59cbb56c7993fd4d646f16b2beea939f25b284d8dfd5",
|
|
"receipt_sha256": {
|
|
"report.json": "7d3442d2544881d0a289bb5cd1e4d76a0c08d15d7949b27509de057814b7deb7",
|
|
"catalog.json": "002de51700f35ca1e5a5f4fcb5b44892d669810d43c93112cedfb1da487d2764",
|
|
"transcript.json": "3275e82eca9afcd6b398ed6f2eb774567283a2bc749288481f42fe127125e561"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-after-zellij-2",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 347.66348599999947,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2296.0857909999995,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 9.664283000000069,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 5.7898119999999835,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 32.0967499999997,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 51721,
|
|
"raw_catalog_including_output_schemas": 750623
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.375,
|
|
"cpu_seconds": 7.131237,
|
|
"kernel_family_peak_bytes_including_page_cache": 867885056,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "df604284d7d8a882abff72a018f6e3d76ebcaea23bbbc7cb53f42d1ae35b6c14",
|
|
"receipt_sha256": {
|
|
"report.json": "86f0fa5aba3fb1780cb17065e4fa5c9c5bccf15ada14d05096e2483f2fdc5fc6",
|
|
"catalog.json": "002de51700f35ca1e5a5f4fcb5b44892d669810d43c93112cedfb1da487d2764",
|
|
"transcript.json": "07b789e228e269b8b78eae1c28b0f9be4cfc72c98c9085c1bdfcdce0bce326a9"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "sdk-after-zellij-3",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 362.0739059999996,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2202.77409,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.819072000000233,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 5.043001000000004,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 30.75821899999937,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 51721,
|
|
"raw_catalog_including_output_schemas": 750623
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.073,
|
|
"cpu_seconds": 6.912569,
|
|
"kernel_family_peak_bytes_including_page_cache": 865886208,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "7d47c2749d88f5450699ef4b975d5919700951f2e4e674340d45f1caa37c4add",
|
|
"receipt_sha256": {
|
|
"report.json": "56e10f8f384370dd064ae4980b07b216f53cd3bdae09909ce78eb4d40c969d40",
|
|
"catalog.json": "002de51700f35ca1e5a5f4fcb5b44892d669810d43c93112cedfb1da487d2764",
|
|
"transcript.json": "2fcc6a9a9b718df82514eb461f03662453425d1a7a57cd2bb58fcc55c5fde6e5"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "model-full-direct",
|
|
"kind": "model",
|
|
"client": "codex-cli 0.161.0",
|
|
"requested_model": "gpt-6.1-sol",
|
|
"reasoning": "medium",
|
|
"model_identity_scope": "requested alias; resolved server-side model identity is not inferred",
|
|
"actual_model_usage": [
|
|
{
|
|
"input_tokens": 169419,
|
|
"cached_input_tokens": 141056,
|
|
"cache_write_input_tokens": 0,
|
|
"output_tokens": 443,
|
|
"reasoning_output_tokens": 14
|
|
}
|
|
],
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"calls": [
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_rust_binary",
|
|
"arguments": {
|
|
"path": "/tmp/rea-perf-rust-20261021/ripgrep",
|
|
"view": {
|
|
"collection": "packages",
|
|
"names": ["serde"],
|
|
"fields": ["name", "version", "kind"],
|
|
"limit": 64
|
|
}
|
|
},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 9014
|
|
},
|
|
{
|
|
"server": "rea",
|
|
"tool": "close_binary",
|
|
"arguments": {},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 170
|
|
}
|
|
],
|
|
"factual_correctness": "requires independent oracle and answer review",
|
|
"wall_seconds": 33.854,
|
|
"cpu_seconds": 12.595863,
|
|
"kernel_family_peak_bytes_including_page_cache": 755277824,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "80031ddca4a1dea8e6f5b79ef7b6ef93b7d4b73a00ff6c944b8ac4fff7bcf832",
|
|
"receipt_sha256": {
|
|
"summary.json": "422f5b19e9e1535a2bfde8b0cccef82c2094301b656c54995dbe7b8423e930ea",
|
|
"answer.txt": "b8fda287b2f86451e7cbfdb6d05823a444296addc6df3c9f7d371efe527197c7",
|
|
"events.jsonl": "5847ca5b3246a3d26676806c1dfeb725bc3609f22a3a631ee6197a5408316ebf",
|
|
"trial-settings.json": "f7233b8ab057bec5f795f3213d88cc95d47899730ca6b27c3a1188966bc9e4ce",
|
|
"context-receipt.json": "6784b47a6b50e34e561dfab240a871fcb797cfdba413e44f66cafbcf7474ead0"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "model-compact-direct",
|
|
"kind": "model",
|
|
"client": "codex-cli 0.161.0",
|
|
"requested_model": "gpt-6.1-sol",
|
|
"reasoning": "medium",
|
|
"model_identity_scope": "requested alias; resolved server-side model identity is not inferred",
|
|
"actual_model_usage": [
|
|
{
|
|
"input_tokens": 173274,
|
|
"cached_input_tokens": 123136,
|
|
"cache_write_input_tokens": 0,
|
|
"output_tokens": 420,
|
|
"reasoning_output_tokens": 19
|
|
}
|
|
],
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"calls": [
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_rust_binary",
|
|
"arguments": {
|
|
"path": "/tmp/rea-perf-rust-20261021/ripgrep",
|
|
"view": {
|
|
"collection": "packages",
|
|
"names": ["serde"],
|
|
"fields": ["name", "version", "kind"],
|
|
"limit": 64
|
|
}
|
|
},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 9014
|
|
},
|
|
{
|
|
"server": "rea",
|
|
"tool": "close_binary",
|
|
"arguments": {},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 170
|
|
}
|
|
],
|
|
"factual_correctness": "requires independent oracle and answer review",
|
|
"wall_seconds": 31.448,
|
|
"cpu_seconds": 8.272158,
|
|
"kernel_family_peak_bytes_including_page_cache": 735793152,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "1720cc27e1cbad8d9805ab4bab44094ce7047fe9c510a9f8fbf44bdb215a4fc7",
|
|
"receipt_sha256": {
|
|
"summary.json": "dc57b6198328f2afff76f729743d3afa440923d94fa73dafbb590e675bc04900",
|
|
"answer.txt": "b04f0adeb03ae2d263c1552a2e5b242d1e2f65c3476f1505b2e4b116fdd585bd",
|
|
"events.jsonl": "51f2f6c5fa22fc88625ceff5e401a6e6029a24e876bde8e806bbce2e833bee1f",
|
|
"trial-settings.json": "5583c1e20270630d63c716ea3f3aa326f12458a3b968c9c1d51ccf5fc6cd4245",
|
|
"context-receipt.json": "9358f5d4e05d0c5a347184398c79c57cb8cb1e93e76aea73f71b6981a4258753"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "model-full-broad",
|
|
"kind": "model",
|
|
"client": "codex-cli 0.161.0",
|
|
"requested_model": "gpt-6.1-sol",
|
|
"reasoning": "medium",
|
|
"model_identity_scope": "requested alias; resolved server-side model identity is not inferred",
|
|
"actual_model_usage": [
|
|
{
|
|
"input_tokens": 126522,
|
|
"cached_input_tokens": 101376,
|
|
"cache_write_input_tokens": 0,
|
|
"output_tokens": 385,
|
|
"reasoning_output_tokens": 0
|
|
}
|
|
],
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"calls": [
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_rust_binary",
|
|
"arguments": {
|
|
"path": "/tmp/rea-perf-rust-20261021/zellij",
|
|
"detail": "summary",
|
|
"view": {
|
|
"collection": "packages",
|
|
"names": ["serde", "zellij"]
|
|
}
|
|
},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 8990
|
|
}
|
|
],
|
|
"factual_correctness": "requires independent oracle and answer review",
|
|
"wall_seconds": 28.434,
|
|
"cpu_seconds": 8.118109,
|
|
"kernel_family_peak_bytes_including_page_cache": 756137984,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "398cfbb69cfa5f57c0bc1e937c20b4e56ca452c6469d17b42010efec5e8fdf90",
|
|
"receipt_sha256": {
|
|
"summary.json": "f9cf799e5f70337df95d4846c414dc8c8525e7a46fc70dc83574863fdfe860a2",
|
|
"answer.txt": "cf9bfb06e92bb6cc1b3eba465e26ea451f96789756e6c8ba99eb5af856b26ff1",
|
|
"events.jsonl": "c78ac4441db3b858f0d5c5363e11f94680adf465cb7254f52767edb1cf5ae6fd",
|
|
"trial-settings.json": "849b7e2ad0f1e44fa809d5403af966ba5c4d640b607c8e731491aa48fc814911",
|
|
"context-receipt.json": "7e3aa7f6b11223689af066f3eec2e6693c868e89dadf5ccf5582feea12056893"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "model-compact-broad",
|
|
"kind": "model",
|
|
"client": "codex-cli 0.161.0",
|
|
"requested_model": "gpt-6.1-sol",
|
|
"reasoning": "medium",
|
|
"model_identity_scope": "requested alias; resolved server-side model identity is not inferred",
|
|
"actual_model_usage": [
|
|
{
|
|
"input_tokens": 166082,
|
|
"cached_input_tokens": 125568,
|
|
"cache_write_input_tokens": 0,
|
|
"output_tokens": 511,
|
|
"reasoning_output_tokens": 0
|
|
}
|
|
],
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"calls": [
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_rust_binary",
|
|
"arguments": {
|
|
"path": "/tmp/rea-perf-rust-20261021/zellij",
|
|
"detail": "summary"
|
|
},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 8228
|
|
},
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_analysis_view",
|
|
"arguments": {
|
|
"source": {
|
|
"kind": "retained-evidence",
|
|
"evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb"
|
|
},
|
|
"view": {
|
|
"kind": "rust",
|
|
"collection": "packages",
|
|
"names": ["zellij", "serde"],
|
|
"fields": ["name", "version", "root"],
|
|
"offset": 0,
|
|
"limit": 20
|
|
}
|
|
},
|
|
"status": "completed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 9010
|
|
}
|
|
],
|
|
"factual_correctness": "requires independent oracle and answer review",
|
|
"wall_seconds": 34.989,
|
|
"cpu_seconds": 8.450645,
|
|
"kernel_family_peak_bytes_including_page_cache": 861052928,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "59740f64c630b144465175ac64ad1aa5c9c6dd8224debe02513f8552a25b79ec",
|
|
"receipt_sha256": {
|
|
"summary.json": "23cbc3cd2141542e3f2783152c82c1b041897428b34d95facba41a27d13cac7d",
|
|
"answer.txt": "78049c2d921c631c7626a4d30d571b74f13f8fa1426b66915222d1623d754698",
|
|
"events.jsonl": "2f644cdefdb0948cb6b5dc3395aa92a7652625549bbb87794261d21473aefd73",
|
|
"trial-settings.json": "cd2302414d40d17f180d97861165390a61c811fe3296d450e84334faf111b911",
|
|
"context-receipt.json": "610f11131f19ba30bd4024d79b7e7b8b29970d83a962d23e62040daa11181932"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "model-full-negative",
|
|
"kind": "model",
|
|
"client": "codex-cli 0.161.0",
|
|
"requested_model": "gpt-6.1-sol",
|
|
"reasoning": "medium",
|
|
"model_identity_scope": "requested alias; resolved server-side model identity is not inferred",
|
|
"actual_model_usage": [
|
|
{
|
|
"input_tokens": 167283,
|
|
"cached_input_tokens": 143488,
|
|
"cache_write_input_tokens": 0,
|
|
"output_tokens": 375,
|
|
"reasoning_output_tokens": 0
|
|
}
|
|
],
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"calls": [
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_rust_binary",
|
|
"arguments": {
|
|
"path": "/tmp/rea-perf-rust-20261021/ripgrep",
|
|
"view": {
|
|
"collection": "packages",
|
|
"offset": -1
|
|
}
|
|
},
|
|
"status": "failed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 838
|
|
}
|
|
],
|
|
"factual_correctness": "requires independent oracle and answer review",
|
|
"wall_seconds": 32.983,
|
|
"cpu_seconds": 7.902407,
|
|
"kernel_family_peak_bytes_including_page_cache": 859930624,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "de350a97d5414e7a4b7d3fed85eda2fa98fbf1bbe03a81728faafd409f3aadfc",
|
|
"receipt_sha256": {
|
|
"summary.json": "a218f6fa36a4ba994dc1f3e2ae4f78d4a47717ea7592e834ff12618f0eabd0e1",
|
|
"answer.txt": "992cefb6b880aa38354b28ee796ba0745406b80fc12f67fe6a644e753ae52cf2",
|
|
"events.jsonl": "30f220843c1f0b62d872e000834436c5dd14de34bd3798ca6c17894c40043820",
|
|
"trial-settings.json": "25eab30f547ae9e111f7fce181982c87dd971ee64e01bcbe527a8284af0afb94",
|
|
"context-receipt.json": "3dde1df61d07132e29671cf39beaec14973f09248cbfa0cc1cf3e5b458c5567b"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "model-compact-negative",
|
|
"kind": "model",
|
|
"client": "codex-cli 0.161.0",
|
|
"requested_model": "gpt-6.1-sol",
|
|
"reasoning": "medium",
|
|
"model_identity_scope": "requested alias; resolved server-side model identity is not inferred",
|
|
"actual_model_usage": [
|
|
{
|
|
"input_tokens": 140530,
|
|
"cached_input_tokens": 113152,
|
|
"cache_write_input_tokens": 0,
|
|
"output_tokens": 342,
|
|
"reasoning_output_tokens": 0
|
|
}
|
|
],
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"calls": [
|
|
{
|
|
"server": "rea",
|
|
"tool": "inspect_rust_binary",
|
|
"arguments": {
|
|
"path": "/tmp/rea-perf-rust-20261021/ripgrep",
|
|
"view": {
|
|
"collection": "packages",
|
|
"offset": -1
|
|
}
|
|
},
|
|
"status": "failed",
|
|
"error": null,
|
|
"codex_event_result_json_utf8_bytes": 838
|
|
}
|
|
],
|
|
"factual_correctness": "requires independent oracle and answer review",
|
|
"wall_seconds": 29.641,
|
|
"cpu_seconds": 7.608495,
|
|
"kernel_family_peak_bytes_including_page_cache": 735641600,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "da7b25fa17b7df1fe27ffc08df4ae764705009091288e42324467db6ee119579",
|
|
"receipt_sha256": {
|
|
"summary.json": "becd51bac0868c0e49ce966443c10d65860d8f87563d76127cb1231482ae3970",
|
|
"answer.txt": "aa8d38d6bbfb2aee64aa5d86deeab364e6033ca5f8077ce4823543f74bad08e8",
|
|
"events.jsonl": "cc38da0b4abe2d60ff2e306b4040beef0dea5aec5e9b3ef629a02054d53536ac",
|
|
"trial-settings.json": "e0668f0a63959a438973a4a6cc8296981dde7a239798d96f543813d7cffc4f90",
|
|
"context-receipt.json": "6355147e996b77c9affa3041785b372167de85f9da371e5fe80d4328787e727b"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
}
|
|
],
|
|
"baseline_revision": "705058f3e2df82503f1c601fc464aea7cbb626b8",
|
|
"candidate_scope": "Same base with the source digests below; only the default input presentation selection changes production behavior.",
|
|
"sources_sha256": {
|
|
"src/config/mcpInputSchemaProfile.ts": "8c07e0a47f91f4dac56233ab9a1ef5ed85e3890f7080f1a45af8002e04a0957a",
|
|
"experiments/analysis-efficiency/mcp-input-catalog.mjs": "159c787384c45ad9987c37d5d0beb49568ce67d010328d9d1e97f34d1ef3cbd6",
|
|
"experiments/analysis-efficiency/mcp-input-catalog-oracle.py": "8f738852edf73f49a722de897ecc41fdd5f11ba9478fd55cca977dfd0f8038ed",
|
|
"experiments/analysis-efficiency/mcp-input-catalog-costs.py": "aa9e71a730e8f9a853fe0e285e09796b84babc50ad685e18e7bc52326263adf6",
|
|
"experiments/analysis-efficiency/agent-trial.py": "3c00697c03306882401e4c0b4cbde2afdaafe755d4161b3eb2d293e765f78c25",
|
|
"experiments/analysis-efficiency/codex_context.py": "79c5ec253c836f67d05e4da19f80283c1d40c292dcbb78f3f984095031bcc52c"
|
|
},
|
|
"acquisition": [
|
|
{
|
|
"package": "ripgrep-14.1.1-r0.apk",
|
|
"url": "https://dl-cdn.alpinelinux.org/alpine/v3.21/community/x86_64/ripgrep-14.1.1-r0.apk",
|
|
"package_sha256": "213dd0b047163f6627cc2fdd6fbfe205009476eb4fc48c352a3f5b9ab647f6d4",
|
|
"package_bytes": 1422830,
|
|
"member": "usr/bin/rg",
|
|
"bytes": 3416168,
|
|
"sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"aports_revision": "4e899d119e4c983a938436d6f397a509521225d1"
|
|
},
|
|
{
|
|
"package": "zellij-0.40.0-r0.apk",
|
|
"url": "https://dl-cdn.alpinelinux.org/alpine/v3.21/community/x86_64/zellij-0.40.0-r0.apk",
|
|
"package_sha256": "575075945415b221857563e19c5f4c661af9f98bbba54f0994c7385c0e432432",
|
|
"package_bytes": 6722129,
|
|
"member": "usr/bin/zellij",
|
|
"bytes": 17151864,
|
|
"sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"aports_revision": "3be26a3a26e76e1bf3eff784bffe3956d29d77a0"
|
|
}
|
|
],
|
|
"independent_oracles": {
|
|
"ripgrep": {
|
|
"artifact_sha256": "78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c",
|
|
"section_sha256": "02b3cb036955be58bf4bd51710fcdec96a1f1a771e1bb7d1397d604557c2a6a7",
|
|
"json_sha256": "ea478aa80f91aa8f5159aba648ddfdda642fa2c98759e54e65623a19065634be",
|
|
"serde_rows": [
|
|
{
|
|
"index": 36,
|
|
"name": "serde",
|
|
"version": "1.0.210",
|
|
"kind": null
|
|
}
|
|
]
|
|
},
|
|
"zellij": {
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"section_sha256": "d0cabaf40a2875c519f68788547e484865463beeacf56bb01defa74253b4ba72",
|
|
"json_sha256": "9bcf8d694440a7e064189616aa40b69046e32ee1c70683ef2e0778150b9163ef",
|
|
"serde_rows": [
|
|
{
|
|
"index": 294,
|
|
"name": "serde",
|
|
"version": "1.0.137",
|
|
"kind": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"model_answer_review": [
|
|
{
|
|
"case": "model-full-direct",
|
|
"passed": true,
|
|
"answer": "| Name | Version | Dependency kind | Original index |\n|---|---|---|---|\n| serde | 1.0.210 | null (omitted; format defaults to runtime) | 36 |\n\nParent Evidence: `ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4` \nArtifact SHA-256: `78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c`\n\nStatic inspection found one exact-name match. Limitation: embedded metadata is unauthenticated and does not establish complete runtime dependencies.",
|
|
"scope": "Independent ELF/zlib/JSON package facts and derived counts, real returned Evidence ID, digest, static-only and runtime-dependency limitations; negative cases preserve the server refusal."
|
|
},
|
|
{
|
|
"case": "model-compact-direct",
|
|
"passed": true,
|
|
"answer": "| Name | Version | Dependency kind | Original index |\n|---|---|---|---|\n| serde | 1.0.210 | `null` (omitted; format defaults to runtime) | 36 |\n\nOne matching embedded record; static inspection only, no execution.\n\nParent Evidence: `ev_be5662081d3c5b609a5e65a78c732674d2fcc160e5b1173ca0d083316673eaa4`\n\nArtifact SHA-256: `78387bbe12b2110df8d2ce364390a00c190f4543a2f40b8279e49f6c5c85af9c`\n\nLimitation: embedded metadata is unauthenticated and does not establish complete runtime dependencies.",
|
|
"scope": "Independent ELF/zlib/JSON package facts and derived counts, real returned Evidence ID, digest, static-only and runtime-dependency limitations; negative cases preserve the server refusal."
|
|
},
|
|
{
|
|
"case": "model-full-broad",
|
|
"passed": true,
|
|
"answer": "REA statically recovered embedded `.dep-v0` metadata without executing the artifact:\n\n- Root package: **zellij 0.40.0**\n- Embedded graph totals: **422 packages, 1,063 dependency edges**\n- **serde present**; only observed version: **1.0.137**\n- Artifact SHA256: `9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db`\n- Supporting Evidence ID: `ev_e28b689b95fd966568747204d0b99dd4bfb552035993ec40c2cd512d3c057cb5`\n\nNames and versions are observed embedded records; counts are derived from those records. They do not authenticate build provenance or establish complete runtime dependencies.",
|
|
"scope": "Independent ELF/zlib/JSON package facts and derived counts, real returned Evidence ID, digest, static-only and runtime-dependency limitations; negative cases preserve the server refusal."
|
|
},
|
|
{
|
|
"case": "model-compact-broad",
|
|
"passed": true,
|
|
"answer": "REA statically recovered cargo-auditable metadata from the embedded `.dep-v0` section:\n\n- **Observed root:** `zellij` **0.40.0**\n- **Derived totals:** **422 packages**, **1,063 dependency edges**\n- **Observed serde:** present; **1.0.137** is the only recorded version.\n- **Artifact SHA256:** `9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db`\n- **Supporting Evidence ID:** `ev_730ffd6a4896e493b094b138088f3b5787bedf5cfb3fb6a540953100805c10b3`\n\nThese are embedded records and counts derived from them; they do not authenticate build provenance or establish complete runtime dependencies. The target was not executed.",
|
|
"scope": "Independent ELF/zlib/JSON package facts and derived counts, real returned Evidence ID, digest, static-only and runtime-dependency limitations; negative cases preserve the server refusal."
|
|
},
|
|
{
|
|
"case": "model-full-negative",
|
|
"passed": true,
|
|
"answer": "Yes. The canonical REA server rejected `view.offset: -1` with `invalid_request` / `invalid_input`:\n\n> `view.offset: Too small: expected number to be >=0`\n\nCalled `inspect_rust_binary` exactly once. No retry or binary execution occurred. The error returned no Evidence ID.",
|
|
"scope": "Independent ELF/zlib/JSON package facts and derived counts, real returned Evidence ID, digest, static-only and runtime-dependency limitations; negative cases preserve the server refusal."
|
|
},
|
|
{
|
|
"case": "model-compact-negative",
|
|
"passed": true,
|
|
"answer": "Yes. The canonical REA server rejected offset `-1` with `invalid_request` / `invalid_input`:\n\n> `view.offset: Too small: expected number to be >=0`\n\nCalled `inspect_rust_binary` exactly once. No corrected retry or binary execution occurred. The error returned no Evidence ID.",
|
|
"scope": "Independent ELF/zlib/JSON package facts and derived counts, real returned Evidence ID, digest, static-only and runtime-dependency limitations; negative cases preserve the server refusal."
|
|
}
|
|
],
|
|
"failed_attempts": [
|
|
{
|
|
"case": "sdk-full-ripgrep-1",
|
|
"reason": "The first benchmark used evidence_id at the root instead of source.kind=retained-evidence. The server correctly refused the harness input; corrected before accepted measurements.",
|
|
"excluded_from_performance_cohorts": true,
|
|
"log_sha256": "acd72e2210cb906ed07cb061390e57bb03ff46d47568f054eb1ced0ba2139d66"
|
|
}
|
|
],
|
|
"model_question_templates": {
|
|
"direct": "Use REA to inspect the local Rust binary {{artifact_path}} without executing it. Return the exact name, version, dependency kind, and original index of every observed serde package. Keep the answer concise, cite the real parent Evidence ID and artifact digest, and state any limitation. Choose the smallest sufficient response.\n",
|
|
"broad": "Determine which embedded dependency metadata REA can recover from {{artifact_path}} without executing it. Report the root package name/version, total package and edge counts, whether serde is present, its observed version(s), the artifact SHA256 and supporting Evidence ID. Distinguish observed metadata from inferences; keep the answer concise.\n",
|
|
"negative": "Use REA inspect_rust_binary once on {{artifact_path}} with view {\"collection\":\"packages\",\"offset\":-1}. Report whether the canonical server rejects the invalid offset. Do not retry with a corrected offset and do not execute the binary.\n"
|
|
},
|
|
"latest_main_integration": {
|
|
"base_revision": "25e1a24a3ed3671a0148757555f18d16c29d936a",
|
|
"comparison_scope": "One explicit-full/default pair on the rebased candidate; not added to original before/after cohorts.",
|
|
"records": [
|
|
{
|
|
"case": "integration-full",
|
|
"kind": "SDK",
|
|
"profile": "full",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 365.156704,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2194.9995639999997,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 8.802002000000357,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 5.010089999999764,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 28.393213999999716,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 200425,
|
|
"arguments": 287,
|
|
"text_replies": 3560,
|
|
"whole_task": 204272,
|
|
"raw_catalog_including_output_schemas": 903497
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.171,
|
|
"cpu_seconds": 7.019359,
|
|
"kernel_family_peak_bytes_including_page_cache": 874827776,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "f22505fae66da7a5083cbb93388dce93d9dfd9b7da0de66f48e70a43ff6e8ba4",
|
|
"receipt_sha256": {
|
|
"report.json": "a4782431a109d8501b78ac41db27e71e6f82c3b333dd37aed893c3b12aae49d1",
|
|
"catalog.json": "1640dd811f3bb6cf2b21a6d0e7b9b750bc45f514f56470f99800917da161e706",
|
|
"transcript.json": "2a34d1b655bcf1873c8cb3156568525ce41ef53f29973eda0df393aca51d306d"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
},
|
|
{
|
|
"case": "integration-default",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 361.093202,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2230.8176569999996,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 7.458020999999462,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 4.059271000000081,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 28.007474000000002,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 287,
|
|
"text_replies": 3560,
|
|
"whole_task": 51715,
|
|
"raw_catalog_including_output_schemas": 750743
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.173,
|
|
"cpu_seconds": 6.994262,
|
|
"kernel_family_peak_bytes_including_page_cache": 872333312,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "56c3438b3e12771d202ecbe60b775a9eb0000ee8b4fb9e629692a8d45790daca",
|
|
"receipt_sha256": {
|
|
"report.json": "928db422930cb420d04a165ef20f2ba569bfe9f156fbf049e1f2d600172d5ade",
|
|
"catalog.json": "56a48174c029aa3abfb9a56e38a40d021919899c5736f129d24c684cfaf01962",
|
|
"transcript.json": "98e2d713f1e3ae8b9561e1b1eea282e04eaf0d15eb515d75a23f2a905e0b8564"
|
|
},
|
|
"observed_resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"bounds": {
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 100,
|
|
"cpu_affinity": [15],
|
|
"task_ceiling": 192
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"executed_validation": {
|
|
"initial_focused": "10 files: 88 passed, 1 skipped, 2 failed (stale default-identity assertion and 30s canonical schema timeout).",
|
|
"corrected_rerun": "Both failed suites: 26 passed with serial files and unchanged deadlines; canonical schema timeout cause unproven.",
|
|
"latest_integration": "3 identity/profile/production doctor files: 32 passed.",
|
|
"check": "Passed on original base and latest-main integration.",
|
|
"docs_check_first_attempt": "Failed because the new README anchor differed from translated README link inventories; reused the existing MCP guide link.",
|
|
"docs_checks": "Initial checks caught a new/duplicate README link absent from translated inventories; the introduction now names the existing guide without adding a link.",
|
|
"docs_check_final": "Passed after preserving the translated README link inventory."
|
|
},
|
|
"review_followup": {
|
|
"root_cause": "The previous ambiguous CATALOG_IDENTITY denoted full advertisement while consumers assumed it represented the default live server.",
|
|
"structural_fix": "Explicit FULL_CATALOG_IDENTITY and DEFAULT_CATALOG_IDENTITY replace the ambiguous export; counts-only canonical consumers retain full identity; default diagnostics use the default; readiness records the typed live server catalog; Claude expectations use the shared input/output profile parsers.",
|
|
"source_sha256": {
|
|
"scripts/generate-skill-metadata.mjs": "e88f47e80a6d0e6b7eb14a464b7e5f3e44993529ecbc0ed6604c9569edb68ae7",
|
|
"scripts/lib/catalog-builders.mjs": "bb0cf8ebfe5a7d0ff090c1ddae6dd8760577b3b824cc1fd7cd9f2e83b558919e",
|
|
"scripts/lib/product-catalog.mjs": "20182284c3e1df7b37b858affb75028aa24724901147b638f4a07190908d9b9b",
|
|
"scripts/lib/release-package-canary.mjs": "c0f3e59832a0cce00829a3bf1e033588d9d840736d1305dbbad636506b2ac6d3",
|
|
"scripts/verify-claude-client.mjs": "8b098bbc00e9cb4877f86564245a16db696a2799fe6c48fe0e65f324629da4d7",
|
|
"scripts/verify-package-pack.mjs": "11b61499b846e896bc65689ca69c1c45db1ab4f0b14614518371a1dd59368a92",
|
|
"scripts/verify-reconstruction-readiness.mjs": "a7f4614694e0cc196b726b989a5bf5b0fdae574c48393e1a981699bc665f9d28",
|
|
"src/application/Doctor.fixture.ts": "e98481ff468f208561dd8b8132b8326317a088706a7ce366f5dd0dc521031292",
|
|
"src/application/Doctor.ts": "cd10aab92516c234e41c1597b35a126be289aae5dfaef0d964ef27ae5c648855",
|
|
"src/application/Setup.fixture.ts": "175487d3f6916852acac7635fccfb61d1616aca28d198278ec7d31a517b68c77",
|
|
"src/catalogIdentity.ts": "54e67816c09ab1abb12955ed0e87f4aa5e6f8607668aadb24ad1dc74e0ca85a3",
|
|
"src/server/EvidenceMcpServer.ts": "4f5913307b381815e7e319d777f4efe89fbee98da87978925028239b8773c88b",
|
|
"src/serverIdentity.ts": "b90af4f999ab0aadec352dfd3244b42f77b835542ec588577c8f3c1438f005df",
|
|
"tests/acceptance/applications/runtime.test.ts": "b57883f459018053893a268554a05910bf1aaa480599c6f7cad79cbbd0f9a1cf",
|
|
"tests/boundary/filesystem/dependencyInstall.test.ts": "055bb0cc573fd0a3b81155177e0dd913ee28bc776fbe370ef53076119e2b5cbd",
|
|
"tests/boundary/filesystem/generatedSkill.test.ts": "3197d6a2274fd505631b274329811c5b25c9f870c0bc6952f04f203b7cf360b2",
|
|
"tests/boundary/mcp/mcpDoctor.test.ts": "c88a665e8560ac97755ca809e6f45b2ad2354809a2eb7100470783a764f9decb",
|
|
"tests/boundary/mcp/outputSchemaProfile.test.ts": "d84e1e0636b811d48dde5d9b532de937f9fd3db49f394e20650e8258aa52ba85",
|
|
"tests/boundary/mcp/serverIdentity.test.ts": "dbe59d532b4a53635e502e93577fbd9f23d754ad31e715af73d461ada126934f",
|
|
"tests/boundary/process/packageTarListing.test.ts": "20581fed2bbbc0c3a3756560026cb138a66074e20f8c159e191d42de4e000f8d"
|
|
},
|
|
"validation": {
|
|
"review-tests": {
|
|
"passed": true,
|
|
"cpu_seconds": 137.239542,
|
|
"family_peak_bytes": 3058552832,
|
|
"log_sha256": "b380cc2270668d047245b3426cd143271658a7ad5da1aad3db073c356605c26c"
|
|
},
|
|
"review-check": {
|
|
"passed": true,
|
|
"cpu_seconds": 28.654837,
|
|
"family_peak_bytes": 1334308864,
|
|
"log_sha256": "b3182a46e432b0b0503088abec8abf8d0224c3da8025eb4f0e8777ac789e5e27"
|
|
},
|
|
"review-docs": {
|
|
"passed": true,
|
|
"cpu_seconds": 14.641149,
|
|
"family_peak_bytes": 507789312,
|
|
"log_sha256": "2f4aea6a070f6012ee7587ead635342cf9d318699b9701a8de09ef79021878d2"
|
|
},
|
|
"readiness-default": {
|
|
"passed": true,
|
|
"cpu_seconds": 29.813437,
|
|
"family_peak_bytes": 1241534464,
|
|
"log_sha256": "e864436ba2db543f6941bfb83ce58d37fdf1c17ca5ff38a78674e7c812b9abb7"
|
|
},
|
|
"readiness-full": {
|
|
"passed": true,
|
|
"cpu_seconds": 28.197651,
|
|
"family_peak_bytes": 1157550080,
|
|
"log_sha256": "f18fc53b6985aeef4d951cb2183eac7c12ea5c85d3426908a1766490ddf26da9"
|
|
},
|
|
"readiness-compact-off": {
|
|
"passed": true,
|
|
"cpu_seconds": 18.102913,
|
|
"family_peak_bytes": 861978624,
|
|
"log_sha256": "0fa90210e8e125f4f0c09db69a594f62ffc1f1c11fc71b848f701bd99e13baa0"
|
|
},
|
|
"review-sdk-default": {
|
|
"passed": true,
|
|
"cpu_seconds": 7.375525,
|
|
"family_peak_bytes": 861224960,
|
|
"log_sha256": "e95b4d93d772530b00a59ea09a4966a3b8eac9a99e640680f53af86f6288cf69"
|
|
}
|
|
},
|
|
"focused_tests": "9 files: 106 passed, 2 skipped.",
|
|
"readiness_profiles": ["default", "full", "compact input / output off"],
|
|
"sdk_catalog_and_complete_parent_unchanged": true,
|
|
"native_selected_identity_proof": [
|
|
{
|
|
"profile": "default",
|
|
"passed": true,
|
|
"saved_native_status_sha256": "b8fa284ad96587530d2664835a83f139b5ded29ddd4e5ab9fdaa15efc9500e00",
|
|
"catalog": {
|
|
"counts": {
|
|
"cli_commands": 160,
|
|
"mcp_tools": 213,
|
|
"mcp_prompts": 6
|
|
},
|
|
"digests": {
|
|
"tools_sha256": "b8c3712bb47a049ccd249b0de3afacdc27da0aea465baaadc8b7f17eef61daf3",
|
|
"prompts_sha256": "84c719b1aa48a7b12ad29e16278fc4c4254d9364f6620792cba6ceaef5b4a98c",
|
|
"combined_sha256": "0389e5636823b38f9c8a1561554e0c32d22a43528e792dc0995583ba37c460e4"
|
|
}
|
|
},
|
|
"readiness_catalog_digest": "0389e5636823b38f9c8a1561554e0c32d22a43528e792dc0995583ba37c460e4"
|
|
},
|
|
{
|
|
"profile": "full",
|
|
"passed": true,
|
|
"saved_native_status_sha256": "d1cb209b015da2a6662a56bcd167bf515fda8dd0baa1145b38d254f4eec0725c",
|
|
"catalog": {
|
|
"counts": {
|
|
"cli_commands": 160,
|
|
"mcp_tools": 213,
|
|
"mcp_prompts": 6
|
|
},
|
|
"digests": {
|
|
"tools_sha256": "7362fced4ad2726682316d0f1e8acf65e90c59192ef163c7cc4ce00c3d756767",
|
|
"prompts_sha256": "84c719b1aa48a7b12ad29e16278fc4c4254d9364f6620792cba6ceaef5b4a98c",
|
|
"combined_sha256": "5ab16853c717a6e98473cb6c5ac1871e186b9784f32ce1ac54d59ccaf1d3634e"
|
|
}
|
|
},
|
|
"readiness_catalog_digest": "5ab16853c717a6e98473cb6c5ac1871e186b9784f32ce1ac54d59ccaf1d3634e"
|
|
}
|
|
],
|
|
"native_client_limit": {
|
|
"client": "Claude Code 2.1.296",
|
|
"model": "loopback Anthropic fixture; no live API claim",
|
|
"end_to_end_passed": false,
|
|
"reason": "The unchanged verifier requires binary_session inline; native Claude persists the ~55KB result. Same failure reproduced on untouched baseline product code after preparing its packaged skill.",
|
|
"probes": [
|
|
{
|
|
"case": "claude-default",
|
|
"fixture_failure": "AssertionError [ERR_ASSERTION]: Claude must return the inline binary_session result before continuing",
|
|
"payload_exit_code": 1,
|
|
"cleanup_verified": true,
|
|
"saved_status_catalog": {
|
|
"counts": {
|
|
"cli_commands": 160,
|
|
"mcp_tools": 213,
|
|
"mcp_prompts": 6
|
|
},
|
|
"digests": {
|
|
"tools_sha256": "b8c3712bb47a049ccd249b0de3afacdc27da0aea465baaadc8b7f17eef61daf3",
|
|
"prompts_sha256": "84c719b1aa48a7b12ad29e16278fc4c4254d9364f6620792cba6ceaef5b4a98c",
|
|
"combined_sha256": "0389e5636823b38f9c8a1561554e0c32d22a43528e792dc0995583ba37c460e4"
|
|
}
|
|
},
|
|
"saved_status_bytes": 55471
|
|
},
|
|
{
|
|
"case": "claude-full",
|
|
"fixture_failure": "AssertionError [ERR_ASSERTION]: Claude must return the inline binary_session result before continuing",
|
|
"payload_exit_code": 1,
|
|
"cleanup_verified": true,
|
|
"saved_status_catalog": {
|
|
"counts": {
|
|
"cli_commands": 160,
|
|
"mcp_tools": 213,
|
|
"mcp_prompts": 6
|
|
},
|
|
"digests": {
|
|
"tools_sha256": "7362fced4ad2726682316d0f1e8acf65e90c59192ef163c7cc4ce00c3d756767",
|
|
"prompts_sha256": "84c719b1aa48a7b12ad29e16278fc4c4254d9364f6620792cba6ceaef5b4a98c",
|
|
"combined_sha256": "5ab16853c717a6e98473cb6c5ac1871e186b9784f32ce1ac54d59ccaf1d3634e"
|
|
}
|
|
},
|
|
"saved_status_bytes": 55471
|
|
},
|
|
{
|
|
"case": "claude-baseline-full-complete",
|
|
"fixture_failure": "AssertionError [ERR_ASSERTION]: Claude must return the inline binary_session result before continuing",
|
|
"payload_exit_code": 1,
|
|
"cleanup_verified": true,
|
|
"saved_status_catalog": {
|
|
"counts": {
|
|
"cli_commands": 160,
|
|
"mcp_tools": 213,
|
|
"mcp_prompts": 6
|
|
},
|
|
"digests": {
|
|
"tools_sha256": "3e27909ade9f9f6e61f361fd0501c9a712b7412666b00758448195749ccb680e",
|
|
"prompts_sha256": "84c719b1aa48a7b12ad29e16278fc4c4254d9364f6620792cba6ceaef5b4a98c",
|
|
"combined_sha256": "71e51816c31c8e9f0dd6956c69b7f36e00ce53e0d5579b583b944979036028ed"
|
|
}
|
|
},
|
|
"saved_status_bytes": 55473
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"ci_followup": {
|
|
"integration_base": "6d356b84344659085f2b912857b5e27fe0160c9b",
|
|
"first_ci_run": 39601241054,
|
|
"cause": "Three tests assumed the old full default in nested input rejection/property guidance.",
|
|
"fix": "Parameterize affected ZIP retention, browser endpoint and literal-seed workflows for full and compact; retain strict full advertisement assertions and enforce canonical valid/invalid behavior for both.",
|
|
"serial_tests": "4 files, 27 passed.",
|
|
"validation": {
|
|
"ci-regression-tests-serial": {
|
|
"passed": true,
|
|
"family_peak_bytes": 2452987904,
|
|
"cpu_seconds": 216.800823,
|
|
"log_sha256": "8fe90cbb0c3c283559ae66be66035117e7884e3565b1637aaf61307400efa73f"
|
|
},
|
|
"check-before-review-push": {
|
|
"passed": true,
|
|
"family_peak_bytes": 1326555136,
|
|
"cpu_seconds": 39.301628,
|
|
"log_sha256": "ce739f3aca7279ef2da53faba08f6e74581a0801e2014c7eb6d6aa402f782e4c"
|
|
},
|
|
"docs-before-review-push": {
|
|
"passed": true,
|
|
"family_peak_bytes": 511111168,
|
|
"cpu_seconds": 11.300216,
|
|
"log_sha256": "7ed6e5274552bf34d89c2b70cdb792b8274b0dbbf80e61884657bb386d238cae"
|
|
}
|
|
},
|
|
"incomplete_attempt": {
|
|
"log_sha256": "22b6035a7b87f0642ab96afc8b25ef29911b69d37082849ef753f4302fe1bf4d",
|
|
"reason": "Parallel files reached the 3 GiB early-stop threshold (4 GiB hard limit), no OOM; incomplete, not a passing run. Serial files passed without raising limits."
|
|
},
|
|
"source_sha256": {
|
|
"tests/boundary/mcp/artifactMcp.inlineInventory.test.ts": "c6c875dd49fc76f7b7b4aae8b9a1f3d379748278bbd0ec2c15f7ae2a7d0ed364",
|
|
"tests/boundary/mcp/browserMcp.test.ts": "bf9d0ad7f8061d2d7963de6a126ef4ed108a9e4eccc8107cedcd4360ac7fe096",
|
|
"tests/boundary/mcp/retainedApplicationEvidenceMcp.test.ts": "1d0d7121d339100e72f454d2b0a34a307a2e3609df3c416dca3674844761a6ba"
|
|
}
|
|
},
|
|
"accounting_followup": {
|
|
"original_cost_script_sha256": "aa9e71a730e8f9a853fe0e285e09796b84babc50ad685e18e7bc52326263adf6",
|
|
"current_cost_script_sha256": "ad32e6726f892be16cc7d352118f7e9f9f0a85649d9edd1049b5d73483df8078",
|
|
"change": "Document receipt redirection and accounting; append .log to the entire directory basename rather than replacing its suffix.",
|
|
"original_records_reprocessed_without_changes": true,
|
|
"additional_real_dotted_directory_validation": {
|
|
"case": "reproduce.sdk.1",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 502.6376340000006,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2992.545244000001,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 9.582700000000841,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 6.301149999999325,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 37.41663999999946,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 289,
|
|
"text_replies": 3562,
|
|
"whole_task": 51719,
|
|
"raw_catalog_including_output_schemas": 750743
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 8.687,
|
|
"cpu_seconds": 8.489351,
|
|
"kernel_family_peak_bytes_including_page_cache": 870670336,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "3d3390f3886b8905d5735ae484e0f142017716482d7e838ae5f5648a4513b79e",
|
|
"receipt_sha256": {
|
|
"report.json": "fa45533fd6909cfa1267f1b9c12af2c3d402ada69e95e97049f6cfb8149f9687",
|
|
"catalog.json": "56a48174c029aa3abfb9a56e38a40d021919899c5736f129d24c684cfaf01962",
|
|
"transcript.json": "ae7e65f061e7628d2c21562e1da0fe81168f73e6e124bf32b9d5fecffe88078d"
|
|
}
|
|
},
|
|
"included_in_original_performance_cohorts": false
|
|
},
|
|
"full_presentation_test_followup": {
|
|
"base_revision": "6d356b84344659085f2b912857b5e27fe0160c9b",
|
|
"change": "Full schema/example conformance cases explicitly select full presentation. Default source comparison and JavaScript facts workflows retain actual canonical refusals; their producer-schema assertions remain strict. Regenerated ignored catalog metadata before the corrected run.",
|
|
"executed_runs": [
|
|
{
|
|
"log": "ci-second-regressions.log",
|
|
"log_sha256": "ede521d31bfcc3db2799166dd3a7a7a433245452bf46182d4000889c6f8f0618",
|
|
"outcome": "27 passed; five full-presentation assumptions failed, including stale generated metadata",
|
|
"resource_receipt": {
|
|
"resource_scope": "rea-efficiency-6c78d365ef9d42d98dfa7a4407a60724.scope",
|
|
"peak_cgroup_bytes_sampled": 2150170624,
|
|
"elapsed_seconds": 186.422,
|
|
"abort": null,
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 200,
|
|
"cpu_affinity": [14, 15],
|
|
"task_ceiling": 192,
|
|
"peak_tasks_sampled": 67,
|
|
"resource_events_last_observed": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"resource_events_final": null,
|
|
"resource_counters_verified": false,
|
|
"cpu_stat_last_observed": {
|
|
"usage_usec": 219960849,
|
|
"user_usec": 202742520,
|
|
"system_usec": 17218328,
|
|
"nr_periods": 1863,
|
|
"nr_throttled": 33,
|
|
"throttled_usec": 44521,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-6c78d365ef9d42d98dfa7a4407a60724.scope",
|
|
"payload_exit_code": 1,
|
|
"observer_pid": 771268,
|
|
"remaining_processes": [771268],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 219959328,
|
|
"user_usec": 202741119,
|
|
"system_usec": 17218209,
|
|
"nr_periods": 1863,
|
|
"nr_throttled": 33,
|
|
"throttled_usec": 44521,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 2152132608,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-6c78d365ef9d42d98dfa7a4407a60724.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
},
|
|
"payload_resource_observation_verified": true,
|
|
"payload_observation_scope": "Counters at payload exit while observer remains alive; not final whole-scope counters.",
|
|
"payload_observer_sources_sha256": {
|
|
"resource-run.py": "378868d8ea3589e3acd640397fa4a543e0a2845768bb35a41119051797690343",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "ci-second-regressions-fixed.log",
|
|
"log_sha256": "a11f10bfb05303eb9b797f9a701d5d86e686ee0aa049804a5668a140596bcf0e",
|
|
"outcome": "31 passed; one 20-second child-process timeout",
|
|
"resource_receipt": {
|
|
"resource_scope": "rea-efficiency-978bb49765c14b3cb1922953928da222.scope",
|
|
"peak_cgroup_bytes_sampled": 2606223360,
|
|
"elapsed_seconds": 251.442,
|
|
"abort": null,
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 200,
|
|
"cpu_affinity": [14, 15],
|
|
"task_ceiling": 192,
|
|
"peak_tasks_sampled": 67,
|
|
"resource_events_last_observed": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"resource_events_final": null,
|
|
"resource_counters_verified": false,
|
|
"cpu_stat_last_observed": {
|
|
"usage_usec": 294221945,
|
|
"user_usec": 270973501,
|
|
"system_usec": 23248443,
|
|
"nr_periods": 2513,
|
|
"nr_throttled": 44,
|
|
"throttled_usec": 38486,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-978bb49765c14b3cb1922953928da222.scope",
|
|
"payload_exit_code": 1,
|
|
"observer_pid": 789544,
|
|
"remaining_processes": [789544],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 294220614,
|
|
"user_usec": 270972276,
|
|
"system_usec": 23248338,
|
|
"nr_periods": 2513,
|
|
"nr_throttled": 44,
|
|
"throttled_usec": 38486,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 2606747648,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-978bb49765c14b3cb1922953928da222.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
},
|
|
"payload_resource_observation_verified": true,
|
|
"payload_observation_scope": "Counters at payload exit while observer remains alive; not final whole-scope counters.",
|
|
"payload_observer_sources_sha256": {
|
|
"resource-run.py": "378868d8ea3589e3acd640397fa4a543e0a2845768bb35a41119051797690343",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "contract-presentation-fresh.log",
|
|
"log_sha256": "cd65b5322e28731cc276dd7251884104db24bbb8dd4f542733756b87d3c2d1fd",
|
|
"outcome": "one passed in a fresh process with unchanged deadlines",
|
|
"resource_receipt": {
|
|
"resource_scope": "rea-efficiency-4e6e2188b9c040edaa35cb43654a1ed8.scope",
|
|
"peak_cgroup_bytes_sampled": 1054052352,
|
|
"elapsed_seconds": 15.652,
|
|
"abort": null,
|
|
"hard_memory_bytes": 4294967296,
|
|
"early_stop_bytes": 3221225472,
|
|
"cpu_quota_percent": 200,
|
|
"cpu_affinity": [14, 15],
|
|
"task_ceiling": 192,
|
|
"peak_tasks_sampled": 33,
|
|
"resource_events_last_observed": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
},
|
|
"resource_events_final": null,
|
|
"resource_counters_verified": false,
|
|
"cpu_stat_last_observed": {
|
|
"usage_usec": 18652902,
|
|
"user_usec": 16999452,
|
|
"system_usec": 1653450,
|
|
"nr_periods": 156,
|
|
"nr_throttled": 0,
|
|
"throttled_usec": 0,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-4e6e2188b9c040edaa35cb43654a1ed8.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 793414,
|
|
"remaining_processes": [793414],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 18652236,
|
|
"user_usec": 16998845,
|
|
"system_usec": 1653390,
|
|
"nr_periods": 156,
|
|
"nr_throttled": 0,
|
|
"throttled_usec": 0,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1055846400,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-4e6e2188b9c040edaa35cb43654a1ed8.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
},
|
|
"payload_resource_observation_verified": true,
|
|
"payload_observation_scope": "Counters at payload exit while observer remains alive; not final whole-scope counters.",
|
|
"payload_observer_sources_sha256": {
|
|
"resource-run.py": "378868d8ea3589e3acd640397fa4a543e0a2845768bb35a41119051797690343",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"all_five_files_have_passing_checks": true,
|
|
"combined_run_passed": false,
|
|
"timeout_cause": "Not established; fresh-process retry passed with unchanged deadlines.",
|
|
"included_in_performance_cohorts": false
|
|
},
|
|
"godot_profile_followup": {
|
|
"ci_head": "c8ed337568c8c28ccbcb5a59de3e35759ee8f250",
|
|
"ci_result": "Portable tests: 15,703 passed, 29 skipped; one Godot full-schema assumption failed.",
|
|
"change": "Run the retained PCK inventory workflow under full and compact; assert full advertisement constraints and canonical invalid-field refusal under both.",
|
|
"local_result": "Three passed, including both profiles and encrypted-directory unknown coverage.",
|
|
"log_sha256": "01a2c366dff66262d145368832bb5e4344768bfeda5fcce579afbff44a0be864",
|
|
"elapsed_seconds": 75.687,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-c5daece4d14c4998abd5732974cbf5e6.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 811836,
|
|
"remaining_processes": [811836],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 83425505,
|
|
"user_usec": 75026217,
|
|
"system_usec": 8399287,
|
|
"nr_periods": 755,
|
|
"nr_throttled": 1,
|
|
"throttled_usec": 33,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1815400448,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-c5daece4d14c4998abd5732974cbf5e6.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
},
|
|
"included_in_performance_cohorts": false
|
|
},
|
|
"cli_identity_followup": {
|
|
"source_derived_root_cause": "Direct CLI status omitted the selected catalog, triggering a compact fallback even for explicit full. Parsed output profile was also discarded by AppConfig.",
|
|
"structural_change": "CLI status derives both input/output profiles from parsed config. Runtime identity requires a caller-supplied catalog; both production callers pass it explicitly. No ambient config reinterpretation at the identity owner.",
|
|
"actual_public_entrypoints": [
|
|
"stdio binary_session",
|
|
"rea capabilities --json",
|
|
"rea providers --json"
|
|
],
|
|
"profile_cases": [
|
|
"default compact/full",
|
|
"full/full",
|
|
"compact/full",
|
|
"full/off",
|
|
"compact/off"
|
|
],
|
|
"executed_runs": [
|
|
{
|
|
"log": "cli-profile-mcpDoctor.log",
|
|
"log_sha256": "7f5c79d2dfd1589a47041eeb4886858858560fc8cfc0860cfa496aef7b860dde",
|
|
"passed_tests": 14,
|
|
"elapsed_seconds": 83.973,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-d7bf0512b44140cf91635a1a692ff825.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 821163,
|
|
"remaining_processes": [821163],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 100650679,
|
|
"user_usec": 87453243,
|
|
"system_usec": 13197435,
|
|
"nr_periods": 834,
|
|
"nr_throttled": 10,
|
|
"throttled_usec": 4235,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1524985856,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-d7bf0512b44140cf91635a1a692ff825.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "cli-profile-serverIdentity.log",
|
|
"log_sha256": "aa75647dd78a6b4df22dc2d0f2816991b941800d7af72664b57c973950084d1f",
|
|
"passed_tests": 11,
|
|
"elapsed_seconds": 49.302,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-8f537b501576473b9b5e32f0e7627f6b.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 823954,
|
|
"remaining_processes": [823954],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 54311975,
|
|
"user_usec": 50014222,
|
|
"system_usec": 4297752,
|
|
"nr_periods": 492,
|
|
"nr_throttled": 1,
|
|
"throttled_usec": 3981,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1885233152,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-8f537b501576473b9b5e32f0e7627f6b.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"included_in_performance_cohorts": false
|
|
},
|
|
"latest_main_8e_integration": {
|
|
"base_revision": "8e3bf56e1",
|
|
"tested_code_revision": "2a6a0812886e1a4e022042947a59575bed1bc954",
|
|
"scope": "Separate integration after upstream browser Evidence schema changes; not a repeated performance cohort.",
|
|
"real_sdk_costs": {
|
|
"case": "latest-main-8e-sdk",
|
|
"kind": "SDK",
|
|
"profile": "default",
|
|
"artifact_sha256": "9a86e9ca47902a869fdf1886f4cf17714f4fa5655427128beadff498cfb392db",
|
|
"tool_count": 213,
|
|
"calls": [
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 370.39350399999967,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 2317.916096,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_analysis_view",
|
|
"elapsed_ms": 9.645430000000488,
|
|
"is_error": false
|
|
},
|
|
{
|
|
"name": "inspect_rust_binary",
|
|
"elapsed_ms": 5.3366600000008475,
|
|
"is_error": true
|
|
},
|
|
{
|
|
"name": "export_evidence_bundle",
|
|
"elapsed_ms": 30.598637999999482,
|
|
"is_error": false
|
|
}
|
|
],
|
|
"parent_evidence_id": "ev_8c9124795a5cf45c2bf816bbfa0ced9c3025550e72d4e3facf5fb2e266d3dadb",
|
|
"parent_semantic_sha256": "df1930ee07a13eb4b47c91f2834c4b0f8d99089e051a02083c7c3cf03bb30467",
|
|
"token_estimates": {
|
|
"input_catalog_once": 47868,
|
|
"arguments": 290,
|
|
"text_replies": 3563,
|
|
"whole_task": 51721,
|
|
"raw_catalog_including_output_schemas": 750781
|
|
},
|
|
"actual_model_usage": null,
|
|
"wall_seconds": 7.785,
|
|
"cpu_seconds": 7.533643,
|
|
"kernel_family_peak_bytes_including_page_cache": 873308160,
|
|
"resource_stop": null,
|
|
"cleanup_verified": true,
|
|
"final_whole_scope_counters": null,
|
|
"guard_sources_sha256": {
|
|
"resource-run.py": "7a9642ab86ba34290564f636eb080cacf38b4185a254028680b238bff172993b",
|
|
"resource_payload.py": "6f089e645459eba80c5d73e39c21606c78173a44daf49fabc3b88c4631ce51c6"
|
|
},
|
|
"log_sha256": "528bc7a1373c01facb84706db0848ed66905e8dfecba17275c3bb2b866a5205c",
|
|
"receipt_sha256": {
|
|
"report.json": "69e9fb06030e7b00a0f3323a1ccf8e2ed53172e36ebfa98d6e2e6abbd33d9faa",
|
|
"catalog.json": "3be1d142d47c9a103cbbab0dcc48e556fe7acb52f812f930ba92b59540beb2d4",
|
|
"transcript.json": "dc2bbf5bb7e5391dd2b510ad8126402c6a796a19d02f2d04beec321fbb7c64e1"
|
|
}
|
|
},
|
|
"full_parent_equal_to_previous_review_check": true,
|
|
"all_catalog_metadata_except_output_schemas_equal": true,
|
|
"public_workflow_checks": "Fourteen production CLI/MCP profile and lifecycle tests passed. Full absolute-path advertisement conformance and default canonical path refusals passed (two tests).",
|
|
"path_followup": "CI e255 exposed a remaining full nested-path advertisement assumption. Only that conformance case selects full; the actual relative-path refusal workflow still exercises the omitted/default profile.",
|
|
"validation_runs": [
|
|
{
|
|
"log": "latest-main-8e-doctor.log",
|
|
"log_sha256": "c7bbb538b8fd409ce2f3381af8166c3f1c66ff2f34b03abe095f99fa5016a367",
|
|
"elapsed_seconds": 103.153,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-47112168490343be9cf3738adf32b051.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 852216,
|
|
"remaining_processes": [852216],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 120761531,
|
|
"user_usec": 104690859,
|
|
"system_usec": 16070672,
|
|
"nr_periods": 1026,
|
|
"nr_throttled": 7,
|
|
"throttled_usec": 15275,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1406656512,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-47112168490343be9cf3738adf32b051.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "absolute-path-profiles.log",
|
|
"log_sha256": "f28b63b8969152fdeec3595ae66ed6ccb4733c9cd21542d0b32d6bb269ceb8a0",
|
|
"elapsed_seconds": 18.742,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-e46c4b026e1b4023917aceaaf79eb563.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 856870,
|
|
"remaining_processes": [856870],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 18867565,
|
|
"user_usec": 16387068,
|
|
"system_usec": 2480497,
|
|
"nr_periods": 185,
|
|
"nr_throttled": 0,
|
|
"throttled_usec": 0,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 969953280,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-e46c4b026e1b4023917aceaaf79eb563.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"included_in_performance_cohorts": false
|
|
},
|
|
"remaining_constraint_followup": {
|
|
"base_revision": "8e3bf56e11bcb56d0e8754fdfa32a7a9f004ca13",
|
|
"ci_observation": "Unchanged 2608 retry passed the prior Java-cleanup failure, then found build_call_path nested coverage constraints assumed a full advertisement.",
|
|
"change": "Function-call direction workflow now exercises full/compact with canonical invalid coverage refusals. Browser scenario keeps default actual advertisement for valid calls, full producer schema negatives, and typed canonical refusal.",
|
|
"audit_scope": "Compared full/compact input catalogs and reviewed negative schema assertions. Fresh isolated processes cover function-call directions, ADB start, browser scenarios, JavaScript source selection and managed workflows.",
|
|
"passing_test_count": 14,
|
|
"failed_local_attempt_preserved": true,
|
|
"executed_runs": [
|
|
{
|
|
"log": "final-negative-functionCallDirectionsMcp.log",
|
|
"log_sha256": "2f5a35b3e0df25daff235f052862a319737455062ca879a700d110f6c4c5d5b2",
|
|
"test_summary": "2 passed (2)",
|
|
"elapsed_seconds": 53.207,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-03b95305041144949970ac47169a4978.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 917614,
|
|
"remaining_processes": [917614],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 58322344,
|
|
"user_usec": 51463945,
|
|
"system_usec": 6858398,
|
|
"nr_periods": 530,
|
|
"nr_throttled": 1,
|
|
"throttled_usec": 14,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1652879360,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-03b95305041144949970ac47169a4978.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "final-negative-adbStartMcp.log",
|
|
"log_sha256": "e3aacf3a950607a210349ae111043d80477021ffeecd6e98897700898fc0f2e2",
|
|
"test_summary": "2 passed (2)",
|
|
"elapsed_seconds": 38.274,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-65b1f5db0a1d468abd392502314307c4.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 918208,
|
|
"remaining_processes": [918208],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 42667409,
|
|
"user_usec": 36781789,
|
|
"system_usec": 5885619,
|
|
"nr_periods": 381,
|
|
"nr_throttled": 2,
|
|
"throttled_usec": 4057,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1313853440,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-65b1f5db0a1d468abd392502314307c4.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "final-negative-browserScenarioMcp.log",
|
|
"log_sha256": "87b905b1b03a47b146eba003674bbe054c75cd6074540c0b907e5e24e7a302b5",
|
|
"test_summary": "1 failed | 1 passed (2)",
|
|
"elapsed_seconds": 39.577,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-da25c46186ea43f6a5c96db67d61f8ff.scope",
|
|
"payload_exit_code": 1,
|
|
"observer_pid": 919050,
|
|
"remaining_processes": [919050],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 43818953,
|
|
"user_usec": 38886090,
|
|
"system_usec": 4932862,
|
|
"nr_periods": 394,
|
|
"nr_throttled": 2,
|
|
"throttled_usec": 3972,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1394446336,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-da25c46186ea43f6a5c96db67d61f8ff.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "final-negative-fixed-browserScenarioMcp.log",
|
|
"log_sha256": "1d4ae533fa12bc1769c9c8b9cf8a5acb81855f68d8a6232e19a27a3a9330c4ad",
|
|
"test_summary": "2 passed (2)",
|
|
"elapsed_seconds": 28.236,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-9424832752364fc295201a0fdfc2f97d.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 923267,
|
|
"remaining_processes": [923267],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 32676191,
|
|
"user_usec": 28426282,
|
|
"system_usec": 4249908,
|
|
"nr_periods": 281,
|
|
"nr_throttled": 0,
|
|
"throttled_usec": 0,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 2045136896,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-9424832752364fc295201a0fdfc2f97d.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "final-negative-fixed-javascriptSourceSelection.log",
|
|
"log_sha256": "3a56ef922664064aec099f4cbd9741131f998487574eaac69ba2af1441f8edbc",
|
|
"test_summary": "6 passed (6)",
|
|
"elapsed_seconds": 36.907,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-6456af0972c948109302b1121f6f1322.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 923954,
|
|
"remaining_processes": [923954],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 45054409,
|
|
"user_usec": 40333838,
|
|
"system_usec": 4720571,
|
|
"nr_periods": 367,
|
|
"nr_throttled": 3,
|
|
"throttled_usec": 4210,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1351868416,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-6456af0972c948109302b1121f6f1322.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"log": "final-negative-fixed-managedMcp.log",
|
|
"log_sha256": "4fcf48f9087eed10a34a81cff4037ea2f47d4fe0335cc0222e80d787fd8e9163",
|
|
"test_summary": "2 passed (2)",
|
|
"elapsed_seconds": 32.557,
|
|
"payload_resource_observation": {
|
|
"phase": "payload-exited-observer-alive",
|
|
"ownership_token": "rea-efficiency-005cd6a613b84d1dbba465a19719d7a0.scope",
|
|
"payload_exit_code": 0,
|
|
"observer_pid": 925544,
|
|
"remaining_processes": [925544],
|
|
"payload_cleanup_verified": true,
|
|
"cpu_stat": {
|
|
"usage_usec": 36764028,
|
|
"user_usec": 33981848,
|
|
"system_usec": 2782180,
|
|
"nr_periods": 324,
|
|
"nr_throttled": 0,
|
|
"throttled_usec": 0,
|
|
"nr_bursts": 0,
|
|
"burst_usec": 0
|
|
},
|
|
"memory_peak_bytes": 1497161728,
|
|
"control_group": "user.slice/user-1004.slice/user@1004.service/app.slice/rea-efficiency-005cd6a613b84d1dbba465a19719d7a0.scope",
|
|
"resource_events": {
|
|
"memory.events": {
|
|
"low": 0,
|
|
"high": 0,
|
|
"max": 0,
|
|
"oom": 0,
|
|
"oom_kill": 0,
|
|
"oom_group_kill": 0
|
|
},
|
|
"pids.events": {
|
|
"max": 0
|
|
}
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"included_in_performance_cohorts": false
|
|
}
|
|
}
|