@hecer/yoke 1.22.0 → 1.23.0

package/docs/benchmarks/2026-10-04-efficiency/raw/yoke-history.jsonl

@@ -0,0 +1,104 @@
+{"runId": "aafcbc1f-5529-4873-9594-3a60657da063", "timestamp": "2026-10-04T08:58:22.717Z", "type": "tokens", "data": {"inputTokens": 26544, "outputTokens": 280, "cachedInputTokens": 7168, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 76, "provider": "codex", "role": "planner", "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true}, "durationMs": 19037, "schemaVersion": 1, "id": "16ae67b1-cb0e-48e4-88d3-da3f57277d09"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:32:19.329Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 8, "data": {}, "schemaVersion": 1, "id": "d8cb2b62-fe45-4646-92b3-812843482a02"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:32:19.330Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "d9404534-cdf0-4561-9d07-877befb8d02b", "phase": "waiting-resource", "durationMs": 12, "schemaVersion": 1, "id": "3b6435b6-5810-4f6b-97c0-fc5ddc4cceaa", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:49.693Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "d9404534-cdf0-4561-9d07-877befb8d02b", "phase": "implementing", "durationMs": 90363, "schemaVersion": 1, "id": "6f5800f4-537a-4778-a811-b75c7902a1d6", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:55.197Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "d9404534-cdf0-4561-9d07-877befb8d02b", "phase": "verifying", "durationMs": 5504, "schemaVersion": 1, "id": "6f5d6c9e-95bf-4131-9d85-c657fb4afe09", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:55.333Z", "type": "tokens", "storyId": "STORY-5", "attemptId": "d9404534-cdf0-4561-9d07-877befb8d02b", "data": {"inputTokens": 305279, "outputTokens": 962, "cachedInputTokens": 273664, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 85, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 305279, "cachedInputTokens": 273664, "cacheWriteInputTokens": 0, "outputTokens": 962, "usageAvailable": true, "reasoningOutputTokens": 85, "costMeasurementComplete": false, "durationMs": 79043, "callId": "71811ccf-9266-4d91-a577-9201ae481d97", "routingAttemptId": "f6ff0fbaff099650713af8e361772407.7af9f824932982db9c38827b35845ae3c9028927bfdc1bc8a1801508a7b9c43f.2"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "adc1e063-cb7b-448d-9572-68fee89b6ae8"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:55.424Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "d9404534-cdf0-4561-9d07-877befb8d02b", "phase": "design", "durationMs": 227, "schemaVersion": 1, "id": "7cf12cef-5b14-48d2-9386-094dc2748ac3", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:55.424Z", "type": "attempt-ended", "storyId": "STORY-5", "attemptId": "d9404534-cdf0-4561-9d07-877befb8d02b", "durationMs": 96106, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "2834cfc8-99c4-4866-b9b3-314ce7acde66"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:55.426Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "integration-queue", "provider": "codex", "durationMs": 3, "schemaVersion": 1, "id": "41e31658-ccac-46b3-b277-ca1ce10191ac", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:33:55.430Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "5507c265-a2c7-40a9-844c-90972249a66d"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:12.650Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "cae8e184-c38a-4dc8-95b4-058d472c26f3", "phase": "waiting-resource", "durationMs": 17223, "schemaVersion": 1, "id": "99852eaa-b83f-4887-8d77-8d4f587987bd", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:13.039Z", "type": "accepted", "storyId": "STORY-5", "schemaVersion": 1, "id": "3fff7879-4512-444a-a921-aeb21506e91c", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:13.055Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "cae8e184-c38a-4dc8-95b4-058d472c26f3", "phase": "committing", "durationMs": 405, "schemaVersion": 1, "id": "39fbb3c6-0a0e-4a44-a422-26eff05e7a52", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:13.055Z", "type": "attempt-ended", "storyId": "STORY-5", "attemptId": "cae8e184-c38a-4dc8-95b4-058d472c26f3", "durationMs": 17628, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "2e837a4b-d36d-4f00-b285-f0226be7ed98"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:13.059Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "integration", "provider": "codex", "durationMs": 17627, "schemaVersion": 1, "id": "5c4fd7a8-403d-4723-b2c5-a565175b0dcb", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:13.276Z", "type": "phase-ended", "storyId": "STORY-6", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "819913e2-0536-4a08-a747-d9a5d4ae4ebf"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:34:13.277Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "phase": "waiting-resource", "durationMs": 5, "schemaVersion": 1, "id": "2d2b7ba2-9416-46ff-b328-0085c84b93ca", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:45:36.492Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "phase": "implementing", "durationMs": 683215, "schemaVersion": 1, "id": "b5c79bdd-3875-46ef-a931-f831a8d8607c", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:45:50.716Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "phase": "verifying", "durationMs": 14224, "schemaVersion": 1, "id": "9ebb9393-87ec-4dbf-a981-443906a59d98", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:45:50.853Z", "type": "tokens", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "data": {"inputTokens": 2950211, "outputTokens": 13068, "cachedInputTokens": 2853888, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 3440, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 2950211, "cachedInputTokens": 2853888, "cacheWriteInputTokens": 0, "outputTokens": 13068, "usageAvailable": true, "reasoningOutputTokens": 3440, "costMeasurementComplete": false, "durationMs": 663112, "callId": "7e0318cf-7b92-4dc5-8f0c-f983fc7a67a5", "routingAttemptId": "0737456746e48fa3ca907792ccb9ee47.31f56116c8aca09363f9c31514bb81d93c640e3ca65d2d303426799ebf903466.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "2b2238eb-39e3-401e-ba87-05f6e5cba05f"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:04.539Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "phase": "design", "durationMs": 13823, "schemaVersion": 1, "id": "77a8237d-35e4-4d69-8b0e-7787dd1f1ba7", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:19.136Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "phase": "verifying", "durationMs": 14597, "schemaVersion": 1, "id": "b3d731d9-e284-4c38-adb0-77057550463a", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:19.152Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "phase": "design", "durationMs": 16, "schemaVersion": 1, "id": "14bcb500-81c0-4653-b334-0138ef9e70c3", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:19.152Z", "type": "attempt-ended", "storyId": "STORY-6", "attemptId": "e916639a-61bc-41e1-a1a3-8e97a00b918a", "durationMs": 725880, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "77b8fca5-033f-46c7-b6ae-bb6c82c19319"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:19.154Z", "type": "phase-ended", "storyId": "STORY-6", "phase": "integration-queue", "provider": "codex", "durationMs": 2, "schemaVersion": 1, "id": "8dca3a81-a625-42ce-a919-6b52a43d0cca", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:19.158Z", "type": "phase-ended", "storyId": "STORY-6", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 3, "data": {}, "schemaVersion": 1, "id": "3dcd69b5-8161-41e2-b2dd-35792a988418"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:47.022Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "ebecc8e9-be5b-413c-a098-8dc8c3155027", "phase": "waiting-resource", "durationMs": 27868, "schemaVersion": 1, "id": "7d8b550f-c003-40c3-a831-877c565dd7dc", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:47.430Z", "type": "accepted", "storyId": "STORY-6", "schemaVersion": 1, "id": "43d3319e-cabe-4fcc-bbd5-5289bb9053b8", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:47.447Z", "type": "phase-ended", "storyId": "STORY-6", "attemptId": "ebecc8e9-be5b-413c-a098-8dc8c3155027", "phase": "committing", "durationMs": 425, "schemaVersion": 1, "id": "a12a3763-f624-47cf-9814-72543935a802", "data": {}}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:47.447Z", "type": "attempt-ended", "storyId": "STORY-6", "attemptId": "ebecc8e9-be5b-413c-a098-8dc8c3155027", "durationMs": 28293, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "548a673c-7a0a-4ef2-8c5a-80183d94d529"}
+{"runId": "fc7bdc45-98c9-449a-bd79-786828cd24ff", "timestamp": "2026-10-04T08:46:47.450Z", "type": "phase-ended", "storyId": "STORY-6", "phase": "integration", "provider": "codex", "durationMs": 28292, "schemaVersion": 1, "id": "6ad1fc02-5512-4366-a8e7-3149cb5c634f", "data": {}}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:03:19.006Z", "type": "phase-ended", "storyId": "STORY-7", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 7, "data": {}, "schemaVersion": 1, "id": "15c8432a-df9e-48c9-9c17-3846ec809282"}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:11.735Z", "type": "tokens", "storyId": "STORY-7", "attemptId": "bff37517-6ade-4cca-b8ea-466a4074c4ab", "data": {"inputTokens": 1800983, "outputTokens": 8456, "cachedInputTokens": 1712512, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 1469, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 1800983, "cachedInputTokens": 1712512, "cacheWriteInputTokens": 0, "outputTokens": 8456, "usageAvailable": true, "reasoningOutputTokens": 1469, "costMeasurementComplete": false, "durationMs": 441916, "callId": "5570580f-3c42-47aa-b22f-92a7ee46e1e6", "routingAttemptId": "49c8f721f06938aa5a68c977f2c015d2.9d12a2401d26f2cf7ba8a88ce8d21236a3d0bc760944d6c08add41e1dc32ed9d.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "b85671b8-378f-4e96-971b-789b50ae88da"}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:23.068Z", "type": "phase-ended", "storyId": "STORY-7", "attemptId": "bff37517-6ade-4cca-b8ea-466a4074c4ab", "phase": "implementing", "durationMs": 484220, "schemaVersion": 1, "id": "c376f102-de36-4a8c-adf4-fd8f449a3cf2", "data": {}}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:41.503Z", "type": "phase-ended", "storyId": "STORY-7", "attemptId": "bff37517-6ade-4cca-b8ea-466a4074c4ab", "phase": "verifying", "durationMs": 18435, "schemaVersion": 1, "id": "fa8e13e3-98db-4466-96b3-f2234ed494a6", "data": {}}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:41.519Z", "type": "phase-ended", "storyId": "STORY-7", "attemptId": "bff37517-6ade-4cca-b8ea-466a4074c4ab", "phase": "design", "durationMs": 16, "schemaVersion": 1, "id": "06e092db-ba8c-46f7-a593-9897ba1bde6b", "data": {}}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:41.878Z", "type": "phase-ended", "storyId": "STORY-7", "attemptId": "bff37517-6ade-4cca-b8ea-466a4074c4ab", "phase": "committing", "durationMs": 359, "schemaVersion": 1, "id": "058eb864-47ae-4624-abe0-4aa89bd56476", "data": {}}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:41.878Z", "type": "attempt-ended", "storyId": "STORY-7", "attemptId": "bff37517-6ade-4cca-b8ea-466a4074c4ab", "durationMs": 503030, "outcome": "completed", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "b4d4d548-e20d-4d90-9c1f-3ab337cf6e3e"}
+{"runId": "f6edac7e-cba0-4ee9-b444-0691b83143b8", "timestamp": "2026-10-04T09:11:41.878Z", "type": "accepted", "storyId": "STORY-7", "schemaVersion": 1, "id": "6aa3860f-4f32-46c6-b72c-0edfee15937e", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T07:56:12.213Z", "type": "phase-ended", "storyId": "STORY-1", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 6, "data": {}, "schemaVersion": 1, "id": "9fbd25e2-9e4e-45bc-98df-5c4738ac0e6f"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T07:56:12.214Z", "type": "phase-ended", "storyId": "STORY-1", "attemptId": "512f0185-fa3d-45fb-bcee-066d6a9f182d", "phase": "waiting-resource", "durationMs": 9, "schemaVersion": 1, "id": "d82ae5d5-705d-4d38-b1e6-329977531acf", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:38.112Z", "type": "phase-ended", "storyId": "STORY-1", "attemptId": "512f0185-fa3d-45fb-bcee-066d6a9f182d", "phase": "implementing", "durationMs": 565898, "schemaVersion": 1, "id": "ea9ebf34-4063-443f-afe0-82c93c0f6b1f", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:41.084Z", "type": "tokens", "storyId": "STORY-1", "attemptId": "512f0185-fa3d-45fb-bcee-066d6a9f182d", "data": {"inputTokens": 1435585, "outputTokens": 12725, "cachedInputTokens": 1314176, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 2848, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 1435585, "cachedInputTokens": 1314176, "cacheWriteInputTokens": 0, "outputTokens": 12725, "usageAvailable": true, "reasoningOutputTokens": 2848, "costMeasurementComplete": false, "durationMs": 560773, "callId": "d82a9585-8c0b-4408-a335-7dddfc9eb2e4", "routingAttemptId": "a0b90c58b45de45793a2116a1d00568b.c191fbd2ea09fc4f9fac2d9307f6bea40b0c657a891c65826e2be0a31c969832.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "f51a71d0-82b9-4d7d-b611-fbab129361c9"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:41.170Z", "type": "phase-ended", "storyId": "STORY-1", "attemptId": "512f0185-fa3d-45fb-bcee-066d6a9f182d", "phase": "verifying", "durationMs": 3058, "schemaVersion": 1, "id": "4d3c29af-589c-4d93-9ef3-c5ac359ae31b", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:41.170Z", "type": "attempt-ended", "storyId": "STORY-1", "attemptId": "512f0185-fa3d-45fb-bcee-066d6a9f182d", "durationMs": 568965, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "40c7f3f8-3e8a-4331-b2ac-bd4eb8c26738"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:41.172Z", "type": "phase-ended", "storyId": "STORY-1", "phase": "integration-queue", "provider": "codex", "durationMs": 3, "schemaVersion": 1, "id": "7e4e8eff-3a82-4208-ba71-8af94ccc96c4", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:41.174Z", "type": "phase-ended", "storyId": "STORY-1", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 1, "data": {}, "schemaVersion": 1, "id": "0781a14a-7633-43b3-9e6e-a6e7bc1bff0f"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:47.201Z", "type": "phase-ended", "storyId": "STORY-1", "attemptId": "0304b338-fd9f-4f28-b91f-74b7730d29d4", "phase": "waiting-resource", "durationMs": 6029, "schemaVersion": 1, "id": "2e30127f-37e8-4cf9-82b7-b034b7628f49", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:47.460Z", "type": "accepted", "storyId": "STORY-1", "schemaVersion": 1, "id": "d7bf9ff6-f5cf-457d-acd8-1da0c51a9926", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:47.474Z", "type": "phase-ended", "storyId": "STORY-1", "attemptId": "0304b338-fd9f-4f28-b91f-74b7730d29d4", "phase": "committing", "durationMs": 273, "schemaVersion": 1, "id": "1412dc1b-3a72-4c2e-9403-a0da59f0fb7d", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:47.474Z", "type": "attempt-ended", "storyId": "STORY-1", "attemptId": "0304b338-fd9f-4f28-b91f-74b7730d29d4", "durationMs": 6302, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "597bed19-838a-4d9d-adeb-cefc598b6a9a"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:47.476Z", "type": "phase-ended", "storyId": "STORY-1", "phase": "integration", "provider": "codex", "durationMs": 6301, "schemaVersion": 1, "id": "a9ef3089-0eca-436e-ab79-197ef6a6d688", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:48.288Z", "type": "phase-ended", "storyId": "STORY-2", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 6, "data": {}, "schemaVersion": 1, "id": "bec319ee-9e22-48e5-8ad2-c13049d85b44"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:48.289Z", "type": "phase-ended", "storyId": "STORY-3", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 5, "data": {}, "schemaVersion": 1, "id": "f35d7471-8831-4908-b5b4-737c6fa23422"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:48.290Z", "type": "phase-ended", "storyId": "STORY-2", "attemptId": "3b4726c7-ae32-4dd2-bcbe-3d22d0869c6c", "phase": "waiting-resource", "durationMs": 95, "schemaVersion": 1, "id": "c5e17dd2-7e5d-4f5d-95db-e8a30bf602c8", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:05:48.430Z", "type": "phase-ended", "storyId": "STORY-3", "attemptId": "cd20d41c-ba19-4bfe-9510-f8f94aded76a", "phase": "waiting-resource", "durationMs": 149, "schemaVersion": 1, "id": "018bb7cc-5161-4fa4-b82d-76c4db13d3de", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:11:55.672Z", "type": "phase-ended", "storyId": "STORY-2", "attemptId": "3b4726c7-ae32-4dd2-bcbe-3d22d0869c6c", "phase": "implementing", "durationMs": 367382, "schemaVersion": 1, "id": "a4fbd777-7f72-450a-9301-2ab845f73185", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:11:58.395Z", "type": "tokens", "storyId": "STORY-2", "attemptId": "3b4726c7-ae32-4dd2-bcbe-3d22d0869c6c", "data": {"inputTokens": 698268, "outputTokens": 8663, "cachedInputTokens": 643968, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 1022, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 698268, "cachedInputTokens": 643968, "cacheWriteInputTokens": 0, "outputTokens": 8663, "usageAvailable": true, "reasoningOutputTokens": 1022, "costMeasurementComplete": false, "durationMs": 361778, "callId": "87f71ca2-014a-4e81-a585-f43f0d60fa29", "routingAttemptId": "91d07ae86c6e79ee785d48273b7c228a.63601eea48853a4e499d7152c0bd423946f9e9e2dfce13bd891c6661236f66fc.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "295d4ed2-902c-480f-a914-203438672889"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:11:58.488Z", "type": "phase-ended", "storyId": "STORY-2", "attemptId": "3b4726c7-ae32-4dd2-bcbe-3d22d0869c6c", "phase": "verifying", "durationMs": 2816, "schemaVersion": 1, "id": "9cb130c4-b321-4c47-ac8a-1b07bb8794b5", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:11:58.488Z", "type": "attempt-ended", "storyId": "STORY-2", "attemptId": "3b4726c7-ae32-4dd2-bcbe-3d22d0869c6c", "durationMs": 370293, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "6bb9e8de-2815-4be6-9dcf-1aa1c29e90ff"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:11:58.491Z", "type": "phase-ended", "storyId": "STORY-2", "phase": "integration-queue", "provider": "codex", "durationMs": 5, "schemaVersion": 1, "id": "0827d220-60ff-42d7-b0ae-67ddc1ed6919", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:11:58.498Z", "type": "phase-ended", "storyId": "STORY-2", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 5, "data": {}, "schemaVersion": 1, "id": "67cd9182-f2be-4ffc-9737-e3f61f13b75c"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:06.888Z", "type": "phase-ended", "storyId": "STORY-2", "attemptId": "f0359aca-3773-4f21-a20b-3acb2cfb1eca", "phase": "waiting-resource", "durationMs": 8396, "schemaVersion": 1, "id": "768a4d7b-b8d0-4dee-807a-a9203cfc38b8", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:07.206Z", "type": "accepted", "storyId": "STORY-2", "schemaVersion": 1, "id": "ffb1d0dd-5936-490b-b8f2-7bacf6c21b0b", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:07.219Z", "type": "phase-ended", "storyId": "STORY-2", "attemptId": "f0359aca-3773-4f21-a20b-3acb2cfb1eca", "phase": "committing", "durationMs": 331, "schemaVersion": 1, "id": "37f32652-4f2b-4369-b0c8-3f2511c65c53", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:07.219Z", "type": "attempt-ended", "storyId": "STORY-2", "attemptId": "f0359aca-3773-4f21-a20b-3acb2cfb1eca", "durationMs": 8727, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "7998cda0-80f9-4492-afd4-adb5bb31a1d4"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:07.222Z", "type": "phase-ended", "storyId": "STORY-2", "phase": "integration", "provider": "codex", "durationMs": 8723, "schemaVersion": 1, "id": "7108da69-0918-4b15-8fc8-f560cc3c6033", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:07.822Z", "type": "phase-ended", "storyId": "STORY-4", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "f90ffab0-99f8-4fc5-91dc-1d5d849b6cbc"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:12:07.823Z", "type": "phase-ended", "storyId": "STORY-4", "attemptId": "4d860ca6-5105-4194-91f2-bf26d85b1253", "phase": "waiting-resource", "durationMs": 6, "schemaVersion": 1, "id": "063a41c5-8f71-4ac9-97b2-cb2cff2f6ba9", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:24.744Z", "type": "phase-ended", "storyId": "STORY-3", "attemptId": "cd20d41c-ba19-4bfe-9510-f8f94aded76a", "phase": "implementing", "durationMs": 696314, "schemaVersion": 1, "id": "b42f9f62-ed9f-494e-8301-30734d1eb4dd", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:29.846Z", "type": "tokens", "storyId": "STORY-3", "attemptId": "cd20d41c-ba19-4bfe-9510-f8f94aded76a", "data": {"inputTokens": 2080455, "outputTokens": 15192, "cachedInputTokens": 1994752, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 3153, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 2080455, "cachedInputTokens": 1994752, "cacheWriteInputTokens": 0, "outputTokens": 15192, "usageAvailable": true, "reasoningOutputTokens": 3153, "costMeasurementComplete": false, "durationMs": 690308, "callId": "97e65260-9a70-4188-941f-45ed107727ae", "routingAttemptId": "9545c3943574500fc80ffd9423a6a916.a927f6503dcd9d2c13017b533f3421b13c4ff21bc458ffaabfc1c05b4bec363a.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "989edf2b-944c-4ea8-9826-9dcbf1cbf15a"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:29.934Z", "type": "phase-ended", "storyId": "STORY-3", "attemptId": "cd20d41c-ba19-4bfe-9510-f8f94aded76a", "phase": "verifying", "durationMs": 5190, "schemaVersion": 1, "id": "19d26f16-a0cf-407a-8c07-fb8c750977d3", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:29.934Z", "type": "attempt-ended", "storyId": "STORY-3", "attemptId": "cd20d41c-ba19-4bfe-9510-f8f94aded76a", "durationMs": 701653, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "7abfc6ce-326c-4eda-ac95-c9700764ea87"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:29.936Z", "type": "phase-ended", "storyId": "STORY-3", "phase": "integration-queue", "provider": "codex", "durationMs": 2, "schemaVersion": 1, "id": "66e2ce61-86a0-46d2-b1cd-c12c5c902181", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:29.939Z", "type": "phase-ended", "storyId": "STORY-3", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "235382d7-e483-4fb9-be99-0bd62c81859e"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:38.761Z", "type": "phase-ended", "storyId": "STORY-3", "attemptId": "439e4a16-e859-4fc3-91b3-3993c3d3f8b2", "phase": "waiting-resource", "durationMs": 8825, "schemaVersion": 1, "id": "d7c65108-03a4-497c-bb3b-5a15d941535c", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:39.108Z", "type": "accepted", "storyId": "STORY-3", "schemaVersion": 1, "id": "8473e2c5-039d-4537-9b8d-9622c0385546", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:39.120Z", "type": "phase-ended", "storyId": "STORY-3", "attemptId": "439e4a16-e859-4fc3-91b3-3993c3d3f8b2", "phase": "committing", "durationMs": 359, "schemaVersion": 1, "id": "2e9e960f-e7fa-4c83-857d-169b98f0e8d3", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:39.120Z", "type": "attempt-ended", "storyId": "STORY-3", "attemptId": "439e4a16-e859-4fc3-91b3-3993c3d3f8b2", "durationMs": 9184, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "85c940c1-61b1-47d1-8c52-3f80d5779fd4"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:17:39.123Z", "type": "phase-ended", "storyId": "STORY-3", "phase": "integration", "provider": "codex", "durationMs": 9183, "schemaVersion": 1, "id": "62237fb9-f65a-4d82-b887-652ceaa9e97a", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:33.582Z", "type": "phase-ended", "storyId": "STORY-4", "attemptId": "4d860ca6-5105-4194-91f2-bf26d85b1253", "phase": "implementing", "durationMs": 505759, "schemaVersion": 1, "id": "c771a1a4-cdf0-4579-b9dd-83d7cda27b76", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:37.621Z", "type": "tokens", "storyId": "STORY-4", "attemptId": "4d860ca6-5105-4194-91f2-bf26d85b1253", "data": {"inputTokens": 921789, "outputTokens": 12190, "cachedInputTokens": 857088, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 778, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 921789, "cachedInputTokens": 857088, "cacheWriteInputTokens": 0, "outputTokens": 12190, "usageAvailable": true, "reasoningOutputTokens": 778, "costMeasurementComplete": false, "durationMs": 498279, "callId": "f1b477ed-aeda-4443-9311-77bc05c59cd3", "routingAttemptId": "c1b056a52726e22472796cce09cca213.97440e868440dc339c93f3538b8259b17c3278c13efc041966a3364d30d3a8eb.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "e1afa5e5-9616-41f3-a164-d970f5ab908e"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:37.706Z", "type": "phase-ended", "storyId": "STORY-4", "attemptId": "4d860ca6-5105-4194-91f2-bf26d85b1253", "phase": "verifying", "durationMs": 4124, "schemaVersion": 1, "id": "bfe8dfd5-5dea-4be5-a9d6-8e2611d020de", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:37.706Z", "type": "attempt-ended", "storyId": "STORY-4", "attemptId": "4d860ca6-5105-4194-91f2-bf26d85b1253", "durationMs": 509889, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "55ab2284-9f84-43f3-b8d4-ba5124a9dae5"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:37.707Z", "type": "phase-ended", "storyId": "STORY-4", "phase": "integration-queue", "provider": "codex", "durationMs": 2, "schemaVersion": 1, "id": "27b2e3da-0f39-4d43-bdbe-b2c86238b7fe", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:37.711Z", "type": "phase-ended", "storyId": "STORY-4", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "8c149ad2-ea9b-4613-ae59-0368c69021c7"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.270Z", "type": "phase-ended", "storyId": "STORY-4", "attemptId": "d7d336ea-fca7-47ee-86cf-b9f373196be0", "phase": "waiting-resource", "durationMs": 11562, "schemaVersion": 1, "id": "c8cf60bd-6a03-44c2-96e6-477f5d0e7f6c", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.509Z", "type": "accepted", "storyId": "STORY-4", "schemaVersion": 1, "id": "b559447a-63d2-45f6-b671-d39ab978ec3c", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.524Z", "type": "phase-ended", "storyId": "STORY-4", "attemptId": "d7d336ea-fca7-47ee-86cf-b9f373196be0", "phase": "committing", "durationMs": 254, "schemaVersion": 1, "id": "bf552d4b-1c34-4ed9-819c-d5a0bba98df3", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.524Z", "type": "attempt-ended", "storyId": "STORY-4", "attemptId": "d7d336ea-fca7-47ee-86cf-b9f373196be0", "durationMs": 11816, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "8f1399e7-bc06-4788-919d-fe89268be764"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.527Z", "type": "phase-ended", "storyId": "STORY-4", "phase": "integration", "provider": "codex", "durationMs": 11815, "schemaVersion": 1, "id": "17a9df7b-9d2c-48cd-8b25-130442c4e606", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.681Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "resource-wait-implementation", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "ed439b5b-42fe-4c6d-93a8-82288ae8b30e"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:20:49.683Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "9ccdd47e-b5a9-40fa-a6f2-7cc9a478fe13", "phase": "waiting-resource", "durationMs": 6, "schemaVersion": 1, "id": "9371ba58-6223-4e00-b39c-0030c732d898", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:28:45.424Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "9ccdd47e-b5a9-40fa-a6f2-7cc9a478fe13", "phase": "implementing", "durationMs": 475741, "schemaVersion": 1, "id": "25e06e67-4af7-41c8-acd1-0a5878b23bf7", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:28:51.416Z", "type": "tokens", "storyId": "STORY-5", "attemptId": "9ccdd47e-b5a9-40fa-a6f2-7cc9a478fe13", "data": {"inputTokens": 1042022, "outputTokens": 10937, "cachedInputTokens": 971904, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 891, "calls": [{"role": "worker", "provider": "codex", "profile": "codex-benchmark", "requestedModel": "gpt-6.1-sol", "requestedReasoningEffort": "medium", "inputTokens": 1042022, "cachedInputTokens": 971904, "cacheWriteInputTokens": 0, "outputTokens": 10937, "usageAvailable": true, "reasoningOutputTokens": 891, "costMeasurementComplete": false, "durationMs": 462491, "callId": "3e82a204-5f58-4911-82aa-3b20d59d92c3", "routingAttemptId": "f6ff0fbaff099650713af8e361772407.7af9f824932982db9c38827b35845ae3c9028927bfdc1bc8a1801508a7b9c43f.1"}], "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true, "escalated": false}, "schemaVersion": 1, "id": "fc52efd5-fe4e-4ad9-8e87-e30da6c1717c"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:28:51.500Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "9ccdd47e-b5a9-40fa-a6f2-7cc9a478fe13", "phase": "verifying", "durationMs": 6076, "schemaVersion": 1, "id": "9b68dcd2-8e58-4e6d-94a5-9c5f5dc7a2d6", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:28:51.500Z", "type": "attempt-ended", "storyId": "STORY-5", "attemptId": "9ccdd47e-b5a9-40fa-a6f2-7cc9a478fe13", "durationMs": 481823, "outcome": "worker-ended", "data": {"usageAvailable": true}, "schemaVersion": 1, "id": "2bb733c4-c360-4712-afbe-705dade2a74a"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:28:51.501Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "integration-queue", "provider": "codex", "durationMs": 2, "schemaVersion": 1, "id": "dfc38893-48fd-4e66-a577-f8078aa6a7d8", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:28:51.504Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "resource-wait-integration", "provider": "codex", "durationMs": 2, "data": {}, "schemaVersion": 1, "id": "c235cff0-365a-4ae0-a258-b6f33d4c4b2a"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:29:09.244Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "206cc04c-2622-481a-8fd2-5b24e1dd893c", "phase": "waiting-resource", "durationMs": 17742, "schemaVersion": 1, "id": "66862f8d-20ce-4cfa-8ffe-a984ac9f5801", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:29:09.539Z", "type": "phase-ended", "storyId": "STORY-5", "attemptId": "206cc04c-2622-481a-8fd2-5b24e1dd893c", "phase": "committing", "durationMs": 295, "schemaVersion": 1, "id": "2ae349bd-943f-4c63-985e-15885c6add64", "data": {}}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:29:09.539Z", "type": "attempt-ended", "storyId": "STORY-5", "attemptId": "206cc04c-2622-481a-8fd2-5b24e1dd893c", "durationMs": 18037, "outcome": "worker-ended", "data": {"usageAvailable": false}, "schemaVersion": 1, "id": "ae0a8b33-6548-4c72-9f2a-a3c9edb85d4c"}
+{"runId": "49ad0044-c2d6-4f1e-a31d-b203c9ded773", "timestamp": "2026-10-04T08:29:09.542Z", "type": "phase-ended", "storyId": "STORY-5", "phase": "integration", "provider": "codex", "durationMs": 18038, "schemaVersion": 1, "id": "b416ccbc-53a4-48df-91a7-98551fcb4d47", "data": {}}
+{"runId": "eb9461dd-0df1-439d-bfee-061432c3ef94", "timestamp": "2026-10-04T07:55:10.045Z", "type": "tokens", "data": {"inputTokens": 26174, "outputTokens": 935, "cachedInputTokens": 7168, "cacheWriteInputTokens": 0, "reasoningOutputTokens": 81, "provider": "codex", "role": "planner", "measurementComplete": true, "costMeasurementComplete": false, "usageAvailable": true}, "durationMs": 40724, "schemaVersion": 1, "id": "8604257c-5078-4c6b-892b-077ba3187f85"}

package/docs/benchmarks/2026-10-04-efficiency/raw/yoke-loop-1.log

@@ -0,0 +1,58 @@
+Commits: Hermann Fischer <HEC_er@web.de> · co-authors: disabled
+Runner: codex · permissions: safe · routing: on · workers: 3 local / 3 shared maximum · isolation: on · cwd: .
+  · parallel 1/3
+  · parallel 1/3
+  · parallel 1/3
+  · route STORY-1: codex-benchmark (implementation: standard; Establishes shared types, exactly 12 seed machines, runnable tooling and shell behavior; downstream stories depend on these contracts. Dependency and configuration changes carry supply-chain risk; existing workspace state is unknown.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-1 implementing…
+  · STORY-1 verifying…
+  · parallel 0/3
+  · integrating STORY-1 waiting-resource…
+  · integrating STORY-1 committing…
+  · integration complete
+  · parallel 0/3
+  · parallel 1/3
+  · parallel 1/3
+  · parallel 2/3
+  · parallel 2/3
+  · parallel 2/3
+  · route STORY-2: codex-benchmark (implementation: strong; Deterministic reducer transitions must coordinate telemetry, histories, incidents, repeated commands and timer cleanup. Incorrect transitions can corrupt simulation state, but the specified local simulation has no external operational effects.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-2 implementing…
+  · parallel 2/3
+  · route STORY-3: codex-benchmark (implementation: strong; SVG topology combines distinctive visual design, accessible nodes, coordinate transforms, pointer gestures and animation states. Interaction logic is executable, while visual distinction and motion quality require inspection; no sensitive data or destructive operations are specified.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-3 implementing…
+  · STORY-2 verifying…
+  · parallel 1/3
+  · integrating STORY-2 waiting-resource…
+  · integrating STORY-2 committing…
+  · integration complete
+  · parallel 1/3
+  · parallel 2/3
+  · parallel 2/3
+  · parallel 2/3
+  · route STORY-4: codex-benchmark (implementation: strong; Several panels must consistently render shared simulation state, telemetry visuals, callbacks and fleet transformations. The inspector criterion says 11 fields while the brief names additional identity/history information, requiring coverage of the explicit field list; controls have local simulated effects.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-4 implementing…
+  · STORY-3 verifying…
+  · parallel 1/3
+  · integrating STORY-3 waiting-resource…
+  · integrating STORY-3 committing…
+  · integration complete
+  · parallel 1/3
+  · STORY-4 verifying…
+  · parallel 0/3
+  · integrating STORY-4 waiting-resource…
+  · integrating STORY-4 committing…
+  · integration complete
+  · parallel 0/3
+  · parallel 1/3
+  · parallel 1/3
+  · parallel 1/3
+  · route STORY-5: codex-benchmark (implementation: strong; Integration coordinates simulation, navigation, selection, incident handling, focus restoration and responsive layout across three dependent stories. Focus and state synchronization failures are consequential for usability; narrow-layout quality is not reliably established by component tests alone.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-5 implementing…
+  · STORY-5 verifying…
+  · parallel 0/3
+  · integrating STORY-5 waiting-resource…
+  · integrating STORY-5 committing…
+  · integration complete
+  · parallel 0/3
+■ blocked on ?: story STORY-5 integration rejected: target HEAD changed from a18e662231d871934f61608797db150f84d0f34c to f84e688f97b02cc9c8763487b6e76006211e2d2a during integrated gates; candidate retained at .yoke/worktrees/c64e9419eb085837e015571a

package/docs/benchmarks/2026-10-04-efficiency/raw/yoke-loop-2.log

@@ -0,0 +1,29 @@
+Commits: Hermann Fischer <HEC_er@web.de> · co-authors: disabled
+Runner: codex · permissions: safe · routing: on · workers: 2 local / 3 shared maximum · isolation: on · cwd: .
+  · parallel 1/2
+  · parallel 1/2
+  · parallel 1/2
+  · route STORY-5: codex-benchmark (implementation: strong; Integration coordinates simulation, navigation, selection, incident handling, focus restoration and responsive layout across three dependent stories. Focus and state synchronization failures are consequential for usability; narrow-layout quality is not reliably established by component tests alone.; 1 verified failure(s), one targeted repair; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-5 implementing…
+  · STORY-5 verifying…
+  · STORY-5 design…
+  · parallel 0/2
+  · integrating STORY-5 waiting-resource…
+  · integrating STORY-5 committing…
+  · integration complete
+  · parallel 0/2
+  · parallel 1/2
+  · parallel 1/2
+  · parallel 1/2
+  · route STORY-6: codex-benchmark (implementation: frontier; Browser verification and defect repair span the entire product, with unknown failures until integration is exercised. Behavioral checks are strong, but screenshot craft requires inspection; broad repair permissions and artifact writes risk regressions or overwriting observer-owned data.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · STORY-6 implementing…
+  · STORY-6 verifying…
+  · STORY-6 design…
+  · STORY-6 verifying…
+  · STORY-6 design…
+  · parallel 0/2
+  · integrating STORY-6 waiting-resource…
+  · integrating STORY-6 committing…
+  · integration complete
+  · parallel 0/2
+✔ loop complete — 6/6

package/docs/benchmarks/2026-10-04-efficiency/raw/yoke-loop-3.log

@@ -0,0 +1,5 @@
+Commits: Hermann Fischer <HEC_er@web.de> · co-authors: disabled
+Runner: codex · permissions: safe · routing: on · workers: 1 local / 3 shared maximum · isolation: on · cwd: .
+■ blocked on ?: change intake blocked by dirty worktree: git worktree is dirty — commit or stash before running the loop
+Loop blocked after 0 iteration(s): 6/7 stories pass
+Reason: change intake blocked by dirty worktree: git worktree is dirty — commit or stash before running the loop

package/docs/benchmarks/2026-10-04-efficiency/raw/yoke-loop-4.log

@@ -0,0 +1,12 @@
+Commits: Hermann Fischer <HEC_er@web.de> · co-authors: disabled
+Runner: codex · permissions: safe · routing: on · workers: 1 local / 3 shared maximum · isolation: on · cwd: .
+▶ STORY-7 (6/7 · 86%) — implementing…
+  · route STORY-7: codex-benchmark (implementation: strong; Repair spans desktop containment, mobile content priority and visual evidence across existing integrated views. Current layout causes are uninspected; responsive changes can regress scrolling, keyboard access and incident visibility. Local simulation limits security and data-loss exposure, but artifact updates must preserve observer-owned measurements.; economic selection unchanged: need 20 recent complete comparable execution sequences for the baseline; incomplete costs and unknown models are excluded from decisions)
+  · codex/gpt-6.1-sol
+Reading prompt from stdin...
+  · verifying…
+  · design…
+  · committing…
+✓ STORY-7 done in 8m23s — 7/7 (100%)
+✔ loop complete — 7/7
+Loop complete after 1 iteration(s): 7/7 stories pass

package/docs/benchmarks/2026-10-04-efficiency/raw/yoke-phases.csv

@@ -0,0 +1,10 @@
+phase,count,seconds
+resource-wait-implementation,8,0.038000000000000006
+waiting-resource,14,97.92699999999999
+implementing,8,3868.892
+verifying,9,74.024
+integration-queue,7,0.019000000000000003
+resource-wait-integration,7,0.017
+committing,8,2.701
+integration,7,99.979
+design,4,14.082

package/docs/benchmarks/2026-10-04-efficiency/regression-comparison.json

@@ -0,0 +1,104 @@
+{
+  "method": "3 paired fresh/repeated target help calls per version, alternating order; each call starts a new Node process",
+  "limits": "Not OS/provider/npm cold/warm cache measurements; no LLM, guardian, approval or full-product speed/cost inference. File reads for snapshots are outside timed calls.",
+  "baseline": "G:\\NN-Developed\\Worktrees\\yoke-1.22-efficiency-baseline",
+  "candidate": "G:\\NN-Developed\\Worktrees\\yoke-1.23-efficiency",
+  "runs": [
+    {
+      "pair": 1,
+      "condition": "fresh-target",
+      "version": "baseline",
+      "milliseconds": 376.805,
+      "changedFiles": 97,
+      "exitCode": 0
+    },
+    {
+      "pair": 1,
+      "condition": "fresh-target",
+      "version": "candidate",
+      "milliseconds": 303.768,
+      "changedFiles": 0,
+      "exitCode": 0
+    },
+    {
+      "pair": 1,
+      "condition": "repeat-target",
+      "version": "baseline",
+      "milliseconds": 390.249,
+      "changedFiles": 1,
+      "exitCode": 0
+    },
+    {
+      "pair": 1,
+      "condition": "repeat-target",
+      "version": "candidate",
+      "milliseconds": 283.96,
+      "changedFiles": 0,
+      "exitCode": 0
+    },
+    {
+      "pair": 2,
+      "condition": "fresh-target",
+      "version": "candidate",
+      "milliseconds": 283.469,
+      "changedFiles": 0,
+      "exitCode": 0
+    },
+    {
+      "pair": 2,
+      "condition": "fresh-target",
+      "version": "baseline",
+      "milliseconds": 396.285,
+      "changedFiles": 97,
+      "exitCode": 0
+    },
+    {
+      "pair": 2,
+      "condition": "repeat-target",
+      "version": "candidate",
+      "milliseconds": 276.348,
+      "changedFiles": 0,
+      "exitCode": 0
+    },
+    {
+      "pair": 2,
+      "condition": "repeat-target",
+      "version": "baseline",
+      "milliseconds": 345.871,
+      "changedFiles": 1,
+      "exitCode": 0
+    },
+    {
+      "pair": 3,
+      "condition": "fresh-target",
+      "version": "baseline",
+      "milliseconds": 396.646,
+      "changedFiles": 97,
+      "exitCode": 0
+    },
+    {
+      "pair": 3,
+      "condition": "fresh-target",
+      "version": "candidate",
+      "milliseconds": 277.688,
+      "changedFiles": 0,
+      "exitCode": 0
+    },
+    {
+      "pair": 3,
+      "condition": "repeat-target",
+      "version": "baseline",
+      "milliseconds": 364.275,
+      "changedFiles": 1,
+      "exitCode": 0
+    },
+    {
+      "pair": 3,
+      "condition": "repeat-target",
+      "version": "candidate",
+      "milliseconds": 282.323,
+      "changedFiles": 0,
+      "exitCode": 0
+    }
+  ]
+}

package/docs/superpowers/plans/2026-10-04-yoke-1.23-efficiency-prd.json

@@ -0,0 +1,11 @@
+[
+  {"id":"E1","title":"Read-only help and early flag validation","priority":1,"passes":false,"acceptance":[{"id":"cli-help","text":"Help preserves target bytes; unknown and conflicting flags fail before dispatch; recovery flags remain valid.","verify":["npm test -- tests/cli-help.test.ts"]},{"id":"cli-entry","text":"Installed and direct CLI entrypoints retain dispatch compatibility.","verify":["npm test -- tests/cli-entry.test.ts"]}]},
+  {"id":"E2","title":"Ignore supervision without hiding user changes","priority":2,"passes":false,"acceptance":[{"id":"gitignore","text":"Supervision ignore is idempotent; tracked runtime files are diagnosed without index mutation.","verify":["npm test -- tests/retrofit/gitignore.test.ts"]},{"id":"git","text":"Runtime noise remains distinguished from source and user modifications.","verify":["npm test -- tests/loop/git.test.ts"]}]},
+  {"id":"E3","title":"Truthful compact parallel status","priority":3,"passes":false,"acceptance":[{"id":"loop-status-render","text":"Active workers, integration and waiting states render deterministically without undefined.","verify":["npm test -- tests/loop/loop-status-render.test.ts"]},{"id":"parallel-status-regressions","text":"Clearing integration status does not claim successful integration.","verify":["npm test -- tests/loop/parallel-status-regressions.test.ts"]}]},
+  {"id":"E4","title":"Browser launch causes and server identity","priority":4,"passes":false,"acceptance":[{"id":"command","text":"Browser failures retain redacted causes; production requires pinned served-source identity and rejects foreign servers.","verify":["npm test -- tests/smoke/command.test.ts"]},{"id":"journeys","text":"Multi-step journeys and existing source-bound smoke evidence remain enforced.","verify":["npm test -- tests/smoke/journeys.test.ts"]}]},
+  {"id":"E5","title":"Operative tool preflight","priority":5,"passes":false,"acceptance":[{"id":"preflight","text":"Read-only preflight separates configuration, availability and unverified host activation.","verify":["npm test -- tests/code-intelligence/preflight.test.ts"]},{"id":"codex-rtk-hook","text":"Native RTK schema is used without duplicate legacy hooks or deletion of foreign hooks.","verify":["npm test -- tests/retrofit/codex-rtk-hook.test.ts"]},{"id":"mcp-client","text":"MCP deadlines and shutdown are bounded, including native Windows cleanup.","verify":["npm test -- tests/code-intelligence/mcp-client.test.ts"]}]},
+  {"id":"E6","title":"Retain proofs and reject dirty completion","priority":6,"passes":false,"acceptance":[{"id":"retained-proof","text":"Hashed source/config/environment-bound evidence survives cleanup; escapes and corruption block integration.","verify":["npm test -- tests/loop/retained-proof.test.ts"]},{"id":"completion-hygiene","text":"Serial and parallel completion changes are preserved and block success rather than being auto-committed.","verify":["npm test -- tests/loop/completion-hygiene.test.ts"]}]},
+  {"id":"E7","title":"Actual write scopes and isolated caches","priority":7,"passes":false,"acceptance":[{"id":"cache-isolation","text":"Shared writable runtime caches are blocked before gates; package-level pnpm links remain allowed.","verify":["npm test -- tests/loop/cache-isolation.test.ts"]},{"id":"retained-proof","text":"Candidate diffs reject undeclared writes, sibling collisions and post-rebase gate drift.","verify":["npm test -- tests/loop/retained-proof.test.ts"]}]},
+  {"id":"E8","title":"Local usage and time coverage","priority":8,"passes":false,"acceptance":[{"id":"local-report","text":"Coverage, deduplication, partial usage, interval sums/unions and failure roles retain unknown values.","verify":["npm test -- tests/observability/local-report.test.ts"]},{"id":"cli-observability","text":"Local usage and tool diagnostics require no model call or target mutation.","verify":["npm test -- tests/cli-observability.test.ts"]}]},
+  {"id":"E9","title":"Regression and release evidence","priority":9,"passes":false,"needs":["E1","E2","E3","E4","E5","E6","E7","E8"],"acceptance":[{"id":"metadata","text":"Release metadata discovery and README synchronization stay deterministic.","verify":["npm test -- tests/release/metadata.test.ts"]},{"id":"command","text":"Served-source identity is checked before browser launch and after journeys.","verify":["npm test -- tests/smoke/command.test.ts"]}]}
+]

package/docs/superpowers/plans/2026-10-04-yoke-1.23-efficiency.md

@@ -0,0 +1,83 @@
+# Yoke 1.23.0 Implementation Plan
+
+> For agentic workers: Use the local `subagent-driven-development` workflow for explicitly scoped independent modules. Do not start nested agents from workers. Root performs integration and dispatches independent read-only review.
+
+**Goal:** Implement the user-approved E1–E9 acceptance contracts in the [design](../specs/2026-10-04-yoke-1.23-efficiency-design.md).
+
+**Architecture:** Reuse CLI dispatch, reporter, telemetry, candidate/recovery and evidence modules. Changes remain additive except correcting unsafe help and misleading diagnostics. Source/HEAD gates remain authoritative.
+
+**Tech Stack:** TypeScript, Node stdlib, Vitest, existing Yoke canon/configuration.
+
+Execution record: E1–E6 production changes and E7 conventional-cache/write guards are implemented; E8 local reporting is implemented with unknown production classification coverage. Independent review found no remaining code/security blockers. The [validation record](../../RELEASE-VALIDATION-1.23.0.md) identifies unfulfilled acceptance items, including real cold/warm measurements, installer-specific guarantees and a new populated NEXUS layout run. Unchecked items below remain open; implementation does not imply full E1–E9 completion.
+
+Baseline: commit 9007c35; offline npm ci installed 53 packages. Focused baseline: 48 passing tests. Full-suite baseline and final verification must be recorded. User changes in G:/NN-Developed/Yoke are outside this worktree.
+
+## Task 1 — CLI and runtime hygiene (root ownership)
+
+Files: `src/cli.ts`, `src/retrofit/gitignore.ts`, `tests/cli-help.test.ts`, `tests/retrofit/gitignore.test.ts`.
+
+- [ ] RED: add real temporary-directory tests for setup/retrofit help, unknown flags, incompatible flags, no mutation and no dispatch. Snapshot directory bytes, not only counts.
+- [ ] RED: assert generated ignores contain `.yoke/supervision/`, actual Git ignores its runtime file, and user files remain dirty.
+- [ ] Run `rtk vitest run tests/cli-help.test.ts tests/retrofit/gitignore.test.ts`; inspect expected behavior failures.
+- [ ] GREEN: guard help before dispatch; validate mutating command flags before execution, reuse usage text. Add only missing supervision ignore entry.
+- [ ] Run same tests plus existing CLI/setup/retrofit suites. Commit only assigned files.
+
+Core regression assertion:
+```ts
+expect(await main(['setup', dir, '--help'])).toBe(0)
+expect(snapshot(dir)).toEqual(before)
+```
+
+## Task 2 — Status and browser failures (root ownership)
+
+Files: `src/loop/run-command.ts`, `src/loop/reporter.ts`, `src/smoke/command.ts`, existing status/smoke tests.
+
+- [ ] RED: parallel worker/integrator/wait states render without undefined; clearing integrator does not announce success.
+- [ ] RED: target-local installed Playwright throws binary/permission/unknown errors; diagnostics preserve redacted cause and never claim package absence.
+- [ ] Run `rtk vitest run tests/loop/loop-status-render.test.ts tests/loop/parallel-status-regressions.test.ts tests/smoke/command.test.ts`.
+- [ ] GREEN: deterministic additive compact fields and accurate terminal messages; distinguish resolution from launch, keep injected null-launch compatibility.
+- [ ] Run status/reporter/smoke suites and typecheck. Commit assigned changes.
+
+Core regression assertions:
+```ts
+expect(loopStatus(dir, now, { compact: true })).toContain('S1:implementing')
+expect(loopStatus(dir, now, { compact: true })).not.toContain('undefined')
+```
+
+## Task 3 — RTK and code-intelligence (tools worker ownership)
+
+Files: `src/retrofit/planners/codex.ts`, `canon/tools/codex-rtk-hook.mjs`, `src/code-intelligence/`, related tests; existing preflight modules as agreed with root.
+
+- [ ] Inspect current implementation and record exact remaining gaps; existing behavior is not rewritten.
+- [ ] RED: native/idempotent hook registration preserves unrelated hooks; real tool schema rewrite; configured workspace identifier resolves, foreign identifier rejects; missing backends explicitly degraded.
+- [ ] GREEN with Node stdlib/current modules; no package installation or external config mutation.
+- [ ] Run targeted planner/hook/backend/MCP tests and typecheck; return RED/GREEN commands and remaining limits.
+
+## Task 4 — Proofs, recovery, scopes and caches (integration worker ownership)
+
+Files: `src/loop/` excluding reporter/run-command/evidence, candidate cleanup/recovery/worker/parallel adapters, related integration tests. New isolated artifact helper permitted; coordinate any shared type edits first.
+
+- [ ] Inspect actual scope/caching/recovery behavior; record existing guarantees.
+- [ ] RED: proof survives integration/cleanup and hash mismatch fails; traversal/symlink rejects; unchanged recovery candidate rechecks gates; unexpected writes and sibling collision cannot silently integrate; caches cannot write into target runtime directories.
+- [ ] GREEN with existing fingerprints/locks/recovery APIs. Preserve candidates on evidence-copy failure; no root-level source commits or permissive sandbox changes.
+- [ ] Run targeted candidate/recovery/parallel/completion tests and typecheck; return exact contracts implemented and any blocked acceptance.
+
+## Task 5 — Usage/time coverage (telemetry worker ownership)
+
+Files: `src/agents/telemetry.ts`, related provider telemetry/types/events modules, new local report module and telemetry tests; no reporter.ts changes without root coordination.
+
+- [ ] RED: roles/attempts and coverage distinguish unknown approvals, deduplicate parent/child usage, input includes cache, reasoning is not added twice, missing prices remain unknown.
+- [ ] RED: overlapping interval union differs from sum; observer/infrastructure/product failures separated; status report reads local data without model calls.
+- [ ] GREEN: expose additive local report and usable entrypoint coordinated with root. No proprietary session discovery or secret content collection.
+- [ ] Run telemetry/event/report suites and typecheck; return new output contract and coverage limits.
+
+## Task 6 — Integrated acceptance and release (root plus independent reviewer)
+
+- [ ] Run whole suite, lint/build, docs/package and dependency checks; retain complete reports where output compaction hides details.
+- [ ] Run deterministic before/after regression benchmark with at least three cold/warm paired samples; distinguish harness regression experiment from authenticated full-product speed comparison. No new paid model benchmark authorized by this plan.
+- [ ] Check copied NEXUS populated-state layout acceptance and server identity evidence; avoid changing observer-owned originals.
+- [ ] Independent read-only spec review and code/security review; implementer cannot claim independent self-review or merge.
+- [ ] Synchronize release version/manifests/README/changelog only after implementation checks. Release notes explicitly name any full-product comparison not run.
+- [ ] Commit complete changes, prepare reviewable PR if host tooling supports it; never claim published without CI/npm evidence.
+
+Each worker records RED before production edits and owns only its module. All workers share this checkout; no worker reverts others' edits or commits another worker's files. Root coordinates collisions and executes final verification after workers finish.