{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 50}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1117.9642857142858, "latency_ms_mean": 0.005923982306350288, "latency_ms_p50": 0.005291993147693574, "mrr": 0.5752976190476191, "ndcg_at_k": 0.575437744798732, "precision_at_k": 0.1392857142857143, "recall_at_k": 0.6517857142857143}, "mode": "eval", "num_queries": 56, "reliability": 86.07, "run": "2026-06-24T22:14:59Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": {"baseline": "tag", "delta": {"context_tokens_mean": 2655.0714285714284, "latency_ms_mean": 2.2753645909168494, "latency_ms_p50": 2.264604496303946, "mrr": 0.3687499999999999, "ndcg_at_k": 0.36858670534433735, "precision_at_k": 0.0785714285714286, "recall_at_k": 0.3303571428571428}, "treatment": "bm25"}, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 50}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3773.035714285714, "latency_ms_mean": 2.2810275534409032, "latency_ms_p50": 2.2696249943692237, "mrr": 0.944047619047619, "ndcg_at_k": 0.9440244501430693, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "ablate", "num_queries": 56, "reliability": 99.29, "run": "2026-06-24T22:15:00Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 63}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3773.035714285714, "latency_ms_mean": 2.2421219465676194, "latency_ms_p50": 2.222791503299959, "mrr": 0.944047619047619, "ndcg_at_k": 0.9440244501430693, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-24T22:21:33Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 71}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3787.6071428571427, "latency_ms_mean": 2.3354829640343917, "latency_ms_p50": 2.306958500412293, "mrr": 0.9464285714285714, "ndcg_at_k": 0.9436900690556803, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-24T22:28:31Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 71}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3787.6071428571427, "latency_ms_mean": 2.4155431079374727, "latency_ms_p50": 2.398500007984694, "mrr": 0.9464285714285714, "ndcg_at_k": 0.9436900690556803, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-24T22:31:15Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 71}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3787.6071428571427, "latency_ms_mean": 2.4154546255366376, "latency_ms_p50": 2.4053329980233684, "mrr": 0.9464285714285714, "ndcg_at_k": 0.9436900690556803, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-24T22:31:21Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 84}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3787.6071428571427, "latency_ms_mean": 2.4190654629429837, "latency_ms_p50": 2.4056659967754968, "mrr": 0.9464285714285714, "ndcg_at_k": 0.9436900690556803, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-24T22:34:29Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 90}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3798.0714285714284, "latency_ms_mean": 2.499385410244161, "latency_ms_p50": 2.4919164934544824, "mrr": 0.9464285714285714, "ndcg_at_k": 0.9436900690556803, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-24T22:38:30Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 99}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3807.6964285714284, "latency_ms_mean": 2.582801303495736, "latency_ms_p50": 2.5506664969725534, "mrr": 0.9464285714285714, "ndcg_at_k": 0.9436900690556803, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-24T22:43:48Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 99}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3802.125, "latency_ms_mean": 2.78333119526256, "latency_ms_p50": 2.723395504290238, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:45:48Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3802.125, "latency_ms_mean": 2.637776035823793, "latency_ms_p50": 2.610103998449631, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:49:56Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3802.125, "latency_ms_mean": 2.6437878204887966, "latency_ms_p50": 2.6439165012561716, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:50:03Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3746.964285714286, "latency_ms_mean": 2.7187001251149923, "latency_ms_p50": 2.6972499981638975, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:52:10Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3746.964285714286, "latency_ms_mean": 2.711520072157977, "latency_ms_p50": 2.6884789986070246, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:53:21Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3746.964285714286, "latency_ms_mean": 2.7119501618082205, "latency_ms_p50": 2.7041040011681616, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:55:44Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3746.964285714286, "latency_ms_mean": 2.7578712147910016, "latency_ms_p50": 2.7443124999990687, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:55:49Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3746.964285714286, "latency_ms_mean": 2.76548733875513, "latency_ms_p50": 2.7551250022952445, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T22:57:26Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1164.9642857142858, "latency_ms_mean": 0.007328072440161902, "latency_ms_p50": 0.00650000583846122, "mrr": 0.5738095238095238, "ndcg_at_k": 0.5741998261928998, "precision_at_k": 0.1392857142857143, "recall_at_k": 0.6517857142857143}, "mode": "eval", "num_queries": 56, "reliability": 86.07, "run": "2026-06-24T22:57:31Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1164.9642857142858, "latency_ms_mean": 0.007400214599329047, "latency_ms_p50": 0.00666698906570673, "mrr": 0.5738095238095238, "ndcg_at_k": 0.5741998261928998, "precision_at_k": 0.1392857142857143, "recall_at_k": 0.6517857142857143}, "mode": "eval", "num_queries": 56, "reliability": 86.07, "run": "2026-06-24T22:57:39Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3746.964285714286, "latency_ms_mean": 2.81057657204136, "latency_ms_p50": 2.7581874965108, "mrr": 0.9470238095238095, "ndcg_at_k": 0.9505981548991542, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:00:08Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3883.2321428571427, "latency_ms_mean": 2.937471713396787, "latency_ms_p50": 2.925687498645857, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:03:20Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3883.2321428571427, "latency_ms_mean": 3.1140468204934484, "latency_ms_p50": 3.036958492884878, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:03:28Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "5b9e4b4", "committed": "2026-06-24T19:25:06Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3883.2321428571427, "latency_ms_mean": 2.965697947209784, "latency_ms_p50": 2.948937501059845, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:05:00Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agent): failure handling with web search and knowledge base lookups", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "2f2c106", "committed": "2026-06-24T23:11:31Z", "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3883.2321428571427, "latency_ms_mean": 2.9814338756425838, "latency_ms_p50": 2.9443544990499504, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:13:16Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agentware): deterministic recall + benchmark spine, live logging, auto-promote", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "2f2c106", "committed": "2026-06-24T23:11:31Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3860.339285714286, "latency_ms_mean": 3.303400178213321, "latency_ms_p50": 3.262562502641231, "mrr": 0.9446428571428571, "ndcg_at_k": 0.9476731953369202, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:34:36Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agentware): deterministic recall + benchmark spine, live logging, auto-promote", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 113}, "commit": "2f2c106", "committed": "2026-06-24T23:11:31Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3860.339285714286, "latency_ms_mean": 3.128557304340315, "latency_ms_p50": 3.117229003692046, "mrr": 0.9446428571428571, "ndcg_at_k": 0.9476731953369202, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-24T23:36:36Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agentware): deterministic recall + benchmark spine, live logging, auto-promote", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 122}, "commit": "f5d0535", "committed": "2026-06-24T23:47:13Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3860.339285714286, "latency_ms_mean": 3.150897339894852, "latency_ms_p50": 3.144145492115058, "mrr": 0.9446428571428571, "ndcg_at_k": 0.9476731953369202, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:13:20Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agents): retrieval methods attached to both agents allso removed reviewer agent", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 122}, "commit": "f5d0535", "committed": "2026-06-24T23:47:13Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3860.339285714286, "latency_ms_mean": 3.5201933564426975, "latency_ms_p50": 3.511563001666218, "mrr": 0.9446428571428571, "ndcg_at_k": 0.9476731953369202, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:14:58Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agents): retrieval methods attached to both agents allso removed reviewer agent", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 122}, "commit": "f5d0535", "committed": "2026-06-24T23:47:13Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3860.339285714286, "latency_ms_mean": 3.5027902132631943, "latency_ms_p50": 3.497291494568344, "mrr": 0.9446428571428571, "ndcg_at_k": 0.9476731953369202, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:17:40Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agents): retrieval methods attached to both agents allso removed reviewer agent", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 128}, "commit": "f5d0535", "committed": "2026-06-24T23:47:13Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3860.339285714286, "latency_ms_mean": 3.538395839703818, "latency_ms_p50": 3.531791502609849, "mrr": 0.9446428571428571, "ndcg_at_k": 0.9476731953369202, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:18:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agents): retrieval methods attached to both agents allso removed reviewer agent", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 128}, "commit": "f5d0535", "committed": "2026-06-24T23:47:13Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3850.5535714285716, "latency_ms_mean": 3.7272478210590116, "latency_ms_p50": 3.7067505036247894, "mrr": 0.9425595238095238, "ndcg_at_k": 0.942786531537237, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T01:21:48Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agents): retrieval methods attached to both agents allso removed reviewer agent", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 128}, "commit": "f5d0535", "committed": "2026-06-24T23:47:13Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3850.5535714285716, "latency_ms_mean": 3.6816518032927497, "latency_ms_p50": 3.670625497761648, "mrr": 0.9425595238095238, "ndcg_at_k": 0.942786531537237, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T01:23:39Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(agents): retrieval methods attached to both agents allso removed reviewer agent", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 133}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3850.5535714285716, "latency_ms_mean": 3.74653425049993, "latency_ms_p50": 3.728063005837612, "mrr": 0.9425595238095238, "ndcg_at_k": 0.942786531537237, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T01:41:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 138}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3850.5535714285716, "latency_ms_mean": 3.7132953743171777, "latency_ms_p50": 3.7050835016998462, "mrr": 0.9425595238095238, "ndcg_at_k": 0.942786531537237, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T01:45:32Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 144}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3750.4285714285716, "latency_ms_mean": 3.8005855889683255, "latency_ms_p50": 3.7964790026308037, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:50:19Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 144}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3763.3214285714284, "latency_ms_mean": 3.957310321701308, "latency_ms_p50": 3.9514160016551614, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:51:51Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 149}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3763.3214285714284, "latency_ms_mean": 4.068527516990018, "latency_ms_p50": 4.058562495629303, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:56:15Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 149}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3741.089285714286, "latency_ms_mean": 4.2492439824854955, "latency_ms_p50": 4.190395506157074, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T01:58:20Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 153}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3741.089285714286, "latency_ms_mean": 4.355214303359389, "latency_ms_p50": 4.27354149724124, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9470222049795459, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9910714285714286}, "mode": "eval", "num_queries": 56, "reliability": 99.64, "run": "2026-06-25T02:05:55Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 160}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3738.785714285714, "latency_ms_mean": 4.6341763037552095, "latency_ms_p50": 4.6188539927243255, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:16:47Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 160}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.551082590166645, "latency_ms_p50": 4.5371669984888285, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:20:50Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 160}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.5580967328403075, "latency_ms_p50": 4.5583540049847215, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:23:00Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 160}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.538389213589004, "latency_ms_p50": 4.547854492557235, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:24:59Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 160}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.613016501285268, "latency_ms_p50": 4.595792001055088, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:25:17Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 160}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.609378035768584, "latency_ms_p50": 4.598937499395106, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:26:53Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 167}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.780119053196229, "latency_ms_p50": 4.7449994963244535, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:47:23Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 167}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3742.3035714285716, "latency_ms_mean": 4.765163696772236, "latency_ms_p50": 4.750000000058208, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:47:43Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 178}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3760.0535714285716, "latency_ms_mean": 5.081799874720413, "latency_ms_p50": 5.036791495513171, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:53:11Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 182}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3789.4821428571427, "latency_ms_mean": 4.726743965095791, "latency_ms_p50": 4.7184169889078476, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T02:58:05Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 182}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3700.8571428571427, "latency_ms_mean": 4.783364661177204, "latency_ms_p50": 4.7691869986010715, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T03:02:20Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 182}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3711.6428571428573, "latency_ms_mean": 4.86489212536461, "latency_ms_p50": 4.877583000052255, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T03:21:11Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 182}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1218.482142857143, "latency_ms_mean": 0.009237412866371284, "latency_ms_p50": 0.00825000461190939, "mrr": 0.5639880952380952, "ndcg_at_k": 0.5668267190988391, "precision_at_k": 0.1392857142857143, "recall_at_k": 0.6517857142857143}, "mode": "eval", "num_queries": 56, "reliability": 86.07, "run": "2026-06-25T03:21:22Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 182}, "commit": "acdd14f", "committed": "2026-06-25T01:34:56Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3711.6428571428573, "latency_ms_mean": 4.935401052404943, "latency_ms_p50": 4.912124997645151, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T03:23:17Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(indexing): rebuildable index from logs and data as source of truth", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 206}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3711.6428571428573, "latency_ms_mean": 4.828985928595232, "latency_ms_p50": 4.783666496223304, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:25:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 206}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3711.6428571428573, "latency_ms_mean": 5.197139911095811, "latency_ms_p50": 5.139562505064532, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:25:41Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 217}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3690.3571428571427, "latency_ms_mean": 4.919101198798411, "latency_ms_p50": 4.900563006231096, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9512578784218547, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:32:28Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 229}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3690.3571428571427, "latency_ms_mean": 4.904089196445836, "latency_ms_p50": 4.882666500634514, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9512578784218547, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:36:43Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 247}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3690.3571428571427, "latency_ms_mean": 4.82561160840435, "latency_ms_p50": 4.823437498998828, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9512578784218547, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:44:49Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": {"baseline": "bm25", "delta": {"context_tokens_mean": -35.553571428571104, "latency_ms_mean": 0.04012278519179979, "latency_ms_p50": 0.046999492042232305, "mrr": 0.0, "ndcg_at_k": 0.0, "precision_at_k": 0.0, "recall_at_k": 0.0}, "treatment": "bm25+acr"}, "acr_gate": {"checks": {"age_stratum": {"old_age_days": 90, "old_count": 0, "old_ndcg_baseline": 0.0, "old_ndcg_treatment": 0.0, "passed": true, "recent_count": 56}, "no_harm": {"determinism_ok": true, "latency_p50": {"baseline": 4.787604011653457, "budget_ms": 10.0, "passed": true, "treatment": 4.834603503695689}, "mrr": {"baseline": 0.9425595238095238, "passed": true, "treatment": 0.9425595238095238}, "passed": true, "recall": {"baseline": 1.0, "passed": true, "treatment": 1.0}}, "primary": {"delta_ndcg": 0.0, "margin": 0.01, "passed": false}, "significance": {"alpha": 0.05, "df": 55, "mean_delta": 0.0, "n": 56, "passed": false, "t": 0.0, "t_crit": 2.009}, "win_rate": {"improved": 0, "passed": false, "regressed": 0, "ties": 56}}, "decided_strategy": "bm25", "params": {"alpha": 0.05, "latency_budget_ms": 10.0, "margin": 0.01, "mrr_eps": 0.0, "old_age_days": 90, "recall_eps": 0.0, "stratum_eps": 1e-09}, "passed": false}, "as_of": "2026-06-25", "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 255}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3654.8035714285716, "latency_ms_mean": 4.894943446613199, "latency_ms_p50": 4.834603503695689, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9512578784218547, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "acr-gate", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:50:44Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 255}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3690.3571428571427, "latency_ms_mean": 4.966802052097462, "latency_ms_p50": 4.96543750341516, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9512578784218547, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:51:30Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 255}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3664.8571428571427, "latency_ms_mean": 5.204678608216844, "latency_ms_p50": 5.194479497731663, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T04:58:21Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 255}, "commit": "35190d5", "committed": "2026-06-25T04:17:03Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3664.8571428571427, "latency_ms_mean": 5.315256017378748, "latency_ms_p50": 5.276729505567346, "mrr": 0.9425595238095238, "ndcg_at_k": 0.9517377071683422, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T05:00:43Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(doc): onboarding to include knowledge base autocommit ON recommended with opt out", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.996078431372549, "tests_failed": 1, "tests_ran": 255}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3799.160714285714, "latency_ms_mean": 5.325559552927318, "latency_ms_p50": 5.301042001519818, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 99.88, "run": "2026-06-25T05:29:27Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 256}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3799.160714285714, "latency_ms_mean": 5.33874103582223, "latency_ms_p50": 5.339250004908536, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T05:30:43Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 256}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1279.0892857142858, "latency_ms_mean": 0.008976911236199417, "latency_ms_p50": 0.008146002073772252, "mrr": 0.5520833333333334, "ndcg_at_k": 0.5578981476702677, "precision_at_k": 0.1392857142857143, "recall_at_k": 0.6517857142857143}, "mode": "eval", "num_queries": 56, "reliability": 86.07, "run": "2026-06-25T05:30:54Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 256}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3799.160714285714, "latency_ms_mean": 5.259185303657432, "latency_ms_p50": 5.228146001172718, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T05:32:12Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 256}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3785.035714285714, "latency_ms_mean": 5.359028393805992, "latency_ms_p50": 5.346958496375009, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T06:05:38Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 261}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3785.035714285714, "latency_ms_mean": 5.3853192319885625, "latency_ms_p50": 5.374791500798892, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T06:09:28Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 261}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3784.0, "latency_ms_mean": 5.735674214520259, "latency_ms_p50": 5.720458488212898, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T06:26:02Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 261}, "commit": "42c8822", "committed": "2026-06-25T05:07:37Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3784.0, "latency_ms_mean": 5.833097429006427, "latency_ms_p50": 5.818166508106515, "mrr": 0.944047619047619, "ndcg_at_k": 0.9529756257741744, "precision_at_k": 0.22500000000000003, "recall_at_k": 1.0}, "mode": "eval", "num_queries": 56, "reliability": 100.0, "run": "2026-06-25T06:27:58Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(acr): authority confidence reranked items for better search with time bias", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 271}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/longmemeval/longmemeval_s_cleaned.json", "metrics": {"latency_ms_mean": 10.59455399103017, "latency_ms_p50": 10.606416006339714, "mrr": 0.9103777978731046, "ndcg_at_k": 0.8830615827171846, "precision_at_k": 0.33276595744680854, "recall_at_k": 0.9140425531914894}, "mode": "eval", "num_queries": 470, "reliability": 96.56, "run": "2026-06-25T08:19:48Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": "longmemeval", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 271}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3800.785714285714, "latency_ms_mean": 6.636690467400642, "latency_ms_p50": 6.584458504221402, "mrr": 0.9352678571428571, "ndcg_at_k": 0.9354369651044034, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-25T08:20:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 271}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3800.785714285714, "latency_ms_mean": 6.802591586165363, "latency_ms_p50": 6.750624990672804, "mrr": 0.9352678571428571, "ndcg_at_k": 0.9354369651044034, "precision_at_k": 0.2178571428571429, "recall_at_k": 0.9732142857142857}, "mode": "eval", "num_queries": 56, "reliability": 98.93, "run": "2026-06-25T08:21:50Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 285}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4150.767857142857, "latency_ms_mean": 8.95450073169611, "latency_ms_p50": 8.960125007433817, "mrr": 0.9343750000000001, "ndcg_at_k": 0.9388900715674471, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T08:49:11Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 285}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4150.767857142857, "latency_ms_mean": 9.075471658953964, "latency_ms_p50": 9.081750002223998, "mrr": 0.9343750000000001, "ndcg_at_k": 0.9388900715674471, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T08:50:13Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 299}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4087.089285714286, "latency_ms_mean": 8.203248517799823, "latency_ms_p50": 8.18106198858004, "mrr": 0.9433035714285715, "ndcg_at_k": 0.9454806116822425, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T08:58:28Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 299}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4087.089285714286, "latency_ms_mean": 8.239922625632191, "latency_ms_p50": 8.206312500988133, "mrr": 0.9433035714285715, "ndcg_at_k": 0.9454806116822425, "precision_at_k": 0.22142857142857145, "recall_at_k": 0.9821428571428571}, "mode": "eval", "num_queries": 56, "reliability": 99.29, "run": "2026-06-25T08:59:13Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 312}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4029.285714285714, "latency_ms_mean": 8.239586286695808, "latency_ms_p50": 8.218646005843766, "mrr": 0.9393069727891156, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T09:09:11Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.8825503355704698, "tests_failed": 35, "tests_ran": 298}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4029.285714285714, "latency_ms_mean": 8.235761822496508, "latency_ms_p50": 8.19072850572411, "mrr": 0.9393069727891156, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 94.69, "run": "2026-06-25T09:09:41Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 312}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4029.285714285714, "latency_ms_mean": 8.361814641310568, "latency_ms_p50": 8.350833508302458, "mrr": 0.9393069727891156, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T09:10:51Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 323}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3984.339285714286, "latency_ms_mean": 8.279288680309296, "latency_ms_p50": 8.269999991171062, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T09:22:15Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 323}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3984.339285714286, "latency_ms_mean": 8.470238069483978, "latency_ms_p50": 8.444353996310383, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T09:23:28Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3984.339285714286, "latency_ms_mean": 8.31223071353244, "latency_ms_p50": 8.303270995384082, "mrr": 0.9390589569160998, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T09:37:44Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3984.339285714286, "latency_ms_mean": 8.576424107429505, "latency_ms_p50": 8.547479505068623, "mrr": 0.9390589569160998, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T09:39:01Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "e8cb9c5", "committed": "2026-06-25T06:37:05Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3984.339285714286, "latency_ms_mean": 8.63963323198342, "latency_ms_p50": 8.6490834801225, "mrr": 0.9390589569160998, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T10:49:33Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(autocommit-message-fix): agentware-autocommit-message-derivation, agentware-init", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "42d58a0", "committed": "2026-06-25T15:34:24Z", "dirty": false, "gold_path": "benchmarks/longmemeval/longmemeval_s_cleaned.json", "metrics": {"latency_ms_mean": 10.522725419116583, "latency_ms_p50": 10.51206249394454, "mrr": 0.9103777978731046, "ndcg_at_k": 0.8830615827171846, "precision_at_k": 0.33276595744680854, "recall_at_k": 0.9140425531914894}, "mode": "eval", "num_queries": 470, "reliability": 96.56, "run": "2026-06-25T15:34:44Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmark): LongMemEval scorer + Mode A baseline + public repro docs", "suite": "longmemeval", "top_k": 5}
{"ablation": {"baseline": "tag", "delta": {"context_tokens_mean": 2547.3035714285716, "latency_ms_mean": 8.596950875861305, "latency_ms_p50": 8.544041513232514, "mrr": 0.41371173469387745, "ndcg_at_k": 0.40848740988791643, "precision_at_k": 0.08214285714285713, "recall_at_k": 0.3392857142857143}, "treatment": "bm25"}, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "42d58a0", "committed": "2026-06-25T15:34:24Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3947.9821428571427, "latency_ms_mean": 8.60752301845683, "latency_ms_p50": 8.553874504286796, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "ablate", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T16:53:03Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmark): LongMemEval scorer + Mode A baseline + public repro docs", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 332}, "commit": "42d58a0", "committed": "2026-06-25T15:34:24Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4053.5178571428573, "latency_ms_mean": 9.185296858049696, "latency_ms_p50": 9.186958501231857, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-25T16:58:10Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmark): LongMemEval scorer + Mode A baseline + public repro docs", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9940828402366864, "tests_failed": 2, "tests_ran": 338}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1400.6785714285713, "latency_ms_mean": 0.011607964552240446, "latency_ms_p50": 0.010812495020218194, "mrr": 0.5251488095238096, "ndcg_at_k": 0.5244158851719039, "precision_at_k": 0.13214285714285715, "recall_at_k": 0.6160714285714286}, "mode": "eval", "num_queries": 56, "reliability": 84.47, "run": "2026-06-25T22:37:18Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9940828402366864, "tests_failed": 2, "tests_ran": 338}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4073.285714285714, "latency_ms_mean": 9.015252929592473, "latency_ms_p50": 8.973874995717779, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.04, "run": "2026-06-25T22:42:46Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9940828402366864, "tests_failed": 2, "tests_ran": 338}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4073.285714285714, "latency_ms_mean": 9.267215055712898, "latency_ms_p50": 9.25031201040838, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.04, "run": "2026-06-25T22:44:05Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9940828402366864, "tests_failed": 2, "tests_ran": 338}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4073.285714285714, "latency_ms_mean": 9.41155064148396, "latency_ms_p50": 9.384916498675011, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.04, "run": "2026-06-25T22:44:52Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9943661971830986, "tests_failed": 2, "tests_ran": 355}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4086.410714285714, "latency_ms_mean": 9.41558778504259, "latency_ms_p50": 9.351895496365614, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.05, "run": "2026-06-26T00:22:34Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9455587392550143, "tests_failed": 19, "tests_ran": 349}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4086.410714285714, "latency_ms_mean": 9.337398821246877, "latency_ms_p50": 9.310104491305538, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 96.58, "run": "2026-06-26T00:23:06Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9630606860158312, "tests_failed": 14, "tests_ran": 379}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4086.7678571428573, "latency_ms_mean": 9.62988312624345, "latency_ms_p50": 9.61356250627432, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 97.11, "run": "2026-06-26T01:19:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9630606860158312, "tests_failed": 14, "tests_ran": 379}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4086.7678571428573, "latency_ms_mean": 9.338029928455528, "latency_ms_p50": 9.31852099893149, "mrr": 0.938860544217687, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 97.11, "run": "2026-06-26T01:21:14Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9947643979057592, "tests_failed": 2, "tests_ran": 382}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4086.7678571428573, "latency_ms_mean": 9.975605572565525, "latency_ms_p50": 9.821396000916138, "mrr": 0.9394841269841271, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.06, "run": "2026-06-26T01:30:45Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9947643979057592, "tests_failed": 2, "tests_ran": 382}, "commit": "ef10608", "committed": "2026-06-25T18:26:15Z", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4086.7678571428573, "latency_ms_mean": 9.987049856655565, "latency_ms_p50": 9.949312501703389, "mrr": 0.9394841269841271, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.06, "run": "2026-06-26T01:30:56Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(benchmarks): add reproducible benchmarks results for cross verification", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 409}, "commit": "d4de4b7", "committed": "2026-06-26T01:38:07Z", "corpus_fingerprint": "188c5def18f21e70c5cee48694fb1c962e1d047f65b4e24cadf789a9a47bc519", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4055.339285714286, "latency_ms_mean": 10.362157697402706, "latency_ms_p50": 10.296937995008193, "mrr": 0.9391233766233766, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T02:38:13Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(decisions): autonomous-decisions + plan-authoring", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 409}, "commit": "d4de4b7", "committed": "2026-06-26T01:38:07Z", "corpus_fingerprint": "597823946c4243e1b7ac9b7f7c95fb4aa433060f8f2423707d33cdf99eb9b4a8", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4061.8035714285716, "latency_ms_mean": 10.458780534723441, "latency_ms_p50": 10.445125008118339, "mrr": 0.9391233766233766, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T02:44:24Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(decisions): autonomous-decisions + plan-authoring", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 409}, "commit": "d4de4b7", "committed": "2026-06-26T01:38:07Z", "corpus_fingerprint": "597823946c4243e1b7ac9b7f7c95fb4aa433060f8f2423707d33cdf99eb9b4a8", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4061.8035714285716, "latency_ms_mean": 10.454662230456181, "latency_ms_p50": 10.463500002515502, "mrr": 0.9391233766233766, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T02:44:47Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(decisions): autonomous-decisions + plan-authoring", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 409}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "e456d705c29f5e5b710287fa377437a65fc6497e04bd826d48215ca5a405404c", "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4061.8035714285716, "latency_ms_mean": 10.243135432184706, "latency_ms_p50": 10.270499493344687, "mrr": 0.9391233766233766, "ndcg_at_k": 0.9329032950598203, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T02:59:16Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 490}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "dbf28d84de632b5e7353f60f2784236ffbf25983d93d4dbff91d1d3173767020", "corpus_size": 183, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1485.25, "latency_ms_mean": 0.01684003759042493, "latency_ms_p50": 0.015354497008956969, "mrr": 0.4857783113245298, "ndcg_at_k": 0.47877892341895706, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T08:10:17Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 490}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "dbf28d84de632b5e7353f60f2784236ffbf25983d93d4dbff91d1d3173767020", "corpus_size": 183, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1485.25, "latency_ms_mean": 0.016047572509186075, "latency_ms_p50": 0.01483349478803575, "mrr": 0.4857783113245298, "ndcg_at_k": 0.47877892341895706, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T08:11:00Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 541}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "2d156a880ed84a05415f473c67cf352c66b830c86157d22c2cc5ad5848edea5d", "corpus_size": 203, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1494.267857142857, "latency_ms_mean": 0.016758143569209745, "latency_ms_p50": 0.015187004464678466, "mrr": 0.4850342637054822, "ndcg_at_k": 0.47877892341895706, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T11:58:42Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 545}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "2d156a880ed84a05415f473c67cf352c66b830c86157d22c2cc5ad5848edea5d", "corpus_size": 203, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1494.267857142857, "latency_ms_mean": 0.015740267851275087, "latency_ms_p50": 0.014458000123340753, "mrr": 0.4850342637054822, "ndcg_at_k": 0.47877892341895706, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T13:17:43Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 555}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "fb3b7f35cc6272499cb860aa9a12c41dc34c66d2ec83daee33ffab6ef0bc350b", "corpus_size": 209, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1494.267857142857, "latency_ms_mean": 0.017202375033775752, "latency_ms_p50": 0.01597949994902592, "mrr": 0.4850342637054822, "ndcg_at_k": 0.47877892341895706, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T13:53:20Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 558}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "22cfd2b317e87063f49f8d16e06c4a006592d8be093991ca22aae75bafc69874", "corpus_size": 212, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1493.267857142857, "latency_ms_mean": 0.016523017864398883, "latency_ms_p50": 0.015395500213344349, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T14:07:54Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 437}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "9cc7681d82fad88da8c4ab8fa27f1230caadef49ef7006c892deb447ffc1ff89", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1493.267857142857, "latency_ms_mean": 0.01665478579785226, "latency_ms_p50": 0.015478999557672068, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T15:22:49Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 441}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "2e539dd6824588914d7399d3e2df8da16d9177d5eb7dcb009e97a33d3ae34fef", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1480.2857142857142, "latency_ms_mean": 0.018217285677175305, "latency_ms_p50": 0.017666001440375112, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T15:55:14Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 450}, "commit": "7bdbbc6", "committed": "2026-06-26T16:06:03Z", "corpus_fingerprint": "2e539dd6824588914d7399d3e2df8da16d9177d5eb7dcb009e97a33d3ae34fef", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3993.8928571428573, "latency_ms_mean": 16.215839303770604, "latency_ms_p50": 16.09431249926274, "mrr": 0.9424603174603174, "ndcg_at_k": 0.935095878714498, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T19:08:36Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(multi-loop): fanout multiple loops at once with logical rebase", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 450}, "commit": "7bdbbc6", "committed": "2026-06-26T16:06:03Z", "corpus_fingerprint": "2e539dd6824588914d7399d3e2df8da16d9177d5eb7dcb009e97a33d3ae34fef", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3993.8928571428573, "latency_ms_mean": 16.221573660914146, "latency_ms_p50": 16.16210400061391, "mrr": 0.9424603174603174, "ndcg_at_k": 0.935095878714498, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T19:10:38Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(multi-loop): fanout multiple loops at once with logical rebase", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 450}, "commit": "7bdbbc6", "committed": "2026-06-26T16:06:03Z", "corpus_fingerprint": "2e539dd6824588914d7399d3e2df8da16d9177d5eb7dcb009e97a33d3ae34fef", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1480.2857142857142, "latency_ms_mean": 0.018959035709745616, "latency_ms_p50": 0.017708000086713582, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T19:11:03Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "feat(multi-loop): fanout multiple loops at once with logical rebase", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 450}, "commit": "7bdbbc6", "committed": "2026-06-26T16:06:03Z", "corpus_fingerprint": "25a0bc02e3d333c7856f0dcfb77ece8bc4d32a0f0eb15da9e6e5ac07970cb17c", "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3993.8928571428573, "latency_ms_mean": 16.45514067890222, "latency_ms_p50": 16.36189549935807, "mrr": 0.9424603174603174, "ndcg_at_k": 0.935095878714498, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T19:15:19Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "feat(multi-loop): fanout multiple loops at once with logical rebase", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.998330550918197, "tests_failed": 1, "tests_ran": 599}, "commit": "8084cc0", "committed": "2026-06-26T19:17:05Z", "corpus_fingerprint": "25a0bc02e3d333c7856f0dcfb77ece8bc4d32a0f0eb15da9e6e5ac07970cb17c", "corpus_size": 226, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3993.8928571428573, "latency_ms_mean": 15.91242630346252, "latency_ms_p50": 15.969916501489934, "mrr": 0.9424603174603174, "ndcg_at_k": 0.935095878714498, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.16, "run": "2026-06-26T19:30:52Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-worklog-promotion-matching-fix", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 599}, "commit": "8084cc0", "committed": "2026-06-26T19:17:05Z", "corpus_fingerprint": "25a0bc02e3d333c7856f0dcfb77ece8bc4d32a0f0eb15da9e6e5ac07970cb17c", "corpus_size": 226, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3993.8928571428573, "latency_ms_mean": 16.016559518123227, "latency_ms_p50": 16.072563001216622, "mrr": 0.9424603174603174, "ndcg_at_k": 0.935095878714498, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T19:37:01Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-worklog-promotion-matching-fix", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 599}, "commit": "8084cc0", "committed": "2026-06-26T19:17:05Z", "corpus_fingerprint": "25a0bc02e3d333c7856f0dcfb77ece8bc4d32a0f0eb15da9e6e5ac07970cb17c", "corpus_size": 226, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1480.2857142857142, "latency_ms_mean": 0.01734069649371252, "latency_ms_p50": 0.01593750130268745, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T19:38:21Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-worklog-promotion-matching-fix", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 606}, "commit": "a52bf15", "committed": "2026-06-26T19:38:33Z", "corpus_fingerprint": "7ed1917d89c5dd3ddd00513a0f364be1ae7fdcd55e0def5decf8856d00dcffc6", "corpus_size": 228, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3984.6964285714284, "latency_ms_mean": 17.2105670178228, "latency_ms_p50": 17.17437550178147, "mrr": 0.9424603174603174, "ndcg_at_k": 0.935095878714498, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T19:59:53Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge o11y-no-daemon: observability dashboard + React webui", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 606}, "commit": "a52bf15", "committed": "2026-06-26T19:38:33Z", "corpus_fingerprint": "7ed1917d89c5dd3ddd00513a0f364be1ae7fdcd55e0def5decf8856d00dcffc6", "corpus_size": 228, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1480.2857142857142, "latency_ms_mean": 0.01949776775031101, "latency_ms_p50": 0.018103999536833726, "mrr": 0.4844390256102441, "ndcg_at_k": 0.47187083757548315, "precision_at_k": 0.11785714285714287, "recall_at_k": 0.5446428571428571}, "mode": "eval", "num_queries": 56, "reliability": 81.79, "run": "2026-06-26T20:01:15Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge o11y-no-daemon: observability dashboard + React webui", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9951768488745981, "tests_failed": 3, "tests_ran": 622}, "commit": "9f02a47", "committed": "2026-06-26T20:03:29Z", "corpus_fingerprint": "830b5915a6794ecf47d06dd933ce779759ba06aa7e42a48ceae81a37eae391f1", "corpus_size": 181, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1499.517857142857, "latency_ms_mean": 0.015778267814831843, "latency_ms_p50": 0.014791499779676087, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.36, "run": "2026-06-26T20:13:35Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-fresh-clone-smoke-test", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9951768488745981, "tests_failed": 3, "tests_ran": 622}, "commit": "9f02a47", "committed": "2026-06-26T20:03:29Z", "corpus_fingerprint": "830b5915a6794ecf47d06dd933ce779759ba06aa7e42a48ceae81a37eae391f1", "corpus_size": 181, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1499.517857142857, "latency_ms_mean": 0.01635039286286753, "latency_ms_p50": 0.01497899938840419, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.36, "run": "2026-06-26T20:14:46Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-fresh-clone-smoke-test", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9951768488745981, "tests_failed": 3, "tests_ran": 622}, "commit": "9f02a47", "committed": "2026-06-26T20:03:29Z", "corpus_fingerprint": "830b5915a6794ecf47d06dd933ce779759ba06aa7e42a48ceae81a37eae391f1", "corpus_size": 181, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4005.464285714286, "latency_ms_mean": 10.246401714279532, "latency_ms_p50": 10.193916501521016, "mrr": 0.9333333333333333, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.07, "run": "2026-06-26T20:21:04Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-fresh-clone-smoke-test", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 622}, "commit": "9f02a47", "committed": "2026-06-26T20:03:29Z", "corpus_fingerprint": "830b5915a6794ecf47d06dd933ce779759ba06aa7e42a48ceae81a37eae391f1", "corpus_size": 181, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4005.464285714286, "latency_ms_mean": 10.221863892963613, "latency_ms_p50": 10.109937500601518, "mrr": 0.9333333333333333, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T20:28:46Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-fresh-clone-smoke-test", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 644}, "commit": "996aa54", "committed": "2026-06-26T20:32:42Z", "corpus_fingerprint": "0b3dcad5f22316672e501e1c47d0c1cdfb823fa57b0167630d331087c72aee92", "corpus_size": 182, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1499.517857142857, "latency_ms_mean": 0.014523767926480755, "latency_ms_p50": 0.013374999980442226, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T20:49:27Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-cached-inverted-index", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 644}, "commit": "996aa54", "committed": "2026-06-26T20:32:42Z", "corpus_fingerprint": "0b3dcad5f22316672e501e1c47d0c1cdfb823fa57b0167630d331087c72aee92", "corpus_size": 182, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1499.517857142857, "latency_ms_mean": 0.015030499980639433, "latency_ms_p50": 0.014332999853650108, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T20:50:36Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-cached-inverted-index", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 657}, "commit": "cf93c14", "committed": "2026-06-26T20:54:08Z", "corpus_fingerprint": "09e894ffb135170291eb2677d6bff6093d88a2ef725a3e62fa297a6f8d6f39d8", "corpus_size": 185, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4005.464285714286, "latency_ms_mean": 10.109000589376851, "latency_ms_p50": 9.79135449961177, "mrr": 0.9333333333333333, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T21:07:20Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-kb-dependency-graph", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 657}, "commit": "cf93c14", "committed": "2026-06-26T20:54:08Z", "corpus_fingerprint": "09e894ffb135170291eb2677d6bff6093d88a2ef725a3e62fa297a6f8d6f39d8", "corpus_size": 185, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1499.517857142857, "latency_ms_mean": 0.01732814293323567, "latency_ms_p50": 0.01616649933566805, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T21:08:41Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-dependency-graph", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 685}, "commit": "9c5091f", "committed": "2026-06-26T21:11:02Z", "corpus_fingerprint": "86881de072d327db5086700167f3df71c1f2e963d5157dc7ee33afe6c06ac908", "corpus_size": 190, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1499.517857142857, "latency_ms_mean": 0.01581771435407323, "latency_ms_p50": 0.014541497876052745, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T21:21:39Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-ingestion-connectors", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 685}, "commit": "9c5091f", "committed": "2026-06-26T21:11:02Z", "corpus_fingerprint": "5a03c59187b22406aa7c0d170ff699666c401197a364463956baedf97617bfdf", "corpus_size": 194, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3991.714285714286, "latency_ms_mean": 24.475899571890686, "latency_ms_p50": 24.462625002342975, "mrr": 0.9333333333333333, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T21:31:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-kb-ingestion-connectors", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 685}, "commit": "9c5091f", "committed": "2026-06-26T21:11:02Z", "corpus_fingerprint": "2ddcb58bce1e195ced4ce28a386a5ed4a38f4bf8846e9bb1755a397bd30cb10e", "corpus_size": 190, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1504.892857142857, "latency_ms_mean": 0.01859298221721214, "latency_ms_p50": 0.016645502910250798, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T21:32:55Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-ingestion-connectors", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 685}, "commit": "820f682", "committed": "2026-06-26T21:32:55Z", "corpus_fingerprint": "2ddcb58bce1e195ced4ce28a386a5ed4a38f4bf8846e9bb1755a397bd30cb10e", "corpus_size": 190, "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3997.5178571428573, "latency_ms_mean": 10.371657839641557, "latency_ms_p50": 10.078270999656525, "mrr": 0.9333333333333333, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T21:40:22Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-kb-mcp-server", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 685}, "commit": "820f682", "committed": "2026-06-26T21:32:55Z", "corpus_fingerprint": "2ddcb58bce1e195ced4ce28a386a5ed4a38f4bf8846e9bb1755a397bd30cb10e", "corpus_size": 190, "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1504.892857142857, "latency_ms_mean": 0.01759742852820117, "latency_ms_p50": 0.01662499926169403, "mrr": 0.49508928571428573, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T21:41:33Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-mcp-server", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 715}, "commit": "820f682", "committed": "2026-06-26T21:32:55Z", "corpus_fingerprint": "e0468927da74896f05f0feb956d4a71bfd633a76993d98ff78d0fd0a03dcacbc", "corpus_size": 193, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 3998.8928571428573, "latency_ms_mean": 10.342273892742273, "latency_ms_p50": 10.171520501899067, "mrr": 0.9333333333333333, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T22:00:37Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-kb-mcp-server", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 715}, "commit": "820f682", "committed": "2026-06-26T21:32:55Z", "corpus_fingerprint": "e0468927da74896f05f0feb956d4a71bfd633a76993d98ff78d0fd0a03dcacbc", "corpus_size": 193, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1512.6964285714287, "latency_ms_mean": 0.01588762513295348, "latency_ms_p50": 0.015249999705702066, "mrr": 0.4946428571428571, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T22:01:49Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-kb-mcp-server", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9986013986013986, "tests_failed": 1, "tests_ran": 715}, "commit": "73068cb", "committed": "2026-06-26T22:03:11Z", "corpus_fingerprint": "e0468927da74896f05f0feb956d4a71bfd633a76993d98ff78d0fd0a03dcacbc", "corpus_size": 193, "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1512.6964285714287, "latency_ms_mean": 0.015607857026874885, "latency_ms_p50": 0.014457997167482972, "mrr": 0.4946428571428571, "ndcg_at_k": 0.48536946353375254, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.46, "run": "2026-06-26T22:05:23Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "Merge feat/260625-team-mode-onboarding-fork", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 0.9986013986013986, "tests_failed": 1, "tests_ran": 715}, "commit": "73068cb", "committed": "2026-06-26T22:03:11Z", "corpus_fingerprint": "5b47f259314e02c5eff48e3539ec98c69a0ba216cfd7238c83720199f5d2e9c5", "corpus_size": 194, "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4187.428571428572, "latency_ms_mean": 10.590446482638072, "latency_ms_p50": 10.491729000932537, "mrr": 0.9329081632653061, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.17, "run": "2026-06-26T22:15:37Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-team-mode-onboarding-fork", "suite": null, "top_k": 5}
{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 715}, "commit": "71edb3f", "committed": "2026-06-26T22:20:05Z", "corpus_fingerprint": "89370cfea0614b4ff06fa1ae0d85c929c605234327ff386da364894530c6bdb4", "corpus_size": 195, "dirty": false, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 4135.410714285715, "latency_ms_mean": 10.426296214323624, "latency_ms_p50": 10.362562497903127, "mrr": 0.9325892857142858, "ndcg_at_k": 0.9285053385997024, "precision_at_k": 0.21428571428571427, "recall_at_k": 0.9553571428571429}, "mode": "eval", "num_queries": 56, "reliability": 98.21, "run": "2026-06-26T22:25:28Z", "schema": "agentware-bench/v1", "strategy": "bm25", "subject": "Merge feat/260625-competitor-comparison-report (+ team-mode test hotfix)", "suite": null, "top_k": 5}