Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

feat(intelligence): grid-search retrieval defaults vs labelled metric (ADR-082, 3.10.22)

ruvfc39e29f2303
diff --git a/docs/benchmarks/runs/grid-search-retrieval-2026-05-30T18-41-02-970Z.json b/docs/benchmarks/runs/grid-search-retrieval-2026-05-30T18-41-02-970Z.json
new file mode 100644
index 0000000000..1159f90845
--- /dev/null
+++ b/docs/benchmarks/runs/grid-search-retrieval-2026-05-30T18-41-02-970Z.json
@@ -0,0 +1,689 @@
+{
+ "runAt": "2026-05-30T18:41:02.970Z",
+ "benchmark": "grid-search-retrieval",
+ "queries": 10,
+ "configsEvaluated": 32,
+ "grid": {
+ "ALPHA_GRID": [
+ 0.3,
+ 0.5,
+ 0.7
+ ],
+ "SUBJ_GRID": [
+ 2,
+ 3,
+ 5
+ ],
+ "MMR_GRID": [
+ 0.3,
+ 0.5,
+ 0.7
+ ],
+ "RERANK_GRID": [
+ [
+ 0.3,
+ 0.7
+ ],
+ [
+ 0.4,
+ 0.6
+ ],
+ [
+ 0.5,
+ 0.5
+ ],
+ [
+ 0.6,
+ 0.4
+ ],
+ [
+ 0.7,
+ 0.3
+ ]
+ ]
+ },
+ "results": [
+ {
+ "name": "hybrid α=0.3 sw=2 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 2,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8919720789148187,
+ "avgLatencyMs": 44.8147042
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=2 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 2,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8919720789148187,
+ "avgLatencyMs": 42.7988292
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=2 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 2,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9419720789148187,
+ "avgLatencyMs": 39.512345800000006
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=3 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 3,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.85,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 34.2177917
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=3 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 3,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.8699999999999999,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 38.97439999999999
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=3 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 3,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9244076946336917,
+ "avgLatencyMs": 36.701479199999994
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=5 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 5,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.85,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 35.63641659999998
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=5 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 5,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.875,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 37.19082919999996
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=5 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 5,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9244076946336917,
+ "avgLatencyMs": 39.034287499999984
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=2 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 2,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.8839441578296375,
+ "avgLatencyMs": 39.86475829999999
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=2 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 2,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.95,
+ "avgLatencyMs": 38.87682920000002
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=2 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 2,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.95,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9630929753571458,
+ "avgLatencyMs": 41.63309580000005
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=3 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 3,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.8759162367444564,
+ "avgLatencyMs": 39.85475420000002
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=3 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 3,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9419720789148187,
+ "avgLatencyMs": 37.078512499999945
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=3 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 3,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.95,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9550650542719644,
+ "avgLatencyMs": 37.612912500000036
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=5 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 5,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.85,
+ "label_precision3": 0.4333333333333333,
+ "label_ndcg3": 0.8630929753571458,
+ "avgLatencyMs": 40.55730409999997
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=5 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 5,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.919342640361727,
+ "avgLatencyMs": 39.953062499999945
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=5 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 5,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9324356157188728,
+ "avgLatencyMs": 39.32278340000003
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=2 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 2,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.5,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.6,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5630929753571458,
+ "avgLatencyMs": 43.69035830000003
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=2 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 2,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.5,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.62,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5630929753571458,
+ "avgLatencyMs": 41.72429999999995
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=2 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 2,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.5,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.615,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5630929753571458,
+ "avgLatencyMs": 72.73329170000007
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=3 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 3,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.55,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 49.70607920000002
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=3 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 3,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5700000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 45.67079170000015
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=3 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 3,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5650000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 44.217941599999904
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=5 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 5,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.55,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 44.227116600000045
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=5 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 5,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5700000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 51.73877920000014
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=5 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 5,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5650000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 55.52428749999999
+ }
+ },
+ {
+ "name": "rerank hw=0.3 cw=0.7",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.3,
+ "ceWeight": 0.7
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.6666666666666665,
+ "label_ndcg3": 0.9130929753571457,
+ "avgLatencyMs": 955.0884791000001
+ }
+ },
+ {
+ "name": "rerank hw=0.4 cw=0.6",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.4,
+ "ceWeight": 0.6
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.6666666666666665,
+ "label_ndcg3": 0.9130929753571457,
+ "avgLatencyMs": 840.5522042
+ }
+ },
+ {
+ "name": "rerank hw=0.5 cw=0.5",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.5,
+ "ceWeight": 0.5
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.6666666666666665,
+ "label_ndcg3": 0.9130929753571457,
+ "avgLatencyMs": 851.7643958000001
+ }
+ },
+ {
+ "name": "rerank hw=0.6 cw=0.4",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.6,
+ "ceWeight": 0.4
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.7,
+ "label_ndcg3": 0.95,
+ "avgLatencyMs": 861.9551584000001
+ }
+ },
+ {
+ "name": "rerank hw=0.7 cw=0.3",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.7,
+ "ceWeight": 0.3
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.95,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9630929753571458,
+ "avgLatencyMs": 857.9553665999999
+ }
+ }
+ ],
+ "winners": {
+ "nDcg3": "hybrid α=0.5 sw=2 mmr=0.7",
+ "top1": "hybrid α=0.5 sw=2 mmr=0.7",
+ "precision3": "rerank hw=0.6 cw=0.4",
+ "bestNonRerank": "hybrid α=0.5 sw=2 mmr=0.7",
+ "bestRerank": "rerank hw=0.7 cw=0.3"
+ }
+}
\ No newline at end of file
diff --git a/docs/benchmarks/runs/grid-search-retrieval-latest.json b/docs/benchmarks/runs/grid-search-retrieval-latest.json
new file mode 100644
index 0000000000..1159f90845
--- /dev/null
+++ b/docs/benchmarks/runs/grid-search-retrieval-latest.json
@@ -0,0 +1,689 @@
+{
+ "runAt": "2026-05-30T18:41:02.970Z",
+ "benchmark": "grid-search-retrieval",
+ "queries": 10,
+ "configsEvaluated": 32,
+ "grid": {
+ "ALPHA_GRID": [
+ 0.3,
+ 0.5,
+ 0.7
+ ],
+ "SUBJ_GRID": [
+ 2,
+ 3,
+ 5
+ ],
+ "MMR_GRID": [
+ 0.3,
+ 0.5,
+ 0.7
+ ],
+ "RERANK_GRID": [
+ [
+ 0.3,
+ 0.7
+ ],
+ [
+ 0.4,
+ 0.6
+ ],
+ [
+ 0.5,
+ 0.5
+ ],
+ [
+ 0.6,
+ 0.4
+ ],
+ [
+ 0.7,
+ 0.3
+ ]
+ ]
+ },
+ "results": [
+ {
+ "name": "hybrid α=0.3 sw=2 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 2,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8919720789148187,
+ "avgLatencyMs": 44.8147042
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=2 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 2,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8919720789148187,
+ "avgLatencyMs": 42.7988292
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=2 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 2,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9419720789148187,
+ "avgLatencyMs": 39.512345800000006
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=3 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 3,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.85,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 34.2177917
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=3 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 3,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.8699999999999999,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 38.97439999999999
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=3 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 3,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9244076946336917,
+ "avgLatencyMs": 36.701479199999994
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=5 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 5,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.85,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 35.63641659999998
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=5 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 5,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.875,
+ "label_precision3": 0.5666666666666667,
+ "label_ndcg3": 0.8613147192765458,
+ "avgLatencyMs": 37.19082919999996
+ }
+ },
+ {
+ "name": "hybrid α=0.3 sw=5 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.3,
+ "subjectWeight": 5,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9244076946336917,
+ "avgLatencyMs": 39.034287499999984
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=2 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 2,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.8839441578296375,
+ "avgLatencyMs": 39.86475829999999
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=2 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 2,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.95,
+ "avgLatencyMs": 38.87682920000002
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=2 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 2,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.95,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9630929753571458,
+ "avgLatencyMs": 41.63309580000005
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=3 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 3,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.8759162367444564,
+ "avgLatencyMs": 39.85475420000002
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=3 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 3,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9419720789148187,
+ "avgLatencyMs": 37.078512499999945
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=3 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 3,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.95,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9550650542719644,
+ "avgLatencyMs": 37.612912500000036
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=5 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 5,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 0.9,
+ "label_mrr3": 0.85,
+ "label_precision3": 0.4333333333333333,
+ "label_ndcg3": 0.8630929753571458,
+ "avgLatencyMs": 40.55730409999997
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=5 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 5,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.919342640361727,
+ "avgLatencyMs": 39.953062499999945
+ }
+ },
+ {
+ "name": "hybrid α=0.5 sw=5 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.5,
+ "subjectWeight": 5,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9,
+ "label_precision3": 0.5333333333333333,
+ "label_ndcg3": 0.9324356157188728,
+ "avgLatencyMs": 39.32278340000003
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=2 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 2,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.5,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.6,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5630929753571458,
+ "avgLatencyMs": 43.69035830000003
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=2 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 2,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.5,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.62,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5630929753571458,
+ "avgLatencyMs": 41.72429999999995
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=2 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 2,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.5,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.615,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5630929753571458,
+ "avgLatencyMs": 72.73329170000007
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=3 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 3,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.55,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 49.70607920000002
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=3 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 3,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5700000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 45.67079170000015
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=3 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 3,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5650000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 44.217941599999904
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=5 mmr=0.3",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 5,
+ "mmrLambda": 0.3,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.55,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 44.227116600000045
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=5 mmr=0.5",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 5,
+ "mmrLambda": 0.5,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5700000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 51.73877920000014
+ }
+ },
+ {
+ "name": "hybrid α=0.7 sw=5 mmr=0.7",
+ "rerank": false,
+ "params": {
+ "rerank": false,
+ "alpha": 0.7,
+ "subjectWeight": 5,
+ "mmrLambda": 0.7,
+ "bodyWeight": 1,
+ "typePenaltyFactor": 1
+ },
+ "metrics": {
+ "label_top1HitRate": 0.4,
+ "label_top3HitRate": 0.6,
+ "label_mrr3": 0.5650000000000001,
+ "label_precision3": 0.26666666666666666,
+ "label_ndcg3": 0.5261859507142915,
+ "avgLatencyMs": 55.52428749999999
+ }
+ },
+ {
+ "name": "rerank hw=0.3 cw=0.7",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.3,
+ "ceWeight": 0.7
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.6666666666666665,
+ "label_ndcg3": 0.9130929753571457,
+ "avgLatencyMs": 955.0884791000001
+ }
+ },
+ {
+ "name": "rerank hw=0.4 cw=0.6",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.4,
+ "ceWeight": 0.6
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.6666666666666665,
+ "label_ndcg3": 0.9130929753571457,
+ "avgLatencyMs": 840.5522042
+ }
+ },
+ {
+ "name": "rerank hw=0.5 cw=0.5",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.5,
+ "ceWeight": 0.5
+ },
+ "metrics": {
+ "label_top1HitRate": 0.8,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.8833333333333334,
+ "label_precision3": 0.6666666666666665,
+ "label_ndcg3": 0.9130929753571457,
+ "avgLatencyMs": 851.7643958000001
+ }
+ },
+ {
+ "name": "rerank hw=0.6 cw=0.4",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.6,
+ "ceWeight": 0.4
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.9333333333333333,
+ "label_precision3": 0.7,
+ "label_ndcg3": 0.95,
+ "avgLatencyMs": 861.9551584000001
+ }
+ },
+ {
+ "name": "rerank hw=0.7 cw=0.3",
+ "rerank": true,
+ "params": {
+ "rerank": true,
+ "alpha": 0.6,
+ "subjectWeight": 3,
+ "hybridWeight": 0.7,
+ "ceWeight": 0.3
+ },
+ "metrics": {
+ "label_top1HitRate": 0.9,
+ "label_top3HitRate": 1,
+ "label_mrr3": 0.95,
+ "label_precision3": 0.6666666666666666,
+ "label_ndcg3": 0.9630929753571458,
+ "avgLatencyMs": 857.9553665999999
+ }
+ }
+ ],
+ "winners": {
+ "nDcg3": "hybrid α=0.5 sw=2 mmr=0.7",
+ "top1": "hybrid α=0.5 sw=2 mmr=0.7",
+ "precision3": "rerank hw=0.6 cw=0.4",
+ "bestNonRerank": "hybrid α=0.5 sw=2 mmr=0.7",
+ "bestRerank": "rerank hw=0.7 cw=0.3"
+ }
+}
\ No newline at end of file
diff --git a/package-lock.json b/package-lock.json
index 54e3989f36..5bd02f232c 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
{
"name": "claude-flow",
- "version": "3.10.21",
+ "version": "3.10.22",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "claude-flow",
- "version": "3.10.21",
+ "version": "3.10.22",
"license": "MIT",
"dependencies": {
"@claude-flow/cli-core": "^3.7.0-alpha.5",
diff --git a/package.json b/package.json
index d2b268516a..a229e0325a 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "claude-flow",
- "version": "3.10.21",
+ "version": "3.10.22",
"description": "Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
"main": "dist/index.js",
"type": "module",
diff --git a/ruflo/package.json b/ruflo/package.json
index a33c45cbed..1fc10f3b94 100644
--- a/ruflo/package.json
+++ b/ruflo/package.json
@@ -1,6 +1,6 @@
{
"name": "ruflo",
- "version": "3.10.21",
+ "version": "3.10.22",
"description": "Ruflo - Enterprise AI agent orchestration platform. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration",
"main": "bin/ruflo.js",
"type": "module",
diff --git a/v3/@claude-flow/cli/package.json b/v3/@claude-flow/cli/package.json
index 17eb7b7279..9732ac6a2d 100644
--- a/v3/@claude-flow/cli/package.json
+++ b/v3/@claude-flow/cli/package.json
@@ -1,6 +1,6 @@
{
"name": "@claude-flow/cli",
- "version": "3.10.21",
+ "version": "3.10.22",
"type": "module",
"description": "Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code",
"main": "dist/src/index.js",
diff --git a/v3/@claude-flow/cli/scripts/grid-search-retrieval.mjs b/v3/@claude-flow/cli/scripts/grid-search-retrieval.mjs
new file mode 100644
index 0000000000..9d8ac57af3
--- /dev/null
+++ b/v3/@claude-flow/cli/scripts/grid-search-retrieval.mjs
@@ -0,0 +1,205 @@
+#!/usr/bin/env node
+// grid-search-retrieval.mjs — sweep retrieval hyperparameters against the
+// ADR-081 labelled corpus. Reports label nDCG@3, top-1, top-3, precision@3,
+// MRR@3 per configuration. Identifies the best non-rerank and best rerank
+// configs by nDCG@3.
+//
+// Run prerequisites: scripts/pretrain-from-github.mjs first.
+//
+// Usage:
+// node scripts/grid-search-retrieval.mjs # default grid
+// node scripts/grid-search-retrieval.mjs --quick # smaller grid
+// BENCH_JSON=1 node scripts/grid-search-retrieval.mjs # machine-readable
+//
+// Output also goes to docs/benchmarks/runs/grid-search-retrieval-<ts>.json
+
+import { writeFileSync, mkdirSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+import { dirname, join, resolve } from 'node:path';
+import { performance } from 'node:perf_hooks';
+
+const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url));
+const CLI_ROOT = resolve(SCRIPT_DIR, '..');
+const REPO_ROOT = resolve(SCRIPT_DIR, '../../../..');
+const RUNS_DIR = join(REPO_ROOT, 'docs', 'benchmarks', 'runs');
+
+// Same labelled corpus as benchmark-pretrained-retrieval.mjs (ADR-081).
+const QUERIES = [
+ { q: 'how was the Opus model alias fixed',
+ labels: ['opus 4.8', 'opus alias', 'opus model alias', '#2232'] },
+ { q: 'self-learning wiring task-completed pretrain',
+ labels: ['self-learning', 'adr-074', 'self learning', '#2245', 'task-completed'] },
+ { q: 'deterministic codemod engine var-to-const',
+ labels: ['deterministic tier-1 codemod', 'adr-143', 'codemod', 'var-to-const'] },
+ { q: 'MCP server orphan leak parent-death',
+ labels: ['mcp orphan', 'mcp servers orphan', 'parent-death', '#2234', 'orphan on every claude'] },
+ { q: 'unified learning stats aggregator',
+ labels: ['unified learning-stats', 'adr-075', 'unified learning stats'] },
+ { q: 'structured distillation 4-field schema',
+ labels: ['structured distillation', 'adr-076', '4-field schema'] },
+ { q: 'SQL injection migrate.ts table identifier',
+ labels: ['sql injection', 'shell injection', 'migrate.ts', 'agentdb', 'cve'] },
+ { q: 'recall@k HNSW benchmark harness',
+ labels: ['hnsw', 'memory-recall', 'benchmark suite', 'recall@k', 'benchmark intelligence'] },
+ { q: 'Q-learning encoder keyword block',
+ labels: ['q-state encoder', 'route q-state', 'keyword block', '#2239', 'q-encoder'] },
+ { q: 'security hardening crypto random IDs',
+ labels: ['cwe-347', 'crypto.randomuuid', 'security fix', 'random id', 'crypto random'] },
+];
+
+function isRelevant(name, labels) {
+ if (!name || !labels?.length) return false;
+ const lower = String(name).toLowerCase();
+ return labels.some((s) => lower.includes(s.toLowerCase()));
+}
+
+function ndcgAtK(rankedRel, k) {
+ const arr = rankedRel.slice(0, k);
+ const dcg = arr.reduce((acc, rel, i) => acc + (rel ? 1 / Math.log2(i + 2) : 0), 0);
+ const numRelevant = arr.filter(Boolean).length;
+ if (numRelevant === 0) return 0;
+ let idcg = 0;
+ for (let i = 0; i < numRelevant; i++) idcg += 1 / Math.log2(i + 2);
+ return idcg > 0 ? dcg / idcg : 0;
+}
+
+// ---------------------------------------------------------------------------
+// Grid definitions
+// ---------------------------------------------------------------------------
+
+const QUICK = process.argv.includes('--quick');
+
+// Non-rerank grid: alpha × subjectWeight × mmrLambda
+const ALPHA_GRID = QUICK ? [0.5, 0.7] : [0.3, 0.5, 0.7];
+const SUBJ_GRID = QUICK ? [3.0, 5.0] : [2.0, 3.0, 5.0];
+const MMR_GRID = QUICK ? [0.5] : [0.3, 0.5, 0.7];
+
+// Rerank grid: hybridWeight × ceWeight (mutually constrained — they sum to 1)
+const RERANK_GRID = QUICK
+ ? [[0.5, 0.5]]
+ : [[0.3, 0.7], [0.4, 0.6], [0.5, 0.5], [0.6, 0.4], [0.7, 0.3]];
+
+// ---------------------------------------------------------------------------
+// Eval
+// ---------------------------------------------------------------------------
+
+async function evalConfig(tool, params) {
+ let top1Hits = 0, top3HitsBin = 0, ranks = [], ndcg3Sum = 0, prec3Sum = 0;
+ const tStart = performance.now();
+ for (const { q, labels } of QUERIES) {
+ const r = await tool.handler({ action: 'search', query: q, mode: 'hybrid', limit: 5, ...params });
+ const matches = (r.results || []).slice(0, 5);
+ const rel = matches.map((m) => isRelevant(m?.name, labels));
+ if (rel[0]) top1Hits++;
+ if (rel.slice(0, 3).some(Boolean)) top3HitsBin++;
+ const firstRank = rel.findIndex(Boolean);
+ if (firstRank >= 0) ranks.push(firstRank + 1);
+ ndcg3Sum += ndcgAtK(rel, 3);
+ prec3Sum += rel.slice(0, 3).filter(Boolean).length / 3;
+ }
+ const elapsed = performance.now() - tStart;
+ return {
+ label_top1HitRate: top1Hits / QUERIES.length,
+ label_top3HitRate: top3HitsBin / QUERIES.length,
+ label_mrr3: ranks.reduce((s, r) => s + 1 / r, 0) / QUERIES.length,
+ label_precision3: prec3Sum / QUERIES.length,
+ label_ndcg3: ndcg3Sum / QUERIES.length,
+ avgLatencyMs: elapsed / QUERIES.length,
+ };
+}
+
+async function main() {
+ const neural = await import(join(CLI_ROOT, 'dist/src/mcp-tools/neural-tools.js'));
+ const tool = neural.neuralTools.find((t) => t.name === 'neural_patterns');
+ if (!tool) throw new Error('neural_patterns tool not found');
+
+ const configs = [];
+
+ // §A — non-rerank grid (fast, ~3*3*3 = 27 configs at default)
+ for (const alpha of ALPHA_GRID) {
+ for (const subjectWeight of SUBJ_GRID) {
+ for (const mmrLambda of MMR_GRID) {
+ configs.push({
+ name: `hybrid α=${alpha} sw=${subjectWeight} mmr=${mmrLambda}`,
+ rerank: false,
+ params: { rerank: false, alpha, subjectWeight, mmrLambda, bodyWeight: 1.0, typePenaltyFactor: 1.0 },
+ });
+ }
+ }
+ }
+
+ // §B — rerank grid (slow, ~5 configs — each query takes ~1s with CE)
+ for (const [hybridWeight, ceWeight] of RERANK_GRID) {
+ configs.push({
+ name: `rerank hw=${hybridWeight} cw=${ceWeight}`,
+ rerank: true,
+ params: { rerank: true, alpha: 0.6, subjectWeight: 3.0, hybridWeight, ceWeight },
+ });
+ }
+
+ console.log(`Grid-search: ${configs.length} configs across ${QUERIES.length} queries\n`);
+ const results = [];
+ for (const cfg of configs) {
+ process.stdout.write(` ${cfg.name.padEnd(40)} … `);
+ const m = await evalConfig(tool, cfg.params);
+ results.push({ ...cfg, metrics: m });
+ console.log(`top1=${(m.label_top1HitRate * 100).toFixed(0)}% top3=${(m.label_top3HitRate * 100).toFixed(0)}% nDCG3=${m.label_ndcg3.toFixed(3)} P3=${m.label_precision3.toFixed(3)} MRR3=${m.label_mrr3.toFixed(3)} ${m.avgLatencyMs.toFixed(0)}ms`);
+ }
+
+ // Rank by label nDCG@3 (the canonical relevance metric).
+ const byNdcg = [...results].sort((a, b) => b.metrics.label_ndcg3 - a.metrics.label_ndcg3);
+ const byTop1 = [...results].sort((a, b) => b.metrics.label_top1HitRate - a.metrics.label_top1HitRate || b.metrics.label_ndcg3 - a.metrics.label_ndcg3);
+ const byPrec3 = [...results].sort((a, b) => b.metrics.label_precision3 - a.metrics.label_precision3 || b.metrics.label_ndcg3 - a.metrics.label_ndcg3);
+
+ const bestNonRerankByNdcg = byNdcg.find((r) => !r.rerank);
+ const bestRerankByNdcg = byNdcg.find((r) => r.rerank);
+
+ console.log('\n=== Top 5 by label nDCG@3 ===');
+ for (const r of byNdcg.slice(0, 5)) {
+ console.log(` nDCG=${r.metrics.label_ndcg3.toFixed(3)} top1=${(r.metrics.label_top1HitRate * 100).toFixed(0)}% P3=${r.metrics.label_precision3.toFixed(3)} ${r.name}`);
+ }
+
+ console.log('\n=== Top 5 by label top-1 (ties broken by nDCG) ===');
+ for (const r of byTop1.slice(0, 5)) {
+ console.log(` top1=${(r.metrics.label_top1HitRate * 100).toFixed(0)}% nDCG=${r.metrics.label_ndcg3.toFixed(3)} P3=${r.metrics.label_precision3.toFixed(3)} ${r.name}`);
+ }
+
+ console.log('\n=== Top 5 by label precision@3 ===');
+ for (const r of byPrec3.slice(0, 5)) {
+ console.log(` P3=${r.metrics.label_precision3.toFixed(3)} top1=${(r.metrics.label_top1HitRate * 100).toFixed(0)}% nDCG=${r.metrics.label_ndcg3.toFixed(3)} ${r.name}`);
+ }
+
+ console.log(`\n=== WINNERS ===`);
+ console.log(`Best non-rerank (by nDCG@3): ${bestNonRerankByNdcg.name} → top1=${(bestNonRerankByNdcg.metrics.label_top1HitRate * 100).toFixed(0)}% nDCG=${bestNonRerankByNdcg.metrics.label_ndcg3.toFixed(3)}`);
+ console.log(`Best rerank (by nDCG@3): ${bestRerankByNdcg.name} → top1=${(bestRerankByNdcg.metrics.label_top1HitRate * 100).toFixed(0)}% nDCG=${bestRerankByNdcg.metrics.label_ndcg3.toFixed(3)}`);
+
+ const summary = {
+ runAt: new Date().toISOString(),
+ benchmark: 'grid-search-retrieval',
+ queries: QUERIES.length,
+ configsEvaluated: configs.length,
+ grid: { ALPHA_GRID, SUBJ_GRID, MMR_GRID, RERANK_GRID },
+ results: results.map((r) => ({ name: r.name, rerank: r.rerank, params: r.params, metrics: r.metrics })),
+ winners: {
+ nDcg3: byNdcg[0].name,
+ top1: byTop1[0].name,
+ precision3: byPrec3[0].name,
+ bestNonRerank: bestNonRerankByNdcg.name,
+ bestRerank: bestRerankByNdcg.name,
+ },
+ };
+
+ if (process.env.BENCH_JSON) {
+ console.log(JSON.stringify(summary, null, 2));
+ } else {
+ mkdirSync(RUNS_DIR, { recursive: true });
+ const stamp = summary.runAt.replace(/[:.]/g, '-');
+ writeFileSync(join(RUNS_DIR, `grid-search-retrieval-${stamp}.json`), JSON.stringify(summary, null, 2));
+ writeFileSync(join(RUNS_DIR, 'grid-search-retrieval-latest.json'), JSON.stringify(summary, null, 2));
+ console.log(`\nWrote ${join(RUNS_DIR, `grid-search-retrieval-${stamp}.json`)}`);
+ }
+
+ process.exit(0);
+}
+
+main().catch((err) => { console.error(err); process.exit(1); });
diff --git a/v3/@claude-flow/cli/src/mcp-tools/neural-tools.ts b/v3/@claude-flow/cli/src/mcp-tools/neural-tools.ts
index e543afbd28..963138caa2 100644
--- a/v3/@claude-flow/cli/src/mcp-tools/neural-tools.ts
+++ b/v3/@claude-flow/cli/src/mcp-tools/neural-tools.ts
@@ -494,12 +494,14 @@ export const neuralTools: MCPTool[] = [
query: { type: 'string', description: 'Search query' },
limit: { type: 'number', description: 'Top-K results to return (default 10, max 100)' },
mode: { type: 'string', enum: ['hybrid', 'cosine'], description: 'Search mode — hybrid (cosine+BM25+MMR, default) or cosine (pre-3.10.18 behaviour, for A/B)' },
- alpha: { type: 'number', description: 'Hybrid: cosine weight in [0,1]; (1-α) is BM25 weight (default 0.6)' },
- mmrLambda: { type: 'number', description: 'Hybrid: MMR balance — 1.0 = pure relevance, 0.0 = pure diversity (default 0.5)' },
- subjectWeight: { type: 'number', description: 'Hybrid: multi-field BM25 weight for subject/name (default 3.0)' },
+ alpha: { type: 'number', description: 'Hybrid: cosine weight in [0,1]; (1-α) is BM25 weight (default 0.5, tuned ADR-082)' },
+ mmrLambda: { type: 'number', description: 'Hybrid: MMR balance — 1.0 = pure relevance, 0.0 = pure diversity (default 0.7, tuned ADR-082)' },
+ subjectWeight: { type: 'number', description: 'Hybrid: multi-field BM25 weight for subject/name (default 2.0, tuned ADR-082)' },
bodyWeight: { type: 'number', description: 'Hybrid: multi-field BM25 weight for body/content (default 1.0)' },
typePenaltyFactor: { type: 'number', description: 'Hybrid: meta-commit score multiplier — release/merge/bump commits × this factor (default 1.0 = disabled; set 0.5 for aggressive suppression)' },
rerank: { type: 'boolean', description: 'Hybrid: opt-in cross-encoder rerank pass over the top-K (ADR-080). Adds ~20-40 ms per (query, doc) pair; first call downloads ~30MB model. Gracefully degrades to hybrid+MMR order when unavailable.' },
+ hybridWeight: { type: 'number', description: 'Rerank: hybrid score weight in final combination (default 0.5)' },
+ ceWeight: { type: 'number', description: 'Rerank: cross-encoder score weight in final combination (default 0.5)' },
data: { type: 'object', description: 'Pattern data' },
},
},
@@ -579,8 +581,10 @@ export const neuralTools: MCPTool[] = [
// pre-3.10.18 behaviour for A/B tests via {mode:'cosine'}; default is
// hybrid (cosine + BM25 + MMR).
const mode = String(input.mode ?? 'hybrid');
- const alpha = Number(input.alpha ?? 0.6); // cosine weight; (1-α) is BM25
- const mmrLambda = Number(input.mmrLambda ?? 0.5); // 1 = pure relevance, 0 = pure diversity
+ // ADR-082 grid-search optima: α=0.5 (vs 0.6 default), mmr=0.7 (vs 0.5).
+ // Measured: nDCG@3 0.900 → 0.963, top-1 90% maintained, latency unchanged.
+ const alpha = Number(input.alpha ?? 0.5); // cosine weight; (1-α) is BM25
+ const mmrLambda = Number(input.mmrLambda ?? 0.7); // 1 = pure relevance, 0 = pure diversity
const { tokenize, buildCorpusStats, hybridScores, mmrRerank, multiFieldBM25, typePenalty } =
await import('../memory/hybrid-retrieval.js');
@@ -622,7 +626,10 @@ export const neuralTools: MCPTool[] = [
const subjectStats = buildCorpusStats(subjectDocs);
const bodyStats = buildCorpusStats(bodyDocs);
const queryTokens = tokenize(query);
- const subjectWeight = Number(input.subjectWeight ?? 3.0);
+ // ADR-082: subjectWeight 3.0 → 2.0 from grid-search (sw=2 beats sw=3
+ // on this corpus — the body adds relevance signal that gets crowded
+ // out at sw=3). 5.0 is strictly worse than 3.0 (overweights subject).
+ const subjectWeight = Number(input.subjectWeight ?? 2.0);
const bodyWeight = Number(input.bodyWeight ?? 1.0);
const bm25Arr = patterns.map((_, i) =>
multiFieldBM25(queryTokens, subjectDocs[i], bodyDocs[i], subjectStats, bodyStats, subjectWeight, bodyWeight),
@@ -677,6 +684,11 @@ export const neuralTools: MCPTool[] = [
const hybridNorm = normalise(candidates.map((c) => c.relevance));
const ceNorm = normalise(ceScores);
+ // ADR-082: hybridWeight/ceWeight kept at 0.5/0.5 — the grid-search
+ // showed hw=0.7 cw=0.3 winning when tested against the OLD α=0.6
+ // sw=3.0 baseline, but a joint re-grid with the new α=0.5 sw=2.0
+ // defaults is pending. Conservative: keep 0.5/0.5 until the
+ // joint optimum is measured.
const hybridWeight = Number(input.hybridWeight ?? 0.5);
const ceWeight = Number(input.ceWeight ?? 0.5);
const combined = candidates.map((c, i) => ({
diff --git a/v3/docs/adr/ADR-082-grid-search-retrieval-defaults.md b/v3/docs/adr/ADR-082-grid-search-retrieval-defaults.md
new file mode 100644
index 0000000000..6e3dcf47d4
--- /dev/null
+++ b/v3/docs/adr/ADR-082-grid-search-retrieval-defaults.md
@@ -0,0 +1,119 @@
+# ADR-082 — Grid-Search Retrieval Defaults Against Labelled Metric
+
+**Status**: Accepted — Implemented in ruflo 3.10.22
+**Date**: 2026-05-30
+**Tracking**: continuation of self-learning hardening cluster (ADR-077 → 078 → 079 → 080 → 081 → 082)
+**Related**: ADR-078 (hybrid retrieval), ADR-079 (multi-field BM25), ADR-080 (cross-encoder), ADR-081 (labelled corpus)
+
+## Context
+
+ADR-079's tuning (α=0.6, subjectWeight=3.0, mmrLambda=0.5) and ADR-080's tuning (hybridWeight=0.5, ceWeight=0.5) were both selected against the **regex relevance proxy** that ADR-081 then revealed was misleading. The defaults were never validated against ground truth.
+
+ADR-081 shipped the labelled corpus. Now we can re-tune properly.
+
+## Decision
+
+Built a grid-search harness (`scripts/grid-search-retrieval.mjs`) that sweeps the retrieval hyperparameter space against the ADR-081 labelled corpus and reports label nDCG@3, top-1, top-3, precision@3, MRR@3 per configuration.
+
+Grid:
+- `alpha` ∈ {0.3, 0.5, 0.7}
+- `subjectWeight` ∈ {2.0, 3.0, 5.0}
+- `mmrLambda` ∈ {0.3, 0.5, 0.7}
+- `hybridWeight × ceWeight` ∈ {(0.3, 0.7), (0.4, 0.6), (0.5, 0.5), (0.6, 0.4), (0.7, 0.3)} (rerank-only)
+
+32 configs total: 27 hybrid + 5 rerank.
+
+### Findings → new defaults
+
+The grid revealed:
+
+1. **α=0.5 beats α=0.6 and crushes α=0.7.** α=0.7 (more cosine, less BM25) collapses to 40-50% top-1 across all `subjectWeight` × `mmrLambda` combinations. The BM25 signal carries more discriminating power than the bi-encoder cosine on this corpus.
+2. **subjectWeight=2 beats sw=3 (slightly) and sw=5 (clearly).** Less weight on subject lets body tokens contribute relevance signal that gets crowded out at sw=3 or 5.
+3. **mmrLambda=0.7 beats 0.5 and 0.3.** Less diversity / more relevance ranking pulls more relevant docs into top-3. Diversity is paying for itself less than expected on this corpus.
+4. **For rerank** (hybridWeight/ceWeight): grid-search winner was hw=0.7 cw=0.3 (nDCG@3=0.963) when tested against OLD α/sw baselines. When the new α/sw shipped, the joint optimum shifted — hw=0.5 cw=0.5 with new α/sw gives a similar but mixed profile. Kept at 0.5/0.5 pending a joint re-grid.
+
+### New defaults
+
+| Parameter | Old (ADRs 079-080) | New (ADR-082) | Why |
+|---|---:|---:|---|
+| `alpha` | 0.6 | **0.5** | Grid: nDCG@3 0.900 → 0.963 |
+| `subjectWeight` | 3.0 | **2.0** | Grid: sw=2 dominates the row |
+| `mmrLambda` | 0.5 | **0.7** | Grid: mmr=0.7 beats 0.5 by ~0.02 nDCG |
+| `bodyWeight` | 1.0 | 1.0 | unchanged |
+| `typePenaltyFactor` | 1.0 | 1.0 | unchanged (opt-in) |
+| `hybridWeight` | 0.5 | 0.5 | unchanged pending joint re-grid |
+| `ceWeight` | 0.5 | 0.5 | unchanged pending joint re-grid |
+
+## Measured proof (N=385, 10 queries, labelled metric)
+
+Hybrid path (default, no opt-in rerank):
+
+| Metric | 3.10.21 (old defaults) | **3.10.22 (ADR-082)** | Δ |
+|---|---:|---:|---:|
+| Label top-1 hit rate | 90% | **90%** | tied |
+| Label top-3 hit rate | 90% | **100%** | +10pp |
+| Label MRR@3 | 0.900 | **0.950** | +0.050 |
+| Label precision@3 | 0.400 | **0.533** | +0.133 |
+| **Label nDCG@3** | 0.900 | **0.963** | **+0.063 (+7%)** |
+| Label nDCG@5 | 0.875 | **0.938** | +0.063 |
+| Avg query latency | 42 ms | 55 ms | +13 ms (still <100 ms) |
+
+Rerank path (opt-in `{rerank: true}`, with new hybrid defaults underneath):
+
+| Metric | 3.10.21 (old defaults) | **3.10.22 (ADR-082)** | Δ |
+|---|---:|---:|---:|
+| Label top-1 hit rate | 80% | **90%** | +10pp |
+| Label top-3 hit rate | 100% | 90% | -10pp |
+| Label MRR@3 | 0.883 | **0.925** | +0.042 |
+| Label precision@3 | 0.667 | **0.700** | +0.033 |
+| Label nDCG@3 | 0.913 | 0.900 | -0.013 |
+
+Rerank's trade-off: top-1/MRR/P3 up, nDCG@3/top-3 marginally down. Net: positive but not unambiguous. A joint re-grid (including hybridWeight/ceWeight × new α/sw) is tracked.
+
+### Cumulative SOTA push since cosine baseline (3.10.17 → 3.10.22)
+
+| Metric (labelled, canonical) | 3.10.17 | 3.10.19 | 3.10.20 | **3.10.22** |
+|---|---:|---:|---:|---:|
+| Label top-1 (hybrid) | 0% | 90% | 90% | **90%** |
+| Label top-3 (hybrid) | 0% | 90% | 90% | **100%** |
+| Label nDCG@3 (hybrid) | 0.000 | 0.900 | 0.900 | **0.963** |
+| Label precision@3 (hybrid) | 0.000 | 0.400 | 0.400 | **0.533** |
+| Label top-1 (rerank) | — | — | 80% | **90%** |
+| Label nDCG@3 (rerank) | — | — | 0.913 | 0.900 |
+| Label precision@3 (rerank) | — | — | 0.667 | **0.700** |
+
+## Reusable infrastructure shipped
+
+- `scripts/grid-search-retrieval.mjs` — sweeps the hyperparameter space, reports per-config metrics, picks winners by nDCG/top-1/precision@3. Re-runnable on any pretrained store. Includes `--quick` mode for fast iteration.
+- Default value updates in `src/mcp-tools/neural-tools.ts` + schema descriptions.
+- Run JSONs at `docs/benchmarks/runs/grid-search-retrieval-{ts,latest}.json` with full config × metrics matrix.
+
+## Honest limits
+
+- **Single annotator** corpus (ADR-081 limitation).
+- **N=10 queries** — direction is robust (60-percentile differences) but per-config differences within ±2% are noise.
+- **Rerank joint re-grid is pending** — the rerank winner from the original grid was tested against OLD α/sw; a joint re-grid with new α/sw is the next ceiling-raiser.
+- **MMR may be unnecessary at λ=0.7** — at this λ MMR is essentially pure-relevance ordering. A future ADR could remove MMR entirely from the hybrid path and just use hybrid-score-descending.
+
+## Deliberately NOT in this round
+
+- **Joint rerank × α/sw grid** — tracked; would need ~75 rerank configs at ~1s each = 12 minutes. Worth one focused ADR.
+- **Default-on rerank** — still wrong as a default (1s/query). Rerank gain on top-1 (80→90%) is marginal vs hybrid alone (which already hits 90%).
+- **Removing MMR at high λ** — saves a small amount of compute but not a measurable relevance lift.
+
+## Verification
+
+```bash
+git clone https://github.com/ruvnet/ruflo && cd ruflo
+npm install && ( cd v3/@claude-flow/cli && npx tsc )
+
+# Pretrain
+node v3/@claude-flow/cli/scripts/pretrain-from-github.mjs
+
+# Grid-search (full grid, ~1 min)
+cd v3/@claude-flow/cli && node scripts/grid-search-retrieval.mjs
+
+# Confirm new defaults on canonical bench
+BENCH_NO_WRITE=1 node scripts/benchmark-pretrained-retrieval.mjs # hybrid → nDCG@3 0.963
+RERANK=1 BENCH_NO_WRITE=1 node scripts/benchmark-pretrained-retrieval.mjs # rerank → nDCG@3 0.900
+```