@claude-flow/cli 3.23.0 → 3.25.0

package/.claude/eval/human-relevance-frozen-v1.json

@@ -0,0 +1,17 @@
+{
+  "version": "human-relevance-frozen-v1",
+  "description": "Frozen, public, human-labeled relevance eval set (ADR-081). Immutable — the red/blue anchor the flywheel must never regress AND against which per-generation human-relevance deltas are reported. Do not edit; supersede with a new version file.",
+  "metric": "nDCG@3 over labelled substring-relevance",
+  "tasks": [
+    { "id": "hr-0", "q": "how was the Opus model alias fixed", "labels": ["opus 4.8", "opus alias", "opus model alias", "#2232"] },
+    { "id": "hr-1", "q": "self-learning wiring task-completed pretrain", "labels": ["self-learning", "adr-074", "#2245", "task-completed"] },
+    { "id": "hr-2", "q": "deterministic codemod engine var-to-const", "labels": ["deterministic tier-1 codemod", "adr-143", "codemod", "var-to-const"] },
+    { "id": "hr-3", "q": "MCP server orphan leak parent-death", "labels": ["mcp orphan", "parent-death", "#2234", "orphan on every claude"] },
+    { "id": "hr-4", "q": "unified learning stats aggregator", "labels": ["unified learning-stats", "adr-075"] },
+    { "id": "hr-5", "q": "structured distillation 4-field schema", "labels": ["structured distillation", "adr-076", "4-field schema"] },
+    { "id": "hr-6", "q": "SQL injection migrate.ts table identifier", "labels": ["sql injection", "migrate.ts", "agentdb", "cve"] },
+    { "id": "hr-7", "q": "recall@k HNSW benchmark harness", "labels": ["hnsw", "recall@k", "benchmark intelligence"] },
+    { "id": "hr-8", "q": "Q-learning encoder keyword block", "labels": ["q-state encoder", "keyword block", "#2239", "q-encoder"] },
+    { "id": "hr-9", "q": "security hardening crypto random IDs", "labels": ["cwe-347", "crypto.randomuuid", "random id", "crypto random"] }
+  ]
+}

package/.claude/evolve-proof/generation-0.json

@@ -0,0 +1,211 @@
+{
+  "label": "single-round proof-of-mechanism",
+  "disclaimers": [
+    "not flywheel proof",
+    "not compounding learning",
+    "not production learning"
+  ],
+  "generation": 0,
+  "parent": null,
+  "branch": "main",
+  "kind": "synthetic",
+  "createdAt": 1700000000000,
+  "inputHoldoutHash": "sha256:3cb58b6d4cd6fe6f0fa1f114d604b5743963eb96c3b9648508bf2ea502dad9f9",
+  "baselineManifestHash": "sha256:ea6643a45ebd3578fedfbe44774d22327f6852115c8670c5ae2996652060f6d8",
+  "candidateManifestHash": "sha256:d17cbe4d0bd2ff9a73d9bcb706905858e5a4b01bca074c6235e479505487e126",
+  "meetsPromotionRule": {
+    "version": "accept/v1+sig",
+    "result": true
+  },
+  "decisionReceipt": {
+    "promotionRuleVersion": "accept/v1+sig",
+    "verdictInputs": {
+      "heldOutScore": 0.7520000000000001,
+      "baselineHeldOutScore": 0.656,
+      "redblue": "PASS",
+      "drift": 0,
+      "driftThreshold": 0.05,
+      "replayDeterministic": true,
+      "receiptCoverage": 1,
+      "canaryRollbackRate": 0,
+      "baselineRollbackRate": 0
+    },
+    "result": {
+      "accept": true,
+      "terms": {
+        "held_out_improves": {
+          "value": "0.7520 > 0.6560",
+          "pass": true
+        },
+        "redblue_pass": {
+          "value": "PASS",
+          "pass": true
+        },
+        "drift_within": {
+          "value": "0 <= 0.05",
+          "pass": true
+        },
+        "replay_deterministic": {
+          "value": true,
+          "pass": true
+        },
+        "receipt_coverage_full": {
+          "value": 1,
+          "pass": true
+        },
+        "canary_no_worse": {
+          "value": "0 <= 0",
+          "pass": true
+        }
+      },
+      "failed": []
+    },
+    "significant": true,
+    "deltaCILow": 0.07600000000000004,
+    "promoted": true,
+    "reason": "promoted (all accept/v1+sig terms held)"
+  },
+  "shadow": {
+    "registrationId": "shadow:44b2b4e021f61a1482f1c3e8794517d4abcb490398d73dbaa70be96978cf39c0",
+    "state": "shadow",
+    "served": false,
+    "candidateManifestHash": "sha256:d17cbe4d0bd2ff9a73d9bcb706905858e5a4b01bca074c6235e479505487e126",
+    "registeredAt": 1700000000000
+  },
+  "costReceipt": {
+    "usd": 0,
+    "llmCalls": 0,
+    "tier": "synthetic",
+    "notes": "deterministic synthetic round — no model, no network, no real store"
+  },
+  "mutationClass": "retrieval:multi",
+  "mutationSummary": "alpha:0.5→0.3, bodyWeight:1→1.5, mmrLambda:0.7→0.5, subjectWeight:2→1, typePenaltyFactor:1→0.5",
+  "deltas": {
+    "benchmark": 0.09600000000000009,
+    "security": 0,
+    "cost": 0
+  },
+  "promotion": {
+    "parentManifestHash": null,
+    "candidateManifestHash": "sha256:d17cbe4d0bd2ff9a73d9bcb706905858e5a4b01bca074c6235e479505487e126",
+    "mutationClass": "retrieval:multi",
+    "mutationSummary": "alpha:0.5→0.3, bodyWeight:1→1.5, mmrLambda:0.7→0.5, subjectWeight:2→1, typePenaltyFactor:1→0.5",
+    "deltas": {
+      "benchmark": 0.09600000000000009,
+      "security": 0,
+      "cost": 0
+    },
+    "decisionReceipt": {
+      "promotionRuleVersion": "accept/v1+sig",
+      "verdictInputs": {
+        "heldOutScore": 0.7520000000000001,
+        "baselineHeldOutScore": 0.656,
+        "redblue": "PASS",
+        "drift": 0,
+        "driftThreshold": 0.05,
+        "replayDeterministic": true,
+        "receiptCoverage": 1,
+        "canaryRollbackRate": 0,
+        "baselineRollbackRate": 0
+      },
+      "result": {
+        "accept": true,
+        "terms": {
+          "held_out_improves": {
+            "value": "0.7520 > 0.6560",
+            "pass": true
+          },
+          "redblue_pass": {
+            "value": "PASS",
+            "pass": true
+          },
+          "drift_within": {
+            "value": "0 <= 0.05",
+            "pass": true
+          },
+          "replay_deterministic": {
+            "value": true,
+            "pass": true
+          },
+          "receipt_coverage_full": {
+            "value": 1,
+            "pass": true
+          },
+          "canary_no_worse": {
+            "value": "0 <= 0",
+            "pass": true
+          }
+        },
+        "failed": []
+      },
+      "significant": true,
+      "deltaCILow": 0.07600000000000004,
+      "promoted": true,
+      "reason": "promoted (all accept/v1+sig terms held)"
+    }
+  },
+  "regression": null,
+  "holdout": [
+    {
+      "taskId": "t0",
+      "baselineScore": 0.6,
+      "candidateScore": 0.7
+    },
+    {
+      "taskId": "t1",
+      "baselineScore": 0.8,
+      "candidateScore": 0.86
+    },
+    {
+      "taskId": "t2",
+      "baselineScore": 0.5,
+      "candidateScore": 0.62
+    },
+    {
+      "taskId": "t3",
+      "baselineScore": 0.72,
+      "candidateScore": 0.8
+    },
+    {
+      "taskId": "t4",
+      "baselineScore": 0.66,
+      "candidateScore": 0.78
+    }
+  ],
+  "baselineManifest": {
+    "schema": "ruflo.proven-config/v1",
+    "policy": {
+      "ref": "sha256:0e7ffc6910134ff6ec2c1074165ee4571ed5df973c777b613c6dac6fea1c46a8",
+      "value": {
+        "alpha": 0.5,
+        "subjectWeight": 2,
+        "mmrLambda": 0.7,
+        "bodyWeight": 1,
+        "typePenaltyFactor": 1
+      }
+    },
+    "layer": "synthetic/proof",
+    "benchmark": {
+      "corpus": "synthetic-proof-v1",
+      "corpusHash": "sha256:3b8a34acbcd0e385ca4d9ddc177f8ea93152d98c29c46d9286419b492beded1b"
+    }
+  },
+  "candidateManifest": {
+    "schema": "ruflo.proven-config/v1",
+    "policy": {
+      "ref": "sha256:6141a8ea990c5063b77e090ae8f37f9c539d8aa8f58dcceb30f3a82f97e57319",
+      "value": {
+        "alpha": 0.3,
+        "subjectWeight": 1,
+        "mmrLambda": 0.5,
+        "bodyWeight": 1.5,
+        "typePenaltyFactor": 0.5
+      }
+    },
+    "layer": "synthetic/proof",
+    "benchmark": {
+      "corpus": "synthetic-proof-v1",
+      "corpusHash": "sha256:3b8a34acbcd0e385ca4d9ddc177f8ea93152d98c29c46d9286419b492beded1b"
+    }
+  }
+}

package/.claude/evolve-proof/real-generation-0.json

@@ -0,0 +1,406 @@
+{
+  "label": "single-round proof-of-mechanism",
+  "disclaimers": [
+    "not flywheel proof",
+    "not compounding learning",
+    "not production learning"
+  ],
+  "generation": 0,
+  "parent": null,
+  "branch": "main",
+  "kind": "real",
+  "createdAt": 1700000200000,
+  "inputHoldoutHash": "sha256:1dae6f77f11f621990b501de0eb9a014ef985b7c98b8e87bcc4813589efcf45c",
+  "baselineManifestHash": "sha256:11704de261dc1364da321c6cc6781a6116c58d453f650e23d36cecbf3ffff82e",
+  "candidateManifestHash": "sha256:3515c407c0555d491432fdce2405389fa6d33831fc64d342364defbf7cf7ffef",
+  "meetsPromotionRule": {
+    "version": "accept/v1+sig",
+    "result": true
+  },
+  "decisionReceipt": {
+    "promotionRuleVersion": "accept/v1+sig",
+    "verdictInputs": {
+      "heldOutScore": 0.7575757575757577,
+      "baselineHeldOutScore": 0.49583333333333335,
+      "redblue": "PASS",
+      "drift": 0,
+      "driftThreshold": 0.05,
+      "replayDeterministic": true,
+      "receiptCoverage": 1,
+      "canaryRollbackRate": 0,
+      "baselineRollbackRate": 0
+    },
+    "result": {
+      "accept": true,
+      "terms": {
+        "held_out_improves": {
+          "value": "0.7576 > 0.4958",
+          "pass": true
+        },
+        "redblue_pass": {
+          "value": "PASS",
+          "pass": true
+        },
+        "drift_within": {
+          "value": "0 <= 0.05",
+          "pass": true
+        },
+        "replay_deterministic": {
+          "value": true,
+          "pass": true
+        },
+        "receipt_coverage_full": {
+          "value": 1,
+          "pass": true
+        },
+        "canary_no_worse": {
+          "value": "0 <= 0",
+          "pass": true
+        }
+      },
+      "failed": []
+    },
+    "significant": true,
+    "deltaCILow": 0.18143939393939393,
+    "promoted": true,
+    "reason": "promoted (all accept/v1+sig terms held)"
+  },
+  "shadow": {
+    "registrationId": "shadow:ead9bee64a9b9571f38228928eb494353505e8a58cce9127c6b0a4bf95a51656",
+    "state": "shadow",
+    "served": false,
+    "candidateManifestHash": "sha256:3515c407c0555d491432fdce2405389fa6d33831fc64d342364defbf7cf7ffef",
+    "registeredAt": 1700000200000
+  },
+  "costReceipt": {
+    "usd": 0,
+    "llmCalls": 0,
+    "tier": "real-local",
+    "notes": "measured on the frozen anchor via live retrieval — no LLM, no network"
+  },
+  "mutationClass": "retrieval:multi",
+  "mutationSummary": "alpha:0.5→0.3, mmrLambda:0.7→0.9, subjectWeight:2→1",
+  "deltas": {
+    "benchmark": 0.26174242424242433,
+    "security": 0,
+    "cost": 0
+  },
+  "promotion": {
+    "parentManifestHash": null,
+    "candidateManifestHash": "sha256:3515c407c0555d491432fdce2405389fa6d33831fc64d342364defbf7cf7ffef",
+    "mutationClass": "retrieval:multi",
+    "mutationSummary": "alpha:0.5→0.3, mmrLambda:0.7→0.9, subjectWeight:2→1",
+    "deltas": {
+      "benchmark": 0.26174242424242433,
+      "security": 0,
+      "cost": 0
+    },
+    "decisionReceipt": {
+      "promotionRuleVersion": "accept/v1+sig",
+      "verdictInputs": {
+        "heldOutScore": 0.7575757575757577,
+        "baselineHeldOutScore": 0.49583333333333335,
+        "redblue": "PASS",
+        "drift": 0,
+        "driftThreshold": 0.05,
+        "replayDeterministic": true,
+        "receiptCoverage": 1,
+        "canaryRollbackRate": 0,
+        "baselineRollbackRate": 0
+      },
+      "result": {
+        "accept": true,
+        "terms": {
+          "held_out_improves": {
+            "value": "0.7576 > 0.4958",
+            "pass": true
+          },
+          "redblue_pass": {
+            "value": "PASS",
+            "pass": true
+          },
+          "drift_within": {
+            "value": "0 <= 0.05",
+            "pass": true
+          },
+          "replay_deterministic": {
+            "value": true,
+            "pass": true
+          },
+          "receipt_coverage_full": {
+            "value": 1,
+            "pass": true
+          },
+          "canary_no_worse": {
+            "value": "0 <= 0",
+            "pass": true
+          }
+        },
+        "failed": []
+      },
+      "significant": true,
+      "deltaCILow": 0.18143939393939393,
+      "promoted": true,
+      "reason": "promoted (all accept/v1+sig terms held)"
+    }
+  },
+  "regression": null,
+  "holdout": [
+    {
+      "taskId": "hv-pattern-1780161324685-1d-tgm8",
+      "baselineScore": 0,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324686-1g-p25o",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324686-1j-m5hq",
+      "baselineScore": 1,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324686-1m-j0ig",
+      "baselineScore": 0,
+      "candidateScore": 0
+    },
+    {
+      "taskId": "hv-pattern-1780161324687-1p-2lpj",
+      "baselineScore": 0,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324687-1s-ibq9",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324688-1v-qvm9",
+      "baselineScore": 0.3333333333333333,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324688-1y-hjpj",
+      "baselineScore": 0.3333333333333333,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324689-21-o5x6",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324689-24-hkmf",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324690-27-igfa",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324690-2a-6t0p",
+      "baselineScore": 0.25,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324690-2d-5hqx",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324691-2g-grco",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324691-2j-zfni",
+      "baselineScore": 0.2,
+      "candidateScore": 0.25
+    },
+    {
+      "taskId": "hv-pattern-1780161324691-2m-wx6m",
+      "baselineScore": 0,
+      "candidateScore": 0
+    },
+    {
+      "taskId": "hv-pattern-1780161324692-2p-8jhd",
+      "baselineScore": 0,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324692-2s-c4t4",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324692-2v-afrs",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324693-2y-2ozh",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324693-31-ac3v",
+      "baselineScore": 0,
+      "candidateScore": 0.3333333333333333
+    },
+    {
+      "taskId": "hv-pattern-1780161324694-34-ysmt",
+      "baselineScore": 0,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324694-37-lvvk",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324694-3a-i470",
+      "baselineScore": 0,
+      "candidateScore": 0.25
+    },
+    {
+      "taskId": "hv-pattern-1780161324695-3d-9awr",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324695-3g-y9cu",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324695-3j-wi4w",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324696-3m-tzr2",
+      "baselineScore": 0.25,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324696-3p-49pp",
+      "baselineScore": 0,
+      "candidateScore": 0
+    },
+    {
+      "taskId": "hv-pattern-1780161324698-3s-5w1r",
+      "baselineScore": 0.25,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324698-3v-4fri",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324698-3y-v3g2",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324699-41-hvmz",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324699-44-nys5",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324699-47-jghz",
+      "baselineScore": 0,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324700-4a-3pj8",
+      "baselineScore": 0.5,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324700-4d-rmrn",
+      "baselineScore": 0.2,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324700-4g-tb58",
+      "baselineScore": 0,
+      "candidateScore": 0
+    },
+    {
+      "taskId": "hv-pattern-1780161324701-4j-kodm",
+      "baselineScore": 0,
+      "candidateScore": 0
+    },
+    {
+      "taskId": "hv-pattern-1780161324701-4m-dt4j",
+      "baselineScore": 0.5,
+      "candidateScore": 0.5
+    },
+    {
+      "taskId": "hv-pattern-1780161324701-4p-e7fi",
+      "baselineScore": 0,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324702-4s-bo8j",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324702-4v-6orz",
+      "baselineScore": 1,
+      "candidateScore": 1
+    },
+    {
+      "taskId": "hv-pattern-1780161324702-4y-0o2q",
+      "baselineScore": 1,
+      "candidateScore": 1
+    }
+  ],
+  "baselineManifest": {
+    "schema": "ruflo.proven-config/v1",
+    "policy": {
+      "ref": "sha256:0e7ffc6910134ff6ec2c1074165ee4571ed5df973c777b613c6dac6fea1c46a8",
+      "value": {
+        "alpha": 0.5,
+        "subjectWeight": 2,
+        "mmrLambda": 0.7,
+        "bodyWeight": 1,
+        "typePenaltyFactor": 1
+      }
+    },
+    "layer": "real/retrieval",
+    "benchmark": {
+      "corpus": "harvested-selfsup-frozen-v1",
+      "corpusHash": "sha256:cfeda09c42a88e2dc86efd650ff167880d7482a8e1af176bf861a09e6cca01be"
+    }
+  },
+  "candidateManifest": {
+    "schema": "ruflo.proven-config/v1",
+    "policy": {
+      "ref": "sha256:7caf5bfd2878b84825b5f641f447a9ecaf177258fecd8b4e82d823d98fb84097",
+      "value": {
+        "alpha": 0.3,
+        "subjectWeight": 1,
+        "mmrLambda": 0.9,
+        "bodyWeight": 1,
+        "typePenaltyFactor": 1
+      }
+    },
+    "layer": "real/retrieval",
+    "benchmark": {
+      "corpus": "harvested-selfsup-frozen-v1",
+      "corpusHash": "sha256:cfeda09c42a88e2dc86efd650ff167880d7482a8e1af176bf861a09e6cca01be"
+    }
+  }
+}