group more related hunks

.gitignore

@@ -4,3 +4,5 @@ reviews/
 evals/fixtures/logs/
 node_modules/
 dist/
+evals/packet-dilution/logs/
+evals/skill-semantics/logs/

evals/packet-dilution/cap1.yml

@@ -0,0 +1,40 @@
+name: packet-dilution-cap1
+repeat: 6
+repo:
+  fixture: repos/settlement
+command:
+  branch: feature
+  base: main
+review:
+  provider: anthropic
+  model: claude-opus-4-8
+  reasoning: high
+  depth: normal
+  verify: true
+  cache: false
+  concurrency: 1
+  maxTimeMinutes: 20
+  lenses:
+    - lang/go
+  packRelatedHunks: true
+  packMaxHunks: 1
+  pinnedPlanPath: evals/packet-dilution/plans/frozen.json
+expect:
+  maxCostUSD: 3
+should_find:
+  - id: dilution-split-remainder
+    path: settlement/fees.go
+    failureModePattern: remainder|dust|lost|unallocated|sum|drop
+    titlePattern: split|fee|remainder|share
+  - id: dilution-cut-order
+    path: settlement/fees.go
+    failureModePattern: cap|order|before|under|rate|incorrect
+    titlePattern: platform|cut|cap|rate
+  - id: dilution-refund-gross
+    path: settlement/fees.go
+    failureModePattern: refund|gross|net|fee|over.?pay|double
+    titlePattern: refund|gross|net
+should_not_find:
+  - id: dilution-rate-guard-control
+    path: settlement/fees.go
+    titlePattern: Rule[0-9]+

evals/packet-dilution/cap3.yml

@@ -0,0 +1,40 @@
+name: packet-dilution-cap3
+repeat: 6
+repo:
+  fixture: repos/settlement
+command:
+  branch: feature
+  base: main
+review:
+  provider: anthropic
+  model: claude-opus-4-8
+  reasoning: high
+  depth: normal
+  verify: true
+  cache: false
+  concurrency: 1
+  maxTimeMinutes: 20
+  lenses:
+    - lang/go
+  packRelatedHunks: true
+  packMaxHunks: 3
+  pinnedPlanPath: evals/packet-dilution/plans/frozen.json
+expect:
+  maxCostUSD: 3
+should_find:
+  - id: dilution-split-remainder
+    path: settlement/fees.go
+    failureModePattern: remainder|dust|lost|unallocated|sum|drop
+    titlePattern: split|fee|remainder|share
+  - id: dilution-cut-order
+    path: settlement/fees.go
+    failureModePattern: cap|order|before|under|rate|incorrect
+    titlePattern: platform|cut|cap|rate
+  - id: dilution-refund-gross
+    path: settlement/fees.go
+    failureModePattern: refund|gross|net|fee|over.?pay|double
+    titlePattern: refund|gross|net
+should_not_find:
+  - id: dilution-rate-guard-control
+    path: settlement/fees.go
+    titlePattern: Rule[0-9]+

evals/packet-dilution/cap5.yml

@@ -0,0 +1,40 @@
+name: packet-dilution-cap5
+repeat: 6
+repo:
+  fixture: repos/settlement
+command:
+  branch: feature
+  base: main
+review:
+  provider: anthropic
+  model: claude-opus-4-8
+  reasoning: high
+  depth: normal
+  verify: true
+  cache: false
+  concurrency: 1
+  maxTimeMinutes: 20
+  lenses:
+    - lang/go
+  packRelatedHunks: true
+  packMaxHunks: 5
+  pinnedPlanPath: evals/packet-dilution/plans/frozen.json
+expect:
+  maxCostUSD: 3
+should_find:
+  - id: dilution-split-remainder
+    path: settlement/fees.go
+    failureModePattern: remainder|dust|lost|unallocated|sum|drop
+    titlePattern: split|fee|remainder|share
+  - id: dilution-cut-order
+    path: settlement/fees.go
+    failureModePattern: cap|order|before|under|rate|incorrect
+    titlePattern: platform|cut|cap|rate
+  - id: dilution-refund-gross
+    path: settlement/fees.go
+    failureModePattern: refund|gross|net|fee|over.?pay|double
+    titlePattern: refund|gross|net
+should_not_find:
+  - id: dilution-rate-guard-control
+    path: settlement/fees.go
+    titlePattern: Rule[0-9]+

evals/packet-dilution/plans/frozen.json

@@ -0,0 +1,164 @@
+{
+  "schemaVersion": 1,
+  "baseSha": "*",
+  "headSha": "*",
+  "planSha256": "52e62561b47bfa7ea5cdb59c7bf8a193a9183b01109c7ea644394f2d1f704dda",
+  "plan": {
+    "diffUnderstanding": {
+      "declaredIntent": "authored pinned plan for the packet-size recall curve",
+      "inferredBehavior": "uniform coverage so packet size is the only variable across arms"
+    },
+    "coverage": [
+      {
+        "hunkId": "d6df72ba",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "175c79f4",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "68109ebd",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "1ff3f41e",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "a8071418",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "53cf00c2",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "ffd09816",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "c9acf88b",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "18197703",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "bbacb370",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "a0be9fac",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "6ae88c80",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "b6e69463",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "d726dbb6",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      },
+      {
+        "hunkId": "fdc5646d",
+        "path": "limits/limits.go",
+        "coverage": "normal",
+        "lenses": [
+          "lang/go"
+        ],
+        "surroundingContextHints": [],
+        "reason": "authored uniform coverage"
+      }
+    ]
+  }
+}

evals/packet-dilution/repos/dilution/base/go.mod

@@ -0,0 +1,3 @@
+module dilution
+
+go 1.23