feat(enrichment): add near-verbatim duplication scan analyzer for review briefs

Author: GildardoDev

.env.example

@@ -65,17 +65,17 @@ GITTENSORY_REVIEW_ENRICHMENT=false
 # Current analyzer names:
 # dependency,lockfileDrift,secret,license,installScript,heavyDependency,actionPin,eol,redos
 # provenance,codeowners,secretLog,assetWeight,typosquat,commitSignature,iacMisconfig,nativeBuild
-# history,docCommentDrift
+# history,docCommentDrift,duplication
 #
 # Profile defaults:
 # fast: dependency,lockfileDrift,secret,license,installScript,heavyDependency,actionPin,eol
 # redos,provenance,secretLog,typosquat,iacMisconfig,nativeBuild
 # balanced (default): dependency,lockfileDrift,secret,license,installScript,heavyDependency
 # actionPin,eol,redos,provenance,codeowners,secretLog,assetWeight,typosquat,commitSignature
-# iacMisconfig,nativeBuild,history,docCommentDrift
+# iacMisconfig,nativeBuild,history,docCommentDrift,duplication
 # deep: dependency,lockfileDrift,secret,license,installScript,heavyDependency,actionPin,eol
 # redos,provenance,codeowners,secretLog,assetWeight,typosquat,commitSignature,iacMisconfig
-# nativeBuild,history,docCommentDrift
+# nativeBuild,history,docCommentDrift,duplication
 # END GENERATED REES ANALYZERS
 
 # Submitter-reputation spend control (internal-only): downgrades new/burst/low-rep

apps/gittensory-ui/src/lib/rees-analyzers.ts

@@ -505,6 +505,34 @@ export const REES_ANALYZERS = [
         "Conservative: only named function declarations with confidently-enumerable params; non-parameter signature edits are not reported.",
     },
   },
+  {
+    name: "duplication",
+    title: "Near-verbatim duplicated code",
+    category: "quality",
+    cost: "github-light",
+    defaultEnabled: true,
+    profiles: ["balanced", "deep"],
+    requires: ["files", "github-token", "head-sha"],
+    limits: {
+      minRun: 8,
+      maxCandidates: 40,
+      maxFetches: 30,
+      maxFindings: 25,
+      maxFileBytes: 500000,
+    },
+    docs: {
+      summary:
+        "Flags added code that is a near-verbatim duplicate of a block already present elsewhere in the repo.",
+      looksAt:
+        "Added diff hunks in changed source files compared against same-extension repo files fetched from the git tree at headSha.",
+      reports:
+        "The head file:line, the existing source file:line it duplicates, and the matched line count.",
+      network:
+        "Calls the GitHub API for the git tree and candidate blobs. Requires headSha and token forwarding for private repos.",
+      notes:
+        "Conservative: trivial/boilerplate lines are dropped and a long contiguous run is required, so incidental overlap is not flagged. Never returns code content.",
+    },
+  },
 ] as const satisfies readonly ReesAnalyzerDoc[];
 
 export const REES_ANALYZER_NAMES = REES_ANALYZERS.map((analyzer) => analyzer.name);

review-enrichment/analyzer-metadata.json

@@ -579,6 +579,36 @@
         "network": "Calls the GitHub API for changed file contents. Requires headSha and token forwarding for private repos.",
         "notes": "Conservative: only named function declarations with confidently-enumerable params; non-parameter signature edits are not reported."
       }
+    },
+    {
+      "name": "duplication",
+      "title": "Near-verbatim duplicated code",
+      "category": "quality",
+      "cost": "github-light",
+      "defaultEnabled": true,
+      "profiles": [
+        "balanced",
+        "deep"
+      ],
+      "requires": [
+        "files",
+        "github-token",
+        "head-sha"
+      ],
+      "limits": {
+        "minRun": 8,
+        "maxCandidates": 40,
+        "maxFetches": 30,
+        "maxFindings": 25,
+        "maxFileBytes": 500000
+      },
+      "docs": {
+        "summary": "Flags added code that is a near-verbatim duplicate of a block already present elsewhere in the repo.",
+        "looksAt": "Added diff hunks in changed source files compared against same-extension repo files fetched from the git tree at headSha.",
+        "reports": "The head file:line, the existing source file:line it duplicates, and the matched line count.",
+        "network": "Calls the GitHub API for the git tree and candidate blobs. Requires headSha and token forwarding for private repos.",
+        "notes": "Conservative: trivial/boilerplate lines are dropped and a long contiguous run is required, so incidental overlap is not flagged. Never returns code content."
+      }
     }
   ]
 }