fix(intelligence): address PE architecture review — RepositoryIdentity constructor + AnalysisCache hash reuse

- GraphBuilder now accepts RepositoryIdentity + extractorVersion as constructor params;
  Provenance is derived internally (never constructed externally by callers)
- Analyzer and EnrichCommand updated to pass RepositoryIdentity directly to GraphBuilder
- AnalysisCache.getHashForPath() added for reverse path→hash lookup
- buildFileInventory() now populates FileEntry.contentHash from cache (no file re-reads)

Addresses BLOCKING 2 and BLOCKING 3 from PE review on RAN-150.

Co-Authored-By: Paperclip <noreply@paperclip.ing>

Author: aksOps

src/main/java/io/github/randomcodespace/iq/analyzer/Analyzer.java

@@ -13,11 +13,9 @@
 import io.github.randomcodespace.iq.detector.DetectorResult;
 import io.github.randomcodespace.iq.detector.DetectorUtils;
 import io.github.randomcodespace.iq.grammar.AntlrParserFactory;
-import io.github.randomcodespace.iq.intelligence.CapabilityLevel;
 import io.github.randomcodespace.iq.intelligence.FileClassification;
 import io.github.randomcodespace.iq.intelligence.FileEntry;
 import io.github.randomcodespace.iq.intelligence.FileInventory;
-import io.github.randomcodespace.iq.intelligence.Provenance;
 import io.github.randomcodespace.iq.intelligence.RepositoryIdentity;
 import io.github.randomcodespace.iq.model.CodeEdge;
 import io.github.randomcodespace.iq.model.CodeNode;
@@ -236,14 +234,7 @@ private AnalysisResult runWithCache(Path root, Integer parallelism, AnalysisCach
 
         // 1b. Resolve repository identity and build file inventory
         RepositoryIdentity repoIdentity = RepositoryIdentity.resolve(root);
-        FileInventory fileInventory = buildFileInventory(files);
-        Provenance provenance = new Provenance(
-                repoIdentity.repoUrl(),
-                repoIdentity.commitSha(),
-                VersionCommand.VERSION,
-                Provenance.CURRENT_SCHEMA_VERSION,
-                CapabilityLevel.PARTIAL
-        );
+        FileInventory fileInventory = buildFileInventory(files, cache);
 
         // Compute language breakdown
         Map<String, Integer> languageBreakdown = new HashMap<>();
@@ -318,7 +309,7 @@ private AnalysisResult runWithCache(Path root, Integer parallelism, AnalysisCach
 
         // 3. Build graph (batched)
         report.accept("Building graph...");
-        var builder = new GraphBuilder(provenance);
+        var builder = new GraphBuilder(repoIdentity, VersionCommand.VERSION);
         int filesAnalyzed = 0;
         for (int i = 0; i < resultSlots.length; i++) {
             DetectorResult result = resultSlots[i];
@@ -347,7 +338,7 @@ private AnalysisResult runWithCache(Path root, Integer parallelism, AnalysisCach
         String projectDirName = root.getFileName() != null ? root.getFileName().toString() : "root";
         var serviceResult = serviceDetector.detect(allNodes, builder.getEdges(), projectDirName, root);
         if (!serviceResult.serviceNodes().isEmpty()) {
-            serviceResult.serviceNodes().forEach(n -> n.setProvenance(provenance));
+            serviceResult.serviceNodes().forEach(n -> n.setProvenance(builder.getProvenance()));
             builder.addNodes(serviceResult.serviceNodes());
             builder.addEdges(serviceResult.serviceEdges());
             allNodes = builder.getNodes(); // refresh reference after adding service nodes
@@ -1278,14 +1269,16 @@ DetectorResult analyzeFile(DiscoveredFile file, Path repoPath, DetectorRegistry
 
     /**
      * Build a deterministic FileInventory from the list of discovered files.
-     * Content hashes are not computed here (too expensive at discovery time); they remain null.
+     * Content hashes are reused from {@code cache} when available (no re-read of files).
+     * Hashes remain null for files not yet present in the cache.
      */
-    private static FileInventory buildFileInventory(List<DiscoveredFile> files) {
+    private static FileInventory buildFileInventory(List<DiscoveredFile> files, AnalysisCache cache) {
         List<FileEntry> entries = new ArrayList<>(files.size());
         for (DiscoveredFile f : files) {
             String relPath = f.path().toString().replace('\\', '/');
             FileClassification cls = FileEntry.classify(relPath, f.language());
-            entries.add(new FileEntry(relPath, f.language(), f.sizeBytes(), null, cls));
+            String contentHash = cache != null ? cache.getHashForPath(relPath) : null;
+            entries.add(new FileEntry(relPath, f.language(), f.sizeBytes(), contentHash, cls));
         }
         return new FileInventory(entries);
     }

src/main/java/io/github/randomcodespace/iq/analyzer/GraphBuilder.java

@@ -3,7 +3,9 @@
 import io.github.randomcodespace.iq.analyzer.linker.LinkResult;
 import io.github.randomcodespace.iq.analyzer.linker.Linker;
 import io.github.randomcodespace.iq.detector.DetectorResult;
+import io.github.randomcodespace.iq.intelligence.CapabilityLevel;
 import io.github.randomcodespace.iq.intelligence.Provenance;
+import io.github.randomcodespace.iq.intelligence.RepositoryIdentity;
 import io.github.randomcodespace.iq.model.CodeEdge;
 import io.github.randomcodespace.iq.model.CodeNode;
 import org.slf4j.Logger;
@@ -45,15 +47,38 @@ public GraphBuilder(int batchSize) {
         this(batchSize, null);
     }
 
-    public GraphBuilder(Provenance provenance) {
-        this(1000, provenance);
+    /**
+     * Construct with repository identity and extractor version.
+     * Provenance is derived internally from the identity.
+     */
+    public GraphBuilder(RepositoryIdentity identity, String extractorVersion) {
+        this(1000, identity, extractorVersion);
+    }
+
+    /**
+     * Construct with batch size, repository identity, and extractor version.
+     * Provenance is derived internally from the identity.
+     */
+    public GraphBuilder(int batchSize, RepositoryIdentity identity, String extractorVersion) {
+        this(batchSize, identity == null ? null : new Provenance(
+                identity.repoUrl(),
+                identity.commitSha(),
+                extractorVersion,
+                Provenance.CURRENT_SCHEMA_VERSION,
+                CapabilityLevel.PARTIAL
+        ));
     }
 
-    public GraphBuilder(int batchSize, Provenance provenance) {
+    private GraphBuilder(int batchSize, Provenance provenance) {
         this.batchSize = Math.max(1, batchSize);
         this.provenance = provenance;
     }
 
+    /** Returns the provenance stamped on every node, or null if none was configured. */
+    public Provenance getProvenance() {
+        return provenance;
+    }
+
     /**
      * Add all nodes and edges from a detector result.
      */

src/main/java/io/github/randomcodespace/iq/cache/AnalysisCache.java

@@ -153,6 +153,23 @@ public synchronized boolean isCached(String contentHash) {
         }
     }
 
+    /**
+     * Look up the content hash stored for a given file path.
+     * Returns null if the path has not been cached yet.
+     */
+    public synchronized String getHashForPath(String filePath) {
+        try (var stmt = conn.prepareStatement(
+                "SELECT content_hash FROM files WHERE path = ? LIMIT 1")) {
+            stmt.setString(1, filePath);
+            try (ResultSet rs = stmt.executeQuery()) {
+                return rs.next() ? rs.getString(1) : null;
+            }
+        } catch (SQLException e) {
+            log.debug("Hash lookup by path failed", e);
+            return null;
+        }
+    }
+
     // --- Store results ---
 
     /**

src/main/java/io/github/randomcodespace/iq/cli/EnrichCommand.java

@@ -5,8 +5,6 @@
 import io.github.randomcodespace.iq.analyzer.linker.Linker;
 import io.github.randomcodespace.iq.cache.AnalysisCache;
 import io.github.randomcodespace.iq.config.CodeIqConfig;
-import io.github.randomcodespace.iq.intelligence.CapabilityLevel;
-import io.github.randomcodespace.iq.intelligence.Provenance;
 import io.github.randomcodespace.iq.intelligence.RepositoryIdentity;
 import io.github.randomcodespace.iq.model.CodeEdge;
 import io.github.randomcodespace.iq.model.CodeNode;
@@ -120,14 +118,7 @@ private int enrichFromCache(AnalysisCache cache, Path root, NumberFormat nf, Ins
         // 2. Run linkers (these work on in-memory node/edge lists)
         CliOutput.step("\uD83D\uDD17", "Running cross-file linkers...");
         RepositoryIdentity repoIdentity = RepositoryIdentity.resolve(root);
-        Provenance provenance = new Provenance(
-                repoIdentity.repoUrl(),
-                repoIdentity.commitSha(),
-                VersionCommand.VERSION,
-                Provenance.CURRENT_SCHEMA_VERSION,
-                CapabilityLevel.PARTIAL
-        );
-        var builder = new GraphBuilder(provenance);
+        var builder = new GraphBuilder(repoIdentity, VersionCommand.VERSION);
         for (CodeNode node : allNodes) {
             builder.addNodes(List.of(node));
         }
@@ -158,7 +149,7 @@ private int enrichFromCache(AnalysisCache cache, Path root, NumberFormat nf, Ins
         String projectName = root.getFileName().toString();
         var serviceResult = serviceDetector.detect(enrichedNodes, enrichedEdges, projectName, root);
         if (!serviceResult.serviceNodes().isEmpty()) {
-            serviceResult.serviceNodes().forEach(n -> n.setProvenance(provenance));
+            serviceResult.serviceNodes().forEach(n -> n.setProvenance(builder.getProvenance()));
             // Add service nodes and edges to the builder
             builder.addNodes(serviceResult.serviceNodes());
             builder.addEdges(serviceResult.serviceEdges());