@equationalapplications/core-llm-wiki 7.7.0 → 7.7.2

package/README.md

@@ -361,6 +361,7 @@ new WikiMemory(db, {
   - Instructions, the ontology manifest, existing facts and identifiers never count, so a model cannot ground a claim by quoting them.
 - **The check.** Both sides are normalized with NFKC, whitespace runs collapse to one space, and matching is case-sensitive. A fact with more than 10 quotes, or any quote not found, fails.
 - **Diagnostics.** `grounding_missing` (reasons `no_evidence`, `evidence_too_short`) and `grounding_failed` (reasons `quote_not_found`, `too_many_quotes`), one per fact, with the new fact's `factId`. Quotes are never included.
+- **Duplicate titles in one ingest.** When chunks yield facts with the same title, ingest keeps one: a grounded fact beats one with missing or failed evidence, and on a tie the first one wins. The others are reported as `fact_deduplicated`. A fact already stored for the same `sourceRef` is not replaced by a later partial ingest.
 - **`upsertGraph`** nodes are host-supplied and never grounded.
 - **Librarian and heal** synthesize across events, so their pass rates are unknown. Measure them on your own event log before opting them in.
 - Evidence quotes are not stored.

package/dist/{chunk-VOSMYISQ.mjs → chunk-NWODQRSM.mjs}

@@ -2166,11 +2166,16 @@ var IngestionService = class {
       let ingestedChunks = 0;
       let failedChunks = 0;
       const failures = [];
-      const seen = /* @__PURE__ */ new Set();
-      const orderedChunkFacts = [];
-      const groundingLedger = /* @__PURE__ */ new Map();
+      const winners = /* @__PURE__ */ new Map();
       const diagBuffer = new DiagnosticBuffer();
       const diagBase = { entityId, operation: "ingest", trigger: "call" };
+      const pushDeduplicated = (chunkIndex, itemIndex) => {
+        diagBuffer.push({
+          ...diagBase,
+          code: "fact_deduplicated",
+          detail: { sourceRef, chunkIndex, itemIndex, reason: "exact_title" }
+        });
+      };
       for (const [chunkIndex, slot] of chunkResults.entries()) {
         if (slot.status === "failed") {
           failedChunks++;
@@ -2181,22 +2186,32 @@ var IngestionService = class {
         for (const r of slot.rejected) {
           diagBuffer.push({ ...diagBase, code: "fact_rejected", detail: { sourceRef, chunkIndex, itemIndex: r.itemIndex, reason: r.reason } });
         }
-        const dedupedFacts = [];
         slot.facts.forEach((fact, k) => {
-          const normalizedTitle = normalizeTitleKey(fact.title);
-          if (!seen.has(normalizedTitle)) {
-            seen.add(normalizedTitle);
-            dedupedFacts.push(fact);
-            if (ingestGrounding) groundingLedger.set(fact, { verdict: slot.verdicts[k], chunkIndex, itemIndex: slot.itemIndexes[k] });
+          const key = normalizeTitleKey(fact.title);
+          const candidate = { chunkIndex, k, itemIndex: slot.itemIndexes[k], rank: slot.verdicts[k]?.status === "grounded" ? 1 : 0 };
+          const current = winners.get(key);
+          if (!current) {
+            winners.set(key, candidate);
+          } else if (candidate.rank > current.rank) {
+            pushDeduplicated(current.chunkIndex, current.itemIndex);
+            winners.set(key, candidate);
           } else {
-            diagBuffer.push({
-              ...diagBase,
-              code: "fact_deduplicated",
-              detail: { sourceRef, chunkIndex, itemIndex: slot.itemIndexes[k], reason: "exact_title" }
-            });
+            pushDeduplicated(candidate.chunkIndex, candidate.itemIndex);
           }
         });
-        orderedChunkFacts.push({ facts: dedupedFacts, ontology_updates: slot.ontology_updates });
+      }
+      const orderedChunkFacts = [];
+      const groundingLedger = /* @__PURE__ */ new Map();
+      for (const [chunkIndex, slot] of chunkResults.entries()) {
+        if (slot.status === "failed") continue;
+        const keptFacts = [];
+        slot.facts.forEach((fact, k) => {
+          const winner = winners.get(normalizeTitleKey(fact.title));
+          if (winner?.chunkIndex !== chunkIndex || winner.k !== k) return;
+          keptFacts.push(fact);
+          if (ingestGrounding) groundingLedger.set(fact, { verdict: slot.verdicts[k], chunkIndex, itemIndex: winner.itemIndex });
+        });
+        orderedChunkFacts.push({ facts: keptFacts, ontology_updates: slot.ontology_updates });
       }
       for (const reason of ["parse", "llm"]) {
         const ofReason = failures.filter((f) => f.source === reason);
@@ -5626,5 +5641,5 @@ var WriteService = class {
 };
 
 export { BaseRepository, DEFAULT_CHUNK_OVERLAP, DEFAULT_MAX_CHUNK_LENGTH, DEFAULT_MAX_EMBED_CHARS, DiagnosticBuffer, EMBED_CHARS_CEILING, EmbeddingService, HEAL_ANCHORS_PER_CANDIDATE, HEAL_BATCH_SIZE, HEAL_MAX_FACT_BODY_CHARS_L3, HEAL_MAX_TASKS, HEAL_RECHECK_MS, HOOK_TIMEOUT_MARKER, ImportExportService, IngestionService, JobManager, MaintenanceService, MetadataRepository, ONTOLOGY_BACKFILL_BATCH_SIZE, ONTOLOGY_BACKFILL_MAX_PROMPT_CHARS, ONTOLOGY_BACKFILL_RECHECK_MS, ONTOLOGY_BACKFILL_SYSTEM_PROMPT, PromptService, PrunePartialFailureError, RetrievalService, SearchService, WikiBusyError, WikiDraftNotFound, WikiDuplicateHashError, WikiGraphNodeOwnershipConflict, WikiIngestEmptyError, WikiInvalidReadOptions, WikiParseError, WikiSourceRefHashCollision, WikiStrictOntologyViolation, WikiTransactionError, WriteService, __privateAdd, __privateGet, __privateSet, chunkText, configureRandomSource, edgeTripleAllowed, emptyManifest, entitySummaryMetaKey, extractSqliteCode, generateId, normalizeSourceHash, normalizeSourceRef, normalizeTitleKey, parseEmbedding, resolveEdgeDefinitions, resolveGrounding, resolveNodeType, safeSlice, typeSatisfies, validateInlineEdges, validateManifest };
-//# sourceMappingURL=chunk-VOSMYISQ.mjs.map
-//# sourceMappingURL=chunk-VOSMYISQ.mjs.map
+//# sourceMappingURL=chunk-NWODQRSM.mjs.map
+//# sourceMappingURL=chunk-NWODQRSM.mjs.map