@ouro.bot/cli 0.1.0-alpha.54 → 0.1.0-alpha.55

package/changelog.json

@@ -1,6 +1,14 @@
 {
   "_note": "This changelog is maintained as part of the PR/version-bump workflow. Agent-curated, not auto-generated. Agents read this file directly via read_file to understand what changed between versions.",
   "versions": [
+    {
+      "version": "0.1.0-alpha.55",
+      "changes": [
+        "Memory fact dedup now catches paraphrased duplicates via cosine similarity on existing embeddings, so semantically equivalent facts no longer slip past the word-overlap check.",
+        "Semantic dedup gracefully handles corrupt JSONL entries with missing or undefined embeddings instead of crashing on bad data.",
+        "Cosine similarity is now imported from associative-recall instead of duplicated in the memory module."
+      ]
+    },
     {
       "version": "0.1.0-alpha.54",
       "changes": [

package/dist/mind/memory.js

@@ -33,7 +33,6 @@ var __importStar = (this && this.__importStar) || (function () {
     };
 })();
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.__memoryTestUtils = void 0;
 exports.ensureMemoryStorePaths = ensureMemoryStorePaths;
 exports.appendFactsWithDedup = appendFactsWithDedup;
 exports.readMemoryFacts = readMemoryFacts;
@@ -46,7 +45,9 @@ const crypto_1 = require("crypto");
 const config_1 = require("../heart/config");
 const identity_1 = require("../heart/identity");
 const runtime_1 = require("../nerves/runtime");
+const associative_recall_1 = require("./associative-recall");
 const DEDUP_THRESHOLD = 0.6;
+const SEMANTIC_DEDUP_THRESHOLD = 0.95;
 const ENTITY_TOKEN = /[a-z0-9]+/g;
 const DEFAULT_EMBEDDING_MODEL = "text-embedding-3-small";
 class OpenAIEmbeddingProvider {
@@ -177,13 +178,24 @@ function appendDailyFact(dailyDir, fact) {
     const dayPath = path.join(dailyDir, `${day}.jsonl`);
     fs.appendFileSync(dayPath, `${JSON.stringify(fact)}\n`, "utf8");
 }
-function appendFactsWithDedup(stores, incoming) {
+function appendFactsWithDedup(stores, incoming, options) {
     const existing = readExistingFacts(stores.factsPath);
     const all = [...existing];
     let added = 0;
     let skipped = 0;
+    const semanticThreshold = options?.semanticThreshold;
     for (const fact of incoming) {
-        const duplicate = all.some((prior) => overlapScore(prior.text, fact.text) > DEDUP_THRESHOLD);
+        const duplicate = all.some((prior) => {
+            if (overlapScore(prior.text, fact.text) > DEDUP_THRESHOLD)
+                return true;
+            if (semanticThreshold !== undefined &&
+                Array.isArray(fact.embedding) && fact.embedding.length > 0 &&
+                Array.isArray(prior.embedding) && prior.embedding.length > 0 &&
+                fact.embedding.length === prior.embedding.length) {
+                return (0, associative_recall_1.cosineSimilarity)(fact.embedding, prior.embedding) > semanticThreshold;
+            }
+            return false;
+        });
         if (duplicate) {
             skipped++;
             continue;
@@ -202,24 +214,6 @@ function appendFactsWithDedup(stores, incoming) {
     });
     return { added, skipped };
 }
-function cosineSimilarity(left, right) {
-    if (left.length === 0 || right.length === 0 || left.length !== right.length)
-        return 0;
-    let dot = 0;
-    let leftNorm = 0;
-    let rightNorm = 0;
-    for (let i = 0; i < left.length; i += 1) {
-        dot += left[i] * right[i];
-        leftNorm += left[i] * left[i];
-        rightNorm += right[i] * right[i];
-    }
-    if (leftNorm === 0 || rightNorm === 0)
-        return 0;
-    return dot / (Math.sqrt(leftNorm) * Math.sqrt(rightNorm));
-}
-exports.__memoryTestUtils = {
-    cosineSimilarity,
-};
 function createDefaultEmbeddingProvider() {
     const apiKey = (0, config_1.getOpenAIEmbeddingsApiKey)().trim();
     if (!apiKey)
@@ -271,7 +265,7 @@ async function saveMemoryFact(options) {
         createdAt: (options.now ?? (() => new Date()))().toISOString(),
         embedding,
     };
-    return appendFactsWithDedup(stores, [fact]);
+    return appendFactsWithDedup(stores, [fact], { semanticThreshold: SEMANTIC_DEDUP_THRESHOLD });
 }
 async function backfillEmbeddings(options) {
     const memoryRoot = options?.memoryRoot ?? path.join((0, identity_1.getAgentRoot)(), "psyche", "memory");
@@ -372,7 +366,7 @@ async function searchMemoryFacts(query, facts, embeddingProvider) {
             .filter((fact) => fact.embedding.length === queryEmbedding.length)
             .map((fact) => ({
             fact,
-            score: cosineSimilarity(queryEmbedding, fact.embedding),
+            score: (0, associative_recall_1.cosineSimilarity)(queryEmbedding, fact.embedding),
         }))
             .filter((entry) => entry.score > 0)
             .sort((left, right) => right.score - left.score)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ouro.bot/cli",
-  "version": "0.1.0-alpha.54",
+  "version": "0.1.0-alpha.55",
   "main": "dist/heart/daemon/ouro-entry.js",
   "bin": {
     "cli": "dist/heart/daemon/ouro-bot-entry.js",