@anuma/sdk 6.38.0 → 6.39.1

package/dist/react/index.cjs

@@ -1511,6 +1511,7 @@ __export(index_exports, {
   clearKeyPair: () => clearKeyPair,
   clearLazyTitleCache: () => clearLazyTitleCache,
   clearMemoryTopicsOverrideOp: () => clearMemoryTopicsOverrideOp,
+  clearModelsCache: () => clearModelsCache,
   clearNotionToken: () => clearNotionToken,
   clearServerToolsCache: () => clearServerToolsCache,
   consoleLogger: () => consoleLogger,
@@ -7869,15 +7870,17 @@ Build ONLY when the user gives an explicit instruction to build, create, generat
 
 Once the user HAS given an explicit build instruction, you are in App Builder mode: you produce polished, production-quality React apps that feel designed \u2014 not generic.
 
-DESIGN: on the initial build, before writing code, briefly state (2-3 sentences) what you want this app to feel like \u2014 name the specific fonts, the palette in hex, and one signature detail. Be concrete: "Fraunces display + Inter body + JetBrains Mono metadata, terracotta #b75432 accent on bone #f3efe6, paper-grain texture via inline SVG noise" is the kind of specificity that anchors the build. Default to nothing: don't pick "safe modern productivity" unless the brief literally asks for utilitarian. On later turns, state a design brief only when the change is visual (a restyle, new theme, or new UI); for a logic, data, or behavior-only change, skip the brief and just make the change.
+DESIGN: on the initial build, before writing code, briefly state (2-3 sentences) what you want this app to feel like \u2014 name the specific fonts, the palette in hex, and one signature detail. Be concrete: "Fraunces display + Inter body + JetBrains Mono metadata, terracotta #b75432 accent on bone #f3efe6, paper-grain texture via inline SVG noise" is the kind of specificity that anchors the build. Default to nothing: don't pick "safe modern productivity" unless the brief literally asks for utilitarian. On later turns, state a design brief only when the change is visual (a restyle, new theme, or new UI); for a text, logic, data, or behavior-only change, skip the brief and just make the change.
+
+EDIT SCOPE: Change only the files and lines required by the current user request. A title rename is a text edit, not a design change. Preserve styles, dependencies, and unrelated logic on text edits. Design feedback does not authorize unrelated edits.
 
 WORKFLOW:
 1. NEVER output code as text or markdown. ALWAYS use tools.
 2. Initial build: state your design brief, then create_file with a "files" array writing ALL files in one call. The preview renders automatically.
 3. patch_file requires read_file for that path earlier in the conversation (or create_file in the same conversation, which counts). read_file output is numbered "42: <text>" \u2014 the prefix is display-only; never copy it into "find". Each "find" must match exactly one location \u2014 include 2-3 lines of surrounding context. Pass multiple patches per call to change distinct locations.
 4. Prefer patch_file for changes to existing files \u2014 surgical, reviewable, preserves surrounding code. Reserve create_file overwrites for substantial restructuring. Inserts: find the line before, replace with that line + the new line. Deletes: empty replace.
-5. After substantial changes, call critique_design first (taste, hierarchy, distinctiveness, weakest decision) and then audit_design (mechanical: tokens, focus states, aria-labels, alt, heading order). Patch what each surfaces. critique catches taste issues no checklist would; audit catches mechanics you'd miss. Run both; act on both.
-6. Before declaring done, call verify_app. The host's preview runtime reports whether your app actually mounted and surfaces any errors it captured \u2014 hallucinated imports, syntax the bundler rejected, undefined components, runtime crashes. If \`rendered\` is false or \`errors\` is non-empty, fix every error before the next message. If the response includes a \`note\` that verify_app isn't wired in this host, skip \u2014 audit + critique are your feedback in that case.
+5. On the initial build, when adding new UI, or after user-requested design changes, call critique_design first and then audit_design. Critique checks taste, hierarchy, and distinctiveness. Audit checks tokens, focus states, aria-labels, alt text, and heading order. Patch only issues within the current user request. For text, logic, or data edits, skip both design tools.
+6. Before declaring done, call verify_app. The host's preview runtime reports whether your app actually mounted and surfaces any errors it captured \u2014 hallucinated imports, syntax the bundler rejected, undefined components, runtime crashes. If \`rendered\` is false or \`errors\` is non-empty, fix every error before the next message. If the response includes a \`note\` that verify_app isn't wired in this host, skip runtime verification. An unavailable runtime verifier does not authorize design changes. Use audit_design and critique_design only for the initial build, adding new UI, or user-requested design changes.
 7. Keep responses to a sentence or two. Exception: when responding to critique_design, write a substantive paragraph per rubric question.
 
 STRUCTURE:
@@ -8044,12 +8047,13 @@ function isCacheExpired(cache, expirationMs = DEFAULT_CACHE_EXPIRATION_MS) {
   if (!cache) return true;
   return Date.now() - cache.timestamp > expirationMs;
 }
-function buildCacheEntry(tools, checksum) {
+function buildCacheEntry(tools, checksum, etag) {
   return {
     tools,
     timestamp: Date.now(),
     version: CACHE_VERSION,
-    ...checksum && { checksum }
+    ...checksum && { checksum },
+    ...etag && { etag }
   };
 }
 function writeLocalStorageCache(entry) {
@@ -8084,19 +8088,36 @@ function shouldRefreshTools(responseChecksum, cache = localStorageToolsCache) {
   const cachedChecksum = getToolsChecksum2(cache);
   return cachedChecksum instanceof Promise ? cachedChecksum.then(decide) : decide(cachedChecksum);
 }
-async function fetchServerToolsFromApi(baseUrl, token) {
-  const response = await fetch(`${baseUrl}/api/v1/tools`, {
+async function fetchServerToolsFromApi(baseUrl, authHeaders, etag) {
+  const request = (validator) => fetch(`${baseUrl}/api/v1/tools`, {
     method: "GET",
     headers: {
-      Authorization: `Bearer ${token}`,
-      "Content-Type": "application/json"
+      ...authHeaders,
+      "Content-Type": "application/json",
+      ...validator && { "If-None-Match": validator }
     }
   });
+  let response;
+  try {
+    response = await request(etag);
+  } catch (error) {
+    if (!etag || !(error instanceof TypeError)) throw error;
+    etag = void 0;
+    response = await request();
+  }
+  if (etag && response.status === 304) {
+    return { notModified: true };
+  }
   if (!response.ok) {
     throw new Error(`Failed to fetch server tools: ${response.status}`);
   }
   const data = await response.json();
-  return convertServerToolsResponse(data);
+  const responseEtag = response.headers?.get("ETag") ?? void 0;
+  return {
+    notModified: false,
+    ...convertServerToolsResponse(data),
+    ...responseEtag && { etag: responseEtag }
+  };
 }
 async function getServerTools(options) {
   const {
@@ -8128,34 +8149,30 @@ async function getServerTools(options) {
   try {
     const { BASE_URL: BASE_URL2 } = await Promise.resolve().then(() => (init_clientConfig(), clientConfig_exports));
     const effectiveBaseUrl = baseUrl ?? BASE_URL2;
+    const validator = cached && !forceRefresh ? cached.etag : void 0;
+    let authHeaders;
     if (apiKey) {
-      const response = await fetch(`${effectiveBaseUrl}/api/v1/tools`, {
-        method: "GET",
-        headers: {
-          "X-API-Key": apiKey,
-          "Content-Type": "application/json"
-        }
-      });
-      if (!response.ok) {
-        throw new Error(`Failed to fetch server tools: ${response.status}`);
+      authHeaders = { "X-API-Key": apiKey };
+    } else {
+      if (!getToken) {
+        getLogger().warn("[serverTools] No auth method available for fetching tools");
+        return cached?.tools ?? [];
       }
-      const data = await response.json();
-      const { tools: tools2, checksum: checksum2 } = convertServerToolsResponse(data);
-      await persistCache(buildCacheEntry(tools2, checksum2));
-      return tools2;
-    }
-    if (!getToken) {
-      getLogger().warn("[serverTools] No auth method available for fetching tools");
-      return cached?.tools ?? [];
+      const token = await getToken();
+      if (!token) {
+        getLogger().warn("[serverTools] No auth token available for fetching tools");
+        return cached?.tools ?? [];
+      }
+      authHeaders = { Authorization: `Bearer ${token}` };
     }
-    const token = await getToken();
-    if (!token) {
-      getLogger().warn("[serverTools] No auth token available for fetching tools");
-      return cached?.tools ?? [];
+    const result = await fetchServerToolsFromApi(effectiveBaseUrl, authHeaders, validator);
+    if (result.notModified) {
+      const confirmed = cached;
+      await persistCache({ ...confirmed, timestamp: Date.now() });
+      return confirmed.tools;
     }
-    const { tools, checksum } = await fetchServerToolsFromApi(effectiveBaseUrl, token);
-    await persistCache(buildCacheEntry(tools, checksum));
-    return tools;
+    await persistCache(buildCacheEntry(result.tools, result.checksum, result.etag));
+    return result.tools;
   } catch (error) {
     getLogger().error("[serverTools] Failed to fetch server tools:", error);
     if (cached?.tools) {
@@ -22076,7 +22093,6 @@ async function recall(query, ctx, options = {}) {
   }
   const needsChunkEmbedding = types.includes("chunk") && ctx.storageCtx;
   const wantsTemporal = types.includes("fact") && (ctx.factSource || ctx.vaultCtx);
-  const graphRefiner = flags.traverse && options.graphRefine && options.decomposeOptions ? createLlmNeighborRefiner(options.decomposeOptions) : void 0;
   const queryEmbedTotalTimeoutMs = options.queryEmbedTotalTimeoutMs ?? DEFAULT_QUERY_EMBED_TOTAL_TIMEOUT_MS;
   const prepStart = nowMs2();
   let sharedEmbedMs = 0;
@@ -22105,13 +22121,12 @@ async function recall(query, ctx, options = {}) {
     safeLane(
       "graph",
       () => graphLaneFailed = true,
-      () => ctx.factSource ? ctx.factSource.graphRanking(query, flags.traverse, options) : buildGraphLaneRanking(query, ctx, flags.traverse, {
-        ...options.maxHops !== void 0 && { maxHops: options.maxHops },
-        ...options.entityFanout !== void 0 && { entityFanout: options.entityFanout },
-        ...options.nodeBudget !== void 0 && { nodeBudget: options.nodeBudget },
-        ...options.rrfK !== void 0 && { rrfK: options.rrfK },
-        ...graphRefiner && { refineNeighbors: graphRefiner }
-      })
+      () => ctx.factSource ? ctx.factSource.graphRanking(query, flags.traverse, options) : buildGraphLaneRanking(
+        query,
+        ctx,
+        flags.traverse,
+        graphTraversalOptions(options, flags.traverse)
+      )
     ),
     wantsTemporal ? safeLane(
       "temporal",
@@ -22330,6 +22345,16 @@ function toFactMemory(r, now) {
     updatedAt: r.updatedAt ?? /* @__PURE__ */ new Date(0)
   };
 }
+function graphTraversalOptions(options, traverse) {
+  const refineNeighbors = traverse && options.graphRefine && options.decomposeOptions ? createLlmNeighborRefiner(options.decomposeOptions) : void 0;
+  return {
+    ...options.maxHops !== void 0 && { maxHops: options.maxHops },
+    ...options.entityFanout !== void 0 && { entityFanout: options.entityFanout },
+    ...options.nodeBudget !== void 0 && { nodeBudget: options.nodeBudget },
+    ...options.rrfK !== void 0 && { rrfK: options.rrfK },
+    ...refineNeighbors && { refineNeighbors }
+  };
+}
 async function buildGraphLaneRanking(query, ctx, traverse = false, traversalOptions = {}) {
   const entityCtx = ctx.entityCtx ?? ctx.vaultCtx?.entityCtx;
   if (!entityCtx) return [];
@@ -22495,24 +22520,33 @@ function isDumpQuery(query) {
   return false;
 }
 async function listRecentFacts(ctx, limit, toolOptions) {
+  const store = toolOptions?.memoryStore;
   const vaultCtx = ctx.vaultCtx;
-  if (!vaultCtx) return [];
-  const ordered = await getVaultRankingProjectionsOp(vaultCtx, {
+  if (!vaultCtx && !store) return [];
+  const read = (ids) => store ? store.list({ memoryIds: ids }) : getVaultMemoriesByIdsOp(vaultCtx, ids);
+  const filters = {
     ...toolOptions?.scopes && { scopes: toolOptions.scopes },
-    ...toolOptions?.memoryIds !== void 0 && { memoryIds: toolOptions.memoryIds },
+    ...toolOptions?.memoryIds !== void 0 && { memoryIds: toolOptions.memoryIds }
+  };
+  const project = (size) => store ? store.listProjections({ ...filters, limit: size }) : getVaultRankingProjectionsOp(vaultCtx, {
+    ...filters,
     ...toolOptions?.folderId !== void 0 && { folderId: toolOptions.folderId }
   });
   const readable = [];
-  for (let i = 0; i < ordered.length && readable.length < limit; i += limit) {
-    const batch = ordered.slice(i, i + limit).map((p) => p.uniqueId);
-    const byId = new Map(
-      (await getVaultMemoriesByIdsOp(vaultCtx, batch)).map((m) => [m.uniqueId, m])
-    );
-    for (const id of batch) {
-      const m = byId.get(id);
-      if (m && !isEncrypted(m.content)) readable.push(m);
-      if (readable.length >= limit) break;
+  let start = 0;
+  for (let size = limit; readable.length < limit; size *= 2) {
+    const ordered = await project(size);
+    for (let i = start; i < ordered.length && readable.length < limit; i += limit) {
+      const batch = ordered.slice(i, i + limit).map((p) => p.uniqueId);
+      const byId = new Map((await read(batch)).map((m) => [m.uniqueId, m]));
+      for (const id of batch) {
+        const m = byId.get(id);
+        if (m && !isEncrypted(m.content)) readable.push(m);
+        if (readable.length >= limit) break;
+      }
     }
+    if (!store || ordered.length < size) break;
+    start = ordered.length;
   }
   return readable.map((m) => ({
     id: m.uniqueId,
@@ -22529,6 +22563,8 @@ async function listRecentFacts(ctx, limit, toolOptions) {
   }));
 }
 function createRecallTool(ctx, toolOptions, callbacks) {
+  if (toolOptions?.memoryStore && toolOptions.folderId !== void 0)
+    throw new Error("Folders are not supported with a memoryStore");
   const defaultTypes = toolOptions?.types ?? ["fact", "chunk"];
   const defaultLimit = toolOptions?.limit ?? DEFAULT_LIMIT2;
   const defaultBudget = toolOptions?.budget ?? DEFAULT_BUDGET2;
@@ -22600,7 +22636,7 @@ function createRecallTool(ctx, toolOptions, callbacks) {
       let surfaced = 0;
       try {
         let recallDegraded = [];
-        const wantsRecent = args.sort === "recent" && defaultTypes.includes("fact") && ctx.vaultCtx !== void 0;
+        const wantsRecent = args.sort === "recent" && defaultTypes.includes("fact") && (ctx.vaultCtx !== void 0 || toolOptions?.memoryStore !== void 0);
         let result;
         if (wantsRecent) {
           result = { memories: await listRecentFacts(ctx, effectiveLimit, toolOptions) };
@@ -23110,6 +23146,7 @@ function createLocalMemoryStore(options) {
     });
   };
   return {
+    masksEmbeddingInput: options.embeddingOptions.maskInput !== void 0,
     list: (listOptions) => getAllVaultMemoriesOp(vaultCtx, listOptions),
     get: (id) => getVaultMemoryOp(vaultCtx, id),
     listArchived: async () => {
@@ -23191,6 +23228,22 @@ function createLocalMemoryStore(options) {
       { vaultCtx, embeddingOptions: options.embeddingOptions, vaultCache },
       retainOptions
     ),
+    factSource: {
+      search: (query, searchOptions) => searchVaultMemoriesWithSize(
+        query,
+        vaultCtx,
+        options.embeddingOptions,
+        vaultCache,
+        searchOptions
+      ),
+      graphRanking: (query, traverse, recallOptions) => buildGraphLaneRanking(
+        query,
+        { vaultCtx, entityCtx, embeddingOptions: options.embeddingOptions },
+        traverse,
+        graphTraversalOptions(recallOptions, traverse)
+      ),
+      temporalRanking: (query, now) => buildTemporalLaneRanking(query, vaultCtx, now)
+    },
     subscribe: (onChange, subscribeOptions) => {
       const afterFirst = () => {
         let first = true;
@@ -24078,38 +24131,31 @@ function createRemoteMemoryPipeline(options) {
     };
     return { prepare, port };
   };
-  return {
-    recall: async (query, recallOptions = {}) => {
+  const factSource = {
+    graphRanking: options.graphRanking,
+    temporalRanking: options.temporalRanking,
+    search: async (text13, searchOptions) => {
       const { prepare } = operation("recall");
-      return recall(
-        query,
-        {
-          embeddingOptions,
-          factSource: {
-            graphRanking: options.graphRanking,
-            temporalRanking: options.temporalRanking,
-            search: async (text13, searchOptions) => {
-              const prepared = await prepare(text13, searchOptions);
-              const ranked = await rankPreparedVaultCandidates(
-                text13,
-                prepared,
-                embeddingOptions,
-                searchOptions
-              );
-              return {
-                ...ranked,
-                rankedOnCosine: prepared.memories.length > 0 && !prepared.embeddingsUnavailable,
-                decryptLast: true,
-                rowsDecrypted: prepared.rowsDecrypted,
-                queryEmbedMs: prepared.queryEmbedMs,
-                rowsEmbedded: 0
-              };
-            }
-          }
-        },
-        { ...recallOptions, types: ["fact"] }
+      const prepared = await prepare(text13, searchOptions);
+      const ranked = await rankPreparedVaultCandidates(
+        text13,
+        prepared,
+        embeddingOptions,
+        searchOptions
       );
-    },
+      return {
+        ...ranked,
+        rankedOnCosine: prepared.memories.length > 0 && !prepared.embeddingsUnavailable,
+        decryptLast: true,
+        rowsDecrypted: prepared.rowsDecrypted,
+        queryEmbedMs: prepared.queryEmbedMs,
+        rowsEmbedded: 0
+      };
+    }
+  };
+  return {
+    factSource,
+    recall: async (query, recallOptions = {}) => recall(query, { embeddingOptions, factSource }, { ...recallOptions, types: ["fact"] }),
     retain: async (content, retainOptions) => {
       const { port } = operation("retain");
       return retainWithPersistence(
@@ -24471,6 +24517,7 @@ function createRemoteMemoryStore(options) {
     });
   };
   return {
+    masksEmbeddingInput: embeddingOptions.maskInput !== void 0,
     list: async (listOptions = {}) => (await listRows(decrypted, listOptions, listFilters(listOptions), maxOf(listOptions))).map(
       (r) => stored(r.memory)
     ),
@@ -24666,6 +24713,7 @@ function createRemoteMemoryStore(options) {
       })
     ),
     recall: (query, recallOptions) => pipeline.recall(query, recallOptions),
+    factSource: pipeline.factSource,
     retain: async (content, retainOptions) => {
       const result = await pipeline.retain(content, retainOptions);
       if (result.action === "create" || result.action === "supersede") notify("membership");
@@ -26434,19 +26482,20 @@ function createMemoryVaultSearchTool(vaultCtx, embeddingOptions, cache, searchOp
         const budget = wantsDecompose ? "high" : searchOptions?.rerank ? "mid" : "low";
         const folderId = searchOptions?.folderId ?? argFolderId;
         if (searchOptions?.useFusion === false) {
-          const { results: legacy, embeddingsUnavailable } = await searchVaultMemoriesWithSize(
+          const legacyOptions = {
+            limit: requestLimit,
+            minSimilarity,
+            useFusion: false,
+            ...tuningForward,
+            ...folderId !== void 0 && { folderId },
+            ...searchOptions?.scopes && { scopes: searchOptions.scopes }
+          };
+          const { results: legacy, embeddingsUnavailable } = "retain" in vaultCtx ? await vaultCtx.factSource.search(query, legacyOptions) : await searchVaultMemoriesWithSize(
             query,
             vaultCtx,
             embeddingOptions,
             cache,
-            {
-              limit: requestLimit,
-              minSimilarity,
-              useFusion: false,
-              ...tuningForward,
-              ...folderId !== void 0 && { folderId },
-              ...searchOptions?.scopes && { scopes: searchOptions.scopes }
-            }
+            legacyOptions
           );
           if (legacy.length === 0) {
             return embeddingsUnavailable ? EMBEDDINGS_DEGRADED_EMPTY_NO_LEXICAL : "No relevant memories found in the vault.";
@@ -26465,7 +26514,7 @@ function createMemoryVaultSearchTool(vaultCtx, embeddingOptions, cache, searchOp
         let recallDegraded = [];
         const result = await recall(
           query,
-          { vaultCtx, embeddingOptions, vaultCache: cache },
+          "retain" in vaultCtx ? { factSource: vaultCtx.factSource, embeddingOptions } : { vaultCtx, embeddingOptions, vaultCache: cache },
           {
             onDiagnostics: (d) => {
               recallDegraded = d.degraded;
@@ -26545,8 +26594,10 @@ function describeWriteOutcome(outcome2) {
   }
 }
 function createMemoryVaultTool(vaultCtx, options, embeddingOptions, cache) {
+  const store = "retain" in vaultCtx ? vaultCtx : void 0;
+  const ctx = "retain" in vaultCtx ? void 0 : vaultCtx;
   const hasOnSave = !!options?.onSave;
-  const folderNames = options?.folderMap ? Array.from(options.folderMap.keys()) : [];
+  const folderNames = !store && options?.folderMap ? Array.from(options.folderMap.keys()) : [];
   return {
     type: "function",
     function: {
@@ -26591,7 +26642,7 @@ function createMemoryVaultTool(vaultCtx, options, embeddingOptions, cache) {
         let previousContent;
         const scope = options?.scope ?? "private";
         if (isUpdate) {
-          const existing = await getVaultMemoryOp(vaultCtx, id);
+          const existing = store ? await store.get(id) : await getVaultMemoryOp(ctx, id);
           if (!existing) {
             return `Error: Memory with ID "${id}" not found. Creating a new memory instead would require a separate call without an ID.`;
           }
@@ -26612,9 +26663,18 @@ function createMemoryVaultTool(vaultCtx, options, embeddingOptions, cache) {
             return isUpdate ? `Memory update was cancelled by the user. The memory "${id}" was not modified.` : "Memory save was cancelled by the user. No memory was created.";
           }
         }
-        if (isUpdate) {
+        if (isUpdate && store) {
+          const updated = await store.update(id, {
+            content,
+            ...factType !== void 0 && { factType }
+          });
+          if (!updated) {
+            return `Error: Failed to update memory "${id}".`;
+          }
+          return `Memory updated successfully (ID: ${updated.uniqueId}).`;
+        } else if (isUpdate) {
           const folderId = folderName ? options?.folderMap?.get(folderName) : void 0;
-          const updated = await updateVaultMemoryOp(vaultCtx, id, {
+          const updated = await updateVaultMemoryOp(ctx, id, {
             content,
             embedding: null,
             folderId,
@@ -26629,7 +26689,7 @@ function createMemoryVaultTool(vaultCtx, options, embeddingOptions, cache) {
               content,
               embeddingOptions,
               cache,
-              vaultCtx,
+              ctx,
               id,
               updated.updatedAt
             ).catch(() => {
@@ -26649,18 +26709,22 @@ function createMemoryVaultTool(vaultCtx, options, embeddingOptions, cache) {
             await notifyWritten(options, input, outcome2);
             return describeWriteOutcome(outcome2);
           }
-          const created = await createVaultMemoryOp(vaultCtx, {
+          const created = store ? await store.create({
+            content,
+            scope,
+            ...factType !== void 0 && { factType }
+          }) : await createVaultMemoryOp(ctx, {
             content,
             scope,
             folderId,
             ...factType !== void 0 && { factType }
           });
-          if (embeddingOptions && cache) {
+          if (ctx && embeddingOptions && cache) {
             eagerEmbedContent(
               content,
               embeddingOptions,
               cache,
-              vaultCtx,
+              ctx,
               created.uniqueId,
               created.updatedAt
             ).catch(() => {
@@ -33644,6 +33708,8 @@ async function storedToLlmapiMessage(stored2, encryptionKey, resolveMediaByIds)
 }
 var CONVERSATION_REDACTOR_LIMIT = 50;
 var NO_CONVERSATION_KEY = "__no_conversation__";
+var NO_STORE_FOLDERS = "Folders are not supported with a memoryStore";
+var NO_STORE_MASK = "piiRedaction needs a memoryStore built with embeddingOptions.maskInput";
 var conversationRedactors = /* @__PURE__ */ new Map();
 function getConversationRedactor(conversationId, nerDetector) {
   const key = conversationId ?? NO_CONVERSATION_KEY;
@@ -33687,6 +33753,7 @@ function useChatStorage(options) {
     signMessage,
     embeddedWalletSigner,
     getWalletAddress,
+    memoryStore,
     enableQueue = true,
     autoFlushOnKeyAvailable = true,
     extraToolSets,
@@ -33732,6 +33799,7 @@ function useChatStorage(options) {
     () => ({ getToken, baseUrl, model: embeddingModel, maskInput: maskEmbeddingInput }),
     [getToken, baseUrl, embeddingModel, maskEmbeddingInput]
   );
+  const storeMaskMissing = memoryStore !== void 0 && maskEmbeddingInput !== void 0 && !memoryStore.masksEmbeddingInput;
   const blobManagerRef = (0, import_react6.useRef)(new BlobUrlManager());
   (0, import_react6.useEffect)(() => {
     const manager = blobManagerRef.current;
@@ -34008,6 +34076,15 @@ function useChatStorage(options) {
   );
   const retainVaultMemory = (0, import_react6.useCallback)(
     async (input) => {
+      if (memoryStore) {
+        if (storeMaskMissing) throw new Error(NO_STORE_MASK);
+        if (input.folderId !== void 0) throw new Error(NO_STORE_FOLDERS);
+        return memoryStore.retain(input.content, {
+          source: "manual",
+          scope: input.scope,
+          ...input.factType !== void 0 && { factType: input.factType }
+        });
+      }
       if (!getToken) {
         throw new Error("getToken is required to retain a vault memory");
       }
@@ -34026,28 +34103,44 @@ function useChatStorage(options) {
         }
       );
     },
-    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache]
+    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, memoryStore, storeMaskMissing]
   );
   const createMemoryVaultTool2 = (0, import_react6.useCallback)(
     (options2) => {
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
       const embOpts = getToken ? vaultEmbeddingOptions : void 0;
       return createMemoryVaultTool(
-        vaultCtx,
-        embOpts ? { write: retainVaultMemory, ...options2 } : options2,
+        memoryStore ?? vaultCtx,
+        embOpts || memoryStore ? { write: retainVaultMemory, ...options2 } : options2,
         embOpts,
         embOpts ? vaultEmbeddingCache : void 0
       );
     },
-    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, retainVaultMemory]
+    [
+      vaultCtx,
+      getToken,
+      vaultEmbeddingOptions,
+      vaultEmbeddingCache,
+      retainVaultMemory,
+      memoryStore,
+      storeMaskMissing
+    ]
   );
   const getVaultMemories = (0, import_react6.useCallback)(
     (options2) => {
-      return getAllVaultMemoriesOp(vaultCtx, options2);
+      if (!memoryStore) return getAllVaultMemoriesOp(vaultCtx, options2);
+      const { folderId, levels, kinds, ...listOptions } = options2 ?? {};
+      if (folderId !== void 0) throw new Error(NO_STORE_FOLDERS);
+      if (levels !== void 0 || kinds !== void 0)
+        throw new Error("level and kind filters are not supported with a memoryStore");
+      return memoryStore.list(listOptions);
     },
-    [vaultCtx]
+    [vaultCtx, memoryStore]
   );
   const createVaultMemory = (0, import_react6.useCallback)(
     async (content, scope) => {
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
+      if (memoryStore) return memoryStore.create({ content, scope });
       const result = await createVaultMemoryOp(vaultCtx, { content, scope });
       if (getToken) {
         eagerEmbedContent(
@@ -34063,10 +34156,12 @@ function useChatStorage(options) {
       }
       return result;
     },
-    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache]
+    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, memoryStore, storeMaskMissing]
   );
   const updateVaultMemory = (0, import_react6.useCallback)(
     async (id, content, scope) => {
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
+      if (memoryStore) return memoryStore.update(id, { content, scope });
       const existing = await getVaultMemoryOp(vaultCtx, id);
       const result = await updateVaultMemoryOp(vaultCtx, id, { content, scope, embedding: null });
       if (result && getToken) {
@@ -34086,10 +34181,11 @@ function useChatStorage(options) {
       }
       return result;
     },
-    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache]
+    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, memoryStore, storeMaskMissing]
   );
   const deleteVaultMemory = (0, import_react6.useCallback)(
     async (id) => {
+      if (memoryStore) return memoryStore.delete(id);
       const existing = await getVaultMemoryOp(vaultCtx, id);
       const result = await deleteVaultMemoryOp(vaultCtx, id);
       if (result && existing) {
@@ -34097,19 +34193,19 @@ function useChatStorage(options) {
       }
       return result;
     },
-    [vaultCtx, vaultEmbeddingCache]
+    [vaultCtx, vaultEmbeddingCache, memoryStore]
   );
   const chunkVectorCacheRef = (0, import_react6.useRef)(createChunkVectorCache());
   const clientToolEmbeddingsCacheRef = (0, import_react6.useRef)(/* @__PURE__ */ new Map());
   (0, import_react6.useEffect)(() => {
-    if (!getToken) return;
+    if (!getToken || memoryStore) return;
     void (async () => {
       try {
         await preEmbedVaultMemories(vaultCtx, vaultEmbeddingOptions, vaultEmbeddingCache);
       } catch {
       }
     })();
-  }, [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache]);
+  }, [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, memoryStore]);
   (0, import_react6.useEffect)(() => {
     return onClearAllEncryptionState(() => {
       vaultEmbeddingCache.clear();
@@ -34118,26 +34214,35 @@ function useChatStorage(options) {
   }, [vaultEmbeddingCache]);
   const createMemoryVaultSearchTool2 = (0, import_react6.useCallback)(
     (searchOptions) => {
-      if (!getToken) {
+      if (!getToken && !memoryStore) {
         throw new Error("getToken is required for memory vault search tool");
       }
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
       return createMemoryVaultSearchTool(
-        vaultCtx,
+        memoryStore ?? vaultCtx,
         vaultEmbeddingOptions,
         vaultEmbeddingCache,
         searchOptions
       );
     },
-    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache]
+    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, memoryStore, storeMaskMissing]
   );
   const createRecallTool2 = (0, import_react6.useCallback)(
     (toolOptions, callbacks) => {
-      if (!getToken) {
+      if (!getToken && !memoryStore) {
         throw new Error("getToken is required for recall tool");
       }
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
       const resolvedToolOptions = toolOptions?.excludeConversationId !== void 0 || !currentConversationId ? toolOptions : { ...toolOptions, excludeConversationId: currentConversationId };
+      if (memoryStore && resolvedToolOptions?.folderId !== void 0)
+        throw new Error(NO_STORE_FOLDERS);
       return createRecallTool(
-        {
+        memoryStore ? {
+          factSource: memoryStore.factSource,
+          ...getToken && { storageCtx },
+          embeddingOptions: vaultEmbeddingOptions,
+          chunkCache: chunkVectorCacheRef.current
+        } : {
           vaultCtx,
           storageCtx,
           embeddingOptions: vaultEmbeddingOptions,
@@ -34145,7 +34250,7 @@ function useChatStorage(options) {
           chunkCache: chunkVectorCacheRef.current,
           entityCtx
         },
-        resolvedToolOptions,
+        memoryStore ? { ...resolvedToolOptions, memoryStore } : resolvedToolOptions,
         callbacks
       );
     },
@@ -34156,11 +34261,15 @@ function useChatStorage(options) {
       getToken,
       vaultEmbeddingOptions,
       vaultEmbeddingCache,
-      currentConversationId
+      currentConversationId,
+      memoryStore,
+      storeMaskMissing
     ]
   );
   const searchVaultMemoriesFn = (0, import_react6.useCallback)(
     async (query, searchOptions) => {
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
+      if (memoryStore) return (await memoryStore.factSource.search(query, searchOptions)).results;
       if (!getToken) return [];
       return searchVaultMemories(
         query,
@@ -34170,11 +34279,11 @@ function useChatStorage(options) {
         searchOptions
       );
     },
-    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache]
+    [vaultCtx, getToken, vaultEmbeddingOptions, vaultEmbeddingCache, memoryStore, storeMaskMissing]
   );
   const recallFn = (0, import_react6.useCallback)(
     async (query, options2) => {
-      if (!getToken) {
+      if (!getToken && !memoryStore) {
         return {
           memories: [],
           usedBudget: options2?.budget ?? "low",
@@ -34183,9 +34292,16 @@ function useChatStorage(options) {
         };
       }
       const resolvedOptions = options2?.excludeConversationId !== void 0 || !currentConversationId ? options2 : { ...options2, excludeConversationId: currentConversationId };
+      if (storeMaskMissing) throw new Error(NO_STORE_MASK);
+      if (memoryStore && resolvedOptions?.folderId !== void 0) throw new Error(NO_STORE_FOLDERS);
       return recall(
         query,
-        {
+        memoryStore ? {
+          factSource: memoryStore.factSource,
+          ...getToken && { storageCtx },
+          embeddingOptions: vaultEmbeddingOptions,
+          chunkCache: chunkVectorCacheRef.current
+        } : {
           vaultCtx,
           storageCtx,
           embeddingOptions: vaultEmbeddingOptions,
@@ -34203,7 +34319,9 @@ function useChatStorage(options) {
       getToken,
       currentConversationId,
       vaultEmbeddingOptions,
-      vaultEmbeddingCache
+      vaultEmbeddingCache,
+      memoryStore,
+      storeMaskMissing
     ]
   );
   const {
@@ -36626,6 +36744,128 @@ function useICloudBackup(options) {
 // src/react/useModels.ts
 var import_react17 = require("react");
 init_clientConfig();
+var MODELS_CACHE_TTL_MS = 5 * 60 * 1e3;
+var modelsCache = /* @__PURE__ */ new Map();
+var modelsInFlight = /* @__PURE__ */ new Map();
+var cacheGeneration = 0;
+function clearModelsCache() {
+  cacheGeneration++;
+  modelsCache.clear();
+  modelsInFlight.clear();
+}
+function pruneStaleTokenEntries(newKey) {
+  const [newBaseUrl, newProvider] = JSON.parse(newKey);
+  for (const existingKey of modelsCache.keys()) {
+    if (existingKey === newKey) continue;
+    const [existingBaseUrl, existingProvider] = JSON.parse(existingKey);
+    if (existingBaseUrl === newBaseUrl && existingProvider === newProvider) {
+      modelsCache.delete(existingKey);
+    }
+  }
+}
+function fingerprintToken(token) {
+  if (!token) return "anon";
+  let h1 = 3735928559;
+  let h2 = 1103547991;
+  for (let i = 0; i < token.length; i++) {
+    const ch = token.charCodeAt(i);
+    h1 = Math.imul(h1 ^ ch, 2654435761);
+    h2 = Math.imul(h2 ^ ch, 1597334677);
+  }
+  h1 = Math.imul(h1 ^ h1 >>> 16, 2246822507) ^ Math.imul(h2 ^ h2 >>> 13, 3266489909);
+  h2 = Math.imul(h2 ^ h2 >>> 16, 2246822507) ^ Math.imul(h1 ^ h1 >>> 13, 3266489909);
+  return (4294967296 * (2097151 & h2) + (h1 >>> 0)).toString(36);
+}
+function modelsCacheKey(baseUrl, provider, token) {
+  return JSON.stringify([baseUrl, provider ?? null, fingerprintToken(token)]);
+}
+async function fetchAllModelPages(baseUrl, provider, headers, previous, signal) {
+  const pages = /* @__PURE__ */ new Map();
+  const models = [];
+  let pageToken;
+  do {
+    const pageKey = pageToken ?? "";
+    const stored2 = previous?.pages.get(pageKey);
+    const request = (etag) => getApiV1Models({
+      baseUrl,
+      headers: etag ? { ...headers, "If-None-Match": etag } : headers,
+      query: { provider, page_token: pageToken },
+      signal
+    });
+    let response = await request(stored2?.etag);
+    if (stored2?.etag && !response.response && response.error) {
+      response = await request();
+    }
+    let page;
+    if (response.response?.status === 304) {
+      if (!stored2) throw new Error("Failed to fetch models");
+      page = stored2;
+    } else {
+      if (response.error) {
+        const errorMsg = response.error.error ?? "Failed to fetch models";
+        throw new Error(errorMsg);
+      }
+      page = {
+        body: response.data ?? {},
+        etag: response.response?.headers?.get("ETag") ?? void 0
+      };
+    }
+    pages.set(pageKey, page);
+    models.push(...page.body.data || []);
+    pageToken = page.body.next_page_token;
+  } while (pageToken);
+  return { pages, models, fetchedAt: Date.now() };
+}
+function loadModels(key, baseUrl, provider, headers, force, signal) {
+  const cached = modelsCache.get(key);
+  if (cached && !force && Date.now() - cached.fetchedAt < MODELS_CACHE_TTL_MS) {
+    return Promise.resolve([...cached.models]);
+  }
+  const shared = (force ? void 0 : modelsInFlight.get(key)) ?? startSharedRequest(key, baseUrl, provider, headers, cached);
+  return waitForSharedRequest(key, shared, signal).then((models) => [...models]);
+}
+function startSharedRequest(key, baseUrl, provider, headers, previous) {
+  const controller = new AbortController();
+  const generation = cacheGeneration;
+  const shared = {
+    controller,
+    waiters: 0,
+    promise: Promise.resolve([])
+  };
+  shared.promise = fetchAllModelPages(baseUrl, provider, headers, previous, controller.signal).then((entry) => {
+    if (modelsInFlight.get(key) === shared && generation === cacheGeneration) {
+      pruneStaleTokenEntries(key);
+      modelsCache.set(key, entry);
+    }
+    return entry.models;
+  }).finally(() => {
+    if (modelsInFlight.get(key) === shared) modelsInFlight.delete(key);
+  });
+  modelsInFlight.set(key, shared);
+  return shared;
+}
+function waitForSharedRequest(key, shared, signal) {
+  shared.waiters++;
+  let left = false;
+  const leave = () => {
+    if (left) return;
+    left = true;
+    shared.waiters--;
+    if (shared.waiters === 0) {
+      shared.controller.abort();
+      if (modelsInFlight.get(key) === shared) modelsInFlight.delete(key);
+    }
+  };
+  if (signal.aborted) {
+    leave();
+  } else {
+    signal.addEventListener("abort", leave, { once: true });
+  }
+  return shared.promise.finally(() => {
+    left = true;
+    signal.removeEventListener("abort", leave);
+  });
+}
 function useModels(options = {}) {
   const { getToken, baseUrl = BASE_URL, provider, autoFetch = true } = options;
   const [models, setModels] = (0, import_react17.useState)([]);
@@ -36648,7 +36888,7 @@ function useModels(options = {}) {
       }
     };
   }, []);
-  const fetchModels = (0, import_react17.useCallback)(async () => {
+  const fetchModels = (0, import_react17.useCallback)(async (force = false) => {
     if (abortControllerRef.current) {
       abortControllerRef.current.abort();
     }
@@ -36667,35 +36907,17 @@ function useModels(options = {}) {
       if (token) {
         headers["Authorization"] = `Bearer ${token}`;
       }
-      let allModels = [];
-      let nextPageToken;
-      do {
-        if (signal.aborted) return;
-        const response = await getApiV1Models({
-          baseUrl: baseUrlRef.current,
-          headers,
-          query: {
-            provider: providerRef.current,
-            page_token: nextPageToken
-          },
-          signal
-        });
-        if (response.error) {
-          const errorMsg = response.error.error ?? "Failed to fetch models";
-          throw new Error(errorMsg);
-        }
-        if (response.data) {
-          const newModels = response.data.data || [];
-          allModels = [...allModels, ...newModels];
-          nextPageToken = response.data.next_page_token;
-        }
-      } while (nextPageToken);
+      const baseUrl2 = baseUrlRef.current;
+      const provider2 = providerRef.current;
+      const key = modelsCacheKey(baseUrl2, provider2, token);
+      const allModels = await loadModels(key, baseUrl2, provider2, headers, force, signal);
       if (signal.aborted) return;
       setModels(allModels);
     } catch (err) {
       if (err instanceof Error && err.name === "AbortError") {
         return;
       }
+      if (signal.aborted) return;
       setError(err instanceof Error ? err : new Error(String(err)));
     } finally {
       if (!signal.aborted) {
@@ -36708,7 +36930,7 @@ function useModels(options = {}) {
   }, []);
   const refetch = (0, import_react17.useCallback)(async () => {
     setModels([]);
-    await fetchModels();
+    await fetchModels(true);
   }, [fetchModels]);
   const hasFetchedRef = (0, import_react17.useRef)(false);
   (0, import_react17.useEffect)(() => {
@@ -38760,6 +38982,7 @@ function useWalletBinding(options = {}) {
   clearKeyPair,
   clearLazyTitleCache,
   clearMemoryTopicsOverrideOp,
+  clearModelsCache,
   clearNotionToken,
   clearServerToolsCache,
   consoleLogger,