@redis-iris/agent-memory 0.3.0 → 0.4.0-beta.1

package/FUNCTIONS.md

@@ -20,7 +20,7 @@ specific category of applications.
 
 ```typescript
 import { AgentMemoryCore } from "@redis-iris/agent-memory/core.js";
-import { bulkCreateLongTermMemories } from "@redis-iris/agent-memory/funcs/bulk-create-long-term-memories.js";
+import { createDocumentIngestion } from "@redis-iris/agent-memory/funcs/create-document-ingestion.js";
 
 // Use `AgentMemoryCore` for best tree-shaking performance.
 // You can create one instance of it to use across an application.
@@ -31,23 +31,20 @@ const agentMemory = new AgentMemoryCore({
 });
 
 async function run() {
-  const res = await bulkCreateLongTermMemories(agentMemory, {
-    memories: [
-      {
-        id: "mem-1",
-        text: "The user prefers dark mode",
-        ownerId: "user-1",
-        namespaceRef: {
-          namespaceId: "ns-product",
-        },
-      },
-    ],
+  const res = await createDocumentIngestion(agentMemory, {
+    documentId: "customer-preferences",
+    revision: "v1",
+    content: "Q3VzdG9tZXIgcHJlZmVycyBlbWFpbCB1cGRhdGVzLg==",
+    mediaType: "text/plain",
+    ownerId: "user-123",
+    extractorId: "document-extractor",
+    idempotencyKey: "customer-preferences-v1",
   });
   if (res.ok) {
     const { value: result } = res;
     console.log(result);
   } else {
-    console.log("bulkCreateLongTermMemories failed:", res.error);
+    console.log("createDocumentIngestion failed:", res.error);
   }
 }
 

package/README.md

@@ -13,10 +13,41 @@ Redis Agent Memory API: API for storing, retrieving, and searching Redis Agent M
 Authentication depends on your deployment. Use the credential issued for your Agent Memory service or store. For self-managed deployments, see the self-managed Agent Memory guide for authentication options.
 <!-- End Summary [summary] -->
 
+## Documentation
+
+- [Developer guide](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/developer-guide/)
+- [TypeScript SDK quickstart](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/typescript-sdk-quickstart/)
+- [REST API reference](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/api-reference/) (HTTP endpoints and schemas, not TypeScript method pages)
+- [REST API quickstart](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/rest-api-quickstart/)
+
+## Recent changes
+
+**Namespace resources (since 0.3.0).** Create and manage namespaces with `listNamespaces`, `createNamespace`, `getNamespace`, `updateNamespace`, and `deleteNamespace`. Bind a session or long-term memory to a namespace resource with `namespaceRef`.
+
+**Namespace routing (0.4.0).** Define a store-wide policy with `putNamespaceRouting` to organize long-term memories in shared namespaces. `accept` rules select a destination; `reject` rules can block a memory from entering that destination, even when a caller names it explicitly. The policy only targets shared namespaces. To route a memory that is already in a shared namespace, call `moveLongTermMemories({ memoryIds: ["mem-1"] })` without `namespaceRef`. Memories in personal namespaces or no namespace are not eligible for automatic routing. A new memory with neither namespace field remains unnamespaced.
+
+**Document ingestion (MemoryETL, 0.4.0).** Generate long-term memories from documents, such as policies, before an agent has any sessions. This complements extraction from session events. Configure a document Extractor, submit a revision with `createDocumentIngestion`, then check its asynchronous status and list the memories it produced. Pass document content as a base64-encoded UTF-8 string.
+
+**Summary Views (0.4.0).** Materialize summaries of long-term memories. The server assigns `ownerId`. Visibility defaults to private; set `SHARED` to publish a view of shared memories to store-authorized callers. Filter sources with `namespaceRef`, and group by owner, session, namespace ID, or memory type. A result read uses that same scope. The service checks the contributing records and withholds invalid output while repair is pending. Choose text or structured output, then refresh on demand or use continuous refresh. Summary Views must be enabled in the deployment.
+
+**Ordering.** Filter-only long-term search accepts `sortBy` (`createdAt` or `updatedAt`) and `sortOrder`. Do not combine sort with `text`. `listNamespaces` accepts the same kind of sort and defaults to `id` ascending. Pass `sortBy` and `sortOrder` after request options so existing positional arguments stay in place.
+
+**Session rows.** `listSessions` still returns session IDs. `listSessionSummaries` returns owner, timestamps, and namespace, with caller-selected order.
+
+**Ingestion hooks.** When a store selects an input hook, memory and document writes require `idempotencyKey`. A stopped hook returns HTTP 422, and a retryable hook returns HTTP 503. Read one decision with `getIngestionHookStatus`, or list them with `listIngestionHookStatuses`.
+
+**Source evidence.** A memory source can be a document or a session. Page the evidence for one source with `listMemorySourceEvidence`.
+
+**Legacy namespace labels.** The flat `namespace` string is deprecated on memories. It does not create or resolve a namespace resource. Do not send it together with `namespaceRef`. Summary View filters, grouping, and result scope accept `namespaceRef` only.
+
+**HTTP 424.** When a memory or model-provider dependency cannot complete the request, the SDK raises `MemoryFailedDependencyErrorResponseContent`. `FailedDependencyErrorResponseContent` still represents other 424 failed-dependency errors.
+
 <!-- Start Table of Contents [toc] -->
 ## Table of Contents
 <!-- $toc-max-depth=2 -->
 * [@redis-iris/agent-memory](#redis-irisagent-memory)
+  * [Documentation](#documentation)
+  * [Recent changes](#recent-changes)
   * [SDK Installation](#sdk-installation)
   * [Requirements](#requirements)
   * [SDK Example Usage](#sdk-example-usage)
@@ -70,7 +101,7 @@ yarn add @redis-iris/agent-memory
 <!-- Start Requirements [requirements] -->
 ## Requirements
 
-For supported JavaScript runtimes, please consult [RUNTIMES.md](RUNTIMES.md).
+For supported JavaScript runtimes, please consult RUNTIMES.md.
 <!-- End Requirements [requirements] -->
 
 <!-- Start SDK Example Usage [usage] -->
@@ -227,7 +258,7 @@ run();
 
 ### Move long-term memories
 
-Optionally move existing memories into a namespace.
+Optionally move existing memories into a namespace. Omit namespaceRef to auto-route memories already in a shared namespace when store routing is enabled.
 
 ```typescript
 import { AgentMemory } from "@redis-iris/agent-memory";
@@ -253,6 +284,251 @@ async function run() {
 
 run();
 
+```
+
+### Set namespace routing policy
+
+Replace the store routing policy. Accept rules pick a shared namespace from memory text. Reject rules can veto that destination, including explicit placements.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.putNamespaceRouting({
+    policy: {
+      enabled: true,
+      rules: [
+        {
+          id: "invoices",
+          destination: {
+            namespaceId: "ns-product",
+          },
+          enabled: true,
+          action: "accept",
+          strategies: [
+            {
+              kind: "matcher_spec",
+              matcher: {
+                kind: "regex",
+                regex: {
+                  pattern: "invoice",
+                },
+              },
+            },
+          ],
+        },
+      ],
+    },
+  });
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Get namespace routing policy
+
+Read the store routing policy. An empty disabled policy is returned when none has been saved.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.getNamespaceRouting();
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Submit a document for extraction
+
+Use an Extractor configured for documents in the control plane. The response accepts an asynchronous job; poll its status before reading outputs. Reuse the idempotency key only for the same submission.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.createDocumentIngestion({
+    documentId: "customer-preferences",
+    revision: "v1",
+    content: "Q3VzdG9tZXIgcHJlZmVycyBlbWFpbCB1cGRhdGVzLg==",
+    mediaType: "text/plain",
+    ownerId: "user-123",
+    extractorId: "document-extractor",
+    idempotencyKey: "customer-preferences-v1",
+  });
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Check document ingestion
+
+Replace the ingestion ID with the ID returned by submission. Wait for a terminal status before listing the extracted memories.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.getDocumentIngestion(
+    "0123456789abcdef0123456789abcdef",
+  );
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Read document ingestion outputs
+
+List the memories created by an ingestion. Use limit and offset to read more pages.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.listDocumentIngestionOutputs(
+    "0123456789abcdef0123456789abcdef",
+  );
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Create a Summary View
+
+Create an owner-grouped view of long-term memories. Summary Views must be enabled in the deployment.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.createSummaryView({
+    name: "Customer preferences",
+    source: "long_term",
+    groupBy: [
+      "ownerId",
+    ],
+    output: {
+      format: "text",
+      instructions: "Summarize the customer's preferences.",
+    },
+    refreshPolicy: {
+      mode: "manual",
+    },
+  });
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Refresh a Summary View
+
+Queue a refresh for one owner. Replace the view ID with the ID returned when creating the view.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.refreshSummaryView(
+    "0123456789abcdef0123456789abcdef",
+    {
+      target: "partition",
+      scope: {
+        ownerId: "user-123",
+      },
+    },
+  );
+
+  console.log(result);
+}
+
+run();
+
+```
+
+### Read a Summary View result
+
+Read the latest result for the same owner scope. Refresh runs asynchronously, so inspect the returned status.
+
+```typescript
+import { AgentMemory } from "@redis-iris/agent-memory";
+
+const agentMemory = new AgentMemory({
+  serverURL: "https://api.example.com",
+  storeId: "<id>",
+  apiKey: "<AGENT_MEMORY_API_KEY>",
+});
+
+async function run() {
+  const result = await agentMemory.getSummaryViewResult(
+    "0123456789abcdef0123456789abcdef",
+    "user-123",
+  );
+
+  console.log(result);
+}
+
+run();
+
 ```
 <!-- End SDK Example Usage [usage] -->
 
@@ -293,28 +569,46 @@ run();
 <details open>
 <summary>Available methods</summary>
 
-### [AgentMemory SDK](docs/sdks/agentmemory/README.md)
-
-* [health](docs/sdks/agentmemory/README.md#health) - Return information about the operational status of the service.
-* [storeHealth](docs/sdks/agentmemory/README.md#storehealth) - Returns read-only health for applicable store-scoped RAM features.
-* [bulkDeleteLongTermMemories](docs/sdks/agentmemory/README.md#bulkdeletelongtermmemories) - Deletes long-term memories in bulk by their IDs.
-* [bulkCreateLongTermMemories](docs/sdks/agentmemory/README.md#bulkcreatelongtermmemories) - Creates long-term memories in bulk.
-* [moveLongTermMemories](docs/sdks/agentmemory/README.md#movelongtermmemories) - Moves long-term memories to one existing namespace resource. Returns 409 when the destination namespace is archived.
-* [searchLongTermMemory](docs/sdks/agentmemory/README.md#searchlongtermmemory) - Runs a semantic search on long-term memory with filtering options.
-* [getLongTermMemory](docs/sdks/agentmemory/README.md#getlongtermmemory) - Returns a long-term memory by its ID.
-* [updateLongTermMemory](docs/sdks/agentmemory/README.md#updatelongtermmemory) - Partially updates a long-term memory by its ID.
-* [updateLongTermMemoryFields](docs/sdks/agentmemory/README.md#updatelongtermmemoryfields) - Atomically updates a custom-typed long-term memory's text and/or attributes, scoped to the caller's bound memory type. Used by the custom-extraction worker.
-* [listNamespaces](docs/sdks/agentmemory/README.md#listnamespaces) - Lists namespace roots or direct children.
-* [createNamespace](docs/sdks/agentmemory/README.md#createnamespace) - Creates a namespace resource as a root, direct child, or explicit hierarchy path. Returns 409 when an active or archived namespace already occupies the requested location.
-* [deleteNamespace](docs/sdks/agentmemory/README.md#deletenamespace) - Deletes an empty leaf namespace. Returns 409 when the namespace has children or memory placements, or when it changed concurrently.
-* [getNamespace](docs/sdks/agentmemory/README.md#getnamespace) - Gets one namespace by its canonical ID.
-* [updateNamespace](docs/sdks/agentmemory/README.md#updatenamespace) - Renames or archives a namespace. Returns 409 when the namespace changed concurrently, an active or archived sibling already uses the requested name, or the namespace is archived.
-* [listSessions](docs/sdks/agentmemory/README.md#listsessions) - Returns a paginated list of session IDs for a store.
-* [addSessionEvent](docs/sdks/agentmemory/README.md#addsessionevent) - Appends a single event to a session. Creates the session if it does not exist. If sessionId is omitted, the server generates one.
-* [deleteSessionMemory](docs/sdks/agentmemory/README.md#deletesessionmemory) - Deletes the session memory for a session.
-* [getSessionMemory](docs/sdks/agentmemory/README.md#getsessionmemory) - Returns the session memory for a session.
-* [deleteSessionEvent](docs/sdks/agentmemory/README.md#deletesessionevent) - Deletes a single event from a session by event ID.
-* [getSessionEvent](docs/sdks/agentmemory/README.md#getsessionevent) - Returns a single event from a session by event ID.
+### AgentMemory SDK
+
+* health - Return information about the operational status of the service.
+* createDocumentIngestion - Submit one revisioned document for extraction.
+* getDocumentIngestion
+* listDocumentIngestionOutputs
+* storeHealth - Returns read-only health for applicable store-scoped RAM features.
+* listIngestionHookStatuses - List hook decisions in stable newest-first order. Pages can be empty after owner filtering; continue while nextCursor is present. Internal run reservations are omitted.
+* getIngestionHookStatus - Read a hook decision and application status. Requires authenticated store access and, when enforced, matching owner scope. Content and secrets are never returned.
+* bulkDeleteLongTermMemories - Deletes long-term memories in bulk by their IDs.
+* bulkCreateLongTermMemories - Creates long-term memories in bulk. Records without namespace or namespaceRef stay un-namespaced. Automatic routing does not place them in a shared namespace. An explicit namespaceRef must pass destination admission and is never rerouted. Admission failures are reported per record in errors.
+* moveLongTermMemories - Moves long-term memories to an explicit namespaceRef, or automatically routes a memory that is already in a shared namespace when namespaceRef is omitted. Personal and un-namespaced memories are not automatic-routing candidates and keep their current placement with a per-item error. If routing is disabled or no shared destination qualifies, the memory also keeps its current placement and receives a per-item error. An explicit destination must pass admission and is never rerouted. Returns 409 when the explicit destination is archived; automatic routing and admission failures are reported per item in errors.
+* searchLongTermMemory - Runs a semantic search on long-term memory with filtering options.
+* getLongTermMemory - Returns a long-term memory by its ID.
+* updateLongTermMemory - Partially updates a long-term memory by its ID. The merged record must pass admission at its destination. Updates never select a different destination automatically.
+* updateLongTermMemoryFields - Atomically updates a custom-typed long-term memory's text and/or attributes, scoped to the caller's bound memory type. Used by the custom-extraction worker. New text must pass destination admission before the update is applied.
+* listMemorySourceLinks - Pages source links for one long-term memory. Tokens bind this query and expire.
+* listMemorySourceEvidence - Pages extraction evidence for one source of a memory, in append order. Tokens bind the store, current owner, memory and source, and expire.
+* getNamespaceRouting - Returns the store's namespace routing policy. An empty disabled policy is returned when none has been saved.
+* putNamespaceRouting - Replaces the store's namespace routing policy. Namespaces remain hierarchy records; routing is an ordered store-level document of plug-in strategies.
+* listNamespaces - Lists namespace roots or direct children.
+* createNamespace - Creates a namespace resource as a root, direct child, or explicit hierarchy path. Returns 409 when an active or archived namespace already occupies the requested location.
+* deleteNamespace - Deletes an empty leaf namespace. Returns 409 when the namespace has children or memory placements, or when it changed concurrently.
+* getNamespace - Gets one namespace by its canonical ID.
+* updateNamespace - Renames or archives a namespace. Returns 409 when the namespace changed concurrently, an active or archived sibling already uses the requested name, or the namespace is archived.
+* listSessions - Returns a paginated list of session IDs for a store.
+* addSessionEvent - Appends a single event to a session. Creates the session if it does not exist. If sessionId is omitted, the server generates one.
+* deleteSessionMemory - Deletes the session memory for a session.
+* getSessionMemory - Returns the session memory for a session.
+* deleteSessionEvent - Deletes a single event from a session by event ID.
+* getSessionEvent - Returns a single event from a session by event ID.
+* listSessionSummaries - Returns paginated session rows with metadata and caller-selected order. The ID-only ListSessions operation remains unchanged.
+* listSourceMemories - Pages memories linked to one source. A source link does not grant access to a memory in another owner or namespace.
+* listSummaryViews - Lists Summary View definitions and high-level state. Partition values are not included.
+* createSummaryView - Creates a Summary View definition and asynchronously enqueues its initial reconciliation.
+* deleteSummaryView - Marks a Summary View deleting and asynchronously removes its schedule and materializations in bounded batches. Repeated requests are idempotent.
+* getSummaryView - Returns one Summary View definition without partition values.
+* updateSummaryView - Updates mutable Summary View fields. Source is immutable. Material changes increment definitionVersion; name- or description-only changes do not enqueue refresh work.
+* refreshSummaryView - Asynchronously enqueues one exact partition refresh or a complete view reconciliation. It never performs generation synchronously.
+* getSummaryViewResult - Returns one authorized exact Summary View partition after validating its contributing source records. Invalid output is withheld while repair is pending.
 
 </details>
 <!-- End Available Resources and Operations [operations] -->
@@ -328,32 +622,50 @@ runtimes or other environments where application bundle size is a primary
 concern. When using a bundler to build your application, all unused
 functionality will be either excluded from the final bundle or tree-shaken away.
 
-To read more about standalone functions, check [FUNCTIONS.md](./FUNCTIONS.md).
+To read more about standalone functions, check FUNCTIONS.md.
 
 <details>
 
 <summary>Available standalone functions</summary>
 
-- [`addSessionEvent`](docs/sdks/agentmemory/README.md#addsessionevent) - Appends a single event to a session. Creates the session if it does not exist. If sessionId is omitted, the server generates one.
-- [`bulkCreateLongTermMemories`](docs/sdks/agentmemory/README.md#bulkcreatelongtermmemories) - Creates long-term memories in bulk.
-- [`bulkDeleteLongTermMemories`](docs/sdks/agentmemory/README.md#bulkdeletelongtermmemories) - Deletes long-term memories in bulk by their IDs.
-- [`createNamespace`](docs/sdks/agentmemory/README.md#createnamespace) - Creates a namespace resource as a root, direct child, or explicit hierarchy path. Returns 409 when an active or archived namespace already occupies the requested location.
-- [`deleteNamespace`](docs/sdks/agentmemory/README.md#deletenamespace) - Deletes an empty leaf namespace. Returns 409 when the namespace has children or memory placements, or when it changed concurrently.
-- [`deleteSessionEvent`](docs/sdks/agentmemory/README.md#deletesessionevent) - Deletes a single event from a session by event ID.
-- [`deleteSessionMemory`](docs/sdks/agentmemory/README.md#deletesessionmemory) - Deletes the session memory for a session.
-- [`getLongTermMemory`](docs/sdks/agentmemory/README.md#getlongtermmemory) - Returns a long-term memory by its ID.
-- [`getNamespace`](docs/sdks/agentmemory/README.md#getnamespace) - Gets one namespace by its canonical ID.
-- [`getSessionEvent`](docs/sdks/agentmemory/README.md#getsessionevent) - Returns a single event from a session by event ID.
-- [`getSessionMemory`](docs/sdks/agentmemory/README.md#getsessionmemory) - Returns the session memory for a session.
-- [`health`](docs/sdks/agentmemory/README.md#health) - Return information about the operational status of the service.
-- [`listNamespaces`](docs/sdks/agentmemory/README.md#listnamespaces) - Lists namespace roots or direct children.
-- [`listSessions`](docs/sdks/agentmemory/README.md#listsessions) - Returns a paginated list of session IDs for a store.
-- [`moveLongTermMemories`](docs/sdks/agentmemory/README.md#movelongtermmemories) - Moves long-term memories to one existing namespace resource. Returns 409 when the destination namespace is archived.
-- [`searchLongTermMemory`](docs/sdks/agentmemory/README.md#searchlongtermmemory) - Runs a semantic search on long-term memory with filtering options.
-- [`storeHealth`](docs/sdks/agentmemory/README.md#storehealth) - Returns read-only health for applicable store-scoped RAM features.
-- [`updateLongTermMemory`](docs/sdks/agentmemory/README.md#updatelongtermmemory) - Partially updates a long-term memory by its ID.
-- [`updateLongTermMemoryFields`](docs/sdks/agentmemory/README.md#updatelongtermmemoryfields) - Atomically updates a custom-typed long-term memory's text and/or attributes, scoped to the caller's bound memory type. Used by the custom-extraction worker.
-- [`updateNamespace`](docs/sdks/agentmemory/README.md#updatenamespace) - Renames or archives a namespace. Returns 409 when the namespace changed concurrently, an active or archived sibling already uses the requested name, or the namespace is archived.
+- `addSessionEvent` - Appends a single event to a session. Creates the session if it does not exist. If sessionId is omitted, the server generates one.
+- `bulkCreateLongTermMemories` - Creates long-term memories in bulk. Records without namespace or namespaceRef stay un-namespaced. Automatic routing does not place them in a shared namespace. An explicit namespaceRef must pass destination admission and is never rerouted. Admission failures are reported per record in errors.
+- `bulkDeleteLongTermMemories` - Deletes long-term memories in bulk by their IDs.
+- `createDocumentIngestion` - Submit one revisioned document for extraction.
+- `createNamespace` - Creates a namespace resource as a root, direct child, or explicit hierarchy path. Returns 409 when an active or archived namespace already occupies the requested location.
+- `createSummaryView` - Creates a Summary View definition and asynchronously enqueues its initial reconciliation.
+- `deleteNamespace` - Deletes an empty leaf namespace. Returns 409 when the namespace has children or memory placements, or when it changed concurrently.
+- `deleteSessionEvent` - Deletes a single event from a session by event ID.
+- `deleteSessionMemory` - Deletes the session memory for a session.
+- `deleteSummaryView` - Marks a Summary View deleting and asynchronously removes its schedule and materializations in bounded batches. Repeated requests are idempotent.
+- `getDocumentIngestion`
+- `getIngestionHookStatus` - Read a hook decision and application status. Requires authenticated store access and, when enforced, matching owner scope. Content and secrets are never returned.
+- `getLongTermMemory` - Returns a long-term memory by its ID.
+- `getNamespace` - Gets one namespace by its canonical ID.
+- `getNamespaceRouting` - Returns the store's namespace routing policy. An empty disabled policy is returned when none has been saved.
+- `getSessionEvent` - Returns a single event from a session by event ID.
+- `getSessionMemory` - Returns the session memory for a session.
+- `getSummaryView` - Returns one Summary View definition without partition values.
+- `getSummaryViewResult` - Returns one authorized exact Summary View partition after validating its contributing source records. Invalid output is withheld while repair is pending.
+- `health` - Return information about the operational status of the service.
+- `listDocumentIngestionOutputs`
+- `listIngestionHookStatuses` - List hook decisions in stable newest-first order. Pages can be empty after owner filtering; continue while nextCursor is present. Internal run reservations are omitted.
+- `listMemorySourceEvidence` - Pages extraction evidence for one source of a memory, in append order. Tokens bind the store, current owner, memory and source, and expire.
+- `listMemorySourceLinks` - Pages source links for one long-term memory. Tokens bind this query and expire.
+- `listNamespaces` - Lists namespace roots or direct children.
+- `listSessions` - Returns a paginated list of session IDs for a store.
+- `listSessionSummaries` - Returns paginated session rows with metadata and caller-selected order. The ID-only ListSessions operation remains unchanged.
+- `listSourceMemories` - Pages memories linked to one source. A source link does not grant access to a memory in another owner or namespace.
+- `listSummaryViews` - Lists Summary View definitions and high-level state. Partition values are not included.
+- `moveLongTermMemories` - Moves long-term memories to an explicit namespaceRef, or automatically routes a memory that is already in a shared namespace when namespaceRef is omitted. Personal and un-namespaced memories are not automatic-routing candidates and keep their current placement with a per-item error. If routing is disabled or no shared destination qualifies, the memory also keeps its current placement and receives a per-item error. An explicit destination must pass admission and is never rerouted. Returns 409 when the explicit destination is archived; automatic routing and admission failures are reported per item in errors.
+- `putNamespaceRouting` - Replaces the store's namespace routing policy. Namespaces remain hierarchy records; routing is an ordered store-level document of plug-in strategies.
+- `refreshSummaryView` - Asynchronously enqueues one exact partition refresh or a complete view reconciliation. It never performs generation synchronously.
+- `searchLongTermMemory` - Runs a semantic search on long-term memory with filtering options.
+- `storeHealth` - Returns read-only health for applicable store-scoped RAM features.
+- `updateLongTermMemory` - Partially updates a long-term memory by its ID. The merged record must pass admission at its destination. Updates never select a different destination automatically.
+- `updateLongTermMemoryFields` - Atomically updates a custom-typed long-term memory's text and/or attributes, scoped to the caller's bound memory type. Used by the custom-extraction worker. New text must pass destination admission before the update is applied.
+- `updateNamespace` - Renames or archives a namespace. Returns 409 when the namespace changed concurrently, an active or archived sibling already uses the requested name, or the namespace is archived.
+- `updateSummaryView` - Updates mutable Summary View fields. Source is immutable. Material changes increment definitionVersion; name- or description-only changes do not enqueue refresh work.
 
 </details>
 <!-- End Standalone functions [standalone-funcs] -->
@@ -363,7 +675,7 @@ To read more about standalone functions, check [FUNCTIONS.md](./FUNCTIONS.md).
 
 A parameter is configured globally. This parameter may be set on the SDK client instance itself during initialization. When configured as an option during SDK initialization, This global value will be used as the default on the operations that use it. When such operations are called, there is a place in each to override the global value, if needed.
 
-For example, you can set `storeId` to `"<id>"` at SDK initialization and then you do not have to pass the same value on calls to operations like `storeHealth`. But if you want to do so you may, which will locally override the global setting. See the example code below for a demonstration.
+For example, you can set `storeId` to `"<id>"` at SDK initialization and then you do not have to pass the same value on calls to operations like `createDocumentIngestion`. But if you want to do so you may, which will locally override the global setting. See the example code below for a demonstration.
 
 
 ### Available Globals
@@ -387,7 +699,15 @@ const agentMemory = new AgentMemory({
 });
 
 async function run() {
-  const result = await agentMemory.storeHealth();
+  const result = await agentMemory.createDocumentIngestion({
+    documentId: "customer-preferences",
+    revision: "v1",
+    content: "Q3VzdG9tZXIgcHJlZmVycyBlbWFpbCB1cGRhdGVzLg==",
+    mediaType: "text/plain",
+    ownerId: "user-123",
+    extractorId: "document-extractor",
+    idempotencyKey: "customer-preferences-v1",
+  });
 
   console.log(result);
 }
@@ -465,7 +785,7 @@ run();
 <!-- Start Error Handling [errors] -->
 ## Error Handling
 
-[`AgentMemoryError`](./src/models/errors/agent-memory-error.ts) is the base class for all HTTP error responses. It has the following properties:
+`AgentMemoryError` is the base class for all HTTP error responses. It has the following properties:
 
 | Property            | Type       | Description                                                                             |
 | ------------------- | ---------- | --------------------------------------------------------------------------------------- |
@@ -489,7 +809,15 @@ const agentMemory = new AgentMemory({
 
 async function run() {
   try {
-    const result = await agentMemory.storeHealth();
+    const result = await agentMemory.createDocumentIngestion({
+      documentId: "customer-preferences",
+      revision: "v1",
+      content: "Q3VzdG9tZXIgcHJlZmVycyBlbWFpbCB1cGRhdGVzLg==",
+      mediaType: "text/plain",
+      ownerId: "user-123",
+      extractorId: "document-extractor",
+      idempotencyKey: "customer-preferences-v1",
+    });
 
     console.log(result);
   } catch (error) {
@@ -518,34 +846,38 @@ run();
 
 ### Error Classes
 **Primary errors:**
-* [`AgentMemoryError`](./src/models/errors/agent-memory-error.ts): The base class for HTTP error responses.
-  * [`BadRequestErrorResponseContent`](./src/models/errors/bad-request-error-response-content.ts): Request validation or input decoding failed. Status code `400`. *
-  * [`AuthenticationErrorResponseContent`](./src/models/errors/authentication-error-response-content.ts): Authentication credentials are missing, malformed, or invalid. Status code `401`. *
-  * [`ForbiddenErrorResponseContent`](./src/models/errors/forbidden-error-response-content.ts): The caller is authenticated but not allowed to access the requested resource. Status code `403`. *
-  * [`NotFoundErrorResponseContent`](./src/models/errors/not-found-error-response-content.ts): The requested resource does not exist. Status code `404`. *
-  * [`TimeoutErrorResponseContent`](./src/models/errors/timeout-error-response-content.ts): The request timed out before the service could complete it. Status code `408`. *
-  * [`ResourceSuspendedErrorResponseContent`](./src/models/errors/resource-suspended-error-response-content.ts): The requested resource exists but is suspended by an administrator. Status code `423`. *
-  * [`TooManyRequestsErrorResponseContent`](./src/models/errors/too-many-requests-error-response-content.ts): The service rejected the request because rate limits were exceeded. Status code `429`. *
-  * [`UnexpectedErrorResponseContent`](./src/models/errors/unexpected-error-response-content.ts): The service failed with an unexpected internal error. Status code `500`. *
-  * [`PayloadTooLargeErrorResponseContent`](./src/models/errors/payload-too-large-error-response-content.ts): The request payload exceeds the maximum supported size. Status code `413`. *
-
-<details><summary>Less common errors (9)</summary>
+* `AgentMemoryError`: The base class for HTTP error responses.
+  * `BadRequestErrorResponseContent`: Request validation or input decoding failed. Status code `400`. *
+  * `AuthenticationErrorResponseContent`: Authentication credentials are missing, malformed, or invalid. Status code `401`. *
+  * `ForbiddenErrorResponseContent`: The caller is authenticated but not allowed to access the requested resource. Status code `403`. *
+  * `UnexpectedErrorResponseContent`: The service failed with an unexpected internal error. Status code `500`. *
+  * `NotFoundErrorResponseContent`: The requested resource does not exist. Status code `404`. *
+  * `TimeoutErrorResponseContent`: The request timed out before the service could complete it. Status code `408`. *
+
+<details><summary>Less common errors (16)</summary>
 
 <br />
 
 **Network errors:**
-* [`ConnectionError`](./src/models/errors/http-client-errors.ts): HTTP client was unable to make a request to a server.
-* [`RequestTimeoutError`](./src/models/errors/http-client-errors.ts): HTTP request timed out due to an AbortSignal signal.
-* [`RequestAbortedError`](./src/models/errors/http-client-errors.ts): HTTP request was aborted by the client.
-* [`InvalidRequestError`](./src/models/errors/http-client-errors.ts): Any input used to create a request is invalid.
-* [`UnexpectedClientError`](./src/models/errors/http-client-errors.ts): Unrecognised or unexpected error.
-
-
-**Inherit from [`AgentMemoryError`](./src/models/errors/agent-memory-error.ts)**:
-* [`FailedDependencyErrorResponseContent`](./src/models/errors/failed-dependency-error-response-content.ts): A dependent resource required to process the request is unavailable or unhealthy. Status code `424`. Applicable to 15 of 20 methods.*
-* [`ConflictErrorResponseContent`](./src/models/errors/conflict-error-response-content.ts): The request conflicts with the current state of the resource. Status code `409`. Applicable to 4 of 20 methods.*
-* [`MemoryFailedDependencyErrorResponseContent`](./src/models/errors/memory-failed-dependency-error-response-content.ts): A resource or model-provider dependency required by Agent Memory could not complete the request. Status code `424`. Applicable to 4 of 20 methods.*
-* [`ResponseValidationError`](./src/models/errors/response-validation-error.ts): Type mismatch between the data returned from the server and the structure expected by the SDK. See `error.rawValue` for the raw value and `error.pretty()` for a nicely formatted multi-line string.
+* `ConnectionError`: HTTP client was unable to make a request to a server.
+* `RequestTimeoutError`: HTTP request timed out due to an AbortSignal signal.
+* `RequestAbortedError`: HTTP request was aborted by the client.
+* `InvalidRequestError`: Any input used to create a request is invalid.
+* `UnexpectedClientError`: Unrecognised or unexpected error.
+
+
+**Inherit from `AgentMemoryError`**:
+* `ResourceSuspendedErrorResponseContent`: The requested resource exists but is suspended by an administrator. Status code `423`. Applicable to 30 of 38 methods.*
+* `FailedDependencyErrorResponseContent`: A dependent resource required to process the request is unavailable or unhealthy. Status code `424`. Applicable to 30 of 38 methods.*
+* `TooManyRequestsErrorResponseContent`: The service rejected the request because rate limits were exceeded. Status code `429`. Applicable to 27 of 38 methods.*
+* `PayloadTooLargeErrorResponseContent`: The request payload exceeds the maximum supported size. Status code `413`. Applicable to 24 of 38 methods.*
+* `ConflictErrorResponseContent`: The request conflicts with the current state of the resource. Status code `409`. Applicable to 8 of 38 methods.*
+* `MemoryFailedDependencyErrorResponseContent`: A resource or model-provider dependency required by Agent Memory could not complete the request. Status code `424`. Applicable to 7 of 38 methods.*
+* `SummaryViewConflictErrorResponseContent`: A Summary View operation conflicts with the current definition or partition state. Status code `409`. Applicable to 5 of 38 methods.*
+* `IngestionHookStoppedErrorResponseContent`: The ingestion hook stopped this operation without applying unapproved content. Status code `422`. Applicable to 3 of 38 methods.*
+* `SummaryViewQuotaErrorResponseContent`: A Summary View operation exceeded an enabled store quota. Exact ceilings are deployment configuration established from benchmark evidence. Status code `429`. Applicable to 3 of 38 methods.*
+* `IngestionHookRetryErrorResponseContent`: A saved ingestion hook decision is waiting for its next bounded attempt. Status code `503`. Applicable to 3 of 38 methods.*
+* `ResponseValidationError`: Type mismatch between the data returned from the server and the structure expected by the SDK. See `error.rawValue` for the raw value and `error.pretty()` for a nicely formatted multi-line string.
 
 </details>
 
@@ -636,7 +968,7 @@ looking for the latest version.
 
 ## Contributions
 
-While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. 
-We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release. 
+While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation.
+We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.
 
 ### SDK Created by [Speakeasy](https://www.speakeasy.com/?utm_source=@redis-iris/agent-memory&utm_campaign=typescript)