@mastra/upstash 1.4.0-alpha.1 → 1.4.0-alpha.3

package/CHANGELOG.md

@@ -1,5 +1,37 @@
 # @mastra/upstash
 
+## 1.4.0-alpha.3
+
+### Patch Changes
+
+- Fixed a crash where updating a thread without a title (for example during observational memory buffering) could write a null title and violate the database's not-null constraint when running a newer @mastra/memory against an older storage package. Memory now checks whether the connected storage adapter supports partial thread updates and backfills the existing title for older adapters, so mixed-version deployments keep working. See #21041 for the original title-clobbering fix this makes backward compatible. ([#21257](https://github.com/mastra-ai/mastra/pull/21257))
+
+- Storage adapters now declare support for partial thread updates, letting newer @mastra/memory preserve existing thread titles instead of overwriting them, while remaining safe against older versions. ([#21257](https://github.com/mastra-ai/mastra/pull/21257))
+
+- Updated dependencies [[`dc4a25d`](https://github.com/mastra-ai/mastra/commit/dc4a25d41af4e2fe97a816070eaec6aa963ab53b), [`dc4a25d`](https://github.com/mastra-ai/mastra/commit/dc4a25d41af4e2fe97a816070eaec6aa963ab53b)]:
+  - @mastra/core@1.58.0-alpha.15
+  - @mastra/redis@1.4.0-alpha.3
+
+## 1.4.0-alpha.2
+
+### Patch Changes
+
+- Fixed generated thread titles being clobbered during a turn ([#21041](https://github.com/mastra-ai/mastra/pull/21041))
+
+  `updateThread` required both `title` and `metadata`, so callers that only needed to
+  change metadata (message persistence, working memory, observational memory, channel
+  subscriptions) had to read the thread and pass its title back. When title generation
+  finished between that read and the write, the freshly generated title was overwritten
+  with the stale one.
+
+  `title` and `metadata` are now independently optional: omitting one leaves that column
+  untouched. Callers that only change metadata no longer send a title, and message
+  persistence no longer rewrites a thread row it just read.
+
+- Updated dependencies [[`1c75e32`](https://github.com/mastra-ai/mastra/commit/1c75e32f7fc0b9fb6f548b4407feaec8a1440212), [`c47165c`](https://github.com/mastra-ai/mastra/commit/c47165c983c87594c6952f1fd2fa51a90205034c), [`e08e789`](https://github.com/mastra-ai/mastra/commit/e08e789c1bf4cd2fe46363f7a4728536ceccc9bd), [`35cc901`](https://github.com/mastra-ai/mastra/commit/35cc90102cf834a84827acaf9eee0b6d6d1e2a3b), [`a8b4cf0`](https://github.com/mastra-ai/mastra/commit/a8b4cf02823cffebc4751a53337dfacf097c1ae1), [`f33264f`](https://github.com/mastra-ai/mastra/commit/f33264f517ae603279afd5c4251e2b40f6dd3618), [`689f2c4`](https://github.com/mastra-ai/mastra/commit/689f2c4b6c0835fe455702b01d21daa8abcd9331), [`eeae63e`](https://github.com/mastra-ai/mastra/commit/eeae63e7fbe8e1f237adc69bca6e2ac13c5ca907), [`4c186a0`](https://github.com/mastra-ai/mastra/commit/4c186a017275f45e6ed4c09de0f89550e2d09e8c), [`b0fa077`](https://github.com/mastra-ai/mastra/commit/b0fa077bcbc9b08551846fe372a0d3d15b71ed72)]:
+  - @mastra/core@1.58.0-alpha.8
+  - @mastra/redis@1.4.0-alpha.2
+
 ## 1.4.0-alpha.1
 
 ### Patch Changes

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-upstash
 description: Documentation for @mastra/upstash. Use when working with @mastra/upstash APIs, configuration, or implementation.
 metadata:
   package: "@mastra/upstash"
-  version: "1.4.0-alpha.1"
+  version: "1.4.0-alpha.3"
 ---
 
 ## When to use
@@ -18,14 +18,14 @@ Read the individual reference documents for detailed explanations and code examp
 
 - [Working memory](references/docs-memory-working-memory.md) - Learn how to configure working memory in Mastra to store persistent user data, preferences.
 
-### Guides
+### Integrations
 
-- [Retrieval, semantic search, reranking](references/guides-rag-retrieval.md) - Guide on retrieval processes in Mastra's RAG systems, including semantic search, filtering, and re-ranking.
-- [Storing embeddings in a vector database](references/guides-rag-vector-databases.md) - Guide on vector storage options in Mastra, including embedded and dedicated vector databases for similarity search.
+- [Upstash](references/integrations-databases-upstash.md) - Documentation for the Upstash storage implementation in Mastra.
 
 ### Reference
 
-- [Reference: Upstash storage](references/reference-storage-upstash.md) - Documentation for the Upstash storage implementation in Mastra.
+- [Retrieval, semantic search, reranking](references/reference-rag-retrieval.md) - Guide on retrieval processes in Mastra's RAG systems, including semantic search, filtering, and re-ranking.
+- [Storing embeddings in a vector database](references/reference-rag-vector-databases.md) - Guide on vector storage options in Mastra, including embedded and dedicated vector databases for similarity search.
 - [Reference: Upstash vector store](references/reference-vectors-upstash.md) - Documentation for the UpstashVector class in Mastra, which provides vector search using Upstash Vector.
 
 

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.4.0-alpha.1",
+  "version": "1.4.0-alpha.3",
   "package": "@mastra/upstash",
   "exports": {},
   "modules": {}

package/dist/docs/references/docs-memory-working-memory.md

@@ -129,6 +129,7 @@ Resource-scoped working memory requires specific storage adapters that support t
 
 - **libSQL** (`@mastra/libsql`)
 - **PostgreSQL** (`@mastra/pg`)
+- **OracleDB** (`@mastra/oracledb`)
 - **Upstash** (`@mastra/upstash`)
 - **MongoDB** (`@mastra/mongodb`)
 

package/dist/docs/references/{reference-storage-upstash.md → integrations-databases-upstash.md}

@@ -1,6 +1,6 @@
 > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
 
-# Upstash storage
+# Upstash
 
 The Upstash storage implementation provides a serverless-friendly storage solution using Upstash's Redis-compatible key-value store.
 

package/dist/docs/references/{guides-rag-retrieval.md → reference-rag-retrieval.md}

@@ -436,6 +436,23 @@ export const ragAgent = new Agent({
 })
 ```
 
+**OracleDB**:
+
+```ts
+import { ORACLEDB_PROMPT } from '@mastra/oracledb'
+
+export const ragAgent = new Agent({
+  id: 'rag-agent',
+  name: 'RAG Agent',
+  model: 'openai/gpt-5.6-sol',
+  instructions: `
+  Process queries using the provided context. Structure responses to be concise and relevant.
+  ${ORACLEDB_PROMPT}
+  `,
+  tools: { vectorQueryTool },
+})
+```
+
 **S3Vectors**:
 
 ```ts
@@ -517,4 +534,4 @@ The re-ranked results combine vector similarity with semantic understanding to i
 
 For more details about re-ranking, see the [rerank()](https://mastra.ai/reference/rag/rerankWithScorer) method.
 
-For graph-based retrieval that follows connections between chunks, see the [GraphRAG](https://mastra.ai/guides/rag/graph-rag) documentation.
+For graph-based retrieval that follows connections between chunks, see the [GraphRAG](https://mastra.ai/reference/rag/graph-rag-guide) documentation.

package/dist/docs/references/{guides-rag-vector-databases.md → reference-rag-vector-databases.md}

@@ -78,6 +78,35 @@ await store.upsert({
 
 PostgreSQL with the pgvector extension is a good solution for teams already using PostgreSQL who want to minimize infrastructure complexity. For detailed setup instructions and best practices, see the [official pgvector repository](https://github.com/pgvector/pgvector).
 
+**OracleDB**:
+
+```ts
+import { OracleVector } from '@mastra/oracledb'
+
+const store = new OracleVector({
+  id: 'oracle-vector',
+  user: process.env.ORACLE_DATABASE_USER,
+  password: process.env.ORACLE_DATABASE_PASSWORD,
+  connectString: process.env.ORACLE_DATABASE_CONNECT_STRING,
+})
+
+await store.createIndex({
+  indexName: 'myCollection',
+  dimension: 1536,
+  indexConfig: { type: 'none' },
+})
+
+await store.upsert({
+  indexName: 'myCollection',
+  vectors: embeddings,
+  metadata: chunks.map(chunk => ({ text: chunk.text })),
+})
+```
+
+### Using Oracle Database Vector Search
+
+OracleDB stores embeddings in native `VECTOR` columns and metadata in Oracle JSON. Exact search is the default; HNSW and IVF indexes can be configured for tuned deployments.
+
 **Pinecone**:
 
 ```ts
@@ -378,7 +407,7 @@ await store.createIndex({
 
 The dimension size must match the output dimension of your chosen embedding model. Common dimension sizes are:
 
-- `OpenAI text-embedding-3-small`: 1536 dimensions (or custom, e.g., 256)
+- OpenAI `text-embedding-3-small`: 1536 dimensions (or custom, e.g., 256)
 - `Cohere embed-multilingual-v3`: 1024 dimensions
 - `VoyageAI voyage-3.5`: 1024 dimensions (or custom: 256, 512, 1024, 2048)
 - `Google gemini-embedding-001`: 768 dimensions (or custom)
@@ -410,6 +439,18 @@ Index names must:
 - Example: `my_index_123` is valid
 - Example: `my-index` is not valid (contains hyphen)
 
+**OracleDB**:
+
+Index names are logical Mastra names. OracleDB maps each logical index to a physical Oracle table internally.
+
+Logical index names must:
+
+- Be non-empty
+- Be 512 characters or fewer
+- Be stable for the lifetime of the vector index
+- Example: `my_collection_123` is valid
+- Example: `customer-support/docs:v1` is valid and is mapped to a safe Oracle table name
+
 **Pinecone**:
 
 Index names must:

package/dist/index.cjs

@@ -334,6 +334,7 @@ function getMessageIndexKey(messageId) {
 	return `msg-idx:${messageId}`;
 }
 var StoreMemoryUpstash = class extends _mastra_core_storage.MemoryStorage {
+	supportsPartialThreadUpdate = true;
 	client;
 	#db;
 	constructor(config) {
@@ -485,7 +486,7 @@ var StoreMemoryUpstash = class extends _mastra_core_storage.MemoryStorage {
 		const now = /* @__PURE__ */ new Date();
 		const updatedThread = {
 			...thread,
-			title,
+			title: title ?? thread.title,
 			metadata: {
 				...thread.metadata,
 				...metadata