@mastra/libsql 1.18.0 → 1.19.0-alpha.0

package/dist/docs/references/reference-storage-retention.md

@@ -4,9 +4,9 @@
 
 Storage grows without bound by default. Retention is an opt-in, age-based cleanup system: you declare per-table `maxAge` policies in the `retention` config, then call `storage.prune()` to delete rows older than their configured age. Anything you don't configure is kept forever, so there is no behavior change until you opt in.
 
-`prune()` deletes rows. It caps growth and is safe to run against large tables (batched, bounded, resumable, cancellable). It never reclaims disk — on SQLite/libSQL the freed pages are reused by future writes so the file stops growing, but handing disk back to the OS (for example a `VACUUM`) is left to the underlying database and the operator to manage.
+`prune()` deletes rows. It caps growth and is safe to run against large tables (batched, bounded, resumable, cancellable). It never reclaims disk: on SQLite/libSQL the freed pages are reused by future writes so the file stops growing, but handing disk back to the OS (for example a `VACUUM`) is left to the underlying database and the operator to manage.
 
-Retention covers **growth tables** only — tables that accumulate rows unbounded as a side effect of normal operation (conversation history, telemetry, job and run records, schedule fire history, event feeds). User-authored artifacts and config (agents, skills, workspaces, prompt blocks, datasets, schedule definitions, channel installations, and so on) grow with user intent and are edited or deleted explicitly, so they're not valid retention keys.
+Retention covers **growth tables** only: tables that accumulate rows unbounded as a side effect of normal operation (conversation history, telemetry, job and run records, schedule fire history, event feeds). User-authored artifacts and config (agents, skills, workspaces, prompt blocks, datasets, schedule definitions, channel installations, and so on) grow with user intent and are edited or deleted explicitly, so they're not valid retention keys.
 
 The reference implementations are [libSQL](https://mastra.ai/reference/storage/libsql), [PostgreSQL](https://mastra.ai/reference/storage/postgresql), and [MongoDB](https://mastra.ai/reference/storage/mongodb). Other adapters keep rows forever until they implement retention.
 
@@ -31,7 +31,7 @@ const storage = new LibSQLStore({
   },
 })
 
-// Wire this to your own cron/scheduler — Mastra never runs it for you.
+// Wire this to your own cron/scheduler: Mastra never runs it for you.
 const results = await storage.prune()
 ```
 
@@ -65,35 +65,35 @@ Set the `retention` field on the store config.
 
 ### Retention-eligible tables
 
-Each domain declares which of its tables can be age-pruned and which timestamp column anchors the comparison. The anchor is chosen so `maxAge` means what you'd expect for that data: creation time for append-only logs, last activity for live state, and completion time for jobs and runs (so in-flight work is never pruned).
-
-| Domain            | Table key          | Anchor column    | `maxAge` measures                                                 |
-| ----------------- | ------------------ | ---------------- | ----------------------------------------------------------------- |
-| `memory`          | `threads`          | `createdAt`      | Thread age                                                        |
-| `memory`          | `messages`         | `createdAt`      | Message age                                                       |
-| `memory`          | `resources`        | `createdAt`      | Resource age                                                      |
-| `threadState`     | `threadState`      | `updatedAt`      | Inactivity — state for still-active threads survives              |
-| `observability`   | `spans`            | `startedAt`      | Span age                                                          |
-| `observability`   | `metrics`          | `timestamp`      | Metric event age (v-next only)                                    |
-| `observability`   | `logs`             | `timestamp`      | Log event age (v-next only)                                       |
-| `observability`   | `scores`           | `timestamp`      | Score event age (v-next only)                                     |
-| `observability`   | `feedback`         | `timestamp`      | Feedback event age (v-next only)                                  |
-| `scores`          | `scorers`          | `createdAt`      | Score record age                                                  |
-| `workflows`       | `workflowSnapshot` | `updatedAt`      | Inactivity — suspended or long-running workflows survive          |
-| `backgroundTasks` | `backgroundTasks`  | `completedAt`    | Time since completion — in-flight tasks (`NULL`) are never pruned |
-| `experiments`     | `experiments`      | `completedAt`    | Time since completion — running experiments are never pruned      |
-| `notifications`   | `notifications`    | `createdAt`      | Notification age                                                  |
-| `harness`         | `sessions`         | `createdAt`      | Session record age                                                |
-| `schedules`       | `triggers`         | `actual_fire_at` | Fire-history age (epoch-ms column)                                |
+Each domain declares which of its tables can be age-pruned and which timestamp column anchors the comparison. The anchor is chosen so `maxAge` means what you'd expect for that data. Append-only logs use creation time, and live state uses last activity. Jobs and runs use completion time, so in-flight work is never pruned.
+
+| Domain            | Table key          | Anchor column    | `maxAge` measures                                                |
+| ----------------- | ------------------ | ---------------- | ---------------------------------------------------------------- |
+| `memory`          | `threads`          | `createdAt`      | Thread age                                                       |
+| `memory`          | `messages`         | `createdAt`      | Message age                                                      |
+| `memory`          | `resources`        | `createdAt`      | Resource age                                                     |
+| `threadState`     | `threadState`      | `updatedAt`      | Inactivity: state for still-active threads survives              |
+| `observability`   | `spans`            | `startedAt`      | Span age                                                         |
+| `observability`   | `metrics`          | `timestamp`      | Metric event age (v-next only)                                   |
+| `observability`   | `logs`             | `timestamp`      | Log event age (v-next only)                                      |
+| `observability`   | `scores`           | `timestamp`      | Score event age (v-next only)                                    |
+| `observability`   | `feedback`         | `timestamp`      | Feedback event age (v-next only)                                 |
+| `scores`          | `scorers`          | `createdAt`      | Score record age                                                 |
+| `workflows`       | `workflowSnapshot` | `updatedAt`      | Inactivity, suspended or long-running workflows survive          |
+| `backgroundTasks` | `backgroundTasks`  | `completedAt`    | Time since completion, in-flight tasks (`NULL`) are never pruned |
+| `experiments`     | `experiments`      | `completedAt`    | Time since completion, running experiments are never pruned      |
+| `notifications`   | `notifications`    | `createdAt`      | Notification age                                                 |
+| `harness`         | `sessions`         | `createdAt`      | Session record age                                               |
+| `schedules`       | `triggers`         | `actual_fire_at` | Fire-history age (epoch-ms column)                               |
 
 > **Note:**
 >
 > - The memory `observational_memory` table has no timestamp anchor, so it can't be age-pruned and isn't a valid retention key.
 > - Experiments prune as whole units: an aged experiment's result rows are deleted together with it (results cascade with their parent), so a run is never left partially deleted. Retention doesn't have a separate `results` key.
-> - For `schedules`, the growth table is the fire history (`schedule_triggers`, one row per fire) — schedule definitions are config and aren't pruned.
+> - For `schedules`, the growth table is the fire history (`schedule_triggers`, one row per fire): schedule definitions are config and aren't pruned.
 > - On PostgreSQL, timestamp anchors use the timezone-aware mirror columns (for example `createdAtZ`, `completedAtZ`).
 > - LibSQL supports all domains above; PostgreSQL and MongoDB support all except `threadState` and `harness`, which they don't implement.
-> - The v-next PostgreSQL observability domain stores signal events in day-partitioned tables (`spans`, `metrics`, `logs`, `scores`, `feedback`). For it, `prune()` drops whole day partitions (or TimescaleDB chunks) that are entirely older than the cutoff instead of deleting rows — effective granularity is one day, and a partition is only dropped once its entire day is past `maxAge`. `PruneResult.deleted` reports the number of rows in the dropped partitions.
+> - The v-next PostgreSQL observability domain stores signal events in day-partitioned tables (`spans`, `metrics`, `logs`, `scores`, `feedback`). For it, `prune()` drops whole day partitions (or TimescaleDB chunks) that are entirely older than the cutoff instead of deleting rows: effective level of detail is one day, and a partition is only dropped once its entire day is past `maxAge`. `PruneResult.deleted` reports the number of rows in the dropped partitions.
 
 ## Methods
 
@@ -103,11 +103,11 @@ Each domain declares which of its tables can be age-pruned and which timestamp c
 
 Deletes rows older than their configured `maxAge` across every domain that has a policy in `retention`. Returns one `PruneResult` per table touched. With no `retention` configured it's a no-op returning `[]`.
 
-`prune()` is designed to be safe on tables with millions of rows. It deletes in bounded, batched chunks — each batch is its own transaction — so it never takes a long lock or bloats the transaction log. It never runs a `VACUUM`.
+`prune()` is designed to be safe on tables with millions of rows. It deletes in bounded, batched chunks (each batch is its own transaction) so it never takes a long lock or bloats the transaction log. It never runs a `VACUUM`.
 
-Pass `options.retention` to replace the configured policies for that call only — for example to skip a domain (keep chat history) or prune more aggressively than the standing config. The store's configured `retention` is unchanged.
+Pass `options.retention` to replace the configured policies for that call only: for example to skip a domain (keep chat history) or prune more aggressively than the standing config. The store's configured `retention` is unchanged.
 
-Anchor-column indexes are created lazily on the first `prune()` call for each table with a policy — never at `init()` — so deployments that don't configure retention pay no extra index write or disk overhead. The first prune of an existing large table pays a one-time index build; subsequent prunes reuse the index.
+Anchor-column indexes are created lazily on the first `prune()` call for each table with a policy (never at `init()`) so deployments that don't configure retention pay no extra index write or disk overhead. The first prune of an existing large table pays a one-time index build. Subsequent prunes reuse the index.
 
 ```typescript
 const results = await storage.prune({
@@ -156,7 +156,7 @@ interface PruneResult {
 
 ## Running prune on a schedule
 
-`prune()` has no built-in scheduler — you decide when it runs. Because it's bounded, a single call may not delete everything. When any result has `done: false`, eligible rows remain and you call again on the next tick. This keeps each invocation short and lets a large backlog drain over several runs.
+`prune()` has no built-in scheduler: you decide when it runs. Because it's bounded, a single call may not delete everything. When any result has `done: false`, eligible rows remain and you call again on the next tick. This keeps each invocation short and lets a large backlog drain over several runs.
 
 ```typescript
 // Runs on your own cron (node-cron, a workflow schedule, an external job, etc.).
@@ -173,7 +173,7 @@ async function retentionTick() {
 }
 ```
 
-You can also cancel a long-running prune with an `AbortSignal` — the loop stops between batches and returns partial results with `done: false`, so the next run resumes cleanly.
+You can also cancel a long-running prune with an `AbortSignal`: the loop stops between batches and returns partial results with `done: false`, so the next run resumes cleanly.
 
 ## MongoDB TTL indexes (alternative to prune)
 
@@ -192,7 +192,7 @@ MongoDB offers native [TTL (Time-To-Live) indexes](https://www.mongodb.com/docs/
 > - You need resumable, cancellable cleanup operations
 > - You're using composite storage with multiple databases
 >
-> Both approaches are valid. TTL is simpler; `prune()` gives more control.
+> Both approaches are valid. TTL is simpler. `prune()` gives more control.
 
 ### Setting up TTL indexes on MongoDB
 
@@ -232,9 +232,9 @@ const storage = new MongoDBStore({
 
 ## Reclaiming disk
 
-`prune()` deletes rows but doesn't shrink the database file. On SQLite/libSQL the freed pages go on a freelist and are reused by future writes, so the file stops growing — for most users this alone solves the unbounded-growth problem.
+`prune()` deletes rows but doesn't shrink the database file. On SQLite/libSQL the freed pages go on a freelist and are reused by future writes, so the file stops growing: for most users this alone solves the unbounded-growth problem.
 
-Handing that free space back to the OS is a separate concern that Mastra doesn't manage. If you specifically need to shrink the file, run the underlying database's compaction (for example `VACUUM` on self-hosted libSQL) yourself, in a maintenance window — a full `VACUUM` locks the file and needs roughly twice the file size in free disk. On PostgreSQL, autovacuum reclaims dead tuples for reuse automatically; a manual `VACUUM FULL` is only needed if you must return disk to the OS.
+Handing that free space back to the OS is a separate concern that Mastra doesn't manage. If you specifically need to shrink the file, run the underlying database's compaction (for example `VACUUM` on self-hosted libSQL) yourself in a maintenance window. A full `VACUUM` locks the file and needs roughly twice the file size in free disk. On PostgreSQL, autovacuum reclaims dead tuples for reuse automatically; a manual `VACUUM FULL` is only needed if you must return disk to the OS.
 
 For MongoDB, deleted documents are reused by future insertions. To reclaim disk space, run [`db.runCommand({ compact: "collection_name" })`](https://www.mongodb.com/docs/manual/reference/command/compact/) during a maintenance window.
 

package/dist/docs/references/reference-vectors-libsql.md

@@ -85,7 +85,7 @@ const results = await store.query({
 
 ### `createIndex()`
 
-Creates a new vector collection. The index name must start with a letter or underscore and can only contain letters, numbers, and underscores. The dimension must be a positive integer.
+Creates a new vector collection. The index name must start with a letter or underscore and can only contain letters, numbers, and underscore characters. The dimension must be a positive integer.
 
 **indexName** (`string`): Name of the index to create
 
@@ -279,7 +279,7 @@ export const libsqlAgent = new Agent({
   name: 'libSQL Agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new LibSQLStore({
       id: 'libsql-agent-storage',

package/dist/index.cjs

@@ -3468,6 +3468,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 		await this.#addColumnIfNotExists(_mastra_core_storage.TABLE_DATASET_ITEMS, "organizationId", "TEXT");
 		await this.#addColumnIfNotExists(_mastra_core_storage.TABLE_DATASET_ITEMS, "projectId", "TEXT");
 		await this.#addColumnIfNotExists(_mastra_core_storage.TABLE_DATASET_ITEMS, "toolMocks", "TEXT");
+		await this.#addColumnIfNotExists(_mastra_core_storage.TABLE_DATASET_ITEMS, "unmockedToolPolicy", "TEXT");
 		await this.#addColumnIfNotExists(_mastra_core_storage.TABLE_DATASET_ITEMS, "externalId", "TEXT");
 		await this.#client.batch([
 			{
@@ -3564,6 +3565,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 			groundTruth: row.groundTruth ? (0, _mastra_core_storage.safelyParseJSON)(row.groundTruth) : void 0,
 			expectedTrajectory: row.expectedTrajectory ? (0, _mastra_core_storage.safelyParseJSON)(row.expectedTrajectory) : void 0,
 			toolMocks: row.toolMocks ? (0, _mastra_core_storage.safelyParseJSON)(row.toolMocks) : void 0,
+			unmockedToolPolicy: row.unmockedToolPolicy ?? void 0,
 			requestContext: row.requestContext ? (0, _mastra_core_storage.safelyParseJSON)(row.requestContext) : void 0,
 			metadata: row.metadata ? (0, _mastra_core_storage.safelyParseJSON)(row.metadata) : void 0,
 			source: row.source ? (0, _mastra_core_storage.safelyParseJSON)(row.source) : void 0,
@@ -3585,6 +3587,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 			groundTruth: row.groundTruth ? (0, _mastra_core_storage.safelyParseJSON)(row.groundTruth) : void 0,
 			expectedTrajectory: row.expectedTrajectory ? (0, _mastra_core_storage.safelyParseJSON)(row.expectedTrajectory) : void 0,
 			toolMocks: row.toolMocks ? (0, _mastra_core_storage.safelyParseJSON)(row.toolMocks) : void 0,
+			unmockedToolPolicy: row.unmockedToolPolicy ?? void 0,
 			requestContext: row.requestContext ? (0, _mastra_core_storage.safelyParseJSON)(row.requestContext) : void 0,
 			metadata: row.metadata ? (0, _mastra_core_storage.safelyParseJSON)(row.metadata) : void 0,
 			source: row.source ? (0, _mastra_core_storage.safelyParseJSON)(row.source) : void 0,
@@ -3898,7 +3901,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 					args: [args.datasetId]
 				},
 				{
-					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, (SELECT organizationId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), (SELECT projectId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), NULL, 0, jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
+					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, unmockedToolPolicy, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, (SELECT organizationId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), (SELECT projectId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), NULL, 0, jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
 					args: [
 						id,
 						args.datasetId,
@@ -3910,6 +3913,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 						jsonbArg(args.groundTruth),
 						jsonbArg(args.expectedTrajectory),
 						jsonbArg(args.toolMocks),
+						args.unmockedToolPolicy ?? null,
 						jsonbArg(args.requestContext),
 						jsonbArg(args.metadata),
 						jsonbArg(args.source),
@@ -3939,6 +3943,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 				groundTruth: args.groundTruth,
 				expectedTrajectory: args.expectedTrajectory,
 				toolMocks: args.toolMocks,
+				unmockedToolPolicy: args.unmockedToolPolicy,
 				requestContext: args.requestContext,
 				metadata: args.metadata,
 				source: args.source,
@@ -3981,6 +3986,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 			const mergedGroundTruth = args.groundTruth !== void 0 ? args.groundTruth : existing.groundTruth;
 			const mergedExpectedTrajectory = args.expectedTrajectory !== void 0 ? args.expectedTrajectory : existing.expectedTrajectory;
 			const mergedToolMocks = args.toolMocks !== void 0 ? args.toolMocks : existing.toolMocks;
+			const mergedUnmockedToolPolicy = args.unmockedToolPolicy !== void 0 ? args.unmockedToolPolicy : existing.unmockedToolPolicy;
 			const mergedRequestContext = args.requestContext !== void 0 ? args.requestContext : existing.requestContext;
 			const mergedMetadata = args.metadata !== void 0 ? args.metadata : existing.metadata;
 			const mergedSource = args.source !== void 0 ? args.source : existing.source;
@@ -3994,7 +4000,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 					args: [args.datasetId, args.id]
 				},
 				{
-					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, (SELECT organizationId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), (SELECT projectId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), NULL, 0, jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
+					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, unmockedToolPolicy, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, (SELECT organizationId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), (SELECT projectId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), NULL, 0, jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
 					args: [
 						args.id,
 						args.datasetId,
@@ -4006,6 +4012,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 						jsonbArg(mergedGroundTruth),
 						jsonbArg(mergedExpectedTrajectory),
 						jsonbArg(mergedToolMocks),
+						mergedUnmockedToolPolicy ?? null,
 						jsonbArg(mergedRequestContext),
 						jsonbArg(mergedMetadata),
 						jsonbArg(mergedSource),
@@ -4033,6 +4040,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 				groundTruth: mergedGroundTruth,
 				expectedTrajectory: mergedExpectedTrajectory,
 				toolMocks: mergedToolMocks,
+				unmockedToolPolicy: mergedUnmockedToolPolicy,
 				requestContext: mergedRequestContext,
 				metadata: mergedMetadata,
 				source: mergedSource,
@@ -4073,7 +4081,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 					args: [datasetId, id]
 				},
 				{
-					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, (SELECT organizationId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), (SELECT projectId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), NULL, 1, jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
+					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, unmockedToolPolicy, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, (SELECT organizationId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), (SELECT projectId FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), NULL, 1, jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
 					args: [
 						id,
 						datasetId,
@@ -4085,6 +4093,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 						jsonbArg(existing.groundTruth),
 						jsonbArg(existing.expectedTrajectory),
 						jsonbArg(existing.toolMocks),
+						existing.unmockedToolPolicy ?? null,
 						jsonbArg(existing.requestContext),
 						jsonbArg(existing.metadata),
 						jsonbArg(existing.source),
@@ -4380,7 +4389,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 					});
 					const externalIds = [...new Set(input.items.flatMap((item) => item.externalId ? [item.externalId] : []))];
 					const historyResult = externalIds.length ? await tx.execute({
-						sql: `SELECT id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, json(input) AS input, json(groundTruth) AS groundTruth, json(expectedTrajectory) AS expectedTrajectory, json(toolMocks) AS toolMocks, json(requestContext) AS requestContext, json(metadata) AS metadata, json(source) AS source, createdAt, updatedAt FROM ${_mastra_core_storage.TABLE_DATASET_ITEMS} WHERE datasetId = ? AND externalId IN (${externalIds.map(() => "?").join(",")}) ORDER BY datasetVersion`,
+						sql: `SELECT id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, json(input) AS input, json(groundTruth) AS groundTruth, json(expectedTrajectory) AS expectedTrajectory, json(toolMocks) AS toolMocks, unmockedToolPolicy, json(requestContext) AS requestContext, json(metadata) AS metadata, json(source) AS source, createdAt, updatedAt FROM ${_mastra_core_storage.TABLE_DATASET_ITEMS} WHERE datasetId = ? AND externalId IN (${externalIds.map(() => "?").join(",")}) ORDER BY datasetVersion`,
 						args: [input.datasetId, ...externalIds]
 					}) : { rows: [] };
 					const plan = this.planDatasetItemBatch(input.items, historyResult.rows.map((row) => this.transformItemRowFull(row)), () => crypto.randomUUID());
@@ -4395,7 +4404,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 						});
 						for (const { id, item } of plan.inserts) {
 							await tx.execute({
-								sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, ?, ?, ?, ?, NULL, 0, jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
+								sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, unmockedToolPolicy, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, ?, ?, ?, ?, NULL, 0, jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
 								args: [
 									id,
 									input.datasetId,
@@ -4407,6 +4416,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 									jsonbArg(item.groundTruth),
 									jsonbArg(item.expectedTrajectory),
 									jsonbArg(item.toolMocks),
+									item.unmockedToolPolicy ?? null,
 									jsonbArg(item.requestContext),
 									jsonbArg(item.metadata),
 									jsonbArg(item.source),
@@ -4425,6 +4435,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 								groundTruth: item.groundTruth,
 								expectedTrajectory: item.expectedTrajectory,
 								toolMocks: item.toolMocks,
+								unmockedToolPolicy: item.unmockedToolPolicy,
 								requestContext: item.requestContext,
 								metadata: item.metadata,
 								source: item.source,
@@ -4485,7 +4496,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 					args: [input.datasetId, item.id]
 				});
 				statements.push({
-					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, ?, ?, NULL, 1, jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
+					sql: `INSERT INTO ${_mastra_core_storage.TABLE_DATASET_ITEMS} (id, datasetId, datasetVersion, externalId, organizationId, projectId, validTo, isDeleted, input, groundTruth, expectedTrajectory, toolMocks, unmockedToolPolicy, requestContext, metadata, source, createdAt, updatedAt) VALUES (?, ?, (SELECT version FROM ${_mastra_core_storage.TABLE_DATASETS} WHERE id = ?), ?, ?, ?, NULL, 1, jsonb(?), jsonb(?), jsonb(?), jsonb(?), ?, jsonb(?), jsonb(?), jsonb(?), ?, ?)`,
 					args: [
 						item.id,
 						input.datasetId,
@@ -4497,6 +4508,7 @@ var DatasetsLibSQL = class extends _mastra_core_storage.DatasetsStorage {
 						jsonbArg(item.groundTruth),
 						jsonbArg(item.expectedTrajectory),
 						jsonbArg(item.toolMocks),
+						item.unmockedToolPolicy ?? null,
 						jsonbArg(item.requestContext),
 						jsonbArg(item.metadata),
 						jsonbArg(item.source),
@@ -4577,6 +4589,7 @@ var ExperimentsLibSQL = class extends _mastra_core_storage.ExperimentsStorage {
 			ifNotExists: [
 				"status",
 				"tags",
+				"comment",
 				"toolMockReport",
 				"organizationId",
 				"projectId"
@@ -4715,6 +4728,7 @@ var ExperimentsLibSQL = class extends _mastra_core_storage.ExperimentsStorage {
 			traceId: row.traceId ?? null,
 			status: row.status ?? null,
 			tags: row.tags ? (0, _mastra_core_storage.safelyParseJSON)(row.tags) : null,
+			comment: row.comment ?? null,
 			toolMockReport: row.toolMockReport ? (0, _mastra_core_storage.safelyParseJSON)(row.toolMockReport) : null,
 			createdAt: (0, _mastra_core_storage.ensureDate)(row.createdAt)
 		};
@@ -5029,6 +5043,10 @@ var ExperimentsLibSQL = class extends _mastra_core_storage.ExperimentsStorage {
 				setClauses.push(`"tags" = ?`);
 				values.push(JSON.stringify(input.tags));
 			}
+			if (input.comment !== void 0) {
+				setClauses.push(`"comment" = ?`);
+				values.push(input.comment);
+			}
 			if (setClauses.length === 0) {
 				const existing = await this.getExperimentResultById({ id: input.id });
 				if (!existing) throw new _mastra_core_error.MastraError({