@mastra/core 1.28.0-alpha.2 → 1.29.0-alpha.0

package/CHANGELOG.md

@@ -1,5 +1,104 @@
 # @mastra/core
 
+## 1.29.0-alpha.0
+
+### Patch Changes
+
+- Update provider registry and model documentation with latest models and providers ([`b510d36`](https://github.com/mastra-ai/mastra/commit/b510d368f73dab6be2e2c2bc99035aaef1fb7d7a))
+
+## 1.28.0
+
+### Minor Changes
+
+- The Workspace `filesystem` option now accepts a resolver function in addition to a static instance. ([#13150](https://github.com/mastra-ai/mastra/pull/13150))
+
+  **Before:** `filesystem: WorkspaceFilesystem` (static, same filesystem for every request)
+  **After:** `filesystem: WorkspaceFilesystem | (({ requestContext }) => WorkspaceFilesystem)` (static or per-request)
+
+  This enables per-request filesystem routing from a single Workspace — useful for multi-tenant setups, role-based access (e.g. admin vs user directories), and scoped filesystem permissions without creating separate Workspace instances.
+
+- Added support for custom language server registration with the `servers` field in `LSPConfig`. Previously, LSP inspection only worked with built-in server definitions for TypeScript, JavaScript, Python, Go, and Rust. You can now register additional language servers, such as PHP, Ruby, Java, Kotlin, Swift, or Elixir, by providing a `CustomLSPServer` definition. ([#14969](https://github.com/mastra-ai/mastra/pull/14969))
+
+  **Example:**
+
+  ```typescript
+  const workspace = new Workspace({
+    lsp: {
+      servers: {
+        phpactor: {
+          id: 'phpactor',
+          name: 'Phpactor Language Server',
+          languageIds: ['php'],
+          extensions: ['.php'],
+          markers: ['composer.json'],
+          command: 'phpactor language-server',
+        },
+      },
+    },
+  });
+  ```
+
+  Custom servers are merged with built-in servers and can also override them by using the same ID. Closes #14828.
+
+### Patch Changes
+
+- Update provider registry and model documentation with latest models and providers ([`733bf53`](https://github.com/mastra-ai/mastra/commit/733bf53d9352aedd3ef38c3d501edb275b65b43c))
+
+- Fixed output processors returning `undefined` from `processOutputStream` causing an `undefined` chunk to be enqueued into the consumer stream. A processor that forgets to `return part` (or explicitly returns `undefined`) now drops that chunk, matching existing `null` behavior, instead of emitting a bogus value to downstream readers. ([#15674](https://github.com/mastra-ai/mastra/pull/15674))
+
+  ```ts
+  // Before: returning undefined emitted { value: undefined, done: false } to consumers
+  // After:  returning undefined drops the chunk, same as returning null
+  const processor = {
+    id: 'my-processor',
+    processOutputStream: async ({ part }) => {
+      if (shouldDrop(part)) return; // implicit undefined — now safely dropped
+      return part;
+    },
+  };
+  ```
+
+- Fixed streamed tool results being replayed when observational memory runs mid-stream. ([#15701](https://github.com/mastra-ai/mastra/pull/15701))
+  Fixed observational memory markers being saved as separate empty assistant messages.
+
+- Fixed false positive provider change detection in observational memory. Message metadata now uses the configured model ID instead of the API response model ID, ensuring consistency with step-start parts and preventing incorrect 'Model changed' activations when the provider returns versioned model names (e.g., gpt-5.4-2026-03-05 vs gpt-5.4). ([#15681](https://github.com/mastra-ai/mastra/pull/15681))
+
+- Fixed interaction between savePerStep and observational memory that caused message duplication. The saveStepMessages method redundantly re-added response messages to the message list on every step, duplicating them. Additionally, savePerStep is now force-disabled when observational memory is enabled, since OM handles its own per-step persistence and the two features conflict. ([#15684](https://github.com/mastra-ai/mastra/pull/15684))
+
+- Fixed rotated response message ids not propagating to the active output stream after error processor retries, which could split a single response across two ids on the API-error retry path. ([#15702](https://github.com/mastra-ai/mastra/pull/15702))
+
+  Fixed processor-supplied options to `writer.custom` being dropped in the agentic execution step, so future options like `transient` now reach the underlying output writer.
+
+- Fixed `agent.stream()` callbacks so that `onStepFinish` and `onFinish` now preserve the provider-level `usage.raw` object on `LanguageModelUsage`. This lets consumers inspect provider-specific cache metrics (e.g., Anthropic and Bedrock prompt caching) directly from the callback payload without having to wrap the stream. ([#15546](https://github.com/mastra-ai/mastra/pull/15546))
+
+  Closes #15510.
+
+- Add opt-in `checkSkillFileMtime` option to detect in-place SKILL.md edits during hot reload. ([#15676](https://github.com/mastra-ai/mastra/pull/15676))
+
+  Previously, only directory mtime was checked for skill staleness, so editing a skill's name (to fix a validation error) or updating its description wouldn't trigger re-discovery until server restart.
+
+  The option is off by default since it doubles `stat()` calls per skill during staleness checks. Recommended for local development only, not for cloud storage backends where `stat()` has higher latency.
+
+  ```ts
+  const myAgent = new Agent({
+    workspace: {
+      filesystem: new LocalFilesystem({ basePath: process.cwd() }),
+      skills: ['./**/skills'],
+      checkSkillFileMtime: true, // Enable for local dev
+    },
+  });
+  ```
+
+- Added `filterIncompleteToolCalls` option to memory config. When set to `false`, suspended tool calls remain visible in the agent's prompt context, allowing the agent to see its own pending interactions in thread history. Defaults to `true` (current behavior). Useful for suspend/resume patterns with providers that support incomplete tool calls (e.g. Anthropic). ([#14721](https://github.com/mastra-ai/mastra/pull/14721))
+
+- Fixed workspace file indexing so vector search works out of the box. ([#15011](https://github.com/mastra-ai/mastra/pull/15011))
+  - Large files that exceeded the embedding model token limit were previously silently skipped, leaving the vector store empty and causing search failures. Large files are now split into overlapping line-based chunks, each indexed separately with correct line-range tracking back to the original file.
+  - The vector index is now created automatically before the first upsert. Previously, backends that require an explicit `createIndex` call (e.g. LibSQL) would leave the table uncreated, causing `no such table` errors on search. Workspaces with `vectorStore` + `embedder` + `autoIndexPaths` configured now work without any manual setup.
+
+- Disable `savePerStep` in Harness to prevent duplicate messages when observational memory is enabled ([#15684](https://github.com/mastra-ai/mastra/pull/15684))
+
+  The `savePerStep` option in Harness caused message duplication when used alongside observational memory. This change temporarily disables `savePerStep` in the Harness runtime while we work on a permanent fix.
+
 ## 1.28.0-alpha.2
 
 ### Minor Changes

package/dist/agent/index.cjs

@@ -1,37 +1,37 @@
 'use strict';
 
-var chunkDMW3LDAI_cjs = require('../chunk-DMW3LDAI.cjs');
+var chunk6ETCJK3W_cjs = require('../chunk-6ETCJK3W.cjs');
 var chunkSRAWH6R4_cjs = require('../chunk-SRAWH6R4.cjs');
 
 
 
 Object.defineProperty(exports, "Agent", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.Agent; }
+  get: function () { return chunk6ETCJK3W_cjs.Agent; }
 });
 Object.defineProperty(exports, "TripWire", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.TripWire; }
+  get: function () { return chunk6ETCJK3W_cjs.TripWire; }
 });
 Object.defineProperty(exports, "isSupportedLanguageModel", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.isSupportedLanguageModel; }
+  get: function () { return chunk6ETCJK3W_cjs.isSupportedLanguageModel; }
 });
 Object.defineProperty(exports, "resolveThreadIdFromArgs", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.resolveThreadIdFromArgs; }
+  get: function () { return chunk6ETCJK3W_cjs.resolveThreadIdFromArgs; }
 });
 Object.defineProperty(exports, "supportedLanguageModelSpecifications", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.supportedLanguageModelSpecifications; }
+  get: function () { return chunk6ETCJK3W_cjs.supportedLanguageModelSpecifications; }
 });
 Object.defineProperty(exports, "tryGenerateWithJsonFallback", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.tryGenerateWithJsonFallback; }
+  get: function () { return chunk6ETCJK3W_cjs.tryGenerateWithJsonFallback; }
 });
 Object.defineProperty(exports, "tryStreamWithJsonFallback", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.tryStreamWithJsonFallback; }
+  get: function () { return chunk6ETCJK3W_cjs.tryStreamWithJsonFallback; }
 });
 Object.defineProperty(exports, "MessageList", {
   enumerable: true,

package/dist/agent/index.js

@@ -1,4 +1,4 @@
-export { Agent, TripWire, isSupportedLanguageModel, resolveThreadIdFromArgs, supportedLanguageModelSpecifications, tryGenerateWithJsonFallback, tryStreamWithJsonFallback } from '../chunk-Y5NA6WRH.js';
+export { Agent, TripWire, isSupportedLanguageModel, resolveThreadIdFromArgs, supportedLanguageModelSpecifications, tryGenerateWithJsonFallback, tryStreamWithJsonFallback } from '../chunk-FRRSKGPV.js';
 export { MessageList, TypeDetector, aiV5ModelMessageToV2PromptMessage, convertMessages } from '../chunk-DLUNYVZY.js';
 //# sourceMappingURL=index.js.map
 //# sourceMappingURL=index.js.map

package/dist/browser/index.cjs

@@ -1,6 +1,6 @@
 'use strict';
 
-var chunkDMW3LDAI_cjs = require('../chunk-DMW3LDAI.cjs');
+var chunk6ETCJK3W_cjs = require('../chunk-6ETCJK3W.cjs');
 var chunk6PAHGAKC_cjs = require('../chunk-6PAHGAKC.cjs');
 var chunkFCQNDFEW_cjs = require('../chunk-FCQNDFEW.cjs');
 var chunk7GW2TQXP_cjs = require('../chunk-7GW2TQXP.cjs');
@@ -1191,7 +1191,7 @@ To fix this, either:
    */
   getInputProcessors(configuredProcessors = []) {
     const hasProcessor = configuredProcessors.some(
-      (p) => !chunkDMW3LDAI_cjs.isProcessorWorkflow(p) && "id" in p && p.id === "browser-context"
+      (p) => !chunk6ETCJK3W_cjs.isProcessorWorkflow(p) && "id" in p && p.id === "browser-context"
     );
     if (hasProcessor) return [];
     return [new BrowserContextProcessor()];

package/dist/browser/index.js

@@ -1,4 +1,4 @@
-import { isProcessorWorkflow } from '../chunk-Y5NA6WRH.js';
+import { isProcessorWorkflow } from '../chunk-FRRSKGPV.js';
 export { BrowserCliHandler, browserCliHandler } from '../chunk-VWQ2LYM3.js';
 import { MastraBase } from '../chunk-WENZPAHS.js';
 import { RegisteredLogger } from '../chunk-DBBWTK24.js';

package/dist/channels/index.cjs

@@ -1,20 +1,20 @@
 'use strict';
 
-var chunkDMW3LDAI_cjs = require('../chunk-DMW3LDAI.cjs');
+var chunk6ETCJK3W_cjs = require('../chunk-6ETCJK3W.cjs');
 
 
 
 Object.defineProperty(exports, "AgentChannels", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.AgentChannels; }
+  get: function () { return chunk6ETCJK3W_cjs.AgentChannels; }
 });
 Object.defineProperty(exports, "ChatChannelProcessor", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.ChatChannelProcessor; }
+  get: function () { return chunk6ETCJK3W_cjs.ChatChannelProcessor; }
 });
 Object.defineProperty(exports, "MastraStateAdapter", {
   enumerable: true,
-  get: function () { return chunkDMW3LDAI_cjs.MastraStateAdapter; }
+  get: function () { return chunk6ETCJK3W_cjs.MastraStateAdapter; }
 });
 //# sourceMappingURL=index.cjs.map
 //# sourceMappingURL=index.cjs.map

package/dist/channels/index.js

@@ -1,3 +1,3 @@
-export { AgentChannels, ChatChannelProcessor, MastraStateAdapter } from '../chunk-Y5NA6WRH.js';
+export { AgentChannels, ChatChannelProcessor, MastraStateAdapter } from '../chunk-FRRSKGPV.js';
 //# sourceMappingURL=index.js.map
 //# sourceMappingURL=index.js.map

package/dist/{chunk-DBFA5FFU.js → chunk-2WNYRCWK.js}

@@ -1,5 +1,5 @@
-import { validateAndSaveScore } from './chunk-3SZVQUBS.js';
-import { isSupportedLanguageModel } from './chunk-Y5NA6WRH.js';
+import { validateAndSaveScore } from './chunk-BZRB4HM2.js';
+import { isSupportedLanguageModel } from './chunk-FRRSKGPV.js';
 import { EntityType } from './chunk-2PBCTS3B.js';
 import { MastraError } from './chunk-FJEVLHJT.js';
 import { RequestContext } from './chunk-AJVVIFTH.js';
@@ -1393,5 +1393,5 @@ var DatasetsManager = class {
 };
 
 export { Dataset, DatasetsManager, compareExperiments, computeMean, computeScorerStats, executeTarget, isRegression, resolveScorers, runExperiment, runScorersForItem };
-//# sourceMappingURL=chunk-DBFA5FFU.js.map
-//# sourceMappingURL=chunk-DBFA5FFU.js.map
+//# sourceMappingURL=chunk-2WNYRCWK.js.map
+//# sourceMappingURL=chunk-2WNYRCWK.js.map