@mastra/editor 0.4.0-alpha.0 → 0.5.0-alpha.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,213 @@
1
1
  # @mastra/editor
2
2
 
3
+ ## 0.5.0-alpha.0
4
+
5
+ ### Minor Changes
6
+
7
+ - Added workspace and skill storage domains with full CRUD, versioning, and implementations across LibSQL, Postgres, and MongoDB. Added `editor.workspace` and `editor.skill` namespaces for managing workspace configurations and skill definitions through the editor. Agents stored in the editor can now reference workspaces (by ID or inline config) and skills, with full hydration to runtime `Workspace` instances during agent resolution. ([#13156](https://github.com/mastra-ai/mastra/pull/13156))
8
+
9
+ **Filesystem-native skill versioning (draft → publish model):**
10
+
11
+ Skills are versioned as filesystem trees with content-addressable blob storage. The editing surface (live filesystem) is separated from the serving surface (versioned blob store), enabling a `draft → publish` workflow:
12
+ - `editor.skill.publish(skillId, source, skillPath)` — Snapshots a skill directory from the filesystem into blob storage, creates a new version with a tree manifest, and sets `activeVersionId`
13
+ - Version switching via `editor.skill.update({ id, activeVersionId })` — Points the skill to a previous version without re-publishing
14
+ - Publishing a skill automatically invalidates cached agents that reference it, so they re-hydrate with the updated version on next access
15
+
16
+ **Agent skill resolution strategies:**
17
+
18
+ Agents can reference skills with different resolution strategies:
19
+ - `strategy: 'latest'` — Resolves the skill's active version (honors `activeVersionId` for rollback)
20
+ - `pin: '<versionId>'` — Pins to a specific version, immune to publishes
21
+ - `strategy: 'live'` — Reads directly from the live filesystem (no blob store)
22
+
23
+ **Blob storage infrastructure:**
24
+ - `BlobStore` abstract class for content-addressable storage keyed by SHA-256 hash
25
+ - `InMemoryBlobStore` for testing
26
+ - LibSQL, Postgres, and MongoDB implementations
27
+ - `S3BlobStore` for storing blobs in S3 or S3-compatible storage (AWS, R2, MinIO, DO Spaces)
28
+ - `BlobStoreProvider` interface and `MastraEditorConfig.blobStores` registry for pluggable blob storage
29
+ - `VersionedSkillSource` and `CompositeVersionedSkillSource` for reading skill files from the blob store at runtime
30
+
31
+ **New storage types:**
32
+ - `StorageWorkspaceSnapshotType` and `StorageSkillSnapshotType` with corresponding input/output types
33
+ - `StorageWorkspaceRef` for ID-based or inline workspace references on agents
34
+ - `StorageSkillConfig` for per-agent skill overrides (`pin`, `strategy`, description, instructions)
35
+ - `SkillVersionTree` and `SkillVersionTreeEntry` for tree manifests
36
+ - `StorageBlobEntry` for content-addressable blob entries
37
+ - `SKILL_BLOBS_SCHEMA` for the `mastra_skill_blobs` table
38
+
39
+ **New editor namespaces:**
40
+ - `editor.workspace` — CRUD for workspace configs, plus `hydrateSnapshotToWorkspace()` for resolving to runtime `Workspace` instances
41
+ - `editor.skill` — CRUD for skill definitions, plus `publish()` for filesystem-to-blob snapshots
42
+
43
+ **Provider registries:**
44
+ - `MastraEditorConfig` accepts `filesystems`, `sandboxes`, and `blobStores` provider registries (keyed by provider ID)
45
+ - Built-in `local` filesystem and sandbox providers are auto-registered
46
+ - `editor.resolveBlobStore()` resolves from provider registry or falls back to the storage backend's blobs domain
47
+ - Providers expose `id`, `name`, `description`, `configSchema` (JSON Schema for UI form rendering), and a factory method
48
+
49
+ **Storage adapter support:**
50
+ - LibSQL: Full `workspaces`, `skills`, and `blobs` domain implementations
51
+ - Postgres: Full `workspaces`, `skills`, and `blobs` domain implementations
52
+ - MongoDB: Full `workspaces`, `skills`, and `blobs` domain implementations
53
+ - All three include `workspace`, `skills`, and `skillsFormat` fields on agent versions
54
+
55
+ **Server endpoints:**
56
+ - `GET/POST/PATCH/DELETE /stored/workspaces` — CRUD for stored workspaces
57
+ - `GET/POST/PATCH/DELETE /stored/skills` — CRUD for stored skills
58
+ - `POST /stored/skills/:id/publish` — Publish a skill from a filesystem source
59
+
60
+ ```ts
61
+ import { MastraEditor } from '@mastra/editor';
62
+ import { s3FilesystemProvider, s3BlobStoreProvider } from '@mastra/s3';
63
+ import { e2bSandboxProvider } from '@mastra/e2b';
64
+
65
+ const editor = new MastraEditor({
66
+ filesystems: { s3: s3FilesystemProvider },
67
+ sandboxes: { e2b: e2bSandboxProvider },
68
+ blobStores: { s3: s3BlobStoreProvider },
69
+ });
70
+
71
+ // Create a skill and publish it
72
+ const skill = await editor.skill.create({
73
+ name: 'Code Review',
74
+ description: 'Reviews code for best practices',
75
+ instructions: 'Analyze the code and provide feedback...',
76
+ });
77
+ await editor.skill.publish(skill.id, source, 'skills/code-review');
78
+
79
+ // Agents resolve skills by strategy
80
+ await editor.agent.create({
81
+ name: 'Dev Assistant',
82
+ model: { provider: 'openai', name: 'gpt-4' },
83
+ workspace: { type: 'id', workspaceId: workspace.id },
84
+ skills: { [skill.id]: { strategy: 'latest' } },
85
+ skillsFormat: 'xml',
86
+ });
87
+ ```
88
+
89
+ ### Patch Changes
90
+
91
+ - Fixed conditional rules not being persisted for workflows, agents, and scorers when creating or updating agents in the CMS. Rules configured on these entities are now correctly saved to storage. ([#13044](https://github.com/mastra-ai/mastra/pull/13044))
92
+
93
+ - CMS draft support with status badges for agents. ([#13194](https://github.com/mastra-ai/mastra/pull/13194))
94
+ - Agent list now resolves the latest (draft) version for each stored agent, showing current edits rather than the last published state.
95
+ - Added `hasDraft` and `activeVersionId` fields to the agent list API response.
96
+ - Agent list badges: "Published" (green) when a published version exists, "Draft" (colored when unpublished changes exist, grayed out otherwise).
97
+ - Added `resolvedVersionId` to all `StorageResolved*Type` types so the server can detect whether the latest version differs from the active version.
98
+ - Added `status` option to `GetByIdOptions` to allow resolving draft vs published versions through the editor layer.
99
+ - Fixed editor cache not being cleared on version activate, restore, and delete — all four versioned domains (agents, scorers, prompt-blocks, mcp-clients) now clear the cache after version mutations.
100
+ - Added `ALTER TABLE` migration for `mastra_agent_versions` in libsql and pg to add newer columns (`mcpClients`, `requestContextSchema`, `workspace`, `skills`, `skillsFormat`).
101
+
102
+ - Updated dependencies [[`252580a`](https://github.com/mastra-ai/mastra/commit/252580a71feb0e46d0ccab04a70a79ff6a2ee0ab), [`f8e819f`](https://github.com/mastra-ai/mastra/commit/f8e819fabdfdc43d2da546a3ad81ba23685f603d), [`f8e819f`](https://github.com/mastra-ai/mastra/commit/f8e819fabdfdc43d2da546a3ad81ba23685f603d), [`5c75261`](https://github.com/mastra-ai/mastra/commit/5c7526120d936757d4ffb7b82232e1641ebd45cb), [`e27d832`](https://github.com/mastra-ai/mastra/commit/e27d83281b5e166fd63a13969689e928d8605944), [`e37ef84`](https://github.com/mastra-ai/mastra/commit/e37ef8404043c94ca0c8e35ecdedb093b8087878), [`6fdd3d4`](https://github.com/mastra-ai/mastra/commit/6fdd3d451a07a8e7e216c62ac364f8dd8e36c2af), [`10cf521`](https://github.com/mastra-ai/mastra/commit/10cf52183344743a0d7babe24cd24fd78870c354), [`6fdd3d4`](https://github.com/mastra-ai/mastra/commit/6fdd3d451a07a8e7e216c62ac364f8dd8e36c2af), [`efdb682`](https://github.com/mastra-ai/mastra/commit/efdb682887f6522149769383908f9790c188ab88), [`0dee7a0`](https://github.com/mastra-ai/mastra/commit/0dee7a0ff4c2507e6eb6e6ee5f9738877ebd4ad1), [`04c2c8e`](https://github.com/mastra-ai/mastra/commit/04c2c8e888984364194131aecb490a3d6e920e61), [`02dc07a`](https://github.com/mastra-ai/mastra/commit/02dc07acc4ad42d93335825e3308f5b42266eba2), [`8650e4d`](https://github.com/mastra-ai/mastra/commit/8650e4d3579a2c3a13e2dba7ec6ee7c82c7f61a8), [`bd222d3`](https://github.com/mastra-ai/mastra/commit/bd222d39e292bfcc4a2d9a9e6ec3976cc5a4f22f), [`bb7262b`](https://github.com/mastra-ai/mastra/commit/bb7262b7c0ca76320d985b40510b6ffbbb936582), [`cf1c6e7`](https://github.com/mastra-ai/mastra/commit/cf1c6e789b131f55638fed52183a89d5078b4876), [`5ffadfe`](https://github.com/mastra-ai/mastra/commit/5ffadfefb1468ac2612b20bb84d24c39de6961c0), [`1e1339c`](https://github.com/mastra-ai/mastra/commit/1e1339cc276e571a48cfff5014487877086bfe68), [`ffa5468`](https://github.com/mastra-ai/mastra/commit/ffa546857fc4821753979b3a34e13b4d76fbbcd4), [`d03df73`](https://github.com/mastra-ai/mastra/commit/d03df73f8fe9496064a33e1c3b74ba0479bf9ee6), [`79b8f45`](https://github.com/mastra-ai/mastra/commit/79b8f45a6767e1a5c3d56cd3c5b1214326b81661), [`9bbf08e`](https://github.com/mastra-ai/mastra/commit/9bbf08e3c20731c79dea13a765895b9fcf29cbf1), [`0a25952`](https://github.com/mastra-ai/mastra/commit/0a259526b5e1ac11e6efa53db1f140272962af2d), [`ffa5468`](https://github.com/mastra-ai/mastra/commit/ffa546857fc4821753979b3a34e13b4d76fbbcd4), [`3264a04`](https://github.com/mastra-ai/mastra/commit/3264a04e30340c3c5447433300a035ea0878df85), [`6fdd3d4`](https://github.com/mastra-ai/mastra/commit/6fdd3d451a07a8e7e216c62ac364f8dd8e36c2af), [`6fdd3d4`](https://github.com/mastra-ai/mastra/commit/6fdd3d451a07a8e7e216c62ac364f8dd8e36c2af), [`088d9ba`](https://github.com/mastra-ai/mastra/commit/088d9ba2577518703c52b0dccd617178d9ee6b0d), [`74fbebd`](https://github.com/mastra-ai/mastra/commit/74fbebd918a03832a2864965a8bea59bf617d3a2), [`74fbebd`](https://github.com/mastra-ai/mastra/commit/74fbebd918a03832a2864965a8bea59bf617d3a2), [`aea6217`](https://github.com/mastra-ai/mastra/commit/aea621790bfb2291431b08da0cc5e6e150303ae7), [`b6a855e`](https://github.com/mastra-ai/mastra/commit/b6a855edc056e088279075506442ba1d6fa6def9), [`ae408ea`](https://github.com/mastra-ai/mastra/commit/ae408ea7128f0d2710b78d8623185198e7cb19c1), [`17e942e`](https://github.com/mastra-ai/mastra/commit/17e942eee2ba44985b1f807e6208cdde672f82f9), [`2015cf9`](https://github.com/mastra-ai/mastra/commit/2015cf921649f44c3f5bcd32a2c052335f8e49b4), [`7ef454e`](https://github.com/mastra-ai/mastra/commit/7ef454eaf9dcec6de60021c8f42192052dd490d6), [`2be1d99`](https://github.com/mastra-ai/mastra/commit/2be1d99564ce79acc4846071082bff353035a87a), [`2708fa1`](https://github.com/mastra-ai/mastra/commit/2708fa1055ac91c03e08b598869f6b8fb51fa37f), [`ba74aef`](https://github.com/mastra-ai/mastra/commit/ba74aef5716142dbbe931351f5243c9c6e4128a9), [`ba74aef`](https://github.com/mastra-ai/mastra/commit/ba74aef5716142dbbe931351f5243c9c6e4128a9), [`ec53e89`](https://github.com/mastra-ai/mastra/commit/ec53e8939c76c638991e21af762e51378eff7543), [`9b5a8cb`](https://github.com/mastra-ai/mastra/commit/9b5a8cb13e120811b0bf14140ada314f1c067894), [`607e66b`](https://github.com/mastra-ai/mastra/commit/607e66b02dc7f531ee37799f3456aa2dc0ca7ac5), [`a215d06`](https://github.com/mastra-ai/mastra/commit/a215d06758dcf590eabfe0b7afd4ae39bdbf082c), [`6909c74`](https://github.com/mastra-ai/mastra/commit/6909c74a7781e0447d475e9dbc1dc871b700f426), [`192438f`](https://github.com/mastra-ai/mastra/commit/192438f8a90c4f375e955f8ff179bf8dc6821a83)]:
103
+ - @mastra/core@1.5.0-alpha.0
104
+ - @mastra/memory@1.4.0-alpha.0
105
+
106
+ ## 0.4.0
107
+
108
+ ### Minor Changes
109
+
110
+ - Added observational memory configuration support for stored agents. When creating or editing a stored agent in the playground, you can now enable observational memory and configure its settings including model provider/name, scope (thread or resource), share token budget, and detailed observer/reflector parameters like token limits, buffer settings, and blocking thresholds. The configuration is serialized as part of the agent's memory config and round-trips through storage. ([#12962](https://github.com/mastra-ai/mastra/pull/12962))
111
+
112
+ **Example usage in the playground:**
113
+
114
+ Enable the Observational Memory toggle in the Memory section, then configure:
115
+ - Top-level model (provider + model) used by both observer and reflector
116
+ - Scope: `thread` (per-conversation) or `resource` (shared across threads)
117
+ - Expand **Observer** or **Reflector** sections to override models and tune token budgets
118
+
119
+ **Programmatic usage via client SDK:**
120
+
121
+ ```ts
122
+ await client.createStoredAgent({
123
+ name: 'My Agent',
124
+ // ...other config
125
+ memory: {
126
+ observationalMemory: true, // enable with defaults
127
+ options: { lastMessages: 40 },
128
+ },
129
+ });
130
+
131
+ // Or with custom configuration:
132
+ await client.createStoredAgent({
133
+ name: 'My Agent',
134
+ memory: {
135
+ observationalMemory: {
136
+ model: 'google/gemini-2.5-flash',
137
+ scope: 'resource',
138
+ shareTokenBudget: true,
139
+ observation: { messageTokens: 50000 },
140
+ reflection: { observationTokens: 60000 },
141
+ },
142
+ options: { lastMessages: 40 },
143
+ },
144
+ });
145
+ ```
146
+
147
+ **Programmatic usage via editor:**
148
+
149
+ ```ts
150
+ await editor.agent.create({
151
+ name: 'My Agent',
152
+ // ...other config
153
+ memory: {
154
+ observationalMemory: true, // enable with defaults
155
+ options: { lastMessages: 40 },
156
+ },
157
+ });
158
+
159
+ // Or with custom configuration:
160
+ await editor.agent.create({
161
+ name: 'My Agent',
162
+ memory: {
163
+ observationalMemory: {
164
+ model: 'google/gemini-2.5-flash',
165
+ scope: 'resource',
166
+ shareTokenBudget: true,
167
+ observation: { messageTokens: 50000 },
168
+ reflection: { observationTokens: 60000 },
169
+ },
170
+ options: { lastMessages: 40 },
171
+ },
172
+ });
173
+ ```
174
+
175
+ - Added MCP client management, integration tools resolution, and built-in Composio and Arcade AI tool providers. ([#12974](https://github.com/mastra-ai/mastra/pull/12974))
176
+
177
+ **MCP Client Namespace**
178
+
179
+ New `editor.mcpClient` namespace for managing stored MCP client configurations with full CRUD operations. Stored agents can reference MCP clients with per-server tool filtering.
180
+
181
+ **Integration Tools**
182
+
183
+ Stored agents now support an `integrationTools` conditional field that resolves tools from registered `ToolProvider` instances at hydration time:
184
+
185
+ ```ts
186
+ import { MastraEditor } from '@mastra/editor';
187
+ import { ComposioToolProvider } from '@mastra/editor/composio';
188
+ import { ArcadeToolProvider } from '@mastra/editor/arcade';
189
+
190
+ const editor = new MastraEditor({
191
+ // ...
192
+ toolProviders: {
193
+ composio: new ComposioToolProvider({ apiKey: '...' }),
194
+ arcade: new ArcadeToolProvider({ apiKey: '...' }),
195
+ },
196
+ });
197
+ ```
198
+
199
+ **Built-in Tool Providers**
200
+ - `@mastra/editor/composio` — Composio tool provider with toolkit/tool discovery and execution via `@composio/core` and `@composio/mastra` SDKs
201
+ - `@mastra/editor/arcade` — Arcade AI tool provider with a pre-seeded catalog of 93 toolkits, tool discovery, and execution via `@arcadeai/arcadejs` SDK
202
+
203
+ Each provider is a separate entry point — importing `@mastra/editor` alone does not load any provider SDK code.
204
+
205
+ ### Patch Changes
206
+
207
+ - Updated dependencies [[`7ef618f`](https://github.com/mastra-ai/mastra/commit/7ef618f3c49c27e2f6b27d7f564c557c0734325b), [`b373564`](https://github.com/mastra-ai/mastra/commit/b37356491d43b4d53067f10cb669abaf2502f218), [`927c2af`](https://github.com/mastra-ai/mastra/commit/927c2af9792286c122e04409efce0f3c804f777f), [`b896b41`](https://github.com/mastra-ai/mastra/commit/b896b41343de7fcc14442fb40fe82d189e65bbe2), [`6415277`](https://github.com/mastra-ai/mastra/commit/6415277a438faa00db2af850ead5dee25f40c428), [`191bc3a`](https://github.com/mastra-ai/mastra/commit/191bc3adfdbe4b262dbc93b7d9c3d6c6a3c8ef92), [`0831bbb`](https://github.com/mastra-ai/mastra/commit/0831bbb5bc750c18e9b22b45f18687c964b70828), [`74fb394`](https://github.com/mastra-ai/mastra/commit/74fb3944f51f55e1fc1ca65eede4254d8fe72aa3), [`63f7eda`](https://github.com/mastra-ai/mastra/commit/63f7eda605eb3e0c8c35ee3912ffe7c999c69f69), [`a5b67a3`](https://github.com/mastra-ai/mastra/commit/a5b67a3589a74415feb663a55d1858324a2afde9), [`877b02c`](https://github.com/mastra-ai/mastra/commit/877b02cdbb15e199184c7f2b8f217be8d3ebada7), [`cb8c38e`](https://github.com/mastra-ai/mastra/commit/cb8c38e6f855ad190383a7112ba95abef072d490), [`7567222`](https://github.com/mastra-ai/mastra/commit/7567222b1366f0d39980594792dd9d5060bfe2ab), [`af71458`](https://github.com/mastra-ai/mastra/commit/af71458e3b566f09c11d0e5a0a836dc818e7a24a), [`eb36bd8`](https://github.com/mastra-ai/mastra/commit/eb36bd8c52fcd6ec9674ac3b7a6412405b5983e1), [`3cbf121`](https://github.com/mastra-ai/mastra/commit/3cbf121f55418141924754a83102aade89835947)]:
208
+ - @mastra/core@1.4.0
209
+ - @mastra/memory@1.3.0
210
+
3
211
  ## 0.4.0-alpha.0
4
212
 
5
213
  ### Minor Changes