@mastra/editor 0.3.0-alpha.3 → 0.3.0
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 +192 -0
- package/package.json +7 -7
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,197 @@
|
|
|
1
1
|
# @mastra/editor
|
|
2
2
|
|
|
3
|
+
## 0.3.0
|
|
4
|
+
|
|
5
|
+
### Minor Changes
|
|
6
|
+
|
|
7
|
+
- Added `requestContextSchema` and rule-based conditional fields for stored agents. ([#12896](https://github.com/mastra-ai/mastra/pull/12896))
|
|
8
|
+
|
|
9
|
+
Stored agent fields (`tools`, `model`, `workflows`, `agents`, `memory`, `scorers`, `inputProcessors`, `outputProcessors`, `defaultOptions`) can now be configured as conditional variants with rule groups that evaluate against request context at runtime. All matching variants accumulate — arrays are concatenated and objects are shallow-merged — so agents dynamically compose their configuration based on the incoming request context.
|
|
10
|
+
|
|
11
|
+
**New `requestContextSchema` field**
|
|
12
|
+
|
|
13
|
+
Stored agents now accept an optional `requestContextSchema` (JSON Schema) that is converted to a Zod schema and passed to the Agent constructor, enabling request context validation.
|
|
14
|
+
|
|
15
|
+
**Conditional field example**
|
|
16
|
+
|
|
17
|
+
```ts
|
|
18
|
+
await agentsStore.create({
|
|
19
|
+
agent: {
|
|
20
|
+
id: 'my-agent',
|
|
21
|
+
name: 'My Agent',
|
|
22
|
+
instructions: 'You are a helpful assistant',
|
|
23
|
+
model: { provider: 'openai', name: 'gpt-4' },
|
|
24
|
+
tools: [
|
|
25
|
+
{ value: { 'basic-tool': {} } },
|
|
26
|
+
{
|
|
27
|
+
value: { 'premium-tool': {} },
|
|
28
|
+
rules: {
|
|
29
|
+
operator: 'AND',
|
|
30
|
+
conditions: [{ field: 'tier', operator: 'equals', value: 'premium' }],
|
|
31
|
+
},
|
|
32
|
+
},
|
|
33
|
+
],
|
|
34
|
+
requestContextSchema: {
|
|
35
|
+
type: 'object',
|
|
36
|
+
properties: { tier: { type: 'string' } },
|
|
37
|
+
},
|
|
38
|
+
},
|
|
39
|
+
});
|
|
40
|
+
```
|
|
41
|
+
|
|
42
|
+
- Added dynamic instructions for stored agents. Agent instructions can now be composed from reusable prompt blocks with conditional rules and variable interpolation, enabling a prompt-CMS-like editing experience. ([#12861](https://github.com/mastra-ai/mastra/pull/12861))
|
|
43
|
+
|
|
44
|
+
**Instruction blocks** can be mixed in an agent's instructions array:
|
|
45
|
+
- `text` — static text with `{{variable}}` interpolation
|
|
46
|
+
- `prompt_block_ref` — reference to a versioned prompt block stored in the database
|
|
47
|
+
- `prompt_block` — inline prompt block with optional conditional rules
|
|
48
|
+
|
|
49
|
+
**Creating a prompt block and using it in a stored agent:**
|
|
50
|
+
|
|
51
|
+
```ts
|
|
52
|
+
// Create a reusable prompt block
|
|
53
|
+
const block = await editor.createPromptBlock({
|
|
54
|
+
id: 'security-rules',
|
|
55
|
+
name: 'Security Rules',
|
|
56
|
+
content: "You must verify the user's identity. The user's role is {{user.role}}.",
|
|
57
|
+
rules: {
|
|
58
|
+
operator: 'AND',
|
|
59
|
+
conditions: [{ field: 'user.isAuthenticated', operator: 'equals', value: true }],
|
|
60
|
+
},
|
|
61
|
+
});
|
|
62
|
+
|
|
63
|
+
// Create a stored agent that references the prompt block
|
|
64
|
+
await editor.createStoredAgent({
|
|
65
|
+
id: 'support-agent',
|
|
66
|
+
name: 'Support Agent',
|
|
67
|
+
instructions: [
|
|
68
|
+
{ type: 'text', content: 'You are a helpful support agent for {{company}}.' },
|
|
69
|
+
{ type: 'prompt_block_ref', id: 'security-rules' },
|
|
70
|
+
{
|
|
71
|
+
type: 'prompt_block',
|
|
72
|
+
content: 'Always be polite.',
|
|
73
|
+
rules: { operator: 'AND', conditions: [{ field: 'tone', operator: 'equals', value: 'formal' }] },
|
|
74
|
+
},
|
|
75
|
+
],
|
|
76
|
+
model: { provider: 'openai', name: 'gpt-4o' },
|
|
77
|
+
});
|
|
78
|
+
|
|
79
|
+
// At runtime, instructions resolve dynamically based on request context
|
|
80
|
+
const agent = await editor.getStoredAgentById('support-agent');
|
|
81
|
+
const result = await agent.generate('Help me reset my password', {
|
|
82
|
+
requestContext: new RequestContext([
|
|
83
|
+
['company', 'Acme Corp'],
|
|
84
|
+
['user.isAuthenticated', true],
|
|
85
|
+
['user.role', 'admin'],
|
|
86
|
+
['tone', 'formal'],
|
|
87
|
+
]),
|
|
88
|
+
});
|
|
89
|
+
```
|
|
90
|
+
|
|
91
|
+
Prompt blocks are versioned — updating a block's content takes effect immediately for all agents referencing it, with no cache clearing required.
|
|
92
|
+
|
|
93
|
+
- **Added stored scorer definitions, editor namespace pattern, and generic storage domains** ([#12846](https://github.com/mastra-ai/mastra/pull/12846))
|
|
94
|
+
- Added a new `scorer-definitions` storage domain for storing LLM-as-judge and preset scorer configurations in the database
|
|
95
|
+
- Introduced a `VersionedStorageDomain` generic base class that unifies `AgentsStorage`, `PromptBlocksStorage`, and `ScorerDefinitionsStorage` with shared CRUD methods (`create`, `getById`, `getByIdResolved`, `update`, `delete`, `list`, `listResolved`)
|
|
96
|
+
- Flattened stored scorer type system: replaced nested `preset`/`customLLMJudge` config with top-level `type`, `instructions`, `scoreRange`, and `presetConfig` fields
|
|
97
|
+
- Refactored `MastraEditor` to use a namespace pattern (`editor.agent.*`, `editor.scorer.*`, `editor.prompt.*`) backed by a `CrudEditorNamespace` base class with built-in caching and an `onCacheEvict` hook
|
|
98
|
+
- Added `rawConfig` support to `MastraBase` and `MastraScorer` via `toRawConfig()`, so hydrated primitives carry their stored configuration
|
|
99
|
+
- Added prompt block and scorer registration to the `Mastra` class (`addPromptBlock`, `removePromptBlock`, `addScorer`, `removeScorer`)
|
|
100
|
+
|
|
101
|
+
**Creating a stored scorer (LLM-as-judge):**
|
|
102
|
+
|
|
103
|
+
```ts
|
|
104
|
+
const scorer = await editor.scorer.create({
|
|
105
|
+
id: 'my-scorer',
|
|
106
|
+
name: 'Response Quality',
|
|
107
|
+
type: 'llm-judge',
|
|
108
|
+
instructions: 'Evaluate the response for accuracy and helpfulness.',
|
|
109
|
+
model: { provider: 'openai', name: 'gpt-4o' },
|
|
110
|
+
scoreRange: { min: 0, max: 1 },
|
|
111
|
+
});
|
|
112
|
+
```
|
|
113
|
+
|
|
114
|
+
**Retrieving and resolving a stored scorer:**
|
|
115
|
+
|
|
116
|
+
```ts
|
|
117
|
+
// Fetch the stored definition from DB
|
|
118
|
+
const definition = await editor.scorer.getById('my-scorer');
|
|
119
|
+
|
|
120
|
+
// Resolve it into a runnable MastraScorer instance
|
|
121
|
+
const runnableScorer = editor.scorer.resolve(definition);
|
|
122
|
+
|
|
123
|
+
// Execute the scorer
|
|
124
|
+
const result = await runnableScorer.run({
|
|
125
|
+
input: 'What is the capital of France?',
|
|
126
|
+
output: 'The capital of France is Paris.',
|
|
127
|
+
});
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
**Editor namespace pattern (before/after):**
|
|
131
|
+
|
|
132
|
+
```ts
|
|
133
|
+
// Before
|
|
134
|
+
const agent = await editor.getStoredAgentById('abc');
|
|
135
|
+
const prompts = await editor.listPromptBlocks();
|
|
136
|
+
|
|
137
|
+
// After
|
|
138
|
+
const agent = await editor.agent.getById('abc');
|
|
139
|
+
const prompts = await editor.prompt.list();
|
|
140
|
+
```
|
|
141
|
+
|
|
142
|
+
**Generic storage domain methods (before/after):**
|
|
143
|
+
|
|
144
|
+
```ts
|
|
145
|
+
// Before
|
|
146
|
+
const store = storage.getStore('agents');
|
|
147
|
+
await store.createAgent({ agent: input });
|
|
148
|
+
await store.getAgentById({ id: 'abc' });
|
|
149
|
+
await store.deleteAgent({ id: 'abc' });
|
|
150
|
+
|
|
151
|
+
// After
|
|
152
|
+
const store = storage.getStore('agents');
|
|
153
|
+
await store.create({ agent: input });
|
|
154
|
+
await store.getById('abc');
|
|
155
|
+
await store.delete('abc');
|
|
156
|
+
```
|
|
157
|
+
|
|
158
|
+
- Add tool description overrides for stored agents: ([#12794](https://github.com/mastra-ai/mastra/pull/12794))
|
|
159
|
+
- Changed stored agent `tools` field from `string[]` to `Record<string, { description?: string }>` to allow per-tool description overrides
|
|
160
|
+
- When a stored agent specifies a custom `description` for a tool, the override is applied at resolution time
|
|
161
|
+
- Updated server API schemas, client SDK types, and editor resolution logic accordingly
|
|
162
|
+
|
|
163
|
+
- **Breaking:** Removed `cloneAgent()` from the `Agent` class. Agent cloning is now handled by the editor package via `editor.agent.clone()`. ([#12904](https://github.com/mastra-ai/mastra/pull/12904))
|
|
164
|
+
|
|
165
|
+
If you were calling `agent.cloneAgent()` directly, use the editor's agent namespace instead:
|
|
166
|
+
|
|
167
|
+
```ts
|
|
168
|
+
// Before
|
|
169
|
+
const result = await agent.cloneAgent({ newId: 'my-clone' });
|
|
170
|
+
|
|
171
|
+
// After
|
|
172
|
+
const editor = mastra.getEditor();
|
|
173
|
+
const result = await editor.agent.clone(agent, { newId: 'my-clone' });
|
|
174
|
+
```
|
|
175
|
+
|
|
176
|
+
**Why:** The `Agent` class should not be responsible for storage serialization. The editor package already handles converting between runtime agents and stored configurations, so cloning belongs there.
|
|
177
|
+
|
|
178
|
+
**Added** `getConfiguredProcessorIds()` to the `Agent` class, which returns raw input/output processor IDs for the agent's configuration.
|
|
179
|
+
|
|
180
|
+
### Patch Changes
|
|
181
|
+
|
|
182
|
+
- Fixed stale agent data in CMS pages by adding removeAgent method to Mastra and updating clearStoredAgentCache to clear both Editor cache and Mastra registry when stored agents are updated or deleted ([#12693](https://github.com/mastra-ai/mastra/pull/12693))
|
|
183
|
+
|
|
184
|
+
- Fixed stored scorers not being registered on the Mastra instance. Scorers created via the editor are now automatically discoverable through `mastra.getScorer()` and `mastra.getScorerById()`, matching the existing behavior of stored agents. Previously, stored scorers could only be resolved inline but were invisible to the runtime registry, causing lookups to fail. ([#12903](https://github.com/mastra-ai/mastra/pull/12903))
|
|
185
|
+
|
|
186
|
+
- Fix memory persistence: ([#12704](https://github.com/mastra-ai/mastra/pull/12704))
|
|
187
|
+
- Fixed memory persistence bug by handling missing vector store gracefully
|
|
188
|
+
- When semantic recall is enabled but no vector store is configured, it now disables semantic recall instead of failing
|
|
189
|
+
- Fixed type compatibility for `embedder` field when creating agents from stored config
|
|
190
|
+
|
|
191
|
+
- Updated dependencies [[`717ffab`](https://github.com/mastra-ai/mastra/commit/717ffab42cfd58ff723b5c19ada4939997773004), [`b31c922`](https://github.com/mastra-ai/mastra/commit/b31c922215b513791d98feaea1b98784aa00803a), [`e4b6dab`](https://github.com/mastra-ai/mastra/commit/e4b6dab171c5960e340b3ea3ea6da8d64d2b8672), [`5719fa8`](https://github.com/mastra-ai/mastra/commit/5719fa8880e86e8affe698ec4b3807c7e0e0a06f), [`83cda45`](https://github.com/mastra-ai/mastra/commit/83cda4523e588558466892bff8f80f631a36945a), [`11804ad`](https://github.com/mastra-ai/mastra/commit/11804adf1d6be46ebe216be40a43b39bb8b397d7), [`2e02cd7`](https://github.com/mastra-ai/mastra/commit/2e02cd7e08ba2d84a275c80d80c069d2b8b66211), [`aa95f95`](https://github.com/mastra-ai/mastra/commit/aa95f958b186ae5c9f4219c88e268f5565c277a2), [`90f7894`](https://github.com/mastra-ai/mastra/commit/90f7894568dc9481f40a4d29672234fae23090bb), [`f5501ae`](https://github.com/mastra-ai/mastra/commit/f5501aedb0a11106c7db7e480d6eaf3971b7bda8), [`44573af`](https://github.com/mastra-ai/mastra/commit/44573afad0a4bc86f627d6cbc0207961cdcb3bc3), [`00e3861`](https://github.com/mastra-ai/mastra/commit/00e3861863fbfee78faeb1ebbdc7c0223aae13ff), [`8109aee`](https://github.com/mastra-ai/mastra/commit/8109aeeab758e16cd4255a6c36f044b70eefc6a6), [`7bfbc52`](https://github.com/mastra-ai/mastra/commit/7bfbc52a8604feb0fff2c0a082c13c0c2a3df1a2), [`1445994`](https://github.com/mastra-ai/mastra/commit/1445994aee19c9334a6a101cf7bd80ca7ed4d186), [`61f44a2`](https://github.com/mastra-ai/mastra/commit/61f44a26861c89e364f367ff40825bdb7f19df55), [`37145d2`](https://github.com/mastra-ai/mastra/commit/37145d25f99dc31f1a9105576e5452609843ce32), [`fdad759`](https://github.com/mastra-ai/mastra/commit/fdad75939ff008b27625f5ec0ce9c6915d99d9ec), [`e4569c5`](https://github.com/mastra-ai/mastra/commit/e4569c589e00c4061a686c9eb85afe1b7050b0a8), [`7309a85`](https://github.com/mastra-ai/mastra/commit/7309a85427281a8be23f4fb80ca52e18eaffd596), [`99424f6`](https://github.com/mastra-ai/mastra/commit/99424f6862ffb679c4ec6765501486034754a4c2), [`44eb452`](https://github.com/mastra-ai/mastra/commit/44eb4529b10603c279688318bebf3048543a1d61), [`6c40593`](https://github.com/mastra-ai/mastra/commit/6c40593d6d2b1b68b0c45d1a3a4c6ac5ecac3937), [`8c1135d`](https://github.com/mastra-ai/mastra/commit/8c1135dfb91b057283eae7ee11f9ec28753cc64f), [`dd39e54`](https://github.com/mastra-ai/mastra/commit/dd39e54ea34532c995b33bee6e0e808bf41a7341), [`b6fad9a`](https://github.com/mastra-ai/mastra/commit/b6fad9a602182b1cc0df47cd8c55004fa829ad61), [`4129c07`](https://github.com/mastra-ai/mastra/commit/4129c073349b5a66643fd8136ebfe9d7097cf793), [`5b930ab`](https://github.com/mastra-ai/mastra/commit/5b930aba1834d9898e8460a49d15106f31ac7c8d), [`4be93d0`](https://github.com/mastra-ai/mastra/commit/4be93d09d68e20aaf0ea3f210749422719618b5f), [`047635c`](https://github.com/mastra-ai/mastra/commit/047635ccd7861d726c62d135560c0022a5490aec), [`8c90ff4`](https://github.com/mastra-ai/mastra/commit/8c90ff4d3414e7f2a2d216ea91274644f7b29133), [`ed232d1`](https://github.com/mastra-ai/mastra/commit/ed232d1583f403925dc5ae45f7bee948cf2a182b), [`3891795`](https://github.com/mastra-ai/mastra/commit/38917953518eb4154a984ee36e6ededdcfe80f72), [`4f955b2`](https://github.com/mastra-ai/mastra/commit/4f955b20c7f66ed282ee1fd8709696fa64c4f19d), [`55a4c90`](https://github.com/mastra-ai/mastra/commit/55a4c9044ac7454349b9f6aeba0bbab5ee65d10f)]:
|
|
192
|
+
- @mastra/core@1.3.0
|
|
193
|
+
- @mastra/memory@1.2.0
|
|
194
|
+
|
|
3
195
|
## 0.3.0-alpha.3
|
|
4
196
|
|
|
5
197
|
### Patch Changes
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/editor",
|
|
3
|
-
"version": "0.3.0
|
|
3
|
+
"version": "0.3.0",
|
|
4
4
|
"description": "Mastra Editor for agent management and instantiation",
|
|
5
5
|
"main": "dist/index.cjs",
|
|
6
6
|
"module": "dist/index.js",
|
|
@@ -20,7 +20,7 @@
|
|
|
20
20
|
"url": "https://github.com/mastra-ai/mastra/issues"
|
|
21
21
|
},
|
|
22
22
|
"dependencies": {
|
|
23
|
-
"@mastra/memory": "1.2.0
|
|
23
|
+
"@mastra/memory": "1.2.0",
|
|
24
24
|
"@mastra/schema-compat": "1.1.0"
|
|
25
25
|
},
|
|
26
26
|
"devDependencies": {
|
|
@@ -28,11 +28,11 @@
|
|
|
28
28
|
"typescript": "^5.9.3",
|
|
29
29
|
"vitest": "4.0.16",
|
|
30
30
|
"zod": "^3.25.76",
|
|
31
|
-
"@internal/ai-sdk-v4": "0.0.
|
|
32
|
-
"@internal/ai-sdk-v5": "0.0.
|
|
33
|
-
"@
|
|
34
|
-
"@mastra/libsql": "1.3.0
|
|
35
|
-
"@
|
|
31
|
+
"@internal/ai-sdk-v4": "0.0.5",
|
|
32
|
+
"@internal/ai-sdk-v5": "0.0.5",
|
|
33
|
+
"@mastra/core": "1.3.0",
|
|
34
|
+
"@mastra/libsql": "1.3.0",
|
|
35
|
+
"@internal/ai-v6": "0.0.5"
|
|
36
36
|
},
|
|
37
37
|
"peerDependencies": {
|
|
38
38
|
"@mastra/core": ">=1.0.0-0 <2.0.0-0",
|