@mastra/mcp-docs-server 1.1.27-alpha.1 → 1.1.27-alpha.2
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/.docs/docs/memory/observational-memory.md +31 -0
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/opencode-go.md +15 -13
- package/.docs/models/providers/regolo-ai.md +83 -0
- package/.docs/models/providers.md +1 -0
- package/.docs/reference/memory/observational-memory.md +2 -0
- package/CHANGELOG.md +7 -0
- package/package.json +4 -4
|
@@ -46,6 +46,37 @@ See [configuration options](https://mastra.ai/reference/memory/observational-mem
|
|
|
46
46
|
|
|
47
47
|
> **Note:** OM currently only supports `@mastra/pg`, `@mastra/libsql`, and `@mastra/mongodb` storage adapters. It uses background agents for managing memory. When using `observationalMemory: true`, the default model is `google/gemini-2.5-flash`. When passing a config object, a `model` must be explicitly set.
|
|
48
48
|
|
|
49
|
+
## Temporal gap markers
|
|
50
|
+
|
|
51
|
+
Temporal gap markers insert a short reminder before a new user message when enough time has passed since the previous message in the thread. They help the agent and the UI see that the conversation resumed after a meaningful pause.
|
|
52
|
+
|
|
53
|
+
Temporal gap markers are off by default. Enable them with `temporalMarkers: true` in the `observationalMemory` config:
|
|
54
|
+
|
|
55
|
+
```typescript
|
|
56
|
+
import { Memory } from '@mastra/memory'
|
|
57
|
+
import { Agent } from '@mastra/core/agent'
|
|
58
|
+
|
|
59
|
+
export const agent = new Agent({
|
|
60
|
+
name: 'my-agent',
|
|
61
|
+
instructions: 'You are a helpful assistant.',
|
|
62
|
+
model: 'openai/gpt-5-mini',
|
|
63
|
+
memory: new Memory({
|
|
64
|
+
options: {
|
|
65
|
+
observationalMemory: {
|
|
66
|
+
model: 'google/gemini-2.5-flash',
|
|
67
|
+
temporalMarkers: true,
|
|
68
|
+
},
|
|
69
|
+
},
|
|
70
|
+
}),
|
|
71
|
+
})
|
|
72
|
+
```
|
|
73
|
+
|
|
74
|
+
Mastra inserts a temporal gap marker when the gap is at least 10 minutes. The marker is stored in memory and also emitted as a transient reminder event, so clients can render it as a lightweight timeline hint.
|
|
75
|
+
|
|
76
|
+
The observer also sees these markers when it processes the thread, so the observations it writes can anchor memories to when they happened (for example, "User asked about deployment after a 2-day gap").
|
|
77
|
+
|
|
78
|
+
See [the API reference](https://mastra.ai/reference/memory/observational-memory) for the full configuration shape.
|
|
79
|
+
|
|
49
80
|
## Benefits
|
|
50
81
|
|
|
51
82
|
- **Prompt caching**: OM's context is stable and observations append over time rather than being dynamically retrieved each turn. This keeps the prompt prefix cacheable, which reduces costs.
|
package/.docs/models/index.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Model Providers
|
|
2
2
|
|
|
3
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
3
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3706 models from 104 providers through a single API.
|
|
4
4
|
|
|
5
5
|
## Features
|
|
6
6
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# OpenCode Go
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 12 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [OpenCode Go documentation](https://opencode.ai/docs/zen).
|
|
6
6
|
|
|
@@ -32,18 +32,20 @@ for await (const chunk of stream) {
|
|
|
32
32
|
|
|
33
33
|
## Models
|
|
34
34
|
|
|
35
|
-
| Model
|
|
36
|
-
|
|
|
37
|
-
| `opencode-go/glm-5`
|
|
38
|
-
| `opencode-go/glm-5.1`
|
|
39
|
-
| `opencode-go/kimi-k2.5`
|
|
40
|
-
| `opencode-go/kimi-k2.6`
|
|
41
|
-
| `opencode-go/mimo-v2-omni`
|
|
42
|
-
| `opencode-go/mimo-v2-pro`
|
|
43
|
-
| `opencode-go/
|
|
44
|
-
| `opencode-go/
|
|
45
|
-
| `opencode-go/
|
|
46
|
-
| `opencode-go/
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| --------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `opencode-go/glm-5` | 205K | | | | | | $1 | $3 |
|
|
38
|
+
| `opencode-go/glm-5.1` | 205K | | | | | | $1 | $4 |
|
|
39
|
+
| `opencode-go/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
|
|
40
|
+
| `opencode-go/kimi-k2.6` | 262K | | | | | | $0.32 | $1 |
|
|
41
|
+
| `opencode-go/mimo-v2-omni` | 262K | | | | | | $0.40 | $2 |
|
|
42
|
+
| `opencode-go/mimo-v2-pro` | 1.0M | | | | | | $1 | $3 |
|
|
43
|
+
| `opencode-go/mimo-v2.5` | 262K | | | | | | $0.40 | $2 |
|
|
44
|
+
| `opencode-go/mimo-v2.5-pro` | 1.0M | | | | | | $1 | $3 |
|
|
45
|
+
| `opencode-go/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
46
|
+
| `opencode-go/minimax-m2.7` | 205K | | | | | | $0.30 | $1 |
|
|
47
|
+
| `opencode-go/qwen3.5-plus` | 262K | | | | | | $0.20 | $1 |
|
|
48
|
+
| `opencode-go/qwen3.6-plus` | 262K | | | | | | $0.50 | $3 |
|
|
47
49
|
|
|
48
50
|
## Advanced configuration
|
|
49
51
|
|
|
@@ -0,0 +1,83 @@
|
|
|
1
|
+
# Regolo AI
|
|
2
|
+
|
|
3
|
+
Access 13 Regolo AI models through Mastra's model router. Authentication is handled automatically using the `REGOLO_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Regolo AI documentation](https://docs.regolo.ai/).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
REGOLO_API_KEY=your-api-key
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
```typescript
|
|
12
|
+
import { Agent } from "@mastra/core/agent";
|
|
13
|
+
|
|
14
|
+
const agent = new Agent({
|
|
15
|
+
id: "my-agent",
|
|
16
|
+
name: "My Agent",
|
|
17
|
+
instructions: "You are a helpful assistant",
|
|
18
|
+
model: "regolo-ai/gpt-oss-120b"
|
|
19
|
+
});
|
|
20
|
+
|
|
21
|
+
// Generate a response
|
|
22
|
+
const response = await agent.generate("Hello!");
|
|
23
|
+
|
|
24
|
+
// Stream a response
|
|
25
|
+
const stream = await agent.stream("Tell me a story");
|
|
26
|
+
for await (const chunk of stream) {
|
|
27
|
+
console.log(chunk);
|
|
28
|
+
}
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Regolo AI documentation](https://docs.regolo.ai/) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ---------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `regolo-ai/gpt-oss-120b` | 128K | | | | | | $1 | $4 |
|
|
38
|
+
| `regolo-ai/gpt-oss-20b` | 128K | | | | | | $0.40 | $2 |
|
|
39
|
+
| `regolo-ai/llama-3.1-8b-instruct` | 120K | | | | | | $0.05 | $0.25 |
|
|
40
|
+
| `regolo-ai/llama-3.3-70b-instruct` | 128K | | | | | | $0.60 | $3 |
|
|
41
|
+
| `regolo-ai/minimax-m2.5` | 190K | | | | | | $0.80 | $4 |
|
|
42
|
+
| `regolo-ai/mistral-small-4-119b` | 256K | | | | | | $0.75 | $3 |
|
|
43
|
+
| `regolo-ai/mistral-small3.2` | 120K | | | | | | $0.50 | $2 |
|
|
44
|
+
| `regolo-ai/qwen-image` | 8K | | | | | | $0.50 | $2 |
|
|
45
|
+
| `regolo-ai/qwen3-coder-next` | 262K | | | | | | $0.30 | $1 |
|
|
46
|
+
| `regolo-ai/qwen3-embedding-8b` | 33K | | | | | | $0.10 | $0.10 |
|
|
47
|
+
| `regolo-ai/qwen3-reranker-4b` | 33K | | | | | | $0.12 | $0.12 |
|
|
48
|
+
| `regolo-ai/qwen3.5-122b` | 262K | | | | | | $0.90 | $4 |
|
|
49
|
+
| `regolo-ai/qwen3.5-9b` | 262K | | | | | | $0.15 | $0.60 |
|
|
50
|
+
|
|
51
|
+
## Advanced configuration
|
|
52
|
+
|
|
53
|
+
### Custom headers
|
|
54
|
+
|
|
55
|
+
```typescript
|
|
56
|
+
const agent = new Agent({
|
|
57
|
+
id: "custom-agent",
|
|
58
|
+
name: "custom-agent",
|
|
59
|
+
model: {
|
|
60
|
+
url: "https://api.regolo.ai/v1",
|
|
61
|
+
id: "regolo-ai/gpt-oss-120b",
|
|
62
|
+
apiKey: process.env.REGOLO_API_KEY,
|
|
63
|
+
headers: {
|
|
64
|
+
"X-Custom-Header": "value"
|
|
65
|
+
}
|
|
66
|
+
}
|
|
67
|
+
});
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
### Dynamic model selection
|
|
71
|
+
|
|
72
|
+
```typescript
|
|
73
|
+
const agent = new Agent({
|
|
74
|
+
id: "dynamic-agent",
|
|
75
|
+
name: "Dynamic Agent",
|
|
76
|
+
model: ({ requestContext }) => {
|
|
77
|
+
const useAdvanced = requestContext.task === "complex";
|
|
78
|
+
return useAdvanced
|
|
79
|
+
? "regolo-ai/qwen3.5-9b"
|
|
80
|
+
: "regolo-ai/gpt-oss-120b";
|
|
81
|
+
}
|
|
82
|
+
});
|
|
83
|
+
```
|
|
@@ -75,6 +75,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
|
|
|
75
75
|
- [Privatemode AI](https://mastra.ai/models/providers/privatemode-ai)
|
|
76
76
|
- [QiHang](https://mastra.ai/models/providers/qihang-ai)
|
|
77
77
|
- [Qiniu](https://mastra.ai/models/providers/qiniu-ai)
|
|
78
|
+
- [Regolo AI](https://mastra.ai/models/providers/regolo-ai)
|
|
78
79
|
- [Requesty](https://mastra.ai/models/providers/requesty)
|
|
79
80
|
- [Scaleway](https://mastra.ai/models/providers/scaleway)
|
|
80
81
|
- [SiliconFlow](https://mastra.ai/models/providers/siliconflow)
|
|
@@ -40,6 +40,8 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
|
|
|
40
40
|
|
|
41
41
|
**shareTokenBudget** (`boolean`): Share the token budget between messages and observations. When enabled, the total budget is \`observation.messageTokens + reflection.observationTokens\`. Messages can use more space when observations are small, and vice versa. This maximizes context usage through flexible allocation. \`shareTokenBudget\` is not yet compatible with async buffering. You must set \`observation: { bufferTokens: false }\` when using this option (this is a temporary limitation). (Default: `false`)
|
|
42
42
|
|
|
43
|
+
**temporalMarkers** (`boolean`): Insert temporal-gap reminder markers before new user messages when the previous message in the thread is at least 10 minutes older. The marker is persisted in memory, emitted as an inline reminder event so clients can render it specially, and shown to the observer so it can anchor observations to when events occurred. (Default: `false`)
|
|
44
|
+
|
|
43
45
|
**retrieval** (`boolean | { vector?: boolean; scope?: 'thread' | 'resource' }`): \*\*Experimental.\*\* Enable retrieval-mode observation groups as durable pointers to raw message history. \`true\` enables cross-thread browsing by default. \`{ vector: true }\` also enables semantic search using Memory's vector store and embedder. \`{ scope: 'thread' }\` restricts the recall tool to the current thread only. Default scope is \`'resource'\`. (Default: `false`)
|
|
44
46
|
|
|
45
47
|
**observation** (`ObservationalMemoryObservationConfig`): Configuration for the observation step. Controls when the Observer agent runs and how it behaves.
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,12 @@
|
|
|
1
1
|
# @mastra/mcp-docs-server
|
|
2
2
|
|
|
3
|
+
## 1.1.27-alpha.2
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- Updated dependencies [[`0a0aa94`](https://github.com/mastra-ai/mastra/commit/0a0aa94729592e99885af2efb90c56aaada62247), [`01a7d51`](https://github.com/mastra-ai/mastra/commit/01a7d513493d21562f677f98550f7ceb165ba78c)]:
|
|
8
|
+
- @mastra/core@1.27.0-alpha.1
|
|
9
|
+
|
|
3
10
|
## 1.1.27-alpha.1
|
|
4
11
|
|
|
5
12
|
### Patch Changes
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/mcp-docs-server",
|
|
3
|
-
"version": "1.1.27-alpha.
|
|
3
|
+
"version": "1.1.27-alpha.2",
|
|
4
4
|
"description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -29,7 +29,7 @@
|
|
|
29
29
|
"jsdom": "^26.1.0",
|
|
30
30
|
"local-pkg": "^1.1.2",
|
|
31
31
|
"zod": "^4.3.6",
|
|
32
|
-
"@mastra/core": "1.
|
|
32
|
+
"@mastra/core": "1.27.0-alpha.1",
|
|
33
33
|
"@mastra/mcp": "^1.5.1"
|
|
34
34
|
},
|
|
35
35
|
"devDependencies": {
|
|
@@ -46,9 +46,9 @@
|
|
|
46
46
|
"tsx": "^4.21.0",
|
|
47
47
|
"typescript": "^5.9.3",
|
|
48
48
|
"vitest": "4.1.4",
|
|
49
|
-
"@internal/lint": "0.0.84",
|
|
50
49
|
"@internal/types-builder": "0.0.59",
|
|
51
|
-
"@
|
|
50
|
+
"@internal/lint": "0.0.84",
|
|
51
|
+
"@mastra/core": "1.27.0-alpha.1"
|
|
52
52
|
},
|
|
53
53
|
"homepage": "https://mastra.ai",
|
|
54
54
|
"repository": {
|