@mastra/mcp-docs-server 1.1.26-alpha.10 → 1.1.26-alpha.13
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/observability/tracing/exporters/langfuse.md +31 -0
- package/.docs/guides/deployment/netlify.md +16 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/digitalocean.md +116 -0
- package/.docs/models/providers/helicone.md +1 -2
- package/.docs/models/providers/openai.md +1 -2
- package/.docs/models/providers/ovhcloud.md +4 -7
- package/.docs/models/providers/tencent-token-plan.md +71 -0
- package/.docs/models/providers/tencent-tokenhub.md +71 -0
- package/.docs/models/providers.md +3 -0
- package/.docs/reference/deployer/netlify.md +50 -2
- package/.docs/reference/observability/tracing/exporters/langfuse.md +2 -0
- package/CHANGELOG.md +7 -0
- package/package.json +3 -3
|
@@ -122,6 +122,35 @@ new LangfuseExporter({
|
|
|
122
122
|
})
|
|
123
123
|
```
|
|
124
124
|
|
|
125
|
+
#### Batch Tuning for High-Volume Traces
|
|
126
|
+
|
|
127
|
+
For self-hosted Langfuse deployments or streamed runs that produce many spans per second, you can tune the OTEL batch size and flush interval to reduce request pressure on the Langfuse ingestion endpoint:
|
|
128
|
+
|
|
129
|
+
```typescript
|
|
130
|
+
new LangfuseExporter({
|
|
131
|
+
publicKey: process.env.LANGFUSE_PUBLIC_KEY!,
|
|
132
|
+
secretKey: process.env.LANGFUSE_SECRET_KEY!,
|
|
133
|
+
flushAt: 500, // Maximum spans per OTEL export batch
|
|
134
|
+
flushInterval: 20, // Maximum seconds between flushes
|
|
135
|
+
})
|
|
136
|
+
```
|
|
137
|
+
|
|
138
|
+
To suppress high-volume span types entirely (for example `MODEL_CHUNK` spans from streamed responses), use the observability-level [`excludeSpanTypes` option](https://mastra.ai/reference/observability/tracing/span-filtering) rather than configuring the exporter:
|
|
139
|
+
|
|
140
|
+
```typescript
|
|
141
|
+
import { SpanType } from '@mastra/core/observability'
|
|
142
|
+
|
|
143
|
+
new Observability({
|
|
144
|
+
configs: {
|
|
145
|
+
langfuse: {
|
|
146
|
+
serviceName: 'my-service',
|
|
147
|
+
exporters: [new LangfuseExporter()],
|
|
148
|
+
excludeSpanTypes: [SpanType.MODEL_CHUNK],
|
|
149
|
+
},
|
|
150
|
+
},
|
|
151
|
+
})
|
|
152
|
+
```
|
|
153
|
+
|
|
125
154
|
### Complete Configuration
|
|
126
155
|
|
|
127
156
|
```typescript
|
|
@@ -133,6 +162,8 @@ new LangfuseExporter({
|
|
|
133
162
|
// Optional settings
|
|
134
163
|
baseUrl: process.env.LANGFUSE_BASE_URL, // Default: https://cloud.langfuse.com
|
|
135
164
|
realtime: process.env.NODE_ENV === 'development', // Dynamic mode selection
|
|
165
|
+
flushAt: 500, // Maximum spans per OTEL export batch
|
|
166
|
+
flushInterval: 20, // Maximum seconds between flushes
|
|
136
167
|
logLevel: 'info', // Diagnostic logging: debug | info | warn | error
|
|
137
168
|
|
|
138
169
|
// Langfuse-specific settings
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Deploy Mastra to Netlify
|
|
2
2
|
|
|
3
|
-
Use `@mastra/deployer-netlify` to deploy your Mastra server
|
|
3
|
+
Use `@mastra/deployer-netlify` to deploy your Mastra server on Netlify. The deployer bundles your code and generates a `.netlify` directory conforming to Netlify's [Frameworks API](https://docs.netlify.com/build/frameworks/frameworks-api/), ready to deploy. You can deploy as serverless functions (default) or as [edge functions](https://docs.netlify.com/build/edge-functions/overview/) for lower latency and longer execution times.
|
|
4
4
|
|
|
5
5
|
> **Info:** This guide covers deploying the [Mastra server](https://mastra.ai/docs/server/mastra-server). If you're using a [server adapter](https://mastra.ai/docs/server/server-adapters) or [web framework](https://mastra.ai/docs/deployment/web-framework), deploy the way you normally would for that framework.
|
|
6
6
|
|
|
@@ -49,6 +49,21 @@ export const mastra = new Mastra({
|
|
|
49
49
|
})
|
|
50
50
|
```
|
|
51
51
|
|
|
52
|
+
To deploy as edge functions instead, pass `{ target: 'edge' }`:
|
|
53
|
+
|
|
54
|
+
```typescript
|
|
55
|
+
import { Mastra } from '@mastra/core'
|
|
56
|
+
import { NetlifyDeployer } from '@mastra/deployer-netlify'
|
|
57
|
+
|
|
58
|
+
export const mastra = new Mastra({
|
|
59
|
+
deployer: new NetlifyDeployer({
|
|
60
|
+
target: 'edge',
|
|
61
|
+
}),
|
|
62
|
+
})
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
Edge functions run on Deno at the edge closest to your users. They have no hard execution timeout (only a CPU time limit), making them a better fit for longer-running AI workflows. See the [constructor options](https://mastra.ai/reference/deployer/netlify) for details.
|
|
66
|
+
|
|
52
67
|
Create a `netlify.toml` file with the following contents in your project root:
|
|
53
68
|
|
|
54
69
|
```toml
|
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 3653 models from 103 providers through a single API.
|
|
4
4
|
|
|
5
5
|
## Features
|
|
6
6
|
|
|
@@ -0,0 +1,116 @@
|
|
|
1
|
+
# DigitalOcean
|
|
2
|
+
|
|
3
|
+
Access 46 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
DIGITALOCEAN_ACCESS_TOKEN=your-api-token
|
|
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: "digitalocean/alibaba-qwen3-32b"
|
|
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 [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `digitalocean/alibaba-qwen3-32b` | 131K | | | | | | $0.25 | $0.55 |
|
|
38
|
+
| `digitalocean/all-mini-lm-l6-v2` | 256 | | | | | | $0.01 | — |
|
|
39
|
+
| `digitalocean/anthropic-claude-4.1-opus` | 200K | | | | | | $15 | $75 |
|
|
40
|
+
| `digitalocean/anthropic-claude-4.5-sonnet` | 1.0M | | | | | | $3 | $15 |
|
|
41
|
+
| `digitalocean/anthropic-claude-4.6-sonnet` | 1.0M | | | | | | $3 | $15 |
|
|
42
|
+
| `digitalocean/anthropic-claude-haiku-4.5` | 200K | | | | | | $1 | $5 |
|
|
43
|
+
| `digitalocean/anthropic-claude-opus-4` | 200K | | | | | | $15 | $75 |
|
|
44
|
+
| `digitalocean/anthropic-claude-opus-4.5` | 200K | | | | | | $5 | $25 |
|
|
45
|
+
| `digitalocean/anthropic-claude-opus-4.6` | 1.0M | | | | | | $5 | $25 |
|
|
46
|
+
| `digitalocean/anthropic-claude-opus-4.7` | 1.0M | | | | | | $5 | $25 |
|
|
47
|
+
| `digitalocean/anthropic-claude-sonnet-4` | 1.0M | | | | | | $3 | $15 |
|
|
48
|
+
| `digitalocean/arcee-trinity-large-thinking` | 256K | | | | | | $0.25 | $0.90 |
|
|
49
|
+
| `digitalocean/deepseek-r1-distill-llama-70b` | 131K | | | | | | $0.99 | $0.99 |
|
|
50
|
+
| `digitalocean/fal-ai/elevenlabs/tts/multilingual-v2` | — | | | | | | — | — |
|
|
51
|
+
| `digitalocean/fal-ai/fast-sdxl` | — | | | | | | — | — |
|
|
52
|
+
| `digitalocean/fal-ai/flux/schnell` | — | | | | | | — | — |
|
|
53
|
+
| `digitalocean/fal-ai/stable-audio-25/text-to-audio` | — | | | | | | — | — |
|
|
54
|
+
| `digitalocean/glm-5` | 203K | | | | | | $1 | $3 |
|
|
55
|
+
| `digitalocean/gte-large-en-v1.5` | 8K | | | | | | $0.09 | — |
|
|
56
|
+
| `digitalocean/kimi-k2.5` | 262K | | | | | | $0.50 | $3 |
|
|
57
|
+
| `digitalocean/llama3.3-70b-instruct` | 128K | | | | | | $0.65 | $0.65 |
|
|
58
|
+
| `digitalocean/minimax-m2.5` | 205K | | | | | | $0.30 | $1 |
|
|
59
|
+
| `digitalocean/multi-qa-mpnet-base-dot-v1` | 512 | | | | | | $0.01 | — |
|
|
60
|
+
| `digitalocean/nvidia-nemotron-3-super-120b` | 256K | | | | | | $0.30 | $0.65 |
|
|
61
|
+
| `digitalocean/openai-gpt-4.1` | 1.0M | | | | | | $2 | $8 |
|
|
62
|
+
| `digitalocean/openai-gpt-4o` | 128K | | | | | | $3 | $10 |
|
|
63
|
+
| `digitalocean/openai-gpt-4o-mini` | 128K | | | | | | $0.15 | $0.60 |
|
|
64
|
+
| `digitalocean/openai-gpt-5` | 400K | | | | | | $1 | $10 |
|
|
65
|
+
| `digitalocean/openai-gpt-5-2-pro` | 400K | | | | | | $21 | $168 |
|
|
66
|
+
| `digitalocean/openai-gpt-5-mini` | 400K | | | | | | $0.25 | $2 |
|
|
67
|
+
| `digitalocean/openai-gpt-5-nano` | 400K | | | | | | $0.05 | $0.40 |
|
|
68
|
+
| `digitalocean/openai-gpt-5.1-codex-max` | 400K | | | | | | $1 | $10 |
|
|
69
|
+
| `digitalocean/openai-gpt-5.2` | 400K | | | | | | $2 | $14 |
|
|
70
|
+
| `digitalocean/openai-gpt-5.3-codex` | 400K | | | | | | $2 | $14 |
|
|
71
|
+
| `digitalocean/openai-gpt-5.4` | 1.0M | | | | | | $3 | $15 |
|
|
72
|
+
| `digitalocean/openai-gpt-5.4-mini` | 400K | | | | | | $0.75 | $5 |
|
|
73
|
+
| `digitalocean/openai-gpt-5.4-nano` | 400K | | | | | | $0.20 | $1 |
|
|
74
|
+
| `digitalocean/openai-gpt-5.4-pro` | 400K | | | | | | $30 | $180 |
|
|
75
|
+
| `digitalocean/openai-gpt-image-1` | — | | | | | | $5 | $40 |
|
|
76
|
+
| `digitalocean/openai-gpt-image-1.5` | — | | | | | | $5 | $10 |
|
|
77
|
+
| `digitalocean/openai-gpt-oss-120b` | 131K | | | | | | $0.10 | $0.70 |
|
|
78
|
+
| `digitalocean/openai-gpt-oss-20b` | 131K | | | | | | $0.05 | $0.45 |
|
|
79
|
+
| `digitalocean/openai-o1` | 200K | | | | | | $15 | $60 |
|
|
80
|
+
| `digitalocean/openai-o3` | 200K | | | | | | $2 | $8 |
|
|
81
|
+
| `digitalocean/openai-o3-mini` | 200K | | | | | | $1 | $4 |
|
|
82
|
+
| `digitalocean/qwen3-embedding-0.6b` | 8K | | | | | | $0.04 | — |
|
|
83
|
+
|
|
84
|
+
## Advanced configuration
|
|
85
|
+
|
|
86
|
+
### Custom headers
|
|
87
|
+
|
|
88
|
+
```typescript
|
|
89
|
+
const agent = new Agent({
|
|
90
|
+
id: "custom-agent",
|
|
91
|
+
name: "custom-agent",
|
|
92
|
+
model: {
|
|
93
|
+
url: "https://inference.do-ai.run/v1",
|
|
94
|
+
id: "digitalocean/alibaba-qwen3-32b",
|
|
95
|
+
apiKey: process.env.DIGITALOCEAN_ACCESS_TOKEN,
|
|
96
|
+
headers: {
|
|
97
|
+
"X-Custom-Header": "value"
|
|
98
|
+
}
|
|
99
|
+
}
|
|
100
|
+
});
|
|
101
|
+
```
|
|
102
|
+
|
|
103
|
+
### Dynamic model selection
|
|
104
|
+
|
|
105
|
+
```typescript
|
|
106
|
+
const agent = new Agent({
|
|
107
|
+
id: "dynamic-agent",
|
|
108
|
+
name: "Dynamic Agent",
|
|
109
|
+
model: ({ requestContext }) => {
|
|
110
|
+
const useAdvanced = requestContext.task === "complex";
|
|
111
|
+
return useAdvanced
|
|
112
|
+
? "digitalocean/qwen3-embedding-0.6b"
|
|
113
|
+
: "digitalocean/alibaba-qwen3-32b";
|
|
114
|
+
}
|
|
115
|
+
});
|
|
116
|
+
```
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Helicone
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 90 Helicone models through Mastra's model router. Authentication is handled automatically using the `HELICONE_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [Helicone documentation](https://helicone.ai/models).
|
|
6
6
|
|
|
@@ -48,7 +48,6 @@ for await (const chunk of stream) {
|
|
|
48
48
|
| `helicone/claude-opus-4-1-20250805` | 200K | | | | | | $15 | $75 |
|
|
49
49
|
| `helicone/claude-sonnet-4` | 200K | | | | | | $3 | $15 |
|
|
50
50
|
| `helicone/claude-sonnet-4-5-20250929` | 200K | | | | | | $3 | $15 |
|
|
51
|
-
| `helicone/codex-mini-latest` | 200K | | | | | | $2 | $6 |
|
|
52
51
|
| `helicone/deepseek-r1-distill-llama-70b` | 128K | | | | | | $0.03 | $0.13 |
|
|
53
52
|
| `helicone/deepseek-reasoner` | 128K | | | | | | $0.56 | $2 |
|
|
54
53
|
| `helicone/deepseek-tng-r1t2-chimera` | 130K | | | | | | $0.30 | $1 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# OpenAI
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 50 OpenAI models through Mastra's model router. Authentication is handled automatically using the `OPENAI_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [OpenAI documentation](https://platform.openai.com/docs/models).
|
|
6
6
|
|
|
@@ -33,7 +33,6 @@ for await (const chunk of stream) {
|
|
|
33
33
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
34
34
|
| ------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
35
35
|
| `openai/chatgpt-image-latest` | — | | | | | | — | — |
|
|
36
|
-
| `openai/codex-mini-latest` | 200K | | | | | | $2 | $6 |
|
|
37
36
|
| `openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
38
37
|
| `openai/gpt-4` | 8K | | | | | | $30 | $60 |
|
|
39
38
|
| `openai/gpt-4-turbo` | 128K | | | | | | $10 | $30 |
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# OVHcloud AI Endpoints
|
|
2
2
|
|
|
3
|
-
Access
|
|
3
|
+
Access 10 OVHcloud AI Endpoints models through Mastra's model router. Authentication is handled automatically using the `OVHCLOUD_API_KEY` environment variable.
|
|
4
4
|
|
|
5
5
|
Learn more in the [OVHcloud AI Endpoints documentation](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//).
|
|
6
6
|
|
|
@@ -15,7 +15,7 @@ const agent = new Agent({
|
|
|
15
15
|
id: "my-agent",
|
|
16
16
|
name: "My Agent",
|
|
17
17
|
instructions: "You are a helpful assistant",
|
|
18
|
-
model: "ovhcloud/
|
|
18
|
+
model: "ovhcloud/gpt-oss-120b"
|
|
19
19
|
});
|
|
20
20
|
|
|
21
21
|
// Generate a response
|
|
@@ -34,7 +34,6 @@ for await (const chunk of stream) {
|
|
|
34
34
|
|
|
35
35
|
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
36
|
| ---------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
-
| `ovhcloud/deepseek-r1-distill-llama-70b` | 131K | | | | | | $0.74 | $0.74 |
|
|
38
37
|
| `ovhcloud/gpt-oss-120b` | 131K | | | | | | $0.09 | $0.47 |
|
|
39
38
|
| `ovhcloud/gpt-oss-20b` | 131K | | | | | | $0.05 | $0.18 |
|
|
40
39
|
| `ovhcloud/llama-3.1-8b-instruct` | 131K | | | | | | $0.11 | $0.11 |
|
|
@@ -42,8 +41,6 @@ for await (const chunk of stream) {
|
|
|
42
41
|
| `ovhcloud/mistral-7b-instruct-v0.3` | 66K | | | | | | $0.11 | $0.11 |
|
|
43
42
|
| `ovhcloud/mistral-nemo-instruct-2407` | 66K | | | | | | $0.14 | $0.14 |
|
|
44
43
|
| `ovhcloud/mistral-small-3.2-24b-instruct-2506` | 131K | | | | | | $0.10 | $0.31 |
|
|
45
|
-
| `ovhcloud/mixtral-8x7b-instruct-v0.1` | 33K | | | | | | $0.70 | $0.70 |
|
|
46
|
-
| `ovhcloud/qwen2.5-coder-32b-instruct` | 33K | | | | | | $0.96 | $0.96 |
|
|
47
44
|
| `ovhcloud/qwen2.5-vl-72b-instruct` | 33K | | | | | | $1 | $1 |
|
|
48
45
|
| `ovhcloud/qwen3-32b` | 33K | | | | | | $0.09 | $0.25 |
|
|
49
46
|
| `ovhcloud/qwen3-coder-30b-a3b-instruct` | 262K | | | | | | $0.07 | $0.26 |
|
|
@@ -58,7 +55,7 @@ const agent = new Agent({
|
|
|
58
55
|
name: "custom-agent",
|
|
59
56
|
model: {
|
|
60
57
|
url: "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
|
|
61
|
-
id: "ovhcloud/
|
|
58
|
+
id: "ovhcloud/gpt-oss-120b",
|
|
62
59
|
apiKey: process.env.OVHCLOUD_API_KEY,
|
|
63
60
|
headers: {
|
|
64
61
|
"X-Custom-Header": "value"
|
|
@@ -77,7 +74,7 @@ const agent = new Agent({
|
|
|
77
74
|
const useAdvanced = requestContext.task === "complex";
|
|
78
75
|
return useAdvanced
|
|
79
76
|
? "ovhcloud/qwen3-coder-30b-a3b-instruct"
|
|
80
|
-
: "ovhcloud/
|
|
77
|
+
: "ovhcloud/gpt-oss-120b";
|
|
81
78
|
}
|
|
82
79
|
});
|
|
83
80
|
```
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
# Tencent Token Plan
|
|
2
|
+
|
|
3
|
+
Access 1 Tencent Token Plan model through Mastra's model router. Authentication is handled automatically using the `TENCENT_TOKEN_PLAN_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Tencent Token Plan documentation](https://cloud.tencent.com/document/product/1823/130060).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
TENCENT_TOKEN_PLAN_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: "tencent-token-plan/hy3-preview"
|
|
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 [Tencent Token Plan documentation](https://cloud.tencent.com/document/product/1823/130060) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| -------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `tencent-token-plan/hy3-preview` | 256K | | | | | | — | — |
|
|
38
|
+
|
|
39
|
+
## Advanced configuration
|
|
40
|
+
|
|
41
|
+
### Custom headers
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
const agent = new Agent({
|
|
45
|
+
id: "custom-agent",
|
|
46
|
+
name: "custom-agent",
|
|
47
|
+
model: {
|
|
48
|
+
url: "https://api.lkeap.cloud.tencent.com/plan/v3",
|
|
49
|
+
id: "tencent-token-plan/hy3-preview",
|
|
50
|
+
apiKey: process.env.TENCENT_TOKEN_PLAN_API_KEY,
|
|
51
|
+
headers: {
|
|
52
|
+
"X-Custom-Header": "value"
|
|
53
|
+
}
|
|
54
|
+
}
|
|
55
|
+
});
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
### Dynamic model selection
|
|
59
|
+
|
|
60
|
+
```typescript
|
|
61
|
+
const agent = new Agent({
|
|
62
|
+
id: "dynamic-agent",
|
|
63
|
+
name: "Dynamic Agent",
|
|
64
|
+
model: ({ requestContext }) => {
|
|
65
|
+
const useAdvanced = requestContext.task === "complex";
|
|
66
|
+
return useAdvanced
|
|
67
|
+
? "tencent-token-plan/hy3-preview"
|
|
68
|
+
: "tencent-token-plan/hy3-preview";
|
|
69
|
+
}
|
|
70
|
+
});
|
|
71
|
+
```
|
|
@@ -0,0 +1,71 @@
|
|
|
1
|
+
# Tencent TokenHub
|
|
2
|
+
|
|
3
|
+
Access 1 Tencent TokenHub model through Mastra's model router. Authentication is handled automatically using the `TENCENT_TOKENHUB_API_KEY` environment variable.
|
|
4
|
+
|
|
5
|
+
Learn more in the [Tencent TokenHub documentation](https://cloud.tencent.com/document/product/1823/130050).
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
TENCENT_TOKENHUB_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: "tencent-tokenhub/hy3-preview"
|
|
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 [Tencent TokenHub documentation](https://cloud.tencent.com/document/product/1823/130050) for details.
|
|
32
|
+
|
|
33
|
+
## Models
|
|
34
|
+
|
|
35
|
+
| Model | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
|
|
36
|
+
| ------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
|
|
37
|
+
| `tencent-tokenhub/hy3-preview` | 256K | | | | | | — | — |
|
|
38
|
+
|
|
39
|
+
## Advanced configuration
|
|
40
|
+
|
|
41
|
+
### Custom headers
|
|
42
|
+
|
|
43
|
+
```typescript
|
|
44
|
+
const agent = new Agent({
|
|
45
|
+
id: "custom-agent",
|
|
46
|
+
name: "custom-agent",
|
|
47
|
+
model: {
|
|
48
|
+
url: "https://tokenhub.tencentmaas.com/v1",
|
|
49
|
+
id: "tencent-tokenhub/hy3-preview",
|
|
50
|
+
apiKey: process.env.TENCENT_TOKENHUB_API_KEY,
|
|
51
|
+
headers: {
|
|
52
|
+
"X-Custom-Header": "value"
|
|
53
|
+
}
|
|
54
|
+
}
|
|
55
|
+
});
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
### Dynamic model selection
|
|
59
|
+
|
|
60
|
+
```typescript
|
|
61
|
+
const agent = new Agent({
|
|
62
|
+
id: "dynamic-agent",
|
|
63
|
+
name: "Dynamic Agent",
|
|
64
|
+
model: ({ requestContext }) => {
|
|
65
|
+
const useAdvanced = requestContext.task === "complex";
|
|
66
|
+
return useAdvanced
|
|
67
|
+
? "tencent-tokenhub/hy3-preview"
|
|
68
|
+
: "tencent-tokenhub/hy3-preview";
|
|
69
|
+
}
|
|
70
|
+
});
|
|
71
|
+
```
|
|
@@ -26,6 +26,7 @@ Direct access to individual AI model providers. Each provider offers unique mode
|
|
|
26
26
|
- [Cortecs](https://mastra.ai/models/providers/cortecs)
|
|
27
27
|
- [D.Run (China)](https://mastra.ai/models/providers/drun)
|
|
28
28
|
- [Deep Infra](https://mastra.ai/models/providers/deepinfra)
|
|
29
|
+
- [DigitalOcean](https://mastra.ai/models/providers/digitalocean)
|
|
29
30
|
- [DInference](https://mastra.ai/models/providers/dinference)
|
|
30
31
|
- [evroc](https://mastra.ai/models/providers/evroc)
|
|
31
32
|
- [FastRouter](https://mastra.ai/models/providers/fastrouter)
|
|
@@ -83,6 +84,8 @@ Direct access to individual AI model providers. Each provider offers unique mode
|
|
|
83
84
|
- [submodel](https://mastra.ai/models/providers/submodel)
|
|
84
85
|
- [Synthetic](https://mastra.ai/models/providers/synthetic)
|
|
85
86
|
- [Tencent Coding Plan (China)](https://mastra.ai/models/providers/tencent-coding-plan)
|
|
87
|
+
- [Tencent Token Plan](https://mastra.ai/models/providers/tencent-token-plan)
|
|
88
|
+
- [Tencent TokenHub](https://mastra.ai/models/providers/tencent-tokenhub)
|
|
86
89
|
- [The Grid AI](https://mastra.ai/models/providers/the-grid-ai)
|
|
87
90
|
- [Together AI](https://mastra.ai/models/providers/togetherai)
|
|
88
91
|
- [Upstage](https://mastra.ai/models/providers/upstage)
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# NetlifyDeployer
|
|
2
2
|
|
|
3
|
-
The `NetlifyDeployer` class handles packaging, configuration, and deployment by adapting Mastra's output to create an optimized version of your server. It extends the base [`Deployer`](https://mastra.ai/reference/deployer) class with Netlify
|
|
3
|
+
The `NetlifyDeployer` class handles packaging, configuration, and deployment by adapting Mastra's output to create an optimized version of your server. It extends the base [`Deployer`](https://mastra.ai/reference/deployer) class with Netlify-specific functionality. It enables you to run Mastra within Netlify serverless functions or edge functions.
|
|
4
4
|
|
|
5
5
|
## Installation
|
|
6
6
|
|
|
@@ -43,9 +43,31 @@ export const mastra = new Mastra({
|
|
|
43
43
|
})
|
|
44
44
|
```
|
|
45
45
|
|
|
46
|
+
## Constructor options
|
|
47
|
+
|
|
48
|
+
- `target?: 'serverless' | 'edge'` — Deploy target for Netlify. Defaults to `'serverless'`.
|
|
49
|
+
|
|
50
|
+
- `'serverless'` — Standard [Netlify Functions](https://docs.netlify.com/functions/overview/) (Node.js runtime, 60s default timeout).
|
|
51
|
+
- `'edge'` — [Netlify Edge Functions](https://docs.netlify.com/build/edge-functions/overview/) (Deno-based runtime, runs at the edge closest to users, no hard timeout).
|
|
52
|
+
|
|
53
|
+
### Edge functions example
|
|
54
|
+
|
|
55
|
+
```typescript
|
|
56
|
+
import { Mastra } from '@mastra/core'
|
|
57
|
+
import { NetlifyDeployer } from '@mastra/deployer-netlify'
|
|
58
|
+
|
|
59
|
+
export const mastra = new Mastra({
|
|
60
|
+
deployer: new NetlifyDeployer({
|
|
61
|
+
target: 'edge',
|
|
62
|
+
}),
|
|
63
|
+
})
|
|
64
|
+
```
|
|
65
|
+
|
|
46
66
|
## Output
|
|
47
67
|
|
|
48
|
-
After running `mastra build`, the deployer generates a `.netlify` folder. The build output includes all agents, tools, and workflows of your project, alongside a
|
|
68
|
+
After running `mastra build`, the deployer generates a `.netlify` folder. The build output includes all agents, tools, and workflows of your project, alongside a `config.json` file that configures the [Netlify Frameworks API](https://docs.netlify.com/build/frameworks/frameworks-api/).
|
|
69
|
+
|
|
70
|
+
### Serverless output (default)
|
|
49
71
|
|
|
50
72
|
```bash
|
|
51
73
|
your-project/
|
|
@@ -77,4 +99,30 @@ The `config.json` file contains:
|
|
|
77
99
|
}
|
|
78
100
|
]
|
|
79
101
|
}
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
### Edge output
|
|
105
|
+
|
|
106
|
+
```bash
|
|
107
|
+
your-project/
|
|
108
|
+
└── .netlify/
|
|
109
|
+
└── v1/
|
|
110
|
+
├── config.json
|
|
111
|
+
└── edge-functions/
|
|
112
|
+
├── index.mjs
|
|
113
|
+
├── package.json
|
|
114
|
+
└── node_modules/
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
The `config.json` file contains:
|
|
118
|
+
|
|
119
|
+
```json
|
|
120
|
+
{
|
|
121
|
+
"edge_functions": [
|
|
122
|
+
{
|
|
123
|
+
"function": "index",
|
|
124
|
+
"path": "/*"
|
|
125
|
+
}
|
|
126
|
+
]
|
|
127
|
+
}
|
|
80
128
|
```
|
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,12 @@
|
|
|
1
1
|
# @mastra/mcp-docs-server
|
|
2
2
|
|
|
3
|
+
## 1.1.26-alpha.12
|
|
4
|
+
|
|
5
|
+
### Patch Changes
|
|
6
|
+
|
|
7
|
+
- Updated dependencies [[`6315317`](https://github.com/mastra-ai/mastra/commit/63153175fe9a7b224e5be7c209bbebc01dd9b0d5), [`9d3b24b`](https://github.com/mastra-ai/mastra/commit/9d3b24b19407ae9c09586cf7766d38dc4dff4a69)]:
|
|
8
|
+
- @mastra/core@1.26.0-alpha.6
|
|
9
|
+
|
|
3
10
|
## 1.1.26-alpha.9
|
|
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": "1.1.26-alpha.
|
|
3
|
+
"version": "1.1.26-alpha.13",
|
|
4
4
|
"description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -30,7 +30,7 @@
|
|
|
30
30
|
"local-pkg": "^1.1.2",
|
|
31
31
|
"zod": "^4.3.6",
|
|
32
32
|
"@mastra/mcp": "^1.5.1-alpha.1",
|
|
33
|
-
"@mastra/core": "1.26.0-alpha.
|
|
33
|
+
"@mastra/core": "1.26.0-alpha.6"
|
|
34
34
|
},
|
|
35
35
|
"devDependencies": {
|
|
36
36
|
"@hono/node-server": "^1.19.11",
|
|
@@ -48,7 +48,7 @@
|
|
|
48
48
|
"vitest": "4.0.18",
|
|
49
49
|
"@internal/lint": "0.0.83",
|
|
50
50
|
"@internal/types-builder": "0.0.58",
|
|
51
|
-
"@mastra/core": "1.26.0-alpha.
|
|
51
|
+
"@mastra/core": "1.26.0-alpha.6"
|
|
52
52
|
},
|
|
53
53
|
"homepage": "https://mastra.ai",
|
|
54
54
|
"repository": {
|