@mastra/mcp-docs-server 1.2.27-alpha.19 → 1.2.27-alpha.22
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/mastra-platform/deploy.md +1 -1
- package/.docs/docs/mastra-platform/system-environment-variables.md +0 -1
- package/.docs/docs/studio/overview.md +2 -0
- package/.docs/integrations/agentic-ui/ai-sdk-ui.md +12 -1
- package/.docs/models/gateways/netlify.md +1 -2
- package/.docs/models/gateways/openrouter.md +1 -2
- package/.docs/models/gateways/vercel.md +1 -1
- package/.docs/models/index.md +1 -1
- package/.docs/models/providers/cortecs.md +1 -1
- package/.docs/models/providers/crossmodel.md +2 -1
- package/.docs/models/providers/kilo.md +11 -12
- package/.docs/models/providers/llmgateway-providers.md +3 -1
- package/.docs/models/providers/nano-gpt.md +9 -10
- package/.docs/models/providers/opencode-go.md +2 -2
- package/.docs/models/providers/opencode.md +1 -4
- package/.docs/models/providers/vivgrid.md +1 -2
- package/.docs/reference/cli/mastra.md +2 -2
- package/.docs/reference/pubsub/redis-streams.md +1 -11
- package/package.json +4 -4
|
@@ -50,7 +50,7 @@ A local `.env` file is optional. Environment variables stored on the platform ar
|
|
|
50
50
|
|
|
51
51
|
The environment slug (`production` above) matches the environment the CLI would have deployed to. The `mastra env db create` command requires an environment argument in non-interactive shells when the project has more than one environment.
|
|
52
52
|
|
|
53
|
-
Preflight also catches database URLs that point at your local machine. A `.env` file with `
|
|
53
|
+
Preflight also catches database URLs that point at your local machine. A `.env` file with `DATABASE_URL=postgres://localhost:5432/myapp` works during development, but the deployed server can't reach your laptop. The CLI therefore warns and offers the same managed provisioning. If you decline, the deploy continues with your value as-is; if you accept, the managed database's connection variables take precedence at deploy time while your local `.env` keeps working for development.
|
|
54
54
|
|
|
55
55
|
> **Note:** If preflight reports a hard-coded local path instead (`Build contains a host-local storage URL`), it can't offer the inline fix. Guard the path with an environment variable first so the file is only used during local development:
|
|
56
56
|
>
|
|
@@ -38,7 +38,6 @@ Attaching a hosted database adds its connection variables to the environments th
|
|
|
38
38
|
| Turso | `TURSO_DATABASE_URL`, `TURSO_AUTH_TOKEN` |
|
|
39
39
|
| Neon | `DATABASE_URL` |
|
|
40
40
|
| Postgres | `POSTGRES_URL` |
|
|
41
|
-
| Redis | `REDIS_URL` |
|
|
42
41
|
|
|
43
42
|
Values are resolved at deploy time and never stored in your project. An environment-scoped database replaces the values of a project-scoped database of the same provider for that environment.
|
|
44
43
|
|
|
@@ -73,6 +73,8 @@ Visualize your workflow as a graph and run it step by step with a custom input.
|
|
|
73
73
|
|
|
74
74
|
Workflow traces show tool calls and raw JSON outputs, along with any execution errors.
|
|
75
75
|
|
|
76
|
+
Select **Run Options** beside the run button to set a **Resource ID** for the runs you start. Studio remembers the value per workflow, and the runs it creates are listed by `GET /api/workflows/:workflowId/runs?resourceId=...`. Leave it empty to create runs without a resource. When your server derives the resource ID from the authenticated user, that value takes precedence over the one you type.
|
|
77
|
+
|
|
76
78
|
### Processors
|
|
77
79
|
|
|
78
80
|
View the input and output processors attached to each agent. The agent detail panel lists every processor by name and type, so you can verify your guardrails and token limiters, plus custom processors are wired up correctly before testing.
|
|
@@ -1262,6 +1262,14 @@ For a complete implementation, see the [workflow-suspend-resume example](https:/
|
|
|
1262
1262
|
|
|
1263
1263
|
Tools can call agents internally and stream the agent's output back to the UI. This creates compact `data-tool-agent` snapshots while the nested step is still running, `data-tool-agent-step` parts when a nested step finishes, and one full `data-tool-agent` snapshot when the nested run finishes.
|
|
1264
1264
|
|
|
1265
|
+
Both part types include delegation metadata for nested supervisor chains:
|
|
1266
|
+
|
|
1267
|
+
- `ancestry`: The delegation path in outer-to-inner order. Each entry contains a `toolCallId` and may include the `toolName` and normalized `agentId`.
|
|
1268
|
+
- `depth`: The number of known agent delegation boundaries. A direct subagent has depth `1`.
|
|
1269
|
+
- `parentAgentId`: The immediate parent agent ID for a nested agent. This field is omitted for a direct subagent because the root supervisor ID isn't part of the tool envelope.
|
|
1270
|
+
|
|
1271
|
+
The part `id` remains the nested agent run ID, so progressive snapshots replace the same UI state as the run continues.
|
|
1272
|
+
|
|
1265
1273
|
The pattern uses:
|
|
1266
1274
|
|
|
1267
1275
|
- `context.mastra.getAgent()` - Get an agent instance from within a tool
|
|
@@ -1357,10 +1365,12 @@ export function NestedAgentChat() {
|
|
|
1357
1365
|
return <p key={index}>{part.text}</p>
|
|
1358
1366
|
}
|
|
1359
1367
|
if (part.type === 'data-tool-agent') {
|
|
1360
|
-
const { id, data } = part as AgentDataPart
|
|
1368
|
+
const { id, data, depth, parentAgentId } = part as AgentDataPart
|
|
1361
1369
|
return (
|
|
1362
1370
|
<div key={index} className="nested-agent">
|
|
1363
1371
|
<strong>Nested Agent: {id}</strong>
|
|
1372
|
+
<p>Delegation depth: {depth}</p>
|
|
1373
|
+
{parentAgentId && <p>Parent agent: {parentAgentId}</p>}
|
|
1364
1374
|
{data.text && <p>{data.text}</p>}
|
|
1365
1375
|
{data.toolErrors?.map(toolError => (
|
|
1366
1376
|
<p key={toolError.toolCallId} className="nested-agent-error">
|
|
@@ -1392,6 +1402,7 @@ Key points:
|
|
|
1392
1402
|
|
|
1393
1403
|
- Piping `fullStream` to `context.writer` creates `data-tool-agent` parts
|
|
1394
1404
|
- Read `data-tool-agent-step` when you need the full payload for the nested step that finished
|
|
1405
|
+
- `AgentDataPart` and `AgentStepDataPart` include the same `ancestry`, `depth`, and optional `parentAgentId` fields
|
|
1395
1406
|
- The `AgentDataPart` has `id` (on the part) and `data.text` (the current nested-agent text snapshot)
|
|
1396
1407
|
- A tool that throws inside the nested agent is reported in `data.toolErrors`, each entry `{ toolCallId, toolName, args?, errorText, providerExecuted? }`. `errorText` is a JSON-safe string, so the failure survives serialization to the client instead of arriving as `{}`
|
|
1397
1408
|
- `toolErrors` resets at each nested step boundary, like `toolCalls` and `toolResults`. For a finished step, read it from `data-tool-agent-step` (`data.step.toolErrors`) or from `data.steps[]` on the final snapshot
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Netlify
|
|
6
6
|
|
|
7
|
-
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access
|
|
7
|
+
Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 260 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
|
|
10
10
|
|
|
@@ -145,7 +145,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
145
145
|
| `openrouter/deepseek/deepseek-v3.2-exp` |
|
|
146
146
|
| `openrouter/deepseek/deepseek-v4-flash` |
|
|
147
147
|
| `openrouter/deepseek/deepseek-v4-flash-0731` |
|
|
148
|
-
| `openrouter/deepseek/deepseek-v4-flash-0731:free` |
|
|
149
148
|
| `openrouter/deepseek/deepseek-v4-flash-vision-exp` |
|
|
150
149
|
| `openrouter/deepseek/deepseek-v4-pro` |
|
|
151
150
|
| `openrouter/deepseek/deepseek-v4-pro-0813` |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# OpenRouter
|
|
6
6
|
|
|
7
|
-
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access
|
|
7
|
+
OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 371 models through Mastra's model router.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
|
|
10
10
|
|
|
@@ -107,7 +107,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
107
107
|
| `deepseek/deepseek-v3.2-exp` |
|
|
108
108
|
| `deepseek/deepseek-v4-flash` |
|
|
109
109
|
| `deepseek/deepseek-v4-flash-0731` |
|
|
110
|
-
| `deepseek/deepseek-v4-flash-0731:free` |
|
|
111
110
|
| `deepseek/deepseek-v4-flash-vision-exp` |
|
|
112
111
|
| `deepseek/deepseek-v4-pro` |
|
|
113
112
|
| `deepseek/deepseek-v4-pro-0813` |
|
|
@@ -374,6 +374,7 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
374
374
|
| `spacexai/grok-voice-think-fast-2.0` |
|
|
375
375
|
| `stepfun/step-3.5-flash` |
|
|
376
376
|
| `stepfun/step-3.7-flash` |
|
|
377
|
+
| `stepfun/step-5-preview` |
|
|
377
378
|
| `tencent/hy-mt2-lite` |
|
|
378
379
|
| `tencent/hy-mt2-plus` |
|
|
379
380
|
| `tencent/hy-mt2-pro` |
|
|
@@ -381,7 +382,6 @@ ANTHROPIC_API_KEY=ant-...
|
|
|
381
382
|
| `tencent/hy4-preview` |
|
|
382
383
|
| `thinkingmachines/inkling` |
|
|
383
384
|
| `thinkingmachines/inkling-small` |
|
|
384
|
-
| `typesafe-ai/jev` |
|
|
385
385
|
| `voyage/rerank-2.5` |
|
|
386
386
|
| `voyage/rerank-2.5-lite` |
|
|
387
387
|
| `voyage/voyage-3-large` |
|
package/.docs/models/index.md
CHANGED
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Model Providers
|
|
6
6
|
|
|
7
|
-
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to
|
|
7
|
+
Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 7364 models from 209 providers through a single API.
|
|
8
8
|
|
|
9
9
|
## Features
|
|
10
10
|
|
|
@@ -129,7 +129,7 @@ for await (const chunk of stream) {
|
|
|
129
129
|
| `cortecs/qwen2.5-vl-72b-instruct` | 32K | | | | | | $1 | $1 |
|
|
130
130
|
| `cortecs/qwen3-235b-a22b-instruct-2507` | 262K | | | | | | $0.07 | $0.46 |
|
|
131
131
|
| `cortecs/qwen3-30b-a3b-instruct-2507` | 262K | | | | | | $0.10 | $0.30 |
|
|
132
|
-
| `cortecs/qwen3-32b` |
|
|
132
|
+
| `cortecs/qwen3-32b` | 16K | | | | | | $0.18 | $0.70 |
|
|
133
133
|
| `cortecs/qwen3-coder-30b-a3b-instruct` | 262K | | | | | | $0.07 | $0.24 |
|
|
134
134
|
| `cortecs/qwen3-coder-next` | 256K | | | | | | $0.17 | $0.89 |
|
|
135
135
|
| `cortecs/qwen3-vl-235b-a22b` | 256K | | | | | | $0.62 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# CrossModel
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 60 CrossModel models through Mastra's model router. Authentication is handled automatically using the `CROSSMODEL_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [CrossModel documentation](https://www.crossmodel.ai/docs).
|
|
10
10
|
|
|
@@ -82,6 +82,7 @@ for await (const chunk of stream) {
|
|
|
82
82
|
| `crossmodel/qwen/qwen3.7-plus` | 1.0M | | | | | | $0.32 | $1 |
|
|
83
83
|
| `crossmodel/qwen/qwen3.8-flash` | 1.0M | | | | | | $0.13 | $0.43 |
|
|
84
84
|
| `crossmodel/qwen/qwen3.8-max` | 1.0M | | | | | | $2 | $6 |
|
|
85
|
+
| `crossmodel/qwen/qwen3.8-omni-flash` | 1.0M | | | | | | $0.13 | $0.43 |
|
|
85
86
|
| `crossmodel/tencent/hy3` | 262K | | | | | | $0.16 | $0.64 |
|
|
86
87
|
| `crossmodel/tencent/hy4-preview` | 1.0M | | | | | | $0.96 | $3 |
|
|
87
88
|
| `crossmodel/x-ai/grok-4.3` | 1.0M | | | | | | $1 | $3 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Kilo Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 378 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Kilo Gateway documentation](https://kilo.ai).
|
|
10
10
|
|
|
@@ -42,9 +42,9 @@ for await (const chunk of stream) {
|
|
|
42
42
|
| `kilo/~anthropic/claude-haiku-latest` | 200K | | | | | | $1 | $5 |
|
|
43
43
|
| `kilo/~anthropic/claude-opus-latest` | 1.0M | | | | | | $5 | $25 |
|
|
44
44
|
| `kilo/~anthropic/claude-sonnet-latest` | 1.0M | | | | | | $2 | $10 |
|
|
45
|
-
| `kilo/~deepseek/deepseek-flash-latest` | 1.0M | | | | | | $0.
|
|
46
|
-
| `kilo/~deepseek/deepseek-pro-latest` | 1.0M | | | | | | $0.
|
|
47
|
-
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.
|
|
45
|
+
| `kilo/~deepseek/deepseek-flash-latest` | 1.0M | | | | | | $0.12 | $0.48 |
|
|
46
|
+
| `kilo/~deepseek/deepseek-pro-latest` | 1.0M | | | | | | $0.66 | $2 |
|
|
47
|
+
| `kilo/~deepseek/deepseek-v4-flash-latest` | 1.0M | | | | | | $0.04 | $0.16 |
|
|
48
48
|
| `kilo/~google/gemini-flash-latest` | 1.0M | | | | | | $0.75 | $4 |
|
|
49
49
|
| `kilo/~google/gemini-pro-latest` | 1.0M | | | | | | $2 | $12 |
|
|
50
50
|
| `kilo/~moonshotai/kimi-latest` | 1.0M | | | | | | $2 | $9 |
|
|
@@ -55,7 +55,7 @@ for await (const chunk of stream) {
|
|
|
55
55
|
| `kilo/~openai/gpt-terra-latest` | 1.1M | | | | | | $2 | $12 |
|
|
56
56
|
| `kilo/~x-ai/grok-latest` | 500K | | | | | | $2 | $6 |
|
|
57
57
|
| `kilo/~z-ai/glm-flash-latest` | 1.0M | | | | | | $0.07 | $0.25 |
|
|
58
|
-
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.
|
|
58
|
+
| `kilo/~z-ai/glm-latest` | 1.0M | | | | | | $0.77 | $2 |
|
|
59
59
|
| `kilo/aion-labs/aion-2.0` | 131K | | | | | | $0.80 | $2 |
|
|
60
60
|
| `kilo/aion-labs/aion-3.0` | 131K | | | | | | $3 | $6 |
|
|
61
61
|
| `kilo/aion-labs/aion-3.0-mini` | 131K | | | | | | $0.70 | $1 |
|
|
@@ -107,7 +107,6 @@ for await (const chunk of stream) {
|
|
|
107
107
|
| `kilo/deepseek/deepseek-v3.2-exp` | 164K | | | | | | $0.27 | $0.41 |
|
|
108
108
|
| `kilo/deepseek/deepseek-v4-flash` | 1.0M | | | | | | $0.14 | $0.28 |
|
|
109
109
|
| `kilo/deepseek/deepseek-v4-flash-0731` | 1.0M | | | | | | $0.44 | $1 |
|
|
110
|
-
| `kilo/deepseek/deepseek-v4-flash-0731:free` | 1.0M | | | | | | — | — |
|
|
111
110
|
| `kilo/deepseek/deepseek-v4-flash-vision-exp` | 1.0M | | | | | | $0.44 | $1 |
|
|
112
111
|
| `kilo/deepseek/deepseek-v4-pro` | 1.0M | | | | | | $2 | $3 |
|
|
113
112
|
| `kilo/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -169,7 +168,7 @@ for await (const chunk of stream) {
|
|
|
169
168
|
| `kilo/meta-llama/llama-3.2-1b-instruct` | 60K | | | | | | $0.03 | $0.20 |
|
|
170
169
|
| `kilo/meta-llama/llama-3.2-3b-instruct` | 131K | | | | | | $0.05 | $0.33 |
|
|
171
170
|
| `kilo/meta-llama/llama-3.3-70b-instruct` | 131K | | | | | | $0.10 | $0.32 |
|
|
172
|
-
| `kilo/meta-llama/llama-4-maverick` |
|
|
171
|
+
| `kilo/meta-llama/llama-4-maverick` | 1.0M | | | | | | $0.19 | $0.65 |
|
|
173
172
|
| `kilo/meta-llama/llama-4-scout` | 328K | | | | | | $0.10 | $0.30 |
|
|
174
173
|
| `kilo/meta-llama/llama-guard-4-12b` | 164K | | | | | | $0.18 | $0.18 |
|
|
175
174
|
| `kilo/meta/muse-glimmer-30b` | 131K | | | | | | $0.30 | $1 |
|
|
@@ -228,7 +227,7 @@ for await (const chunk of stream) {
|
|
|
228
227
|
| `kilo/nvidia/nemotron-3-ultra-550b-a55b:free` | 1.0M | | | | | | — | — |
|
|
229
228
|
| `kilo/nvidia/nemotron-3.5-content-safety` | 131K | | | | | | $0.20 | $0.20 |
|
|
230
229
|
| `kilo/nvidia/nemotron-3.5-content-safety:free` | 128K | | | | | | — | — |
|
|
231
|
-
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.
|
|
230
|
+
| `kilo/nvidia/nemotron-3.5-lightning` | 262K | | | | | | $0.07 | $0.18 |
|
|
232
231
|
| `kilo/nvidia/nemotron-3.5-lightning:free` | 1.0M | | | | | | — | — |
|
|
233
232
|
| `kilo/openai/gpt-3.5-turbo` | 16K | | | | | | $0.50 | $2 |
|
|
234
233
|
| `kilo/openai/gpt-3.5-turbo-0613` | 4K | | | | | | $1 | $2 |
|
|
@@ -337,14 +336,14 @@ for await (const chunk of stream) {
|
|
|
337
336
|
| `kilo/qwen/qwen3-vl-8b-thinking` | 131K | | | | | | $0.18 | $2 |
|
|
338
337
|
| `kilo/qwen/qwen3.5-122b-a10b` | 262K | | | | | | $0.26 | $2 |
|
|
339
338
|
| `kilo/qwen/qwen3.5-27b` | 262K | | | | | | $0.20 | $2 |
|
|
340
|
-
| `kilo/qwen/qwen3.5-35b-a3b` |
|
|
339
|
+
| `kilo/qwen/qwen3.5-35b-a3b` | 256K | | | | | | $0.16 | $1 |
|
|
341
340
|
| `kilo/qwen/qwen3.5-397b-a17b` | 262K | | | | | | $0.39 | $2 |
|
|
342
|
-
| `kilo/qwen/qwen3.5-9b` |
|
|
341
|
+
| `kilo/qwen/qwen3.5-9b` | 256K | | | | | | $0.10 | $0.15 |
|
|
343
342
|
| `kilo/qwen/qwen3.5-flash-02-23` | 1.0M | | | | | | $0.07 | $0.26 |
|
|
344
343
|
| `kilo/qwen/qwen3.5-plus-02-15` | 1.0M | | | | | | $0.26 | $2 |
|
|
345
344
|
| `kilo/qwen/qwen3.5-plus-20260420` | 1.0M | | | | | | $0.30 | $2 |
|
|
346
345
|
| `kilo/qwen/qwen3.6-27b` | 262K | | | | | | $0.45 | $3 |
|
|
347
|
-
| `kilo/qwen/qwen3.6-35b-a3b` | 262K | | | | | | $0.
|
|
346
|
+
| `kilo/qwen/qwen3.6-35b-a3b` | 262K | | | | | | $0.15 | $1 |
|
|
348
347
|
| `kilo/qwen/qwen3.6-flash` | 1.0M | | | | | | $0.19 | $1 |
|
|
349
348
|
| `kilo/qwen/qwen3.6-max-preview` | 262K | | | | | | $1 | $6 |
|
|
350
349
|
| `kilo/qwen/qwen3.6-plus` | 1.0M | | | | | | $0.33 | $2 |
|
|
@@ -379,7 +378,7 @@ for await (const chunk of stream) {
|
|
|
379
378
|
| `kilo/tencent/hy-mt2-1.8b` | 8K | | | | | | $0.04 | $0.18 |
|
|
380
379
|
| `kilo/tencent/hy-mt2-30b-a3b` | 8K | | | | | | $0.07 | $0.29 |
|
|
381
380
|
| `kilo/tencent/hy-mt2-7b` | 8K | | | | | | $0.07 | $0.29 |
|
|
382
|
-
| `kilo/tencent/hy3` | 262K | | | | | | $0.
|
|
381
|
+
| `kilo/tencent/hy3` | 262K | | | | | | $0.13 | $0.53 |
|
|
383
382
|
| `kilo/tencent/hy3-preview` | 262K | | | | | | $0.18 | $0.60 |
|
|
384
383
|
| `kilo/tencent/hy4-preview` | 1.0M | | | | | | $0.83 | $3 |
|
|
385
384
|
| `kilo/thedrummer/cydonia-24b-v4.1` | 131K | | | | | | $0.30 | $0.50 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# LLM Gateway
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 404 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
|
|
10
10
|
|
|
@@ -146,6 +146,7 @@ for await (const chunk of stream) {
|
|
|
146
146
|
| `llmgateway-providers/azure/o4-mini` | 200K | | | | | | $1 | $4 |
|
|
147
147
|
| `llmgateway-providers/baidu/deepseek-v4-flash` | 1.0M | | | | | | $0.44 | $1 |
|
|
148
148
|
| `llmgateway-providers/baidu/deepseek-v4-pro` | 1.0M | | | | | | $1 | $4 |
|
|
149
|
+
| `llmgateway-providers/baidu/deepseek-v4.1-flash` | 1.0M | | | | | | $0.30 | $1 |
|
|
149
150
|
| `llmgateway-providers/baidu/glm-5` | 203K | | | | | | $1 | $3 |
|
|
150
151
|
| `llmgateway-providers/baidu/glm-5.1` | 203K | | | | | | $1 | $4 |
|
|
151
152
|
| `llmgateway-providers/baidu/glm-5.2` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -361,6 +362,7 @@ for await (const chunk of stream) {
|
|
|
361
362
|
| `llmgateway-providers/sakana/fugu-max` | 1.0M | | | | | | $2 | $6 |
|
|
362
363
|
| `llmgateway-providers/sakana/fugu-ultra` | 1.0M | | | | | | $5 | $30 |
|
|
363
364
|
| `llmgateway-providers/sakana/fugu-ultra-v2.0` | 1.0M | | | | | | $5 | $30 |
|
|
365
|
+
| `llmgateway-providers/scx-ai-gp/deepseek-v4.1-flash` | 1.0M | | | | | | $0.15 | $0.60 |
|
|
364
366
|
| `llmgateway-providers/scx-ai-gp/glm-5.2` | 1.0M | | | | | | $0.88 | $3 |
|
|
365
367
|
| `llmgateway-providers/scx-ai-gp/glm-5.2-fast` | 1.0M | | | | | | $2 | $7 |
|
|
366
368
|
| `llmgateway-providers/scx-ai-gp/glm-5.3` | 1.0M | | | | | | $1 | $4 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# NanoGPT
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 576 NanoGPT models through Mastra's model router. Authentication is handled automatically using the `NANO_GPT_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [NanoGPT documentation](https://docs.nano-gpt.com).
|
|
10
10
|
|
|
@@ -141,8 +141,8 @@ for await (const chunk of stream) {
|
|
|
141
141
|
| `nano-gpt/deepseek/deepseek-v4-pro-0813` | 1.0M | | | | | | $1 | $3 |
|
|
142
142
|
| `nano-gpt/deepseek/deepseek-v4-pro-0813:thinking` | 1.0M | | | | | | $1 | $3 |
|
|
143
143
|
| `nano-gpt/deepseek/deepseek-v4-pro:thinking` | 1.0M | | | | | | $1 | $2 |
|
|
144
|
-
| `nano-gpt/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.
|
|
145
|
-
| `nano-gpt/deepseek/deepseek-v4.1-flash:thinking` | 1.0M | | | | | | $0.
|
|
144
|
+
| `nano-gpt/deepseek/deepseek-v4.1-flash` | 1.0M | | | | | | $0.13 | $0.52 |
|
|
145
|
+
| `nano-gpt/deepseek/deepseek-v4.1-flash:thinking` | 1.0M | | | | | | $0.13 | $0.52 |
|
|
146
146
|
| `nano-gpt/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond` | 33K | | | | | | $0.49 | $0.49 |
|
|
147
147
|
| `nano-gpt/doubao-1.5-pro-256k` | 256K | | | | | | $0.80 | $1 |
|
|
148
148
|
| `nano-gpt/doubao-1.5-pro-32k` | 32K | | | | | | $0.13 | $0.33 |
|
|
@@ -440,7 +440,7 @@ for await (const chunk of stream) {
|
|
|
440
440
|
| `nano-gpt/qwen/qwen3-max-2026-01-23` | 256K | | | | | | $1 | $6 |
|
|
441
441
|
| `nano-gpt/qwen/qwen3-next-80b-a3b-instruct` | 262K | | | | | | $0.15 | $0.65 |
|
|
442
442
|
| `nano-gpt/qwen/qwen3-next-80b-a3b-thinking` | 256K | | | | | | $0.15 | $0.65 |
|
|
443
|
-
| `nano-gpt/qwen/qwen3-vl-235b-a22b-instruct` | 131K | | | | | | $0.30 | $
|
|
443
|
+
| `nano-gpt/qwen/qwen3-vl-235b-a22b-instruct` | 131K | | | | | | $0.30 | $2 |
|
|
444
444
|
| `nano-gpt/qwen/qwen3-vl-235b-a22b-thinking` | 131K | | | | | | $0.50 | $6 |
|
|
445
445
|
| `nano-gpt/qwen/qwen3.5-122b-a10b` | 131K | | | | | | $0.44 | $3 |
|
|
446
446
|
| `nano-gpt/qwen/qwen3.5-122b-a10b:thinking` | 131K | | | | | | $0.44 | $3 |
|
|
@@ -473,18 +473,19 @@ for await (const chunk of stream) {
|
|
|
473
473
|
| `nano-gpt/qwen/qwen3.8-27b` | 262K | | | | | | $0.15 | $0.70 |
|
|
474
474
|
| `nano-gpt/qwen/qwen3.8-27b-cybersecurity` | 262K | | | | | | $0.10 | $0.60 |
|
|
475
475
|
| `nano-gpt/qwen/qwen3.8-27b-fable` | 524K | | | | | | $0.25 | $2 |
|
|
476
|
+
| `nano-gpt/qwen/qwen3.8-27b-hemmingway` | 262K | | | | | | $0.25 | $2 |
|
|
476
477
|
| `nano-gpt/qwen/qwen3.8-27b-obliterated` | 524K | | | | | | $0.25 | $2 |
|
|
477
478
|
| `nano-gpt/qwen/qwen3.8-27b-obliterated:thinking` | 524K | | | | | | $0.25 | $2 |
|
|
478
479
|
| `nano-gpt/qwen/qwen3.8-27b-queen` | 524K | | | | | | $0.25 | $2 |
|
|
479
|
-
| `nano-gpt/qwen/qwen3.8-27b-uncensored` | 524K | | | | | | $0.
|
|
480
|
-
| `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking` | 524K | | | | | | $0.
|
|
480
|
+
| `nano-gpt/qwen/qwen3.8-27b-uncensored` | 524K | | | | | | $0.15 | $1 |
|
|
481
|
+
| `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking` | 524K | | | | | | $0.15 | $1 |
|
|
481
482
|
| `nano-gpt/qwen/qwen3.8-27b:thinking` | 262K | | | | | | $0.15 | $0.70 |
|
|
482
483
|
| `nano-gpt/qwen/qwen3.8-flash` | 992K | | | | | | $0.14 | $0.42 |
|
|
483
484
|
| `nano-gpt/qwen/qwen3.8-max` | 991K | | | | | | $2 | $6 |
|
|
484
485
|
| `nano-gpt/qwen/qwen3.8-max-0902` | 992K | | | | | | $2 | $6 |
|
|
485
486
|
| `nano-gpt/qwen/qwen3.8-max:thinking` | 991K | | | | | | $2 | $6 |
|
|
486
487
|
| `nano-gpt/qwen/qwen3.8-omni-flash` | 992K | | | | | | $0.15 | $0.47 |
|
|
487
|
-
| `nano-gpt/qwen3-vl-235b-a22b-instruct-original` | 33K | | | | | | $0.
|
|
488
|
+
| `nano-gpt/qwen3-vl-235b-a22b-instruct-original` | 33K | | | | | | $0.30 | $2 |
|
|
488
489
|
| `nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted` | 262K | | | | | | $0.31 | $0.31 |
|
|
489
490
|
| `nano-gpt/Qwen3.5-27B-Queen-Derestricted` | 262K | | | | | | $0.31 | $0.31 |
|
|
490
491
|
| `nano-gpt/ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0` | 33K | | | | | | $0.50 | $0.50 |
|
|
@@ -509,8 +510,8 @@ for await (const chunk of stream) {
|
|
|
509
510
|
| `nano-gpt/stepfun-ai/step-3.5-flash` | 262K | | | | | | $0.10 | $0.30 |
|
|
510
511
|
| `nano-gpt/stepfun-ai/step-3.5-flash-2603` | 262K | | | | | | $0.10 | $0.30 |
|
|
511
512
|
| `nano-gpt/stepfun/step-3.7-flash:thinking` | 262K | | | | | | $0.20 | $1 |
|
|
513
|
+
| `nano-gpt/stepfun/step-5-preview` | 1.0M | | | | | | $1 | $3 |
|
|
512
514
|
| `nano-gpt/TEE/deepseek-v3.2` | 164K | | | | | | $0.50 | $1 |
|
|
513
|
-
| `nano-gpt/TEE/deepseek-v4-flash` | 1.0M | | | | | | $0.20 | $0.40 |
|
|
514
515
|
| `nano-gpt/TEE/deepseek-v4.1-flash` | 1.0M | | | | | | $0.65 | $1 |
|
|
515
516
|
| `nano-gpt/TEE/gemma-4-26b-a4b-uncensored` | 66K | | | | | | $0.15 | $0.70 |
|
|
516
517
|
| `nano-gpt/TEE/gemma-4-31b-it` | 262K | | | | | | $0.15 | $0.46 |
|
|
@@ -592,8 +593,6 @@ for await (const chunk of stream) {
|
|
|
592
593
|
| `nano-gpt/z-ai/glm-4.6v-original` | 128K | | | | | | $0.60 | $0.90 |
|
|
593
594
|
| `nano-gpt/z-ai/glm-4.7` | 200K | | | | | | $0.20 | $0.80 |
|
|
594
595
|
| `nano-gpt/z-ai/glm-4.7-flash` | 200K | | | | | | $0.07 | $0.40 |
|
|
595
|
-
| `nano-gpt/z-ai/glm-4.7-flash-original` | 200K | | | | | | $0.07 | $0.40 |
|
|
596
|
-
| `nano-gpt/z-ai/glm-4.7-flash-original:thinking` | 200K | | | | | | $0.07 | $0.40 |
|
|
597
596
|
| `nano-gpt/z-ai/glm-4.7-flash:thinking` | 200K | | | | | | $0.07 | $0.40 |
|
|
598
597
|
| `nano-gpt/z-ai/glm-4.7-original` | 200K | | | | | | $0.60 | $2 |
|
|
599
598
|
| `nano-gpt/z-ai/glm-4.7-original:thinking` | 200K | | | | | | $0.60 | $2 |
|
|
@@ -6,7 +6,7 @@
|
|
|
6
6
|
|
|
7
7
|
Access 36 OpenCode Go models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
|
-
Learn more in the [OpenCode Go documentation](https://opencode.ai/docs/
|
|
9
|
+
Learn more in the [OpenCode Go documentation](https://opencode.ai/docs/go).
|
|
10
10
|
|
|
11
11
|
```bash
|
|
12
12
|
OPENCODE_API_KEY=your-api-key
|
|
@@ -32,7 +32,7 @@ for await (const chunk of stream) {
|
|
|
32
32
|
}
|
|
33
33
|
```
|
|
34
34
|
|
|
35
|
-
> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [OpenCode Go documentation](https://opencode.ai/docs/
|
|
35
|
+
> **Note:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [OpenCode Go documentation](https://opencode.ai/docs/go) for details.
|
|
36
36
|
|
|
37
37
|
## Models
|
|
38
38
|
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# OpenCode Zen
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 104 OpenCode Zen models through Mastra's model router. Authentication is handled automatically using the `OPENCODE_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [OpenCode Zen documentation](https://opencode.ai/docs/zen).
|
|
10
10
|
|
|
@@ -91,9 +91,6 @@ for await (const chunk of stream) {
|
|
|
91
91
|
| `opencode/grok-4.5` | 500K | | | | | | $2 | $6 |
|
|
92
92
|
| `opencode/grok-4.6` | 500K | | | | | | $2 | $6 |
|
|
93
93
|
| `opencode/grok-build-0.1` | 256K | | | | | | $1 | $2 |
|
|
94
|
-
| `opencode/jev-1.13` | 64K | | | | | | $0.04 | — |
|
|
95
|
-
| `opencode/jev-1.13-free` | 64K | | | | | | — | — |
|
|
96
|
-
| `opencode/jev-latest` | 64K | | | | | | $0.04 | — |
|
|
97
94
|
| `opencode/kimi-k2.5` | 262K | | | | | | $0.60 | $3 |
|
|
98
95
|
| `opencode/kimi-k2.6` | 262K | | | | | | $0.95 | $4 |
|
|
99
96
|
| `opencode/kimi-k2.7-code` | 262K | | | | | | $0.95 | $4 |
|
|
@@ -4,7 +4,7 @@
|
|
|
4
4
|
|
|
5
5
|
# Vivgrid
|
|
6
6
|
|
|
7
|
-
Access
|
|
7
|
+
Access 29 Vivgrid models through Mastra's model router. Authentication is handled automatically using the `VIVGRID_API_KEY` environment variable.
|
|
8
8
|
|
|
9
9
|
Learn more in the [Vivgrid documentation](https://docs.vivgrid.com/models).
|
|
10
10
|
|
|
@@ -66,7 +66,6 @@ for await (const chunk of stream) {
|
|
|
66
66
|
| `vivgrid/gpt-5.6-sol` | 1.1M | | | | | | $5 | $30 |
|
|
67
67
|
| `vivgrid/gpt-5.6-terra` | 1.1M | | | | | | $3 | $15 |
|
|
68
68
|
| `vivgrid/gpt-6-astra` | 1.1M | | | | | | $10 | $50 |
|
|
69
|
-
| `vivgrid/jev` | 64K | | | | | | $0.04 | — |
|
|
70
69
|
| `vivgrid/kimi-k3` | 1.0M | | | | | | $3 | $15 |
|
|
71
70
|
|
|
72
71
|
Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.
|
|
@@ -543,11 +543,11 @@ mastra env db create --kind neon --name my-app-db --region aws-us-east-1 --share
|
|
|
543
543
|
|
|
544
544
|
#### `--kind`
|
|
545
545
|
|
|
546
|
-
Database provider (required). One of `turso
|
|
546
|
+
Database provider (required). One of `turso` or `neon`.
|
|
547
547
|
|
|
548
548
|
#### `--name`
|
|
549
549
|
|
|
550
|
-
Database name. Defaults to a name derived from the project slug and provider (for example `my-app-turso` or `my-app-
|
|
550
|
+
Database name. Defaults to a name derived from the project slug and provider (for example `my-app-turso` or `my-app-pg`).
|
|
551
551
|
|
|
552
552
|
#### `--region`
|
|
553
553
|
|
|
@@ -177,14 +177,4 @@ A subscription never reclaims an event its own handler is still processing, so a
|
|
|
177
177
|
|
|
178
178
|
Lease keys are namespaced under the same `keyPrefix` as topics, as `<keyPrefix>:lease:<key>`. All operations are atomic: `acquireLease` uses `SET NX PX` and refreshes its own TTL idempotently, while `releaseLease`, `renewLease`, and `transferLease` use Lua scripts that check ownership before mutating, so a concurrent renewal from another owner is never clobbered.
|
|
179
179
|
|
|
180
|
-
You don't call these methods directly. Configuring `RedisStreamsPubSub` as the `pubsub` backend is enough for the runtime to detect and use the capability. See [`LeaseProvider`](https://mastra.ai/reference/pubsub/lease-provider) for the full method contract.
|
|
181
|
-
|
|
182
|
-
## Managed provisioning
|
|
183
|
-
|
|
184
|
-
When you deploy a project that reads `REDIS_URL` from the environment, the Mastra CLI's `deploy` preflight offers to attach a managed Redis on the Mastra platform in one step.
|
|
185
|
-
|
|
186
|
-
If you accept, `mastra deploy` provisions the database and waits for it to reach the ready state before injecting `REDIS_URL` into the deploy so `new RedisStreamsPubSub({ url: process.env.REDIS_URL })` connects without extra setup.
|
|
187
|
-
|
|
188
|
-
The prompt is shown only when three conditions hold: `REDIS_URL` is referenced by user code, the environment's value is missing or points to a localhost address, and the run is interactive (a terminal without the `--yes` flag). Non-interactive runs (CI, `--yes`) report the issue with a copy-pasteable `mastra env db create --kind redis` command instead of silently creating infrastructure.
|
|
189
|
-
|
|
190
|
-
You can also provision a managed Redis up front with `mastra env db create --kind redis`. Once attached, the platform meters CPU seconds and memory GB-hours and shows them on the project's Database Usage page.
|
|
180
|
+
You don't call these methods directly. Configuring `RedisStreamsPubSub` as the `pubsub` backend is enough for the runtime to detect and use the capability. See [`LeaseProvider`](https://mastra.ai/reference/pubsub/lease-provider) for the full method contract.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mastra/mcp-docs-server",
|
|
3
|
-
"version": "1.2.27-alpha.
|
|
3
|
+
"version": "1.2.27-alpha.22",
|
|
4
4
|
"description": "MCP server for accessing Mastra.ai documentation, changelogs, and news.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -27,7 +27,7 @@
|
|
|
27
27
|
"@modelcontextprotocol/sdk": "^1.27.1",
|
|
28
28
|
"local-pkg": "^1.1.2",
|
|
29
29
|
"zod": "^4.6.4",
|
|
30
|
-
"@mastra/core": "1.68.0-alpha.
|
|
30
|
+
"@mastra/core": "1.68.0-alpha.10"
|
|
31
31
|
},
|
|
32
32
|
"devDependencies": {
|
|
33
33
|
"@hono/node-server": "^2.0.0",
|
|
@@ -43,8 +43,8 @@
|
|
|
43
43
|
"typescript": "^7.0.2",
|
|
44
44
|
"vitest": "4.1.11",
|
|
45
45
|
"@internal/lint": "0.0.133",
|
|
46
|
-
"@
|
|
47
|
-
"@
|
|
46
|
+
"@mastra/core": "1.68.0-alpha.10",
|
|
47
|
+
"@internal/types-builder": "0.0.108"
|
|
48
48
|
},
|
|
49
49
|
"homepage": "https://mastra.ai",
|
|
50
50
|
"repository": {
|