@mastra/mcp-docs-server 1.3.6 → 1.3.7-alpha.3

package/.docs/models/providers/nano-gpt.md

@@ -129,7 +129,7 @@ for await (const chunk of stream) {
 | `nano-gpt/deepseek-reasoner`                                     | 64K     |       |           |       |       |       | $0.40      | $2          |
 | `nano-gpt/deepseek-reasoner-cheaper`                             | 128K    |       |           |       |       |       | $0.40      | $2          |
 | `nano-gpt/deepseek-v3-0324`                                      | 128K    |       |           |       |       |       | $0.20      | $0.77       |
-| `nano-gpt/deepseek/deepseek-latest`                              | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `nano-gpt/deepseek/deepseek-latest`                              | 1.0M    |       |           |       |       |       | $0.37      | $3          |
 | `nano-gpt/deepseek/deepseek-v3.2`                                | 163K    |       |           |       |       |       | $0.28      | $0.42       |
 | `nano-gpt/deepseek/deepseek-v3.2:thinking`                       | 163K    |       |           |       |       |       | $0.28      | $0.42       |
 | `nano-gpt/deepseek/deepseek-v4-flash`                            | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
@@ -141,8 +141,8 @@ for await (const chunk of stream) {
 | `nano-gpt/deepseek/deepseek-v4-flash-vision-exp`                 | 1.0M    |       |           |       |       |       | $0.22      | $0.66       |
 | `nano-gpt/deepseek/deepseek-v4-flash:thinking`                   | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
 | `nano-gpt/deepseek/deepseek-v4-pro`                              | 1.0M    |       |           |       |       |       | $1         | $2          |
-| `nano-gpt/deepseek/deepseek-v4-pro-0813`                         | 1.0M    |       |           |       |       |       | $1         | $3          |
-| `nano-gpt/deepseek/deepseek-v4-pro-0813:thinking`                | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `nano-gpt/deepseek/deepseek-v4-pro-0813`                         | 1.0M    |       |           |       |       |       | $0.37      | $3          |
+| `nano-gpt/deepseek/deepseek-v4-pro-0813:thinking`                | 1.0M    |       |           |       |       |       | $0.37      | $3          |
 | `nano-gpt/deepseek/deepseek-v4-pro:thinking`                     | 1.0M    |       |           |       |       |       | $1         | $2          |
 | `nano-gpt/deepseek/deepseek-v4.1-flash`                          | 1.0M    |       |           |       |       |       | $0.13      | $0.52       |
 | `nano-gpt/deepseek/deepseek-v4.1-flash:thinking`                 | 1.0M    |       |           |       |       |       | $0.13      | $0.52       |
@@ -284,7 +284,7 @@ for await (const chunk of stream) {
 | `nano-gpt/meta-llama/llama-3.1-8b-instruct`                      | 131K    |       |           |       |       |       | $0.05      | $0.09       |
 | `nano-gpt/meta-llama/llama-3.2-3b-instruct`                      | 131K    |       |           |       |       |       | $0.03      | $0.05       |
 | `nano-gpt/meta-llama/llama-3.3-70b-instruct`                     | 131K    |       |           |       |       |       | $0.05      | $0.23       |
-| `nano-gpt/meta-llama/llama-4-maverick`                           | 1.0M    |       |           |       |       |       | $0.15      | $0.60       |
+| `nano-gpt/meta-llama/llama-4-maverick`                           | 1.0M    |       |           |       |       |       | $0.19      | $0.65       |
 | `nano-gpt/meta-llama/llama-4-scout`                              | 328K    |       |           |       |       |       | $0.09      | $0.46       |
 | `nano-gpt/meta/muse-glimmer-30b`                                 | 131K    |       |           |       |       |       | $0.35      | $2          |
 | `nano-gpt/meta/muse-spark-1.1`                                   | 1.0M    |       |           |       |       |       | $1         | $4          |
@@ -333,11 +333,11 @@ for await (const chunk of stream) {
 | `nano-gpt/moonshotai/kimi-k2-instruct-0711`                      | 128K    |       |           |       |       |       | $0.40      | $2          |
 | `nano-gpt/moonshotai/Kimi-K2-Instruct-0905`                      | 262K    |       |           |       |       |       | $0.40      | $2          |
 | `nano-gpt/moonshotai/kimi-k2-thinking`                           | 262K    |       |           |       |       |       | $0.60      | $3          |
-| `nano-gpt/moonshotai/kimi-k2.5`                                  | 262K    |       |           |       |       |       | $0.30      | $2          |
-| `nano-gpt/moonshotai/kimi-k2.5:thinking`                         | 262K    |       |           |       |       |       | $0.30      | $2          |
+| `nano-gpt/moonshotai/kimi-k2.5`                                  | 262K    |       |           |       |       |       | $0.38      | $2          |
+| `nano-gpt/moonshotai/kimi-k2.5:thinking`                         | 262K    |       |           |       |       |       | $0.38      | $2          |
 | `nano-gpt/moonshotai/kimi-k2.6`                                  | 262K    |       |           |       |       |       | $0.50      | $3          |
 | `nano-gpt/moonshotai/kimi-k2.6:thinking`                         | 262K    |       |           |       |       |       | $0.50      | $3          |
-| `nano-gpt/moonshotai/kimi-k2.7-code`                             | 262K    |       |           |       |       |       | $0.95      | $4          |
+| `nano-gpt/moonshotai/kimi-k2.7-code`                             | 262K    |       |           |       |       |       | $0.67      | $3          |
 | `nano-gpt/moonshotai/kimi-k2.7-code-highspeed`                   | 262K    |       |           |       |       |       | $2         | $8          |
 | `nano-gpt/moonshotai/kimi-k3`                                    | 1.0M    |       |           |       |       |       | $2         | $10         |
 | `nano-gpt/moonshotai/kimi-latest`                                | 1.0M    |       |           |       |       |       | $2         | $10         |
@@ -448,10 +448,9 @@ for await (const chunk of stream) {
 | `nano-gpt/qwen/qwen3-coder-30b-a3b-instruct`                     | 128K    |       |           |       |       |       | $0.10      | $0.40       |
 | `nano-gpt/qwen/qwen3-coder-flash`                                | 128K    |       |           |       |       |       | $0.30      | $2          |
 | `nano-gpt/qwen/qwen3-coder-next`                                 | 262K    |       |           |       |       |       | $0.25      | $0.80       |
-| `nano-gpt/qwen/qwen3-coder-plus`                                 | 128K    |       |           |       |       |       | $1         | $5          |
 | `nano-gpt/qwen/qwen3-max`                                        | 256K    |       |           |       |       |       | $1         | $6          |
 | `nano-gpt/qwen/qwen3-max-2026-01-23`                             | 256K    |       |           |       |       |       | $1         | $6          |
-| `nano-gpt/qwen/qwen3-next-80b-a3b-instruct`                      | 262K    |       |           |       |       |       | $0.15      | $0.65       |
+| `nano-gpt/qwen/qwen3-next-80b-a3b-instruct`                      | 262K    |       |           |       |       |       | $0.09      | $1          |
 | `nano-gpt/qwen/qwen3-next-80b-a3b-thinking`                      | 256K    |       |           |       |       |       | $0.15      | $0.65       |
 | `nano-gpt/qwen/qwen3-vl-235b-a22b-instruct`                      | 131K    |       |           |       |       |       | $0.30      | $2          |
 | `nano-gpt/qwen/qwen3-vl-235b-a22b-thinking`                      | 131K    |       |           |       |       |       | $0.50      | $6          |
@@ -498,8 +497,8 @@ for await (const chunk of stream) {
 | `nano-gpt/qwen/qwen3.8-27b-queen`                                | 524K    |       |           |       |       |       | $0.25      | $2          |
 | `nano-gpt/qwen/qwen3.8-27b-swift`                                | 262K    |       |           |       |       |       | $0.10      | $0.60       |
 | `nano-gpt/qwen/qwen3.8-27b-synthia`                              | 262K    |       |           |       |       |       | $0.10      | $0.60       |
-| `nano-gpt/qwen/qwen3.8-27b-uncensored`                           | 1.0M    |       |           |       |       |       | $0.75      | $3          |
-| `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking`                  | 1.0M    |       |           |       |       |       | $0.75      | $3          |
+| `nano-gpt/qwen/qwen3.8-27b-uncensored`                           | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `nano-gpt/qwen/qwen3.8-27b-uncensored:thinking`                  | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `nano-gpt/qwen/qwen3.8-27b:thinking`                             | 1.0M    |       |           |       |       |       | $0.15      | $0.70       |
 | `nano-gpt/qwen/qwen3.8-flash`                                    | 992K    |       |           |       |       |       | $0.14      | $0.42       |
 | `nano-gpt/qwen/qwen3.8-max`                                      | 991K    |       |           |       |       |       | $2         | $6          |
@@ -539,8 +538,8 @@ for await (const chunk of stream) {
 | `nano-gpt/TEE/gemma-4-31b-it`                                    | 262K    |       |           |       |       |       | $0.15      | $0.46       |
 | `nano-gpt/TEE/gemma4-31b`                                        | 262K    |       |           |       |       |       | $0.40      | $1          |
 | `nano-gpt/TEE/gemma4-31b:thinking`                               | 262K    |       |           |       |       |       | $0.40      | $1          |
-| `nano-gpt/TEE/glm-5.1`                                           | 203K    |       |           |       |       |       | $2         | $5          |
-| `nano-gpt/TEE/glm-5.1-thinking`                                  | 203K    |       |           |       |       |       | $2         | $5          |
+| `nano-gpt/TEE/glm-5.1`                                           | 203K    |       |           |       |       |       | $0.70      | $3          |
+| `nano-gpt/TEE/glm-5.1-thinking`                                  | 203K    |       |           |       |       |       | $0.70      | $3          |
 | `nano-gpt/TEE/glm-5.2`                                           | 1.0M    |       |           |       |       |       | $1         | $4          |
 | `nano-gpt/TEE/glm-5.2:thinking`                                  | 1.0M    |       |           |       |       |       | $1         | $4          |
 | `nano-gpt/TEE/glm-5.3`                                           | 1.0M    |       |           |       |       |       | $1         | $4          |
@@ -569,6 +568,7 @@ for await (const chunk of stream) {
 | `nano-gpt/TheDrummer/Cydonia-24B-v4.3`                           | 33K     |       |           |       |       |       | $0.12      | $0.15       |
 | `nano-gpt/TheDrummer/Magidonia-24B-v4.3`                         | 33K     |       |           |       |       |       | $0.10      | $0.12       |
 | `nano-gpt/TheDrummer/Rocinante-12B-v1.1`                         | 16K     |       |           |       |       |       | $0.41      | $0.59       |
+| `nano-gpt/TheDrummer/Skyfall-31B-v4.2`                           | 16K     |       |           |       |       |       | $0.12      | $0.15       |
 | `nano-gpt/TheDrummer/skyfall-36b-v2`                             | 33K     |       |           |       |       |       | $0.55      | $0.80       |
 | `nano-gpt/TheDrummer/UnslopNemo-12B-v4.1`                        | 8K      |       |           |       |       |       | $0.49      | $0.49       |
 | `nano-gpt/thinkingmachines/inkling`                              | 1.0M    |       |           |       |       |       | $1         | $4          |
@@ -597,9 +597,9 @@ for await (const chunk of stream) {
 | `nano-gpt/x-ai/grok-4.3`                                         | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `nano-gpt/x-ai/grok-4.5`                                         | 500K    |       |           |       |       |       | $2         | $6          |
 | `nano-gpt/x-ai/grok-4.6`                                         | 500K    |       |           |       |       |       | $2         | $6          |
-| `nano-gpt/x-ai/grok-4.7`                                         | 500K    |       |           |       |       |       | $2         | $5          |
+| `nano-gpt/x-ai/grok-4.7`                                         | 500K    |       |           |       |       |       | $2         | $6          |
 | `nano-gpt/x-ai/grok-build-0.1`                                   | 256K    |       |           |       |       |       | $1         | $2          |
-| `nano-gpt/x-ai/grok-latest`                                      | 500K    |       |           |       |       |       | $2         | $5          |
+| `nano-gpt/x-ai/grok-latest`                                      | 500K    |       |           |       |       |       | $2         | $6          |
 | `nano-gpt/xiaomi/mimo-v2.5`                                      | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
 | `nano-gpt/xiaomi/mimo-v2.5-pro`                                  | 1.0M    |       |           |       |       |       | $0.43      | $0.87       |
 | `nano-gpt/xiaomi/mimo-v2.5-pro:thinking`                         | 1.0M    |       |           |       |       |       | $0.43      | $0.87       |
@@ -616,11 +616,11 @@ for await (const chunk of stream) {
 | `nano-gpt/z-ai/GLM-4.5:thinking`                                 | 128K    |       |           |       |       |       | $0.30      | $1          |
 | `nano-gpt/z-ai/glm-4.5v`                                         | 66K     |       |           |       |       |       | $0.60      | $2          |
 | `nano-gpt/z-ai/glm-4.5v:thinking`                                | 66K     |       |           |       |       |       | $0.60      | $2          |
-| `nano-gpt/z-ai/glm-4.6`                                          | 200K    |       |           |       |       |       | $0.35      | $1          |
-| `nano-gpt/z-ai/glm-4.6-original`                                 | 256K    |       |           |       |       |       | $0.35      | $1          |
+| `nano-gpt/z-ai/glm-4.6`                                          | 200K    |       |           |       |       |       | $0.50      | $2          |
+| `nano-gpt/z-ai/glm-4.6-original`                                 | 256K    |       |           |       |       |       | $0.50      | $2          |
 | `nano-gpt/z-ai/GLM-4.6-turbo`                                    | 205K    |       |           |       |       |       | $1         | $3          |
 | `nano-gpt/z-ai/GLM-4.6-turbo:thinking`                           | 205K    |       |           |       |       |       | $1         | $3          |
-| `nano-gpt/z-ai/glm-4.6:thinking`                                 | 200K    |       |           |       |       |       | $0.35      | $1          |
+| `nano-gpt/z-ai/glm-4.6:thinking`                                 | 200K    |       |           |       |       |       | $0.50      | $2          |
 | `nano-gpt/z-ai/glm-4.6v`                                         | 128K    |       |           |       |       |       | $0.30      | $0.90       |
 | `nano-gpt/z-ai/glm-4.6v-original`                                | 128K    |       |           |       |       |       | $0.60      | $0.90       |
 | `nano-gpt/z-ai/glm-4.7`                                          | 200K    |       |           |       |       |       | $0.40      | $2          |
@@ -629,13 +629,13 @@ for await (const chunk of stream) {
 | `nano-gpt/z-ai/glm-4.7-original`                                 | 200K    |       |           |       |       |       | $0.60      | $2          |
 | `nano-gpt/z-ai/glm-4.7-original:thinking`                        | 200K    |       |           |       |       |       | $0.60      | $2          |
 | `nano-gpt/z-ai/glm-4.7:thinking`                                 | 200K    |       |           |       |       |       | $0.40      | $2          |
-| `nano-gpt/z-ai/glm-5`                                            | 200K    |       |           |       |       |       | $0.50      | $3          |
-| `nano-gpt/z-ai/glm-5-original`                                   | 200K    |       |           |       |       |       | $1         | $3          |
-| `nano-gpt/z-ai/glm-5-original:thinking`                          | 200K    |       |           |       |       |       | $1         | $3          |
+| `nano-gpt/z-ai/glm-5`                                            | 200K    |       |           |       |       |       | $0.60      | $2          |
+| `nano-gpt/z-ai/glm-5-original`                                   | 200K    |       |           |       |       |       | $0.60      | $2          |
+| `nano-gpt/z-ai/glm-5-original:thinking`                          | 200K    |       |           |       |       |       | $0.60      | $2          |
 | `nano-gpt/z-ai/glm-5-turbo`                                      | 203K    |       |           |       |       |       | $1         | $4          |
-| `nano-gpt/z-ai/glm-5:thinking`                                   | 200K    |       |           |       |       |       | $0.50      | $3          |
-| `nano-gpt/z-ai/glm-5.1`                                          | 200K    |       |           |       |       |       | $0.75      | $3          |
-| `nano-gpt/z-ai/glm-5.1:thinking`                                 | 200K    |       |           |       |       |       | $0.75      | $3          |
+| `nano-gpt/z-ai/glm-5:thinking`                                   | 200K    |       |           |       |       |       | $0.60      | $2          |
+| `nano-gpt/z-ai/glm-5.1`                                          | 200K    |       |           |       |       |       | $0.70      | $3          |
+| `nano-gpt/z-ai/glm-5.1:thinking`                                 | 200K    |       |           |       |       |       | $0.70      | $3          |
 | `nano-gpt/z-ai/glm-5.2`                                          | 1.0M    |       |           |       |       |       | $0.42      | $1          |
 | `nano-gpt/z-ai/glm-5.2:thinking`                                 | 1.0M    |       |           |       |       |       | $0.42      | $1          |
 | `nano-gpt/z-ai/glm-5.3`                                          | 1.0M    |       |           |       |       |       | $0.60      | $1          |

package/.docs/models/providers/nearai.md

@@ -4,7 +4,7 @@
 
 # ![NEAR AI Cloud logo](https://models.dev/logos/nearai.svg)NEAR AI Cloud
 
-Access 51 NEAR AI Cloud models through Mastra's model router. Authentication is handled automatically using the `NEARAI_API_KEY` environment variable.
+Access 56 NEAR AI Cloud models through Mastra's model router. Authentication is handled automatically using the `NEARAI_API_KEY` environment variable.
 
 Learn more in the [NEAR AI Cloud documentation](https://docs.near.ai/).
 
@@ -41,15 +41,19 @@ for await (const chunk of stream) {
 | `nearai/anthropic/claude-fable-5`          | 1.0M    |       |           |       |       |       | $10        | $50         |
 | `nearai/anthropic/claude-fable-5-1`        | 1.0M    |       |           |       |       |       | $10        | $50         |
 | `nearai/anthropic/claude-haiku-4-5`        | 200K    |       |           |       |       |       | $1         | $5          |
+| `nearai/anthropic/claude-haiku-5-5`        | 1.0M    |       |           |       |       |       | $0.10      | $0.50       |
 | `nearai/anthropic/claude-opus-4-6`         | 200K    |       |           |       |       |       | $5         | $25         |
 | `nearai/anthropic/claude-opus-4-7`         | 1.0M    |       |           |       |       |       | $5         | $25         |
 | `nearai/anthropic/claude-opus-4-8`         | 1.0M    |       |           |       |       |       | $5         | $25         |
 | `nearai/anthropic/claude-opus-5`           | 1.0M    |       |           |       |       |       | $5         | $25         |
+| `nearai/anthropic/claude-opus-5-5`         | 1.0M    |       |           |       |       |       | $4         | $20         |
 | `nearai/anthropic/claude-sonnet-4-5`       | 200K    |       |           |       |       |       | $3         | $15         |
 | `nearai/anthropic/claude-sonnet-4-6`       | 1.0M    |       |           |       |       |       | $3         | $15         |
 | `nearai/anthropic/claude-sonnet-5`         | 1.0M    |       |           |       |       |       | $2         | $10         |
+| `nearai/anthropic/claude-sonnet-5-5`       | 1.0M    |       |           |       |       |       | $2         | $10         |
 | `nearai/black-forest-labs/FLUX.2-klein-4B` | 128K    |       |           |       |       |       | $1         | $1          |
 | `nearai/deepseek/deepseek-v3.2`            | 128K    |       |           |       |       |       | $1         | $1          |
+| `nearai/deepseek/deepseek-v4.1-flash`      | 1.0M    |       |           |       |       |       | $0.30      | $1          |
 | `nearai/google/gemini-2.5-flash`           | 1.0M    |       |           |       |       |       | $0.30      | $3          |
 | `nearai/google/gemini-2.5-flash-lite`      | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
 | `nearai/google/gemini-2.5-pro`             | 1.0M    |       |           |       |       |       | $1         | $10         |
@@ -88,6 +92,7 @@ for await (const chunk of stream) {
 | `nearai/qwen/qwen3.7-max`                  | 1.0M    |       |           |       |       |       | $3         | $8          |
 | `nearai/Qwen/Qwen3.8-27B`                  | 262K    |       |           |       |       |       | $0.04      | $1          |
 | `nearai/x-ai/grok-4.6`                     | 500K    |       |           |       |       |       | $2         | $6          |
+| `nearai/x-ai/grok-4.7`                     | 500K    |       |           |       |       |       | $2         | $6          |
 | `nearai/z-ai/glm-5.3-flash`                | 1.0M    |       |           |       |       |       | $0.15      | $0.50       |
 
 Model availability, capabilities, context windows, and pricing are sourced from [models.dev](https://models.dev) and may change.

package/.docs/reference/auth/better-auth.md

@@ -41,7 +41,7 @@ export const mastra = new Mastra({
 
 **name** (`string`): Custom name for the auth provider instance. (Default: `'better-auth'`)
 
-**authorizeUser** (`(user: BetterAuthUser, request: HonoRequest) => Promise<boolean> | boolean`): Custom authorization function to determine if a user should be granted access. Called after session verification. By default, allows all authenticated users with valid sessions.
+**authorizeUser** (`(user: BetterAuthUser, request: MastraAuthRequest) => Promise<boolean> | boolean`): Custom authorization function to determine if a user should be granted access. Called after session verification. By default, allows all authenticated users with valid sessions.
 
 **public** (`Array<string | RegExp | [string, Methods | Methods[]]>`): Public routes that do not require authentication. Supports exact paths, wildcards, and path params.
 

package/.docs/reference/auth/clerk.md

@@ -57,7 +57,7 @@ export const mastra = new Mastra({
 
 **name** (`string`): Custom name for the auth provider instance.
 
-**authorizeUser** (`(user: User, request: HonoRequest) => Promise<boolean> | boolean`): Custom authorization function to determine if a user should be granted access. Called after token verification. By default, allows all authenticated users, unless organizationId or organizationSlug is set, in which case only members of that organization are allowed.
+**authorizeUser** (`(user: User, request: MastraAuthRequest) => Promise<boolean> | boolean`): Custom authorization function to determine if a user should be granted access. Called after token verification. By default, allows all authenticated users, unless organizationId or organizationSlug is set, in which case only members of that organization are allowed.
 
 ## Related
 

package/.docs/reference/auth/neon.md

@@ -154,9 +154,9 @@ The `MastraRBACNeon` constructor accepts a `MastraRBACNeonOptions` object.
 
 **organizationId** (`string`): Restricts membership lookup to one Neon Auth organization.
 
-**getUserRoles** (`(user: EEUser) => Promise<string[]> | string[]`): Custom function for extracting role names. When omitted, the provider fetches organization memberships from Neon Auth.
+**getUserRoles** (`(user: NeonAuthUser) => Promise<string[]> | string[]`): Custom function for extracting role names. When omitted, the provider fetches organization memberships from Neon Auth.
 
-**cache** (`{ ttlMs?: number; maxSize?: number }`): Role lookup cache configuration. The defaults are 30,000 ms and 1,000 entries.
+**cache** (`{ ttlMs?: number; maxSize?: number }`): Role lookup cache configuration. The defaults are 60,000 ms and 1,000 entries.
 
 ### Methods
 

package/.docs/reference/datasets/compareExperiments.md

@@ -16,7 +16,7 @@ import { Mastra } from '@mastra/core'
 const mastra = new Mastra({/* storage config */})
 
 const comparison = await mastra.datasets.compareExperiments({
-  experimentIds: ['exp-baseline', 'exp-new'],
+  experimentIds: ['exp-baseline', 'exp-prompt-v2', 'exp-new-model'],
   baselineId: 'exp-baseline',
 })
 
@@ -27,24 +27,29 @@ for (const item of comparison.items) {
   console.log(`  Input: ${JSON.stringify(item.input)}`)
 
   for (const [expId, result] of Object.entries(item.results)) {
-    if (result) {
-      console.log(
-        `  ${expId}: output=${JSON.stringify(result.output)}, scores=${JSON.stringify(result.scores)}`,
-      )
+    if (!result) {
+      console.log(`  ${expId}: did not run this item`)
+      continue
     }
+    console.log(
+      `  ${expId}: output=${JSON.stringify(result.output)}, scores=${JSON.stringify(result.scores)}`,
+    )
   }
 }
 ```
 
 ## Parameters
 
-**experimentIds** (`string[]`): Array of experiment IDs to compare. Must contain at least 2.
+**experimentIds** (`string[]`): Array of experiment IDs to compare. Duplicate IDs are removed before the 2-ID minimum is checked, so the list must contain at least 2 distinct IDs.
 
-**baselineId** (`string`): ID of the baseline experiment. Defaults to the first ID in experimentIds.
+**baselineId** (`string`): ID of the baseline experiment. Must be one of experimentIds. Defaults to the first ID in experimentIds.
 
 ## Returns
 
-Throws `MastraError` if fewer than 2 experiment IDs are provided.
+Throws a `MastraError` with ID `COMPARE_INVALID_INPUT` when:
+
+- `experimentIds` contains fewer than 2 distinct IDs.
+- `baselineId` isn't one of `experimentIds`. Earlier versions silently ignored an unknown `baselineId`.
 
 **result** (`Promise<object>`): Comparison results.
 
@@ -58,7 +63,11 @@ Throws `MastraError` if fewer than 2 experiment IDs are provided.
 
 **result.items.groundTruth** (`unknown | null`): Ground truth for the item.
 
-**result.items.results** (`Record<string, { output: unknown; scores: Record<string, number | null> } | null>`): Results keyed by experiment ID. Each entry contains the output and scorer results for that experiment.
+**result.items.results** (`Record<string, { output: unknown; scores: Record<string, number | null> } | null>`): Results keyed by experiment ID, with an entry for every experiment in experimentIds. Each entry contains the output and scorer results for that experiment, or null when that experiment did not run the item.
+
+## HTTP route
+
+`POST /api/datasets/:datasetId/compare` calls this method. The route accepts between 2 and 10 IDs in `experimentIds`. It also still accepts the deprecated `{ experimentIdA, experimentIdB }` body, which compares the two experiments with `experimentIdA` as the baseline.
 
 ## Related
 

package/.docs/reference/datasets/dataset.md

@@ -60,7 +60,7 @@ const history = await dataset.getItemHistory({ itemId: 'item-id' })
 
 ## Access
 
-`Dataset` isn't instantiated directly. Obtain one via `DatasetsManager`:
+Obtain a `Dataset` through `DatasetsManager`, which resolves the dataset and applies tenancy scope:
 
 ```typescript
 const dataset = await mastra.datasets.get({ id: 'dataset-id' })
@@ -68,6 +68,8 @@ const dataset = await mastra.datasets.get({ id: 'dataset-id' })
 const dataset = await mastra.datasets.create({ name: 'My dataset' })
 ```
 
+`Dataset` also has a public constructor (`new Dataset(id, mastra)`) that skips the manager's lookup and tenancy scoping.
+
 ## Properties
 
 For the full dataset record (name, description, schemas, version, timestamps), call [`dataset.getDetails()`](https://mastra.ai/reference/datasets/getDetails).

package/.docs/reference/datasets/finalizeExperiment.md

@@ -6,7 +6,7 @@
 
 **Added in:** `@mastra/core@1.61.0`
 
-Finalizes a caller-driven experiment created with [`createExperiment()`](https://mastra.ai/reference/datasets/createExperiment), with or without a target. Mastra computes the final counts server-side from the persisted result rows and marks the experiment `'completed'`. The caller never tracks completion bookkeeping.
+Finalizes a caller-driven experiment created with [`createExperiment()`](https://mastra.ai/reference/datasets/createExperiment), with or without a target. Mastra computes the final counts server-side from the persisted result rows and marks the experiment `'completed'`. An experiment that's already `'failed'` is returned unchanged and stays failed. The caller never tracks completion bookkeeping.
 
 Counts are per item, so `succeededCount + failedCount + skippedCount === totalItems` even when items have multiple attempts:
 
@@ -16,7 +16,7 @@ Counts are per item, so `succeededCount + failedCount + skippedCount === totalIt
 
 Attempt-level detail remains available through [`listExperimentResults()`](https://mastra.ai/reference/datasets/listExperimentResults).
 
-Finalization is idempotent: calling it on an already-finalized experiment returns the stored record without recomputing.
+Finalization is idempotent: calling it on an already completed or failed experiment returns the stored record without recomputing.
 
 ## Usage example
 

package/.docs/reference/datasets/listExperiments.md

@@ -67,9 +67,9 @@ for (const exp of experiments) {
 
 **result.experiments.datasetVersion** (`number | null`): Dataset version used for the experiment.
 
-**result.experiments.targetType** (`'agent' | 'workflow' | 'scorer' | 'processor'`): Type of target used.
+**result.experiments.targetType** (`'agent' | 'workflow' | 'scorer' | 'processor' | null`): Type of target used. null for caller-driven ingestion experiments.
 
-**result.experiments.targetId** (`string`): ID of the target used.
+**result.experiments.targetId** (`string | null`): ID of the target used. null for caller-driven ingestion experiments.
 
 **result.experiments.status** (`'pending' | 'running' | 'completed' | 'failed'`): Current status of the experiment.
 

package/.docs/reference/datasets/submitExperimentResult.md

@@ -37,7 +37,7 @@ The item must be visible at the experiment's pinned dataset version. Submissions
 
 **groundTruth** (`unknown`): Expected output. Defaults to the dataset item's ground truth at the pinned version.
 
-**error** (`object`): Error details (message, optional stack and code) when the item failed.
+**error** (`object | null`): Error details (message, optional stack and code) when the item failed.
 
 **startedAt** (`Date`): When the worker started this item.
 

package/.docs/reference/editor/tools.md

@@ -78,10 +78,18 @@ Stored HTTP definitions don't accept arbitrary headers. When the reserved `mastr
 
 MCP tools can be allowlisted at two levels:
 
-1. **Server level**: The stored server's `tools` map limits tools for every agent that uses the client.
-2. **Agent level**: The agent's MCP client reference limits the remaining tools for that agent.
+1. **Server level**: The stored server's `tools` map limits tools for every agent that uses the client. Omitting `tools` at this level exposes all of the server's tools.
+2. **Agent level**: The agent's MCP client reference limits the remaining tools for that agent. Omitting `tools` at this level selects no tools.
 
-Agent-level tool names can use namespaced or bare names. An explicit empty `tools` map selects all tools. With the current resolver, omitting `tools` from an agent-level MCP reference selects none.
+Agent-level tool names can use namespaced or bare names. To select every remaining tool at the agent level, pass an explicit empty `tools` map:
+
+```typescript
+const mcpClients = {
+  'docs-client': { tools: {} }, // all tools
+  'search-client': { tools: { docs_search: {} } }, // only docs_search
+  'billing-client': {}, // no tools
+}
+```
 
 ### Namespacing
 

package/.docs/reference/evals/completeness.md

@@ -25,7 +25,7 @@ The `.run()` method returns a result in the following shape:
 ```typescript
 {
   runId: string,
-  extractStepResult: {
+  preprocessStepResult: {
     inputElements: string[],
     outputElements: string[],
     missingElements: string[],
@@ -52,9 +52,9 @@ The extraction process includes:
 - Special handling of short words (3 characters or less)
 - Deduplication of elements
 
-### `extractStepResult`
+### `preprocessStepResult`
 
-From the `.run()` method, you can get the `extractStepResult` object with the following properties:
+From the `.run()` method, you can get the `preprocessStepResult` object with the following properties:
 
 - **inputElements**: Key elements found in the input (e.g., nouns, verbs, topics, terms).
 - **outputElements**: Key elements found in the output.

package/.docs/reference/evals/context-precision.md

@@ -34,7 +34,7 @@ Either `context` or `contextExtractor` must be provided. If both are provided, `
 
 ## `.run()` returns
 
-**score** (`number`): Mean Average Precision score between 0 and scale (default 0-1)
+**score** (`number`): Mean Average Precision score between 0 and scale (default 0-1). Assumes a positive scale.
 
 **reason** (`string`): Human-readable explanation of the context precision evaluation
 

package/.docs/reference/evals/create-scorer.md

@@ -10,7 +10,7 @@ Mastra provides a unified `createScorer` factory that allows you to define custo
 
 Use the `createScorer` factory to define your scorer with a name, description, and optional judge configuration. Then chain step methods to build your evaluation pipeline. You must provide at least a `generateScore` step.
 
-**Prompt object steps** are step configurations expressed as objects with `description` + `createPrompt` (and `outputSchema` for `preprocess`/`analyze`). These steps invoke the judge LLM. **Function steps** are plain functions and never call the judge.
+**Prompt object steps** are step configurations expressed as objects with `description` + `createPrompt` (and `outputSchema` for `preprocess`/`analyze`, but not for `generateScore`). These steps invoke the judge LLM. **Function steps** are plain functions and never call the judge.
 
 ```typescript
 import { createScorer } from '@mastra/core/evals'
@@ -65,7 +65,7 @@ This function returns a scorer builder that you can chain step methods onto. See
 
 The judge only runs for steps defined as **prompt objects** (`preprocess`, `analyze`, `generateScore`, `generateReason` in prompt mode). If you use function steps only, the judge is never called and there is no LLM output to inspect. In that case, any score/reason must be produced by your functions.
 
-When a prompt-object step runs, its structured LLM output is stored in the corresponding result field (`preprocessStepResult`, `analyzeStepResult`, or the value consumed by `calculateScore` in `generateScore`).
+When a prompt-object step runs, its structured LLM output is stored in the corresponding result field (`preprocessStepResult` or `analyzeStepResult`). For `generateScore`, the judge returns `{ score: number }` and `score` becomes the scorer's score.
 
 ## Retry judge requests
 
@@ -289,15 +289,11 @@ The method must return a numerical score.
 
 **description** (`string`): Description of what this scoring step does.
 
-**outputSchema** (`StandardJSONSchemaV1`): Standard JSON Schema for the expected output of the generateScore step.
-
 **createPrompt** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
 
 **judge** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
 
-When using prompt object mode, you must also provide a `calculateScore` function to convert the LLM output to a numerical score:
-
-**calculateScore** (`function`): Function: ({ run, results, analyzeStepResult }) => number. Converts the LLM's structured output into a numerical score.
+In prompt object mode, don't set `outputSchema`. Mastra asks the judge for structured output of the form `{ score: number }` and uses `score` as the step result.
 
 ### `generateReason`
 

package/.docs/reference/evals/faithfulness.md

@@ -12,9 +12,11 @@ The `createFaithfulnessScorer()` function accepts a single options object with t
 
 **model** (`LanguageModel`): Configuration for the model used to evaluate faithfulness.
 
-**context** (`string[]`): Array of context chunks against which the output's claims will be verified.
+**options** (`{ context?: string[]; scale?: number }`): Configuration options for the scorer.
 
-**scale** (`number`): The maximum score value. The final score will be normalized to this scale. (Default: `1`)
+**options.context** (`string[]`): Array of context chunks against which the output's claims will be verified. When omitted, the scorer uses the results of tool calls in the run output.
+
+**options.scale** (`number`): The maximum score value. The final score will be normalized to this scale.
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
 
@@ -22,7 +24,7 @@ This function returns an instance of the MastraScorer class. The `.run()` method
 
 **runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult** (`string[]`): Array of extracted claims from the output.
+**preprocessStepResult** (`object`): Object with the claims extracted from the output: { claims: string\[] }
 
 **preprocessPrompt** (`string`): The prompt sent to the LLM for the preprocess step (optional).
 
@@ -64,7 +66,7 @@ Final score: `(supported_claims / total_claims) * scale`
 
 ### Score interpretation
 
-A faithfulness score between 0 and 1:
+A faithfulness score between 0 and the configured scale (default 1). With the default scale:
 
 - **1.0**: All claims are accurate and directly supported by the context.
 - **0.7 to 0.9**: Most claims are correct, with minor additions or omissions.

package/.docs/reference/evals/filter-run.md

@@ -115,7 +115,7 @@ The `partTypes` option accepts `MastraPartType` values. Each value is prefix-mat
 ## Filtering behavior
 
 - **Part type filtering** applies to both `input.rememberedMessages` and `output` when they contain agent message arrays.
-- **Tool name filtering** only affects messages that contain tool invocations. Text-only messages pass through.
+- **Tool name filtering** only affects messages that contain tool invocations. Messages without tool invocations are filtered by `partTypes` only, and pass through when `partTypes` isn't set.
 - **System messages** (`systemMessages`, `taggedSystemMessages`) are never filtered, regardless of `partTypes` or `toolNames`.
 - **Message limits** (`maxRememberedMessages`, `maxOutputMessages`) apply after type and tool filtering, taking the most recent messages.
-- When both `partTypes` and `toolNames` are set, a message must satisfy both filters to be kept.
+- When both `partTypes` and `toolNames` are set, a message with tool invocations must satisfy both filters to be kept.

package/.docs/reference/evals/trajectory-accuracy.md

@@ -93,13 +93,14 @@ The discriminated union includes these additional step types:
 | Step type              | Key properties                                                |
 | ---------------------- | ------------------------------------------------------------- |
 | `mcp_tool_call`        | `toolArgs`, `toolResult`, `mcpServer`, `success`              |
+| `provider_tool_call`   | `toolArgs`, `toolResult`, `success`                           |
 | `model_generation`     | `modelId`, `promptTokens`, `completionTokens`, `finishReason` |
 | `agent_run`            | `agentId`                                                     |
 | `workflow_run`         | `workflowId`, `status`                                        |
 | `workflow_conditional` | `conditionCount`, `selectedSteps`                             |
 | `workflow_parallel`    | `branchCount`, `parallelSteps`                                |
 | `workflow_loop`        | `loopType`, `totalIterations`                                 |
-| `workflow_sleep`       | `durationMs`, `sleepType`                                     |
+| `workflow_sleep`       | `sleepDurationMs`, `sleepType`                                |
 | `workflow_wait_event`  | `eventName`, `eventReceived`                                  |
 | `processor_run`        | `processorId`                                                 |
 
@@ -261,7 +262,7 @@ Only checks that each expected step is present. Order is ignored, and extra step
 
 ## Code-based scoring details
 
-- **Continuous scores**: Returns values between 0.0 and 1.0 in relaxed mode; binary (0 or 1) in strict mode
+- **Continuous scores**: Returns values between 0.0 and 1.0 in every ordering mode. In strict mode, the score is the share of expected steps matched in order, minus penalties for extra steps and, when `allowRepeatedSteps` is `false`, repeated steps
 - **Deterministic**: Same input always produces the same output
 - **Fast**: No external API calls
 

package/.docs/reference/index.md

@@ -27,7 +27,6 @@ The Reference section provides documentation of Mastra's API, including paramete
 - [.getMetadata()](https://mastra.ai/reference/agents/getMetadata)
 - [.getModel()](https://mastra.ai/reference/agents/getModel)
 - [.getSkill()](https://mastra.ai/reference/agents/getSkill)
-- [.getTools()](https://mastra.ai/reference/agents/getTools)
 - [.getVoice()](https://mastra.ai/reference/agents/getVoice)
 - [.listAgents()](https://mastra.ai/reference/agents/listAgents)
 - [.listScorers()](https://mastra.ai/reference/agents/listScorers)

package/.docs/reference/memory/listThreads.md

@@ -69,7 +69,7 @@ const result = await memory.listThreads({
 
 **page** (`number`): Page number (0-indexed) to retrieve
 
-**perPage** (`number | false`): Maximum number of threads to return per page, or false to fetch all
+**perPage** (`number | false`): Maximum number of threads to return per page, or false to fetch all (Default: `100`)
 
 **orderBy** (`{ field: 'createdAt' | 'updatedAt', direction: 'ASC' | 'DESC' }`): Sort configuration with field and direction (defaults to { field: 'createdAt', direction: 'DESC' })
 

package/.docs/reference/memory/observational-memory.md

@@ -99,7 +99,7 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **observation.activateOnProviderChange** (`boolean`): Force buffered observations to activate when the actor provider or model changes. If unset, the top-level activateOnProviderChange value is used for observations. Currently only applied when using the standalone ObservationalMemory class; new Memory(...) applies the top-level activateOnProviderChange only.
 
-**observation.blockAfter** (`number`): Safety net for when background buffering can't keep up. Values from 1 up to (but not including) 100 are multipliers of messageTokens: 1.2 resolves to 120% of the threshold (36k tokens with the default 30k). Values of 100 or more are absolute token counts and must be greater than messageTokens. Above this point, activation uses the smallest set of buffered chunks that reaches the retention target, even when that overshoots the target by more than the usual safeguard allows. It never activates more chunks than are needed to reach the retention target, so it removes only slightly more history than a normal activation. It changes the result only when the retention floor is above roughly 20,000 tokens; with the default bufferActivation (a 6k floor) it has no observable effect. Activation usually keeps a minimum remaining context (the smaller of 1000 tokens or the retention floor), but a single buffered chunk that covers the whole pending window still activates and can leave less. Crossing blockAfter does not trigger a blocking observation. A synchronous (blocking) observation runs when the messageTokens threshold is reached and activating buffered chunks doesn't bring pending tokens back under it, for example when a large tool result arrives after buffering has stopped. All remaining buffered chunks are activated first, so the synchronous observation only covers messages no chunk has observed. Only relevant when bufferTokens is set. Defaults to 1.2 when async buffering is enabled.
+**observation.blockAfter** (`number`): Safety net for when background buffering can't keep up. Values from 1 up to (but not including) 100 are multipliers of messageTokens: 1.2 resolves to 120% of the threshold (36k tokens with the default 30k). Multipliers apply to a per-thread messageTokens override when one is set. Values of 100 or more are absolute token counts and must be greater than messageTokens. Between messageTokens and blockAfter, only async buffering and activation run: reaching the threshold without a buffered chunk to activate starts background buffering, and the chunk activates on a later step. A synchronous (blocking) observation runs if pending tokens still reach blockAfter after buffered activation. All remaining buffered chunks are activated first, so the synchronous observation only covers messages no chunk has observed. Set blockAfter: 1 to observe synchronously at messageTokens. Above this point, activation also uses the smallest set of buffered chunks that reaches the retention target, even when that overshoots the target by more than the usual safeguard allows. It never activates more chunks than are needed to reach the retention target, so it removes only slightly more history than a normal activation. It changes the result only when the retention floor is above roughly 20,000 tokens; with the default bufferActivation (a 6k floor) it has no observable effect. Activation usually keeps a minimum remaining context (the smaller of 1000 tokens or the retention floor), but a single buffered chunk that covers the whole pending window still activates and can leave less. Only relevant when bufferTokens is set. Defaults to 1.2 when async buffering is enabled.
 
 **observation.previousObserverTokens** (`number | false`): Optional token budget for the observer's previous-observations context. When set to a number, the observations passed to the Observer agent are tail-truncated to fit within this budget while keeping the newest observations and preserving highlighted 🔴 items when possible. When a buffered reflection is pending, the already-reflected observation lines are automatically replaced with the reflection summary before truncation. Set to 0 to omit previous observations entirely, or false to disable truncation explicitly.
 
@@ -371,7 +371,7 @@ export const agent = new Agent({
 
 Async buffering is **enabled by default**. It pre-computes observations in the background as the conversation grows: when the `messageTokens` threshold is reached, buffered observations activate instantly with no blocking LLM call.
 
-The lifecycle follows **buffer → activate → remove messages → repeat**. Background Observer calls run at `bufferTokens` intervals and produce chunks of observations. At the threshold, activation moves observations into the log and removes raw messages from context. Above `blockAfter`, activation may overshoot the retention target instead of activating fewer chunks. A synchronous observation runs if pending tokens are still at or above the threshold after all buffered chunks have been activated.
+The lifecycle follows **buffer → activate → remove messages → repeat**. Background Observer calls run at `bufferTokens` intervals and produce chunks of observations. At the threshold, activation moves observations into the log and removes raw messages from context. Between the threshold and `blockAfter`, buffering continues in the background and the next ready chunk activates on a later step. A synchronous observation runs if pending tokens still reach `blockAfter` after all buffered chunks have been activated. Above `blockAfter`, activation may also overshoot the retention target instead of activating fewer chunks.
 
 Default settings:
 
@@ -402,7 +402,7 @@ export const agent = new Agent({
           bufferTokens: 5_000,
           // Activate to retain 30% of threshold
           bufferActivation: 0.7,
-          // Above 1.5x the threshold, let activation overshoot the retention target
+          // Observe synchronously at 1.5x the threshold if no buffered chunk is ready
           blockAfter: 1.5,
         },
         reflection: {

package/.docs/reference/migrations/mcp-v2.md

@@ -16,12 +16,12 @@ Streamable HTTP still streams responses as Server-Sent Events. What's removed is
 
 ### `@mastra/core` peer range
 
-`@mastra/mcp` 2.0 requires `@mastra/core` 1.68 or newer, which adds the shared server contract (`mcpVersion`, `MCPToolExecutionResultV2`, `context.mcp.protocolVersion`). Update both packages together.
+`@mastra/mcp` 2.0 requires `@mastra/core` 1.76 or a later 1.x release, which includes the shared server contract (`mcpVersion`, `MCPToolExecutionResultV2`, `context.mcp.protocolVersion`). Update both packages together.
 
 ```diff
 - "@mastra/core": "^1.60.0",
 - "@mastra/mcp": "^1.17.0"
-+ "@mastra/core": "^1.68.0",
++ "@mastra/core": "^1.76.0",
 + "@mastra/mcp": "^2.0.0"
 ```
 

package/.docs/reference/migrations/upgrade-to-v1/agent.md

@@ -81,7 +81,7 @@ To migrate, replace property access with the corresponding getter methods.
 - const tools = agent.tools;
 - const instructions = agent.instructions;
 + const llm = agent.getLLM();
-+ const tools = agent.getTools();
++ const tools = await agent.listTools();
 + const instructions = agent.getInstructions();
 ```
 

package/.docs/reference/migrations/vnext-to-standard-apis.md

@@ -153,7 +153,7 @@ The following options are available in the standard `.stream()` and `generate()`
   - `errorStrategy` - Determines what happens when the output doesn’t match the schema:
 
     - 'warn' - log a warning
-    - 'error' - throw an error
+    - 'strict' - throw an error
     - 'fallback' - return a fallback value you provide
 
     ```typescript

package/.docs/reference/observability/feedback.md

@@ -345,7 +345,7 @@ Use `FeedbackInput` with `mastra.observability.addFeedback()`, `recordedTrace.ad
 
 **metadata** (`Record<string, unknown>`): Additional feedback-specific metadata.
 
-**experimentId** (`string`): Experiment or eval run identifier.
+**experimentId** (`string`): Deprecated. The experiment is derived from the target trace or span. Read correlationContext.experimentId on the exported event instead.
 
 **sourceId** (`string`): ID of the source record this feedback is linked to.