@mastra/mcp-docs-server 1.1.8 → 1.1.9-alpha.1

package/.docs/reference/evals/toxicity.md

@@ -1,4 +1,4 @@
-# Toxicity Scorer
+# Toxicity scorer
 
 The `createToxicityScorer()` function evaluates whether an LLM's output contains racist, biased, or toxic elements. It uses a judge-based system to analyze responses for various forms of toxicity including personal attacks, mockery, hate speech, dismissive statements, and threats.
 
@@ -12,7 +12,7 @@ The `createToxicityScorer()` function accepts a single options object with the f
 
 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.
 
-## .run() Returns
+## `.run()` returns
 
 **runId** (`string`): The id of the run (optional).
 
@@ -41,7 +41,7 @@ This function returns an instance of the MastraScorer class. The `.run()` method
 }
 ```
 
-## Scoring Details
+## Scoring details
 
 The scorer evaluates toxicity through multiple aspects:
 

package/.docs/reference/harness/harness-class.md

@@ -1,4 +1,4 @@
-# Harness Class
+# Harness class
 
 **Added in:** `@mastra/core@1.5.0`
 
@@ -82,6 +82,8 @@ await harness.sendMessage({ content: 'Hello!' })
 
 **subagents.allowedHarnessTools** (`string[]`): Tool IDs from the harness's shared \`tools\` config. Merged with \`tools\` above to let subagents use a subset of harness tools.
 
+**subagents.allowedWorkspaceTools** (`string[]`): Workspace tool names the subagent is allowed to use. Uses the exposed names (after any renames via workspace tool config). When set, workspace tools not in this list are hidden from the model. Non-workspace tools are never affected. When omitted, all workspace tools are visible.
+
 **subagents.defaultModelId** (`string`): Default model ID for this subagent type.
 
 **subagents.maxSteps** (`number`): Optional maximum number of steps for the spawned subagent. Defaults to \`50\` when omitted.
@@ -94,7 +96,7 @@ await harness.sendMessage({ content: 'Hello!' })
 
 **heartbeatHandlers** (`HeartbeatHandler[]`): Periodic background tasks started during \`init()\`. Use for gateway sync, cache refresh, and similar tasks.
 
-**idGenerator** (`() => string`): Custom ID generator for threads, messages, and other entities. (Default: `timestamp + random string`)
+**idGenerator** (`() => string`): Custom ID generator for Harness-managed IDs such as threads and mode-run identifiers. (Default: `timestamp + random string`)
 
 **modelAuthChecker** (`ModelAuthChecker`): Custom auth checker for model providers. Return \`true\`/\`false\` to override the default environment variable check, or \`undefined\` to fall back to defaults.
 
@@ -567,7 +569,7 @@ if (harness.isWorkspaceReady()) {
 
 #### `destroyWorkspace()`
 
-Destroy the workspace and release resources. Only applies to static workspaces — dynamic workspaces are not destroyed.
+Destroy the workspace and release resources. Only applies to static workspaces — dynamic workspaces aren't destroyed.
 
 ```typescript
 await harness.destroyWorkspace()

package/.docs/reference/index.md

@@ -266,12 +266,14 @@ The Reference section provides documentation of Mastra's API, including paramete
 - [.start()](https://mastra.ai/reference/workflows/run-methods/start)
 - [.startAsync()](https://mastra.ai/reference/workflows/run-methods/startAsync)
 - [.timeTravel()](https://mastra.ai/reference/workflows/run-methods/timeTravel)
+- [BlaxelSandbox](https://mastra.ai/reference/workspace/blaxel-sandbox)
 - [DaytonaSandbox](https://mastra.ai/reference/workspace/daytona-sandbox)
 - [E2BSandbox](https://mastra.ai/reference/workspace/e2b-sandbox)
 - [GCSFilesystem](https://mastra.ai/reference/workspace/gcs-filesystem)
 - [LocalFilesystem](https://mastra.ai/reference/workspace/local-filesystem)
 - [LocalSandbox](https://mastra.ai/reference/workspace/local-sandbox)
 - [S3Filesystem](https://mastra.ai/reference/workspace/s3-filesystem)
+- [SandboxProcessManager](https://mastra.ai/reference/workspace/process-manager)
 - [Workspace Class](https://mastra.ai/reference/workspace/workspace-class)
 - [WorkspaceFilesystem](https://mastra.ai/reference/workspace/filesystem)
 - [WorkspaceSandbox](https://mastra.ai/reference/workspace/sandbox)

package/.docs/reference/memory/clone-utilities.md

@@ -1,8 +1,8 @@
-# Cloned Thread Utilities
+# Cloned thread utilities
 
 The Memory class provides utility methods for working with cloned threads. These methods help you check clone status, retrieve clone metadata, navigate clone relationships, and track clone history.
 
-## isClone()
+## `isClone()`
 
 Checks whether a thread is a clone of another thread.
 
@@ -28,7 +28,7 @@ if (memory.isClone(thread)) {
 }
 ```
 
-## getCloneMetadata()
+## `getCloneMetadata()`
 
 Retrieves the clone metadata from a thread if it exists.
 
@@ -54,7 +54,7 @@ if (cloneInfo) {
 }
 ```
 
-## getSourceThread()
+## `getSourceThread()`
 
 Retrieves the original source thread that a cloned thread was created from.
 
@@ -79,7 +79,7 @@ if (sourceThread) {
 }
 ```
 
-## listClones()
+## `listClones()`
 
 Lists all threads that were cloned from a specific source thread.
 
@@ -104,7 +104,7 @@ for (const clone of clones) {
 }
 ```
 
-## getCloneHistory()
+## `getCloneHistory()`
 
 Retrieves the full clone history chain for a thread, tracing back to the original.
 
@@ -136,7 +136,7 @@ for (let i = 0; i < history.length; i++) {
 }
 ```
 
-## Complete Example
+## Complete example
 
 ```typescript
 import { mastra } from './mastra'

package/.docs/reference/memory/cloneThread.md

@@ -2,7 +2,7 @@
 
 The `.cloneThread()` method creates a copy of an existing conversation thread, including all its messages. This enables creating divergent conversation paths from a specific point in a conversation. When semantic recall is enabled, the method also creates vector embeddings for the cloned messages.
 
-## Usage Example
+## Usage example
 
 ```typescript
 const { thread, clonedMessages } = await memory.cloneThread({
@@ -52,7 +52,7 @@ The cloned thread's metadata includes a `clone` property with:
 
 **lastMessageId** (`string`): The ID of the last message in the source thread at the time of cloning.
 
-## Extended Usage Example
+## Extended usage example
 
 ```typescript
 import { mastra } from './mastra'
@@ -98,7 +98,7 @@ const response = await agent.generate("Let's try a different approach", {
 })
 ```
 
-## Vector Embeddings
+## Vector embeddings
 
 When the Memory instance has semantic recall enabled (with a vector store and embedder configured), `cloneThread()` automatically creates vector embeddings for all cloned messages. This ensures that semantic search works correctly on the cloned thread.
 
@@ -127,7 +127,7 @@ const results = await memory.recall({
 })
 ```
 
-## Observational Memory
+## Observational memory
 
 When [Observational Memory](https://mastra.ai/docs/memory/observational-memory) is enabled, `cloneThread()` automatically clones the OM records associated with the source thread. The behavior depends on the OM scope:
 
@@ -135,4 +135,4 @@ When [Observational Memory](https://mastra.ai/docs/memory/observational-memory)
 - **Resource-scoped OM (same `resourceId`)**: The OM record is shared between the source and cloned threads since they belong to the same resource. No duplication occurs.
 - **Resource-scoped OM (different `resourceId`)**: The OM record is cloned to the new resource. Message IDs are remapped and any thread-identifying tags within observations are updated to reference the cloned thread.
 
-Only the current (most recent) OM generation is cloned — older history generations are not copied. Transient processing state (observation/reflection in-progress flags) is reset on the cloned record.
+Only the current (most recent) OM generation is cloned — older history generations aren't copied. Transient processing state (observation/reflection in-progress flags) is reset on the cloned record.

package/.docs/reference/memory/createThread.md

@@ -2,7 +2,7 @@
 
 The `.createThread()` method creates a new conversation thread in the memory system. Each thread represents a distinct conversation or context and can contain multiple messages.
 
-## Usage Example
+## Usage example
 
 ```typescript
 await memory?.createThread({ resourceId: 'user-123' })

package/.docs/reference/memory/deleteMessages.md

@@ -2,7 +2,7 @@
 
 The `.deleteMessages()` method deletes multiple messages by their IDs.
 
-## Usage Example
+## Usage example
 
 ```typescript
 await memory?.deleteMessages(['671ae63f-3a91-4082-a907-fe7de78e10ec'])

package/.docs/reference/memory/getThreadById.md

@@ -2,7 +2,7 @@
 
 The `.getThreadById()` method retrieves a specific thread by its ID.
 
-## Usage Example
+## Usage example
 
 ```typescript
 await memory?.getThreadById({ threadId: 'thread-123' })

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

@@ -2,7 +2,7 @@
 
 The `listThreads()` method retrieves threads with pagination support and optional filtering by `resourceId`, `metadata`, or both.
 
-## Usage Examples
+## Usage examples
 
 ### List all threads with pagination
 
@@ -26,7 +26,7 @@ const result = await memory.listThreads({
 })
 ```
 
-### Filter by resourceId
+### Filter by `resourceId`
 
 ```typescript
 const result = await memory.listThreads({
@@ -119,7 +119,7 @@ while (hasMorePages) {
 }
 ```
 
-## Metadata Filtering
+## Metadata filtering
 
 The metadata filter uses AND logic - all specified key-value pairs must match for a thread to be included in the results:
 

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

@@ -1,4 +1,4 @@
-# Memory Class
+# Memory class
 
 The `Memory` class provides a robust system for managing conversation history and thread-based message storage in Mastra. It enables persistent storage of conversations, semantic search capabilities, and efficient message retrieval. You must configure a storage provider for conversation history, and if you enable semantic recall you will also need to provide a vector store and embedder.
 

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

@@ -1,4 +1,4 @@
-# Observational Memory
+# Observational memory
 
 **Added in:** `@mastra/memory@1.1.0`
 
@@ -26,6 +26,8 @@ export const agent = new Agent({
 
 The `observationalMemory` option accepts `true`, a configuration object, or `false`. Setting `true` enables OM with `google/gemini-2.5-flash` as the default model. When passing a config object, a `model` must be explicitly set — either at the top level, or on `observation.model` and/or `reflection.model`.
 
+Observer input is multimodal-aware. OM keeps text placeholders like `[Image #1: screenshot.png]` in the transcript it builds for the Observer, and also sends the underlying image parts when possible. This applies to both single-thread observation and batched multi-thread observation. Non-image files appear as placeholders only.
+
 **enabled** (`boolean`): Enable or disable Observational Memory. When omitted from a config object, defaults to \`true\`. Only \`enabled: false\` explicitly disables it. (Default: `true`)
 
 **model** (`string | LanguageModel | DynamicModel | ModelWithRetries[]`): Model for both the Observer and Reflector agents. Sets the model for both at once. Cannot be used together with \`observation.model\` or \`reflection.model\` — an error will be thrown if both are set. When using \`observationalMemory: true\`, defaults to \`google/gemini-2.5-flash\`. When passing a config object, this or \`observation.model\`/\`reflection.model\` must be set. Use \`"default"\` to explicitly use the default model (\`google/gemini-2.5-flash\`). (Default: `'google/gemini-2.5-flash' (when using observationalMemory: true)`)
@@ -40,7 +42,7 @@ The `observationalMemory` option accepts `true`, a configuration object, or `fal
 
 **observation.instruction** (`string`): Custom instruction appended to the Observer's system prompt. Use this to customize what the Observer focuses on, such as domain-specific preferences or priorities.
 
-**observation.messageTokens** (`number`): Token count of unobserved messages that triggers observation. When unobserved message tokens exceed this threshold, the Observer agent is called.
+**observation.messageTokens** (`number`): Token count of unobserved messages that triggers observation. When unobserved message tokens exceed this threshold, the Observer agent is called. Image parts are included with model-aware estimates when possible, with deterministic fallbacks when image metadata is incomplete. Image-like \`file\` parts are counted the same way when uploads are normalized as files.
 
 **observation.maxTokensPerBatch** (`number`): Maximum tokens per batch when observing multiple threads in resource scope. Threads are chunked into batches of this size and processed in parallel. Lower values mean more parallelism but more API calls.
 
@@ -80,9 +82,9 @@ OM persists token payload estimates so repeated counting can reuse prior tiktoke
 
 - Part-level cache: `part.providerMetadata.mastra`.
 - String-content fallback cache: message-level metadata when no parts exist.
-- Cache entries are ignored and recomputed if cache version/tokenizer source does not match.
-- Per-message and per-conversation overhead are always recomputed at runtime and are not cached.
-- `data-*` and `reasoning` parts are skipped and do not receive cache entries.
+- Cache entries are ignored and recomputed if cache version/tokenizer source doesn't match.
+- Per-message and per-conversation overhead are always recomputed at runtime and aren't cached.
+- `data-*` and `reasoning` parts are skipped and don't receive cache entries.
 
 ## Examples
 
@@ -283,7 +285,7 @@ observationalMemory: {
 
 Setting `bufferTokens: false` disables both observation and reflection async buffering. Observations and reflections will run synchronously when their thresholds are reached.
 
-> **Note:** Async buffering is not supported with `scope: 'resource'` and is automatically disabled in resource scope.
+> **Note:** Async buffering isn't supported with `scope: 'resource'` and is automatically disabled in resource scope.
 
 ## Streaming data parts
 

package/.docs/reference/memory/recall.md

@@ -2,7 +2,7 @@
 
 the `.recall()` method retrieves messages from a specific thread, with support for pagination, filtering options, and semantic search.
 
-## Usage Example
+## Usage example
 
 ```typescript
 await memory?.recall({ threadId: 'user-123' })

package/.docs/reference/observability/tracing/bridges/otel.md

@@ -12,7 +12,7 @@ new OtelBridge()
 
 ## Methods
 
-### executeInContext
+### `executeInContext`
 
 ```typescript
 executeInContext<T>(spanId: string, fn: () => Promise<T>): Promise<T>
@@ -22,7 +22,7 @@ Executes an async function within the OTEL context of a Mastra span. OTEL-instru
 
 **Returns:** `Promise<T>` - The result of the function execution.
 
-### executeInContextSync
+### `executeInContextSync`
 
 ```typescript
 executeInContextSync<T>(spanId: string, fn: () => T): T
@@ -38,9 +38,9 @@ Executes a synchronous function within the OTEL context of a Mastra span.
 async shutdown(): Promise<void>
 ```
 
-Shuts down the bridge and cleans up resources. Ends any spans that were not properly closed.
+Shuts down the bridge and cleans up resources. Ends any spans that weren't properly closed.
 
-## Usage Examples
+## Usage examples
 
 ### Basic Usage
 
@@ -92,13 +92,13 @@ const mastra = new Mastra({
 })
 ```
 
-## OpenTelemetry Setup Requirements
+## `OpenTelemetry` setup requirements
 
 The OtelBridge requires an active OpenTelemetry SDK to function. The bridge reads from OTEL's ambient context.
 
 See the [OtelBridge Guide](https://mastra.ai/docs/observability/tracing/bridges/otel) for complete setup instructions, including how to configure OTEL instrumentation and run your application.
 
-## Tags Support
+## Tags support
 
 The OtelBridge supports trace tagging for categorization and filtering. Tags are only applied to root spans and are included as the `mastra.tags` attribute on native OTEL spans.
 

package/.docs/reference/observability/tracing/configuration.md

@@ -1,6 +1,6 @@
 # Configuration
 
-## ObservabilityRegistryConfig
+## `ObservabilityRegistryConfig`
 
 ```typescript
 interface ObservabilityRegistryConfig {
@@ -16,7 +16,7 @@ interface ObservabilityRegistryConfig {
 
 **configSelector** (`ConfigSelector`): Runtime configuration selector function
 
-## ObservabilityInstanceConfig
+## `ObservabilityInstanceConfig`
 
 ```typescript
 interface ObservabilityInstanceConfig {
@@ -55,7 +55,7 @@ interface ObservabilityInstanceConfig {
 
 **serializationOptions.maxObjectKeys** (`number`): Maximum number of keys in objects (default: 50)
 
-## SamplingStrategy
+## `SamplingStrategy`
 
 ```typescript
 type SamplingStrategy =
@@ -65,7 +65,7 @@ type SamplingStrategy =
   | { type: 'custom'; sampler: (options?: TracingOptions) => boolean }
 ```
 
-## ConfigSelector
+## `ConfigSelector`
 
 ```typescript
 type ConfigSelector = (
@@ -74,7 +74,7 @@ type ConfigSelector = (
 ) => string | undefined
 ```
 
-## ConfigSelectorOptions
+## `ConfigSelectorOptions`
 
 ```typescript
 interface ConfigSelectorOptions {
@@ -82,11 +82,11 @@ interface ConfigSelectorOptions {
 }
 ```
 
-# Registry Methods
+## Registry methods
 
 The Observability class provides methods for managing observability instances:
 
-## registerInstance
+### `registerInstance`
 
 ```typescript
 registerInstance(
@@ -98,7 +98,7 @@ registerInstance(
 
 Registers an observability instance in the registry.
 
-## getInstance
+### `getInstance`
 
 ```typescript
 getInstance(name: string): ObservabilityInstance | undefined;
@@ -106,7 +106,7 @@ getInstance(name: string): ObservabilityInstance | undefined;
 
 Retrieves an observability instance by name.
 
-## getDefaultInstance
+### `getDefaultInstance`
 
 ```typescript
 getDefaultInstance(): ObservabilityInstance | undefined;
@@ -114,7 +114,7 @@ getDefaultInstance(): ObservabilityInstance | undefined;
 
 Returns the default observability instance.
 
-## getSelectedInstance
+### `getSelectedInstance`
 
 ```typescript
 getSelectedInstance(
@@ -124,7 +124,7 @@ getSelectedInstance(
 
 Returns the observability instance selected by the config selector or default.
 
-## listInstances
+### `listInstances`
 
 ```typescript
 listInstances(): ReadonlyMap<string, ObservabilityInstance>;
@@ -132,7 +132,7 @@ listInstances(): ReadonlyMap<string, ObservabilityInstance>;
 
 Returns all registered observability instances.
 
-## hasInstance
+### `hasInstance`
 
 ```typescript
 hasInstance(name: string): boolean;
@@ -140,7 +140,7 @@ hasInstance(name: string): boolean;
 
 Checks if an observability instance exists.
 
-## setConfigSelector
+### `setConfigSelector`
 
 ```typescript
 setConfigSelector(selector: ConfigSelector): void;
@@ -148,7 +148,7 @@ setConfigSelector(selector: ConfigSelector): void;
 
 Sets the config selector function.
 
-## unregisterInstance
+### `unregisterInstance`
 
 ```typescript
 unregisterInstance(name: string): boolean;
@@ -156,7 +156,7 @@ unregisterInstance(name: string): boolean;
 
 Removes an observability instance from the registry.
 
-## clear
+### clear
 
 ```typescript
 clear(): void;
@@ -164,7 +164,7 @@ clear(): void;
 
 Clears all instances without shutdown.
 
-## shutdown
+### shutdown
 
 ```typescript
 async shutdown(): Promise<void>;
@@ -172,7 +172,7 @@ async shutdown(): Promise<void>;
 
 Shuts down all observability instances and clears the registry.
 
-## See Also
+## See also
 
 ### Documentation
 

package/.docs/reference/observability/tracing/exporters/arize.md

@@ -8,7 +8,7 @@ Sends Tracing data to Arize Phoenix, Arize AX, or any OpenTelemetry-compatible o
 new ArizeExporter(config: ArizeExporterConfig)
 ```
 
-## ArizeExporterConfig
+## `ArizeExporterConfig`
 
 ```typescript
 type ArizeExporterConfig = Omit<OtelExporterConfig, 'provider'> & {
@@ -38,7 +38,7 @@ Non-reserved span attributes are serialized into the OpenInference `metadata` pa
 
 ## Methods
 
-### exportTracingEvent
+### `exportTracingEvent`
 
 ```typescript
 async exportTracingEvent(event: TracingEvent): Promise<void>
@@ -106,11 +106,11 @@ const exporter = new ArizeExporter({
 })
 ```
 
-## OpenInference Semantic Conventions
+## `OpenInference` semantic conventions
 
 The ArizeExporter implements [OpenInference Semantic Conventions](https://github.com/Arize-ai/openinference/tree/main/spec) for generative AI applications, providing standardized trace structure across different observability platforms.
 
-## Tags Support
+## Tags support
 
 The ArizeExporter supports trace tagging for categorization and filtering. Tags are only applied to root spans and are mapped to the native OpenInference `tag.tags` semantic convention.
 

package/.docs/reference/observability/tracing/exporters/braintrust.md

@@ -8,7 +8,7 @@ Sends Tracing data to Braintrust for eval and observability.
 new BraintrustExporter(config: BraintrustExporterConfig)
 ```
 
-## BraintrustExporterConfig
+## `BraintrustExporterConfig`
 
 ```typescript
 interface BraintrustExporterConfig extends BaseExporterConfig {
@@ -26,7 +26,7 @@ Extends `BaseExporterConfig`, which includes:
 
 ## Methods
 
-### exportTracingEvent
+### `exportTracingEvent`
 
 ```typescript
 async exportTracingEvent(event: TracingEvent): Promise<void>
@@ -80,7 +80,7 @@ const exporter = new BraintrustExporter({
 })
 ```
 
-## Span Type Mapping
+## Span type mapping
 
 | Span Type                   | Braintrust Type |
 | --------------------------- | --------------- |

package/.docs/reference/observability/tracing/exporters/cloud-exporter.md

@@ -8,7 +8,7 @@ Sends traces to Mastra Cloud for online visualization and monitoring.
 new CloudExporter(config?: CloudExporterConfig)
 ```
 
-## CloudExporterConfig
+## `CloudExporterConfig`
 
 ```typescript
 interface CloudExporterConfig extends BaseExporterConfig {
@@ -34,7 +34,7 @@ Extends `BaseExporterConfig`, which includes:
 - `logger?: IMastraLogger` - Logger instance
 - `logLevel?: LogLevel | 'debug' | 'info' | 'warn' | 'error'` - Log level (default: INFO)
 
-## Environment Variables
+## Environment variables
 
 The exporter reads these environment variables if not provided in config:
 
@@ -49,7 +49,7 @@ readonly name = 'mastra-cloud-observability-exporter';
 
 ## Methods
 
-### exportTracingEvent
+### `exportTracingEvent`
 
 ```typescript
 async exportTracingEvent(event: TracingEvent): Promise<void>
@@ -90,7 +90,7 @@ The exporter batches spans for efficient network usage:
 - Flushes when `maxBatchWaitMs` elapsed since first span in batch
 - Flushes on `shutdown()`
 
-### Error Handling
+### Error handling
 
 - Uses exponential backoff retry with `maxRetries` attempts
 - Drops batches after all retries fail
@@ -102,7 +102,7 @@ The exporter batches spans for efficient network usage:
 - Ignores `SPAN_STARTED` and `SPAN_UPDATED` events
 - Formats spans to MastraCloudSpanRecord format
 
-## MastraCloudSpanRecord
+## `MastraCloudSpanRecord`
 
 Internal format for cloud spans:
 
@@ -143,7 +143,7 @@ const customExporter = new CloudExporter({
 })
 ```
 
-## See Also
+## See also
 
 ### Documentation
 

package/.docs/reference/observability/tracing/exporters/console-exporter.md

@@ -22,7 +22,7 @@ readonly name = 'tracing-console-exporter';
 
 ## Methods
 
-### exportTracingEvent
+### `exportTracingEvent`
 
 ```typescript
 async exportTracingEvent(event: TracingEvent): Promise<void>
@@ -38,7 +38,7 @@ async shutdown(): Promise<void>
 
 Logs shutdown message.
 
-## Output Format
+## Output format
 
 The exporter outputs different formats based on event type:
 
@@ -107,7 +107,7 @@ const exporterWithLogger = new ConsoleExporter({
 })
 ```
 
-## Implementation Details
+## Implementation details
 
 - Formats attributes as JSON with 2-space indentation
 - Calculates and displays span duration in milliseconds
@@ -115,7 +115,7 @@ const exporterWithLogger = new ConsoleExporter({
 - Logs unimplemented event types as warnings
 - Uses 80-character separator lines between events
 
-## See Also
+## See also
 
 ### Documentation
 

package/.docs/reference/observability/tracing/exporters/datadog.md

@@ -8,7 +8,7 @@ Sends Tracing data to Datadog's LLM Observability product for monitoring and ana
 new DatadogExporter(config: DatadogExporterConfig)
 ```
 
-## DatadogExporterConfig
+## `DatadogExporterConfig`
 
 ```typescript
 interface DatadogExporterConfig extends BaseExporterConfig {
@@ -29,7 +29,7 @@ Extends `BaseExporterConfig`, which includes:
 
 ## Methods
 
-### exportTracingEvent
+### `exportTracingEvent`
 
 ```typescript
 async exportTracingEvent(event: TracingEvent): Promise<void>
@@ -87,7 +87,7 @@ const exporter = new DatadogExporter({
 })
 ```
 
-## Span Mapping
+## Span mapping
 
 Mastra span types are mapped to Datadog LLMObs span kinds:
 
@@ -103,7 +103,7 @@ Mastra span types are mapped to Datadog LLMObs span kinds:
 
 All unmapped span types (including `MODEL_CHUNK`, `WORKFLOW_STEP`, `GENERIC`, and future span types) automatically default to `task`.
 
-## Environment Variables
+## Environment variables
 
 The exporter reads configuration from these environment variables: