@mastra/memory 1.24.0-alpha.0 → 1.25.0-alpha.0

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

@@ -4,7 +4,7 @@
 
 **Added in:** `@mastra/memory@1.1.0`
 
-Observational Memory (OM) is Mastra's memory system for long-context agentic memory. Two background agents — an **Observer** that watches conversations and creates observations, and a **Reflector** that restructures observations by combining related items, reflecting on overarching patterns, and condensing where possible — maintain an observation log that replaces raw message history as it grows.
+Observational Memory (OM) is Mastra's memory system for long-context agentic memory. An **Observer** watches conversations and creates observations. A **Reflector** restructures those observations by combining related items and condensing overarching patterns. Together, they maintain an observation log that replaces raw message history as it grows.
 
 ## Usage
 
@@ -27,7 +27,7 @@ export const agent = new Agent({
 
 ## Configuration
 
-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`.
+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, set `model` at the top level or on `observation.model` and/or `reflection.model`; when all model fields are omitted, OM falls back to `google/gemini-2.5-flash`.
 
 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.
 
@@ -35,7 +35,7 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **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 | ModelByInputTokens | 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)`)
+**model** (`string | LanguageModel | DynamicModel | ModelByInputTokens | 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 this and observation.model/reflection.model are all omitted, OM falls back to google/gemini-2.5-flash. Use "default" to explicitly use the default model (google/gemini-2.5-flash). (Default: `'google/gemini-2.5-flash'`)
 
 **scope** (`'resource' | 'thread'`): Memory scope for observations. 'thread' keeps observations per-thread. 'resource' (experimental) shares observations across all threads for a resource, enabling cross-conversation memory. (Default: `'thread'`)
 
@@ -47,7 +47,9 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **temporalMarkers** (`boolean`): Insert temporal-gap reminder markers before new user messages when the previous message in the thread is at least 10 minutes older. The marker is persisted in memory, emitted as an inline reminder event so clients can render it specially, and shown to the observer so it can anchor observations to when events occurred. (Default: `false`)
 
-**retrieval** (`boolean | { vector?: boolean; scope?: 'thread' | 'resource' }`): Enable retrieval-mode observation groups as durable pointers to raw message history. true enables cross-thread browsing by default. { vector: true } also enables semantic search using Memory's vector store and embedder. { scope: 'thread' } restricts the recall tool to the current thread only. Default scope is 'resource'. (Default: `false`)
+**retrieval** (`boolean | { vector?: boolean; scope?: 'thread' | 'resource' }`): Let the agent look up the raw message history behind its observations. Observation groups keep durable pointers to the original messages, and a recall tool is registered so the agent can browse them. true enables cross-thread browsing by default. { vector: true } also enables semantic search using Memory's vector store and embedder. { scope: 'thread' } restricts the recall tool to the current thread only. Default scope is 'resource'. (Default: `false`)
+
+**hooks** (`ObserveHooks`): Lifecycle hooks fired for every observation/reflection cycle — the manual observe()/reflect() APIs, turn-driven synchronous observation, and fire-and-forget async buffering. Callbacks receive threadId/resourceId/trigger call context ('manual' | 'turn-sync' | 'async-buffer'), and the end hooks (onObservationEnd/onReflectionEnd) additionally receive the OM model call's token usage and providerMetadata (where providers such as the AI Gateway report per-call cost), so apps can account for OM model spend without wrapping the observer/reflector models in middleware. Failed async-buffered cycles never throw; they report through the end hook's error field. Errors thrown by these hooks are caught and logged — they never fail the cycle.
 
 **observation** (`ObservationalMemoryObservationConfig`): Configuration for the observation step. Controls when the Observer agent runs and how it behaves.
 
@@ -59,29 +61,33 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **observation.extract** (`Extractor[]`): Custom values to extract after observation. Schema-less extractors are requested inline in the Observer output. Schema-backed extractors run as a follow-up structured output call and are stored in thread OM metadata.
 
-**observation.observeAttachments** (`boolean | string[]`): Controls which image/file attachments are forwarded to the Observer model alongside their placeholder text lines. true (default) forwards all attachments. false drops all attachments while keeping placeholders visible. An array is a case-insensitive mimeType allowlist supporting exact matches ('application/pdf'), wildcard subtypes ('image/\*'), and bare '\*' for everything. Useful when the Observer model is text-only (e.g. some DeepSeek endpoints) while the main agent uses a multimodal model. Tool-result attachments are filtered using the same rule.
+**observation.manageWorkingMemory** (`boolean`): Let the Observer manage working memory through OM extraction. Adds WorkingMemoryExtractor, defaults workingMemory.agentManaged to false, and defaults workingMemory.useStateSignals to true. See Working memory updates.
+
+**observation.observeAttachments** (`'auto' | boolean | string[]`): Controls which image/file attachments are forwarded to the Observer model alongside their placeholder text lines. true (default) forwards all attachments. false drops all attachments while keeping placeholders visible. 'auto' uses the provider capabilities registry to decide: attachments are forwarded when the Observer model supports multimodal input, dropped otherwise, and forwarded when no capability data is available for the model. An array is a case-insensitive mimeType allowlist supporting exact matches ('application/pdf'), wildcard subtypes ('image/\*'), and bare '\*' for everything. Useful when the Observer model is text-only (e.g. some DeepSeek endpoints) while the main agent uses a multimodal model. Tool-result attachments are filtered using the same rule.
 
 **observation.messageTokens** (`number`): Token count of unobserved messages that triggers observation. When unobserved message tokens exceed this threshold, the Observer agent is called. Text is estimated locally with tokenx. Image parts are included with model-aware heuristics 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.
 
-**observation.modelSettings** (`ObservationalMemoryModelSettings`): Model settings for the Observer agent.
+**observation.modelSettings** (`ObservationalMemoryModelSettings`): Model settings for the Observer agent. The maxOutputTokens: 100\_000 default is only applied with default model selection (no model set, "default", or a ModelByInputTokens selector). Custom models get no maxOutputTokens default.
 
 **observation.modelSettings.temperature** (`number`): Temperature for generation. Lower values produce more consistent output.
 
-**observation.modelSettings.maxOutputTokens** (`number`): Maximum output tokens. Set high to prevent truncation of observations.
+**observation.modelSettings.maxOutputTokens** (`number`): Maximum output tokens. Set high to prevent truncation of observations. The 100000 default is only applied with default model selection; custom models get no default.
 
-**observation.bufferTokens** (`number | false`): Token interval for async background observation buffering. Can be an absolute token count (e.g. 5000) or a fraction of messageTokens (e.g. 0.25 = buffer every 25% of threshold). When set, observations run in the background at this interval, storing results in a buffer. When the main messageTokens threshold is reached, buffered observations activate instantly without a blocking LLM call. Must resolve to less than messageTokens. Set to false to explicitly disable all async buffering (both observation and reflection).
+**observation.providerOptions** (`ProviderOptions`): Provider-specific options passed to the Observer agent, such as Google thinking configuration.
+
+**observation.bufferTokens** (`number | false`): How often background observation buffering runs. Values between 0 and 1 are fractions of messageTokens: 0.25 buffers every 25% of the threshold (7.5k tokens with the default 30k). Values of 1 or more are absolute token counts: 5000 buffers every 5k tokens. Buffered observations are stored until the messageTokens threshold is reached, then activate instantly without a blocking LLM call. Must resolve to less than messageTokens. Set to false to disable all async buffering (both observation and reflection).
 
 **observation.bufferOnIdle** (`boolean`): Run background observation buffering when an agent turn ends and the agent becomes idle. This is separate from bufferTokens, which controls step-time async buffering. Set this to true to buffer short idle turns without waiting for the next turn or the messageTokens threshold.
 
-**observation.bufferActivation** (`number`): Controls how much of the message window to retain after activation. Accepts a ratio (0-1) or an absolute token count (≥ 1000). For example, 0.8 means: activate enough buffers to remove 80% of messageTokens and leave 20% as active message history. An absolute token count like 4000 targets a goal of keeping \~4k message tokens remaining after activation. Higher values remove more message history per activation when using a ratio. Higher values keep more message history when using a token count.
+**observation.bufferActivation** (`number`): How much of the message window to clear when buffered observations activate. Values between 0 and 1 are the fraction of messageTokens to remove: 0.8 removes \~80% of the message history and keeps \~20% (6k tokens with the default 30k). Values of 1000 or more are the token count to keep: 4000 keeps \~4k message tokens after activation. Note the direction flips: a higher ratio removes more history, while a higher token count keeps more.
 
-**observation.activateAfterIdle** (`number | string | false | "auto"`): Time before buffered observations are forced to activate after inactivity. Accepts milliseconds, a duration string, "auto" for a provider-aware prompt cache TTL, or false. If unset, the top-level activateAfterIdle value is used for observations. Set false to disable the top-level idle setting for observations.
+**observation.activateAfterIdle** (`number | string | false | "auto"`): Time before buffered observations are forced to activate after inactivity. Accepts milliseconds, a duration string, "auto" for a provider-aware prompt cache TTL, or false. If unset, the top-level activateAfterIdle value is used for observations. Set false to disable the top-level idle setting for observations. Currently only applied when using the standalone ObservationalMemory class; new Memory(...) applies the top-level activateAfterIdle only.
 
-**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.
+**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`): Token threshold above which synchronous (blocking) observation is forced. Between messageTokens and blockAfter, only async buffering/activation is used. Above blockAfter, a synchronous observation runs as a last resort, while buffered activation still preserves a minimum remaining context (min(1000, retention floor)). Accepts a multiplier (1 < value < 2, multiplied by messageTokens) or an absolute token count (≥ 2, must be greater than messageTokens). Only relevant when bufferTokens is set. Defaults to 1.2 when async buffering is enabled.
+**observation.blockAfter** (`number`): Safety net that forces a synchronous (blocking) observation when background buffering can't keep up. Values from 1 up to (but not including) 100 are multipliers of messageTokens: 1.2 forces a blocking observation at 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. Between messageTokens and blockAfter, only async buffering and activation run; buffered activation still preserves a minimum remaining context (the smaller of 1000 tokens or the retention floor). 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.
 
@@ -95,19 +101,21 @@ OM performs thresholding with fast local token estimation. Text uses `tokenx`, a
 
 **reflection.observationTokens** (`number`): Token count of observations that triggers reflection. When observation tokens exceed this threshold, the Reflector agent is called to condense them.
 
-**reflection.modelSettings** (`ObservationalMemoryModelSettings`): Model settings for the Reflector agent.
+**reflection.modelSettings** (`ObservationalMemoryModelSettings`): Model settings for the Reflector agent. The maxOutputTokens: 100\_000 default is only applied with default model selection (no model set, "default", or a ModelByInputTokens selector). Custom models get no maxOutputTokens default.
 
 **reflection.modelSettings.temperature** (`number`): Temperature for generation. Lower values produce more consistent output.
 
-**reflection.modelSettings.maxOutputTokens** (`number`): Maximum output tokens. Set high to prevent truncation of observations.
+**reflection.modelSettings.maxOutputTokens** (`number`): Maximum output tokens. Set high to prevent truncation of observations. The 100000 default is only applied with default model selection; custom models get no default.
+
+**reflection.providerOptions** (`ProviderOptions`): Provider-specific options passed to the Reflector agent, such as Google thinking configuration.
 
-**reflection.bufferActivation** (`number`): Ratio (0-1) controlling when async reflection buffering starts. When observation tokens reach observationTokens \* bufferActivation, reflection runs in the background. On activation at the full threshold, the buffered reflection replaces the observations it covers, preserving any new observations appended after that range.
+**reflection.bufferActivation** (`number`): When background reflection starts, as a ratio (0-1) of observationTokens: 0.5 starts reflecting in the background once observations reach 50% of the threshold (20k tokens with the default 40k). When the full threshold is reached, the buffered reflection replaces the observations it covers, preserving any new observations appended after that range.
 
-**reflection.activateAfterIdle** (`number | string | false | "auto"`): Time before buffered reflections are forced to activate after inactivity. Accepts milliseconds, a duration string, "auto" for a provider-aware prompt cache TTL, or false. Reflections do not inherit top-level activateAfterIdle; set this explicitly to opt reflections into idle activation.
+**reflection.activateAfterIdle** (`number | string | false | "auto"`): Time before buffered reflections are forced to activate after inactivity. Accepts milliseconds, a duration string, "auto" for a provider-aware prompt cache TTL, or false. Reflections do not inherit top-level activateAfterIdle; set this explicitly to opt reflections into idle activation. Currently only applied when using the standalone ObservationalMemory class; this setting has no effect through new Memory(...).
 
-**reflection.activateOnProviderChange** (`boolean`): Force buffered reflections to activate when the actor provider or model changes. Reflections do not inherit top-level activateOnProviderChange; set this explicitly to opt reflections into provider-change activation.
+**reflection.activateOnProviderChange** (`boolean`): Force buffered reflections to activate when the actor provider or model changes. Reflections do not inherit top-level activateOnProviderChange; set this explicitly to opt reflections into provider-change activation. Currently only applied when using the standalone ObservationalMemory class; this setting has no effect through new Memory(...).
 
-**reflection.blockAfter** (`number`): Token threshold above which synchronous (blocking) reflection is forced. Between observationTokens and blockAfter, only async buffering/activation is used. Above blockAfter, a synchronous reflection runs as a last resort. Accepts a multiplier (1 < value < 2, multiplied by observationTokens) or an absolute token count (≥ 2, must be greater than observationTokens). Only relevant when bufferActivation is set. Defaults to 1.2 when async reflection is enabled.
+**reflection.blockAfter** (`number`): Safety net that forces a synchronous (blocking) reflection when background reflection can't keep up. Values from 1 up to (but not including) 100 are multipliers of observationTokens: 1.2 forces a blocking reflection at 120% of the threshold (48k tokens with the default 40k). Values of 100 or more are absolute token counts and must be greater than observationTokens. Between observationTokens and blockAfter, only async buffering and activation run. Only relevant when bufferActivation is set. Defaults to 1.2 when async reflection is enabled.
 
 ### Token estimate metadata cache
 
@@ -150,7 +158,7 @@ const memory = new Memory({
 
 **name** (`string`): Human-readable extractor name. OM slugifies this value into the extractor slug. Names must be unique after slug generation.
 
-**slug** (`string`): Generated stable identifier for persisted values and XML tags. Slugs use lowercase letters, numbers, and hyphens. Built-in slugs and reserved XML tags cannot be used by custom extractors.
+**slug** (`string`): Read-only property derived from name — not a constructor option. Generated stable identifier for persisted values and XML tags. Slugs use lowercase letters, numbers, and hyphens. Built-in slugs and reserved XML tags cannot be used by custom extractors.
 
 **instructions** (`string | (context) => string`): Instructions for what to extract and when to update the value. Use a function to derive instructions from runtime context.
 
@@ -158,6 +166,8 @@ const memory = new Memory({
 
 **includePreviousExtraction** (`boolean`): Controls whether the previous extraction is shown to the extractor on future OM runs. Set to false for values that should only come from the current OM run. (Default: `true`)
 
+**metadataKeyPath** (`string | false`): Dot-separated OM metadata path used to persist the extracted value. Set to false to skip OM metadata persistence entirely. (Default: `'extracted.<slug>'`)
+
 **onExtracted** (`(context) => T | void | Promise<T | void>`): Optional hook called after a custom extractor returns a value and before metadata is persisted. Returning a value replaces the extracted value. Throwing records an extraction failure.
 
 ### Extraction behavior
@@ -170,7 +180,7 @@ const memory = new Memory({
 - Schema-less extractors are inline string extractors emitted directly in the Observer or Reflector output.
 - Dynamic extractor functions receive runtime context, including `source`, `threadId`, `resourceId`, `mainAgent`, `memory`, and `requestContext` when available.
 - `WorkingMemoryExtractor` uses the normal extractor pipeline to update working memory through the active `Memory` instance. It uses structured extraction when working memory has a JSON schema and skips OM metadata persistence, so the working memory payload isn't duplicated under OM extracted metadata.
-- `observationalMemory.observation.manageWorkingMemory` adds `WorkingMemoryExtractor`, defaults `workingMemory.agentManaged` to `false`, and defaults `workingMemory.useStateSignals` to `true` when working memory is enabled.
+- `observationalMemory.observation.manageWorkingMemory` adds `WorkingMemoryExtractor` and defaults `workingMemory.agentManaged` to `false`. It defaults `workingMemory.useStateSignals` to `true` when working memory is enabled.
 - Extraction failures are reported in OM marker data and don't discard other successful extracted values.
 
 ## Examples
@@ -269,7 +279,7 @@ export const agent = new Agent({
   id: 'my-agent',
   name: 'my-agent',
   instructions: 'You are a helpful assistant.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     options: {
       observationalMemory: {
@@ -290,7 +300,7 @@ export const agent = new Agent({
   id: 'my-agent',
   name: 'my-agent',
   instructions: 'You are a helpful assistant.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     options: {
       observationalMemory: {
@@ -318,7 +328,7 @@ export const agent = new Agent({
   id: 'health-assistant',
   name: 'health-assistant',
   instructions: 'You are a health and wellness assistant.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     options: {
       observationalMemory: {
@@ -341,16 +351,16 @@ export const agent = new Agent({
 
 ### Async buffering
 
-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.
+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 is: **buffer → activate → remove messages → repeat**. Background Observer calls run at `bufferTokens` intervals, each producing a chunk of observations. At threshold, chunks activate: observations move into the log, raw messages are removed from context. The `blockAfter` threshold forces a synchronous fallback if buffering can't keep up.
+The lifecycle follows **buffer → activate → remove messages → repeat**. Background Observer calls run at `bufferTokens` intervals, each producing a chunk of observations. At threshold, chunks activate: observations move into the log, raw messages are removed from context. The `blockAfter` threshold forces a synchronous fallback if buffering can't keep up.
 
 Default settings:
 
-- `observation.bufferTokens: 0.2` — buffer every 20% of `messageTokens` (e.g. every \~6k tokens with a 30k threshold)
-- `observation.bufferActivation: 0.8` — on activation, remove enough messages to keep only 20% of the threshold remaining
+- `observation.bufferTokens: 0.2`: Buffer every 20% of `messageTokens` (e.g. every \~6k tokens with a 30k threshold)
+- `observation.bufferActivation: 0.8`: On activation, remove enough messages to keep only 20% of the threshold remaining
 - Buffered observations include continuation hints (`suggestedResponse`, `currentTask`) that survive activation to maintain conversational continuity
-- `reflection.bufferActivation: 0.5` — start background reflection at 50% of observation threshold
+- `reflection.bufferActivation: 0.5`: start background reflection at 50% of observation threshold
 
 To customize:
 
@@ -476,7 +486,7 @@ interface DataOmStatusPart {
 }
 ```
 
-`buffered.reflection.inputObservationTokens` is the size of the observations that were sent to the Reflector. `buffered.reflection.observationTokens` is the compressed result — the size of what will replace those observations when the reflection activates. A client can use these two values to show a compression ratio.
+`buffered.reflection.inputObservationTokens` is the size of the observations that were sent to the Reflector. `buffered.reflection.observationTokens` is the compressed result: the size of what will replace those observations when the reflection activates. A client can use these two values to show a compression ratio.
 
 Clients can derive percentages and post-activation estimates from the raw values:
 
@@ -643,7 +653,7 @@ Emitted when async buffering fails. The system falls back to synchronous process
 
 ### `data-om-activation`
 
-Emitted when buffered observations or reflections are activated (moved into the active context window). This is an instant operation — no LLM call is involved.
+Emitted when buffered observations or reflections are activated (moved into the active context window). This is an instant operation: no LLM call is involved.
 
 **cycleId** (`string`): Unique ID for this activation event.
 
@@ -663,18 +673,45 @@ Emitted when buffered observations or reflections are activated (moved into the
 
 **observations** (`string`): The activated observations text.
 
+**triggeredBy** (`'threshold' | 'ttl' | 'provider_change'`): Whether activation was triggered by threshold crossing, activateAfterIdle expiry, or a model/provider change.
+
+**lastActivityAt** (`number`): Unix-ms timestamp of the last assistant message part used for TTL checks.
+
+**ttlExpiredMs** (`number`): How long activateAfterIdle had been exceeded when activation fired.
+
+**previousModel** (`string`): Previous assistant model identifier that triggered activation (e.g. openai/gpt-4o).
+
+**currentModel** (`string`): Current actor model identifier that triggered activation.
+
 **recordId** (`string`): The OM record ID.
 
 **threadId** (`string`): This thread's ID.
 
 **config** (`ObservationMarkerConfig`): Snapshot of config at activation time.
 
+### `data-om-thread-update`
+
+Emitted when the Observer updates the thread title. Only emitted when `observation.threadTitle` is enabled.
+
+**cycleId** (`string`): Unique ID for this observation cycle — shared with observation markers.
+
+**threadId** (`string`): The thread ID that was updated.
+
+**oldTitle** (`string`): The previous thread title. Undefined if the thread had no title.
+
+**newTitle** (`string`): The new thread title.
+
+**timestamp** (`string`): When this update occurred.
+
 ## Standalone usage
 
 Most users should use the `Memory` class above. Using `ObservationalMemory` directly is mainly useful for benchmarking, experimentation, or when you need to control processor ordering with other processors (like [guardrails](https://mastra.ai/docs/agents/guardrails)).
 
+The `ObservationalMemory` class is the engine; to attach it to an agent, wrap it in an `ObservationalMemoryProcessor`, which needs a `Memory` instance for loading and persisting messages. Note that `stores.memory` is typed as optional on storage adapters, so a non-null assertion (or a runtime check) is needed:
+
 ```typescript
-import { ObservationalMemory } from '@mastra/memory/processors'
+import { ObservationalMemory, ObservationalMemoryProcessor } from '@mastra/memory/processors'
+import { Memory } from '@mastra/memory'
 import { Agent } from '@mastra/core/agent'
 import { LibSQLStore } from '@mastra/libsql'
 
@@ -683,8 +720,11 @@ const storage = new LibSQLStore({
   url: 'file:./memory.db',
 })
 
+const memory = new Memory({ storage })
+
 const om = new ObservationalMemory({
-  storage: storage.stores.memory,
+  storage: storage.stores.memory!,
+  memory,
   model: 'google/gemini-2.5-flash',
   scope: 'resource',
   observation: {
@@ -695,13 +735,15 @@ const om = new ObservationalMemory({
   },
 })
 
+const omProcessor = new ObservationalMemoryProcessor(om, memory)
+
 export const agent = new Agent({
   id: 'my-agent',
   name: 'my-agent',
   instructions: 'You are a helpful assistant.',
   model: 'openai/gpt-5-mini',
-  inputProcessors: [om],
-  outputProcessors: [om],
+  inputProcessors: [omProcessor],
+  outputProcessors: [omProcessor],
 })
 ```
 
@@ -717,7 +759,7 @@ The standalone `ObservationalMemory` class accepts all the same options as the `
 
 ## Recall tool
 
-When `retrieval` is set (any truthy value), a `recall` tool is registered so the agent can page through raw messages behind observation group ranges. By default (scope `'resource'`), the tool supports listing threads (`mode: "threads"`), browsing other threads (`threadId`), and cross-thread search. With `retrieval: { vector: true }`, semantic search is available (`mode: "search"`). Set `scope: 'thread'` to restrict the tool to the current thread only. The tool is automatically added to the agent's tool list — no manual registration is needed.
+When `retrieval` is set (any truthy value), a `recall` tool is registered so the agent can page through raw messages behind observation group ranges. By default (scope `'resource'`), the tool supports listing threads (`mode: "threads"`), browsing other threads (`threadId`), and cross-thread search. With `retrieval: { vector: true }`, semantic search is available (`mode: "search"`). Set `scope: 'thread'` to restrict the tool to the current thread only. The tool is automatically added to the agent's tool list.
 
 ### Parameters
 
@@ -725,9 +767,11 @@ When `retrieval` is set (any truthy value), a `recall` tool is registered so the
 
 **query** (`string`): Search query for mode: "search". Finds messages semantically similar to this text across all threads for the current user.
 
-**cursor** (`string`): A message ID to anchor the recall query. Required for mode: "messages" when browsing the current thread. Extract the start or end ID from an observation group range (e.g. from \_range: \startId:endId\\\_, use either startId or endId). If a range string is passed directly, the tool returns a hint explaining how to extract the correct ID. Can be omitted when threadId is provided to start reading from the beginning of that thread.
+**cursor** (`string`): A message ID to anchor the recall query. Extract the start or end ID from an observation group range (e.g. from \_range: \startId:endId\\\_, use either startId or endId). If a range string is passed directly, the tool returns a hint explaining how to extract the correct ID. When both cursor and threadId are omitted for mode: "messages", the tool browses the current thread from the position set by anchor.
+
+**threadId** (`string`): Browse a different thread by its ID, or pass "current" for the active thread. Use mode: "threads" first to discover thread IDs. When provided without a cursor, reading starts from the beginning of the thread.
 
-**threadId** (`string`): Browse a different thread by its ID. Use mode: "threads" first to discover thread IDs. When provided without a cursor, reading starts from the beginning of the thread.
+**anchor** (`'start' | 'end'`): For mode: "messages" without a cursor, page from the start (oldest-first) or end (newest-first) of the thread. (Default: `'start'`)
 
 **page** (`number`): Pagination offset. For messages: positive values page forward from cursor, negative values page backward. For threads: page number (0-indexed). 0 is treated as 1 for messages. (Default: `1`)
 
@@ -735,6 +779,10 @@ When `retrieval` is set (any truthy value), a `recall` tool is registered so the
 
 **detail** (`'low' | 'high'`): Controls how much content is shown per message part. 'low' shows truncated text and tool names with positional indices (\[p0], \[p1]). 'high' shows full content including tool arguments and results, clamped to one part per call with continuation hints. (Default: `'low'`)
 
+**partType** (`'text' | 'tool-call' | 'tool-result' | 'reasoning' | 'image' | 'file'`): Filter results to only include message parts of this type. Only applies to mode: "messages".
+
+**toolName** (`string`): Filter results to only include tool-call and tool-result parts matching this tool name. Only applies to mode: "messages".
+
 **partIndex** (`number`): Fetch a single message part at full detail by its positional index. Use this when a low-detail recall shows an interesting part at \[p1] — call again with partIndex: 1 to see the full content without loading every part.
 
 **before** (`string`): For mode: "threads" only. Filter to threads created before this date. Accepts ISO 8601 format (e.g. "2026-03-15", "2026-03-10T00:00:00Z").
@@ -753,6 +801,8 @@ When `retrieval` is set (any truthy value), a `recall` tool is registered so the
 
 **limit** (`number`): The limit used for this query.
 
+**detail** (`'low' | 'high'`): The detail level used for this query.
+
 **hasNextPage** (`boolean`): Whether more messages exist after this page.
 
 **hasPrevPage** (`boolean`): Whether more messages exist before this page.
@@ -798,7 +848,7 @@ const selector = new ModelByInputTokens({
   upTo: {
     10_000: 'google/gemini-2.5-flash', // Fast for small inputs
     40_000: 'openai/gpt-5-mini', // Stronger for medium inputs
-    1_000_000: 'openai/gpt-5.5', // Most capable for large inputs
+    1_000_000: 'openai/gpt-5.6-sol', // Most capable for large inputs
   },
 })
 ```

package/dist/docs/references/reference-memory-summarizeConversation.md

@@ -2,11 +2,11 @@
 
 # summarizeConversation()
 
-The standalone `summarizeConversation()` function summarizes a conversation in one shot. It distills the messages you pass in with the same Observer plumbing that powers [Observational Memory](https://mastra.ai/reference/memory/observational-memory) — without Observational Memory attached to an agent, and without reading from or writing to storage.
+The standalone `summarizeConversation()` function summarizes a conversation in one shot. It distills the messages you pass in with the same Observer plumbing that powers [Observational Memory](https://mastra.ai/reference/memory/observational-memory): without Observational Memory attached to an agent, and without reading from or writing to storage.
 
-Nothing is written back to memory. The summary and extracted values are returned to you (and to each extractor's `onExtracted` hook), so you decide where they go — for example your own database.
+Nothing is written back to memory. The summary and extracted values are returned to you (and to each extractor's `onExtracted` hook), so you decide where they go: for example your own database.
 
-Use this when you already have the messages in hand and want explicit control over what gets summarized. To summarize a stored thread by ID instead, use [`Memory.summarizeThread()`](https://mastra.ai/reference/memory/summarizeThread), which loads the messages for you.
+Use this when you already have the messages in hand and want explicit control over what gets summarized. For a stored thread identified by ID, use [`Memory.summarizeThread()`](https://mastra.ai/reference/memory/summarizeThread), which loads the messages for you.
 
 ## Usage example
 

package/dist/docs/references/reference-memory-summarizeThread.md

@@ -2,13 +2,13 @@
 
 # Memory.summarizeThread()
 
-The `.summarizeThread()` method summarizes a thread's conversation in one shot. It loads the thread's messages from storage and distills them with the same Observer plumbing that powers [Observational Memory](https://mastra.ai/reference/memory/observational-memory) — as a standalone call, without Observational Memory attached to an agent.
+The `.summarizeThread()` method summarizes a thread's conversation in one shot. It loads the thread's messages from storage and distills them with the same Observer plumbing that powers [Observational Memory](https://mastra.ai/reference/memory/observational-memory): as a standalone call, without Observational Memory attached to an agent.
 
 Messages load page-by-page starting from the newest, bounded by `lastMessages` and `maxInputTokens`, so summarizing a long thread doesn't read its entire history from storage.
 
-Nothing is written back to memory. The summary and extracted values are returned to you (and to each extractor's `onExtracted` hook), so you decide where they go — for example your own database.
+Nothing is written back to memory. The summary and extracted values are returned to you (and to each extractor's `onExtracted` hook), so you decide where they go: for example your own database.
 
-Use this when a session ends and you want a summary or structured extraction of the whole conversation, such as a voice call at hang-up. To summarize messages you already have in hand (without loading them from a thread), use the standalone [`summarizeConversation()`](https://mastra.ai/reference/memory/summarizeConversation) function instead — it takes the same options with `messages` in place of `threadId`.
+Use this when a session ends and you want a summary or structured extraction of the whole conversation, such as a voice call at hang-up. For messages you already have in hand (without loading them from a thread), use the standalone [`summarizeConversation()`](https://mastra.ai/reference/memory/summarizeConversation) function instead. It takes the same options with `messages` in place of `threadId`.
 
 ## Usage example
 

package/dist/docs/references/reference-processors-token-limiter-processor.md

@@ -84,7 +84,7 @@ export const agent = new Agent({
   id: 'context-limited-agent',
   name: 'context-limited-agent',
   instructions: 'You are a helpful assistant',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({/* ... */}),
   inputProcessors: [
     new TokenLimiterProcessor({ limit: 4000 }), // Limits historical messages to ~4000 tokens
@@ -94,7 +94,7 @@ export const agent = new Agent({
 
 ### As a per-step input processor (limit multi-step token growth)
 
-When an agent uses tools across multiple steps (e.g. `maxSteps > 1`), each step accumulates conversation history from all previous steps. Use `inputProcessors` to also limit tokens at each step of the agentic loop — the `TokenLimiterProcessor` automatically applies to both the initial input and every subsequent step:
+When an agent uses tools across multiple steps (e.g. `maxSteps > 1`), each step accumulates conversation history from all previous steps. Use `inputProcessors` to also limit tokens at each step of the agentic loop. The `TokenLimiterProcessor` automatically applies to both the initial input and every subsequent step:
 
 ```typescript
 import { Agent } from '@mastra/core/agent'
@@ -104,7 +104,7 @@ export const agent = new Agent({
   id: 'multi-step-agent',
   name: 'multi-step-agent',
   instructions: 'You are a helpful research assistant with access to tools',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   inputProcessors: [
     new TokenLimiterProcessor({ limit: 8000 }), // Applied at every step
   ],
@@ -128,7 +128,7 @@ export const agent = new Agent({
   id: 'response-limited-agent',
   name: 'response-limited-agent',
   instructions: 'You are a helpful assistant',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   outputProcessors: [
     new TokenLimiterProcessor({
       limit: 1000,

package/dist/docs/references/reference-storage-dsql.md

@@ -183,7 +183,7 @@ storage.db // Database client for executing queries
 storage.pool // Underlying pg.Pool instance
 ```
 
-This enables direct queries and custom transaction management. When using these fields:
+It supports direct queries and custom transaction management. When using these fields:
 
 - You are responsible for proper connection and transaction handling.
 - Closing the store (`storage.close()`) will destroy the connection pool if it was created by the store.
@@ -199,7 +199,7 @@ Connections are authenticated with IAM. No database passwords are required. `@ma
 
 #### Single database, schema-based isolation
 
-Each cluster exposes a single database named `postgres`. Logical separation is done via schemas. The `schemaName` option controls where Mastra tables are created.
+Each cluster exposes a single database `postgres`. Logical separation is done via schemas. The `schemaName` option controls where Mastra tables are created.
 
 #### No PostgreSQL extensions
 
@@ -243,7 +243,7 @@ export const dsqlAgent = new Agent({
   name: 'DSQL Agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new DSQLStore({
       id: 'dsql-agent-storage',

package/dist/docs/references/reference-storage-dynamodb.md

@@ -2,7 +2,7 @@
 
 # DynamoDB storage
 
-The DynamoDB storage implementation provides a scalable and performant NoSQL database solution for Mastra, leveraging a single-table design pattern with [ElectroDB](https://electrodb.dev/).
+The DynamoDB storage implementation provides a high-capacity and performant NoSQL database solution for Mastra, using a single-table design pattern with [ElectroDB](https://electrodb.dev/).
 
 > **Observability Not Supported:** DynamoDB storage **doesn't support the observability domain**. Traces from the `MastraStorageExporter` can't be persisted to DynamoDB, and [Studio's](https://mastra.ai/docs/studio/overview) observability features won't work with DynamoDB as your only storage provider. To enable observability, use [composite storage](https://mastra.ai/reference/storage/composite) to route observability data to a supported provider like ClickHouse.
 
@@ -124,7 +124,7 @@ For local development, you can use [DynamoDB Local](https://docs.aws.amazon.com/
 
 ## TTL (time to live) configuration
 
-DynamoDB TTL allows you to automatically delete items after a specified time period. This is useful for:
+DynamoDB TTL allows you to automatically delete items after a specified duration for these use cases:
 
 - **Cost optimization**: Automatically remove old data to reduce storage costs
 - **Data lifecycle management**: Implement retention policies for compliance
@@ -259,19 +259,19 @@ Before diving into the architectural details, keep these key points in mind when
 
 ## Architectural approach
 
-This storage adapter utilizes a **single-table design pattern** leveraging [ElectroDB](https://electrodb.dev/), a common and recommended approach for DynamoDB. This differs architecturally from relational database adapters (like `@mastra/pg` or `@mastra/libsql`) that typically use multiple tables, each dedicated to a specific entity (threads, messages, etc.).
+This storage adapter utilizes a **single-table design pattern** with [ElectroDB](https://electrodb.dev/), a common and recommended approach for DynamoDB. This differs architecturally from relational database adapters (like `@mastra/pg` or `@mastra/libsql`) that typically use multiple tables, each dedicated to a specific entity (threads, messages, etc.).
 
 Key aspects of this approach:
 
-- **DynamoDB Native:** The single-table design is optimized for DynamoDB's key-value and query capabilities, often leading to better performance and scalability compared to mimicking relational models.
+- **DynamoDB Native:** The single-table design is optimized for DynamoDB's key-value and query capabilities, often leading to better performance and capacity compared to mimicking relational models.
 - **External Table Management:** Unlike some adapters that might offer helper functions to create tables via code, this adapter **expects the DynamoDB table and its associated Global Secondary Indexes (GSIs) to be provisioned externally** before use. Please refer to [TABLE\_SETUP.md](https://github.com/mastra-ai/mastra/blob/main/stores/dynamodb/TABLE_SETUP.md) for detailed instructions using tools like AWS CloudFormation or CDK. The adapter focuses solely on interacting with the pre-existing table structure.
 - **Consistency via Interface:** While the underlying storage model differs, this adapter adheres to the same `MastraStorage` interface as other adapters, ensuring it can be used interchangeably within the Mastra `Memory` component.
 
 ### Mastra Data in the Single Table
 
-Within the single DynamoDB table, different Mastra data entities (such as Threads, Messages, Traces, Evals, and Workflows) are managed and distinguished using ElectroDB. ElectroDB defines specific models for each entity type, which include unique key structures and attributes. This allows the adapter to store and retrieve diverse data types efficiently within the same table.
+Within the single DynamoDB table, different Mastra data entities (such as Threads, Messages, Traces, Evals, and Workflows) are managed and distinguished using ElectroDB. ElectroDB defines specific models for each entity type, which include unique key structures and attributes. It allows the adapter to store and retrieve diverse data types efficiently within the same table.
 
-For example, a `Thread` item might have a primary key like `THREAD#<threadId>`, while a `Message` item belonging to that thread might use `THREAD#<threadId>` as a partition key and `MESSAGE#<messageId>` as a sort key. The Global Secondary Indexes (GSIs), detailed in `TABLE_SETUP.md`, are strategically designed to support common access patterns across these different entities, such as fetching all messages for a thread or querying traces associated with a particular workflow.
+For example, a `Thread` item might have a primary key like `THREAD#<threadId>`, while a `Message` item belonging to that thread might use `THREAD#<threadId>` as a partition key and `MESSAGE#<messageId>` as a sort key. The Global Secondary Indexes (GSIs), detailed in `TABLE_SETUP.md`, are strategically designed to support common access patterns across these different entities, such as fetching all messages for a thread or querying traces associated with a workflow.
 
 ### Advantages of Single-Table Design
 
@@ -279,6 +279,6 @@ This implementation uses a single-table design pattern with ElectroDB, which off
 
 1. **Lower cost (potentially):** Fewer tables can simplify Read/Write Capacity Unit (RCU/WCU) provisioning and management, especially with on-demand capacity.
 2. **Better performance:** Related data can be co-located or accessed efficiently through GSIs, enabling fast lookups for common access patterns.
-3. **Simplified administration:** Fewer distinct tables to monitor, back up, and manage.
+3. **Simplified administration:** Fewer distinct tables to monitor and back up, with less to manage.
 4. **Reduced complexity in access patterns:** ElectroDB helps manage the complexity of item types and access patterns on a single table.
 5. **Transaction support:** DynamoDB transactions can be used across different "entity" types stored within the same table if needed.

package/dist/docs/references/reference-storage-mongodb.md

@@ -2,7 +2,7 @@
 
 # MongoDB storage
 
-The MongoDB storage implementation provides a scalable storage solution using MongoDB databases with support for both document storage and vector operations.
+The MongoDB storage implementation provides a high-capacity storage solution using MongoDB databases with support for both document storage and vector operations.
 
 ## Installation
 
@@ -210,7 +210,7 @@ export const mongodbAgent = new Agent({
   name: 'mongodb-agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new MongoDBStore({
       id: 'mongodb-storage',

package/dist/docs/references/reference-storage-postgresql.md

@@ -317,7 +317,7 @@ export const mastra = new Mastra({
 })
 ```
 
-This pattern ensures only one `PostgresStore` instance is created regardless of how many times the module is reloaded during development. The same pattern can be applied to other storage providers like `LibSQLStore`.
+The pattern ensures only one `PostgresStore` instance is created regardless of how many times the module is reloaded during development. The same pattern can be applied to other storage providers like `LibSQLStore`.
 
 > **Tip:** This singleton pattern is only necessary during local development with HMR. In production builds, modules are only loaded once.
 
@@ -337,7 +337,7 @@ export const pgAgent = new Agent({
   name: 'PG Agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new PostgresStore({
       id: 'pg-agent-storage',

package/dist/docs/references/reference-storage-redis.md

@@ -183,7 +183,7 @@ export const redisAgent = new Agent({
   name: 'Redis Agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new RedisStore({
       id: 'redis-agent-storage',

package/dist/docs/references/reference-storage-upstash.md

@@ -105,7 +105,7 @@ export const upstashAgent = new Agent({
   name: 'Upstash Agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new UpstashStore({
       id: 'upstash-agent-storage',

package/dist/docs/references/reference-vectors-libsql.md

@@ -85,7 +85,7 @@ const results = await store.query({
 
 ### `createIndex()`
 
-Creates a new vector collection. The index name must start with a letter or underscore and can only contain letters, numbers, and underscores. The dimension must be a positive integer.
+Creates a new vector collection. The index name must start with a letter or underscore and can only contain letters, numbers, and underscore characters. The dimension must be a positive integer.
 
 **indexName** (`string`): Name of the index to create
 
@@ -279,7 +279,7 @@ export const libsqlAgent = new Agent({
   name: 'libSQL Agent',
   instructions:
     'You are an AI agent with the ability to automatically recall memories from previous interactions.',
-  model: 'openai/gpt-5.5',
+  model: 'openai/gpt-5.6-sol',
   memory: new Memory({
     storage: new LibSQLStore({
       id: 'libsql-agent-storage',