@mastra/memory 1.33.0-alpha.3 → 1.33.0

package/dist/docs/SKILL.md

@@ -3,7 +3,7 @@ name: mastra-memory
 description: Documentation for @mastra/memory. Use when working with @mastra/memory APIs, configuration, or implementation.
 metadata:
   package: "@mastra/memory"
-  version: "1.33.0-alpha.3"
+  version: "1.33.0"
 ---
 
 ## When to use

package/dist/docs/assets/SOURCE_MAP.json

@@ -1,5 +1,5 @@
 {
-  "version": "1.33.0-alpha.3",
+  "version": "1.33.0",
   "package": "@mastra/memory",
   "exports": {},
   "modules": {

package/dist/docs/references/docs-agents-human-in-the-loop.md

@@ -120,12 +120,14 @@ The function can be asynchronous. For decisions that depend on the tool name and
 
 ```typescript
 import { Classifier } from '@mastra/core/classifier'
-import { model } from '../models/evaluation-model'
+import { createTypeSafeAi } from '@ai-sdk/typesafe-ai'
 import { agent } from './agent'
 
 const approvalClassifier = new Classifier({
   id: 'tool-approval-classifier',
-  model,
+  model: createTypeSafeAi({ apiKey: process.env.TYPESAFE_AI_API_KEY }).evaluationModel(
+    'jev-latest',
+  ),
   questions: {
     requiresApproval: {
       type: 'boolean',

package/dist/docs/references/docs-evals-evals-with-memory.md

@@ -10,15 +10,16 @@ Agents that use memory in `thread` scope, including observational memory, requir
 ObservationalMemory (scope: 'thread') requires a threadId, but none was found in RequestContext or MessageList.
 ```
 
-This page covers the three working patterns for running Mastra evals against memory-enabled agents, what each path supports, and which one to pick. A complete runnable repro for all three approaches lives in [`examples/evals-with-memory`](https://github.com/mastra-ai/mastra/tree/main/examples/evals-with-memory).
+Choose an approach based on how you want to share memory across eval items. For runnable examples, see [`examples/evals-with-memory`](https://github.com/mastra-ai/mastra/tree/main/examples/evals-with-memory).
 
 ## When to use which approach
 
-| Goal                                             | Approach                                                                                  |
-| ------------------------------------------------ | ----------------------------------------------------------------------------------------- |
-| One shared conversation across every item        | [`runEvals` with global `targetOptions.memory`](#shared-thread-with-runevals)             |
-| One independent thread per item, focused CI loop | [`runEvals` per item](#per-item-threads-with-runevals)                                    |
-| Per-item threads driven by a stored `Dataset`    | [`dataset.startExperiment` with an inline task](#dataset-experiments-with-an-inline-task) |
+| Goal                                                     | Approach                                                                                      |
+| -------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
+| One shared conversation across every item                | [`runEvals` with global `targetOptions.memory`](#shared-thread-with-runevals)                 |
+| One independent thread per item, focused CI loop         | [`runEvals` per item](#per-item-threads-with-runevals)                                        |
+| Fresh thread per item in a stored `Dataset`              | [`dataset.startExperiment` with a registered agent](https://mastra.ai/docs/evals/experiments) |
+| Explicit thread selection per item in a stored `Dataset` | [`dataset.startExperiment` with an inline task](#dataset-experiments-with-an-inline-task)     |
 
 Pre-seeding `RequestContext` with `MastraMemory` **isn't** a supported way to drive memory into an agent. Thread resolution reads `args.memory.thread`, `RequestContext.MastraMemory` is populated by `prepare-memory-step` after the agent has already resolved its thread.
 

package/dist/docs/references/docs-harness-background-tasks.md

@@ -231,7 +231,7 @@ When this `researchAgent` is delegated to from a supervisor that has no backgrou
 
 Mastra supports one nested background-tool level inside a delegated run: a root agent can delegate to a subagent, and that subagent can dispatch an eligible ordinary tool in the background. A second delegated-agent edge runs in the foreground and doesn't receive nested background guidance. This limit is execution-scoped and doesn't mutate the shared subagent configuration.
 
-Which layer to use depends on where consistency matters: subagent-level configuration travels with the agent, so its background behavior stays the same under every supervisor, whereas the supervisor-side opt-in above centralizes that tuning in one place. This boundary stops at a single nested delegation level and has no workflow integration.
+Which layer to use depends on where consistency matters: subagent-level configuration travels with the agent, which keeps its background behavior the same under every supervisor, whereas the supervisor-side opt-in above centralizes that tuning in one place. This boundary stops at a single nested delegation level and has no workflow integration.
 
 ## Suspending and resuming
 
@@ -268,7 +268,7 @@ export const reviewTool = createTool({
 })
 ```
 
-The first invocation of `execute` sees `resumeData === undefined` and calls `suspend`. After the task is resumed, the runtime restarts the tool with `resumeData` populated. The `if` condition is false, so the tool returns its real result.
+The first invocation of `execute` sees `resumeData === undefined` and calls `suspend`. After the task is resumed, the runtime restarts the tool with `resumeData` populated. The `if` condition is false. The tool returns its real result.
 
 To resume the task once an approval arrives:
 

package/dist/docs/references/docs-harness-goals.md

@@ -67,11 +67,26 @@ A goal step runs inside the agentic execution loop, right after `isTaskComplete`
 
 The step is a no-op for background-task, mid-tool-loop, and working-memory-only iterations, the same gating as `isTaskComplete`.
 
-**The judge model is the activation switch.** If no judge resolves (neither the per-objective override nor the agent's `goal.judge`), the goal step performs no scoring or budget consumption and emits no `goal` chunk.
+Each evaluation emits a typed `goal` stream chunk (`GoalEvaluationPayload`: `objective`, `iteration`, `maxRuns`, `passed`, `status`, `results`, `reason`, `duration`, `timedOut`, `maxRunsReached`, `suppressFeedback`) so a UI can show goal progress mid-run.
+
+**The judge model is the activation switch.** If no judge resolves, from either the per-objective override or the agent's `goal.judge`, the goal step performs no scoring or budget consumption and emits no `goal` chunk. The gate covers every scorer: Mastra checks it before selecting a scorer, so a custom `goal.scorer` still needs a judge to resolve.
+
+Effective settings resolve as per-objective record value, then agent `goal` config, then a built-in default (`maxRuns` `50` and the default judge prompt).
+
+### Judge and scorer
+
+`goal.judge` and `goal.scorer` work at different levels. `goal.scorer` is the evaluation pipeline that produces the score the loop gates on. `goal.judge` is the model the default pipeline calls to reach that score.
+
+Omit `scorer` and Mastra builds a default LLM-as-judge scorer, which returns `1` when the objective is achieved and `0` otherwise. Configure it with these settings:
 
-Effective settings resolve as per-objective record value → agent `goal` config → built-in default (`maxRuns` `50`, a default judge prompt).
+- `goal.judge`: The model that decides whether the objective is met.
+- `goal.prompt`: Extra instructions for the judge. Defaults to the built-in goal judge prompt.
+- `goal.tools`: Read-only verification tools the judge can call before deciding, so it can confirm the work instead of grading the agent's text alone.
+- `goal.maxSteps`: Step budget for the judge's own agentic loop. Defaults to `5`.
 
-By default the step uses a built-in LLM-as-judge scorer that returns `1` when the objective is achieved and `0` otherwise. Supply your own scorer with `goal.scorer` to customize judging.
+Pass `goal.scorer` to replace the pipeline with your own [scorer](https://mastra.ai/reference/evals/create-scorer), either a scorer instance or a registered scorer id. The custom scorer brings its own judging, so `goal.prompt`, `goal.tools`, and `goal.maxSteps` no longer apply, and Mastra stops resolving the judge model for judging. A `goal.judge` resolver function still runs, and its return value is discarded.
+
+Configure the default scorer with `judge`, `maxRuns`, and `prompt`:
 
 ```typescript
 const worker = new Agent({
@@ -91,7 +106,15 @@ const worker = new Agent({
 })
 ```
 
-Each evaluation emits a typed `goal` stream chunk (`GoalEvaluationPayload`: `objective`, `iteration`, `maxRuns`, `passed`, `status`, `results`, `reason`, `duration`, `timedOut`, `maxRunsReached`, `suppressFeedback`) so a UI can show goal progress mid-run.
+To hand the decision to your own scorer, pass it as `scorer` and keep `judge` set, because the activation gate still applies:
+
+```typescript
+goal: {
+  judge: 'openai/gpt-5-mini',
+  // Replaces the built-in judge pipeline. `prompt`, `tools`, and `maxSteps` no longer apply.
+  scorer: 'tests-pass',
+}
+```
 
 ## Managing the objective
 

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

@@ -128,7 +128,7 @@ export const agent = new Agent({
 
 Mastra inserts a temporal gap marker when the gap is at least 10 minutes. The marker is stored in memory and also emitted as a transient reminder event, so clients can render it as a lightweight timeline hint.
 
-The observer also sees these markers when it processes the thread, so the observations it writes can anchor memories to when they happened (for example, "User asked about deployment after a 2-day gap").
+The observer also sees these markers when it processes the thread. The observations it writes can anchor memories to when they happened (for example, "User asked about deployment after a 2-day gap").
 
 See [the API reference](https://mastra.ai/reference/memory/observational-memory) for the full configuration shape.
 
@@ -223,7 +223,7 @@ A provider outage usually takes out both stages, so set the policy on both if yo
 
 This policy applies only to Observer and Reflector model and provider failures in synchronous, resource-scoped, and buffered observation. Persistence, indexing, transform, locking, invariant, and explicit abort failures remain fatal. It doesn't prevent the underlying provider or network error, change `blockAfter`, or change attachment handling.
 
-> **Warning:** `'continue'` has no backstop for a sustained outage. Unobserved messages stay pending and keep accruing in the main agent's context, so a long outage moves the failure from the memory layer to the model's context limit.
+> **Warning:** `'continue'` has no backstop for a sustained outage. Unobserved messages stay pending and keep accruing in the main agent's context. A long outage moves the failure from the memory layer to the model's context limit.
 
 See [the API reference](https://mastra.ai/reference/memory/observational-memory) for the full configuration shape.
 
@@ -231,7 +231,7 @@ See [the API reference](https://mastra.ai/reference/memory/observational-memory)
 
 - **Prompt caching**: OM's context is stable and observations append over time rather than being retrieved at runtime each turn. This keeps the prompt prefix cacheable, which reduces costs.
 - **Compression**: Raw message history and tool results get compressed into a dense observation log. Smaller context means faster responses and longer coherent conversations.
-- **Zero context rot**: The agent sees relevant information instead of noisy tool calls and irrelevant tokens, so the agent stays on task over long sessions.
+- **Zero context rot**: The agent sees relevant information instead of noisy tool calls and irrelevant tokens, which keeps the agent on task over long sessions.
 
 ## How it works
 

package/dist/docs/references/docs-memory-overview.md

@@ -202,7 +202,7 @@ Each delegation creates a fresh `threadId` and a deterministic `resourceId` for
 
 > **Note:** Title generation (`generateTitle`) is a top-level thread concern and **isn't** applied to inherited subagent threads. Because each delegation creates an ephemeral thread that no one sees, running title generation for it would waste an LLM call per delegation. To generate titles for a subagent's own threads, give that subagent its own memory configuration.
 
-The supervisor forwards its conversation context to the subagent so it has enough background to complete the task. Only the delegation prompt and the subagent's response are saved; the full parent conversation isn't stored. You can control which messages reach the subagent with the [`messageFilter`](https://mastra.ai/docs/subagents) callback.
+The supervisor forwards its conversation context to the subagent so it has enough background to complete the task. Only the delegation prompt and the subagent's response are saved. The full parent conversation isn't stored. You can control which messages reach the subagent with the [`messageFilter`](https://mastra.ai/docs/subagents) callback.
 
 > **Note:** Subagent resource IDs are always suffixed with the agent name (`{parentResourceId}-{agentName}`). Different subagents under the same supervisor never share a resource ID through delegation.
 

package/dist/index.cjs

@@ -1,5 +1,5 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
-const require_src = require("./src-CeFdO1YZ.cjs");
+const require_src = require("./src-CMESxrGy.cjs");
 let _mastra_core_processors = require("@mastra/core/processors");
 exports.Extractor = require_src.Extractor;
 exports.KnowledgeSemanticIndexCoordinator = require_src.KnowledgeSemanticIndexCoordinator;

package/dist/index.js

@@ -1,2 +1,2 @@
-import { C as SUMMARIZE_THREAD_DEFAULTS, G as StaleKnowledgeSemanticIndexError, Q as Extractor, S as deepMergeWorkingMemory, U as Subconscious, W as KnowledgeSemanticIndexCoordinator, a as extractWorkingMemoryContent, b as WorkingMemoryStateProcessor, c as getObservationsAsOf, i as WorkingMemory, n as MessageHistory, o as extractWorkingMemoryTags, q as ModelByInputTokens, r as SemanticRecall, s as removeWorkingMemoryTags, t as Memory, v as WORKING_MEMORY_STATE_ID, w as summarizeConversation, x as WorkingMemoryExtractor, y as WORKING_MEMORY_STATE_PROCESSOR_ID } from "./src-BikfoIdS.js";
+import { C as SUMMARIZE_THREAD_DEFAULTS, G as StaleKnowledgeSemanticIndexError, Q as Extractor, S as deepMergeWorkingMemory, U as Subconscious, W as KnowledgeSemanticIndexCoordinator, a as extractWorkingMemoryContent, b as WorkingMemoryStateProcessor, c as getObservationsAsOf, i as WorkingMemory, n as MessageHistory, o as extractWorkingMemoryTags, q as ModelByInputTokens, r as SemanticRecall, s as removeWorkingMemoryTags, t as Memory, v as WORKING_MEMORY_STATE_ID, w as summarizeConversation, x as WorkingMemoryExtractor, y as WORKING_MEMORY_STATE_PROCESSOR_ID } from "./src-BdfOygyn.js";
 export { Extractor, KnowledgeSemanticIndexCoordinator, Memory, MessageHistory, ModelByInputTokens, SUMMARIZE_THREAD_DEFAULTS, SemanticRecall, StaleKnowledgeSemanticIndexError, Subconscious, WORKING_MEMORY_STATE_ID, WORKING_MEMORY_STATE_PROCESSOR_ID, WorkingMemory, WorkingMemoryExtractor, WorkingMemoryStateProcessor, deepMergeWorkingMemory, extractWorkingMemoryContent, extractWorkingMemoryTags, getObservationsAsOf, removeWorkingMemoryTags, summarizeConversation };

package/dist/processors/index.cjs

@@ -1,5 +1,5 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
-const require_src = require("../src-CeFdO1YZ.cjs");
+const require_src = require("../src-CMESxrGy.cjs");
 exports.Extractor = require_src.Extractor;
 exports.KnowledgeSemanticIndexCoordinator = require_src.KnowledgeSemanticIndexCoordinator;
 exports.ModelByInputTokens = require_src.ModelByInputTokens;

package/dist/processors/index.js

@@ -1,2 +1,2 @@
-import { A as formatMessagesForObserver, B as OBSERVATION_CONTEXT_PROMPT_THREAD, D as buildObserverPrompt, E as OBSERVER_SYSTEM_PROMPT, F as parseAnchorId, G as StaleKnowledgeSemanticIndexError, H as getObservationContextPrompt, I as stripEphemeralAnchorIds, J as SUBCONSCIOUS_ACTIVITY_STATE_ID, K as SubconsciousRemindExtractor, L as OBSERVATIONAL_MEMORY_DEFAULTS, M as optimizeObservationsForContext, N as parseObserverOutput, O as buildObserverSystemPrompt, P as injectAnchorIds, Q as Extractor, R as OBSERVATION_CONTEXT_INSTRUCTIONS, T as TokenCounter, U as Subconscious, V as OBSERVATION_CONTINUATION_HINT, W as KnowledgeSemanticIndexCoordinator, X as publishSubconsciousActivity, Y as buildSubconsciousActivitySnapshot, Z as renderSubconsciousActivity, _ as wrapInObservationGroup, c as getObservationsAsOf, d as combineObservationGroupRanges, f as deriveObservationGroupProvenance, g as stripObservationGroups, h as renderObservationGroupsForReflection, j as hasCurrentTaskSection, k as extractCurrentTask, l as ObservationalMemoryProcessor, m as reconcileObservationGroupsFromReflection, p as parseObservationGroups, q as ModelByInputTokens, u as ObservationalMemory, w as summarizeConversation, x as WorkingMemoryExtractor, z as OBSERVATION_CONTEXT_PROMPT } from "../src-BikfoIdS.js";
+import { A as formatMessagesForObserver, B as OBSERVATION_CONTEXT_PROMPT_THREAD, D as buildObserverPrompt, E as OBSERVER_SYSTEM_PROMPT, F as parseAnchorId, G as StaleKnowledgeSemanticIndexError, H as getObservationContextPrompt, I as stripEphemeralAnchorIds, J as SUBCONSCIOUS_ACTIVITY_STATE_ID, K as SubconsciousRemindExtractor, L as OBSERVATIONAL_MEMORY_DEFAULTS, M as optimizeObservationsForContext, N as parseObserverOutput, O as buildObserverSystemPrompt, P as injectAnchorIds, Q as Extractor, R as OBSERVATION_CONTEXT_INSTRUCTIONS, T as TokenCounter, U as Subconscious, V as OBSERVATION_CONTINUATION_HINT, W as KnowledgeSemanticIndexCoordinator, X as publishSubconsciousActivity, Y as buildSubconsciousActivitySnapshot, Z as renderSubconsciousActivity, _ as wrapInObservationGroup, c as getObservationsAsOf, d as combineObservationGroupRanges, f as deriveObservationGroupProvenance, g as stripObservationGroups, h as renderObservationGroupsForReflection, j as hasCurrentTaskSection, k as extractCurrentTask, l as ObservationalMemoryProcessor, m as reconcileObservationGroupsFromReflection, p as parseObservationGroups, q as ModelByInputTokens, u as ObservationalMemory, w as summarizeConversation, x as WorkingMemoryExtractor, z as OBSERVATION_CONTEXT_PROMPT } from "../src-BdfOygyn.js";
 export { Extractor, KnowledgeSemanticIndexCoordinator, ModelByInputTokens, OBSERVATIONAL_MEMORY_DEFAULTS, OBSERVATION_CONTEXT_INSTRUCTIONS, OBSERVATION_CONTEXT_PROMPT, OBSERVATION_CONTEXT_PROMPT_THREAD, OBSERVATION_CONTINUATION_HINT, OBSERVER_SYSTEM_PROMPT, ObservationalMemory, ObservationalMemoryProcessor, SUBCONSCIOUS_ACTIVITY_STATE_ID, StaleKnowledgeSemanticIndexError, Subconscious, SubconsciousRemindExtractor, TokenCounter, WorkingMemoryExtractor, buildObserverPrompt, buildObserverSystemPrompt, buildSubconsciousActivitySnapshot, combineObservationGroupRanges, deriveObservationGroupProvenance, extractCurrentTask, formatMessagesForObserver, getObservationContextPrompt, getObservationsAsOf, hasCurrentTaskSection, injectAnchorIds, optimizeObservationsForContext, parseAnchorId, parseObservationGroups, parseObserverOutput, publishSubconsciousActivity, reconcileObservationGroupsFromReflection, renderObservationGroupsForReflection, renderSubconsciousActivity, stripEphemeralAnchorIds, stripObservationGroups, summarizeConversation, wrapInObservationGroup };

package/dist/processors/observational-memory/error.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"error.d.ts","sourceRoot":"","sources":["../../../src/processors/observational-memory/error.ts"],"names":[],"mappings":"AAQA,wBAAgB,yBAAyB,CAAC,KAAK,EAAE,OAAO,GAAG,OAAO,CAqBjE;AAED,MAAM,MAAM,eAAe,GAAG,OAAO,GAAG,UAAU,CAAC;AACnD,MAAM,MAAM,aAAa,GAAG,gBAAgB,GAAG,iBAAiB,CAAC;AAEjE,qBAAa,qBAAsB,SAAQ,KAAK;IAE5C,QAAQ,CAAC,WAAW,EAAE,aAAa;gBAA1B,WAAW,EAAE,aAAa,EACnC,KAAK,EAAE,OAAO;CAKjB;AAED,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,OAAO,GAAG,KAAK,IAAI,qBAAqB,CAMtF;AAED,wBAAgB,oBAAoB,CAAC,KAAK,EAAE,OAAO,EAAE,aAAa,EAAE,eAAe;;;EAKlF;AAED,uGAAuG;AACvG,wBAAgB,aAAa,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CA4CpD"}
+{"version":3,"file":"error.d.ts","sourceRoot":"","sources":["../../../src/processors/observational-memory/error.ts"],"names":[],"mappings":"AAQA,wBAAgB,yBAAyB,CAAC,KAAK,EAAE,OAAO,GAAG,OAAO,CAqBjE;AAED,MAAM,MAAM,eAAe,GAAG,OAAO,GAAG,UAAU,CAAC;AACnD,MAAM,MAAM,aAAa,GAAG,gBAAgB,GAAG,iBAAiB,CAAC;AAEjE,qBAAa,qBAAsB,SAAQ,KAAK;IAE5C,QAAQ,CAAC,WAAW,EAAE,aAAa;gBAA1B,WAAW,EAAE,aAAa,EACnC,KAAK,EAAE,OAAO;CAKjB;AAED,wBAAgB,uBAAuB,CAAC,KAAK,EAAE,OAAO,GAAG,KAAK,IAAI,qBAAqB,CAMtF;AAED,wBAAgB,oBAAoB,CAAC,KAAK,EAAE,OAAO,EAAE,aAAa,EAAE,eAAe;;;EAKlF;AAED,uGAAuG;AACvG,wBAAgB,aAAa,CAAC,KAAK,EAAE,OAAO,GAAG,MAAM,CAiDpD"}

package/dist/{src-BikfoIdS.js → src-BdfOygyn.js}

@@ -3712,7 +3712,7 @@ function trimStartOfStream() {
 	};
 }
 //#endregion
-//#region ../_vendored/ai_v5/dist/dist-DeQB2Mal.js
+//#region ../_vendored/ai_v5/dist/dist-KmM6rhg_.js
 var marker$2$4 = "vercel.ai.error";
 var symbol$2$4 = Symbol.for(marker$2$4);
 var _a$2$4;
@@ -8999,7 +8999,7 @@ var object$1 = ({ schema: inputSchema }) => {
 	};
 };
 //#endregion
-//#region ../_vendored/ai_v6/dist/dist--V1K8YWk.js
+//#region ../_vendored/ai_v6/dist/dist-BBy3PDi4.js
 var marker$2 = "vercel.ai.error";
 var symbol$2 = Symbol.for(marker$2);
 var _a$2;
@@ -11544,7 +11544,7 @@ var _b14;
 	}
 });
 //#endregion
-//#region ../_vendored/ai_v6/dist/dist-CWofJnzt.js
+//#region ../_vendored/ai_v6/dist/dist-CM5SoUT8.js
 function getContext() {
 	return { headers: {} };
 }
@@ -18932,6 +18932,7 @@ function formatOmError(error) {
 		}
 		if (visited.has(value)) return;
 		visited.add(value);
+		if (typeof value.id === "string" && typeof value.domain === "string" && typeof value.category === "string") add(value.id);
 		add(value.message);
 		if (typeof value.statusCode === "number") add(`HTTP ${value.statusCode}`);
 		if (typeof value.responseBody === "string") try {
@@ -34458,4 +34459,4 @@ Notes:
 //#endregion
 export { formatMessagesForObserver as A, OBSERVATION_CONTEXT_PROMPT_THREAD as B, SUMMARIZE_THREAD_DEFAULTS as C, buildObserverPrompt as D, OBSERVER_SYSTEM_PROMPT as E, parseAnchorId as F, StaleKnowledgeSemanticIndexError as G, getObservationContextPrompt as H, stripEphemeralAnchorIds as I, SUBCONSCIOUS_ACTIVITY_STATE_ID as J, SubconsciousRemindExtractor as K, OBSERVATIONAL_MEMORY_DEFAULTS as L, optimizeObservationsForContext as M, parseObserverOutput as N, buildObserverSystemPrompt as O, injectAnchorIds as P, Extractor as Q, OBSERVATION_CONTEXT_INSTRUCTIONS as R, deepMergeWorkingMemory as S, TokenCounter as T, Subconscious as U, OBSERVATION_CONTINUATION_HINT as V, KnowledgeSemanticIndexCoordinator as W, publishSubconsciousActivity as X, buildSubconsciousActivitySnapshot as Y, renderSubconsciousActivity as Z, wrapInObservationGroup as _, extractWorkingMemoryContent as a, WorkingMemoryStateProcessor as b, getObservationsAsOf as c, combineObservationGroupRanges as d, deriveObservationGroupProvenance as f, stripObservationGroups as g, renderObservationGroupsForReflection as h, WorkingMemory as i, hasCurrentTaskSection as j, extractCurrentTask as k, ObservationalMemoryProcessor as l, reconcileObservationGroupsFromReflection as m, MessageHistory$1 as n, extractWorkingMemoryTags as o, parseObservationGroups as p, ModelByInputTokens as q, SemanticRecall as r, removeWorkingMemoryTags as s, Memory as t, ObservationalMemory as u, WORKING_MEMORY_STATE_ID as v, summarizeConversation as w, WorkingMemoryExtractor as x, WORKING_MEMORY_STATE_PROCESSOR_ID as y, OBSERVATION_CONTEXT_PROMPT as z };
 
-//# sourceMappingURL=src-BikfoIdS.js.map
+//# sourceMappingURL=src-BdfOygyn.js.map