feat: calibration ratio

api/app/clients/BaseClient.js

@@ -855,6 +855,10 @@ class BaseClient {
       }
     }
 
+    if (this.contextMeta) {
+      responseMessage.contextMeta = this.contextMeta;
+    }
+
     responseMessage.databasePromise = this.saveMessageToDatabase(
       responseMessage,
       saveOptions,

api/server/controllers/agents/client.js

@@ -334,6 +334,14 @@ class AgentClient extends BaseClient {
     /** Preserve canonical pre-format token counts for all history entering graph formatting */
     this.indexTokenCountMap = canonicalTokenCountMap;
 
+    /** Extract contextMeta from the parent response (second-to-last in ordered chain;
+     *  last is the current user message). Seeds the pruner's calibration EMA for this run. */
+    const parentResponse =
+      orderedMessages.length >= 2 ? orderedMessages[orderedMessages.length - 2] : undefined;
+    if (parentResponse?.contextMeta && !parentResponse.isCreatedByUser) {
+      this.contextMeta = parentResponse.contextMeta;
+    }
+
     const result = {
       tokenCountMap,
       prompt: payload,
@@ -807,11 +815,26 @@ class AgentClient extends BaseClient {
 
         memoryPromise = this.runMemory(messages);
 
+        /** Seed calibration ratio from previous run if encoding matches */
+        const currentEncoding = this.getEncoding();
+        const prevMeta = this.contextMeta;
+        const calibrationRatio =
+          prevMeta?.encoding === currentEncoding && prevMeta?.calibrationRatio > 0
+            ? prevMeta.calibrationRatio
+            : undefined;
+
+        if (prevMeta) {
+          logger.debug(
+            `[AgentClient] contextMeta from parent: ratio=${prevMeta.calibrationRatio}, encoding=${prevMeta.encoding}, current=${currentEncoding}, seeded=${calibrationRatio ?? 'none'}`,
+          );
+        }
+
         run = await createRun({
           agents,
           messages,
           indexTokenCountMap,
           initialSummary,
+          calibrationRatio,
           runId: this.responseMessageId,
           signal: abortController.signal,
           customHandlers: this.options.eventHandlers,
@@ -849,6 +872,21 @@ class AgentClient extends BaseClient {
 
       const hideSequentialOutputs = config.configurable.hide_sequential_outputs;
       await runAgents(initialMessages);
+
+      /** Capture calibration ratio from the completed run for persistence on the response message */
+      if (this.run) {
+        const ratio = this.run.getCalibrationRatio();
+        if (ratio > 0 && ratio !== 1) {
+          this.contextMeta = {
+            calibrationRatio: Math.round(ratio * 1000) / 1000,
+            encoding: this.getEncoding(),
+          };
+          logger.debug(
+            `[AgentClient] contextMeta to persist: ratio=${this.contextMeta.calibrationRatio}, encoding=${this.contextMeta.encoding}`,
+          );
+        }
+      }
+
       /** @deprecated Agent Chain */
       if (hideSequentialOutputs) {
         this.contentParts = this.contentParts.filter((part, index) => {

packages/api/src/agents/run.ts

@@ -209,6 +209,7 @@ export async function createRun({
   indexTokenCountMap,
   summarizationConfig,
   initialSummary,
+  calibrationRatio,
   streaming = true,
   streamUsage = true,
 }: {
@@ -224,6 +225,8 @@ export async function createRun({
   summarizationConfig?: SummarizationConfig;
   /** Cross-run summary from formatAgentMessages, forwarded to AgentContext */
   initialSummary?: { text: string; tokenCount: number };
+  /** Calibration ratio from previous run's contextMeta, seeds the pruner EMA */
+  calibrationRatio?: number;
 } & Pick<RunConfig, 'tokenCounter' | 'customHandlers' | 'indexTokenCountMap'>): Promise<
   Run<IState>
 > {
@@ -421,5 +424,6 @@ export async function createRun({
     tokenCounter,
     customHandlers,
     indexTokenCountMap,
+    calibrationRatio,
   });
 }

packages/data-provider/src/schemas.ts

@@ -630,6 +630,12 @@ export const tMessageSchema = z.object({
   feedback: feedbackSchema.optional(),
   /** metadata */
   metadata: z.record(z.unknown()).optional(),
+  contextMeta: z
+    .object({
+      calibrationRatio: z.number().optional(),
+      encoding: z.string().optional(),
+    })
+    .optional(),
 });
 
 export type MemoryArtifact = {

packages/data-schemas/src/schema/message.ts

@@ -114,6 +114,14 @@ const messageSchema: Schema<IMessage> = new Schema(
       type: String,
     },
     metadata: { type: mongoose.Schema.Types.Mixed },
+    contextMeta: {
+      type: {
+        calibrationRatio: { type: Number },
+        encoding: { type: String },
+      },
+      _id: false,
+      default: undefined,
+    },
     attachments: { type: [{ type: mongoose.Schema.Types.Mixed }], default: undefined },
     /*
     attachments: {

packages/data-schemas/src/types/message.ts

@@ -39,6 +39,10 @@ export interface IMessage extends Document {
   iconURL?: string;
   addedConvo?: boolean;
   metadata?: Record<string, unknown>;
+  contextMeta?: {
+    calibrationRatio?: number;
+    encoding?: string;
+  };
   attachments?: unknown[];
   expiredAt?: Date | null;
   createdAt?: Date;