feat(core): Add byte size limit and oldest first truncation for gen_ai messages

packages/core/src/utils/ai/messageTruncation.ts

@@ -0,0 +1,37 @@
+export function getByteSize(str: string): number {
+  return new TextEncoder().encode(str).length;
+}
+
+export function truncateMessagesByBytes(messages: unknown[], maxBytes: number): unknown[] {
+  if (!Array.isArray(messages) || messages.length === 0) {
+    return messages;
+  }
+
+  const messagesJson = JSON.stringify(messages);
+  const totalBytes = getByteSize(messagesJson);
+
+  if (totalBytes <= maxBytes) {
+    return messages;
+  }
+
+  let truncatedMessages = [...messages];
+
+  while (truncatedMessages.length > 0) {
+    const truncatedJson = JSON.stringify(truncatedMessages);
+    const truncatedBytes = getByteSize(truncatedJson);
+
+    if (truncatedBytes <= maxBytes) {
+      break;
+    }
+
+    truncatedMessages.shift();
+  }
+
+  return truncatedMessages;
+}
+
+export const DEFAULT_GEN_AI_MESSAGES_BYTE_LIMIT = 100000;
+
+export function truncateGenAiMessages(messages: unknown[]): unknown[] {
+  return truncateMessagesByBytes(messages, DEFAULT_GEN_AI_MESSAGES_BYTE_LIMIT);
+}

packages/core/src/utils/anthropic-ai/index.ts

@@ -23,6 +23,7 @@ import {
   GEN_AI_RESPONSE_TOOL_CALLS_ATTRIBUTE,
   GEN_AI_SYSTEM_ATTRIBUTE,
 } from '../ai/gen-ai-attributes';
+import { truncateGenAiMessages } from '../ai/messageTruncation';
 import { buildMethodPath, getFinalOperationName, getSpanOperation, setTokenUsageAttributes } from '../ai/utils';
 import { handleCallbackErrors } from '../handleCallbackErrors';
 import { instrumentAsyncIterableStream, instrumentMessageStream } from './streaming';
@@ -71,16 +72,16 @@ function extractRequestAttributes(args: unknown[], methodPath: string): Record<s
   return attributes;
 }
 
-/**
- * Add private request attributes to spans.
- * This is only recorded if recordInputs is true.
- */
 function addPrivateRequestAttributes(span: Span, params: Record<string, unknown>): void {
   if ('messages' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.messages) });
+    const messages = params.messages;
+    const truncatedMessages = truncateGenAiMessages(messages as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedMessages) });
   }
   if ('input' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.input) });
+    const input = params.input;
+    const truncatedInput = truncateGenAiMessages(input as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedInput) });
   }
   if ('prompt' in params) {
     span.setAttributes({ [GEN_AI_PROMPT_ATTRIBUTE]: JSON.stringify(params.prompt) });

packages/core/src/utils/google-genai/index.ts

@@ -22,6 +22,7 @@ import {
   GEN_AI_USAGE_OUTPUT_TOKENS_ATTRIBUTE,
   GEN_AI_USAGE_TOTAL_TOKENS_ATTRIBUTE,
 } from '../ai/gen-ai-attributes';
+import { truncateGenAiMessages } from '../ai/messageTruncation';
 import { buildMethodPath, getFinalOperationName, getSpanOperation } from '../ai/utils';
 import { handleCallbackErrors } from '../handleCallbackErrors';
 import { CHAT_PATH, CHATS_CREATE_METHOD, GOOGLE_GENAI_SYSTEM_NAME } from './constants';
@@ -128,25 +129,23 @@ function extractRequestAttributes(
   return attributes;
 }
 
-/**
- * Add private request attributes to spans.
- * This is only recorded if recordInputs is true.
- * Handles different parameter formats for different Google GenAI methods.
- */
 function addPrivateRequestAttributes(span: Span, params: Record<string, unknown>): void {
-  // For models.generateContent: ContentListUnion: Content | Content[] | PartUnion | PartUnion[]
   if ('contents' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.contents) });
+    const contents = params.contents;
+    const truncatedContents = truncateGenAiMessages(contents as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedContents) });
   }
 
-  // For chat.sendMessage: message can be string or Part[]
   if ('message' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.message) });
+    const message = params.message;
+    const truncatedMessage = truncateGenAiMessages(message as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedMessage) });
   }
 
-  // For chats.create: history contains the conversation history
   if ('history' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.history) });
+    const history = params.history;
+    const truncatedHistory = truncateGenAiMessages(history as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedHistory) });
   }
 }
 

packages/core/src/utils/openai/index.ts

@@ -19,6 +19,7 @@ import {
   GEN_AI_RESPONSE_TOOL_CALLS_ATTRIBUTE,
   GEN_AI_SYSTEM_ATTRIBUTE,
 } from '../ai/gen-ai-attributes';
+import { truncateGenAiMessages } from '../ai/messageTruncation';
 import { OPENAI_INTEGRATION_NAME } from './constants';
 import { instrumentStream } from './streaming';
 import type {
@@ -188,13 +189,16 @@ function addResponseAttributes(span: Span, result: unknown, recordOutputs?: bool
   }
 }
 
-// Extract and record AI request inputs, if present. This is intentionally separate from response attributes.
 function addRequestAttributes(span: Span, params: Record<string, unknown>): void {
   if ('messages' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.messages) });
+    const messages = params.messages;
+    const truncatedMessages = truncateGenAiMessages(messages as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedMessages) });
   }
   if ('input' in params) {
-    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(params.input) });
+    const input = params.input;
+    const truncatedInput = truncateGenAiMessages(input as unknown[]);
+    span.setAttributes({ [GEN_AI_REQUEST_MESSAGES_ATTRIBUTE]: JSON.stringify(truncatedInput) });
   }
 }
 

packages/core/src/utils/vercel-ai/index.ts

@@ -3,6 +3,7 @@ import { SEMANTIC_ATTRIBUTE_SENTRY_OP, SEMANTIC_ATTRIBUTE_SENTRY_ORIGIN } from '
 import type { Event } from '../../types-hoist/event';
 import type { Span, SpanAttributes, SpanAttributeValue, SpanJSON, SpanOrigin } from '../../types-hoist/span';
 import { spanToJSON } from '../spanUtils';
+import { truncateGenAiMessages } from '../ai/messageTruncation';
 import { toolCallSpanMap } from './constants';
 import type { TokenSummary } from './types';
 import { accumulateTokensForParent, applyAccumulatedTokens } from './utils';
@@ -187,7 +188,13 @@ function processGenerateSpan(span: Span, name: string, attributes: SpanAttribute
   }
 
   if (attributes[AI_PROMPT_ATTRIBUTE]) {
-    span.setAttribute('gen_ai.prompt', attributes[AI_PROMPT_ATTRIBUTE]);
+    const prompt = attributes[AI_PROMPT_ATTRIBUTE];
+    if (Array.isArray(prompt)) {
+      const truncatedPrompt = truncateGenAiMessages(prompt);
+      span.setAttribute('gen_ai.prompt', JSON.stringify(truncatedPrompt));
+    } else {
+      span.setAttribute('gen_ai.prompt', prompt);
+    }
   }
   if (attributes[AI_MODEL_ID_ATTRIBUTE] && !attributes[GEN_AI_RESPONSE_MODEL_ATTRIBUTE]) {
     span.setAttribute(GEN_AI_RESPONSE_MODEL_ATTRIBUTE, attributes[AI_MODEL_ID_ATTRIBUTE]);