docs(js): Add streamGenAiSpans to AI monitoring and integration docs

docs/platforms/javascript/common/ai-agent-monitoring/index.mdx

@@ -69,6 +69,7 @@ import { openAIIntegration } from "___SDK_PACKAGE___";
 Sentry.init({
   dsn: "___PUBLIC_DSN___",
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     openAIIntegration(),
   ],
@@ -101,6 +102,7 @@ import { openAIIntegration } from "___SDK_PACKAGE___";
 Sentry.init({
   dsn: "___PUBLIC_DSN___",
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     openAIIntegration({
       recordInputs: false, // Don't capture prompts
@@ -120,9 +122,9 @@ Sentry.init({
 
 ### Streaming Gen AI Spans
 
-AI spans with large inputs and outputs can hit transaction payload size limits. Set `streamGenAiSpans` to `true` to send `gen_ai` spans as standalone envelope items instead of bundling them in the transaction.
+Set `streamGenAiSpans` to `true` to send `gen_ai` spans as standalone envelope items instead of bundling them in the transaction. This is recommended for all AI monitoring setups and is required for <Link to="/ai/monitoring/conversations/">Conversations</Link> to work.
 
-Enable this option if `gen_ai` spans are being dropped because the transaction payload exceeds size limits.
+Without this option, AI spans with large inputs and outputs can hit transaction payload size limits and be dropped.
 
 </SplitSectionText>
 <SplitSectionCode>

docs/platforms/javascript/common/configuration/integrations/anthropic.mdx

@@ -127,6 +127,7 @@ Defaults to `true` if `sendDefaultPii` is `true`.
   dsn: "____PUBLIC_DSN____",
   // Tracing must be enabled for agent monitoring to work
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
   Sentry.anthropicAIIntegration({
   // your options here

docs/platforms/javascript/common/configuration/integrations/google-genai.mdx

@@ -123,6 +123,7 @@ Sentry.init({
   dsn: "____PUBLIC_DSN____",
    // Tracing must be enabled for agent monitoring to work
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     Sentry.googleGenAIIntegration({
       // your options here

docs/platforms/javascript/common/configuration/integrations/langchain.mdx

@@ -127,6 +127,7 @@ Sentry.init({
   dsn: "____PUBLIC_DSN____",
   // Tracing must be enabled for agent monitoring to work
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     Sentry.langChainIntegration({
       // your options here

docs/platforms/javascript/common/configuration/integrations/langgraph.mdx

@@ -149,6 +149,7 @@ Sentry.init({
   dsn: "____PUBLIC_DSN____",
   // Tracing must be enabled for agent monitoring to work
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     Sentry.langGraphIntegration({
       // your options here

docs/platforms/javascript/common/configuration/integrations/openai.mdx

@@ -127,6 +127,7 @@ Sentry.init({
   dsn: "____PUBLIC_DSN____",
   // Tracing must be enabled for agent monitoring to work
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     Sentry.openAIIntegration({
       // your options here
@@ -160,7 +161,7 @@ Streaming and non-streaming requests are automatically detected and handled appr
 
 <Alert>
 
-When using OpenAI's streaming API, you must also pass `stream_options: { include_usage: true }` to receive token usage data. Without this option, OpenAI does not include `prompt_tokens` or `completion_tokens` in streamed responses, and Sentry will be unable to capture `gen_ai.usage.input_tokens` / `gen_ai.usage.output_tokens` on the resulting span. This is an OpenAI API behavior, not a Sentry limitation. See [OpenAI docs on stream options](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options).
+When using OpenAI's streaming API, you must also pass `stream_options: { include_usage: true }` to receive token usage data. Without this option, OpenAI does not include `prompt_tokens` or `completion_tokens` in streamed responses, and Sentry will be unable to capture `gen_ai.usage.input_tokens` / `gen_ai.usage.output_tokens` on the resulting span. This is an OpenAI API behavior, not a Sentry limitation. See [OpenAI API reference](https://platform.openai.com/docs/api-reference/chat/create).
 
 </Alert>
 

docs/platforms/javascript/common/configuration/integrations/vercelai.mdx

@@ -46,6 +46,7 @@ The `vercelAIIntegration` adds instrumentation for the [`ai`](https://www.npmjs.
 Sentry.init({
   dsn: "____PUBLIC_DSN____"
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [
     Sentry.vercelAIIntegration({
       recordInputs: true,
@@ -64,6 +65,7 @@ This integration is not enabled by default. You need to manually enable it by pa
 Sentry.init({
   dsn: "____PUBLIC_DSN____"
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [Sentry.vercelAIIntegration()],
 });
 ```
@@ -77,6 +79,7 @@ This integration is enabled by default in the Node runtime, but not in the Edge
 Sentry.init({
   dsn: "____PUBLIC_DSN____"
   tracesSampleRate: 1.0,
+  streamGenAiSpans: true,
   integrations: [Sentry.vercelAIIntegration()],
 });
 ```

docs/platforms/javascript/common/configuration/options.mdx

@@ -602,6 +602,14 @@ See <PlatformLink to="/tracing/distributed-tracing/dealing-with-cors-issues/">De
 
 </SdkOption>
 
+<SdkOption name="streamGenAiSpans" type='boolean' defaultValue='false' availableSince='10.53.0'>
+
+When set to `true`, `gen_ai` spans are sent as standalone envelope items instead of being bundled in the transaction payload. This prevents AI spans with large inputs and outputs from being dropped due to transaction payload size limits.
+
+Enable this option if you are using <PlatformLink to="/ai-agent-monitoring/">AI Agent Monitoring</PlatformLink> or the <Link to="/ai/monitoring/conversations/">Conversations</Link> feature.
+
+</SdkOption>
+
 ## Logs Options
 
 <PlatformSection supported={["javascript.electron"]}>