diff --git a/docs/platforms/javascript/common/configuration/integrations/anthropic.mdx b/docs/platforms/javascript/common/configuration/integrations/anthropic.mdx
index 127c485cd8b0da..b7b6bee8682e04 100644
--- a/docs/platforms/javascript/common/configuration/integrations/anthropic.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/anthropic.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher. On earlier versions, see the [Agent Tra
+
+
_Import name: `Sentry.anthropicAIIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `anthropicAIIntegration` adds instrumentation for the [`@anthropic-ai/sdk`](https://www.npmjs.com/package/@anthropic-ai/sdk) SDK to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled Anthropic SDK is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, wrap your client with `Sentry.instrumentAnthropicAiClient()`.
+
+
+
## Supported Operations
By default, tracing support is added to the following Anthropic SDK calls:
@@ -60,6 +86,8 @@ Records outputs from Anthropic SDK calls (such as generated text and responses).
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -72,3 +100,23 @@ Sentry.init({
],
});
```
+
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `anthropicAIIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
diff --git a/docs/platforms/javascript/common/configuration/integrations/google-genai.mdx b/docs/platforms/javascript/common/configuration/integrations/google-genai.mdx
index c60b0695852a70..d7dc9b4058c837 100644
--- a/docs/platforms/javascript/common/configuration/integrations/google-genai.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/google-genai.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher. On earlier versions, see the [Agent Tra
+
+
_Import name: `Sentry.googleGenAIIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `googleGenAIIntegration` adds instrumentation for the [`@google/genai`](https://www.npmjs.com/package/@google/genai) SDK to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled Google Gen AI SDK is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, wrap your client with `Sentry.instrumentGoogleGenAIClient()`.
+
+
+
## Supported Operations
By default, tracing support is added to the following Google Gen AI SDK calls:
@@ -62,6 +88,8 @@ Records outputs from Google Gen AI SDK calls (such as generated text and respons
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -74,3 +102,23 @@ Sentry.init({
],
});
```
+
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `googleGenAIIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
diff --git a/docs/platforms/javascript/common/configuration/integrations/langchain.mdx b/docs/platforms/javascript/common/configuration/integrations/langchain.mdx
index 6f7f6d5cf5163a..268984b54248c6 100644
--- a/docs/platforms/javascript/common/configuration/integrations/langchain.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/langchain.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher. On earlier versions, see the [Agent Tra
+
+
_Import name: `Sentry.langChainIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `langChainIntegration` adds instrumentation for [`langchain`](https://www.npmjs.com/package/langchain) to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled LangChain is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, pass a handler from `Sentry.createLangChainCallbackHandler()` in your LangChain `callbacks`.
+
+
+
## Supported Operations
By default, tracing support is added to the following LangChain operations:
@@ -125,6 +151,8 @@ Records outputs from LangChain operations (such as generated text and responses)
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -137,3 +165,23 @@ Sentry.init({
],
});
```
+
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `langChainIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
diff --git a/docs/platforms/javascript/common/configuration/integrations/langgraph.mdx b/docs/platforms/javascript/common/configuration/integrations/langgraph.mdx
index d7ebd920a1c916..98fe88ceeb95e7 100644
--- a/docs/platforms/javascript/common/configuration/integrations/langgraph.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/langgraph.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher. On earlier versions, see the [Agent Tra
+
+
_Import name: `Sentry.langGraphIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `langGraphIntegration` adds instrumentation for [`@langchain/langgraph`](https://www.npmjs.com/package/@langchain/langgraph) to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled LangGraph is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, use [Manual Instrumentation](#manual-instrumentation).
+
+
+
## Supported Operations
By default, tracing support is added to the following LangGraph operations:
@@ -89,6 +115,8 @@ Records outputs from LangGraph operations (such as generated responses, agent ou
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -102,6 +130,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `langGraphIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
+
## Manual Instrumentation
_Import names: `Sentry.instrumentStateGraph`, `Sentry.instrumentCreateReactAgent`_
diff --git a/docs/platforms/javascript/common/configuration/integrations/mistral.mdx b/docs/platforms/javascript/common/configuration/integrations/mistral.mdx
index e2b68cd712f15e..579fda8344ade2 100644
--- a/docs/platforms/javascript/common/configuration/integrations/mistral.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/mistral.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher.
+
+
_Import name: `Sentry.mistralAIIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `mistralAIIntegration` adds instrumentation for the [`@mistralai/mistralai`](https://www.npmjs.com/package/@mistralai/mistralai) SDK to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,8 @@ Sentry.init({
});
```
+
+
On Deno, preload Sentry's import hook so the Mistral SDK can be instrumented:
@@ -120,6 +128,8 @@ Records outputs from Mistral AI SDK calls (such as generated text and responses)
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -133,6 +143,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `mistralAIIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
+
## Manual Instrumentation
diff --git a/docs/platforms/javascript/common/configuration/integrations/openai.mdx b/docs/platforms/javascript/common/configuration/integrations/openai.mdx
index eb623d3b7ba8fa..ba85723c4b39ce 100644
--- a/docs/platforms/javascript/common/configuration/integrations/openai.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/openai.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher. On earlier versions, see the [Agent Tra
+
+
_Import name: `Sentry.openAIIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `openAIIntegration` adds instrumentation for the [`openai`](https://www.npmjs.com/package/openai) SDK to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled OpenAI SDK is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, wrap your client with `Sentry.instrumentOpenAiClient()`.
+
+
+
## Supported Operations
By default, tracing support is added to the following OpenAI SDK calls:
@@ -60,6 +86,8 @@ Records outputs from OpenAI SDK calls (such as generated text and responses).
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -72,3 +100,23 @@ Sentry.init({
],
});
```
+
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `openAIIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
diff --git a/docs/platforms/javascript/common/configuration/integrations/together-ai.mdx b/docs/platforms/javascript/common/configuration/integrations/together-ai.mdx
index 7562be4b48ed13..c7c32d1a1d4b5b 100644
--- a/docs/platforms/javascript/common/configuration/integrations/together-ai.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/together-ai.mdx
@@ -12,12 +12,18 @@ Requires SDK version `11.0.0` or higher.
+
+
_Import name: `Sentry.togetherAIIntegration`_
+
+
This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](./../#modifying-default-integrations).
The `togetherAIIntegration` adds instrumentation for the [`together-ai`](https://www.npmjs.com/package/together-ai) SDK to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs. Together AI speaks the OpenAI wire format, so it reuses the same span and streaming logic as the OpenAI integration.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +33,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled Together AI SDK is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, see manual instrumentation.
+
+
+
## Supported Operations
By default, tracing support is added to the following Together AI SDK calls:
@@ -58,6 +84,8 @@ Records outputs from Together AI SDK calls (such as generated text and responses
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -70,3 +98,23 @@ Sentry.init({
],
});
```
+
+
+
+
+
+On Cloudflare, `@sentry/cloudflare` doesn't export `togetherAIIntegration`, so set these through the `dataCollection` option in your `instrument.server.ts` file instead. This applies to all AI integrations:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ dataCollection: {
+ genAI: { inputs: false, outputs: false },
+ },
+}));
+```
+
+
diff --git a/docs/platforms/javascript/common/configuration/integrations/vercelai.mdx b/docs/platforms/javascript/common/configuration/integrations/vercelai.mdx
index f6092ec3f8d80c..0fcbe5fe19172e 100644
--- a/docs/platforms/javascript/common/configuration/integrations/vercelai.mdx
+++ b/docs/platforms/javascript/common/configuration/integrations/vercelai.mdx
@@ -18,6 +18,8 @@ This integration is enabled by default when tracing is enabled. If you'd like to
The `vercelAIIntegration` adds instrumentation for the [`ai`](https://www.npmjs.com/package/ai) SDK by Vercel to capture agent tracing `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -27,6 +29,26 @@ Sentry.init({
});
```
+
+
+
+
+On Cloudflare, there is no `Sentry.init()`. Add `sentryCloudflareVitePlugin()` alongside Cloudflare's Vite plugin so the bundled AI SDK is instrumented:
+
+```typescript {filename:vite.config.mts}
+import { cloudflare } from "@cloudflare/vite-plugin";
+import { sentryCloudflareVitePlugin } from "@sentry/cloudflare/vite";
+import { defineConfig } from "vite";
+
+export default defineConfig({
+ plugins: [cloudflare(), sentryCloudflareVitePlugin()],
+});
+```
+
+Build-time instrumentation is enabled by default, and the plugin registers the integration in both `vite dev` and `vite build`. Keep the `nodejs_compat` flag enabled in your Wrangler configuration, and see the Vite plugin page for the full setup. Without the plugin, or with `buildTimeInstrumentation: false`, see manual instrumentation.
+
+
+
@@ -113,6 +135,8 @@ Records outputs from `ai` function calls (such as generated text and responses).
Defaults to `true` if `dataCollection.genAI.outputs` is `true`, which is the default.
+
+
```javascript
Sentry.init({
dsn: "___PUBLIC_DSN___",
@@ -125,3 +149,26 @@ Sentry.init({
],
});
```
+
+
+
+
+
+On Cloudflare, pass the options from your `instrument.server.ts` file:
+
+```typescript {filename:src/instrument.server.ts}
+import * as Sentry from "@sentry/cloudflare";
+
+export default Sentry.defineCloudflareOptions((env) => ({
+ dsn: "___PUBLIC_DSN___",
+ tracesSampleRate: 1.0,
+ integrations: [
+ Sentry.vercelAIIntegration({
+ recordInputs: false,
+ recordOutputs: false,
+ }),
+ ],
+}));
+```
+
+
diff --git a/docs/product/agents/getting-started.mdx b/docs/product/agents/getting-started.mdx
index d7eb1d4e149bf6..8234431b984710 100644
--- a/docs/product/agents/getting-started.mdx
+++ b/docs/product/agents/getting-started.mdx
@@ -31,8 +31,6 @@ To start sending agent data to Sentry, make sure you've created a Sentry project
- [Flue](/platforms/javascript/guides/flue/)
- [Laravel](/platforms/php/guides/laravel/agent-tracing/)
- [Mastra](/platforms/javascript/guides/mastra/)
-- [Flue](/platforms/javascript/guides/flue/)
-- [Eve](/platforms/javascript/guides/eve/)
- [Next.js](/platforms/javascript/guides/nextjs/agent-tracing/)
- [Node.js](/platforms/javascript/guides/node/agent-tracing/)
- [Pi Durable](/platforms/javascript/guides/pi-durable/)