ai 7.0.0-beta.81 → 7.0.0-beta.83

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # ai
 
+## 7.0.0-beta.83
+
+### Patch Changes
+
+- Updated dependencies [6b0a40d]
+  - @ai-sdk/gateway@4.0.0-beta.46
+
+## 7.0.0-beta.82
+
+### Patch Changes
+
+- e27ed76: feat(devtools): add new devtools integration for telemetry
+
 ## 7.0.0-beta.81
 
 ### Patch Changes

package/dist/index.js

@@ -1401,7 +1401,7 @@ var import_provider_utils3 = require("@ai-sdk/provider-utils");
 var import_provider_utils4 = require("@ai-sdk/provider-utils");
 
 // src/version.ts
-var VERSION = true ? "7.0.0-beta.81" : "0.0.0-test";
+var VERSION = true ? "7.0.0-beta.83" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/dist/index.mjs

@@ -1285,7 +1285,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.0-beta.81" : "0.0.0-test";
+var VERSION = true ? "7.0.0-beta.83" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/dist/internal/index.js

@@ -154,7 +154,7 @@ var import_provider_utils2 = require("@ai-sdk/provider-utils");
 var import_provider_utils3 = require("@ai-sdk/provider-utils");
 
 // src/version.ts
-var VERSION = true ? "7.0.0-beta.81" : "0.0.0-test";
+var VERSION = true ? "7.0.0-beta.83" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/dist/internal/index.mjs

@@ -134,7 +134,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.0-beta.81" : "0.0.0-test";
+var VERSION = true ? "7.0.0-beta.83" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/docs/02-getting-started/09-coding-agents.mdx

@@ -87,28 +87,26 @@ Install the DevTools package:
   </Tabs>
 </div>
 
-### Add the middleware
+### Register the integration
 
-Wrap your language model with the DevTools middleware using [`wrapLanguageModel`](/docs/ai-sdk-core/middleware):
+Register `DevToolsTelemetry` globally so it captures all AI SDK calls:
 
 ```ts
-import { wrapLanguageModel, gateway } from 'ai';
-import { devToolsMiddleware } from '@ai-sdk/devtools';
+import { registerTelemetryIntegration } from 'ai';
+import { DevToolsTelemetry } from '@ai-sdk/devtools';
 
-const model = wrapLanguageModel({
-  model: gateway('anthropic/claude-sonnet-4.5'),
-  middleware: devToolsMiddleware(),
-});
+registerTelemetryIntegration(DevToolsTelemetry());
 ```
 
-Use the wrapped model with any AI SDK Core function:
+Then enable [telemetry](/docs/ai-sdk-core/telemetry) on your AI SDK calls:
 
-```ts
+```ts highlight="5"
 import { generateText } from 'ai';
 
 const result = await generateText({
-  model, // wrapped model with DevTools middleware
+  model: openai('gpt-4o'),
   prompt: 'What cities are in the United States?',
+  experimental_telemetry: { isEnabled: true },
 });
 ```
 

package/docs/03-ai-sdk-core/60-telemetry.mdx

@@ -116,14 +116,14 @@ You can also pass one or more integrations to individual `generateText` or `stre
 
 ```ts highlight="6-8"
 import { streamText } from 'ai';
-import { devToolsIntegration } from '@ai-sdk/devtools';
+import { DevToolsTelemetry } from '@ai-sdk/devtools';
 
 const result = streamText({
   model: openai('gpt-4o'),
   prompt: 'Hello!',
   experimental_telemetry: {
     isEnabled: true,
-    integrations: [devToolsIntegration()],
+    integrations: [DevToolsTelemetry()],
   },
 });
 ```
@@ -133,7 +133,7 @@ You can combine multiple integrations — they all receive the same lifecycle ev
 ```ts
 experimental_telemetry: {
   isEnabled: true,
-  integrations: [devToolsIntegration(), customLogger()],
+  integrations: [DevToolsTelemetry(), customLogger()],
 },
 ```
 

package/docs/03-ai-sdk-core/65-devtools.mdx

@@ -14,7 +14,7 @@ AI SDK DevTools gives you full visibility over your AI SDK calls with [`generate
 
 DevTools is composed of two parts:
 
-1. **Middleware**: Captures runs and steps from your AI SDK calls
+1. **Telemetry Integration**: Captures runs and steps from your AI SDK calls via the [telemetry](/docs/ai-sdk-core/telemetry) system
 2. **Viewer**: A web UI to inspect the captured data
 
 ## Installation
@@ -32,28 +32,42 @@ pnpm add @ai-sdk/devtools
 
 ## Using DevTools
 
-### Add the middleware
+### Register the integration
 
-Wrap your language model with the DevTools middleware using [`wrapLanguageModel`](/docs/ai-sdk-core/middleware):
+Register `DevToolsTelemetry` globally so it captures all AI SDK calls:
 
 ```ts
-import { wrapLanguageModel, gateway } from 'ai';
-import { devToolsMiddleware } from '@ai-sdk/devtools';
+import { registerTelemetryIntegration } from 'ai';
+import { DevToolsTelemetry } from '@ai-sdk/devtools';
 
-const model = wrapLanguageModel({
-  model: gateway('anthropic/claude-sonnet-4.5'),
-  middleware: devToolsMiddleware(),
-});
+registerTelemetryIntegration(DevToolsTelemetry());
 ```
 
-The wrapped model can be used with any AI SDK Core function:
+Then enable telemetry on your AI SDK calls:
 
-```ts highlight="4"
+```ts highlight="5"
 import { generateText } from 'ai';
 
 const result = await generateText({
-  model, // wrapped model with DevTools
+  model: openai('gpt-4o'),
   prompt: 'What cities are in the United States?',
+  experimental_telemetry: { isEnabled: true },
+});
+```
+
+You can also pass the integration to individual calls instead of registering it globally:
+
+```ts highlight="7-9"
+import { streamText } from 'ai';
+import { DevToolsTelemetry } from '@ai-sdk/devtools';
+
+const result = streamText({
+  model: openai('gpt-4o'),
+  prompt: 'Hello!',
+  experimental_telemetry: {
+    isEnabled: true,
+    integrations: [DevToolsTelemetry()],
+  },
 });
 ```
 
@@ -80,7 +94,7 @@ npx @ai-sdk/devtools
 
 ## Captured data
 
-The DevTools middleware captures the following information from your AI SDK calls:
+DevTools captures the following information from your AI SDK calls:
 
 - **Input parameters and prompts**: View the complete input sent to your LLM
 - **Output content and tool calls**: Inspect generated text and tool invocations
@@ -94,14 +108,14 @@ DevTools organizes captured data into runs and steps:
 - **Run**: A complete multi-step AI interaction, grouped by the initial prompt
 - **Step**: A single LLM call within a run (e.g., one `generateText` or `streamText` call)
 
-Multi-step interactions, such as those created by tool calling or agent loops, are grouped together as a single run with multiple steps.
+Multi-step interactions, such as those created by tool calling or agent loops, are grouped together as a single run with multiple steps. Nested sub-agent calls are linked to their parent run, making it easy to trace the full execution tree.
 
 ## How it works
 
-The DevTools middleware intercepts all `generateText` and `streamText` calls through the [language model middleware](/docs/ai-sdk-core/middleware) system. Captured data is stored locally in a JSON file (`.devtools/generations.json`) and served through a web UI built with Hono and React.
+The `DevToolsTelemetry` integration hooks into the AI SDK [telemetry](/docs/ai-sdk-core/telemetry) lifecycle to capture all `generateText`, `streamText`, `generateObject`, and `streamObject` calls. Captured data is stored locally in a JSON file (`.devtools/generations.json`) and served through a web UI built with Hono and React.
 
 <Note type="warning">
-  The middleware automatically adds `.devtools` to your `.gitignore` file.
+  The integration automatically adds `.devtools` to your `.gitignore` file.
   Verify that `.devtools` is in your `.gitignore` to ensure you don't commit
   sensitive AI interaction data to your repository.
 </Note>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.0-beta.81",
+  "version": "7.0.0-beta.83",
   "description": "AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -44,7 +44,7 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/gateway": "4.0.0-beta.45",
+    "@ai-sdk/gateway": "4.0.0-beta.46",
     "@ai-sdk/provider": "4.0.0-beta.10",
     "@ai-sdk/provider-utils": "5.0.0-beta.17"
   },