ai 7.0.0-beta.182 → 7.0.0-beta.183

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # ai
 
+## 7.0.0-beta.183
+
+### Patch Changes
+
+- Updated dependencies [8e990ff]
+  - @ai-sdk/gateway@4.0.0-beta.111
+
 ## 7.0.0-beta.182
 
 ### Patch Changes

package/dist/index.js

@@ -1088,7 +1088,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.0-beta.182" : "0.0.0-test";
+var VERSION = true ? "7.0.0-beta.183" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/dist/internal/index.js

@@ -83,7 +83,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.0-beta.182" : "0.0.0-test";
+var VERSION = true ? "7.0.0-beta.183" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/docs/02-foundations/06-provider-options.mdx

@@ -87,6 +87,8 @@ console.log(
 
 When working with reasoning models, you may want to see _how_ the model arrived at its answer. The `reasoningSummary` option surfaces the model's thought process.
 
+When `reasoningEffort` is set to a value other than `'none'`, the OpenAI Responses provider defaults `reasoningSummary` to `'detailed'`. Set `reasoningSummary: null` to omit reasoning summaries.
+
 #### Streaming
 
 ```ts

package/docs/03-agents/07-workflow-agent.mdx

@@ -627,7 +627,9 @@ whether approval is required (see [Tool Approval](#tool-approval) above).
 
 ### `uiMessages` / `collectUIMessages` is gone
 
-`DurableAgent.stream()` returned accumulated `uiMessages` when `collectUIMessages: true` was set. `WorkflowAgent.stream()` returns `ModelMessage[]` on `result.messages` instead — persist those and convert them at the edge with `convertToModelMessages` / `convertToUIMessages` as needed.
+`DurableAgent.stream()` returned accumulated `uiMessages` when `collectUIMessages: true` was set. `WorkflowAgent.stream()` returns `ModelMessage[]` on `result.messages` instead.
+
+For persistence, store `UIMessage[]` as your source of truth and call [`convertToModelMessages`](/docs/reference/ai-sdk-ui/convert-to-model-messages) before passing them to the agent — this is the pattern described in [Chatbot Message Persistence](/docs/ai-sdk-ui/chatbot-message-persistence). There is no built-in `ModelMessage` → `UIMessage` conversion, so avoid persisting `result.messages` as your only copy if you need to render the conversation in the UI later.
 
 ```diff
   const result = await agent.stream({

package/docs/03-agents/08-terminal-ui.mdx

@@ -55,6 +55,31 @@ await runAgentTUI({
 
 `runAgentTUI` runs until the user exits with `Esc` or `Ctrl+C`.
 
+## Sandbox
+
+Pass a sandbox session with the `sandbox` option when your agent tools need an
+execution environment:
+
+```ts
+import { createJustBashSandbox } from '@ai-sdk/sandbox-just-bash';
+
+const sandboxSession = await createJustBashSandbox({
+  cwd: '/home/user',
+}).createSession();
+
+await runAgentTUI({
+  title: 'Sandbox Agent',
+  agent,
+  sandbox: sandboxSession.restricted(),
+});
+```
+
+The terminal UI forwards the sandbox to every agent call as
+`experimental_sandbox`. Tool description functions and tool `execute` functions
+can read it from their options and delegate command or file operations to it.
+Add the sandbox description to your agent instructions if the model should know
+details such as the working directory, public hostname, or exposed ports.
+
 ## Display Options
 
 You can control how tool calls, reasoning, and response statistics are shown:

package/docs/07-reference/06-ai-sdk-tui/01-run-agent-tui.mdx

@@ -88,6 +88,13 @@ await runAgentTUI({
               description:
                 'The model context window size in tokens. When provided, the terminal UI shows total token usage as a percentage of this context window.',
             },
+            {
+              name: 'sandbox',
+              type: 'Experimental_SandboxSession',
+              isOptional: true,
+              description:
+                'Sandbox session that is passed through to the agent as `experimental_sandbox` on every call.',
+            },
           ],
         },
       ],
@@ -161,6 +168,28 @@ await runAgentTUI({
 });
 ```
 
+## Example with Sandbox
+
+```ts
+import { createJustBashSandbox } from '@ai-sdk/sandbox-just-bash';
+
+const sandboxSession = await createJustBashSandbox({
+  cwd: '/home/user',
+}).createSession();
+
+await runAgentTUI({
+  title: 'Sandbox Assistant',
+  agent,
+  sandbox: sandboxSession.restricted(),
+});
+```
+
+The sandbox is forwarded to every `agent.stream()` call as
+`experimental_sandbox`, making it available to tool description functions and
+tool `execute` functions. Include the sandbox description in the agent
+instructions when the model should know sandbox-specific details such as the
+working directory or exposed ports.
+
 ## Compatibility
 
 Use `runAgentTUI` for agents that can run directly from free-form user input.

package/docs/08-migration-guides/23-migration-guide-7-0.mdx

@@ -5,6 +5,18 @@ description: Learn how to upgrade AI SDK 6.x to 7.0.
 
 # Migrate AI SDK 6.x to 7.0
 
+Use the command below to add the migration skill:
+
+```bash
+npx skills add vercel/ai --skill migrate-ai-sdk-v6-to-v7
+```
+
+Then ask your agent:
+
+```txt
+Use the migrate-ai-sdk-v6-to-v7 skill and migrate my app from AI SDK v6 to v7.
+```
+
 ## Recommended Migration Process
 
 1. Backup your project. If you use a versioning control system, make sure all previous versions are committed.
@@ -1821,6 +1833,14 @@ const { messages, sendMessage } = useChat(() => ({
 
 The `Chat` class continues to work as a deprecated export, so you can migrate incrementally.
 
+## OpenAI Provider
+
+### Responses Reasoning Summary Defaults to Detailed
+
+For the OpenAI Responses provider, setting `reasoning` or `providerOptions.openai.reasoningEffort` to a value other than `'none'` now defaults `providerOptions.openai.reasoningSummary` to `'detailed'`.
+
+If you want to keep reasoning summaries disabled, set `providerOptions.openai.reasoningSummary` to `null`.
+
 ## Anthropic Provider
 
 ### `providerMetadata.anthropic.cacheCreationInputTokens` Removed
@@ -1862,3 +1882,11 @@ Every type, class, and function in `@ai-sdk/google` that contained `GoogleGenera
 The old names still work as deprecated aliases, but you should migrate to the new names, if you currently reference them.
 
 The main entry point the `google` constant, remains unchanged, so if that's all you use from the provider, no changes are required.
+
+# Migration Skill
+
+Use the command below to add the migration skill and guide your agent
+
+```bash
+npx skills add vercel/ai --skill migrate-ai-sdk-v6-to-v7
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.0-beta.182",
+  "version": "7.0.0-beta.183",
   "type": "module",
   "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",
@@ -42,7 +42,7 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/gateway": "4.0.0-beta.110",
+    "@ai-sdk/gateway": "4.0.0-beta.111",
     "@ai-sdk/provider": "4.0.0-beta.19",
     "@ai-sdk/provider-utils": "5.0.0-beta.49"
   },