ai 7.0.109 → 7.0.110

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,12 @@
1
1
  # ai
2
2
 
3
+ ## 7.0.110
4
+
5
+ ### Patch Changes
6
+
7
+ - Updated dependencies [49295bb]
8
+ - @ai-sdk/gateway@4.0.89
9
+
3
10
  ## 7.0.109
4
11
 
5
12
  ### Patch Changes
package/dist/index.js CHANGED
@@ -1334,7 +1334,7 @@ import {
1334
1334
  } from "@ai-sdk/provider-utils";
1335
1335
 
1336
1336
  // src/version.ts
1337
- var VERSION = true ? "7.0.109" : "0.0.0-test";
1337
+ var VERSION = true ? "7.0.110" : "0.0.0-test";
1338
1338
 
1339
1339
  // src/util/download/download.ts
1340
1340
  var download = async ({
@@ -91,7 +91,7 @@ import {
91
91
  } from "@ai-sdk/provider-utils";
92
92
 
93
93
  // src/version.ts
94
- var VERSION = true ? "7.0.109" : "0.0.0-test";
94
+ var VERSION = true ? "7.0.110" : "0.0.0-test";
95
95
 
96
96
  // src/util/download/download.ts
97
97
  var download = async ({
@@ -145,6 +145,7 @@ Here are the capabilities of popular models:
145
145
  | [OpenAI](/providers/ai-sdk-providers/openai) | `gpt-5.1` | <Check /> | <Check /> | <Check /> | <Check /> |
146
146
  | [OpenAI](/providers/ai-sdk-providers/openai) | `gpt-5-codex` | <Check /> | <Check /> | <Check /> | <Check /> |
147
147
  | [OpenAI](/providers/ai-sdk-providers/openai) | `gpt-5-chat-latest` | <Check /> | <Check /> | <Check /> | <Check /> |
148
+ | [Anthropic](/providers/ai-sdk-providers/anthropic) | `claude-opus-5-5` | <Check /> | <Check /> | <Check /> | <Check /> |
148
149
  | [Anthropic](/providers/ai-sdk-providers/anthropic) | `claude-sonnet-5` | <Check /> | <Check /> | <Check /> | <Check /> |
149
150
  | [Anthropic](/providers/ai-sdk-providers/anthropic) | `claude-fable-5-1` | <Check /> | <Check /> | <Check /> | <Check /> |
150
151
  | [Anthropic](/providers/ai-sdk-providers/anthropic) | `claude-fable-5` | <Check /> | <Check /> | <Check /> | <Check /> |
@@ -55,7 +55,7 @@ Use a provider's `evaluationModel` factory:
55
55
  | Anthropic | `anthropic.evaluationModel('claude-haiku-4-5-20251001')` |
56
56
  | Google | `google.evaluationModel('gemini-3.5-flash-lite')` |
57
57
 
58
- TypeSafe AI supplies native Choice, Score, and Boolean evaluations. OpenAI,
58
+ TypeSafe AI's [Jev](https://vercel.com/i/what-is-jev) supplies native Choice, Score, and Boolean evaluations. OpenAI,
59
59
  Anthropic, and Google adapt structured language-model output for all three types.
60
60
  Boolean answers contain prompted estimates of P(true), validated to be finite
61
61
  and in `[0, 1]`. These estimates are not guaranteed to be calibrated. Choice and
@@ -272,3 +272,13 @@ Runnable examples are in
272
272
  [`examples/ai-functions/src/evaluate`](https://github.com/vercel/ai/tree/main/examples/ai-functions/src/evaluate),
273
273
  including basic examples for TypeSafe, OpenAI, Anthropic, and Google, model
274
274
  registries, custom aliases, default-provider strings, and probability-based routing.
275
+
276
+ ## Related resources
277
+
278
+ Explore use cases, implementation guides, and a deployable template for using
279
+ Jev from TypeSafe AI with the AI SDK:
280
+
281
+ - [Jev use cases](https://vercel.com/i/jev-use-cases): Explore ideas for applying evaluation in your application.
282
+ - [Classify, route, and score with Jev and AI SDK](https://vercel.com/kb/guide/typesafe-jev-and-ai-sdk): Learn how to ask typed questions, route answers using probabilities, and test routing logic with a mock evaluation model.
283
+ - [Jev and AI SDK form router guide](https://vercel.com/kb/guide/jev-ai-sdk-form-router): Explore form routing with Jev and the AI SDK.
284
+ - [Jev and AI SDK form router template](https://vercel.com/templates/next.js/jev-and-ai-sdk): Deploy a Next.js application that routes form submissions with Jev and uses a language model fallback for uncertain or failed evaluations.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ai",
3
- "version": "7.0.109",
3
+ "version": "7.0.110",
4
4
  "type": "module",
5
5
  "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.",
6
6
  "license": "Apache-2.0",
@@ -42,14 +42,14 @@
42
42
  }
43
43
  },
44
44
  "dependencies": {
45
- "@ai-sdk/gateway": "4.0.88",
45
+ "@ai-sdk/gateway": "4.0.89",
46
46
  "@ai-sdk/provider": "4.0.17",
47
47
  "@ai-sdk/provider-utils": "5.0.45"
48
48
  },
49
49
  "devDependencies": {
50
- "@ai-sdk/amazon-bedrock": "5.0.90",
50
+ "@ai-sdk/amazon-bedrock": "5.0.91",
51
51
  "@ai-sdk/deepseek": "3.0.50",
52
- "@ai-sdk/google": "4.0.76",
52
+ "@ai-sdk/google": "4.0.77",
53
53
  "@ai-sdk/groq": "4.0.46",
54
54
  "@ai-sdk/huggingface": "2.0.53",
55
55
  "@ai-sdk/moonshotai": "3.0.54",