ai 7.0.0-beta.8 → 7.0.0-beta.81

package/CHANGELOG.md

@@ -1,5 +1,560 @@
 # ai
 
+## 7.0.0-beta.81
+
+### Patch Changes
+
+- 2fe1099: feat(ai): emit streaming chunks throught the onChunk callback
+- f04adcb: feat(ai): refresh `customProvider` and `createProviderRegistry` to support file and skill upload abstractions
+
+## 7.0.0-beta.80
+
+### Patch Changes
+
+- 3ae1786: fix: better context type inference
+- Updated dependencies [3ae1786]
+  - @ai-sdk/provider-utils@5.0.0-beta.17
+  - @ai-sdk/gateway@4.0.0-beta.45
+
+## 7.0.0-beta.79
+
+### Patch Changes
+
+- 6866afe: fix(ai): fix `lastAssistantMessageIsCompleteWithApprovalResponses` to no longer ignore `providerExecuted` tool approvals
+
+## 7.0.0-beta.78
+
+### Patch Changes
+
+- f372547: fix(ai): fix `providerExecuted` tool approvals being passed to language model twice
+- Updated dependencies [7943a4b]
+  - @ai-sdk/gateway@4.0.0-beta.44
+
+## 7.0.0-beta.77
+
+### Patch Changes
+
+- 2add429: fix(ai): skip passing invalid JSON inputs to response messages
+
+## 7.0.0-beta.76
+
+### Major Changes
+
+- fcc6869: refactor(ai/core): rename `ModelCallStreamPart` to `LanguageModelStreamPart` and align stream model call naming (`streamLanguageModelCall`, `experimental_streamLanguageModelCall`).
+
+  This updates experimental low-level stream primitives to use "language model call" terminology consistently.
+
+## 7.0.0-beta.75
+
+### Patch Changes
+
+- 176466a: chore(provider): align V4 model return types to have their own definitions across all model interfaces
+- Updated dependencies [176466a]
+  - @ai-sdk/provider@4.0.0-beta.10
+  - @ai-sdk/gateway@4.0.0-beta.43
+  - @ai-sdk/provider-utils@5.0.0-beta.16
+
+## 7.0.0-beta.74
+
+### Patch Changes
+
+- e311194: feat(ai): allow passing provider instance to `uploadFile` and `uploadSkill` as shorthand
+- Updated dependencies [e311194]
+  - @ai-sdk/provider@4.0.0-beta.9
+  - @ai-sdk/gateway@4.0.0-beta.42
+  - @ai-sdk/provider-utils@5.0.0-beta.15
+
+## 7.0.0-beta.73
+
+### Patch Changes
+
+- Updated dependencies [1464561]
+  - @ai-sdk/gateway@4.0.0-beta.41
+
+## 7.0.0-beta.72
+
+### Patch Changes
+
+- 664a0eb: feat (ai/core): support plain string model IDs in `rerank()` function
+
+  The `rerank()` function now accepts plain model strings (e.g., `'cohere/rerank-v3.5'`) in addition to `RerankingModel` objects, matching the behavior of `generateText`, `embed`, and other core functions.
+
+## 7.0.0-beta.71
+
+### Patch Changes
+
+- e68be55: fix(ai): skip stringifying text when streaming partial text
+- Updated dependencies [939171f]
+  - @ai-sdk/gateway@4.0.0-beta.40
+
+## 7.0.0-beta.70
+
+### Patch Changes
+
+- Updated dependencies [0694029]
+  - @ai-sdk/gateway@4.0.0-beta.39
+
+## 7.0.0-beta.69
+
+### Major Changes
+
+- 72223e7: chore(ai): remove deprecated isToolOrDynamicToolUIPart function
+
+### Patch Changes
+
+- 34bd95d: feat(ai): add support for uploading provider skills using the provider references abstraction
+- 008271d: feat(openai-compatible): emit warning when using kebab-case instead of camelCase
+- Updated dependencies [34bd95d]
+- Updated dependencies [008271d]
+  - @ai-sdk/provider@4.0.0-beta.8
+  - @ai-sdk/gateway@4.0.0-beta.38
+  - @ai-sdk/provider-utils@5.0.0-beta.14
+
+## 7.0.0-beta.68
+
+### Major Changes
+
+- 7e26e81: chore: rename experimental_context to context
+
+### Patch Changes
+
+- b0c2869: chore(ai): remove deprecated `media` type part from `ToolResultOutput`
+- Updated dependencies [b0c2869]
+- Updated dependencies [7e26e81]
+  - @ai-sdk/provider-utils@5.0.0-beta.13
+  - @ai-sdk/gateway@4.0.0-beta.37
+
+## 7.0.0-beta.67
+
+### Patch Changes
+
+- d1a8bed: fix(ui): export `isDynamicToolUIPart` from `ai` package
+
+## 7.0.0-beta.66
+
+### Patch Changes
+
+- Updated dependencies [fb0c233]
+- Updated dependencies [d1f0d2b]
+  - @ai-sdk/gateway@4.0.0-beta.36
+
+## 7.0.0-beta.65
+
+### Patch Changes
+
+- Updated dependencies [46d1149]
+  - @ai-sdk/provider-utils@5.0.0-beta.12
+  - @ai-sdk/gateway@4.0.0-beta.35
+
+## 7.0.0-beta.64
+
+### Patch Changes
+
+- Updated dependencies [71b0e7d]
+  - @ai-sdk/gateway@4.0.0-beta.34
+
+## 7.0.0-beta.63
+
+### Patch Changes
+
+- 6fd51c0: fix(provider): preserve error type prefix in getErrorMessage
+- Updated dependencies [6fd51c0]
+  - @ai-sdk/provider-utils@5.0.0-beta.11
+  - @ai-sdk/provider@4.0.0-beta.7
+  - @ai-sdk/gateway@4.0.0-beta.33
+
+## 7.0.0-beta.62
+
+### Patch Changes
+
+- Updated dependencies [11746ca]
+  - @ai-sdk/gateway@4.0.0-beta.32
+
+## 7.0.0-beta.61
+
+### Patch Changes
+
+- c29a26f: feat(provider): add support for provider references and uploading files as supported per provider
+- Updated dependencies [c29a26f]
+  - @ai-sdk/provider-utils@5.0.0-beta.10
+  - @ai-sdk/provider@4.0.0-beta.6
+  - @ai-sdk/gateway@4.0.0-beta.31
+
+## 7.0.0-beta.60
+
+### Patch Changes
+
+- 38fc777: Add AI Gateway hint to provider READMEs
+
+## 7.0.0-beta.59
+
+### Patch Changes
+
+- Updated dependencies [4552cbf]
+  - @ai-sdk/gateway@4.0.0-beta.30
+
+## 7.0.0-beta.58
+
+### Patch Changes
+
+- 2e17091: fix(types): move shared tool set utility types into provider-utils
+
+  Moved `ToolSet`, `InferToolSetContext`, and `UnionToIntersection` into `@ai-sdk/provider-utils` and updated `ai` internals to import them directly from there. This keeps the shared tool typing utilities colocated with the core tool type definitions.
+
+- Updated dependencies [2e17091]
+  - @ai-sdk/provider-utils@5.0.0-beta.9
+  - @ai-sdk/gateway@4.0.0-beta.29
+
+## 7.0.0-beta.57
+
+### Major Changes
+
+- 986c6fd: feat(ai): change type of experimental_context from unknown to generic
+- 493295c: Remove the deprecated `ToolCallOptions` export.
+
+  Use `ToolExecutionOptions` instead.
+
+### Patch Changes
+
+- Updated dependencies [986c6fd]
+- Updated dependencies [493295c]
+  - @ai-sdk/provider-utils@5.0.0-beta.8
+  - @ai-sdk/gateway@4.0.0-beta.28
+
+## 7.0.0-beta.56
+
+### Patch Changes
+
+- Updated dependencies [70a9aae]
+  - @ai-sdk/gateway@4.0.0-beta.27
+
+## 7.0.0-beta.55
+
+### Major Changes
+
+- b3c9f6a: feat(ai): create new opentelemetry package (@ai-sdk/otel)
+
+## 7.0.0-beta.54
+
+### Patch Changes
+
+- 5d0f18e: feat(ai): move opentelemetry to new package
+
+## 7.0.0-beta.53
+
+### Patch Changes
+
+- 9b47dea: fix(ai): remove otel Tracer api from telemetry settings
+
+## 7.0.0-beta.52
+
+### Patch Changes
+
+- b56301c: feat(ai): decouple otel from generate/streamObject
+
+## 7.0.0-beta.51
+
+### Patch Changes
+
+- 6abd098: split `prepareToolsAndToolChoice()` into `prepareTools()` and `prepareToolChoice()`
+
+## 7.0.0-beta.50
+
+### Patch Changes
+
+- 3debdb7: feat(ai): rename `stepCountIs` to `isStepCount`
+
+## 7.0.0-beta.49
+
+### Patch Changes
+
+- Updated dependencies [294cbe7]
+  - @ai-sdk/gateway@4.0.0-beta.26
+
+## 7.0.0-beta.48
+
+### Patch Changes
+
+- 5c4d910: feat(ai): add new `isLoopFinished` stop condition helper for unlimited steps
+
+## 7.0.0-beta.47
+
+### Patch Changes
+
+- bc67b4f: feat(ai): add experimental callbacks for structured outputs
+
+## 7.0.0-beta.46
+
+### Patch Changes
+
+- 31ee822: refactoring(ai): extract filterActiveTools and expose it as experimental_filterActiveTools
+
+## 7.0.0-beta.45
+
+### Patch Changes
+
+- Updated dependencies [435895b]
+  - @ai-sdk/gateway@4.0.0-beta.25
+
+## 7.0.0-beta.44
+
+### Patch Changes
+
+- Updated dependencies [d30466c]
+  - @ai-sdk/gateway@4.0.0-beta.24
+
+## 7.0.0-beta.43
+
+### Patch Changes
+
+- Updated dependencies [4ec78cd]
+  - @ai-sdk/gateway@4.0.0-beta.23
+
+## 7.0.0-beta.42
+
+### Patch Changes
+
+- a3fd75b: feat(ai): expose Experimental_ModelCallStreamPart type
+
+## 7.0.0-beta.41
+
+### Patch Changes
+
+- Updated dependencies [7ceff62]
+  - @ai-sdk/gateway@4.0.0-beta.22
+
+## 7.0.0-beta.40
+
+### Patch Changes
+
+- 989d3d2: fix(ai): include generated files in OTEL response attributes
+
+## 7.0.0-beta.39
+
+### Patch Changes
+
+- f4cfccd: feat(ai): decouple otel from rerank function
+
+## 7.0.0-beta.38
+
+### Patch Changes
+
+- 1f509d4: fix(ai): force template check on 'kind' param
+- Updated dependencies [1f509d4]
+  - @ai-sdk/provider-utils@5.0.0-beta.7
+  - @ai-sdk/provider@4.0.0-beta.5
+  - @ai-sdk/gateway@4.0.0-beta.21
+
+## 7.0.0-beta.37
+
+### Patch Changes
+
+- Updated dependencies [4f91b5d]
+  - @ai-sdk/gateway@4.0.0-beta.20
+
+## 7.0.0-beta.36
+
+### Patch Changes
+
+- 118b953: feat(ai): decouple otel from embed functions
+
+## 7.0.0-beta.35
+
+### Patch Changes
+
+- 99bf941: feat(ai): extract streamModelCall function for streaming text generation
+
+## 7.0.0-beta.34
+
+### Patch Changes
+
+- Updated dependencies [72889f8]
+  - @ai-sdk/gateway@4.0.0-beta.19
+
+## 7.0.0-beta.33
+
+### Patch Changes
+
+- caf1b6f: feat(ai): introduce experimental callbacks for rerank function
+
+## 7.0.0-beta.32
+
+### Major Changes
+
+- 4b46062: refactoring(ai): extract tool callback invocation into separate function and forward chunks before callback invocation
+
+### Patch Changes
+
+- Updated dependencies [165b97a]
+  - @ai-sdk/gateway@4.0.0-beta.18
+
+## 7.0.0-beta.31
+
+### Patch Changes
+
+- e79e644: chore(ai/core): remove `timeout` from `CallSettings` as it was effectively unused there
+
+## 7.0.0-beta.30
+
+### Patch Changes
+
+- f5a6f89: README updates
+
+## 7.0.0-beta.29
+
+### Patch Changes
+
+- 877bf12: fix(ai): flatten model attributes for telemetry
+
+## 7.0.0-beta.28
+
+### Major Changes
+
+- b9cf502: refactoring(ai): delay tool execution in stream text until model call is finished
+
+## 7.0.0-beta.27
+
+### Patch Changes
+
+- 3887c70: feat(provider): add new top-level reasoning parameter to spec and support it in `generateText` and `streamText`
+- Updated dependencies [3887c70]
+  - @ai-sdk/provider-utils@5.0.0-beta.6
+  - @ai-sdk/provider@4.0.0-beta.4
+  - @ai-sdk/gateway@4.0.0-beta.17
+
+## 7.0.0-beta.26
+
+### Patch Changes
+
+- f0b0b20: feat(ai): add per-tool timeout overrides via toolTimeouts
+
+## 7.0.0-beta.25
+
+### Patch Changes
+
+- ff9ce30: feat(ai): introduce experimental callbacks for embed function
+
+## 7.0.0-beta.24
+
+### Major Changes
+
+- 776b617: feat(provider): adding new 'custom' content type
+
+### Patch Changes
+
+- Updated dependencies [776b617]
+  - @ai-sdk/provider-utils@5.0.0-beta.5
+  - @ai-sdk/provider@4.0.0-beta.3
+  - @ai-sdk/gateway@4.0.0-beta.16
+
+## 7.0.0-beta.23
+
+### Patch Changes
+
+- 80d4dde: fix(ai): include tool input on tool result for provider executed dynamic tools
+- Updated dependencies [61753c3]
+  - @ai-sdk/provider-utils@5.0.0-beta.4
+  - @ai-sdk/gateway@4.0.0-beta.15
+
+## 7.0.0-beta.22
+
+### Patch Changes
+
+- Updated dependencies [ead9144]
+  - @ai-sdk/gateway@4.0.0-beta.14
+
+## 7.0.0-beta.21
+
+### Patch Changes
+
+- 34fd051: feat(ai): add toolMs to timeout configuration
+
+## 7.0.0-beta.20
+
+### Patch Changes
+
+- Updated dependencies [2095655]
+  - @ai-sdk/gateway@4.0.0-beta.13
+
+## 7.0.0-beta.19
+
+### Patch Changes
+
+- Updated dependencies [f7d4f01]
+  - @ai-sdk/provider-utils@5.0.0-beta.3
+  - @ai-sdk/provider@4.0.0-beta.2
+  - @ai-sdk/gateway@4.0.0-beta.12
+
+## 7.0.0-beta.18
+
+### Patch Changes
+
+- Updated dependencies [5c2a5a2]
+  - @ai-sdk/provider@4.0.0-beta.1
+  - @ai-sdk/gateway@4.0.0-beta.11
+  - @ai-sdk/provider-utils@5.0.0-beta.2
+
+## 7.0.0-beta.17
+
+### Patch Changes
+
+- Updated dependencies [4d6ab9a]
+  - @ai-sdk/gateway@4.0.0-beta.10
+
+## 7.0.0-beta.16
+
+### Major Changes
+
+- 5b8c58f: feat(ai): decouple otel from core functions
+
+## 7.0.0-beta.15
+
+### Patch Changes
+
+- Updated dependencies [980f777]
+- Updated dependencies [7185ba2]
+  - @ai-sdk/gateway@4.0.0-beta.9
+
+## 7.0.0-beta.14
+
+### Patch Changes
+
+- Updated dependencies [4adc485]
+  - @ai-sdk/gateway@4.0.0-beta.8
+
+## 7.0.0-beta.13
+
+### Patch Changes
+
+- c26ca8d: Remove custom User-Agent header from HttpChatTransport to fix CORS preflight failures in Safari and Firefox
+
+## 7.0.0-beta.12
+
+### Patch Changes
+
+- Updated dependencies [e046ea3]
+  - @ai-sdk/gateway@4.0.0-beta.7
+
+## 7.0.0-beta.11
+
+### Patch Changes
+
+- Updated dependencies [82288b0]
+  - @ai-sdk/gateway@4.0.0-beta.6
+
+## 7.0.0-beta.10
+
+### Patch Changes
+
+- Updated dependencies [aa5a583]
+  - @ai-sdk/gateway@4.0.0-beta.5
+
+## 7.0.0-beta.9
+
+### Patch Changes
+
+- 1fe058b: fix(anthropic): preserve the error code returned by model
+
 ## 7.0.0-beta.8
 
 ### Patch Changes
@@ -926,13 +1481,13 @@
   Before
 
   ```ts
-  model.textEmbeddingModel('my-model-id');
+  model.textEmbeddingModel("my-model-id");
   ```
 
   After
 
   ```ts
-  model.embeddingModel('my-model-id');
+  model.embeddingModel("my-model-id");
   ```
 
 - b67d224: Fixes an issue where `providerMetadata` and `providerExecuted` were lost when tool input validation failed
@@ -955,15 +1510,15 @@
   This change replaces
 
   ```ts
-  import { experimental_createMCPClient } from 'ai';
-  import { Experimental_StdioMCPTransport } from 'ai/mcp-stdio';
+  import { experimental_createMCPClient } from "ai";
+  import { Experimental_StdioMCPTransport } from "ai/mcp-stdio";
   ```
 
   with
 
   ```ts
-  import { experimental_createMCPClient } from '@ai-sdk/mcp';
-  import { Experimental_StdioMCPTransport } from '@ai-sdk/mcp/mcp-stdio';
+  import { experimental_createMCPClient } from "@ai-sdk/mcp";
+  import { Experimental_StdioMCPTransport } from "@ai-sdk/mcp/mcp-stdio";
   ```
 
 - 90e5bdd: chore(ai): restructure agent files
@@ -1050,7 +1605,7 @@
 - 81d4308: feat: provider-executed dynamic tools
 - e0d1ea9: fix(ai): align logic of text-end with reasoning-end
 - 2406576: chore(agent): rename messages property on agent ui stream functions to uiMessages
-- b1aeea7: feat(ai): set default stopWhen on Agent to stepCountIs(20)
+- b1aeea7: feat(ai): set default stopWhen on Agent to isStepCount(20)
 - dce4e7b: chore(agent): rename system to instructions
 - 4ece5f9: feat(agent): add experimental_download to ToolLoopAgent
 - a417a34: feat(agent): introduce version property
@@ -1483,13 +2038,13 @@
   Before
 
   ```ts
-  model.textEmbeddingModel('my-model-id');
+  model.textEmbeddingModel("my-model-id");
   ```
 
   After
 
   ```ts
-  model.embeddingModel('my-model-id');
+  model.embeddingModel("my-model-id");
   ```
 
 - Updated dependencies [8d9e8ad]
@@ -1836,15 +2391,15 @@
   This change replaces
 
   ```ts
-  import { experimental_createMCPClient } from 'ai';
-  import { Experimental_StdioMCPTransport } from 'ai/mcp-stdio';
+  import { experimental_createMCPClient } from "ai";
+  import { Experimental_StdioMCPTransport } from "ai/mcp-stdio";
   ```
 
   with
 
   ```ts
-  import { experimental_createMCPClient } from '@ai-sdk/mcp';
-  import { Experimental_StdioMCPTransport } from '@ai-sdk/mcp/mcp-stdio';
+  import { experimental_createMCPClient } from "@ai-sdk/mcp";
+  import { Experimental_StdioMCPTransport } from "@ai-sdk/mcp/mcp-stdio";
   ```
 
 ## 6.0.0-beta.71
@@ -2226,7 +2781,7 @@
 
 - aa0515c: feat(ai): move Agent to stable
 - e7d9b00: feat(agent): add optional name property to agent
-- b1aeea7: feat(ai): set default stopWhen on Agent to stepCountIs(20)
+- b1aeea7: feat(ai): set default stopWhen on Agent to isStepCount(20)
 
 ## 5.1.0-beta.18
 
@@ -2763,7 +3318,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1', {
+    model: luma.image("photon-flash-1", {
       maxImagesPerCall: 5,
       pollIntervalMillis: 500,
     }),
@@ -2776,7 +3331,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1'),
+    model: luma.image("photon-flash-1"),
     prompt,
     n: 10,
     maxImagesPerCall: 5,
@@ -2796,7 +3351,7 @@
 - c7710a9: chore (ai): rename DataStreamToSSETransformStream to JsonToSseTransformStream
 - bfbfc4c: feat (ai): streamText/generateText: totalUsage contains usage for all steps. usage is for a single step.
 - 9ae327d: chore (ui): replace chat store concept with chat instances
-- 9315076: chore (ai): rename continueUntil to stopWhen. Rename maxSteps stop condition to stepCountIs.
+- 9315076: chore (ai): rename continueUntil to stopWhen. Rename maxSteps stop condition to isStepCount.
 - 247ee0c: chore (ai): remove steps from tool invocation ui parts
 - 109c0ac: chore (ai): rename id to chatId (in post request, resume request, and useChat)
 - 954aa73: feat (ui): extended regenerate support
@@ -2976,10 +3531,10 @@
   The `experimental_generateImage` method from the `ai` package now returnes revised prompts for OpenAI's image models.
 
   ```js
-  const prompt = 'Santa Claus driving a Cadillac';
+  const prompt = "Santa Claus driving a Cadillac";
 
   const { providerMetadata } = await experimental_generateImage({
-    model: openai.image('dall-e-3'),
+    model: openai.image("dall-e-3"),
     prompt,
   });
 
@@ -3539,7 +4094,7 @@
 ### Major Changes
 
 - 72d7d72: chore (ai): stable activeTools
-- 9315076: chore (ai): rename continueUntil to stopWhen. Rename maxSteps stop condition to stepCountIs.
+- 9315076: chore (ai): rename continueUntil to stopWhen. Rename maxSteps stop condition to isStepCount.
 
 ### Patch Changes
 
@@ -3642,7 +4197,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1', {
+    model: luma.image("photon-flash-1", {
       maxImagesPerCall: 5,
       pollIntervalMillis: 500,
     }),
@@ -3655,7 +4210,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1'),
+    model: luma.image("photon-flash-1"),
     prompt,
     n: 10,
     maxImagesPerCall: 5,
@@ -3753,10 +4308,10 @@
   The `experimental_generateImage` method from the `ai` package now returnes revised prompts for OpenAI's image models.
 
   ```js
-  const prompt = 'Santa Claus driving a Cadillac';
+  const prompt = "Santa Claus driving a Cadillac";
 
   const { providerMetadata } = await experimental_generateImage({
-    model: openai.image('dall-e-3'),
+    model: openai.image("dall-e-3"),
     prompt,
   });