Backport: fix(ai): remove unused mode setting from generateObject and streamObject (#10897)

This is an automated backport of #10896 to the release-v5.0 branch. FYI @lgrammel Co-authored-by: Lars Grammel <lars.grammel@gmail.com>

Author: vercel-ai-sdk[bot]

.changeset/thin-jobs-train.md

@@ -0,0 +1,5 @@
+---
+'ai': patch
+---
+
+fix(ai): remove unused mode setting from generateObject and streamObject

content/docs/07-reference/01-ai-sdk-core/03-generate-object.mdx

@@ -105,14 +105,6 @@ To see `generateObject` in action, check out the [additional examples](#more-exa
  type: "'object' | 'array' | 'enum' | 'no-schema' | undefined",
  description: "The type of output to generate. Defaults to 'object'.",
  },
- {
- name: 'mode',
- type: "'auto' | 'json' | 'tool'",
- description:
- "The mode to use for object generation. Not every model supports all modes. \
- Defaults to 'auto' for 'object' output and to 'json' for 'no-schema' output. \
- Must be 'json' for 'no-schema' output.",
- },
  {
  name: 'schema',
  type: 'Zod Schema | JSON Schema',

content/docs/07-reference/01-ai-sdk-core/04-stream-object.mdx

@@ -118,14 +118,6 @@ To see `streamObject` in action, check out the [additional examples](#more-examp
  type: "'object' | 'array' | 'enum' | 'no-schema' | undefined",
  description: "The type of output to generate. Defaults to 'object'.",
  },
- {
- name: 'mode',
- type: "'auto' | 'json' | 'tool'",
- description:
- "The mode to use for object generation. Not every model supports all modes. \
- Defaults to 'auto' for 'object' output and to 'json' for 'no-schema' output. \
- Must be 'json' for 'no-schema' output.",
- },
  {
  name: 'schema',
  type: 'Zod Schema | JSON Schema',

packages/ai/src/generate-object/generate-object.ts

@@ -128,7 +128,6 @@ export async function generateObject<
 The enum values that the model should use.
  */
  enum: Array<RESULT>;
- mode?: 'json';
  output: 'enum';
  }
  : OUTPUT extends 'no-schema'
@@ -152,21 +151,6 @@ Used by some providers for additional LLM guidance, e.g.
 via tool or schema description.
  */
  schemaDescription?: string;
-
- /**
-The mode to use for object generation.
-
-The schema is converted into a JSON schema and used in one of the following ways
-
-- 'auto': The provider will choose the best mode for the model.
-- 'tool': A tool with the JSON schema as parameters is provided and the provider is instructed to use it.
-- 'json': The JSON schema and an instruction are injected into the prompt. If the provider supports JSON mode, it is enabled. If the provider supports JSON grammars, the grammar is used.
-
-Please note that most providers do not support all modes.
-
-Default and recommended: 'auto' (best mode for the model).
- */
- mode?: 'auto' | 'json' | 'tool';
  }) & {
  output?: OUTPUT;
 

packages/ai/src/generate-object/stream-object.ts

@@ -185,7 +185,6 @@ export function streamObject<
 The enum values that the model should use.
  */
  enum: Array<RESULT>;
- mode?: 'json';
  output: 'enum';
  }
  : OUTPUT extends 'no-schema'
@@ -209,21 +208,6 @@ Used by some providers for additional LLM guidance, e.g.
 via tool or schema description.
  */
  schemaDescription?: string;
-
- /**
-The mode to use for object generation.
-
-The schema is converted into a JSON schema and used in one of the following ways
-
-- 'auto': The provider will choose the best mode for the model.
-- 'tool': A tool with the JSON schema as parameters is provided and the provider is instructed to use it.
-- 'json': The JSON schema and an instruction are injected into the prompt. If the provider supports JSON mode, it is enabled. If the provider supports JSON grammars, the grammar is used.
-
-Please note that most providers do not support all modes.
-
-Default and recommended: 'auto' (best mode for the model).
- */
- mode?: 'auto' | 'json' | 'tool';
  }) & {
  output?: OUTPUT;