ai_sdk_openai 1.2.0

OpenAI provider for the AI SDK Dart port.

1.2.0

• Refactored onto the shared ai_sdk_openai_compatible base. The OpenAI Chat Completions wire format (multimodal content parts, tools / tool_choice, response_format JSON schema, SSE streaming + usage, non-streaming tool-call parsing) now lives in one place that the OpenAI provider configures. No public API or behavior change.
• Errors: non-2xx responses on the embeddings / image / speech / transcription endpoints (and chat, via the shared base) now throw a typed AiApiCallError instead of a raw DioException.
• Fixed: no longer sends response_format when generating images with gpt-image-1 (the model rejects the parameter with a 400).
• Now requires ai_sdk_openai_compatible ^1.2.0.
• 100% line coverage.

---

1.1.0

New Features

• OpenAILanguageModelOptions — typed options class for OpenAI-specific call settings.
  • reasoningEffort — 'low' | 'medium' | 'high' passed as reasoning_effort in the request body (for o1, o3, o4-mini reasoning models).
  • reasoningSummary — 'auto' | 'concise' | 'detailed' passed as reasoning_summary.
  • Pass via providerOptions: {'openai': options.toMap()} or directly as snake_case keys.
• Native structured output (response_format: json_schema) — when LanguageModelV3CallOptions.outputSchema is set (automatically set by generateObject / streamObject), the provider sends response_format: {type: 'json_schema', json_schema: {name: 'response', schema: ..., strict: true}} instead of relying solely on system-prompt instructions.

---

1.0.0+1

• Improved pubspec descriptions for better pub.dev discoverability.
• Added example/example.md with usage examples and links to runnable apps.

1.0.0

First stable release. Depends on ai_sdk_dart 1.0.0.

• openai('gpt-4.1-mini') factory — create language model instances for any OpenAI-compatible endpoint.
• openaiEmbedding(modelId) — text embedding models (text-embedding-3-small / large).
• openaiImage(modelId) — image generation (DALL-E 3).
• Full SSE streaming with tool call delta accumulation.
• stream_options: {include_usage: true} for streaming usage reporting.
• Tool choice mapping: auto / required / none / specific.
• Strict tool schema forwarding (strict: true).
• Extended thinking passthrough via provider metadata.
• Source, file content, and raw finish reason forwarding.
• Configurable baseUrl for Azure OpenAI and compatible endpoints.

---

0.2.0

• Initial release.
• openai(modelId) factory for language model instances.
• openaiEmbedding(modelId) factory for embedding model instances.
• openaiImage(modelId) factory for image generation model instances.
• Full SSE streaming with tool call accumulation.
• Tool choice mapping (auto / required / none / specific tool).
• Strict tool schema forwarding (strict: true).
• Source and file content extraction from responses.
• Provider metadata and raw finish reason forwarding.