@ai-sdk/openai

provider-utils: Preserve streamed tool calls with unreliable IDs and indices

The OpenAI Responses provider now accepts providerOptions.openai.reasoningEffortUpdate on empty system messages and sends each update at its position in the conversation. This lets applications change reasoning effort during a conversation while preserving the prompt prefix for caching.

openai: Expose Chat Completions audio transcripts as generated text

openai: Accept incomplete function_call items on the Responses stream, so a call truncated by max_output_tokens finishes with length instead of a TypeValidationError

GPT-6 Sol and Luna model IDs

openai: Return an AI SDK error for empty chat completion choices

Include explicit message item types in Azure AI Foundry Responses requests.

Add async function tool calling support for OpenAI Responses models.

openai: Add GPT-6 reasoning configuration updates

openai: Add support for the gpt-6-astra

Normalize non-object replayed Chat Completions tool arguments to empty objects.

Add blocked domain filters to the OpenAI and Azure Responses API web search tools.

Apply reasoning, service tier, and image defaults to recognizable future OpenAI model family versions.

Send null content for tool-call-only assistant messages.

provider/openai: Add GPT-5.6 reasoning and prompt cache controls

provider/openai,provider/gateway: Add gpt-5.6 model ids

openai: Add orchestration token usage details to Responses API usage

Trigger release for all packages after provenance setup

provider/openai: Add gpt-image-2 model support

Add AI Gateway hint to provider READMEs

Add gpt-5.4-mini, gpt-5.4-mini-2026-03-17, gpt-5.4-nano, and gpt-5.4-nano-2026-03-17 models.

provider/openai: Drop reasoning parts without encrypted content when store: false

provider/openai: Add gpt-5.3-chat-latest

provider/openai: Add GPT-5.4 model support

Support phase parameter on Responses API message items. The phase field ('commentary' or 'final_answer') is returned by models like gpt-5.3-codex on assistant message output items and must be preserved when sending follow-up requests. The phase value is available in providerMetadata.openai.phase on text parts and is automatically included on assistant messages sent back to the API.

openai: Allow null/undefined type in streaming tool call deltas

Azure AI Foundry and Mistral deployed on Azure omit the type field in
streaming tool_calls deltas. The chat stream parser now accepts a missing
type field (treating it as "function") instead of throwing
InvalidResponseDataError: Expected 'function' type.

Fixes #12770

provider/openai: Add gpt-5.3-codex

openai: Change web search tool action to be optional

openai: Add changeset and tests for per-image usage metadata

Differentiate text vs image input tokens

Trigger new release for @ai-v5 dist-tag

Feat (provider/openai): add gpt-image-1.5 model support

Add GPT-5.2 support for non-reasoning parameters (temperature, topP, logProbs) when reasoningEffort is none.

fix(openai); fix url_citation schema in chat api

openai: Change find action type to find_in_page action type

openai: Add gpt-5.2 models

provider/openai: Add GPT 5.1 Codex Max to OpenAI Responses model IDs list

provider/openai: Add support for OpenAI xhigh reasoning effort

openai: Additional settings for file search tool