@ai-sdk/openai

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.

Preserve stored tool search output item IDs from provider metadata.

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

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

security: Prevent streaming tool calls from finalizing on parsable partial JSON

Streaming tool call arguments were finalized using isParsableJson() as a heuristic for completion. If partial accumulated JSON happened to be valid JSON before all chunks arrived, the tool call would be executed with incomplete arguments. Tool call finalization now only occurs in flush() after the stream is fully consumed.

More precise default message for tool execution denial

openai: Throw retryable errors for OpenAI stream failures before output starts

Return a helpful error when the Responses stream parser receives Chat Completions chunks.

openai: Add support for web_search_call.results include option

Publish all packages under the @ai-v6 dist tag.

openai: Add orchestration token usage details to Responses API usage

provider/openai: Send client-executed tool calls as full function_call items in the Responses API so they pair with their function_call_output by call_id

openai: Add namespaces for tool definitions

openai: round-trip namespace on function_call input items

When tool_search dispatches a deferred tool, the resulting function_call carries a namespace field identifying which deferred-tool group the model picked. #14789 preserved this on the read side (providerMetadata.openai.namespace), but the write side still serialized function_call input items without namespace. Multi-step / multi-turn conversations then failed with Missing namespace for function_call '<name>'. ... Round-trip the model's function_call item with its namespace field included.

convert-to-openai-responses-input.ts now reads namespace from providerOptions.openai.namespace (or providerMetadata.openai.namespace) on tool-call parts and includes it on the serialized function_call item, mirroring how itemId is round-tripped.

feat(provider/azure):web search tool in the Azure OpenAI Responses API.

openai: Forward web_search_call.action.queries from Responses API

openai: Skip passing reasoning items when using previous response id

openai: Add opt-in pass-through for unsupported file media types

Add allowedTools provider option for OpenAI Responses

provider/openai: Forward imageDetail providerOptions on tool-result image content

openai: Add GPT-5.5 chat model IDs

openai, openai-compatible: Only send null content for assistant messages with tool calls

openai: Preserve namespace on function_call output items

Trigger release for all packages after provenance setup

Patch - send content: null instead of empty string for tool-only assistant messages

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

openai: Default undefined tool-call input to empty object before serializing tool arguments

Add AI Gateway hint to provider READMEs

openai: Support file-url parts in tool output content

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.

openai: Preserve raw finish reason for failed responses stream events

Handle response.failed chunks in Responses API streaming so finishReason.raw is preserved from incomplete_details.reason (e.g. max_output_tokens), and map failed-without-reason cases to unified error instead of other.

Publish v6 to latest npm dist tag

openai: Add new tool search tool

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

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

provider/openai: Add GPT-5.4 model support