Type represents the type of the data.

Configuration for test execution

ChatToolType represents the type of tool.

============================================================ errTest — minimal error type for test use ===============================================

CohereThinkingType represents the type of reasoning

Duration is a time.Duration value that accepts both human-readable duration strings and plain integer nanosecond values on JSON unmarshal, providing b

============================================================================ Transcription Streaming Types ===========================================

ModelFamily is a typed enum identifying the underlying model family of an alias target. It enables provider routing decisions (request shape, response

OpenAIProvider implements the Provider interface for OpenAI's GPT API.

============================================================================= 7. TOOL CONFIGURATION STRUCTURES =======================================

==================== MODEL TYPES ====================

AnthropicProvider implements the Provider interface for Anthropic's Claude API.

==================== RESPONSE TYPES ====================

BedrockServiceTierType represents the processing tier for a Bedrock request. See https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_S

Bifrost gateway configuration

Main test runner for Bifrost integration tests

ChatAssistantMessage represents a message in a chat conversation.

ChatContentBlock represents a content block in a message.

ChatContentBlockType represents the type of content block in a message.

ChatStreamResponseChoiceDelta represents a delta in the stream response

ChatTool represents a tool definition. Three shapes coexist under this type: 1. OpenAI function tool: Type="function", Function non-nil. 2. Custom

ChatToolChoiceStruct represents a tool choice.

ChatToolChoiceType for all providers, make sure to check the provider's documentation to see which tool choices are supported.

ClientConfig represents the core configuration for Bifrost HTTP transport and the Bifrost Client. It includes settings for excess request handling, Pr

==================== MODEL TYPES ====================

CohereProvider implements the Provider interface for Cohere.

Config is the OTEL plugin configuration: a set of export profiles plus a single shared span filter. It accepts two JSON shapes (see UnmarshalJSON): -

Configuration loader for Bifrost integration tests

Entry represents a single model's pricing information. Field names and JSON tags match the datasheet schema exactly. AdditionalAttributes carries edit

Model configuration for a integration

MatchType controls how an override pattern is matched against model names.

Modality represents server content modalities.

ModelProvider represents the different AI model providers supported by Bifrost.

Generic OpenAPI bundler that hoists all registered components into #/components/{type}/{name} refs rather than fully inlining $refs. Alg

QueryScope mutates a query to enforce caller-driven row-level constraints. Set on ctx by an upstream wrapper; inner store query helpers apply it blind

============================================================================= 5. TOOL CHOICE CONFIGURATION ===========================================

Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v

ScopeKind identifies which governance scope an override applies to.

TableVirtualKeyProviderConfig represents a provider configuration for a virtual key

ToolFunctionParameters represents the parameters for a function definition. It supports JSON Schema fields used by various providers (OpenAI, Anthropi

resolver is the internal interface each auth-type-specific resolver implements. RequestHeaders is identical across all auth types (extras only) and li