streaming

type AccumulatedData struct {
	RequestID             string
	Model                 string
	Status                string
	Stream                bool
	Latency               int64 // in milliseconds
	TimeToFirstToken      int64 // Time to first token in milliseconds (streaming only)
	StartTimestamp        time.Time
	EndTimestamp          time.Time
	OutputMessage         *schemas.ChatMessage
	OutputMessages        []schemas.ResponsesMessage // For responses API
	ToolCalls             []schemas.ChatAssistantMessageToolCall
	ErrorDetails          *schemas.BifrostError
	TokenUsage            *schemas.BifrostLLMUsage
	CacheDebug            *schemas.BifrostCacheDebug
	Cost                  *float64
	AudioOutput           *schemas.BifrostSpeechResponse
	TranscriptionOutput   *schemas.BifrostTranscriptionResponse
	ImageGenerationOutput *schemas.BifrostImageGenerationResponse
	FinishReason          *string
	RawResponse           *string
}

type Accumulator struct {
	// contains filtered or unexported fields
}

type AudioStreamChunk struct {
	Timestamp          time.Time                            // When chunk was received
	Delta              *schemas.BifrostSpeechStreamResponse // The actual delta content
	FinishReason       *string                              // If this is the final chunk
	TokenUsage         *schemas.SpeechUsage                 // Token usage if available
	SemanticCacheDebug *schemas.BifrostCacheDebug           // Semantic cache debug if available
	Cost               *float64                             // Cost in dollars from pricing plugin
	ErrorDetails       *schemas.BifrostError                // Error if any
	ChunkIndex         int                                  // Index of the chunk in the stream
	RawResponse        *string
}

type ChatStreamChunk struct {
	Timestamp          time.Time                              // When chunk was received
	Delta              *schemas.ChatStreamResponseChoiceDelta // The actual delta content
	FinishReason       *string                                // If this is the final chunk
	TokenUsage         *schemas.BifrostLLMUsage               // Token usage if available
	SemanticCacheDebug *schemas.BifrostCacheDebug             // Semantic cache debug if available
	Cost               *float64                               // Cost in dollars from pricing plugin
	ErrorDetails       *schemas.BifrostError                  // Error if any
	ChunkIndex         int                                    // Index of the chunk in the stream
	RawResponse        *string                                // Raw response if available
}

type ImageStreamChunk struct {
	Timestamp          time.Time                                     // When chunk was received
	Delta              *schemas.BifrostImageGenerationStreamResponse // The actual stream response
	FinishReason       *string                                       // If this is the final chunk
	ChunkIndex         int                                           // Index of the chunk in the stream
	ImageIndex         int                                           // Index of the image in the stream
	ErrorDetails       *schemas.BifrostError                         // Error if any
	Cost               *float64                                      // Cost in dollars from pricing plugin
	SemanticCacheDebug *schemas.BifrostCacheDebug                    // Semantic cache debug if available
	TokenUsage         *schemas.ImageUsage                           // Token usage if available
	RawResponse        *string                                       // Raw response if available
}

type ProcessedStreamResponse struct {
	RequestID  string
	StreamType StreamType
	Provider   schemas.ModelProvider
	Model      string
	Data       *AccumulatedData
	RawRequest *interface{}
}

type ResponsesStreamChunk struct {
	Timestamp          time.Time                               // When chunk was received
	StreamResponse     *schemas.BifrostResponsesStreamResponse // The actual stream response
	FinishReason       *string                                 // If this is the final chunk
	TokenUsage         *schemas.BifrostLLMUsage                // Token usage if available
	SemanticCacheDebug *schemas.BifrostCacheDebug              // Semantic cache debug if available
	Cost               *float64                                // Cost in dollars from pricing plugin
	ErrorDetails       *schemas.BifrostError                   // Error if any
	ChunkIndex         int                                     // Index of the chunk in the stream
	RawResponse        *string
}

type StreamAccumulator struct {
	RequestID                 string
	StartTimestamp            time.Time
	FirstChunkTimestamp       time.Time // Timestamp when the first chunk was received (for TTFT calculation)
	ChatStreamChunks          []*ChatStreamChunk
	ResponsesStreamChunks     []*ResponsesStreamChunk
	TranscriptionStreamChunks []*TranscriptionStreamChunk
	AudioStreamChunks         []*AudioStreamChunk
	ImageStreamChunks         []*ImageStreamChunk

	// De-dup maps to prevent chunk loss on out-of-order arrival
	ChatChunksSeen          map[int]struct{}
	ResponsesChunksSeen     map[int]struct{}
	TranscriptionChunksSeen map[int]struct{}
	AudioChunksSeen         map[int]struct{}
	ImageChunksSeen         map[string]struct{} // Composite key: "imageIndex:chunkIndex" to scope de-dup per image

	// Track highest ChunkIndex for metadata extraction (TokenUsage, Cost, FinishReason)
	MaxChatChunkIndex          int
	MaxResponsesChunkIndex     int
	MaxTranscriptionChunkIndex int
	MaxAudioChunkIndex         int

	IsComplete     bool
	FinalTimestamp time.Time

	Timestamp time.Time
	// contains filtered or unexported fields
}

type StreamType string

type TranscriptionStreamChunk struct {
	Timestamp          time.Time                                   // When chunk was received
	Delta              *schemas.BifrostTranscriptionStreamResponse // The actual delta content
	FinishReason       *string                                     // If this is the final chunk
	TokenUsage         *schemas.TranscriptionUsage                 // Token usage if available
	SemanticCacheDebug *schemas.BifrostCacheDebug                  // Semantic cache debug if available
	Cost               *float64                                    // Cost in dollars from pricing plugin
	ErrorDetails       *schemas.BifrostError                       // Error if any
	ChunkIndex         int                                         // Index of the chunk in the stream
	RawResponse        *string
}