llmproxy

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

type BillingResult struct {
	// Provider is the provider name.
	Provider string
	// Model is the model identifier.
	Model string
	// PromptTokens is the number of input tokens.
	PromptTokens int
	// CompletionTokens is the number of output tokens.
	CompletionTokens int
	// CachedTokens is the number of prompt tokens served from cache.
	CachedTokens int
	// TotalTokens is the sum of prompt and completion tokens.
	TotalTokens int
	// InputCost is the calculated input cost in USD (non-cached prompt tokens).
	InputCost float64
	// CachedInputCost is the cost for cached prompt tokens in USD.
	CachedInputCost float64
	// OutputCost is the calculated output cost in USD.
	OutputCost float64
	// TotalCost is the sum of all costs in USD.
	TotalCost float64
}

type BodyMetadata struct {
	// Model is the requested model identifier (e.g., "gpt-4", "claude-3-opus").
	Model string `json:"model"`
	// Messages contains the conversation history for chat completions.
	Messages []Message `json:"messages,omitempty"`
	// MaxTokens is the maximum number of tokens to generate.
	MaxTokens int `json:"max_tokens,omitempty"`
	// Stream indicates whether streaming is requested.
	Stream bool `json:"stream"`
	// Custom holds provider-specific fields that don't map to standard fields.
	Custom map[string]any `json:"-"`
}

type BodyParser interface {
	// Parse reads the request body and extracts metadata.
	// It returns the parsed metadata, the raw body bytes (for later use),
	// and any error encountered during parsing.
	//
	// The caller is responsible for closing the body ReadCloser.
	Parse(body io.ReadCloser) (BodyMetadata, []byte, error)
}

type CacheDetail struct {
	// TTL is the time-to-live for the cache entry (e.g., "5m", "1h").
	TTL string `json:"ttl,omitempty"`
	// CacheWriteTokens is the number of tokens written to cache at this TTL.
	CacheWriteTokens int `json:"cache_write_tokens,omitempty"`
}

type CacheUsage struct {
	// CachedTokens is the number of tokens served from cache (OpenAI).
	CachedTokens int `json:"cached_tokens,omitempty"`
	// CacheCreationInputTokens is the number of tokens written to cache (Anthropic).
	CacheCreationInputTokens int `json:"cache_creation_input_tokens,omitempty"`
	// CacheReadInputTokens is the number of tokens read from cache (Anthropic).
	CacheReadInputTokens int `json:"cache_read_input_tokens,omitempty"`
	// Ephemeral5mInputTokens is the number of 5-minute cache write tokens (Anthropic).
	Ephemeral5mInputTokens int `json:"ephemeral_5m_input_tokens,omitempty"`
	// Ephemeral1hInputTokens is the number of 1-hour cache write tokens (Anthropic).
	Ephemeral1hInputTokens int `json:"ephemeral_1h_input_tokens,omitempty"`
	// CacheWriteTokens is the number of tokens written to cache (Bedrock).
	CacheWriteTokens int `json:"cache_write_tokens,omitempty"`
	// CacheDetails contains TTL-based cache write breakdown (Bedrock).
	CacheDetails []CacheDetail `json:"cache_details,omitempty"`
}

type Choice struct {
	// Index is the position of this choice in the choices array.
	Index int `json:"index"`
	// Message contains the completed message (for non-streaming responses).
	Message *Message `json:"message,omitempty"`
	// Delta contains the partial message (for streaming responses).
	Delta *Message `json:"delta,omitempty"`
	// FinishReason indicates why the completion stopped (e.g., "stop", "length").
	FinishReason string `json:"finish_reason"`
}

type CostInfo struct {
	// Input is the cost per 1M input tokens in USD.
	Input float64
	// Output is the cost per 1M output tokens in USD.
	Output float64
	// CacheRead is the cost per 1M cached input tokens (optional).
	CacheRead float64
	// CacheWrite is the cost per 1M cache write tokens (optional, Anthropic).
	CacheWrite float64
}

type CostLookup func(provider string, model string) (CostInfo, bool)

type Interceptor interface {
	// Intercept processes a request through the interceptor chain.
	//
	// Parameters:
	//   - req: The HTTP request to send upstream
	//   - meta: Parsed metadata from the request body
	//   - rawBody: The original request body bytes
	//   - next: The next handler in the chain (call this to continue)
	//
	// Returns:
	//   - resp: The HTTP response (body will be re-attached from rawRespBody)
	//   - respMeta: Parsed response metadata
	//   - rawRespBody: The raw response body bytes
	//   - error: Any error that occurred
	Intercept(req *http.Request, meta BodyMetadata, rawBody []byte, next RoundTripFunc) (resp *http.Response, respMeta ResponseMetadata, rawRespBody []byte, err error)
}

type InterceptorChain []Interceptor

type Logger interface {
	// Debug level logging
	Debug(msg string, args ...interface{})
	// Info level logging
	Info(msg string, args ...interface{})
	// Warning level logging
	Warn(msg string, args ...interface{})
	// Error level logging
	Error(msg string, args ...interface{})
}

type LoggerFunc func(level string, msg string, args ...interface{})

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

type Message struct {
	// Role is the role of the message author (e.g., "user", "assistant", "system").
	Role string `json:"role"`
	// Content is the text content of the message.
	Content string `json:"content"`
}

type MetaContextKey struct{}

type MetaContextValue struct {
	Meta    BodyMetadata
	RawBody []byte
	OrgID   string
}

type Provider interface {
	// Name returns the provider's unique identifier (e.g., "openai", "anthropic").
	Name() string

	// BodyParser returns the parser for extracting request metadata.
	BodyParser() BodyParser

	// RequestEnricher returns the enricher for modifying outgoing requests.
	RequestEnricher() RequestEnricher

	// ResponseExtractor returns the extractor for parsing responses.
	ResponseExtractor() ResponseExtractor

	// URLResolver returns the resolver for determining upstream URLs.
	URLResolver() URLResolver
}

type ProviderOption func(*BaseProvider)

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

type ProxyOption func(*Proxy)

type Registry interface {
	// Register adds a provider to the registry.
	Register(p Provider)

	// Get retrieves a provider by name.
	// Returns the provider and true if found, nil and false otherwise.
	Get(name string) (Provider, bool)

	// Match selects a provider for the given request.
	// Implementations may parse the request body to determine routing.
	// Returns the matched provider, or an error if no match is found.
	Match(req *http.Request) (Provider, error)
}

type RequestEnricher interface {
	// Enrich modifies the request with provider-specific enhancements.
	// The meta parameter contains parsed body metadata for decision-making.
	// The rawBody contains the original request body bytes.
	//
	// Implementations should modify req in place (headers, URL, etc.)
	// and return nil on success, or an error to abort the request.
	Enrich(req *http.Request, meta BodyMetadata, rawBody []byte) error
}

type ResponseExtractor interface {
	// Extract parses the HTTP response and returns unified metadata.
	//
	// The method reads and consumes the response body, parses it for metadata,
	// and returns both the metadata and the raw body bytes. The proxy will
	// re-attach the raw bytes to the response so the caller can read them.
	//
	// Parameters:
	//   - resp: The HTTP response from the upstream provider
	//
	// Returns:
	//   - metadata: Parsed response metadata (tokens, model, etc.)
	//   - rawBody: The original response body bytes (must be returned for forwarding)
	//   - error: Any parsing error
	Extract(resp *http.Response) (metadata ResponseMetadata, rawBody []byte, err error)
}

type ResponseMetadata struct {
	// ID is the unique identifier for the response (provider-specific).
	ID string `json:"id,omitempty"`
	// Object is the object type (e.g., "chat.completion").
	Object string `json:"object,omitempty"`
	// Model is the model used for the completion.
	Model string `json:"model,omitempty"`
	// Usage contains token consumption statistics.
	Usage Usage `json:"usage"`
	// Choices contains the completion choices.
	Choices []Choice `json:"choices,omitempty"`
	// Custom holds provider-specific response fields.
	Custom map[string]any `json:"-"`
}

type RoundTripFunc func(*http.Request) (*http.Response, ResponseMetadata, []byte, error)

type URLResolver interface {
	// Resolve returns the upstream URL for the given request metadata.
	// The returned URL should be the full endpoint for the completion request.
	//
	// Implementations can use metadata fields (like Model) to make routing decisions.
	Resolve(meta BodyMetadata) (*url.URL, error)
}

type Usage struct {
	// PromptTokens is the number of tokens in the prompt.
	PromptTokens int `json:"prompt_tokens"`
	// CompletionTokens is the number of tokens generated in the completion.
	CompletionTokens int `json:"completion_tokens"`
	// TotalTokens is the sum of prompt and completion tokens.
	TotalTokens int `json:"total_tokens"`
}