provider

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

type Bedrock struct{}

type ChatStream interface {
	Recv() ([]byte, error)
	Usage() Usage
	Model() string
	Close() error
}

type Message struct {
	Role    Role   `json:"role"`
	Content string `json:"content"`
}

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

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

type Provider interface {
	// Name is the stable provider identifier used in config, routing, and the
	// OTel gen_ai.system attribute (e.g. "anthropic").
	Name() string
	// Chat performs one chat completion. It must honor ctx for cancellation and
	// deadlines — this is how the governor's kill switch and time budget reach an
	// in-flight call. It must always populate Usage on success.
	Chat(ctx context.Context, req Request) (*Response, error)
}

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

type Request struct {
	// Model is the provider-specific model identifier (e.g. "claude-sonnet-4-5").
	Model string `json:"model"`
	// System is an optional system prompt, kept separate from Messages because
	// some providers (Anthropic) take it as a distinct field.
	System string `json:"system,omitempty"`
	// Messages is the ordered conversation, excluding the system prompt.
	Messages []Message `json:"messages"`
	// MaxTokens caps the completion length. Required by some providers
	// (Anthropic); a provider may supply a sane default when zero.
	MaxTokens int `json:"max_tokens,omitempty"`
	// Temperature is optional; nil means "use the provider default".
	Temperature *float64 `json:"temperature,omitempty"`
}

type Response struct {
	// ID is the provider's response identifier, for the OTel span and audit log.
	ID string `json:"id"`
	// Model is the model that actually served the request.
	Model string `json:"model"`
	// Content is the assistant's text output (concatenated across content blocks).
	Content string `json:"content"`
	// FinishReason is the provider's stop reason, normalized loosely
	// ("stop", "length", "tool_use", ...).
	FinishReason string `json:"finish_reason"`
	// Usage is the token accounting for this call.
	Usage Usage `json:"usage"`
}

type Role string

type Streamer interface {
	// ChatStream starts a streaming completion. The returned ChatStream yields the
	// provider's raw SSE chunks verbatim (so the client receives authentic,
	// untranslated SSE) while it accumulates token usage. Honor ctx so the
	// governor's kill switch / time budget interrupt an in-flight stream.
	ChatStream(ctx context.Context, req Request) (ChatStream, error)
}

type Usage struct {
	PromptTokens     int64 `json:"prompt_tokens"`
	CompletionTokens int64 `json:"completion_tokens"`
}