model

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

type AzureConfig struct {
	ProviderConfig
	Deployment string `json:"deployment"`
	APIVersion string `json:"api_version"`
}

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

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

type ChatRequest struct {
	Model       string           `json:"model"`
	Messages    []Message        `json:"messages"`
	MaxTokens   int              `json:"max_tokens,omitempty"`
	Temperature float64          `json:"temperature,omitempty"`
	TopP        float64          `json:"top_p,omitempty"`
	Stream      bool             `json:"stream,omitempty"`
	Tools       []ToolDefinition `json:"tools,omitempty"`
	Stop        []string         `json:"stop,omitempty"`
	// ResponseFormat controls output format. Values:
	//   "json_object"  — model returns valid JSON (no schema enforcement)
	//   "json_schema"  — model returns JSON conforming to Metadata["json_schema"]
	ResponseFormat string         `json:"response_format,omitempty"`
	Metadata       map[string]any `json:"metadata,omitempty"`
}

type ChatResponse struct {
	ID         string     `json:"id"`
	Content    string     `json:"content"`
	Role       string     `json:"role"`
	Usage      Usage      `json:"usage"`
	ToolCalls  []ToolCall `json:"tool_calls,omitempty"`
	StopReason StopReason `json:"stop_reason,omitempty"`
	// Delta is true when this is a partial streaming response.
	Delta bool `json:"delta,omitempty"`
}

type EmbeddingRequest struct {
	Model string   `json:"model"`
	Input []string `json:"input"`
}

type EmbeddingResponse struct {
	Embeddings [][]float32 `json:"embeddings"`
	Usage      Usage       `json:"usage"`
}

type EmbeddingsProvider interface {
	Embed(ctx context.Context, req *EmbeddingRequest) (*EmbeddingResponse, error)
}

type EstimatingCounter struct {
	CharsPerToken float64
}

type FallbackProvider struct {

	// OnFallback is called when a provider fails and the next one is tried.
	// It receives the failed provider index, its name, and the error.
	OnFallback func(index int, name string, err error)
	// contains filtered or unexported fields
}

type FunctionDef struct {
	Name        string         `json:"name"`
	Description string         `json:"description"`
	Parameters  map[string]any `json:"parameters"` // JSON Schema
}

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

type Message struct {
	Role       string     `json:"role"` // system, user, assistant, tool
	Content    string     `json:"content"`
	Name       string     `json:"name,omitempty"`
	ToolCallID string     `json:"tool_call_id,omitempty"`
	ToolCalls  []ToolCall `json:"tool_calls,omitempty"`
}

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

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

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

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

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

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

type Provider interface {
	// Chat sends a request and returns a complete response.
	Chat(ctx context.Context, req *ChatRequest) (*ChatResponse, error)
	// StreamChat returns a channel of partial responses for streaming.
	// The channel is closed when the response is complete.
	StreamChat(ctx context.Context, req *ChatRequest) (<-chan *ChatResponse, error)
	// Name returns a human-readable name for this provider.
	Name() string
	// Model returns the default model ID for this provider.
	Model() string
}

type ProviderConfig struct {
	APIKey        string `json:"api_key"`
	BaseURL       string `json:"base_url,omitempty"`
	Model         string `json:"model"`
	MaxRetries    int    `json:"max_retries,omitempty"`
	TimeoutSec    int    `json:"timeout_sec,omitempty"`
	OrgID         string `json:"org_id,omitempty"`
	ContextWindow int    `json:"context_window,omitempty"` // override default context window size for the model
}

type StopReason string

type SummarizationConfig struct {
	// Threshold is the fraction of the context window that triggers summarization (default 0.8).
	Threshold float64
	// PreserveRecentTurns is the number of recent user/assistant message pairs to keep
	// unsummarized so the model retains immediate conversational context (default 5).
	PreserveRecentTurns int
	// MaxSummaryTokens caps the length of the generated summary (default 1024).
	MaxSummaryTokens int
	// Prompt overrides the default summarization system prompt.
	Prompt string
}

type SummarizeResult struct {
	Summary           string    // the new rolling summary
	PreservedMessages []Message // recent messages kept intact
}

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

type TokenCounter interface {
	CountTokens(messages []Message) int
	CountString(s string) int
}

type ToolCall struct {
	ID        string `json:"id"`
	Name      string `json:"name"`
	Arguments string `json:"arguments"` // JSON string
}

type ToolDefinition struct {
	Type     string      `json:"type"` // "function"
	Function FunctionDef `json:"function"`
}

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