llm

type Message struct {
	Role             Role
	Text             string
	ToolCalls        []ToolCall
	ToolResults      []ToolResult
	Reasoning        string         // Internal reasoning/thought process from the model
	ProviderMetadata map[string]any // Opaque provider-specific data (e.g. thought signatures)
	// CacheBreakpoint, when true on a RoleSystem message, marks the end of the
	// stable cacheable prefix. Providers that support prompt caching (e.g.
	// Anthropic) use this to inject a cache-control marker; all other providers
	// ignore it.
	CacheBreakpoint bool
}

type Model interface {
	GenerateContent(ctx context.Context, messages []Message, tools []ToolDef, maxTokens int) (*Response, error)
	// GenerateStructuredContent requests the model to produce output adhering to
	// the provided JSON Schema. The schema should be a map[string]any following
	// the JSON Schema specification.
	GenerateStructuredContent(ctx context.Context, messages []Message, schema map[string]any, config StructuredConfig) (*Response, error)
}

type Response struct {
	Text             string         // set when the model produced a final answer
	ToolCalls        []ToolCall     // set when the model wants to invoke tools
	Reasoning        string         // set when the model provides internal reasoning
	ProviderMetadata map[string]any // opaque data to be echoed in subsequent turns
	Usage            Usage          // token usage for this interaction
}

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

type Role string

type StructuredConfig struct {
	// ModelOverride allows using a different model for the structured pass.
	ModelOverride string
	// MaxTokens limits the length of the LLM response.
	MaxTokens int
}

type ToolCall struct {
	ID        string
	Name      string
	Arguments string // raw JSON
}

type ToolDef struct {
	Name        string
	Description string
	Parameters  map[string]any // full JSON Schema object
}

type ToolResult struct {
	ToolCallID string
	Name       string
	Content    string
}

type Usage struct {
	PromptTokens   int // tokens in the input prompt
	OutputTokens   int // tokens in the generated response (excluding thinking)
	ThinkingTokens int // tokens used for model internal reasoning/thinking
	CachedTokens   int // tokens served from a cache
}