llm

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

type Config struct {
	// Provider selects a preset endpoint. Ignored when BaseURL is set.
	Provider string
	// APIKey overrides LLM_API_KEY. Empty means read the environment. Hosted
	// presets require a key; local presets and a custom BaseURL do not.
	APIKey string
	// BaseURL is any OpenAI-compatible endpoint, including a local one.
	BaseURL string
	// Model is the model identifier passed to the provider.
	Model string
	// Timeout bounds a single completion call. Zero uses a default.
	Timeout time.Duration
	// Cache enables in-memory response caching keyed on the request.
	Cache bool
	// MaxCalls caps completions for the lifetime of the client. Zero is
	// unlimited. It exists so a misbehaving caller cannot run up an unbounded
	// bill against a paid provider.
	MaxCalls int
	// MaxConcurrency caps in-flight completions. Zero or negative means one.
	MaxConcurrency int
}

type Format struct {
	// JSON asks the provider to return a single JSON value. Callers that need a
	// specific shape state it in the prompt and validate the result; this only
	// requests JSON rather than prose.
	JSON bool
}

type Request struct {
	// System is an optional system instruction.
	System string
	// Prompt is the user input.
	Prompt string
	// Format optionally constrains the output.
	Format Format
}