package llm

import "context"

// AskPetalMessages assembles the message array for one Ask Petal turn: the
// suggestion-context system prompt followed by the (length-capped) client-side
// conversation history. The backend is stateless, so the full history rides on
// every request (spec: no server-side sessions).
func AskPetalMessages(systemPrompt string, history []Message) []Message {
	msgs := make([]Message, 0, len(history)+1)
	msgs = append(msgs, Message{Role: "system", Content: systemPrompt})
	msgs = append(msgs, TrimHistory(history)...)
	return msgs
}

// StreamAskPetal opens an SSE-friendly token stream for an Ask Petal reply using
// the conversational sampling parameters from the spec. The caller forwards the
// returned chunks to the browser; the channel closes when generation ends.
func StreamAskPetal(ctx context.Context, client LLMClient, systemPrompt string, history []Message) (<-chan string, error) {
	return client.Stream(ctx, CompletionRequest{
		Messages:          AskPetalMessages(systemPrompt, history),
		MaxTokens:         512,
		Temperature:       0.7,
		RepetitionPenalty: 1.15,
		TopP:              0.92,
		Stop:              []string{"\n\n\n"},
		Stream:            true,
	})
}