zesdex/src/app/runtime/shortsend.rs

//! Short-send / message shaping: compacts long conversation histories so
//! they fit within the provider's context window before being sent to the
//! LLM API.
use crate::dto::chat::message::ChatMessage;

const MAX_WIRE_TOKENS: usize = 2_000_000;
const MIN_MESSAGES_BEFORE_SHAPE: usize = 20;
const ENGAGE_HYSTERESIS: usize = 5;

/// Decide whether the message list should be shaped (compacted) before
/// sending to the LLM.
///
/// Flow: skip shaping if fewer than `MIN_MESSAGES_BEFORE_SHAPE` messages
/// → once past that threshold, use hysteresis (require 5 more messages
/// before re-engaging if shaping is currently active) to avoid oscillation.
///
/// Return: `true` if shaping should be applied.
pub fn should_shape(total_messages: usize, prev_shaped: bool) -> bool {
    if total_messages < MIN_MESSAGES_BEFORE_SHAPE {
        return false;
    }
    let threshold = if prev_shaped {
        MIN_MESSAGES_BEFORE_SHAPE + ENGAGE_HYSTERESIS
    } else {
        MIN_MESSAGES_BEFORE_SHAPE
    };
    total_messages >= threshold
}

/// Compact a long message list by dropping middle messages and inserting
/// a summary placeholder.
///
/// Flow: if the estimated token count is within budget, return messages
/// unchanged → otherwise keep the system message and the most recent
/// messages (up to `MAX_WIRE_TOKENS / 200` of them) with a `[prior
/// conversation compacted]` system message in between.
///
/// Why: keeps context-size overhead roughly constant regardless of
/// session length.
///
/// Return: a new Vec<ChatMessage> that preserves the first message and
/// the tail.
pub fn shape_messages(messages: &[ChatMessage], token_count: usize) -> Vec<ChatMessage> {
    if token_count <= MAX_WIRE_TOKENS || messages.len() < 10 {
        return messages.to_vec();
    }
    let keep_recent = messages
        .iter()
        .rev()
        .take(MAX_WIRE_TOKENS / 200)
        .cloned()
        .collect::<Vec<_>>();
    let mut result = Vec::new();
    if let Some(first) = messages.first() {
        result.push(first.clone());
    }
    result.push(ChatMessage::system(
        "[prior conversation compacted]".to_string(),
    ));
    result.extend(keep_recent.into_iter().rev());
    result
}