hyperhive/hive-c0re/src/limits.rs

//! Wire-protocol size limits shared across the agent + manager
//! sockets. Caps on inline message bodies stop a single chatty agent
//! (or a misbehaving extra-MCP server) from flooding the broker
//! sqlite with megabyte-sized rows that then bloat every recipient's
//! wake-prompt context. Anything genuinely larger should be written
//! to a state file and the path sent as the body.
//!
//! Reminders get a separate auto-file escape hatch (see
//! `agent_server::handle_remind`) so callers don't have to think
//! about it — oversized reminder bodies get persisted to disk
//! transparently and the inbox sees a pointer.

/// Per-message body cap. Applies to `send`, `ask` question text,
/// `answer` body, and the stored inline form of a reminder. 4 KiB
/// catches the bulk of conversational overflow (status reports,
/// bullet-list summaries, short proposals) while staying small
/// enough that a backed-up inbox of ~10 unread messages only adds
/// ~40 KiB to the recipient's wake-prompt context. Genuinely
/// long-form artifacts (audit reports, full diffs, transcripts)
/// still belong in a state file — the error message on overflow
/// points callers at that escape hatch.
pub const MESSAGE_MAX_BYTES: usize = 4096;

/// Validate that `body` fits under [`MESSAGE_MAX_BYTES`]. Returns a
/// caller-ready error string (caller wraps in
/// `AgentResponse::Err`/`ManagerResponse::Err`) on failure.
///
/// `label` shows up in the error message verbatim — pass a short
/// noun like `"send"`, `"question"`, `"broadcast"` so the model can
/// tell which call got rejected.
pub fn check_size(label: &str, body: &str) -> Result<(), String> {
    if body.len() > MESSAGE_MAX_BYTES {
        Err(format!(
            "{label} body too long ({} bytes, max {MESSAGE_MAX_BYTES}); write the \
             payload to a file under your `/agents/<you>/state/` dir and send the \
             path as the body instead",
            body.len()
        ))
    } else {
        Ok(())
    }
}

/// Per-status soft cap. `set_status` renders as a short chip on the
/// dashboard agent card — the front-end truncates long strings to
/// keep the row layout intact, so a multi-paragraph "session report"
/// is wasted bytes that just bloat the rescan emit + container view
/// payload. Cap at 200 chars to fit the chip plus a little
/// descriptive padding without forcing the operator to read a
/// scrolling chunk.
pub const STATUS_MAX_CHARS: usize = 200;

/// Validate a `set_status` payload. Single-line + bounded so
/// callers can't dump multi-paragraph session reports into the
/// dashboard chip. Whitespace trim is done by the caller before the
/// store-to-disk step — we run validation on the trimmed form so
/// surrounding whitespace doesn't push a borderline-legal status
/// past the cap.
///
/// Empty / all-whitespace input is accepted: the call site treats
/// that as "clear the status" and removes the on-disk sentinel. Tests
/// + caller cover both directions.
///
/// Returns a caller-ready error string suitable for surfacing in the
/// `*Response::Err` shape.
pub fn check_status_text(text: &str) -> Result<(), String> {
    let trimmed = text.trim();
    if trimmed.is_empty() {
        // Empty = clear-status sentinel; nothing to validate.
        return Ok(());
    }
    // Newline / carriage-return: status is a single-line chip on the
    // dashboard. Multi-line session reports should go to a state file.
    if trimmed.contains('\n') || trimmed.contains('\r') {
        return Err(
            "set_status text must be a single line — write multi-line context to \
             a file under your `/agents/<you>/state/` dir and reference that path \
             from the chip instead"
                .to_owned(),
        );
    }
    let len = trimmed.chars().count();
    if len > STATUS_MAX_CHARS {
        return Err(format!(
            "set_status text too long ({len} chars, max {STATUS_MAX_CHARS}); the \
             dashboard chip truncates anything longer, so trim to a short summary \
             and write the detail to `/agents/<you>/state/<file>` instead"
        ));
    }
    Ok(())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn accepts_short_body() {
        assert!(check_size("send", "hello").is_ok());
        assert!(check_size("send", &"x".repeat(MESSAGE_MAX_BYTES)).is_ok());
    }

    #[test]
    fn rejects_oversize_body() {
        let err = check_size("send", &"x".repeat(MESSAGE_MAX_BYTES + 1)).unwrap_err();
        assert!(err.contains("send body too long"));
        assert!(err.contains(&format!("max {MESSAGE_MAX_BYTES}")));
    }

    #[test]
    fn label_threads_through() {
        let err = check_size("question", &"x".repeat(MESSAGE_MAX_BYTES + 1)).unwrap_err();
        assert!(err.starts_with("question body too long"));
    }

    #[test]
    fn check_status_accepts_short_single_line() {
        assert!(check_status_text("idle").is_ok());
        assert!(check_status_text("processing matrix messages").is_ok());
        // Boundary: exactly STATUS_MAX_CHARS chars trimmed is still
        // accepted; one more rejects.
        let max = "a".repeat(STATUS_MAX_CHARS);
        assert!(check_status_text(&max).is_ok());
    }

    #[test]
    fn check_status_accepts_empty_and_whitespace() {
        // Empty + whitespace-only are the "clear status" sentinel and
        // bypass the rest of the checks.
        assert!(check_status_text("").is_ok());
        assert!(check_status_text("   ").is_ok());
        assert!(check_status_text("\n\t  ").is_ok());
    }

    #[test]
    fn check_status_rejects_multi_line() {
        let err = check_status_text("line one\nline two").unwrap_err();
        assert!(err.contains("single line"), "err = {err}");
        // Carriage return alone also rejects (windows linebreak / CR-only).
        assert!(check_status_text("a\rb").is_err());
    }

    #[test]
    fn check_status_rejects_oversize() {
        let too_long = "a".repeat(STATUS_MAX_CHARS + 1);
        let err = check_status_text(&too_long).unwrap_err();
        assert!(err.contains("too long"), "err = {err}");
        assert!(err.contains(&format!("max {STATUS_MAX_CHARS}")));
    }

    #[test]
    fn check_status_counts_chars_not_bytes() {
        // Multi-byte chars (emoji, accented letters) count once each
        // per char — chars().count() not byte len. STATUS_MAX_CHARS
        // worth of 4-byte chars is still legal.
        let emoji = "💜".repeat(STATUS_MAX_CHARS);
        assert!(
            check_status_text(&emoji).is_ok(),
            "{STATUS_MAX_CHARS} emoji should fit"
        );
        let too_many = "💜".repeat(STATUS_MAX_CHARS + 1);
        assert!(check_status_text(&too_many).is_err());
    }

    #[test]
    fn check_status_validates_post_trim() {
        // Leading/trailing whitespace is trimmed before the length
        // check — a borderline-legal payload with spaces around it
        // still passes.
        let padded = format!("  {}  ", "a".repeat(STATUS_MAX_CHARS));
        assert!(check_status_text(&padded).is_ok());
    }
}