odysseus-dev/odysseus · error · HTTPException

Daily message limit reached ({cap}). Try again in 24 hours.

Error message

Daily message limit reached ({cap}). Try again in 24 hours.

What it means

A usage-quota gate that counts the user's own user-role chat messages across all their sessions in the trailing 24 UTC hours and rejects with HTTP 429 when the count reaches the max_messages_per_day cap. It fires before any LLM work so no tokens are spent over quota.

Source

Thrown at routes/chat_helpers.py:239

    if cap <= 0:
        return

    from datetime import datetime as _dt, timedelta as _td
    from core.database import Session as _DbSess, ChatMessage as _Cm
    db = SessionLocal()
    try:
        count = (
            db.query(_Cm)
            .join(_DbSess, _Cm.session_id == _DbSess.id)
            .filter(_DbSess.owner == user,
                    _Cm.role == "user",
                    _Cm.timestamp >= _dt.utcnow() - _td(days=1))
            .count()
        )
    finally:
        db.close()
    if count >= cap:
        raise HTTPException(429, f"Daily message limit reached ({cap}). Try again in 24 hours.")


def needs_auto_name(name: str) -> bool:
    """Check if a session still has its default/placeholder name."""
    if not name:
        return True
    if name.startswith("Chat:") or name == "Chat":
        return True
    # Default frontend name: "modelname HH:MM:SS AM/PM"
    if re.match(r"^.+ \d{1,2}:\d{2}:\d{2}(\s*(AM|PM))?$", name, re.IGNORECASE):
        return True
    return False


async def auto_name_session(session_manager, sess):
    """Generate a short title for a session from its first user message."""
    try:
        from src.llm_core import llm_call_async

View on GitHub (pinned to f9235ebbf1)

Solutions

1. Wait until messages age out of the 24-hour UTC window (quota is rolling, not calendar-day)
2. Ask an admin to raise or remove max_messages_per_day for the user
3. Audit for scripted or duplicated sends inflating the count

// Before sending, check remaining quota if the API exposes it; otherwise track sends client-side
if (messagesSentToday >= knownCap) { showQuotaExceededUI(retryAt: nextUtcRollout); return; }

try { await sendChat(...); } catch (e) {
  if (e.status === 429 && /Daily message limit/.test(e.message)) { disableComposeUntilWindowRolls(); }
}

When it happens

Trigger: User at or over their daily cap sends any chat message. Each user-role row in ChatMessage joined to a session owned by the user within the last day counts toward cap.

Common situations: Free-tier user with a low cap hitting it mid-conversation; automated scripts posting messages that burn the quota; cap set very low (e.g. 10) by an admin for testing and never raised.

Related errors

• d.detail || 'Failed'
• Your account is not allowed to use model '{sess.model}'.
• Session '{session}' not found
• Selected model endpoint was removed. Pick another model in S
• No model selected for this chat. Open the model picker and c

AI-assisted analysis of odysseus-dev/odysseus@f9235ebbf1 (2026-08-14). Data as JSON: /api/errors/71cabeb570d7f153. Report an issue: GitHub.