vinzenz/hyperhive
0
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

no nap tool — recv with long wait_seconds replaces it; max raised to 180s

Browse source 
recv-with-timeout is strictly better than a fixed sleep because it
wakes instantly on incoming messages. drop the half-written nap MCP
tool, raise the recv wait_seconds cap from 60s to 180s on both
agent and manager sockets.

prompts updated: agent.md + manager.md now spell out the pattern —
when there's nothing else useful to do, call recv with
wait_seconds=180 to park the turn; do NOT use Bash sleep for the
same purpose. todo drops the nap entry and the napping-state-badge
follow-up; both replaced by 'just use a long recv'.
This commit is contained in:
müde 2026-05-15 20:53:15 +02:00
parent f65ee88269
commit 7d93dd9db4
6 changed files with 16 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

8
hive-c0re/src/agent_server.rs
View file

@ -79,10 +79,12 @@ async fn serve(stream: UnixStream, agent: String, broker: Arc<Broker>) -> Result
/// Default and max long-poll window for `Recv`. Caller can request a
/// shorter (or longer up to `RECV_LONG_POLL_MAX`) wait via the
/// `wait_seconds` field; values above the cap are clamped. Set well
/// below typical TCP / proxy idle limits.
/// `wait_seconds` field; values above the cap are clamped. 180s
/// max keeps us under typical TCP/proxy idle limits while letting
/// agents park their turn until a message lands instead of busy-
/// looping with short waits.
const RECV_LONG_POLL_DEFAULT: std::time::Duration = std::time::Duration::from_secs(30);
const RECV_LONG_POLL_MAX: std::time::Duration = std::time::Duration::from_secs(60);
const RECV_LONG_POLL_MAX: std::time::Duration = std::time::Duration::from_secs(180);
fn recv_timeout(wait_seconds: Option<u64>) -> std::time::Duration {
match wait_seconds {