vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2

subagent: make a missed continue the tool call's own error

Browse source 
`continue` returned "started" the instant `Claude::spawn` handed back a
pid, and a resume that matched nothing only surfaced later, as an
end-of-turn todo. By then the caller had moved on believing it had a
running subagent.

A pid is proof enough for `start`, which creates its session: the spawn
succeeding is the whole story. It is not proof for a resume — claude
exits non-zero a fraction of a second *after* the process exists. So
`continue` now waits for the first real answer and reports a miss as its
own `Err`, carrying claude's message and the directory searched.

The wait ends on whichever comes first, so a successful `continue` pays
no fixed delay: the turn's first non-terminal stream event settles it at
about the same moment a miss's exit would have. Measured on this box:
14 runs of the driver's own invocation against a missing session took
550-1087 ms spawn to exit, and a healthy turn's first event lands at
roughly 500 ms. The five-second cap is ~4.6x the slowest miss and is only
ever reached by a child that neither speaks nor exits.

The underway signal reads the event's kind, not its content: a missed
resume is not silent — it emits a terminal `result` event and stderr
before exiting — so "any sink callback" would have reported every miss as
a successful start. Liveness still counts all three callbacks.

The end-of-turn todo is unchanged for every failure later in the turn;
the only one it no longer repeats is the miss the caller was just handed.

Refs #4405
This commit is contained in:
atlas 2026-09-14 20:34:54 +02:00 • committed by mara
commit 6e2de33f26
5 changed files with 385 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

20
hive-subagent-mcp/src/mcp.rs
View file

@ -149,14 +149,16 @@ impl SubagentMcp {
description = "Give an existing named subagent session a new turn — whether that's \
because its previous turn finished and you have a follow-up instruction, or you're \
reattaching after this daemon restarted (the session itself survives independently \
of the daemon that spawned it). Returns as soon as confirmed running, same as \
`start`; a name already running is refused. A name with no session to resume is not \
refused up front — claude's own `--resume` decides that, and a miss arrives as a \
failed turn naming the directory that was searched, so check `dir` before concluding \
the session is gone. Resuming a session whose last turn was killed is allowed — the \
reply says so, since that turn's work stopped wherever it had got to."
of the daemon that spawned it). Returns once the turn is underway rather than the \
instant the process exists — a second or so, not the length of the turn — so a \
reply saying the turn started means it started; a name already running is refused. \
A name with no session to resume is not refused up front, because claude's own \
`--resume` decides that: a miss comes back as this call's own error, naming the \
directory that was searched, so check `dir` before concluding the session is gone. \
Resuming a session whose last turn was killed is allowed — the reply says so, since \
that turn's work stopped wherever it had got to."
)]
fn r#continue(&self, Parameters(args): Parameters<ContinueArgs>) -> String {
async fn r#continue(&self, Parameters(args): Parameters<ContinueArgs>) -> String {
match session::continue_(
&self.state,
&args.name,
@ -164,7 +166,9 @@ impl SubagentMcp {
args.model,
args.effort,
args.dir.as_deref(),
) {
)
.await
{
Ok(msg) => msg,
Err(e) => format!("continue error: {e:#}"),
}