hyperhive/hive-host-sock
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 31008c83df feat: pause an agent's turn loop without stopping its container
A paused agent keeps its container, its claude session and its
dashboard/todo servers up, but stops driving turns. Messages queue
unacked and are drained on resume.

The whole protocol is a single marker file, `<harness>/paused`. That
directory is already a bind-mount shared between host and container, so
both sides just stat the same path: the harness reads it to decide
whether to drive a turn, hive-c0re reads it to render the badge and
writes/removes it for `hivectl pause|resume`. No new wire protocol, no
container round-trip, and it is sticky across restarts by construction.

Not calling `recv_next` while paused *is* the queueing semantic, so
there is no fencing to get wrong: reminders buffer in their unbounded
channel, the todo `Notify` permit coalesces, and a `request_next_turn`
that raced the pause survives because the gate sits above
`self_continue.take()`.

Graceful stop is handled host-side rather than in the harness: a paused
agent provably has no turn in flight, so `run_signal` skips the fence
entirely instead of eating the full `GRACEFUL_STOP_TIMEOUT` waiting for
a checkpoint turn that will never run.

`paused` is reported on `ContainerView` / `AgentStatusRow` for the
dashboard, orthogonal to `running` and reported for stopped containers
too.

Closes: hyperhive/hyperhive issue 2271
2026-07-26 03:11:33 +02:00
..
src feat: pause an agent's turn loop without stopping its container 2026-07-26 03:11:33 +02:00
Cargo.toml docs(#2627): add READMEs for hive-jobq + the socket wire crates 2026-07-23 12:34:22 +02:00
README.md docs(#2627): add READMEs for hive-jobq + the socket wire crates 2026-07-23 12:34:22 +02:00

hive-host-sock

Wire types for the host admin socket (/run/hyperhive/host.sock) — the host-control protocol spoken between the hivectl operator CLI and the hive-c0re daemon.

Why it's its own crate

Re-homed out of hive-sh4re so a standalone hivectl depends on just this protocol crate instead of the whole daemon-shared crate. hivectl drives the full hive (spawn / kill / destroy / rebuild / deploy) over this socket without linking hive-c0re; keeping the request/response shapes here is what makes that thin dependency possible.

Shape

Serde-derived request/response enums for the host admin protocol. The larger shared payload types some variants reference (Approval, AgentStatusRow, jobs::DagView) stay in hive-sh4re — this crate is only the protocol envelope, no server or client implementation.

See docs/boundary.md (host admin socket access) for the trust model around who may connect to the socket, and hive-priv-sock for the sibling split on the privileged-helper socket.