vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

hive-runtime: cancel and idle watchdog for ACP turns

Browse source 
`Runtime` gets a fourth operation, `canceller()`: a handle that stops the
turn in flight from outside `run`. The ACP backend returns one; claude
returns `None`, because the harness stops a claude turn by signalling the
`claude` process, and that path is unchanged.

Both stops send the agent `session/cancel`:

- `Canceller::cancel()`, when asked from outside. The turn then ends
  normally, reported with stop reason `cancelled` whatever reason the agent
  gives. opencode 1.15.10, for one, answers a cancelled prompt with
  `end_turn` (`acp/agent.ts` `prompt()` always returns `end_turn`).
- The idle watchdog, once no `session/update` has arrived for
  `Config::idle_timeout`, the same field claude's watchdog reads. The turn
  fails with `AcpError::IdleTimeout`.

An agent that has not answered the prompt 10s after `session/cancel` is
killed (`IdleKilled` / `CancelIgnored`), and the next turn respawns it.

The watchdog is also what ends a turn stuck on a provider HTTP 429.
opencode 1.15.10 retries a retryable provider error with no attempt limit
(`session/retry.ts` `policy`, `session/processor.ts` `Effect.retry`) and
forwards neither `session.status` nor `session.error` over ACP (its
`handleEvent` only handles `permission.asked` and `message.part.*`). So the
ACP client sees nothing at all until the provider recovers. The
`IdleTimeout` message says a silently retried provider error looks like
this.

Refs #4391
This commit is contained in:
atlas 2026-09-29 23:22:50 +02:00
commit bcbeb8ac9c
6 changed files with 333 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

16
hive-runtime/README.md
View file

@ -1,7 +1,7 @@
# hive-runtime
The layer an agent's turns are driven through: one `Runtime` interface
(`run`, `compact`, `archive`) with a backend per runtime.
(`run`, `compact`, `archive`, `canceller`) with a backend per runtime.
- **claude** — `claude --print` through the `hive-claude` crate's
`InfiniteSession`. A pass-through: same spawn, same session handling, same
@ -30,8 +30,16 @@ The crate depends on no hyperhive binary crate, so `hive-agent` and
- `loadSession`, to pick its session back up after a harness restart.
Without it every restart starts a new session.
## ACP backend: stopping a turn
A turn is stopped with `session/cancel`: by the `Canceller` handle, or by the
idle watchdog once no `session/update` has arrived for
`Config::idle_timeout`. An agent that has not answered the prompt 10s later
is killed, and the next turn respawns it. A watchdog stop fails the turn
with `AcpError::IdleTimeout` (`IdleKilled` if the agent was killed). This is
the only way a provider error the agent retries without reporting it, such as
an HTTP 429, ends the turn.
## ACP backend: not yet
`compact` returns `Error::Unsupported`, there is no cancel, and no idle
watchdog (`Config::idle_timeout` is ignored). An agent that retries a failing
provider on its own keeps the turn open until it gives up.
`compact` returns `Error::Unsupported`.