vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity
hyperhive/docs/tools
History
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 43e69d345e subagents, ACP: stop with SIGINT only, so claude ends its own tool commands 
claude's Bash tool starts every command in a new session, so a signal to
claude's process group never reaches it. claude stops those commands
itself when SIGINT makes it shut down. A SIGKILL leaves them running,
re-parented to init. Per the ruling on #4999, every stop is SIGINT and
nothing escalates.

- Subagent `interrupt` always sends SIGINT. The `force` argument is gone
  from the MCP tool and from `session::interrupt`. A caller that still
  sends `force: true` gets SIGINT; the argument is ignored.
- `interrupt` used to free the session name before it signalled, so a
  `continue` could start a second claude on the session while the first
  was still exiting. The `running` map now holds a three-state `Slot`
  (starting, running, stopping). An interrupted claude turn is
  `Stopping` until the turn task's own `finish_turn` clears it. `status`
  says "stopping", and `start`/`continue` on that name are refused.
  `interrupt` still returns at once. The ACP arm is unchanged: its name
  is freed when `session/cancel` is sent.
- ACP `Connection` drop sends its process group SIGINT, not SIGKILL, and
  the spawn no longer sets tokio's `kill_on_drop`, which SIGKILLed the
  leader after the `Drop` body. The test fixture's background grandchild
  resets SIGINT to default, since `&` starts it ignored.

Tests: a fake claude that records SIGINT, interrupted, fails with
`cancel(true)` (the old `force: true` path). An interrupted fake claude
that keeps running keeps its name claimed and `continue` is refused,
which fails when the slot is freed before the signal. A fake ACP agent
that records SIGINT, dropped, fails with SIGKILL in `Drop`, and also with
SIGINT in `Drop` but `kill_on_drop(true)` left in place.

Not changed: hive-claude's idle watchdog (still SIGKILL, separate
hive-claude change), the units' `KillSignal`, `machinectl kill`, and the
login helper.
2026-10-11 02:44:31 +02:00
..
bash.md docs: drop statements about absent things, state current behaviour 2026-10-02 11:43:10 +02:00
forge-cli.md hive-forge: comments --since --limit returns N, not at most 49 2026-10-09 21:46:14 +02:00
forge.md hive-forge: fetch issue comments in one request; the endpoint has no paging 2026-10-09 21:19:47 +02:00
hivectl-cli.md swarm-ci-runner: run the forge CI runner as a swarm service 2026-10-05 13:55:37 +02:00
hivectl.md docs: config changes are operator merges on the forge 2026-10-02 23:13:04 +02:00
matrix.md hive-matrix-mcp: fix list_rooms/list_invites docs to say room_id, not id 2026-10-04 20:40:15 +02:00
README.md docs: scheduled prompts are swarm-level; the hive page is a read-only list 2026-10-04 21:23:31 +02:00
subagent.md subagents, ACP: stop with SIGINT only, so claude ends its own tool commands 2026-10-11 02:44:31 +02:00
swarm-logs-cli.md docs: gate write-good.Passive on CI 2026-09-20 16:24:11 +02:00
swarmctl-cli.md swarm: show each agent's effective model and effort, and where they came from 2026-10-10 17:37:23 +02:00

README.md

Tools

hivectl is your tool — the operator's own host CLI. Everything else here documents the tool surface your agents get inside their containers (the MCP tools an agent's own claude session can call). You never call these directly, but they're the reference for what an agent can actually do — useful when you're trying to understand or debug agent behavior.

For the operator

  • hivectl — the curated guide: provisioning forge and matrix accounts, gateway htpasswd management, container lifecycle shortcuts, interactive agent shell access.
  • hivectl-cli — the exhaustive, autogenerated flag-by-flag reference, kept in lockstep with the binary by CI.

For the swarm operator

  • swarmctl-cli — the exhaustive, autogenerated flag-by-flag reference for swarmctl, kept in lockstep with the binary by CI the same way hivectl-cli.md is. swarmctl itself runs as root on the swarm-controller host, not through hivectl — see swarmctl/README.md for why. Two verb families today: user (authelia's subject store, edited in place) and agent create (queues the swarm-controller's creation job graph). No curated guide yet; add one here if/when that grows.

What your agents can do

  • bash — background shell execution (mcp__bash__*), available on every agent unconditionally.
  • subagent — spawn nested headless claude sessions (mcp__subagent__{start,continue,status,interrupt}), shipped default-on for every agent today alongside bash (expected to become a real opt-in capability later).
  • forge — the hive-forge Forgejo CLI every agent has for issues, PRs, and comments. Not an MCP tool — a binary agents shell out to instead of ad-hoc curl.
  • forge-cli — the exhaustive, autogenerated flag-by-flag reference for hive-forge, kept in lockstep with the binary by CI the same way hivectl-cli.md is.
  • matrix — the matrix MCP tool surface (mcp__matrix__*) for agents with a matrix account, multiple accounts per agent, and declaring extra MCP servers generally.