Watch
0
0
Fork
You've already forked hyperhive
0
hyperhive/hive-subagent-mcp
Repository files (latest commit first)
Filename Latest commit message Latest commit date
iris da5fcbfd9b subagents publish their model and effort as headers on every row, and the swarm shows them
The subagent daemon stamps Swarm-Model and Swarm-Effort on each row it
publishes. The list endpoint reads them off the newest row it already fetches,
so a long-running subagent keeps them past the stream's 24 hour window, and the
terminal page's menu and the agent panel's list show them beside the name.
2026-10-28 21:55:02 +01:00
..
src subagents publish their model and effort as headers on every row, and the swarm shows them 2026-10-28 21:55:02 +01:00
tests subagent: keep runs at +1000 when their cgroup is unavailable 2026-10-13 12:25:27 +02:00
Cargo.toml agent_permissions, agent_term and subagent_term take their wire contracts from swarm-wire 2026-10-19 18:30:44 +02:00
README.md subagent: give each run its own signal URL, and drop the name argument 2026-09-14 22:24:51 +02:00

hive-subagent-mcp

Per-agent daemon (hive-subagent-daemon) that spawns nested headless claude sessions on request and serves the tool surface (start/continue/status/interrupt, plus a separate subagent-facing goal_reached/need_help route, one per-session URL) directly over streamable-http. No stdio bridge, no per-turn respawn — an agent's claude reconnects to the same stable URL every turn.

Independent of hive-bash-mcp — a subagent spawns a full nested claude session, a much heavier capability than a bash command, worth its own deployable/restartable unit.

Shape

One bin (hive-subagent-daemon, src/main.rs) built from the crate's own lib (src/lib.rs):

  • session.rs — the actual claude-facing logic: Claude::spawn + RunningClaude::wait/cancel_handle (not InfiniteSession::run, which has no cancel handle to reach in — see the module doc for the v1 scope this trades away), the turn-continuation loop a goal switches on, and the in-memory maps that are the only state this daemon keeps (no task files — a restart stops whatever's running; the actual claude session is the durable store, found again by name via hive_claude::SessionStore).
  • mcp.rs — the rmcp tool routers (the parent's start/continue/status/interrupt on /mcp, the subagent's goal_reached/need_help on /signal/mcp/<token>) + serve_http. Neither signal tool takes a session name: the token in the path is minted per run and resolved to a session before dispatch, so a subagent has no way to name — and therefore no way to signal — a sibling. One route with a path parameter, because the Router is built once at startup and sessions come and go for the daemon's whole life.
  • paths.rs — the in-agent todo-socket path.