| Filename | Latest commit message | Latest commit date |
|---|---|---|
9a71d1e094
Nothing capped how many subagents an agent runs at once; the operator wants to set that per agent from swarm-ui (#5234, shape (b)). AgentInference gains `max_subagents: Option<u32>`. An absent field decodes as None, so every stored value still parses and means "no cap", which is today's behaviour. swarm-controller accepts 1..=32 on PUT. 0 would refuse every start; 32 is far more concurrent claude sessions than one agent container has memory for, so anything above it is a typo, not a cap. The subagent daemon already read the agent's agent-inference key for subagent_models; it now reads it on every start and continue (not only those naming a model) and refuses a new run once the cap's worth of names is tracked, counted under the same lock as the name reservation. Every tracked slot counts: running, starting, a goal run between turns, and an interrupted one still exiting. A goal re-prompt never goes through the reservation, so it is never refused. A failed read applies no cap, as it falls back for models. swarmctl's `inference set` does GET, merge, PUT; its mirror type now carries the field so a set from the CLI keeps a cap set in swarm-ui instead of dropping it, and `get` prints it. |
||
| .. | ||
| src | ||
| tests | ||
| Cargo.toml | ||
| README.md | ||
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(notInfiniteSession::run, which has no cancel handle to reach in — see the module doc for the v1 scope this trades away), the turn-continuation loop agoalswitches 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 viahive_claude::SessionStore).mcp.rs— thermcptool routers (the parent'sstart/continue/status/interrupton/mcp, the subagent'sgoal_reached/need_helpon/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 theRouteris built once at startup and sessions come and go for the daemon's whole life.paths.rs— the in-agent todo-socket path.