| Filename | Latest commit message | Latest commit date |
|---|---|---|
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. |
||
| .. | ||
| prompts | ||
| src | ||
| Cargo.toml | ||
| README.md | ||
hive-agent
The in-container harness serve-loop binary — one instance per agent.
Long-polls the broker inbox and drives one turn per inbox message
through hive-runtime, on the agent's runtime (claude --print by
default, or an ACP agent). It has one role
(agent); the Surface trait + AgentSurface zero-sized type tag keep
the turn loop generic and testable for future roles without a
parallel copy of the loop.
When to use it
You don't call into this crate from elsewhere — it's the top-level
binary systemd starts per agent container. Look here when you need to
understand or change: what happens between a message landing in the
inbox and the agent's reply, how the harness bootstraps login/auth,
how it serves the per-agent web UI, or how turn/event stats get
recorded. Architecture detail lives in
docs/turn-loop/; this README is just the
map of the module tree.
Shape
main.rs— the serve loop and theSurfacetrait; broker calls (inbox poll, ack, send) go throughhive-sock-clientwithhive-core-agent-sockwire types.turn.rs— the turn-loop policy layer: renders the system prompt + MCP config, runs the turn throughhive-runtime, classifies the outcome, and feeds the event/turn-stats sinks.login.rs/login_session.rs— first-run and session-resume auth flow for theclaudeCLI.mcp_config.rs— renders the per-turn--mcp-config/--allowedToolsblob from tool groups + capabilities.todos.rs/reminders.rs/todo_server.rs— the harness-local loose-ends v2 stores (sqlite-backed) and the in-agent socket server extra MCP daemons +hive-agent-mcpdial into for todo/reminder ops.vacuum.rs— periodic sqlite vacuum sweep for the harness-local stores.events.rs/turn_stats.rs/stats.rs— append-only event sink and per-turn telemetry recording (context usage, cost, tool favorites) underharness/.prompt.rs— system-prompt renderer (persona + tool docs + environment facts).web_ui/— the per-agent dashboard (terminal pane, status, schedules) served over the built-inhive-agentweb port.paths.rs— canonical path resolution for state/harness dirs and the harness-local sqlite files.
Siblings: hive-agent-mcp (the MCP server this loop points the
agent at every turn) and hive-runtime (the library a turn runs
through).
docs/turn-loop/::Harness binary shape
covers all three together.