| Filename | Latest commit message | Latest commit date |
|---|---|---|
An agent's queue credential could subscribe to every subject in the swarm account, so any agent could read every other agent's terminal, turn state, operator input and request replies. Agents are the least trusted clients on the queue (mara's ruling on #4901), so their grants now carry a subscribe allow-list: - an agent's own credential (the harness and its subagent daemon): `_INBOX.agent.<agent>.>` and `$SWARM.input.<agent>` - the hive's shared agent client: `_INBOX.client.<client-id>.>` Hive and swarm-controller grants are unchanged (no `sub` claim, so still every subject). The clients connect with the matching inbox prefix, so the replies they rely on still arrive: the icon write's JetStream ack and the schedule DIRECT.GET. `connect_with_token` takes the agent name and sets the prefix itself; the hive-shared fallback uses the new `connect_with_inbox_prefix`. The harness no longer subscribes to its input subject when it fell back to the hive's shared client: that identity names no agent, so it cannot be granted one agent's input without all of them. It logs that and skips, the same as the schedule reader on that path. Refs #4901 |
||
| .. | ||
| 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.