vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity
hyperhive/hive-agent
History
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 8be90ae8f2 hive-agent: bound each claude plugin call with a deadline 
The claude plugin marketplace add/update and install calls fetch over
the network and are awaited before the web UI is spawned. One hung
fetch stopped the agent from booting at all, against the module's own
promise that plugin failures never block boot.

Each call now runs under a 2 minute deadline; on expiry the child is
killed, a warning is logged and boot continues, as for any other
plugin failure.
2026-10-16 11:40:59 +02:00
..
prompts Point agents at /agents/<name>/work and default subagents to it 2026-10-16 00:32:41 +02:00
src hive-agent: bound each claude plugin call with a deadline 2026-10-16 11:40:59 +02:00
Cargo.toml agent permissions: one set, tool groups included, set at agent creation 2026-10-15 18:01:40 +02:00
README.md agent permissions: one set, tool groups included, set at agent creation 2026-10-15 18:01:40 +02:00

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 the Surface trait; broker calls (inbox poll, ack, send) go through hive-sock-client with hive-core-agent-sock wire types.
  • turn.rs — the turn-loop policy layer: renders the system prompt + MCP config, runs the turn through hive-runtime, classifies the outcome, and feeds the event/turn-stats sinks.
  • login.rs / login_session.rs — first-run and session-resume auth flow for the claude CLI.
  • mcp_config.rs — renders the per-turn --mcp-config / --allowedTools blob from the agent's permissions.
  • 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-mcp dial 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) under harness/.
  • prompt.rs — system-prompt renderer (persona + tool docs + environment facts).
  • web_ui/ — the per-agent dashboard (terminal pane, status, schedules) served over the built-in hive-agent web 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.