vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
hyperhive/hive-agent
History
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas c3e6e23d22 disk_watch: stay silent when the agent owns nothing worth deleting 
The todo fired on filesystem usage alone, so every agent on a busy host
got woken by a disk it had no power over. Measured case: a 927G volume
at 81%, 742G used, of which one agent's entire tree was 5.3G. The todo
cost that agent a full turn to arrive at "not actionable".

`summary_for` now also requires a non-empty `big_dirs()` result. An
agent that owns no oversized directory cannot free meaningful space, so
there is nothing to say to it; the shared store filling up is the host's
signal. Agents that ARE sitting on a stale `target/` still get told, with
the same bucketed anti-nag summary as before.

Drops the conditional around the "Biggest directories" section, which is
now unreachable when empty. Existing tests passed `&[]` as a
don't-care — they now pass a directory, since that argument became
load-bearing.

Closes #2759
2026-07-27 12:10:27 +02:00
..
prompts prompts: fix rebase conflict + qualify inbox tool names consistently 2026-07-26 17:33:41 +02:00
src disk_watch: stay silent when the agent owns nothing worth deleting 2026-07-27 12:10:27 +02:00
Cargo.toml refactor(sock): one socket client, retry as a policy value 2026-07-26 22:44:48 +02:00
README.md remove hive-agent-wake — no shipped consumer 2026-07-25 20:05:32 +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 claude --print turn per inbox message, over the hive-claude driver. There is one role here (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 lands in the inbox" and "claude produces a reply", how login/auth is bootstrapped, how the per-agent web UI is served, or how turn/event stats get recorded. Architecture detail lives in docs/turn-loop.md; this README is just the map of the module tree.

Shape

  • turn.rs — the turn-loop policy layer: renders the system prompt + MCP config, invokes hive-claude, classifies the outcome, and feeds the event/turn-stats sinks.
  • client.rs — broker client (inbox poll, ack, send) speaking the hive-sh4re wire protocol.
  • 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 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-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/.
  • forge_notify.rs — subscribes to forge notifications and wakes the harness on new activity.
  • 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.

Sibling: hive-agent-mcp (the MCP server this loop points claude at every turn). Both are described together in docs/turn-loop.md::Harness binary shape.