vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
hyperhive/hive-core-agent-sock
History
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 0a80f21003 prompts+docs: the lifecycle tools reach the whole subtree, not just direct children 
`require_descendant` (`socket_server/mod.rs:666`) authorises
kill/start/restart/update/get_logs with `topology::is_descendant_of` — the
caller's whole subtree, itself included. That has been true since `53b4e752`
(#1865), whose message says "a parent owns its whole subtree; the root covers
every agent as a consequence, no positional privilege", and two tests pin it
(`is_descendant_of_in_grandchild`, `is_descendant_of_in_self_is_true`).

The prose never followed. The four lifecycle tool descriptions, their
`// IMPORTANT:` comments, `docs/tools/lifecycle.md`, the tools README,
hive-agent-mcp's README and the system prompt every agent is rendered from all
still said "direct children only" — while `list_containers`, four tools away in
the same file, said "direct children + their subtrees".

`lifecycle.md` also taught the model #1865 deleted: "Privileged agents (for
example ruth) may operate on any sub-agent — the topology scope applies to all
others." There is no privileged class to belong to; ruth reaches every agent
because the check is transitive and everything sits under it.

Same drift on the state-query side: `resolve_agent_state_target` is
subtree-scoped by the same commit, so `get_loose_ends`' argument doc, the
`QueryAgentState` capability doc and `docs/turn-loop/mcp.md` were all telling a
parent it needs a capability to read a grandchild's threads.

Two smaller corrections found on the way:

* `list_containers` returns the caller itself. `is_descendant_of` is true for
  `candidate == ancestor` and `handle_list_descendants` filters the topology
  with it; called from a leaf agent it answers one row, that agent.
* `request_init_config` accepts any unused name — the requester becomes its
  parent — or an existing agent already in the caller's subtree, not "a direct
  child". The editing surface is narrower than the guard, though: only direct
  children's config repos are bind-mounted, so re-seeding deeper in the subtree
  leaves no local copy to edit. `lifecycle.md` now says so.

The prompt's other stale claim, the dead `request_apply_commit`, is #4226 and
was fixed independently by damocles in #4227 while this was being gated. This
branch keeps only the scope wording on that line.

Closes #4225.
2026-09-11 15:23:50 +02:00
..
src prompts+docs: the lifecycle tools reach the whole subtree, not just direct children 2026-09-11 15:23:50 +02:00
Cargo.toml docs(#2627): add READMEs for the remaining infra crates 2026-07-23 13:16:29 +02:00
README.md treefmt: apply prettier 2026-09-02 15:25:07 +02:00

README.md

hive-core-agent-sock

Wire types for the per-agent + manager socket (/run/hive/mcp.sock) — the unified Request / Response protocol spoken between an agent's in-container harness (and the manager) and the hive-c0re daemon.

Why it's its own crate

Re-homed out of hive-sh4re so this one socket owns its protocol crate, mirroring the hive-host-sock / hive-priv-sock splits. The shared payload types it references (Message, LooseEnd, Approval, …) stay in hive-sh4re, which this crate depends on — this crate is just the request/response envelope for this socket.

Not to be confused with hive-agent-sock

This is the host-served protocol: the harness talks out to hive-c0re over /run/hive/mcp.sock (broker sends, approvals, lifecycle). hive-agent-sock is the separate in-container socket the harness serves to its own local producers — that one never leaves the container. See docs/trust-boundary/boundary.md for the socket topology.