hyperhive/hive-core-agent-sock
Repository files (latest commit first)
Filename Latest commit message Latest commit date
atlas 11097ed336 remove the get_host_journal MCP tool and its capability
swarm-logs covers every host-tier unit this tool could reach, so the
second, capability-gated path into host journald earns nothing and is
removed outright rather than disabled behind a flag.

Removed end to end: the MCP tool definition + handler, the
GetHostJournal/HostJournal wire variants, hive-c0re's
dispatch_host_journal handler, the ReadHostJournal capability, and the
harness-side capability->--allowedTools gate. get_host_journal was the
only capability that mapped to an MCP tool, so allowed_capability_tools
could only ever return an empty vec; it goes too rather than linger as a
function that provably does nothing.

capabilities::has_cap/caps_for stay: #4624 gave ManageRootAgent's
bind-mount enforcement (hive-c0re/src/lifecycle/host_config.rs) a
second caller of has_cap, so they're no longer callerless once this
lands on top of it.

hive-sh4re's journal module (JournalPriority) had no consumer outside
this tool and is deleted.

An existing capabilities.json still naming read_host_journal does not
error: capabilities::prune_unknown drops unrecognised names with a
warn!, and an agent left with no capabilities has its entry removed. No
migration step is needed.

Untouched: hive-c0re/src/dashboard/journal.rs's
read_host_journal_response, which matches the name but is the private
helper behind the operator-only GET /api/journal-host dashboard route
and carries no capability check.
2026-09-21 19:31:45 +02:00
..
src remove the get_host_journal MCP tool and its capability 2026-09-21 19:31:45 +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

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.