Watch

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	fix(#2733 ): write the agent pause marker via hive-priv	2026-07-27 09:42:31 +02:00
README.md	treefmt: apply prettier	2026-09-02 15:25:07 +02:00

README.md

hive-sh4re

The shared payload vocabulary between hive-c0re and the in-container harness — the common types (Message, Approval, LooseEnd, HelperEvent, …) that the per-socket wire protocols are built from. The request/response envelopes themselves now live in the per-socket crates (below); this crate holds the payloads they carry.

Where it sits

This is the shared payload crate; the per-socket protocol envelopes have been split into their own smaller crates so specialised binaries don't have to pull in all of hive-sh4re:

hive-host-sock — host admin socket (hivectl ↔ hive-c0re)
hive-core-agent-sock — per-agent/manager socket (/run/hive/mcp.sock)
hive-priv-sock — the privileged-helper socket

Those crates re-export or reference the payload types that still live here (Approval, Message, LooseEnd, …).

Modules

wire_time — the timestamp convention: wire fields are chrono::DateTime<Utc> (serialized RFC 3339), while sqlite storage + input args stay unix-epoch i64; this module owns the two boundary conversions.
paths — well-known on-disk path helpers.
assets — resolves bundled runtime asset paths (branding, prompts) under HIVE_ASSETS_DIR.

Agent-name fields are typed as hive_types::Ident for serde-validated parsing at the socket boundary.