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

docs: get_agent_meta response gains hive_name + swarm_name (follow-up to #741)

Browse source 
turn-loop.md: add optional hive_name / swarm_name fields to get_agent_meta
response shape; note they are omitted when the host options are unset.
CLAUDE.md: update hive-gateway.nix entry to mention per-agent routing
and .well-known; drop stale #609 cookie.
This commit is contained in:
lexis 2026-05-31 12:56:30 +02:00 • committed by Mara
commit a823fa4dd9
2 changed files with 13 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

7
CLAUDE.md
View file

@ -255,9 +255,10 @@ nix/
modules/hive-gateway.nix nginx nixos-container in front of all hyperhive modules/hive-gateway.nix nginx nixos-container in front of all hyperhive
surfaces (`services.hyperhive.gateway.enable`, surfaces (`services.hyperhive.gateway.enable`,
default on); proxies `/` → c0re dashboard, default on); proxies `/` → c0re dashboard,
static-serves matrix GUI at `/matrix/` when `/agent/<name>/` → per-agent UI (driven by
`matrix.gui.enable`; `localHostsEntry` for c0re-written JSON at `gateway.agentPortsFile`),
local-dev DNS; v0 HTTP-only (#609) `/matrix/` → fluffychat-web GUI when enabled;
`.well-known/matrix/` auto-discovery; v0 HTTP-only
modules/hive-matrix.nix optional in-container matrix-tuwunel modules/hive-matrix.nix optional in-container matrix-tuwunel
homeserver (`services.hyperhive.matrix.enable`, homeserver (`services.hyperhive.matrix.enable`,
default off); server_name defaults to bare default off); server_name defaults to bare

16
docs/turn-loop.md
View file

@ -252,15 +252,17 @@ it as a stdio child via `--mcp-config`. The hyperhive socket name is
over-length text with a clear error. over-length text with a clear error.
- `get_agent_meta(name?)` — fetch identity + status metadata for - `get_agent_meta(name?)` — fetch identity + status metadata for
an agent: `{ name, role, hyperhive_rev, running, status_text, an agent: `{ name, role, hyperhive_rev, running, status_text,
status_set_at }`. Pass `name` to query a peer (e.g. check status_set_at, hive_name?, swarm_name? }`. Pass `name` to query
whether a sub-agent is idle before sending it work). Omit a peer (e.g. check whether a sub-agent is idle before sending it
`name` to get your own identity stamp — replaces the previous work). Omit `name` to get your own identity stamp — replaces the
`whoami` tool. `running` is `true` when the container is up. previous `whoami` tool. `running` is `true` when the container is
When `running` is `false` the host clears `status_text` / up. When `running` is `false` the host clears `status_text` /
`status_set_at` (they would be stale snapshots from before the `status_set_at` (they would be stale snapshots from before the
container stopped) before serving the response. Status fields are container stopped) before serving the response. Status fields are
also `None` when the target has never called `set_status` or also `None` when the target has never called `set_status` or has
has cleared it. cleared it. `hive_name` and `swarm_name` are present when
`services.hyperhive.hiveName` / `services.hyperhive.swarmName`
are configured on the host; omitted in single-hive deployments.
- `request_next_turn()` — ask the harness to start another turn - `request_next_turn()` — ask the harness to start another turn
immediately after this one ends, even if the inbox is empty. Use for immediately after this one ends, even if the inbox is empty. Use for
multi-turn tasks (long builds, sequential steps) where you want to multi-turn tasks (long builds, sequential steps) where you want to