docs(turn-loop): fix stale rmcp version + AgentRequest::Wake reference

Verified against Cargo.lock (rmcp resolves to 2.2.0, Cargo.toml pins
"2") and hive-core-agent-sock/src/lib.rs (the Wake variant lives on
Request there; hive_sh4re::AgentRequest doesn't exist).
This commit is contained in:
iris 2026-08-15 12:26:46 +02:00 committed by mara
commit 6d74476572

View file

@ -1,6 +1,6 @@
# MCP surface
The harness ships an embedded MCP server (rmcp 1.7). The built-in
The harness ships an embedded MCP server (rmcp 2). The built-in
`hyperhive` surface is served over streamable HTTP by a persistent
`hive-mcp-http` daemon (loopback, `127.0.0.1:<hyperhive.mcp.httpPort>`,
per-container private netns). Claude connects to its stable URL via
@ -162,8 +162,8 @@ External MCP servers (and any other in-container process) can
inject a wake-up event into the agent's inbox via the per-agent
socket at `/run/hive/mcp.sock`. Speak the wire protocol directly —
JSON-line over the unix socket: `{"cmd":"wake","from":"matrix","body":
"new dm from @alice"}\n`. Same shape as any other `AgentRequest`; see
`hive-sh4re::AgentRequest::Wake`. Every built-in producer that wakes
"new dm from @alice"}\n`. Same shape as any other request on this
socket; see `hive_core_agent_sock::Request::Wake`. Every built-in producer that wakes
the harness (matrix, bash) dials the socket directly — there is no
CLI wrapper, just the raw protocol.