vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

hive-subagent-mcp: run an agent's subagents on its runtime

Browse source 
The subagent daemon now reads the parent agent's runtime at startup
(`hive_runtime::RuntimeSpec`, from the harness's `HIVE_RUNTIME` /
`HIVE_ACP_*`, which `mcp.nix` forwards onto its unit). On claude
nothing changes. On ACP, each run drives an `AcpRuntime` whose session
id is kept per name under the harness dir: `start` archives the old one,
`continue` loads it (and fails when none is recorded), `interrupt` sends
`session/cancel`, a role goes in front of the first prompt, and
permission requests get the answers a claude subagent's tool list
gives. The unit loads `backendEnvironmentFile` on ACP only, so the
agent can authenticate.

The end-of-turn handling moves out of the claude loop into `after_turn`
unchanged, so both loops share it.

Refs #4391
This commit is contained in:
atlas 2026-09-30 01:39:21 +02:00 • committed by mara
commit 84d4808d54
10 changed files with 689 additions and 71 deletions
Download patch file Download diff file Expand all files Collapse all files

25
docs/tools/subagent.md
View file

@ -288,6 +288,31 @@ agent that needs a stable or non-default port.
Own systemd unit, defined alongside the other per-agent MCP daemons in
`nix/agent-modules/mcp.nix`.
## Runtime
A subagent runs on its parent agent's runtime
(`services.hyperhive.agent.runtime`). The unit gets the harness's
`HIVE_RUNTIME`/`HIVE_ACP_*` variables, and the daemon reads them once at
startup (`hive_runtime::RuntimeSpec`). On `claude`, everything else on this
page applies as written.
On `acp`:
- each run spawns its own copy of the parent's ACP agent, which exits
when the run ends. The unit loads `backendEnvironmentFile` for it.
- the session id lives in `subagent-acp-session-<name>` under the harness
dir. `start` moves an old one aside, `continue` loads it into a fresh
agent process, and a `continue` with none recorded fails straight away.
- a role goes in front of the session's first prompt, since ACP has no
system prompt.
- `interrupt` sends `session/cancel`, and `force` changes nothing. The
runtime kills an agent that ignores the cancel for 10s.
- `model` and `effort` do nothing: the agent runs the model it's
configured with.
- the agent's permission requests get the same answers a claude subagent's
tool list gives: MCP tools and file tools, `fetch` with `web_tools`,
`execute` with `execution` (`session::acp_permits`).
## The tool surface a subagent gets
Two flags, each covering one half, and neither covering the other: