hivectl: add hive-wide start/stop verbs

`hivectl stop` brings the whole hive down in one operator action — all
sub-agents plus the ci/forge/gateway/matrix infra containers — and
`hivectl start` brings it back up. Scope flags (--agents, --agent <name>,
--ci, --forge, --gateway, --matrix) narrow the set; a bare invocation
targets everything. hive-c0re never stops itself.

- hive-sh4re: HostRequest::{Stop,Start} + LifecycleScope wire type;
  priv_proto InfraAction + ControlInfraContainer + the
  CONTROLLABLE_INFRA_CONTAINERS allowlist (adds hive-matrix, excludes
  hive-c0re).
- hive-priv: control_infra_container handler (systemctl <verb>
  container@<name>, allowlist-validated root-side).
- hive-c0re: handle_stop / handle_start fan out agents via lifecycle and
  infra via hive-priv; per-target failures are aggregated. Infra
  systemctl routes through hive-priv (the privsep boundary).
- The --graceful flag is threaded through Stop now; the per-agent quiesce
  itself lands with the graceful-agent-stop work.
This commit is contained in:
atlas 2026-06-19 00:30:37 +02:00 committed by mara
commit fbb48ed3ce
6 changed files with 407 additions and 7 deletions

View file

@ -19,7 +19,7 @@ use std::os::unix::process::CommandExt as _;
use std::path::{Path, PathBuf};
use anyhow::{Context as _, Result, bail};
use clap::{Parser, Subcommand};
use clap::{Args, Parser, Subcommand};
use hive_c0re::coordinator::Coordinator;
#[derive(Parser)]
@ -100,6 +100,36 @@ enum Cmd {
#[arg(long)]
fresh: bool,
},
/// Stop containers hive-wide in one operator action. Bare `hivectl
/// stop` stops **everything** — all sub-agents plus the ci, forge,
/// gateway, and matrix infra containers. Narrow it with scope flags:
/// `--agents` (all sub-agents), `--ci` / `--forge` / `--gateway` /
/// `--matrix` (named infra), and `--agent <name>` (repeatable) for
/// specific sub-agents. Flags are additive (e.g. `--agents --matrix`).
/// Requires the hive-c0re daemon (connects to the host admin socket).
/// hive-c0re itself is never stopped — it services the request.
Stop {
#[command(flatten)]
scope: ScopeArgs,
/// Gracefully quiesce each agent (finish the current turn, drain
/// the inbox) before stopping, instead of a hard stop.
#[arg(long)]
graceful: bool,
/// Path to the hive-c0re host admin socket.
#[arg(long, default_value = DEFAULT_HOST_SOCKET)]
socket: PathBuf,
},
/// Start containers hive-wide — the inverse of `hivectl stop`. Bare
/// `hivectl start` starts everything back up; the same scope flags as
/// `stop` narrow it (`--agents`, `--ci`, `--forge`, `--gateway`,
/// `--matrix`, `--agent <name>`). Requires the hive-c0re daemon.
Start {
#[command(flatten)]
scope: ScopeArgs,
/// Path to the hive-c0re host admin socket.
#[arg(long, default_value = DEFAULT_HOST_SOCKET)]
socket: PathBuf,
},
/// Emit the full CLI reference as `CommonMark` to stdout.
///
/// Hidden tooling command (not part of day-to-day operator admin):
@ -111,6 +141,49 @@ enum Cmd {
MarkdownDocs,
}
/// Shared scope flags for `hivectl stop` / `hivectl start`. With no flag
/// set the verb targets **everything** (all sub-agents + every controllable
/// infra container). Setting any flag restricts to the selected classes,
/// additively.
// One bool per selectable container class, each mapping 1:1 to a clap flag;
// orthogonal toggles, not a state machine — hence the bools allow (mirrors
// `hive_sh4re::LifecycleScope`).
#[allow(clippy::struct_excessive_bools)]
#[derive(Args)]
struct ScopeArgs {
/// All sub-agent containers.
#[arg(long)]
agents: bool,
/// A specific sub-agent by name. Repeatable: `--agent a --agent b`.
#[arg(long = "agent", value_name = "NAME")]
agent: Vec<String>,
/// The CI runner container (`hive-ci`).
#[arg(long)]
ci: bool,
/// The forge container (`hive-forge`).
#[arg(long)]
forge: bool,
/// The gateway container (`hive-gateway`).
#[arg(long)]
gateway: bool,
/// The matrix container (`hive-matrix`).
#[arg(long)]
matrix: bool,
}
impl ScopeArgs {
fn to_scope(&self) -> hive_sh4re::LifecycleScope {
hive_sh4re::LifecycleScope {
agents: self.agents,
agent_names: self.agent.clone(),
ci: self.ci,
forge: self.forge,
gateway: self.gateway,
matrix: self.matrix,
}
}
}
#[derive(Subcommand)]
enum ForgeCmd {
/// Create or refresh the Forgejo account + token for `<name>`.
@ -348,6 +421,12 @@ async fn main() -> Result<()> {
AgentsCmd::Restart { name, socket } => agents_restart(&socket, &name).await,
AgentsCmd::RestartAll { socket } => agents_restart_all(&socket).await,
},
Cmd::Stop {
scope,
graceful,
socket,
} => stop(&socket, scope.to_scope(), graceful).await,
Cmd::Start { scope, socket } => start(&socket, scope.to_scope()).await,
Cmd::Choom { name, fresh } => choom(&name, fresh),
Cmd::MarkdownDocs => {
print!("{}", clap_markdown::help_markdown::<Cli>());
@ -804,6 +883,43 @@ async fn agents_restart_all(socket: &Path) -> Result<()> {
Ok(())
}
async fn stop(socket: &Path, scope: hive_sh4re::LifecycleScope, graceful: bool) -> Result<()> {
let resp =
hive_c0re::client::request(socket, hive_sh4re::HostRequest::Stop { scope, graceful })
.await
.with_context(|| format!("connect to daemon socket {}", socket.display()))?;
render_lifecycle(&resp, "stopped")
}
async fn start(socket: &Path, scope: hive_sh4re::LifecycleScope) -> Result<()> {
let resp = hive_c0re::client::request(socket, hive_sh4re::HostRequest::Start { scope })
.await
.with_context(|| format!("connect to daemon socket {}", socket.display()))?;
render_lifecycle(&resp, "started")
}
/// Render a hive-wide stop/start response: one `<verb>: <name>` line per
/// touched container, then surface any aggregated per-target failure as a
/// non-zero exit. `verb` is the past-tense word printed per item
/// (`stopped` / `started`).
fn render_lifecycle(resp: &hive_sh4re::HostResponse, verb: &str) -> Result<()> {
let items = resp.agents.as_deref().unwrap_or(&[]);
if items.is_empty() {
println!("{verb}: nothing matched the requested scope");
} else {
for item in items {
println!("{verb}: {item}");
}
}
if !resp.ok {
bail!(
"{verb}: {}",
resp.error.as_deref().unwrap_or("unknown error")
);
}
Ok(())
}
/// Reject usernames containing `:` (field separator) or control chars
/// that would corrupt the htpasswd file format.
fn validate_htpasswd_username(username: &str) -> Result<()> {