hivectl: resolve stop/start scope to names at the c0re entry point

Per review: c0re expands the LifecycleScope to explicit container-name
lists (scoped_agents / scoped_infra) in the dispatch arm, then hands those
lists to handle_stop / handle_start. The 'all agents' flag no longer flows
past the resolution boundary, so downstream consumers (incl. the future
graceful-stop queue) always operate on concrete names. CLI --agents flag
unchanged.
This commit is contained in:
atlas 2026-06-19 00:40:22 +02:00 committed by mara
commit c673dce73d

View file

@ -94,8 +94,20 @@ async fn dispatch(req: &HostRequest, coord: Arc<Coordinator>) -> HostResponse {
HostResponse::success()
}
HostRequest::RestartAll => handle_restart_all().await?,
HostRequest::Stop { scope, graceful } => handle_stop(scope, *graceful).await?,
HostRequest::Start { scope } => handle_start(scope).await?,
HostRequest::Stop { scope, graceful } => {
// Resolve the scope to explicit container names at the entry
// point, then operate on names — never pass the bare "all
// agents" flag deeper (it'd force every consumer, incl. the
// graceful-stop queue, to re-expand it).
let agents = scoped_agents(scope).await?;
let infra = scoped_infra(scope);
handle_stop(&agents, &infra, *graceful).await?
}
HostRequest::Start { scope } => {
let agents = scoped_agents(scope).await?;
let infra = scoped_infra(scope);
handle_start(&agents, &infra).await?
}
HostRequest::Destroy { name, purge } => {
actions::destroy(&coord, name, *purge).await?;
HostResponse::success()
@ -202,24 +214,25 @@ async fn handle_restart_all() -> Result<HostResponse> {
}
}
/// Stop the containers a [`LifecycleScope`] selects (`hivectl stop`): the
/// scoped sub-agents, then the scoped infra containers. Agents go down
/// before infra so they're not mid-request against a forge/matrix that's
/// already gone. Per-target failures are aggregated rather than aborting on
/// the first error, mirroring `handle_restart_all`.
async fn handle_stop(scope: &LifecycleScope, graceful: bool) -> Result<HostResponse> {
tracing::info!(?scope, graceful, "stop");
/// Stop the given `agents` (resolved logical names) then `infra` containers
/// (`hivectl stop`). Agents go down before infra so they're not mid-request
/// against a forge/matrix that's already gone. Per-target failures are
/// aggregated rather than aborting on the first error, mirroring
/// `handle_restart_all`. Callers resolve the [`LifecycleScope`] to these
/// explicit name lists up front — this never sees the "all" flag.
async fn handle_stop(agents: &[String], infra: &[&str], graceful: bool) -> Result<HostResponse> {
tracing::info!(?agents, ?infra, graceful, "stop");
let mut ok_items: Vec<String> = Vec::new();
let mut errors: Vec<String> = Vec::new();
for agent in scoped_agents(scope).await? {
for agent in agents {
// TODO(graceful agent stop): when `graceful`, run the per-agent
// quiesce (turn-end → drain → reject new messages) before the kill.
// The flag is threaded through the wire now; the quiesce itself
// lands with the graceful-agent-stop work.
let _ = graceful;
match lifecycle::kill(&agent).await {
Ok(()) => ok_items.push(agent),
match lifecycle::kill(agent).await {
Ok(()) => ok_items.push(agent.clone()),
Err(e) => {
tracing::warn!(%agent, error = ?e, "stop: agent kill failed");
errors.push(format!("{agent}: {e:#}"));
@ -227,7 +240,7 @@ async fn handle_stop(scope: &LifecycleScope, graceful: bool) -> Result<HostRespo
}
}
for container in scoped_infra(scope) {
for &container in infra {
match crate::priv_client::control_infra_container(container, InfraAction::Stop).await {
Ok(()) => ok_items.push(container.to_owned()),
Err(e) => {
@ -240,15 +253,16 @@ async fn handle_stop(scope: &LifecycleScope, graceful: bool) -> Result<HostRespo
Ok(finish_lifecycle(ok_items, &errors))
}
/// Start the containers a [`LifecycleScope`] selects (`hivectl start`) —
/// the inverse of [`handle_stop`]. Infra comes up before agents so the
/// agents find forge/matrix/gateway ready. Per-target failures aggregated.
async fn handle_start(scope: &LifecycleScope) -> Result<HostResponse> {
tracing::info!(?scope, "start");
/// Start the given `infra` containers then `agents` (`hivectl start`) — the
/// inverse of [`handle_stop`]. Infra comes up before agents so the agents
/// find forge/matrix/gateway ready. Per-target failures aggregated. Callers
/// resolve the [`LifecycleScope`] to these explicit name lists up front.
async fn handle_start(agents: &[String], infra: &[&str]) -> Result<HostResponse> {
tracing::info!(?agents, ?infra, "start");
let mut ok_items: Vec<String> = Vec::new();
let mut errors: Vec<String> = Vec::new();
for container in scoped_infra(scope) {
for &container in infra {
match crate::priv_client::control_infra_container(container, InfraAction::Start).await {
Ok(()) => ok_items.push(container.to_owned()),
Err(e) => {
@ -258,9 +272,9 @@ async fn handle_start(scope: &LifecycleScope) -> Result<HostResponse> {
}
}
for agent in scoped_agents(scope).await? {
match lifecycle::start(&agent).await {
Ok(()) => ok_items.push(agent),
for agent in agents {
match lifecycle::start(agent).await {
Ok(()) => ok_items.push(agent.clone()),
Err(e) => {
tracing::warn!(%agent, error = ?e, "start: agent start failed");
errors.push(format!("{agent}: {e:#}"));