refactor(#1474): extract dispatch arm logic into helpers (server + agent_server)

This commit is contained in:
damocles 2026-06-09 11:34:49 +02:00 committed by mara
commit c6d9f59c4d
2 changed files with 476 additions and 396 deletions

View file

@ -73,42 +73,10 @@ async fn handle(stream: UnixStream, coord: Arc<Coordinator>) -> Result<()> {
}
}
#[allow(
clippy::too_many_lines,
reason = "flat dispatch table: one match arm per host-socket request \
variant; splitting it would scatter the routing logic"
)]
async fn dispatch(req: &HostRequest, coord: Arc<Coordinator>) -> HostResponse {
let result: anyhow::Result<HostResponse> = async {
Ok(match req {
HostRequest::Spawn { name } => {
tracing::info!(%name, "spawn");
let agent_dir = coord.ensure_runtime(name)?;
let hive = coord.hive_env();
let paths = Coordinator::agent_paths(name, agent_dir);
match lifecycle::spawn(name, &hive, &paths).await {
Ok(()) => {
coord.notify_manager(&hive_sh4re::HelperEvent::Spawned {
agent: name.clone(),
ok: true,
note: None,
sha: None,
});
}
Err(e) => {
// Roll back socket registration if container creation failed.
coord.unregister_agent(name);
coord.notify_manager(&hive_sh4re::HelperEvent::Spawned {
agent: name.clone(),
ok: false,
note: Some(format!("{e:#}")),
sha: None,
});
return Err(e);
}
}
HostResponse::success()
}
HostRequest::Spawn { name } => handle_spawn(&coord, name).await?,
HostRequest::RequestSpawn { name } => {
tracing::info!(%name, "request_spawn");
let id =
@ -118,86 +86,18 @@ async fn dispatch(req: &HostRequest, coord: Arc<Coordinator>) -> HostResponse {
tracing::info!(%id, %name, "spawn approval queued");
HostResponse::success()
}
HostRequest::Kill { name } => {
tracing::info!(%name, "kill");
lifecycle::kill(name).await?;
coord.unregister_agent(name);
coord.notify_manager(&hive_sh4re::HelperEvent::Killed {
agent: name.clone(),
});
HostResponse::success()
}
HostRequest::Kill { name } => handle_kill(&coord, name).await?,
HostRequest::Restart { name } => {
tracing::info!(%name, "restart");
lifecycle::restart(name).await?;
HostResponse::success()
}
HostRequest::RestartAll => {
tracing::info!("restart-all");
let agents = lifecycle::list().await?;
let mut ok_agents: Vec<String> = Vec::new();
let mut errors: Vec<String> = Vec::new();
for agent in &agents {
if let Err(e) = lifecycle::restart(agent).await {
tracing::warn!(%agent, error = ?e, "restart-all: failed to restart agent");
errors.push(format!("{agent}: {e:#}"));
} else {
ok_agents.push(agent.clone());
}
}
if errors.is_empty() {
HostResponse::list(ok_agents)
} else {
HostResponse {
ok: false,
error: Some(errors.join("; ")),
agents: Some(ok_agents),
approvals: None,
}
}
}
HostRequest::RestartAll => handle_restart_all().await?,
HostRequest::Destroy { name, purge } => {
actions::destroy(&coord, name, *purge).await?;
HostResponse::success()
}
HostRequest::Rebuild { name } => {
tracing::info!(%name, "rebuild");
let agent_dir = coord.ensure_runtime(name)?;
let hive = coord.hive_env();
let paths = Coordinator::agent_paths(name, agent_dir);
let result = lifecycle::rebuild(name, &hive, &paths, &|_| (), &|_| ()).await;
// Mirror auto_update::rebuild_agent — the manager wants
// to know about every rebuild attempt regardless of
// which surface triggered it, especially failures
// (build error → manager can adjust the agent's
// agent.nix). Without this the admin-socket CLI was
// a notify-gap.
match &result {
Ok(()) => {
coord.notify_manager(&hive_sh4re::HelperEvent::Rebuilt {
agent: name.clone(),
ok: true,
note: None,
sha: None,
tag: None,
});
// Wake the agent's next turn with the
// "you were rebuilt" hint. Same pattern as
// auto_update::rebuild_agent and the dashboard
// rebuild path — this is the CLI's equivalent.
coord.kick_agent(name, "container rebuilt");
}
Err(e) => coord.notify_manager(&hive_sh4re::HelperEvent::Rebuilt {
agent: name.clone(),
ok: false,
note: Some(format!("{e:#}")),
sha: None,
tag: None,
}),
}
result?;
HostResponse::success()
}
HostRequest::Rebuild { name } => handle_rebuild(&coord, name).await?,
HostRequest::List => HostResponse::list(lifecycle::list().await?),
HostRequest::Pending => HostResponse::pending(coord.approvals.pending()?),
HostRequest::Approve { id } => {
@ -229,3 +129,111 @@ async fn dispatch(req: &HostRequest, coord: Arc<Coordinator>) -> HostResponse {
Err(e) => HostResponse::error(format!("{e:#}")),
}
}
/// Create + start the container for `name`, rolling back socket
/// registration and notifying the manager on failure.
async fn handle_spawn(coord: &Arc<Coordinator>, name: &str) -> Result<HostResponse> {
tracing::info!(%name, "spawn");
let agent_dir = coord.ensure_runtime(name)?;
let hive = coord.hive_env();
let paths = Coordinator::agent_paths(name, agent_dir);
match lifecycle::spawn(name, &hive, &paths).await {
Ok(()) => {
coord.notify_manager(&hive_sh4re::HelperEvent::Spawned {
agent: name.to_owned(),
ok: true,
note: None,
sha: None,
});
}
Err(e) => {
// Roll back socket registration if container creation failed.
coord.unregister_agent(name);
coord.notify_manager(&hive_sh4re::HelperEvent::Spawned {
agent: name.to_owned(),
ok: false,
note: Some(format!("{e:#}")),
sha: None,
});
return Err(e);
}
}
Ok(HostResponse::success())
}
/// Kill `name`'s container, unregister its socket, notify the manager.
async fn handle_kill(coord: &Arc<Coordinator>, name: &str) -> Result<HostResponse> {
tracing::info!(%name, "kill");
lifecycle::kill(name).await?;
coord.unregister_agent(name);
coord.notify_manager(&hive_sh4re::HelperEvent::Killed {
agent: name.to_owned(),
});
Ok(HostResponse::success())
}
/// Restart every container, aggregating per-agent failures into one
/// response rather than aborting on the first error.
async fn handle_restart_all() -> Result<HostResponse> {
tracing::info!("restart-all");
let agents = lifecycle::list().await?;
let mut ok_agents: Vec<String> = Vec::new();
let mut errors: Vec<String> = Vec::new();
for agent in &agents {
if let Err(e) = lifecycle::restart(agent).await {
tracing::warn!(%agent, error = ?e, "restart-all: failed to restart agent");
errors.push(format!("{agent}: {e:#}"));
} else {
ok_agents.push(agent.clone());
}
}
if errors.is_empty() {
Ok(HostResponse::list(ok_agents))
} else {
Ok(HostResponse {
ok: false,
error: Some(errors.join("; ")),
agents: Some(ok_agents),
approvals: None,
})
}
}
/// Rebuild `name`'s container, notifying the manager of the outcome
/// (success or failure) and kicking the agent's next turn on success.
async fn handle_rebuild(coord: &Arc<Coordinator>, name: &str) -> Result<HostResponse> {
tracing::info!(%name, "rebuild");
let agent_dir = coord.ensure_runtime(name)?;
let hive = coord.hive_env();
let paths = Coordinator::agent_paths(name, agent_dir);
let result = lifecycle::rebuild(name, &hive, &paths, &|_| (), &|_| ()).await;
// Mirror auto_update::rebuild_agent — the manager wants to know
// about every rebuild attempt regardless of which surface triggered
// it, especially failures (build error → manager can adjust the
// agent's agent.nix). Without this the admin-socket CLI was a
// notify-gap.
match &result {
Ok(()) => {
coord.notify_manager(&hive_sh4re::HelperEvent::Rebuilt {
agent: name.to_owned(),
ok: true,
note: None,
sha: None,
tag: None,
});
// Wake the agent's next turn with the "you were rebuilt"
// hint. Same pattern as auto_update::rebuild_agent and the
// dashboard rebuild path — this is the CLI's equivalent.
coord.kick_agent(name, "container rebuilt");
}
Err(e) => coord.notify_manager(&hive_sh4re::HelperEvent::Rebuilt {
agent: name.to_owned(),
ok: false,
note: Some(format!("{e:#}")),
sha: None,
tag: None,
}),
}
result?;
Ok(HostResponse::success())
}