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

Set resource caps and inference when creating an agent

Browse source 
POST /api/agents takes optional limits and inference objects, checked by
the same rules as the two PUT routes before anything is queued and stored
ahead of the job graph. The create form gets collapsed sections for both,
reusing the fields of the detail-panel editors.
This commit is contained in:
iris 2026-10-15 11:32:48 +02:00 • committed by mara
commit e36a15de91
8 changed files with 389 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

22
swarm-controller/src/inference.rs
View file

@ -87,7 +87,7 @@ pub(crate) fn check_model(name: &str, what: &str) -> Result<(), String> {
impl InferenceSettings {
/// The value to store, or why it is refused.
fn into_stored(self) -> Result<AgentInference, String> {
pub(crate) fn into_stored(self) -> Result<AgentInference, String> {
if let Some(model) = &self.model {
check_model(model, "model")?;
}
@ -313,18 +313,28 @@ pub(crate) async fn put_agent_inference(
&format!("no hive's wanted state declares an agent {agent:?} that is not destroyed"),
));
}
let store = open(&client).await?;
store(&client, &agent, &value).await?;
Ok(Json(value.into()))
}
/// Replace `agent`'s stored inference settings with `value`.
pub(crate) async fn store(
client: &async_nats::Client,
agent: &str,
value: &AgentInference,
) -> Result<(), ProblemDetails> {
let store = open(client).await?;
for _ in 0..MAX_ATTEMPTS {
let (current, revision, undecodable) = read_or_default::<AgentInference>(&store, &agent)
let (current, revision, undecodable) = read_or_default::<AgentInference>(&store, agent)
.await
.map_err(|e| queue_problem(&e))?;
if (current == value && !undecodable)
|| write(&store, &agent, &value, revision)
if (current == *value && !undecodable)
|| write(&store, agent, value, revision)
.await
.map_err(|e| queue_problem(&e))?
{
tracing::info!(%agent, ?value, "set inference settings");
return Ok(Json(value.into()));
return Ok(());
}
}
Err(queue_problem(&anyhow::anyhow!(