Ilker ManapandClaude Opus 5.5
62657f4c2a
CPU replicas start on half the machine's CPUs, not all of them: two busy llama.cpp servers each spinning on all 8 vCPUs fell to 0.8 tok/s apiece, where at 4 threads they keep 5.5. llamacpp.threads sets it per node. Inference requests can be traced over OTLP/HTTP (tracing.endpoint), with admission, schedule and upstream spans and traceparent sent to the engine. Security: onboarding no longer puts the cluster root in the system trust store and removes it where it was; the mirror's mutual-TLS API can be limited to named certificates (--api-client); init.log no longer keeps the administrator's password; a warning when auth is off on a public listen; the recorded actor is sanitised and sudo-aware; Ray's dashboard is off, and the remaining engine gaps are documented. reconciler.go and agent.go are split by topic, the status mapping of each failure is tested, and the plan's checklist is brought up to date. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
35 lines
729 B
Go
35 lines
729 B
Go
package agent
|
|
|
|
import (
|
|
"slices"
|
|
|
|
llmgwv1 "gitea.mynodes.xyz/ilker/llmgw/api/gen/llmgw/v1"
|
|
)
|
|
|
|
// logsReply answers a request for one of this node's logs.
|
|
func (a *Agent) logsReply(req *llmgwv1.LogsRequest) *llmgwv1.LogsReply {
|
|
n := int(req.GetLines())
|
|
if n <= 0 {
|
|
n = 200
|
|
}
|
|
n = min(n, agentLogLines)
|
|
shards := a.sup.IDs()
|
|
slices.Sort(shards)
|
|
out := &llmgwv1.LogsReply{
|
|
RequestId: req.GetRequestId(),
|
|
Sources: append([]string{"agent"}, shards...),
|
|
}
|
|
switch src := req.GetSource(); src {
|
|
case "", "agent":
|
|
out.Lines = a.logRing.tail(n)
|
|
default:
|
|
sh, err := a.sup.Get(src)
|
|
if err != nil {
|
|
out.Error = "no engine " + src + " runs on this node"
|
|
return out
|
|
}
|
|
out.Lines = sh.Logs(n)
|
|
}
|
|
return out
|
|
}
|