Standbys that answer the client API themselves, behind router.active_active
CI / test (push) Successful in 9m35s

A standby follows the leader's Ready replicas over the agent port, every
two seconds, and reports back the replicas its router used and the
on-demand models it was asked for. No engine keys travel: every control
plane derives them from the cluster secret. Budgets are raised to the
store's every 30 s. Unheard from the leader for a minute, a standby
passes /v1 on as before. Off by default.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-11-01 13:47:47 +01:00
1 parent f664592948
commit 8b7eefef16
22 files changed
+936 -15

No files matched your search

+27
View File
@@ -0,0 +1,27 @@
package adminapi
import (
"encoding/json"
"io"
"net/http"
"gitea.mynodes.xyz/ilker/llmgw/internal/control"
)
// registerRouting is what a standby answering requests itself reads from the
// leader, and reports back to it. Reached by the standby through the agent
// port with its control-plane certificate, like the rest of the forwarded API.
func (a *API) registerRouting(mux Mux) {
mux.HandleFunc("GET /api/v1/routing", func(w http.ResponseWriter, _ *http.Request) {
writeJSON(w, http.StatusOK, a.ctl.Routing())
})
mux.HandleFunc("POST /api/v1/routing/activity", func(w http.ResponseWriter, r *http.Request) {
var act control.Activity
if err := json.NewDecoder(io.LimitReader(r.Body, 8<<20)).Decode(&act); err != nil {
writeError(w, http.StatusBadRequest, err.Error())
return
}
a.ctl.RecordActivity(act)
writeJSON(w, http.StatusOK, a.ctl.Routing())
})
}