riotpiao-poimen/homelab-frontend
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add TTFT & ITL Metrics for LLM Inference (#28)
CI / CI (push) Successful in 4m7s
Details

Browse Source 
Time-to-First-Token (TTFT) and Inter-Token Latency (ITL) metrics for LLM inference observability

Metrics: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total

Closes #31 #32 #33

---------

Co-authored-by: poimen <[email protected]>
Reviewed-on: #28
This commit was merged in pull request #28.
This commit is contained in:
rock
2026-09-15 08:53:58 +00:00
co-authored by poimen
parent 30e0a83a50
commit d439536ca9
22 changed files with 2224 additions and 199 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/gateway/main.go
+29 -4
View File
@@ -11,6 +11,7 @@ import (
"forgejo.riotpiao.com/rock/homelab-frontend/internal/auth"
"forgejo.riotpiao.com/rock/homelab-frontend/internal/config"
"forgejo.riotpiao.com/rock/homelab-frontend/internal/notification"
"forgejo.riotpiao.com/rock/homelab-frontend/internal/proxy"
"forgejo.riotpiao.com/rock/homelab-frontend/internal/server"
"forgejo.riotpiao.com/rock/homelab-frontend/internal/serviceadapter"
@@ -75,13 +76,38 @@ func main() {
// Add workflow service adapter (uses Temporal handler for gRPC forwarding)
workflowSpec := serviceadapter.GetWorkflowSpec()
workflowAdapterHandler := serviceadapter.NewWorkflowAdapter(temporalHandler)
workflowAdapter := &serviceadapter.ServiceAdapter{
Namespace: "api",
Namespace: "temporal",
ServiceName: "workflow",
Handler: workflowAdapterHandler,
Spec: *workflowSpec,
}
_ = registry.Add(workflowAdapter)
// Add notification service adapter (internal handler, no upstream proxy)
notifHandler := notification.NewHandler()
notifAdapter := &serviceadapter.ServiceAdapter{
Namespace: "notification",
ServiceName: "notification",
Handler: notifHandler,
Spec: serviceadapter.Spec{
ServiceName: "notification",
Auth: serviceadapter.Auth{Required: true},
Resources: []serviceadapter.Resource{
{Name: "send-email", Methods: []serviceadapter.Method{{Verb: "POST", UpstreamPath: "/send-email"}}},
{Name: "send-message", Methods: []serviceadapter.Method{{Verb: "POST", UpstreamPath: "/send-message"}}},
{Name: "list-messages", Methods: []serviceadapter.Method{{Verb: "GET", UpstreamPath: "/list-messages"}}},
{Name: "delete-message", Methods: []serviceadapter.Method{{Verb: "DELETE", UpstreamPath: "/delete-message"}}},
{Name: "delete-all-messages", Methods: []serviceadapter.Method{{Verb: "DELETE", UpstreamPath: "/delete-all-messages"}}},
{Name: "list-applications", Methods: []serviceadapter.Method{{Verb: "GET", UpstreamPath: "/list-applications"}}},
{Name: "create-application", Methods: []serviceadapter.Method{{Verb: "POST", UpstreamPath: "/create-application"}}},
{Name: "delete-application", Methods: []serviceadapter.Method{{Verb: "DELETE", UpstreamPath: "/delete-application"}}},
},
},
}
_ = registry.Add(notifAdapter)
// Add other adapters from config
for _, a := range cfg.Adapters {
_ = registry.Add(a)
@@ -96,8 +122,7 @@ func main() {
dispatcher := serviceadapter.NewDispatcher(registry, jwtValidator)
// Wire workflow adapter to temporal handler for proper request forwarding
workflowAdapterImpl := serviceadapter.NewWorkflowAdapter(temporalHandler)
_ = workflowAdapterImpl // The dispatcher will call temporal handler directly for gRPC
// workflowAdapterHandler (above) handles JSON-to-gRPC translation for workflow service
// Create router that handles health endpoints, X-Service (ServiceAdapter) routing,
// temporal endpoints, and passes others to upstream handler