mirror of
https://github.com/lukaszraczylo/traefik-llmgateway.git
synced 2026-10-14 05:18:54 +00:00
lukaszraczylo
e91f0e36ff
1. refreshProvider (the plugin's only background goroutine) had no recover(): a panicking adapter's listModels would crash the whole Traefik process. Restructured around deferred recover + finishRefresh, so a panic is turned into a logged error, inFlight always releases, and the next interval retries. Documented as a scoped exception to limits.go's no-background-goroutine rule. 2. newGateway wrapped ctx in an outer 5s WithTimeout before warmFill, but warmFill already derives a fresh 5s budget per provider from whatever ctx it receives. The outer wrap made that a single budget shared across every discovery-enabled provider instead of a per-provider one - providers after the first could get a near-expired context and fail instantly. Dropped the outer wrapper; construction's worst case is now N * 5s, accepted. 3. group.allowsModel stripped at any first slash, so a glob like 'deepseek-*' could spuriously match a bare model id that merely contains a slash (e.g. an upstream's own 'uni/deepseek-v4-flash-0731' naming) even though the leading segment names no configured provider. allowsModel is now an exact glob with no internal splitting; resolveAgainst and listFor generate the provider-prefixed and bare-suffix candidates themselves, only when a prefix legitimately names a configured provider. Updated the Task-3 TestIdentify assertion to match. 4. Annotated the discarded json.Encode error in handleModels. Gate: go test ./... -count=1, -race, gofmt, vet, fieldalignment, golangci-lint (incl gosec) all clean.
24 lines
733 B
Go
24 lines
733 B
Go
package traefikllmgateway
|
|
|
|
import (
|
|
"encoding/json"
|
|
"net/http"
|
|
)
|
|
|
|
// handleModels implements GET /v1/models: an authenticated caller gets back
|
|
// an OpenAI-compatible {"object":"list","data":[...]} envelope of the
|
|
// models their group can see, via modelRegistry.listFor.
|
|
func (g *Gateway) handleModels(w http.ResponseWriter, r *http.Request) {
|
|
_, grp, ok := g.auth.identify(r)
|
|
if !ok {
|
|
writeOAIError(w, http.StatusUnauthorized, "authentication_error", "invalid or missing API key")
|
|
return
|
|
}
|
|
|
|
w.Header().Set("Content-Type", "application/json")
|
|
_ = json.NewEncoder(w).Encode(map[string]any{ // headers already committed; nothing useful to do on encode failure
|
|
"object": "list",
|
|
"data": g.registry.listFor(grp),
|
|
})
|
|
}
|