feat(gateway): dispatch /v1/systemone by model
Clef-flash is a decision model, not a chat model. It serves Clef's own System One / Jev API at /v1/systemone: a state plus a schema of typed questions in, one probability per allowed option out, single prefill pass, no decoding and no free-form text. Router previously dispatched by body `model` only for /v1/chat/completions, /v1/embeddings and /v1/rerank. A request to /v1/systemone therefore fell through to the configured routes, found none, and answered "no routes configured". Adding the path to the dispatch predicate is the whole fix: routeByModel already sets upstreamPath := path, so the upstream receives /v1/systemone unchanged. There is deliberately no /rerank-style rewrite. Config: `ornith:35b` is removed with the Ollama predictor, and its GPU now serves clef-flash. `qwen2.5:3b-instruct` already pointed at qwen-cpu and is unchanged. Callers of ornith:35b must move to `reasoning`, which keeps its serving name while running Qwen3-30B-A3B. Tests cover body dispatch, unknown_model parity with the other three paths, and that the upstream path is not rewritten.
This commit is contained in:
@@ -13,11 +13,14 @@ import (
|
||||
)
|
||||
|
||||
// RouteRequest determines which upstream should handle the request.
|
||||
// For /v1/chat/completions, /v1/embeddings, and /v1/rerank, it uses body-based dispatch.
|
||||
// For /v1/chat/completions, /v1/embeddings, /v1/rerank and /v1/systemone, it
|
||||
// uses body-based dispatch.
|
||||
// For other routes, it looks up by path in the configured routes.
|
||||
func (h *Handler) RouteRequest(r *http.Request) (*Route, error) {
|
||||
// For /v1/chat/completions, /v1/embeddings, /v1/rerank use body-based dispatch
|
||||
if r.Method == "POST" && (r.URL.Path == "/v1/chat/completions" || r.URL.Path == "/v1/embeddings" || r.URL.Path == "/v1/rerank") {
|
||||
// For /v1/chat/completions, /v1/embeddings, /v1/rerank and /v1/systemone use
|
||||
// body-based dispatch. /v1/systemone is Clef's decision API: same
|
||||
// body-based model lookup, different request/response schema.
|
||||
if r.Method == "POST" && (r.URL.Path == "/v1/chat/completions" || r.URL.Path == "/v1/embeddings" || r.URL.Path == "/v1/rerank" || r.URL.Path == "/v1/systemone") {
|
||||
return h.routeByModel(r, r.URL.Path)
|
||||
}
|
||||
|
||||
@@ -46,7 +49,7 @@ func (h *Handler) RouteRequest(r *http.Request) (*Route, error) {
|
||||
// routeByModel reads the request body to find the "model" field and routes accordingly.
|
||||
// The body is preserved for forwarding to the upstream.
|
||||
// Returns a modelValidationError for client errors (invalid JSON, missing/unknown model).
|
||||
// The path parameter indicates which endpoint is being called (/v1/chat/completions, /v1/embeddings, /v1/rerank)
|
||||
// The path parameter indicates which endpoint is being called (/v1/chat/completions, /v1/embeddings, /v1/rerank, /v1/systemone)
|
||||
func (h *Handler) routeByModel(r *http.Request, path string) (*Route, error) {
|
||||
// If there's no body, we can't determine the model
|
||||
if r.Body == nil {
|
||||
|
||||
@@ -0,0 +1,169 @@
|
||||
package proxy
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/http/httptest"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"forgejo.riotpiao.com/rock/homelab-frontend/internal/config"
|
||||
)
|
||||
|
||||
// TestSystemoneRoutesByModel verifies POST /v1/systemone dispatches on the body
|
||||
// "model" field instead of falling through to path-based route lookup. Before
|
||||
// that path joined body dispatch, the request reached the route table and
|
||||
// failed with "no routes configured" when no routes were defined.
|
||||
func TestSystemoneRoutesByModel(t *testing.T) {
|
||||
clefCalled := false
|
||||
clefServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
clefCalled = true
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(http.StatusOK)
|
||||
fmt.Fprint(w, `{"decision":"allow"}`)
|
||||
}))
|
||||
defer clefServer.Close()
|
||||
|
||||
clefAddr := strings.TrimPrefix(clefServer.URL, "http://")
|
||||
|
||||
cfg := &config.Config{
|
||||
Models: map[string]*config.ModelUpstream{
|
||||
"clef-flash": {
|
||||
Name: "clef-flash",
|
||||
Address: clefAddr,
|
||||
},
|
||||
},
|
||||
Routes: make(map[string]*config.Route),
|
||||
}
|
||||
|
||||
handler := New(cfg)
|
||||
defer handler.Close()
|
||||
|
||||
server := httptest.NewServer(handler)
|
||||
defer server.Close()
|
||||
|
||||
resp, err := http.Post(
|
||||
server.URL+"/v1/systemone",
|
||||
"application/json",
|
||||
bytes.NewReader([]byte(`{"model":"clef-flash","state":"x","questions":{}}`)),
|
||||
)
|
||||
if err != nil {
|
||||
t.Fatalf("request failed: %v", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
if !clefCalled {
|
||||
t.Errorf("upstream clef-flash service was not called")
|
||||
}
|
||||
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
t.Errorf("expected 200 for known systemone model, got %d", resp.StatusCode)
|
||||
}
|
||||
|
||||
body, readErr := io.ReadAll(resp.Body)
|
||||
if readErr != nil {
|
||||
t.Fatalf("failed to read response body: %v", readErr)
|
||||
}
|
||||
if strings.Contains(string(body), "no routes configured") {
|
||||
t.Errorf("systemone request fell through to route lookup: %s", string(body))
|
||||
}
|
||||
if !strings.Contains(string(body), `"decision":"allow"`) {
|
||||
t.Errorf("expected upstream response body, got %s", string(body))
|
||||
}
|
||||
}
|
||||
|
||||
// TestSystemoneUnknownModelValidationError verifies an unknown model on
|
||||
// /v1/systemone returns the same modelValidationError kind as the other three
|
||||
// body-dispatched paths.
|
||||
func TestSystemoneUnknownModelValidationError(t *testing.T) {
|
||||
cfg := &config.Config{
|
||||
Models: map[string]*config.ModelUpstream{
|
||||
"clef-flash": {
|
||||
Name: "clef-flash",
|
||||
Address: "localhost:9000",
|
||||
},
|
||||
},
|
||||
Routes: make(map[string]*config.Route),
|
||||
}
|
||||
|
||||
handler := New(cfg)
|
||||
defer handler.Close()
|
||||
|
||||
paths := []string{
|
||||
"/v1/chat/completions",
|
||||
"/v1/embeddings",
|
||||
"/v1/rerank",
|
||||
"/v1/systemone",
|
||||
}
|
||||
for _, path := range paths {
|
||||
req := httptest.NewRequest(
|
||||
"POST",
|
||||
path,
|
||||
strings.NewReader(`{"model":"unknown-model"}`),
|
||||
)
|
||||
route, err := handler.RouteRequest(req)
|
||||
if route != nil {
|
||||
t.Errorf("%s: expected nil route for unknown model", path)
|
||||
}
|
||||
var validationErr *modelValidationError
|
||||
if !errors.As(err, &validationErr) {
|
||||
t.Fatalf("%s: expected modelValidationError, got %v", path, err)
|
||||
}
|
||||
if validationErr.Kind != "unknown_model" {
|
||||
t.Errorf("%s: expected kind unknown_model, got %s", path, validationErr.Kind)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestSystemoneUpstreamPathNotRewritten verifies routeByModel keeps the request
|
||||
// path for /v1/systemone: upstream must see /v1/systemone, not
|
||||
// /v1/chat/completions. /v1/rerank is the only endpoint with a path rewrite.
|
||||
func TestSystemoneUpstreamPathNotRewritten(t *testing.T) {
|
||||
upstreamPath := ""
|
||||
|
||||
upstreamServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
upstreamPath = r.URL.Path
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(http.StatusOK)
|
||||
fmt.Fprint(w, `{"decision":"deny"}`)
|
||||
}))
|
||||
defer upstreamServer.Close()
|
||||
|
||||
upstreamAddr := strings.TrimPrefix(upstreamServer.URL, "http://")
|
||||
|
||||
cfg := &config.Config{
|
||||
Models: map[string]*config.ModelUpstream{
|
||||
"clef-flash": {
|
||||
Name: "clef-flash",
|
||||
Address: upstreamAddr,
|
||||
},
|
||||
},
|
||||
Routes: make(map[string]*config.Route),
|
||||
}
|
||||
|
||||
handler := New(cfg)
|
||||
defer handler.Close()
|
||||
|
||||
server := httptest.NewServer(handler)
|
||||
defer server.Close()
|
||||
|
||||
resp, err := http.Post(
|
||||
server.URL+"/v1/systemone",
|
||||
"application/json",
|
||||
bytes.NewReader([]byte(`{"model":"clef-flash","state":"x","questions":{}}`)),
|
||||
)
|
||||
if err != nil {
|
||||
t.Fatalf("request failed: %v", err)
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
if upstreamPath != "/v1/systemone" {
|
||||
t.Errorf("expected upstream path /v1/systemone, got %s", upstreamPath)
|
||||
}
|
||||
if upstreamPath == "/v1/chat/completions" {
|
||||
t.Errorf("upstream path was rewritten to /v1/chat/completions")
|
||||
}
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user