proxy: implement setParamsByID filter (#535)
Add setParamsByID filter that applies different request parameters based
on the requested model ID, enabling per-alias behaviour for a single
loaded model.
- add SetParamsByID field to Filters struct and SanitizedSetParamsByID
method
- substitute ${MODEL_ID} and other macros in setParamsByID keys and
values
- validate no unknown macros remain in keys or values after substitution
- apply setParamsByID in proxyInferenceHandler after setParams (can
override it)
- update config-schema.json with setParamsByID definition
- update UI to show aliases and make them selectable in the Playground
closes #534
This commit is contained in:
@@ -1046,6 +1046,61 @@ func TestProxyManager_FiltersStripParams(t *testing.T) {
|
||||
// t.Logf("%v", response)
|
||||
}
|
||||
|
||||
func TestProxyManager_FiltersSetParamsByID(t *testing.T) {
|
||||
// no explicit aliases — setParamsByID keys are auto-registered as aliases
|
||||
configStr := strings.Replace(`
|
||||
logLevel: error
|
||||
models:
|
||||
model1:
|
||||
cmd: 'SRPATH --port ${PORT} --silent --respond model1'
|
||||
proxy: "http://127.0.0.1:${PORT}"
|
||||
filters:
|
||||
setParams:
|
||||
reasoning_effort: medium
|
||||
setParamsByID:
|
||||
"${MODEL_ID}:high":
|
||||
reasoning_effort: high
|
||||
"${MODEL_ID}:low":
|
||||
reasoning_effort: low
|
||||
`, "SRPATH", simpleResponderPath, -1)
|
||||
|
||||
cfg, err := config.LoadConfigFromReader(strings.NewReader(configStr))
|
||||
if !assert.NoError(t, err, "invalid test configuration") {
|
||||
return
|
||||
}
|
||||
|
||||
proxy := New(cfg)
|
||||
defer proxy.StopProcesses(StopWaitForInflightRequest)
|
||||
|
||||
tests := []struct {
|
||||
requestedModel string
|
||||
wantEffort string
|
||||
}{
|
||||
// setParams applies, no setParamsByID match
|
||||
{requestedModel: "model1", wantEffort: "medium"},
|
||||
// setParamsByID overrides setParams
|
||||
{requestedModel: "model1:high", wantEffort: "high"},
|
||||
{requestedModel: "model1:low", wantEffort: "low"},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.requestedModel, func(t *testing.T) {
|
||||
reqBody := fmt.Sprintf(`{"model":%q}`, tt.requestedModel)
|
||||
req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
|
||||
w := CreateTestResponseRecorder()
|
||||
proxy.ServeHTTP(w, req)
|
||||
assert.Equal(t, http.StatusOK, w.Code)
|
||||
|
||||
var response map[string]interface{}
|
||||
assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
|
||||
|
||||
requestBody, _ := response["request_body"].(string)
|
||||
gotEffort := gjson.Get(requestBody, "reasoning_effort").String()
|
||||
assert.Equal(t, tt.wantEffort, gotEffort, "reasoning_effort mismatch for model %s", tt.requestedModel)
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestProxyManager_HealthEndpoint(t *testing.T) {
|
||||
config := config.AddDefaultGroupToConfig(config.Config{
|
||||
HealthCheckTimeout: 15,
|
||||
|
||||
Reference in New Issue
Block a user