[management, proxy] Management-owned LLM pricing: file-backed defaults + (#6965)

management/internals/modules/agentnetwork/handlers/providers_handler.go

@@ -7,6 +7,7 @@ package handlers
 
 import (
 	"encoding/json"
+	"math"
 	"net/http"
 	"net/url"
 	"strings"
@@ -15,6 +16,7 @@ import (
 
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/catalog"
+	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/pricing"
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
 	nbcontext "github.com/netbirdio/netbird/management/server/context"
 	"github.com/netbirdio/netbird/shared/management/http/api"
@@ -52,11 +54,45 @@ func (h *handler) getCatalogProviders(w http.ResponseWriter, r *http.Request) {
 	entries := catalog.All()
 	out := make([]api.AgentNetworkCatalogProvider, 0, len(entries))
 	for _, e := range entries {
-		out = append(out, e.ToAPIResponse())
+		resp := e.ToAPIResponse()
+		applyDefaultPricing(e, &resp)
+		out = append(out, resp)
 	}
 	util.WriteJSONObject(r.Context(), w, out)
 }
 
+// applyDefaultPricing overwrites the catalog response's model rates with
+// the LIVE default pricing table, which may differ from the compiled-in
+// catalog rates when the operator provides a defaults_llm_pricing.yaml.
+// This keeps the dashboard's model-row prefill identical to what the
+// proxy will actually bill — the same table the synthesizer ships.
+func applyDefaultPricing(cp catalog.Provider, resp *api.AgentNetworkCatalogProvider) {
+	if len(cp.PricingSurfaces) == 0 {
+		return
+	}
+	for i := range resp.Models {
+		m := &resp.Models[i]
+		e, ok := pricing.LookupDefault(cp.PricingSurfaces, m.Id)
+		if !ok {
+			continue
+		}
+		m.InputPer1k = e.InputPer1k
+		m.OutputPer1k = e.OutputPer1k
+		m.CachedInputPer1k = positiveRatePtr(e.CachedInputPer1k)
+		m.CacheReadPer1k = positiveRatePtr(e.CacheReadPer1k)
+		m.CacheCreationPer1k = positiveRatePtr(e.CacheCreationPer1k)
+	}
+}
+
+// positiveRatePtr renders a cache rate for the API: absent (nil) when
+// unset, matching the catalog response convention.
+func positiveRatePtr(v float64) *float64 {
+	if v <= 0 {
+		return nil
+	}
+	return &v
+}
+
 func (h *handler) getAllProviders(w http.ResponseWriter, r *http.Request) {
 	userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
 	if err != nil {
@@ -213,5 +249,38 @@ func validate(req *api.AgentNetworkProviderRequest, requireAPIKey bool) error {
 	if requireAPIKey && (req.ApiKey == nil || strings.TrimSpace(*req.ApiKey) == "") {
 		return status.Errorf(status.InvalidArgument, "api_key is required")
 	}
+	if req.Models != nil {
+		for i, m := range *req.Models {
+			if err := validateModel(i, m); err != nil {
+				return err
+			}
+		}
+	}
+	return nil
+}
+
+// validateModel is the single ingress guard for operator-entered pricing:
+// these rates are synthesized into the proxy's cost_meter config verbatim,
+// and a negative or non-finite rate there would poison every cost the
+// proxy records, so reject at the API boundary.
+func validateModel(i int, m api.AgentNetworkProviderModel) error {
+	if strings.TrimSpace(m.Id) == "" {
+		return status.Errorf(status.InvalidArgument, "models[%d]: id is required", i)
+	}
+	rates := map[string]*float64{
+		"input_per_1k":          &m.InputPer1k,
+		"output_per_1k":         &m.OutputPer1k,
+		"cached_input_per_1k":   m.CachedInputPer1k,
+		"cache_read_per_1k":     m.CacheReadPer1k,
+		"cache_creation_per_1k": m.CacheCreationPer1k,
+	}
+	for field, v := range rates {
+		if v == nil {
+			continue
+		}
+		if *v < 0 || math.IsNaN(*v) || math.IsInf(*v, 0) {
+			return status.Errorf(status.InvalidArgument, "models[%d] (%s): %s must be a finite, non-negative USD rate", i, m.Id, field)
+		}
+	}
 	return nil
 }

management/internals/modules/agentnetwork/handlers/providers_handler_test.go

@@ -0,0 +1,53 @@
+package handlers
+
+import (
+	"math"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/shared/management/http/api"
+)
+
+func f(v float64) *float64 { return &v }
+
+// TestValidate_ModelRates guards the single ingress point for operator-entered
+// pricing. These rates flow verbatim into the proxy's cost_meter config at
+// synthesis time; the proxy treats a bad rate as a chain-build failure, so
+// rejecting here is what keeps an account's gateway from going down.
+func TestValidate_ModelRates(t *testing.T) {
+	base := func(models ...api.AgentNetworkProviderModel) *api.AgentNetworkProviderRequest {
+		key := "sk-test"
+		return &api.AgentNetworkProviderRequest{
+			ProviderId:  "openai_api",
+			Name:        "OpenAI",
+			UpstreamUrl: "https://api.openai.com",
+			ApiKey:      &key,
+			Models:      &models,
+		}
+	}
+
+	valid := api.AgentNetworkProviderModel{
+		Id: "gpt-4o", InputPer1k: 0.0025, OutputPer1k: 0.01,
+		CachedInputPer1k: f(0.00125),
+	}
+	require.NoError(t, validate(base(valid), true), "finite non-negative rates must pass")
+
+	zeroRates := api.AgentNetworkProviderModel{Id: "self-hosted-llama", InputPer1k: 0, OutputPer1k: 0}
+	require.NoError(t, validate(base(zeroRates), true), "explicit zero prices are allowed (free / self-hosted models)")
+
+	cases := map[string]api.AgentNetworkProviderModel{
+		"empty id":           {Id: "  ", InputPer1k: 0.001, OutputPer1k: 0.002},
+		"negative input":     {Id: "m", InputPer1k: -0.001, OutputPer1k: 0.002},
+		"negative output":    {Id: "m", InputPer1k: 0.001, OutputPer1k: -0.002},
+		"NaN input":          {Id: "m", InputPer1k: math.NaN(), OutputPer1k: 0.002},
+		"Inf output":         {Id: "m", InputPer1k: 0.001, OutputPer1k: math.Inf(1)},
+		"negative cached":    {Id: "m", InputPer1k: 0.001, OutputPer1k: 0.002, CachedInputPer1k: f(-1)},
+		"NaN cache read":     {Id: "m", InputPer1k: 0.001, OutputPer1k: 0.002, CacheReadPer1k: f(math.NaN())},
+		"Inf cache creation": {Id: "m", InputPer1k: 0.001, OutputPer1k: 0.002, CacheCreationPer1k: f(math.Inf(-1))},
+	}
+	for name, m := range cases {
+		assert.Error(t, validate(base(m), true), "case %q must be rejected", name)
+	}
+}