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

shared/llm/model.go

@@ -0,0 +1,58 @@
+// Package llm holds LLM model-identifier helpers shared by the proxy and
+// the management server. The proxy normalizes model ids parsed off inbound
+// requests; management normalizes the operator's registered model ids at
+// synthesis time so both sides of the pricing / routing contract compare
+// equal.
+package llm
+
+import (
+	"regexp"
+	"strings"
+)
+
+// bedrockRegionPrefixes are the cross-region inference-profile prefixes that
+// front a Bedrock model id (e.g. "eu.anthropic.claude-...").
+var bedrockRegionPrefixes = []string{"us.", "eu.", "apac.", "global."}
+
+// bedrockVersionSuffix matches the trailing "-vN[:N]" or "-YYYYMMDD-vN[:N]"
+// version/throughput suffix of a Bedrock model id.
+var bedrockVersionSuffix = regexp.MustCompile(`-(\d{8}-)?v\d+(:\d+)?$`)
+
+// NormalizeBedrockModel strips an ARN wrapper, a cross-region inference-profile
+// prefix, and the version/throughput suffix from a Bedrock model id so it
+// matches the catalog/pricing key, e.g.
+// "eu.anthropic.claude-sonnet-4-5-20250929-v1:0" -> "anthropic.claude-sonnet-4-5"
+// and the inference-profile ARN's last segment likewise. It is the single
+// source of truth shared by the proxy's request parser (which normalizes the
+// request model from the URL path), the proxy's router (which normalizes the
+// operator's registered Bedrock model ids so both sides compare equal), and
+// the management synthesizer (which keys per-provider pricing entries by the
+// normalized id the parser will emit at billing time).
+func NormalizeBedrockModel(modelID string) string {
+	m := modelID
+	// A full ARN (inference-profile / provisioned-throughput / foundation-model)
+	// carries the model id in its last path segment.
+	if strings.HasPrefix(m, "arn:") {
+		if i := strings.LastIndex(m, "/"); i >= 0 {
+			m = m[i+1:]
+		}
+	}
+	for _, p := range bedrockRegionPrefixes {
+		if strings.HasPrefix(m, p) {
+			m = m[len(p):]
+			break
+		}
+	}
+	return bedrockVersionSuffix.ReplaceAllString(m, "")
+}
+
+// NormalizeVertexModel strips the "@version" suffix from a Vertex AI model id
+// (e.g. "claude-sonnet-4-5@20250929" -> "claude-sonnet-4-5") so it matches
+// the catalog/pricing key. Vertex publisher models are priced under their
+// vendor surface with the bare, unversioned id.
+func NormalizeVertexModel(modelID string) string {
+	if at := strings.Index(modelID, "@"); at >= 0 {
+		return modelID[:at]
+	}
+	return modelID
+}

shared/llm/model_test.go

@@ -0,0 +1,36 @@
+package llm
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestNormalizeBedrockModel(t *testing.T) {
+	cases := map[string]string{
+		"eu.anthropic.claude-sonnet-4-5-20250929-v1:0": "anthropic.claude-sonnet-4-5",
+		"us.anthropic.claude-haiku-4-5":                "anthropic.claude-haiku-4-5",
+		"us.anthropic.claude-opus-4-8-20250101-v1:0":   "anthropic.claude-opus-4-8",
+		"apac.anthropic.claude-haiku-4-5-v1:0":         "anthropic.claude-haiku-4-5",
+		"amazon.nova-2-lite-v1:0":                      "amazon.nova-2-lite",
+		"anthropic.claude-sonnet-4-5-20250929-v1:0":    "anthropic.claude-sonnet-4-5",
+		"meta.llama3-3-70b-instruct-v1:0":              "meta.llama3-3-70b-instruct",
+		"amazon.nova-pro-v1:0":                         "amazon.nova-pro",
+		// Inference-profile ARN — model id lives in the last path segment.
+		"arn:aws:bedrock:eu-central-1:123456789012:inference-profile/eu.anthropic.claude-sonnet-4-5-20250929-v1:0": "anthropic.claude-sonnet-4-5",
+	}
+	for in, want := range cases {
+		require.Equal(t, want, NormalizeBedrockModel(in), "normalize %q", in)
+	}
+}
+
+func TestNormalizeVertexModel(t *testing.T) {
+	cases := map[string]string{
+		"claude-sonnet-4-5@20250929": "claude-sonnet-4-5",
+		"claude-haiku-4-5":           "claude-haiku-4-5",
+		"gpt-4o@2024-08-06":          "gpt-4o",
+	}
+	for in, want := range cases {
+		require.Equal(t, want, NormalizeVertexModel(in), "normalize %q", in)
+	}
+}