sendnrw/netbird
2
0
Fork 0
mirror of https://github.com/netbirdio/netbird.git synced 2026-09-08 16:01:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Misha Bragin
2026-07-31 20:52:56 +02:00
committed by GitHub
parent feecb993f4
commit 0780a806f2
47 changed files with 3196 additions and 1540 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
proxy/internal/middleware/builtin/llm_request_parser/bedrock_test.go
View File

@@ -6,23 +6,6 @@ import (
"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-opus-4-8-20250101-v1:0": "anthropic.claude-opus-4-8",
"apac.anthropic.claude-haiku-4-5-v1:0": "anthropic.claude-haiku-4-5",
"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",
"amazon.nova-2-lite-v1:0": "amazon.nova-2-lite",
// 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 TestParseBedrockPath(t *testing.T) {
tests := []struct {
path string

39
proxy/internal/middleware/builtin/llm_request_parser/middleware.go
View File

@@ -8,7 +8,6 @@ package llm_request_parser
import (
"context"
"net/url"
"regexp"
"strconv"
"strings"
"unicode/utf8"
@@ -253,9 +252,7 @@ func parseVertexPath(reqPath string) (vertexRequest, bool) {
if c := strings.LastIndex(rest, ":"); c >= 0 {
model, action = rest[:c], rest[c+1:]
}
if at := strings.Index(model, "@"); at >= 0 {
model = model[:at]
}
model = llm.NormalizeVertexModel(model)
if model == "" {
return vertexRequest{}, false
}
@@ -343,14 +340,6 @@ func trimBedrockNamespace(reqPath string) string {
return reqPath
}
// 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+)?$`)
// parseBedrockPath extracts the model and streaming/converse flags from an AWS
// Bedrock runtime model endpoint:
//
@@ -375,7 +364,7 @@ func parseBedrockPath(reqPath string) (bedrockRequest, bool) {
if decoded, err := url.PathUnescape(rawModel); err == nil {
rawModel = decoded
}
model := normalizeBedrockModel(rawModel)
model := llm.NormalizeBedrockModel(rawModel)
if model == "" {
return bedrockRequest{}, false
}
@@ -389,30 +378,6 @@ func parseBedrockPath(reqPath string) (bedrockRequest, bool) {
}
}
// 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 "arn:aws:bedrock:eu-central-1:123:inference-profile/eu.anthropic.claude-sonnet-4-5-20250929-v1:0"
// -> "anthropic.claude-sonnet-4-5".
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, "")
}
// invokeBedrock emits the model/provider/session/prompt for an AWS Bedrock
// request. Bedrock is metered under the dedicated "bedrock" parser, which reads
// both the InvokeModel and Converse response shapes.