sendnrw/netbird
2
0
Fork 0
mirror of https://github.com/netbirdio/netbird.git synced 2026-08-28 10:31:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge main into embedded-vnc

Browse Source 
# Conflicts:
#	client/configs/configs.go
This commit is contained in:
Viktor Liu
2026-07-31 21:11:49 +02:00
parent a117c19b0d 0780a806f2
commit 86d775fbc2
82 changed files with 4993 additions and 1689 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
shared/llm/model.go Normal file
View File

@@ -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
}

36
shared/llm/model_test.go Normal file
View File

@@ -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)
}
}

37
shared/management/http/api/openapi.yml
View File

@@ -5284,6 +5284,21 @@ components:
format: double
description: Cost per 1k output tokens, in USD.
example: 0.0006
cached_input_per_1k:
type: number
format: double
description: OpenAI-shape cache rate — cost per 1k cached prompt tokens (a subset of input tokens), in USD. Omitted means inherit NetBird's default rate for this model when one exists; 0 means no discount (cached tokens bill at input_per_1k).
example: 0.000075
cache_read_per_1k:
type: number
format: double
description: Anthropic-shape cache rate — cost per 1k cache-read tokens (additive to input tokens), in USD. Omitted means inherit NetBird's default rate for this model when one exists; 0 means cache reads bill at input_per_1k.
example: 0.0003
cache_creation_per_1k:
type: number
format: double
description: Anthropic-shape cache rate — cost per 1k cache-creation tokens (additive to input tokens), in USD. Omitted means inherit NetBird's default rate for this model when one exists; 0 means cache writes bill at input_per_1k.
example: 0.00375
required:
- id
- input_per_1k
@@ -5309,6 +5324,21 @@ components:
format: double
description: Output token price per 1k tokens, in USD.
example: 0.015
cached_input_per_1k:
type: number
format: double
description: OpenAI-shape cache rate — default cost per 1k cached prompt tokens (a subset of input tokens), in USD. Absent when the model has no cached-input discount.
example: 0.000075
cache_read_per_1k:
type: number
format: double
description: Anthropic-shape cache rate — default cost per 1k cache-read tokens (additive to input tokens), in USD. Absent when the model has no cache-read rate.
example: 0.0003
cache_creation_per_1k:
type: number
format: double
description: Anthropic-shape cache rate — default cost per 1k cache-creation tokens (additive to input tokens), in USD. Absent when the model has no cache-creation rate.
example: 0.00375
context_window:
type: integer
description: Maximum context window in tokens.
@@ -5367,6 +5397,13 @@ components:
$ref: '#/components/schemas/AgentNetworkCatalogExtraHeader'
identity_injection:
$ref: '#/components/schemas/AgentNetworkCatalogIdentityInjection'
pricing_surfaces:
type: array
description: |
Cost-meter pricing surfaces this provider's traffic is metered under ("openai", "anthropic", "bedrock"). Tells the dashboard which cache-rate fields apply to this provider's models: "openai" → cached_input_per_1k (cached prompt tokens are a subset of input); "anthropic"/"bedrock" → cache_read_per_1k + cache_creation_per_1k (additive buckets). Absent/empty for gateway and custom entries, whose upstream shape NetBird cannot know ahead of time — surface all cache fields for those.
items:
type: string
example: ["openai"]
models:
type: array
description: Catalog models available for this provider.

21
shared/management/http/api/types.gen.go
View File

@@ -2017,6 +2017,15 @@ type AgentNetworkCatalogJSONMetadataInjection struct {
// AgentNetworkCatalogModel defines model for AgentNetworkCatalogModel.
type AgentNetworkCatalogModel struct {
// CacheCreationPer1k Anthropic-shape cache rate — default cost per 1k cache-creation tokens (additive to input tokens), in USD. Absent when the model has no cache-creation rate.
CacheCreationPer1k *float64 `json:"cache_creation_per_1k,omitempty"`
// CacheReadPer1k Anthropic-shape cache rate — default cost per 1k cache-read tokens (additive to input tokens), in USD. Absent when the model has no cache-read rate.
CacheReadPer1k *float64 `json:"cache_read_per_1k,omitempty"`
// CachedInputPer1k OpenAI-shape cache rate — default cost per 1k cached prompt tokens (a subset of input tokens), in USD. Absent when the model has no cached-input discount.
CachedInputPer1k *float64 `json:"cached_input_per_1k,omitempty"`
// ContextWindow Maximum context window in tokens.
ContextWindow int `json:"context_window"`
@@ -2070,6 +2079,9 @@ type AgentNetworkCatalogProvider struct {
// Name Display name for the provider.
Name string `json:"name"`
// PricingSurfaces Cost-meter pricing surfaces this provider's traffic is metered under ("openai", "anthropic", "bedrock"). Tells the dashboard which cache-rate fields apply to this provider's models: "openai" → cached_input_per_1k (cached prompt tokens are a subset of input); "anthropic"/"bedrock" → cache_read_per_1k + cache_creation_per_1k (additive buckets). Absent/empty for gateway and custom entries, whose upstream shape NetBird cannot know ahead of time — surface all cache fields for those.
PricingSurfaces *[]string `json:"pricing_surfaces,omitempty"`
}
// AgentNetworkCatalogProviderKind Presentation grouping for the provider Select on the dashboard.
@@ -2293,6 +2305,15 @@ type AgentNetworkProvider struct {
// AgentNetworkProviderModel A model exposed by the provider, with the operator's per-1k input/output prices in USD.
type AgentNetworkProviderModel struct {
// CacheCreationPer1k Anthropic-shape cache rate — cost per 1k cache-creation tokens (additive to input tokens), in USD. Omitted means inherit NetBird's default rate for this model when one exists; 0 means cache writes bill at input_per_1k.
CacheCreationPer1k *float64 `json:"cache_creation_per_1k,omitempty"`
// CacheReadPer1k Anthropic-shape cache rate — cost per 1k cache-read tokens (additive to input tokens), in USD. Omitted means inherit NetBird's default rate for this model when one exists; 0 means cache reads bill at input_per_1k.
CacheReadPer1k *float64 `json:"cache_read_per_1k,omitempty"`
// CachedInputPer1k OpenAI-shape cache rate — cost per 1k cached prompt tokens (a subset of input tokens), in USD. Omitted means inherit NetBird's default rate for this model when one exists; 0 means no discount (cached tokens bill at input_per_1k).
CachedInputPer1k *float64 `json:"cached_input_per_1k,omitempty"`
// Id Model identifier (e.g. "gpt-4o-mini").
Id string `json:"id"`