sendnrw/netbird
2
0
Fork 0
mirror of https://github.com/netbirdio/netbird.git synced 2026-10-03 20:19:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

[proxy,management] Conform the Agent Network endpoint to the LLM gateway protocol (#7154)

Browse Source 
[proxy,management] Conform the Agent Network endpoint to the LLM gateway protocol

Reviewed the proxy against Claude Code's published gateway contract. The
transport layer already held up; fourteen gaps sat one layer up, in the model
catalog and in the non-inference endpoints clients call.

Two of them cost money. The catalog carried no claude-opus-5 or
claude-sonnet-5, so an operator could not authorise the models coding agents
default to — those requests denied as not-routable, or priced at zero where a
catch-all carried them. And gateway records pin ParserID "openai" while the
same record serves /v1/messages, so Anthropic responses were read with the
OpenAI parser, which never looks at message_start where input tokens live:
input metered as roughly zero on every stream and cost was skipped entirely.

The rest fix requests refused for structural rather than policy reasons: model
discovery denied for every account with a model allowlist, token counting
denied on Bedrock and mis-parsed on Vertex, startup probes refused and written
into the access log at every session start, and denials rendered in a shape no
LLM client parses. Two changes are additive by design — the deny body keeps
every field it had and adds the vendor's error object alongside, and body-level
identity injection is now gated on the request's dialect so it stops sending
OpenAI-shape fields into Anthropic bodies that reject them.

The end-to-end work turned up one more: the discovery filter treated any slash
in a model id as a gateway prefix, which would have dropped every self-hosted
"Qwen/..." model from the picker.
This commit is contained in:
Maycon Santos
2026-08-23 20:02:33 +02:00
committed by GitHub
parent ee253feddf
commit 766fcae3f8
39 changed files with 3094 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files
management/internals/modules/agentnetwork/catalog/catalog.go
+6
View File
@@ -296,6 +296,8 @@ var providers = []Provider{
// account to be on >= 30-day data retention or all requests
// 400.
Models: []Model{
{ID: "claude-opus-5", Label: "Claude Opus 5", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "claude-sonnet-5", Label: "Claude Sonnet 5", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000},
{ID: "claude-fable-5", Label: "Claude Fable 5", InputPer1k: 0.010, OutputPer1k: 0.050, CacheReadPer1k: 0.001, CacheCreationPer1k: 0.0125, ContextWindow: 1000000},
{ID: "claude-opus-4-8", Label: "Claude Opus 4.8", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "claude-opus-4-7", Label: "Claude Opus 4.7", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
@@ -355,6 +357,8 @@ var providers = []Provider{
// Llama 3.3 70B entry kept unchanged — LiteLLM tracks only
// per-region Llama 3 entries; standalone 3.3 not yet listed.
Models: []Model{
{ID: "anthropic.claude-opus-5", Label: "Claude Opus 5 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "anthropic.claude-sonnet-5", Label: "Claude Sonnet 5 (Bedrock)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000},
{ID: "anthropic.claude-opus-4-8", Label: "Claude Opus 4.8 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "anthropic.claude-opus-4-7", Label: "Claude Opus 4.7 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "anthropic.claude-opus-4-6", Label: "Claude Opus 4.6 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
@@ -406,6 +410,8 @@ var providers = []Provider{
// exists — the router denies unmeterable publishers rather than forward
// them uncounted.
Models: []Model{
{ID: "claude-opus-5", Label: "Claude Opus 5 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "claude-sonnet-5", Label: "Claude Sonnet 5 (Vertex)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000},
{ID: "claude-fable-5", Label: "Claude Fable 5 (Vertex)", InputPer1k: 0.010, OutputPer1k: 0.050, CacheReadPer1k: 0.001, CacheCreationPer1k: 0.0125, ContextWindow: 1000000},
{ID: "claude-opus-4-8", Label: "Claude Opus 4.8 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "claude-opus-4-7", Label: "Claude Opus 4.7 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
management/internals/modules/agentnetwork/catalog/catalog_test.go
+36
View File
@@ -0,0 +1,36 @@
package catalog
import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// TestClaudeLineupSelectable pins the models Claude Code resolves to by
// default. A model absent from the lineup can't be ticked on a provider
// record, so llm_router denies it as not-routable and the operator has no
// way to authorise the client's own default.
func TestClaudeLineupSelectable(t *testing.T) {
for providerID, wanted := range map[string][]string{
"anthropic_api": {"claude-opus-5", "claude-sonnet-5", "claude-haiku-4-5"},
"bedrock_api": {"anthropic.claude-opus-5", "anthropic.claude-sonnet-5", "anthropic.claude-haiku-4-5"},
"vertex_ai_api": {"claude-opus-5", "claude-sonnet-5", "claude-haiku-4-5"},
} {
provider, ok := Lookup(providerID)
require.True(t, ok, "catalog must define %s", providerID)
selectable := make(map[string]Model, len(provider.Models))
for _, m := range provider.Models {
selectable[m.ID] = m
}
for _, id := range wanted {
model, found := selectable[id]
require.True(t, found, "%s must offer %s", providerID, id)
assert.NotEmpty(t, model.Label, "%s/%s needs a label for the picker", providerID, id)
assert.Positive(t, model.InputPer1k, "%s/%s needs an input rate", providerID, id)
assert.Positive(t, model.OutputPer1k, "%s/%s needs an output rate", providerID, id)
assert.Positive(t, model.ContextWindow, "%s/%s needs a context window", providerID, id)
}
}
}
management/internals/modules/agentnetwork/pricing/defaults.go
-6
View File
@@ -47,17 +47,11 @@ var supplementalDefaults = map[string]map[string]Entry{
"gpt-5-nano": {InputPer1k: 0.00005, OutputPer1k: 0.0004, CachedInputPer1k: 0.000005},
},
"anthropic": {
// claude-opus-5 is not yet in the catalog lineup but gateway /
// grandfathered traffic uses it; priced so it isn't skipped.
"claude-opus-5": {InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625},
// "kimi-k3[1m]" is the 1M-context alias some Claude Code guides
// configure against Moonshot's Anthropic-compatible endpoint;
// priced identically to kimi-k3 so those requests aren't skipped.
"kimi-k3[1m]": {InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003},
},
"bedrock": {
"anthropic.claude-opus-5": {InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625},
},
}
var (
management/internals/modules/agentnetwork/pricing/defaults_llm_pricing.example.yaml
+10
View File
@@ -82,6 +82,11 @@ anthropic:
output_per_1k: 0.015
cache_read_per_1k: 0.0003
cache_creation_per_1k: 0.00375
claude-sonnet-5:
input_per_1k: 0.003
output_per_1k: 0.015
cache_read_per_1k: 0.0003
cache_creation_per_1k: 0.00375
kimi-k3:
input_per_1k: 0.003
output_per_1k: 0.015
@@ -145,6 +150,11 @@ bedrock:
output_per_1k: 0.015
cache_read_per_1k: 0.0003
cache_creation_per_1k: 0.00375
anthropic.claude-sonnet-5:
input_per_1k: 0.003
output_per_1k: 0.015
cache_read_per_1k: 0.0003
cache_creation_per_1k: 0.00375
meta.llama3-3-70b-instruct:
input_per_1k: 0.00072
output_per_1k: 0.00072
management/internals/modules/agentnetwork/pricing/defaults_test.go
+5 -3
View File
@@ -116,11 +116,13 @@ func TestDefaultTable_PinnedRates(t *testing.T) {
assert.InDelta(t, 0.010, fable.InputPer1k, 1e-9, "claude-fable-5 input")
assert.InDelta(t, 0.0125, fable.CacheCreationPer1k, 1e-9, "claude-fable-5 cache creation")
// Supplementals present on their surfaces.
// Every id below must stay priced whichever source provides it: the
// catalog lineup for the current Claude 5 family, supplementalDefaults
// for the ids the dashboard deliberately doesn't offer.
for surface, ids := range map[string][]string{
"openai": {"gpt-5", "gpt-5-mini", "gpt-5-nano"},
"anthropic": {"claude-opus-5", "kimi-k3[1m]", "kimi-k3"},
"bedrock": {"anthropic.claude-opus-5"},
"anthropic": {"claude-opus-5", "claude-sonnet-5", "kimi-k3[1m]", "kimi-k3"},
"bedrock": {"anthropic.claude-opus-5", "anthropic.claude-sonnet-5"},
} {
for _, id := range ids {
_, ok := table[surface][id]