sendnrw/netbird
2
0
Fork 0
mirror of https://github.com/netbirdio/netbird.git synced 2026-10-24 14:29:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

merge main

Browse Source
This commit is contained in:
pascal
2026-08-05 13:56:35 +02:00
parent 1926e983fb 6526fc2bec
commit c93aa03c0e
295 changed files with 18571 additions and 4721 deletions
Download Patch File Download Diff File Expand all files Collapse all files
management/cmd/management.go
+24
View File
@@ -23,6 +23,7 @@ import (
"github.com/netbirdio/netbird/management/server/types"
"github.com/netbirdio/netbird/formatter/hook"
agentnetworkpricing "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/pricing"
"github.com/netbirdio/netbird/management/internals/server"
nbconfig "github.com/netbirdio/netbird/management/internals/server/config"
nbdomain "github.com/netbirdio/netbird/shared/management/domain"
@@ -112,6 +113,29 @@ var (
mgmtSingleAccModeDomain = ""
}
// Load the management-side LLM pricing defaults file: an
// explicitly configured path is required to load (a typo must
// fail startup — the operator believes those rates are live);
// otherwise <datadir>/defaults_llm_pricing.yaml is probed and
// may be absent (compiled-in defaults serve). A relative path
// is resolved against the datadir so a bare filename lands
// alongside the store. Either way the path stays watched: the
// reloader picks up edits — and the file appearing later —
// without a restart.
pricingPath := config.AgentNetwork.PricingDefaultsFile
pricingRequired := pricingPath != ""
if !pricingRequired {
pricingPath = agentnetworkpricing.DefaultFileName
}
if !filepath.IsAbs(pricingPath) {
pricingPath = filepath.Join(config.Datadir, pricingPath)
}
log.Infof("loading agent-network pricing defaults from %s (required: %v)", pricingPath, pricingRequired)
if err := agentnetworkpricing.LoadFile(pricingPath, pricingRequired); err != nil {
return fmt.Errorf("load agent-network pricing defaults: %v", err)
}
agentnetworkpricing.StartReloader(ctx, agentnetworkpricing.ReloadInterval)
srv := newServer(&server.Config{
NbConfig: config,
DNSDomain: dnsDomain,
management/internals/modules/agentnetwork/accesslog_ingest.go
+56 -41
View File
@@ -18,21 +18,26 @@ import (
// contract between the proxy and management; management flattens them into
// queryable columns. Keep in sync with the proxy side.
const (
metaKeyProvider = "llm.provider"
metaKeyModel = "llm.model"
metaKeyResolvedProviderID = "llm.resolved_provider_id"
metaKeySelectedPolicyID = "llm.selected_policy_id"
metaKeyPolicyDecision = "llm_policy.decision"
metaKeyPolicyReason = "llm_policy.reason"
metaKeyInputTokens = "llm.input_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyOutputTokens = "llm.output_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyTotalTokens = "llm.total_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyCostUSDTotal = "cost.usd_total"
metaKeyStream = "llm.stream"
metaKeySessionID = "llm.session_id"
metaKeyAuthorisingGroups = "llm.authorising_groups"
metaKeyRequestPrompt = "llm.request_prompt"
metaKeyResponseCompletion = "llm.response_completion"
metaKeyProvider = "llm.provider"
metaKeyModel = "llm.model"
metaKeyResolvedProviderID = "llm.resolved_provider_id"
metaKeySelectedPolicyID = "llm.selected_policy_id"
metaKeyPolicyDecision = "llm_policy.decision"
metaKeyPolicyReason = "llm_policy.reason"
metaKeyInputTokens = "llm.input_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyOutputTokens = "llm.output_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyTotalTokens = "llm.total_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyCachedInputTokens = "llm.cached_input_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyCacheCreationTokens = "llm.cache_creation_tokens" //nolint:gosec // metadata key name, not a credential
metaKeyCostUSDInput = "cost.usd_input"
metaKeyCostUSDCachedInput = "cost.usd_cached_input"
metaKeyCostUSDCacheCreate = "cost.usd_cache_creation"
metaKeyCostUSDOutput = "cost.usd_output"
metaKeyStream = "llm.stream"
metaKeySessionID = "llm.session_id"
metaKeyAuthorisingGroups = "llm.authorising_groups"
metaKeyRequestPrompt = "llm.request_prompt"
metaKeyResponseCompletion = "llm.response_completion"
)
// IngestAccessLog flattens the metadata-bearing reverse-proxy access-log entry
@@ -108,20 +113,25 @@ func flattenAccessLog(e *accesslogs.AccessLogEntry) (*types.AgentNetworkAccessLo
BytesUpload: e.BytesUpload,
BytesDownload: e.BytesDownload,
Provider: meta[metaKeyProvider],
Model: meta[metaKeyModel],
SessionID: meta[metaKeySessionID],
ResolvedProviderID: meta[metaKeyResolvedProviderID],
SelectedPolicyID: meta[metaKeySelectedPolicyID],
Decision: meta[metaKeyPolicyDecision],
DenyReason: meta[metaKeyPolicyReason],
InputTokens: parseMetaInt(meta, metaKeyInputTokens),
OutputTokens: parseMetaInt(meta, metaKeyOutputTokens),
TotalTokens: parseMetaInt(meta, metaKeyTotalTokens),
CostUSD: parseMetaFloat(meta, metaKeyCostUSDTotal),
Stream: parseMetaBool(meta, metaKeyStream),
RequestPrompt: meta[metaKeyRequestPrompt],
ResponseCompletion: meta[metaKeyResponseCompletion],
Provider: meta[metaKeyProvider],
Model: meta[metaKeyModel],
SessionID: meta[metaKeySessionID],
ResolvedProviderID: meta[metaKeyResolvedProviderID],
SelectedPolicyID: meta[metaKeySelectedPolicyID],
Decision: meta[metaKeyPolicyDecision],
DenyReason: meta[metaKeyPolicyReason],
InputTokens: parseMetaInt(meta, metaKeyInputTokens),
OutputTokens: parseMetaInt(meta, metaKeyOutputTokens),
TotalTokens: parseMetaInt(meta, metaKeyTotalTokens),
CachedInputTokens: parseMetaInt(meta, metaKeyCachedInputTokens),
CacheCreationTokens: parseMetaInt(meta, metaKeyCacheCreationTokens),
InputCostUSD: parseMetaFloat(meta, metaKeyCostUSDInput),
CachedInputCostUSD: parseMetaFloat(meta, metaKeyCostUSDCachedInput),
CacheCreationCostUSD: parseMetaFloat(meta, metaKeyCostUSDCacheCreate),
OutputCostUSD: parseMetaFloat(meta, metaKeyCostUSDOutput),
Stream: parseMetaBool(meta, metaKeyStream),
RequestPrompt: meta[metaKeyRequestPrompt],
ResponseCompletion: meta[metaKeyResponseCompletion],
}
var groups []types.AgentNetworkAccessLogGroup
@@ -140,18 +150,23 @@ func flattenAccessLog(e *accesslogs.AccessLogEntry) (*types.AgentNetworkAccessLo
// log's ID so the two correlate.
func usageFromFlattenedLog(e *types.AgentNetworkAccessLog, groups []types.AgentNetworkAccessLogGroup) (*types.AgentNetworkUsage, []types.AgentNetworkUsageGroup) {
usage := &types.AgentNetworkUsage{
ID: e.ID,
AccountID: e.AccountID,
Timestamp: e.Timestamp,
UserID: e.UserID,
ResolvedProviderID: e.ResolvedProviderID,
Provider: e.Provider,
Model: e.Model,
SessionID: e.SessionID,
InputTokens: e.InputTokens,
OutputTokens: e.OutputTokens,
TotalTokens: e.TotalTokens,
CostUSD: e.CostUSD,
ID: e.ID,
AccountID: e.AccountID,
Timestamp: e.Timestamp,
UserID: e.UserID,
ResolvedProviderID: e.ResolvedProviderID,
Provider: e.Provider,
Model: e.Model,
SessionID: e.SessionID,
InputTokens: e.InputTokens,
OutputTokens: e.OutputTokens,
TotalTokens: e.TotalTokens,
CachedInputTokens: e.CachedInputTokens,
CacheCreationTokens: e.CacheCreationTokens,
InputCostUSD: e.InputCostUSD,
CachedInputCostUSD: e.CachedInputCostUSD,
CacheCreationCostUSD: e.CacheCreationCostUSD,
OutputCostUSD: e.OutputCostUSD,
}
usageGroups := make([]types.AgentNetworkUsageGroup, 0, len(groups))
management/internals/modules/agentnetwork/accesslog_ingest_realstore_test.go
+37 -12
View File
@@ -28,17 +28,22 @@ func newIngestTestEntry() *accesslogs.AccessLogEntry {
UserId: "user-1",
AgentNetwork: true,
Metadata: map[string]string{
metaKeyProvider: "openai",
metaKeyModel: "gpt-5.4",
metaKeyResolvedProviderID: "prov-1",
metaKeySessionID: "sess-1",
metaKeyInputTokens: "100",
metaKeyOutputTokens: "50",
metaKeyTotalTokens: "150",
metaKeyCostUSDTotal: "0.0123",
metaKeyStream: "true",
metaKeyRequestPrompt: "hello",
metaKeyResponseCompletion: "world",
metaKeyProvider: "openai",
metaKeyModel: "gpt-5.4",
metaKeyResolvedProviderID: "prov-1",
metaKeySessionID: "sess-1",
metaKeyInputTokens: "100",
metaKeyOutputTokens: "50",
metaKeyTotalTokens: "1174",
metaKeyCachedInputTokens: "256",
metaKeyCacheCreationTokens: "768",
metaKeyCostUSDInput: "0.0071",
metaKeyCostUSDCachedInput: "0.0009",
metaKeyCostUSDCacheCreate: "0.0020",
metaKeyCostUSDOutput: "0.0023",
metaKeyStream: "true",
metaKeyRequestPrompt: "hello",
metaKeyResponseCompletion: "world",
// repeated id must be de-duplicated before the group rows insert.
metaKeyAuthorisingGroups: "grp-eng,grp-eng,grp-ops",
},
@@ -65,7 +70,19 @@ func TestIngestAccessLog_RealStore_LogCollectionOff(t *testing.T) {
require.Len(t, usage, 1, "usage row must be written even with log collection off")
assert.Equal(t, int64(100), usage[0].InputTokens, "input tokens must round-trip from metadata")
assert.Equal(t, int64(50), usage[0].OutputTokens, "output tokens must round-trip from metadata")
assert.InDelta(t, 0.0123, usage[0].CostUSD, 1e-9, "cost must round-trip from metadata")
assert.Equal(t, int64(256), usage[0].CachedInputTokens, "cache-read tokens must round-trip from metadata")
assert.Equal(t, int64(768), usage[0].CacheCreationTokens, "cache-write tokens must round-trip from metadata")
// The per-bucket breakdown is the only cost state stored, and must survive
// the write/read cycle as real columns — usage rows are the only cost
// record for accounts with log collection off, so a dropped column here
// loses the split permanently.
assert.InDelta(t, 0.0071, usage[0].InputCostUSD, 1e-9, "input cost must round-trip from metadata")
assert.InDelta(t, 0.0009, usage[0].CachedInputCostUSD, 1e-9, "cache-read cost must round-trip from metadata")
assert.InDelta(t, 0.0020, usage[0].CacheCreationCostUSD, 1e-9, "cache-write cost must round-trip from metadata")
assert.InDelta(t, 0.0023, usage[0].OutputCostUSD, 1e-9, "output cost must round-trip from metadata")
// Aggregates are derived from the stored columns, never stored themselves.
assert.InDelta(t, 0.0123, usage[0].TotalCostUSD(), 1e-9, "total is derived from the stored buckets")
assert.InDelta(t, 0.0029, usage[0].CacheCostUSD(), 1e-9, "cache cost is derived from the two cache buckets")
logs, _, err := s.GetAgentNetworkAccessLogs(ctx, store.LockingStrengthNone, testAccountID, types.AgentNetworkAccessLogFilter{})
require.NoError(t, err)
@@ -96,6 +113,14 @@ func TestIngestAccessLog_RealStore_LogCollectionOn(t *testing.T) {
require.Equal(t, int64(1), total, "exactly one access-log row expected")
require.Len(t, logs, 1, "full access-log row must be written when log collection is on")
assert.Equal(t, "gpt-5.4", logs[0].Model, "model must flatten from metadata")
assert.Equal(t, int64(256), logs[0].CachedInputTokens, "cache-read tokens must flatten from metadata")
assert.Equal(t, int64(768), logs[0].CacheCreationTokens, "cache-write tokens must flatten from metadata")
assert.InDelta(t, 0.0029, logs[0].CacheCostUSD(), 1e-9, "cache cost is derived from the two cache buckets")
assert.InDelta(t, 0.0123, logs[0].TotalCostUSD(), 1e-9, "total is derived from the stored buckets")
assert.InDelta(t, 0.0071, logs[0].InputCostUSD, 1e-9, "input cost must flatten from metadata")
assert.InDelta(t, 0.0009, logs[0].CachedInputCostUSD, 1e-9, "cache-read cost must flatten from metadata")
assert.InDelta(t, 0.0020, logs[0].CacheCreationCostUSD, 1e-9, "cache-write cost must flatten from metadata")
assert.InDelta(t, 0.0023, logs[0].OutputCostUSD, 1e-9, "output cost must flatten from metadata")
assert.Equal(t, "hello", logs[0].RequestPrompt, "prompt must be retained when log collection is on")
assert.Equal(t, "world", logs[0].ResponseCompletion, "completion must be retained when log collection is on")
assert.True(t, logs[0].Stream, "stream flag must flatten from metadata")
management/internals/modules/agentnetwork/accesslog_sessions_realstore_test.go
+3 -3
View File
@@ -38,7 +38,7 @@ func accessLogRow(id, sessionID string, ts time.Time, opts ...func(*types.AgentN
InputTokens: 100,
OutputTokens: 50,
TotalTokens: 150,
CostUSD: 0.01,
InputCostUSD: 0.01,
}
for _, o := range opts {
o(e)
@@ -74,7 +74,7 @@ func withTokens(in, out, total int64, cost float64) func(*types.AgentNetworkAcce
e.InputTokens = in
e.OutputTokens = out
e.TotalTokens = total
e.CostUSD = cost
e.InputCostUSD = cost
}
}
@@ -155,7 +155,7 @@ func TestAccessLogSessions_FoldAndAggregate(t *testing.T) {
assert.Equal(t, int64(310), a.InputTokens, "input tokens summed")
assert.Equal(t, int64(135), a.OutputTokens, "output tokens summed")
assert.Equal(t, int64(445), a.TotalTokens, "total tokens summed")
assert.InDelta(t, 0.031, a.CostUSD, 1e-9, "cost summed")
assert.InDelta(t, 0.031, a.TotalCostUSD(), 1e-9, "cost summed")
assert.Equal(t, "deny", a.Decision, "any deny makes the session a deny")
assert.ElementsMatch(t, []string{"openai", "anthropic"}, a.Providers, "distinct providers")
assert.ElementsMatch(t, []string{"gpt-5.4", "claude-haiku-4-5"}, a.Models, "distinct models")
management/internals/modules/agentnetwork/catalog/catalog.go
+122 -54
View File
@@ -7,12 +7,28 @@ package catalog
import "github.com/netbirdio/netbird/shared/management/http/api"
// Model is the in-memory representation of a catalog model.
//
// The three cache rates mirror the proxy cost meter's Entry semantics
// (USD per 1k tokens; 0 = no rate configured, that bucket bills at
// InputPer1k):
// - CachedInputPer1k: OpenAI-shape rate for cached prompt tokens
// (a SUBSET of input tokens). Typically 0.1-0.5x input.
// - CacheReadPer1k / CacheCreationPer1k: Anthropic-shape rates for
// the two ADDITIVE prompt-cache buckets. Typically 0.1x / 1.25x
// input.
//
// The catalog is the single default-pricing source: the agentnetwork
// pricing package folds these models into per-surface tables that the
// synthesizer ships to the proxy's cost_meter.
type Model struct {
ID string
Label string
InputPer1k float64
OutputPer1k float64
ContextWindow int
ID string
Label string
InputPer1k float64
OutputPer1k float64
CachedInputPer1k float64
CacheReadPer1k float64
CacheCreationPer1k float64
ContextWindow int
}
// ProviderKind groups catalog entries for UI presentation. The split
@@ -65,6 +81,17 @@ type Provider struct {
// surface — the proxy middleware then falls back to URL sniffing
// or skips request-side enrichment.
ParserID string
// PricingSurfaces names the cost-meter pricing surfaces this
// provider's Models are priced under ("openai", "anthropic",
// "bedrock" — the llm.Parser surface the request parser stamps as
// llm.provider at billing time). NOT derivable from ParserID:
// bedrock_api and vertex_ai_api leave ParserID empty (URL-sniffed)
// yet price under "bedrock" / "anthropic", and kimi_api serves two
// body shapes so it prices under both. Nil for gateway/custom
// entries, which declare no models. Same (surface, model) pair
// contributed by two providers must carry identical rates — the
// pricing package's tests enforce that.
PricingSurfaces []string
// IdentityInjection, when non-nil, instructs the proxy to stamp
// the caller's NetBird identity onto upstream requests under the
// configured header names. Used for gateways like LiteLLM that
@@ -219,6 +246,7 @@ var providers = []Provider{
DefaultContentType: "application/json",
BrandColor: "#10A37F",
ParserID: "openai",
PricingSurfaces: []string{"openai"},
// Pricing + context windows cross-checked against LiteLLM's
// model_prices_and_context_window.json. Notable corrections from
// earlier values: o4-mini repriced from $4/$16 to $1.10/$4.40
@@ -226,20 +254,20 @@ var providers = []Provider{
// family context windows split between 1.05M for full-size
// models and 272K for mini/nano/codex variants.
Models: []Model{
{ID: "gpt-5.5", Label: "GPT-5.5", InputPer1k: 0.005, OutputPer1k: 0.030, ContextWindow: 1050000},
{ID: "gpt-5.5-pro", Label: "GPT-5.5 Pro", InputPer1k: 0.030, OutputPer1k: 0.180, ContextWindow: 1050000},
{ID: "gpt-5.4", Label: "GPT-5.4", InputPer1k: 0.0025, OutputPer1k: 0.015, ContextWindow: 1050000},
{ID: "gpt-5.4-pro", Label: "GPT-5.4 Pro", InputPer1k: 0.030, OutputPer1k: 0.180, ContextWindow: 1050000},
{ID: "gpt-5.4-mini", Label: "GPT-5.4 Mini", InputPer1k: 0.00075, OutputPer1k: 0.0045, ContextWindow: 272000},
{ID: "gpt-5.4-nano", Label: "GPT-5.4 Nano", InputPer1k: 0.0002, OutputPer1k: 0.00125, ContextWindow: 272000},
{ID: "gpt-5.3-codex", Label: "GPT-5.3 Codex", InputPer1k: 0.00175, OutputPer1k: 0.014, ContextWindow: 272000},
{ID: "gpt-5.3-chat-latest", Label: "GPT-5.3 Chat", InputPer1k: 0.00175, OutputPer1k: 0.014, ContextWindow: 128000},
{ID: "o4-mini", Label: "o4-mini", InputPer1k: 0.0011, OutputPer1k: 0.0044, ContextWindow: 200000},
{ID: "gpt-4.1", Label: "GPT-4.1", InputPer1k: 0.002, OutputPer1k: 0.008, ContextWindow: 1047576},
{ID: "gpt-4.1-mini", Label: "GPT-4.1 mini", InputPer1k: 0.0004, OutputPer1k: 0.0016, ContextWindow: 1047576},
{ID: "gpt-4.1-nano", Label: "GPT-4.1 nano", InputPer1k: 0.0001, OutputPer1k: 0.0004, ContextWindow: 1047576},
{ID: "gpt-4o", Label: "GPT-4o", InputPer1k: 0.0025, OutputPer1k: 0.010, ContextWindow: 128000},
{ID: "gpt-4o-mini", Label: "GPT-4o mini", InputPer1k: 0.00015, OutputPer1k: 0.0006, ContextWindow: 128000},
{ID: "gpt-5.5", Label: "GPT-5.5", InputPer1k: 0.005, OutputPer1k: 0.030, CachedInputPer1k: 0.0005, ContextWindow: 1050000},
{ID: "gpt-5.5-pro", Label: "GPT-5.5 Pro", InputPer1k: 0.030, OutputPer1k: 0.180, CachedInputPer1k: 0.003, ContextWindow: 1050000},
{ID: "gpt-5.4", Label: "GPT-5.4", InputPer1k: 0.0025, OutputPer1k: 0.015, CachedInputPer1k: 0.00025, ContextWindow: 1050000},
{ID: "gpt-5.4-pro", Label: "GPT-5.4 Pro", InputPer1k: 0.030, OutputPer1k: 0.180, CachedInputPer1k: 0.003, ContextWindow: 1050000},
{ID: "gpt-5.4-mini", Label: "GPT-5.4 Mini", InputPer1k: 0.00075, OutputPer1k: 0.0045, CachedInputPer1k: 0.000075, ContextWindow: 272000},
{ID: "gpt-5.4-nano", Label: "GPT-5.4 Nano", InputPer1k: 0.0002, OutputPer1k: 0.00125, CachedInputPer1k: 0.00002, ContextWindow: 272000},
{ID: "gpt-5.3-codex", Label: "GPT-5.3 Codex", InputPer1k: 0.00175, OutputPer1k: 0.014, CachedInputPer1k: 0.000175, ContextWindow: 272000},
{ID: "gpt-5.3-chat-latest", Label: "GPT-5.3 Chat", InputPer1k: 0.00175, OutputPer1k: 0.014, CachedInputPer1k: 0.000175, ContextWindow: 128000},
{ID: "o4-mini", Label: "o4-mini", InputPer1k: 0.0011, OutputPer1k: 0.0044, CachedInputPer1k: 0.000275, ContextWindow: 200000},
{ID: "gpt-4.1", Label: "GPT-4.1", InputPer1k: 0.002, OutputPer1k: 0.008, CachedInputPer1k: 0.0005, ContextWindow: 1047576},
{ID: "gpt-4.1-mini", Label: "GPT-4.1 mini", InputPer1k: 0.0004, OutputPer1k: 0.0016, CachedInputPer1k: 0.0001, ContextWindow: 1047576},
{ID: "gpt-4.1-nano", Label: "GPT-4.1 nano", InputPer1k: 0.0001, OutputPer1k: 0.0004, CachedInputPer1k: 0.000025, ContextWindow: 1047576},
{ID: "gpt-4o", Label: "GPT-4o", InputPer1k: 0.0025, OutputPer1k: 0.010, CachedInputPer1k: 0.00125, ContextWindow: 128000},
{ID: "gpt-4o-mini", Label: "GPT-4o mini", InputPer1k: 0.00015, OutputPer1k: 0.0006, CachedInputPer1k: 0.000075, ContextWindow: 128000},
{ID: "gpt-4-turbo", Label: "GPT-4 Turbo", InputPer1k: 0.01, OutputPer1k: 0.03, ContextWindow: 128000},
{ID: "gpt-3.5-turbo", Label: "GPT-3.5 Turbo", InputPer1k: 0.0005, OutputPer1k: 0.0015, ContextWindow: 16385},
{ID: "text-embedding-3-large", Label: "text-embedding-3-large", InputPer1k: 0.00013, OutputPer1k: 0, ContextWindow: 8191},
@@ -257,6 +285,7 @@ var providers = []Provider{
DefaultContentType: "application/json",
BrandColor: "#D97757",
ParserID: "anthropic",
PricingSurfaces: []string{"anthropic"},
// Per Anthropic's current model lineup. Pricing in USD per 1k
// tokens. Context windows: 4.6+ family is 1M; Haiku 4.5 stays at
// 200K. claude-3-7-sonnet and claude-3-5-haiku retired
@@ -267,14 +296,14 @@ var providers = []Provider{
// account to be on >= 30-day data retention or all requests
// 400.
Models: []Model{
{ID: "claude-fable-5", Label: "Claude Fable 5", InputPer1k: 0.010, OutputPer1k: 0.050, ContextWindow: 1000000},
{ID: "claude-opus-4-8", Label: "Claude Opus 4.8", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "claude-opus-4-7", Label: "Claude Opus 4.7", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "claude-opus-4-6", Label: "Claude Opus 4.6", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "claude-opus-4-1", Label: "Claude Opus 4.1 (deprecated, retires 2026-08-05)", InputPer1k: 0.015, OutputPer1k: 0.075, ContextWindow: 200000},
{ID: "claude-sonnet-4-6", Label: "Claude Sonnet 4.6", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 1000000},
{ID: "claude-sonnet-4-5", Label: "Claude Sonnet 4.5", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 200000},
{ID: "claude-haiku-4-5", Label: "Claude Haiku 4.5", InputPer1k: 0.001, OutputPer1k: 0.005, ContextWindow: 200000},
{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},
{ID: "claude-opus-4-6", Label: "Claude Opus 4.6", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "claude-opus-4-1", Label: "Claude Opus 4.1 (deprecated, retires 2026-08-05)", InputPer1k: 0.015, OutputPer1k: 0.075, CacheReadPer1k: 0.0015, CacheCreationPer1k: 0.01875, ContextWindow: 200000},
{ID: "claude-sonnet-4-6", Label: "Claude Sonnet 4.6", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000},
{ID: "claude-sonnet-4-5", Label: "Claude Sonnet 4.5", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 200000},
{ID: "claude-haiku-4-5", Label: "Claude Haiku 4.5", InputPer1k: 0.001, OutputPer1k: 0.005, CacheReadPer1k: 0.0001, CacheCreationPer1k: 0.00125, ContextWindow: 200000},
},
},
{
@@ -288,18 +317,19 @@ var providers = []Provider{
DefaultContentType: "application/json",
BrandColor: "#0078D4",
ParserID: "openai",
PricingSurfaces: []string{"openai"},
// Mirrors openai_api pricing — Azure resells OpenAI models at the
// same per-token rates, just under different deployment names.
Models: []Model{
{ID: "gpt-5.5", Label: "GPT-5.5 (Azure)", InputPer1k: 0.005, OutputPer1k: 0.030, ContextWindow: 1050000},
{ID: "gpt-5.4", Label: "GPT-5.4 (Azure)", InputPer1k: 0.0025, OutputPer1k: 0.015, ContextWindow: 1050000},
{ID: "gpt-5.4-mini", Label: "GPT-5.4 Mini (Azure)", InputPer1k: 0.00075, OutputPer1k: 0.0045, ContextWindow: 272000},
{ID: "gpt-5.4-nano", Label: "GPT-5.4 Nano (Azure)", InputPer1k: 0.0002, OutputPer1k: 0.00125, ContextWindow: 272000},
{ID: "o4-mini", Label: "o4-mini (Azure)", InputPer1k: 0.0011, OutputPer1k: 0.0044, ContextWindow: 200000},
{ID: "gpt-4.1", Label: "GPT-4.1 (Azure)", InputPer1k: 0.002, OutputPer1k: 0.008, ContextWindow: 1047576},
{ID: "gpt-4.1-mini", Label: "GPT-4.1 mini (Azure)", InputPer1k: 0.0004, OutputPer1k: 0.0016, ContextWindow: 1047576},
{ID: "gpt-4o", Label: "GPT-4o (Azure)", InputPer1k: 0.0025, OutputPer1k: 0.010, ContextWindow: 128000},
{ID: "gpt-4o-mini", Label: "GPT-4o mini (Azure)", InputPer1k: 0.00015, OutputPer1k: 0.0006, ContextWindow: 128000},
{ID: "gpt-5.5", Label: "GPT-5.5 (Azure)", InputPer1k: 0.005, OutputPer1k: 0.030, CachedInputPer1k: 0.0005, ContextWindow: 1050000},
{ID: "gpt-5.4", Label: "GPT-5.4 (Azure)", InputPer1k: 0.0025, OutputPer1k: 0.015, CachedInputPer1k: 0.00025, ContextWindow: 1050000},
{ID: "gpt-5.4-mini", Label: "GPT-5.4 Mini (Azure)", InputPer1k: 0.00075, OutputPer1k: 0.0045, CachedInputPer1k: 0.000075, ContextWindow: 272000},
{ID: "gpt-5.4-nano", Label: "GPT-5.4 Nano (Azure)", InputPer1k: 0.0002, OutputPer1k: 0.00125, CachedInputPer1k: 0.00002, ContextWindow: 272000},
{ID: "o4-mini", Label: "o4-mini (Azure)", InputPer1k: 0.0011, OutputPer1k: 0.0044, CachedInputPer1k: 0.000275, ContextWindow: 200000},
{ID: "gpt-4.1", Label: "GPT-4.1 (Azure)", InputPer1k: 0.002, OutputPer1k: 0.008, CachedInputPer1k: 0.0005, ContextWindow: 1047576},
{ID: "gpt-4.1-mini", Label: "GPT-4.1 mini (Azure)", InputPer1k: 0.0004, OutputPer1k: 0.0016, CachedInputPer1k: 0.0001, ContextWindow: 1047576},
{ID: "gpt-4o", Label: "GPT-4o (Azure)", InputPer1k: 0.0025, OutputPer1k: 0.010, CachedInputPer1k: 0.00125, ContextWindow: 128000},
{ID: "gpt-4o-mini", Label: "GPT-4o mini (Azure)", InputPer1k: 0.00015, OutputPer1k: 0.0006, CachedInputPer1k: 0.000075, ContextWindow: 128000},
{ID: "gpt-35-turbo", Label: "GPT-3.5 Turbo (Azure)", InputPer1k: 0.0005, OutputPer1k: 0.0015, ContextWindow: 16385},
},
},
@@ -313,6 +343,9 @@ var providers = []Provider{
AuthHeaderTemplate: "Bearer ${API_KEY}",
DefaultContentType: "application/json",
BrandColor: "#FF9900",
// ParserID stays empty (path-style dispatch via IsBedrockPathStyle);
// the request parser meters these under the "bedrock" surface.
PricingSurfaces: []string{"bedrock"},
// Anthropic models on Bedrock take the anthropic.* prefix and
// follow the same lineup / pricing as the first-party Anthropic
// catalog entry above. claude-3-7-sonnet and claude-3-5-haiku
@@ -322,13 +355,13 @@ 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-4-8", Label: "Claude Opus 4.8 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "anthropic.claude-opus-4-7", Label: "Claude Opus 4.7 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "anthropic.claude-opus-4-6", Label: "Claude Opus 4.6 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "anthropic.claude-opus-4-1", Label: "Claude Opus 4.1 (Bedrock, deprecated 2026-08-05)", InputPer1k: 0.015, OutputPer1k: 0.075, ContextWindow: 200000},
{ID: "anthropic.claude-sonnet-4-6", Label: "Claude Sonnet 4.6 (Bedrock)", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 1000000},
{ID: "anthropic.claude-sonnet-4-5", Label: "Claude Sonnet 4.5 (Bedrock)", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 200000},
{ID: "anthropic.claude-haiku-4-5", Label: "Claude Haiku 4.5 (Bedrock)", InputPer1k: 0.001, OutputPer1k: 0.005, ContextWindow: 200000},
{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},
{ID: "anthropic.claude-opus-4-1", Label: "Claude Opus 4.1 (Bedrock, deprecated 2026-08-05)", InputPer1k: 0.015, OutputPer1k: 0.075, CacheReadPer1k: 0.0015, CacheCreationPer1k: 0.01875, ContextWindow: 200000},
{ID: "anthropic.claude-sonnet-4-6", Label: "Claude Sonnet 4.6 (Bedrock)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000},
{ID: "anthropic.claude-sonnet-4-5", Label: "Claude Sonnet 4.5 (Bedrock)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 200000},
{ID: "anthropic.claude-haiku-4-5", Label: "Claude Haiku 4.5 (Bedrock)", InputPer1k: 0.001, OutputPer1k: 0.005, CacheReadPer1k: 0.0001, CacheCreationPer1k: 0.00125, ContextWindow: 200000},
{ID: "meta.llama3-3-70b-instruct", Label: "Llama 3.3 70B (Bedrock)", InputPer1k: 0.00072, OutputPer1k: 0.00072, ContextWindow: 128000},
{ID: "amazon.nova-2-lite", Label: "Amazon Nova 2 Lite (Bedrock, preview)", InputPer1k: 0.0003, OutputPer1k: 0.0025, ContextWindow: 1000000},
{ID: "amazon.nova-pro", Label: "Amazon Nova Pro (Bedrock)", InputPer1k: 0.0008, OutputPer1k: 0.0032, ContextWindow: 300000},
@@ -358,6 +391,10 @@ var providers = []Provider{
AuthHeaderTemplate: "Bearer ${API_KEY}",
DefaultContentType: "application/json",
BrandColor: "#4285F4",
// ParserID stays empty (path-style dispatch via IsVertexPathStyle);
// Anthropic-on-Vertex requests are metered under the "anthropic"
// surface with the bare, unversioned model id.
PricingSurfaces: []string{"anthropic"},
// Vertex carries the model in the URL path and authenticates with a
// service-account-minted OAuth token (api_key = "keyfile::<base64 SA>").
// Only Anthropic-on-Vertex is metered today: the request parser maps the
@@ -369,14 +406,14 @@ var providers = []Provider{
// exists — the router denies unmeterable publishers rather than forward
// them uncounted.
Models: []Model{
{ID: "claude-fable-5", Label: "Claude Fable 5 (Vertex)", InputPer1k: 0.010, OutputPer1k: 0.050, ContextWindow: 1000000},
{ID: "claude-opus-4-8", Label: "Claude Opus 4.8 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "claude-opus-4-7", Label: "Claude Opus 4.7 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "claude-opus-4-6", Label: "Claude Opus 4.6 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, ContextWindow: 1000000},
{ID: "claude-opus-4-1", Label: "Claude Opus 4.1 (Vertex, deprecated 2026-08-05)", InputPer1k: 0.015, OutputPer1k: 0.075, ContextWindow: 200000},
{ID: "claude-sonnet-4-6", Label: "Claude Sonnet 4.6 (Vertex)", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 1000000},
{ID: "claude-sonnet-4-5", Label: "Claude Sonnet 4.5 (Vertex)", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 200000},
{ID: "claude-haiku-4-5", Label: "Claude Haiku 4.5 (Vertex)", InputPer1k: 0.001, OutputPer1k: 0.005, ContextWindow: 200000},
{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},
{ID: "claude-opus-4-6", Label: "Claude Opus 4.6 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000},
{ID: "claude-opus-4-1", Label: "Claude Opus 4.1 (Vertex, deprecated 2026-08-05)", InputPer1k: 0.015, OutputPer1k: 0.075, CacheReadPer1k: 0.0015, CacheCreationPer1k: 0.01875, ContextWindow: 200000},
{ID: "claude-sonnet-4-6", Label: "Claude Sonnet 4.6 (Vertex)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000},
{ID: "claude-sonnet-4-5", Label: "Claude Sonnet 4.5 (Vertex)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 200000},
{ID: "claude-haiku-4-5", Label: "Claude Haiku 4.5 (Vertex)", InputPer1k: 0.001, OutputPer1k: 0.005, CacheReadPer1k: 0.0001, CacheCreationPer1k: 0.00125, ContextWindow: 200000},
},
},
{
@@ -390,6 +427,7 @@ var providers = []Provider{
DefaultContentType: "application/json",
BrandColor: "#FF7000",
ParserID: "openai",
PricingSurfaces: []string{"openai"},
// Pricing + context windows cross-checked against LiteLLM. Key
// gotchas the marketing page hides:
// - `mistral-medium-latest` aliases to Medium 3.1 ($0.40/$2),
@@ -448,6 +486,10 @@ var providers = []Provider{
// model id "k3") is account-bound seat licensing rather than a
// meterable platform key, so it's deliberately not the default.
ParserID: "",
// Both body shapes are metered: /v1/chat/completions under
// "openai", /anthropic/v1/messages under "anthropic" — so the
// K3 entry is priced on both surfaces.
PricingSurfaces: []string{"openai", "anthropic"},
// Pricing per Moonshot's platform rates at K3 launch (July 2026):
// $3/$15 per MTok with $0.30 cached input, flat across the 1M-token
// window. kimi-k3 is the ONLY model the platform serves newer
@@ -458,7 +500,14 @@ var providers = []Provider{
// The consumer app's "K3 Swarm Max" mode is not an API SKU, so it
// doesn't appear here.
Models: []Model{
{ID: "kimi-k3", Label: "Kimi K3", InputPer1k: 0.003, OutputPer1k: 0.015, ContextWindow: 1000000},
// Carries both cache shapes: Moonshot reports cache hits
// OpenAI-style on /v1/chat/completions (CachedInputPer1k)
// and Anthropic-style on /anthropic/v1/messages
// (CacheReadPer1k) — $0.30/MTok either way. Each surface's
// cost formula reads only its own field, so the superset
// entry prices both endpoints correctly. No cache-creation
// rate published; writes bill at the input rate.
{ID: "kimi-k3", Label: "Kimi K3", InputPer1k: 0.003, OutputPer1k: 0.015, CachedInputPer1k: 0.0003, CacheReadPer1k: 0.0003, ContextWindow: 1000000},
},
},
{
@@ -758,13 +807,28 @@ func IsBedrockPathStyle(providerID string) bool {
func (p Provider) ToAPIResponse() api.AgentNetworkCatalogProvider {
models := make([]api.AgentNetworkCatalogModel, 0, len(p.Models))
for _, m := range p.Models {
models = append(models, api.AgentNetworkCatalogModel{
am := api.AgentNetworkCatalogModel{
Id: m.ID,
Label: m.Label,
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
ContextWindow: m.ContextWindow,
})
}
// Cache rates are emitted only when configured so the dashboard
// can prefill them; 0 stays off the wire (absent = no rate).
if m.CachedInputPer1k > 0 {
v := m.CachedInputPer1k
am.CachedInputPer1k = &v
}
if m.CacheReadPer1k > 0 {
v := m.CacheReadPer1k
am.CacheReadPer1k = &v
}
if m.CacheCreationPer1k > 0 {
v := m.CacheCreationPer1k
am.CacheCreationPer1k = &v
}
models = append(models, am)
}
kind := api.AgentNetworkCatalogProviderKindProvider
switch p.Kind {
@@ -784,6 +848,10 @@ func (p Provider) ToAPIResponse() api.AgentNetworkCatalogProvider {
BrandColor: p.BrandColor,
Models: models,
}
if len(p.PricingSurfaces) > 0 {
surfaces := append([]string(nil), p.PricingSurfaces...)
resp.PricingSurfaces = &surfaces
}
if len(p.ExtraHeaders) > 0 {
extras := make([]api.AgentNetworkCatalogExtraHeader, 0, len(p.ExtraHeaders))
for _, h := range p.ExtraHeaders {
management/internals/modules/agentnetwork/handlers/handlers_test.go
+15 -1
View File
@@ -17,6 +17,7 @@ import (
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
"github.com/netbirdio/netbird/management/server/account"
nbcontext "github.com/netbirdio/netbird/management/server/context"
"github.com/netbirdio/netbird/management/server/permissions"
"github.com/netbirdio/netbird/management/server/store"
@@ -61,10 +62,23 @@ func newAgentNetworkHandlerFixture(t *testing.T) *agentNetworkHandlerFixture {
Return(true, context.Background(), nil).
AnyTimes()
manager := agentnetwork.NewManager(st, perms, nil, nil)
// Swallow activity events so the mutation paths (create/update/delete)
// are exercisable through the HTTP layer.
accounts := account.NewMockManager(ctrl)
accounts.EXPECT().
StoreEvent(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any()).
AnyTimes()
accounts.EXPECT().
UpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).
AnyTimes()
manager := agentnetwork.NewManager(st, perms, accounts, nil)
h := &handler{manager: manager}
router := mux.NewRouter()
router.HandleFunc("/agent-network/providers", h.createProvider).Methods("POST")
router.HandleFunc("/agent-network/providers/{providerId}", h.getProvider).Methods("GET")
router.HandleFunc("/agent-network/providers/{providerId}", h.updateProvider).Methods("PUT")
h.addPolicyEndpoints(router)
h.addConsumptionEndpoints(router)
h.addBudgetRuleEndpoints(router)
management/internals/modules/agentnetwork/handlers/providers_handler.go
+70 -1
View File
@@ -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
+102
View File
@@ -0,0 +1,102 @@
package handlers
import (
"encoding/json"
"math"
nethttp "net/http"
"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)
}
}
// TestProviderHandler_UpdateReplacesFullState pins the update contract shared
// with the other PUT endpoints: the request replaces the provider's mutable
// state, so optional fields absent from the JSON land as their zero values.
// The two exceptions are server-side: the api_key (a secret — omitted means
// "not rotated") and the session keypair, both preserved by the manager. The
// identity headers stay on the wire as explicit empty strings so a cleared
// value round-trips.
func TestProviderHandler_UpdateReplacesFullState(t *testing.T) {
f := newAgentNetworkHandlerFixture(t)
create := `{
"provider_id": "openai_api",
"name": "openai",
"upstream_url": "https://api.openai.com",
"api_key": "sk-test",
"enabled": true,
"metadata_disabled": true,
"skip_tls_verification": true,
"extra_values": {"x-portkey-config": "pc-prod-3f2a"},
"identity_header_user_id": "x-bf-dim-netbird_user_id",
"models": [{"id": "gpt-4o", "input_per_1k": 0.0025, "output_per_1k": 0.01}]
}`
rec := f.do(t, nethttp.MethodPost, "/agent-network/providers", create)
require.Equal(t, nethttp.StatusOK, rec.Code, "create must succeed: %s", rec.Body.String())
var created api.AgentNetworkProvider
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &created))
// Minimal update: only the required fields, no api_key. Everything
// optional must land as its zero value.
update := `{"provider_id": "openai_api", "name": "openai-renamed", "upstream_url": "https://api.openai.com", "enabled": true}`
rec = f.do(t, nethttp.MethodPut, "/agent-network/providers/"+created.Id, update)
require.Equal(t, nethttp.StatusOK, rec.Code, "update without api_key must succeed (key is preserved): %s", rec.Body.String())
var updated api.AgentNetworkProvider
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &updated))
assert.Equal(t, "openai-renamed", updated.Name, "sent field must apply")
assert.True(t, updated.Enabled, "sent field must apply")
assert.False(t, updated.MetadataDisabled, "omitted metadata_disabled must land as false — PUT replaces the full state")
assert.False(t, updated.SkipTlsVerification, "omitted skip_tls_verification must land as false")
assert.Nil(t, updated.ExtraValues, "omitted extra_values must be cleared")
assert.Equal(t, "", updated.IdentityHeaderUserId, "omitted identity header must be cleared yet stay on the wire")
assert.Empty(t, updated.Models, "omitted models must be cleared")
assert.Contains(t, rec.Body.String(), `"identity_header_user_id":""`,
"cleared identity header must round-trip as an explicit empty string")
}
management/internals/modules/agentnetwork/handlers/settings_handler.go
+9 -16
View File
@@ -2,7 +2,6 @@ package handlers
import (
"encoding/json"
"errors"
"net/http"
"github.com/gorilla/mux"
@@ -11,19 +10,20 @@ import (
nbcontext "github.com/netbirdio/netbird/management/server/context"
"github.com/netbirdio/netbird/shared/management/http/api"
"github.com/netbirdio/netbird/shared/management/http/util"
"github.com/netbirdio/netbird/shared/management/status"
)
// addSettingsEndpoints registers the Agent Network settings routes. The
// settings row is bootstrapped server-side on first provider create; GET reads
// it and PUT updates the mutable collection toggles (cluster/subdomain stay
// immutable).
// settings row is bootstrapped server-side on first provider create or on the
// first PUT carrying a cluster; GET reads it and PUT applies a partial update
// of the mutable collection toggles (cluster/subdomain stay immutable).
func (h *handler) addSettingsEndpoints(router *mux.Router) {
router.HandleFunc("/agent-network/settings", h.getSettings).Methods("GET", "OPTIONS")
router.HandleFunc("/agent-network/settings", h.updateSettings).Methods("PUT", "OPTIONS")
}
// updateSettings applies the collection toggles to the account's settings row.
// updateSettings replaces the mutable settings fields on the account's row.
// A request carrying a cluster bootstraps the row when the account doesn't
// have one yet.
func (h *handler) updateSettings(w http.ResponseWriter, r *http.Request) {
userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
if err != nil {
@@ -48,11 +48,9 @@ func (h *handler) updateSettings(w http.ResponseWriter, r *http.Request) {
util.WriteJSONObject(r.Context(), w, updated.ToAPIResponse())
}
// getSettings returns the account's agent-network settings. The settings
// row is bootstrapped on first provider create, so freshly-onboarded
// accounts have nothing to read. Rather than 404-ing in that case (which
// the dashboard would have to special-case), return a JSON null with 200
// so consumers can branch on the body alone.
// getSettings returns the account's agent-network settings. Accounts that
// haven't been bootstrapped yet read as the defaults with an empty cluster,
// subdomain and endpoint; the manager synthesises that view.
func (h *handler) getSettings(w http.ResponseWriter, r *http.Request) {
userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
if err != nil {
@@ -62,11 +60,6 @@ func (h *handler) getSettings(w http.ResponseWriter, r *http.Request) {
settings, err := h.manager.GetSettings(r.Context(), userAuth.AccountId, userAuth.UserId)
if err != nil {
var sErr *status.Error
if errors.As(err, &sErr) && sErr.Type() == status.NotFound {
util.WriteJSONObject(r.Context(), w, nil)
return
}
util.WriteError(r.Context(), err, w)
return
}
management/internals/modules/agentnetwork/handlers/settings_handler_test.go
+137
View File
@@ -0,0 +1,137 @@
package handlers
import (
"encoding/json"
"net/http"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/shared/management/http/api"
)
// TestSettingsHandler_GetUnbootstrappedReturnsDefaults pins the settings-read
// convention shared with the account and DNS settings endpoints: settings
// always read as a JSON object. Before bootstrap that object carries the
// defaults with an empty cluster/subdomain/endpoint (the "not bootstrapped"
// signal) and no timestamps — never a 404 and never the legacy null body.
func TestSettingsHandler_GetUnbootstrappedReturnsDefaults(t *testing.T) {
f := newAgentNetworkHandlerFixture(t)
rec := f.do(t, http.MethodGet, "/agent-network/settings", "")
require.Equal(t, http.StatusOK, rec.Code,
"unbootstrapped account must read as 200 with defaults: got %d body=%s", rec.Code, rec.Body.String())
require.NotEqual(t, "null", trimSpace(rec.Body.String()),
"the legacy 200+null shape must not come back")
var got api.AgentNetworkSettings
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
assert.Empty(t, got.Cluster, "cluster must be empty until bootstrapped")
assert.Empty(t, got.Subdomain, "subdomain must be empty until bootstrapped")
assert.Empty(t, got.Endpoint, "endpoint must be empty until bootstrapped, not a bare dot")
assert.True(t, got.EnableLogCollection, "defaults must show log collection on, matching bootstrap")
assert.False(t, got.EnablePromptCollection, "defaults must show prompt collection off")
assert.False(t, got.RedactPii, "defaults must show redaction off")
require.NotNil(t, got.AccessLogRetentionDays)
assert.Equal(t, 30, *got.AccessLogRetentionDays, "defaults must show the bootstrap retention")
assert.Nil(t, got.CreatedAt, "no timestamps before a row exists")
assert.Nil(t, got.UpdatedAt, "no timestamps before a row exists")
}
// TestSettingsHandler_PutBootstrapsWithCluster covers the settings-first
// bootstrap path: a PUT carrying a cluster on an unbootstrapped account
// creates the row (cluster pinned, subdomain assigned) and applies the
// mutable fields from the same request.
func TestSettingsHandler_PutBootstrapsWithCluster(t *testing.T) {
f := newAgentNetworkHandlerFixture(t)
rec := f.do(t, http.MethodPut, "/agent-network/settings",
`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": false, "access_log_retention_days": 30}`)
require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String())
var got api.AgentNetworkSettings
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
assert.Equal(t, "eu.proxy.netbird.io", got.Cluster, "cluster must be pinned from the request")
assert.NotEmpty(t, got.Subdomain, "subdomain must be assigned at bootstrap")
assert.Equal(t, got.Subdomain+".eu.proxy.netbird.io", got.Endpoint, "endpoint must combine subdomain and cluster")
assert.True(t, got.EnableLogCollection, "toggle from the bootstrap request must apply")
assert.True(t, got.EnablePromptCollection, "toggle from the bootstrap request must apply")
require.NotNil(t, got.AccessLogRetentionDays)
assert.Equal(t, 30, *got.AccessLogRetentionDays, "retention from the bootstrap request must apply")
// The row is now readable via GET.
rec = f.do(t, http.MethodGet, "/agent-network/settings", "")
require.Equal(t, http.StatusOK, rec.Code, "GET after bootstrap must succeed")
}
// TestSettingsHandler_PutWithoutClusterOnUnbootstrapped pins that a PUT
// without a cluster cannot conjure a settings row out of nothing — there is
// no cluster to pin — and surfaces as 404 like the GET.
func TestSettingsHandler_PutWithoutClusterOnUnbootstrapped(t *testing.T) {
f := newAgentNetworkHandlerFixture(t)
rec := f.do(t, http.MethodPut, "/agent-network/settings",
`{"enable_log_collection": false, "enable_prompt_collection": false, "redact_pii": false}`)
assert.Equal(t, http.StatusNotFound, rec.Code,
"cluster-less PUT on an unbootstrapped account must 404: got %d body=%s", rec.Code, rec.Body.String())
assert.Contains(t, rec.Body.String(), "cluster",
"the error must point the caller at the bootstrap paths: %s", rec.Body.String())
}
// TestSettingsHandler_PutReplacesMutableFields pins the update contract shared
// with the other PUT endpoints: the request replaces every mutable field, so a
// toggle absent from the JSON lands as its zero value rather than being
// preserved. Cluster and subdomain survive untouched.
func TestSettingsHandler_PutReplacesMutableFields(t *testing.T) {
f := newAgentNetworkHandlerFixture(t)
rec := f.do(t, http.MethodPut, "/agent-network/settings",
`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": true, "access_log_retention_days": 14}`)
require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String())
var before api.AgentNetworkSettings
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &before))
rec = f.do(t, http.MethodPut, "/agent-network/settings",
`{"enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`)
require.Equal(t, http.StatusOK, rec.Code, "update PUT must succeed: %s", rec.Body.String())
var got api.AgentNetworkSettings
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
assert.True(t, got.EnableLogCollection, "sent toggle must apply")
assert.False(t, got.EnablePromptCollection, "sent toggle must apply")
assert.False(t, got.RedactPii, "sent toggle must apply")
require.NotNil(t, got.AccessLogRetentionDays)
assert.Equal(t, 0, *got.AccessLogRetentionDays,
"retention absent from the request must land as the zero value — PUT replaces all mutable fields")
assert.Equal(t, before.Cluster, got.Cluster, "cluster must survive updates untouched")
assert.Equal(t, before.Subdomain, got.Subdomain, "subdomain must survive updates untouched")
}
// TestSettingsHandler_PutRejectsClusterChange pins cluster immutability: once
// assigned, a differing cluster is rejected as a validation error instead of
// being silently ignored, so callers never observe a value other than the one
// they sent. Echoing the assigned cluster back stays valid, which lets
// declarative clients send their full desired state idempotently.
func TestSettingsHandler_PutRejectsClusterChange(t *testing.T) {
f := newAgentNetworkHandlerFixture(t)
rec := f.do(t, http.MethodPut, "/agent-network/settings",
`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`)
require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String())
rec = f.do(t, http.MethodPut, "/agent-network/settings",
`{"cluster": "us.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`)
assert.Equal(t, http.StatusUnprocessableEntity, rec.Code,
"cluster change must be rejected as a validation error: got %d body=%s", rec.Code, rec.Body.String())
rec = f.do(t, http.MethodPut, "/agent-network/settings",
`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": true}`)
require.Equal(t, http.StatusOK, rec.Code, "echoing the assigned cluster must stay valid: %s", rec.Body.String())
var got api.AgentNetworkSettings
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
assert.Equal(t, "eu.proxy.netbird.io", got.Cluster, "cluster must be unchanged")
assert.True(t, got.RedactPii, "toggle sent alongside the echoed cluster must apply")
}
management/internals/modules/agentnetwork/manager.go
+147 -76
View File
@@ -86,12 +86,17 @@ type Manager interface {
// PolicySelectionInput is the per-request selection envelope. The
// proxy populates it from CapturedData (account, user, groups) plus
// the provider llm_router resolved.
// the provider llm_router resolved and the model it extracted.
type PolicySelectionInput struct {
AccountID string
UserID string
GroupIDs []string
ProviderID string
// Model is the already-normalised upstream model id the proxy extracted
// (parser strips Bedrock region/version, Vertex @version), so a
// case-insensitive compare suffices. Empty = undetermined → not permitted
// (fail closed).
Model string
}
// PolicySelectionResult names the policy that "pays" for this request
@@ -152,14 +157,14 @@ func NewManager(
}
func (m *managerImpl) GetAllProviders(ctx context.Context, accountID, userID string) ([]*types.Provider, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Read); err != nil {
return nil, err
}
return m.store.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, accountID)
}
func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, providerID string) (*types.Provider, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Read); err != nil {
return nil, err
}
return m.store.GetAgentNetworkProviderByID(ctx, store.LockingStrengthNone, accountID, providerID)
@@ -170,9 +175,14 @@ func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, provid
// been created yet; otherwise it is ignored (the cluster is pinned on
// Settings and every provider in the account routes through it).
func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error) {
if err := m.requirePermission(ctx, provider.AccountID, userID, operations.Create); err != nil {
if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil {
return nil, err
}
if strings.TrimSpace(bootstrapCluster) != "" {
if err := m.requireSettingsBootstrapPermission(ctx, provider.AccountID, userID); err != nil {
return nil, err
}
}
// An empty api_key would silently produce a synthesised service
// that 401s on every upstream request. Surface the misconfiguration
@@ -197,7 +207,7 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide
}
if strings.TrimSpace(bootstrapCluster) != "" {
if _, err := m.bootstrapSettingsIfNeeded(ctx, provider.AccountID, bootstrapCluster); err != nil {
if _, err := m.bootstrapSettingsIfNeeded(ctx, m.store, provider.AccountID, bootstrapCluster); err != nil {
// The provider create has already succeeded; logging the
// bootstrap miss matches the plan's PoC behaviour. The synth
// path treats a missing settings row as a no-op, and the next
@@ -213,7 +223,7 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide
}
func (m *managerImpl) UpdateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) {
if err := m.requirePermission(ctx, provider.AccountID, userID, operations.Update); err != nil {
if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Update); err != nil {
return nil, err
}
@@ -252,7 +262,7 @@ func (m *managerImpl) UpdateProvider(ctx context.Context, userID string, provide
}
func (m *managerImpl) DeleteProvider(ctx context.Context, accountID, userID, providerID string) error {
if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Delete); err != nil {
return err
}
@@ -301,21 +311,21 @@ func pluralize(n int, singular, plural string) string {
}
func (m *managerImpl) GetAllPolicies(ctx context.Context, accountID, userID string) ([]*types.Policy, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Read); err != nil {
return nil, err
}
return m.store.GetAccountAgentNetworkPolicies(ctx, store.LockingStrengthNone, accountID)
}
func (m *managerImpl) GetPolicy(ctx context.Context, accountID, userID, policyID string) (*types.Policy, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Read); err != nil {
return nil, err
}
return m.store.GetAgentNetworkPolicyByID(ctx, store.LockingStrengthNone, accountID, policyID)
}
func (m *managerImpl) CreatePolicy(ctx context.Context, userID string, policy *types.Policy) (*types.Policy, error) {
if err := m.requirePermission(ctx, policy.AccountID, userID, operations.Create); err != nil {
if err := m.requirePermission(ctx, policy.AccountID, userID, modules.AgentNetworkPolicies, operations.Create); err != nil {
return nil, err
}
@@ -341,7 +351,7 @@ func (m *managerImpl) CreatePolicy(ctx context.Context, userID string, policy *t
}
func (m *managerImpl) UpdatePolicy(ctx context.Context, userID string, policy *types.Policy) (*types.Policy, error) {
if err := m.requirePermission(ctx, policy.AccountID, userID, operations.Update); err != nil {
if err := m.requirePermission(ctx, policy.AccountID, userID, modules.AgentNetworkPolicies, operations.Update); err != nil {
return nil, err
}
@@ -368,7 +378,7 @@ func (m *managerImpl) UpdatePolicy(ctx context.Context, userID string, policy *t
}
func (m *managerImpl) DeletePolicy(ctx context.Context, accountID, userID, policyID string) error {
if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Delete); err != nil {
return err
}
@@ -388,21 +398,21 @@ func (m *managerImpl) DeletePolicy(ctx context.Context, accountID, userID, polic
}
func (m *managerImpl) GetAllGuardrails(ctx context.Context, accountID, userID string) ([]*types.Guardrail, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Read); err != nil {
return nil, err
}
return m.store.GetAccountAgentNetworkGuardrails(ctx, store.LockingStrengthNone, accountID)
}
func (m *managerImpl) GetGuardrail(ctx context.Context, accountID, userID, guardrailID string) (*types.Guardrail, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Read); err != nil {
return nil, err
}
return m.store.GetAgentNetworkGuardrailByID(ctx, store.LockingStrengthNone, accountID, guardrailID)
}
func (m *managerImpl) CreateGuardrail(ctx context.Context, userID string, guardrail *types.Guardrail) (*types.Guardrail, error) {
if err := m.requirePermission(ctx, guardrail.AccountID, userID, operations.Create); err != nil {
if err := m.requirePermission(ctx, guardrail.AccountID, userID, modules.AgentNetworkGuardrails, operations.Create); err != nil {
return nil, err
}
@@ -424,7 +434,7 @@ func (m *managerImpl) CreateGuardrail(ctx context.Context, userID string, guardr
}
func (m *managerImpl) UpdateGuardrail(ctx context.Context, userID string, guardrail *types.Guardrail) (*types.Guardrail, error) {
if err := m.requirePermission(ctx, guardrail.AccountID, userID, operations.Update); err != nil {
if err := m.requirePermission(ctx, guardrail.AccountID, userID, modules.AgentNetworkGuardrails, operations.Update); err != nil {
return nil, err
}
@@ -447,7 +457,7 @@ func (m *managerImpl) UpdateGuardrail(ctx context.Context, userID string, guardr
}
func (m *managerImpl) DeleteGuardrail(ctx context.Context, accountID, userID, guardrailID string) error {
if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Delete); err != nil {
return err
}
@@ -468,7 +478,7 @@ func (m *managerImpl) DeleteGuardrail(ctx context.Context, accountID, userID, gu
// GetAllBudgetRules returns every account-level budget rule for the account.
func (m *managerImpl) GetAllBudgetRules(ctx context.Context, accountID, userID string) ([]*types.AccountBudgetRule, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Read); err != nil {
return nil, err
}
return m.store.GetAccountAgentNetworkBudgetRules(ctx, store.LockingStrengthNone, accountID)
@@ -476,7 +486,7 @@ func (m *managerImpl) GetAllBudgetRules(ctx context.Context, accountID, userID s
// GetBudgetRule returns a single account-level budget rule.
func (m *managerImpl) GetBudgetRule(ctx context.Context, accountID, userID, ruleID string) (*types.AccountBudgetRule, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Read); err != nil {
return nil, err
}
return m.store.GetAgentNetworkBudgetRuleByID(ctx, store.LockingStrengthNone, accountID, ruleID)
@@ -486,7 +496,7 @@ func (m *managerImpl) GetBudgetRule(ctx context.Context, accountID, userID, rule
// enforced at request time (CheckLLMPolicyLimits), not baked into the synth
// proxy config, so no reconcile is needed.
func (m *managerImpl) CreateBudgetRule(ctx context.Context, userID string, rule *types.AccountBudgetRule) (*types.AccountBudgetRule, error) {
if err := m.requirePermission(ctx, rule.AccountID, userID, operations.Create); err != nil {
if err := m.requirePermission(ctx, rule.AccountID, userID, modules.AgentNetworkBudgets, operations.Create); err != nil {
return nil, err
}
@@ -508,7 +518,7 @@ func (m *managerImpl) CreateBudgetRule(ctx context.Context, userID string, rule
// UpdateBudgetRule updates an existing account-level budget rule.
func (m *managerImpl) UpdateBudgetRule(ctx context.Context, userID string, rule *types.AccountBudgetRule) (*types.AccountBudgetRule, error) {
if err := m.requirePermission(ctx, rule.AccountID, userID, operations.Update); err != nil {
if err := m.requirePermission(ctx, rule.AccountID, userID, modules.AgentNetworkBudgets, operations.Update); err != nil {
return nil, err
}
@@ -531,7 +541,7 @@ func (m *managerImpl) UpdateBudgetRule(ctx context.Context, userID string, rule
// DeleteBudgetRule removes an account-level budget rule.
func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, ruleID string) error {
if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Delete); err != nil {
return err
}
@@ -549,40 +559,83 @@ func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, r
return nil
}
// UpdateSettings applies the mutable account-level settings — the collection
// toggles — onto the existing row. Cluster and Subdomain are immutable and are
// preserved from the persisted row regardless of the input. Because the
// collection toggles change the synthesised service config (prompt-capture
// gating, access-log emission), a reconcile is triggered so the proxy and peer
// network maps converge on the new state.
// UpdateSettings replaces the mutable account-level settings — the collection
// toggles and retention — on the account's row. When the account has no
// settings row yet, a non-empty settings.Cluster bootstraps one (same path as
// first provider create); without it the update fails with NotFound. On an
// existing row the cluster and subdomain are immutable: a differing
// settings.Cluster is rejected rather than silently ignored so callers never
// observe a value other than what they sent. Because the collection toggles
// change the synthesised service config (prompt-capture gating, access-log
// emission), a reconcile is triggered so the proxy and peer network maps
// converge on the new state.
func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error) {
if err := m.requirePermission(ctx, settings.AccountID, userID, operations.Update); err != nil {
if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Update); err != nil {
return nil, err
}
existing, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID)
requestedCluster := strings.TrimSpace(settings.Cluster)
// The row lock from LockingStrengthUpdate only holds for the duration of
// the surrounding transaction, so the read, the cluster-immutability
// check, and the save must share one — otherwise concurrent PUTs could
// interleave between them.
var updated *types.Settings
err := m.store.ExecuteInTransaction(ctx, func(tx store.Store) error {
existing, err := tx.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID)
switch {
case err == nil:
if requestedCluster != "" && requestedCluster != existing.Cluster {
return status.Errorf(status.InvalidArgument, "cluster is immutable once assigned (current: %s)", existing.Cluster)
}
case isNotFound(err):
if requestedCluster == "" {
return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; pass cluster to bootstrap them, or create a provider with bootstrap_cluster set")
}
// Bootstrapping pins the cluster and subdomain — a settings
// create on top of the update the caller already passed, matching
// the gate on the provider-create bootstrap path.
if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil {
return err
}
existing, err = m.bootstrapSettingsIfNeeded(ctx, tx, settings.AccountID, requestedCluster)
if err != nil {
return err
}
default:
return fmt.Errorf("get agent network settings: %w", err)
}
existing.EnableLogCollection = settings.EnableLogCollection
existing.EnablePromptCollection = settings.EnablePromptCollection
existing.RedactPii = settings.RedactPii
existing.AccessLogRetentionDays = settings.AccessLogRetentionDays
existing.UpdatedAt = time.Now().UTC()
if err := tx.SaveAgentNetworkSettings(ctx, existing); err != nil {
return fmt.Errorf("save agent network settings: %w", err)
}
updated = existing
return nil
})
if err != nil {
return nil, fmt.Errorf("get agent network settings: %w", err)
}
existing.EnableLogCollection = settings.EnableLogCollection
existing.EnablePromptCollection = settings.EnablePromptCollection
existing.RedactPii = settings.RedactPii
existing.AccessLogRetentionDays = settings.AccessLogRetentionDays
existing.UpdatedAt = time.Now().UTC()
if err := m.store.SaveAgentNetworkSettings(ctx, existing); err != nil {
return nil, fmt.Errorf("save agent network settings: %w", err)
return nil, err
}
m.accountManager.StoreEvent(ctx, userID, settings.AccountID, settings.AccountID, activity.AgentNetworkSettingsUpdated, map[string]any{
"log_collection": existing.EnableLogCollection,
"prompt_collection": existing.EnablePromptCollection,
"redact_pii": existing.RedactPii,
"log_collection": updated.EnableLogCollection,
"prompt_collection": updated.EnablePromptCollection,
"redact_pii": updated.RedactPii,
})
m.reconcile(ctx, settings.AccountID)
return existing, nil
return updated, nil
}
// isNotFound reports whether err is a status.NotFound error.
func isNotFound(err error) bool {
var sErr *status.Error
return errors.As(err, &sErr) && sErr.Type() == status.NotFound
}
// validateProviderRefs ensures every destination provider id refers to a
@@ -606,14 +659,38 @@ func (m *managerImpl) validateProviderRefs(ctx context.Context, accountID string
return nil
}
// GetSettings returns the agent-network settings row for the account.
// Returns the underlying status.NotFound when no row has been
// bootstrapped yet (i.e. the account has no providers).
// GetSettings returns the agent-network settings row for the account. When no
// row has been bootstrapped yet, the defaults are returned (without
// persisting) with cluster and subdomain empty — settings always read as an
// object, like the account and DNS settings endpoints.
func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string) (*types.Settings, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Read); err != nil {
return nil, err
}
return m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
settings, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
switch {
case err == nil:
return settings, nil
case isNotFound(err):
return types.DefaultSettings(accountID), nil
default:
return nil, err
}
}
// requireSettingsBootstrapPermission gates the one-time settings bootstrap a
// first provider create performs. Pinning the account's cluster and subdomain
// is a settings write, so it needs the settings permission on top of the
// provider one. No-op once the settings row exists.
func (m *managerImpl) requireSettingsBootstrapPermission(ctx context.Context, accountID, userID string) error {
_, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
if err == nil {
return nil
}
if !isNotFound(err) {
return fmt.Errorf("get agent network settings: %w", err)
}
return m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Create)
}
// bootstrapSettingsIfNeeded creates the per-account agent-network
@@ -621,8 +698,9 @@ func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string)
// hint the dashboard sends (auto-picked from the active cluster list);
// the subdomain is picked from the curated wordlist avoiding
// collisions on the same cluster. Idempotent: if a row already exists
// it is returned untouched and the hint is ignored.
func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID, providerCluster string) (*types.Settings, error) {
// it is returned untouched and the hint is ignored. st is the store to
// operate on — pass the transaction store when calling from within one.
func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.Store, accountID, providerCluster string) (*types.Settings, error) {
if accountID == "" {
return nil, fmt.Errorf("bootstrap settings: account id is required")
}
@@ -630,16 +708,15 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID,
return nil, fmt.Errorf("bootstrap settings: provider cluster is required")
}
existing, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
existing, err := st.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
if err == nil {
return existing, nil
}
var sErr *status.Error
if !errors.As(err, &sErr) || sErr.Type() != status.NotFound {
if !isNotFound(err) {
return nil, fmt.Errorf("get agent network settings: %w", err)
}
siblings, err := m.store.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster)
siblings, err := st.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster)
if err != nil {
return nil, fmt.Errorf("list agent network settings on cluster: %w", err)
}
@@ -658,18 +735,12 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID,
m.labelRngMu.Unlock()
now := time.Now().UTC()
settings := &types.Settings{
AccountID: accountID,
Cluster: providerCluster,
Subdomain: subdomain,
// Logs on by default; usage is collected regardless. Retention bounds
// how long full log rows are kept.
EnableLogCollection: true,
AccessLogRetentionDays: types.DefaultAccessLogRetentionDays,
CreatedAt: now,
UpdatedAt: now,
}
if err := m.store.SaveAgentNetworkSettings(ctx, settings); err != nil {
settings := types.DefaultSettings(accountID)
settings.Cluster = providerCluster
settings.Subdomain = subdomain
settings.CreatedAt = now
settings.UpdatedAt = now
if err := st.SaveAgentNetworkSettings(ctx, settings); err != nil {
return nil, fmt.Errorf("save agent network settings: %w", err)
}
return settings, nil
@@ -680,7 +751,7 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID,
// counter view; permission gate is the same Read role that gates
// every other agent-network surface.
func (m *managerImpl) ListConsumption(ctx context.Context, accountID, userID string) ([]*types.Consumption, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkUsage, operations.Read); err != nil {
return nil, err
}
return m.store.ListAgentNetworkConsumption(ctx, store.LockingStrengthNone, accountID)
@@ -689,7 +760,7 @@ func (m *managerImpl) ListConsumption(ctx context.Context, accountID, userID str
// ListAccessLogs returns a paginated, server-side-filtered page of
// agent-network access logs plus the total count matching the filter.
func (m *managerImpl) ListAccessLogs(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLog, int64, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkLogs, operations.Read); err != nil {
return nil, 0, err
}
return m.store.GetAgentNetworkAccessLogs(ctx, store.LockingStrengthNone, accountID, filter)
@@ -699,7 +770,7 @@ func (m *managerImpl) ListAccessLogs(ctx context.Context, accountID, userID stri
// agent-network access logs grouped by session, plus the total number of
// sessions matching the filter.
func (m *managerImpl) ListAccessLogSessions(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLogSession, int64, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkLogs, operations.Read); err != nil {
return nil, 0, err
}
return m.store.GetAgentNetworkAccessLogSessions(ctx, store.LockingStrengthNone, accountID, filter)
@@ -708,7 +779,7 @@ func (m *managerImpl) ListAccessLogSessions(ctx context.Context, accountID, user
// GetUsageOverview returns the filtered usage rows aggregated into time buckets
// at the requested granularity, oldest-first.
func (m *managerImpl) GetUsageOverview(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter, granularity types.UsageGranularity) ([]*types.AgentNetworkUsageBucket, error) {
if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkUsage, operations.Read); err != nil {
return nil, err
}
rows, err := m.store.GetAgentNetworkUsageRows(ctx, store.LockingStrengthNone, accountID, filter)
@@ -782,8 +853,8 @@ func (m *managerImpl) RecordConsumption(ctx context.Context, accountID string, k
return m.store.IncrementAgentNetworkConsumption(ctx, accountID, kind, dimID, windowSeconds, windowStart, tokensIn, tokensOut, costUSD)
}
func (m *managerImpl) requirePermission(ctx context.Context, accountID, userID string, op operations.Operation) error {
ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.AgentNetwork, op)
func (m *managerImpl) requirePermission(ctx context.Context, accountID, userID string, module modules.Module, op operations.Operation) error {
ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, module, op)
if err != nil {
return status.NewPermissionValidationError(err)
}
@@ -872,8 +943,8 @@ func (*mockManager) UpdateBudgetRule(_ context.Context, _ string, r *types.Accou
func (*mockManager) DeleteBudgetRule(_ context.Context, _, _, _ string) error { return nil }
func (*mockManager) GetSettings(_ context.Context, _, _ string) (*types.Settings, error) {
return nil, status.Errorf(status.NotFound, "agent network settings not found")
func (*mockManager) GetSettings(_ context.Context, accountID, _ string) (*types.Settings, error) {
return types.DefaultSettings(accountID), nil
}
func (*mockManager) UpdateSettings(_ context.Context, _ string, s *types.Settings) (*types.Settings, error) {
management/internals/modules/agentnetwork/policyselect.go
+108
View File
@@ -5,6 +5,7 @@ import (
"fmt"
"math"
"sort"
"strings"
"time"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
@@ -35,6 +36,10 @@ const (
denyCodeAccountTokenCapExceeded = "llm_account.token_cap_exceeded"
//nolint:gosec // account deny code label, not a credential
denyCodeAccountBudgetCapExceeded = "llm_account.budget_cap_exceeded"
// denyCodeModelBlocked is returned when policies govern the request's
// (provider, caller-groups) but none permits the model. Matches the proxy
// guardrail's code so both layers surface the same label.
denyCodeModelBlocked = "llm_policy.model_blocked"
)
// consumptionCache holds the consumption counters prefetched for one
@@ -159,6 +164,25 @@ func (m *managerImpl) SelectPolicyForRequest(ctx context.Context, in PolicySelec
}
candidates := filterApplicablePolicies(policies, in)
// Model-allowlist gate scoped to the matched policies: keep candidates whose
// guardrails permit the model (none enabled = unrestricted), deny when
// policies apply but none permits it. Skip the load when none has a guardrail.
if len(candidates) > 0 && anyPolicyHasGuardrails(candidates) {
guardrailsByID, gErr := m.loadGuardrailsByID(ctx, in.AccountID)
if gErr != nil {
return nil, gErr
}
permitted := filterModelPermittedPolicies(candidates, guardrailsByID, in.Model)
if len(permitted) == 0 {
return &PolicySelectionResult{
Allow: false,
DenyCode: denyCodeModelBlocked,
DenyReason: modelBlockedReason(in.Model),
}, nil
}
candidates = permitted
}
// Prefetch every consumption counter the ceiling + candidate policies will
// read, in a single store round-trip, then score against the cache.
cache, err := m.prefetchConsumption(ctx, in, rules, candidates, now)
@@ -250,6 +274,90 @@ func filterApplicablePolicies(policies []*types.Policy, in PolicySelectionInput)
return out
}
// anyPolicyHasGuardrails reports whether any policy references at least one
// guardrail, so the selector can skip loading guardrails when none do.
func anyPolicyHasGuardrails(policies []*types.Policy) bool {
for _, p := range policies {
if p != nil && len(p.GuardrailIDs) > 0 {
return true
}
}
return false
}
// loadGuardrailsByID loads the account's guardrails indexed by ID. Used by the
// model-allowlist gate to resolve each candidate policy's attached guardrails.
func (m *managerImpl) loadGuardrailsByID(ctx context.Context, accountID string) (map[string]*types.Guardrail, error) {
guardrails, err := m.store.GetAccountAgentNetworkGuardrails(ctx, store.LockingStrengthNone, accountID)
if err != nil {
return nil, fmt.Errorf("list account guardrails: %w", err)
}
byID := make(map[string]*types.Guardrail, len(guardrails))
for _, g := range guardrails {
if g != nil {
byID[g.ID] = g
}
}
return byID, nil
}
// filterModelPermittedPolicies returns the subset of policies whose guardrails
// permit the model. Order is preserved so downstream scoring is unaffected.
func filterModelPermittedPolicies(policies []*types.Policy, byID map[string]*types.Guardrail, model string) []*types.Policy {
out := make([]*types.Policy, 0, len(policies))
for _, p := range policies {
if policyPermitsModel(p, byID, model) {
out = append(out, p)
}
}
return out
}
// policyPermitsModel reports whether a policy permits the model. No
// allowlist-enabled guardrail = unrestricted (permits any, incl. empty);
// otherwise the model must be in the union of its allowlists, so an
// empty/undetermined model fails closed.
func policyPermitsModel(p *types.Policy, byID map[string]*types.Guardrail, model string) bool {
if p == nil {
return false
}
wanted := normaliseModelID(model)
restricted := false
for _, gID := range p.GuardrailIDs {
g, ok := byID[gID]
if !ok || g == nil || !g.Checks.ModelAllowlist.Enabled {
continue
}
restricted = true
if wanted == "" {
continue
}
for _, allowed := range g.Checks.ModelAllowlist.Models {
if normaliseModelID(allowed) == wanted {
return true
}
}
}
return !restricted
}
// normaliseModelID lowercases and trims a model identifier so the allowlist
// compare is case-insensitive and trim-tolerant. Mirrors the proxy guardrail's
// normaliseModel so both layers agree on what "same model" means.
func normaliseModelID(model string) string {
return strings.ToLower(strings.TrimSpace(model))
}
// modelBlockedReason builds the human-readable deny reason for a model-allowlist
// rejection. The model is quoted when known; an undetermined model is reported
// as such so the access log distinguishes "wrong model" from "no model".
func modelBlockedReason(model string) string {
if normaliseModelID(model) == "" {
return "request model could not be determined for the policy allowlist"
}
return fmt.Sprintf("model %q is not permitted by any applicable policy allowlist", model)
}
// candidate is the per-policy intermediate the selector ranks. A
// policy that's been exhausted on any enabled cap never makes it
// into this slice; the selector's deny envelope carries the latest
management/internals/modules/agentnetwork/policyselect_model_test.go
+329
View File
@@ -0,0 +1,329 @@
package agentnetwork
import (
"context"
"errors"
"testing"
"time"
"github.com/golang/mock/gomock"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
"github.com/netbirdio/netbird/management/server/store"
)
// guardedPolicy builds an enabled, uncapped policy that authorises sourceGroups
// to reach providerID under the given guardrails. Uncapped keeps the selector's
// headroom scoring trivial so these tests isolate the model-allowlist gate.
func guardedPolicy(id, account string, sourceGroups []string, providerID string, guardrailIDs ...string) *types.Policy {
return &types.Policy{
ID: id,
AccountID: account,
Enabled: true,
SourceGroups: sourceGroups,
DestinationProviderIDs: []string{providerID},
GuardrailIDs: guardrailIDs,
CreatedAt: time.Now().UTC(),
}
}
// allowlistGuardrail builds a guardrail whose model allowlist is enabled and
// carries the given models.
func allowlistGuardrail(id, account string, models ...string) *types.Guardrail {
return &types.Guardrail{
ID: id,
AccountID: account,
Checks: types.GuardrailChecks{
ModelAllowlist: types.GuardrailModelAllowlist{Enabled: true, Models: models},
},
}
}
func expectPolicies(mockStore *store.MockStore, account string, policies ...*types.Policy) {
mockStore.EXPECT().
GetAccountAgentNetworkPolicies(gomock.Any(), gomock.Any(), account).
Return(policies, nil)
}
func expectGuardrails(mockStore *store.MockStore, account string, guardrails ...*types.Guardrail) {
mockStore.EXPECT().
GetAccountAgentNetworkGuardrails(gomock.Any(), gomock.Any(), account).
Return(guardrails, nil)
}
// TestSelectPolicy_ModelBlockedByAllowlist proves the authoritative allowlist
// decision: a policy authorises the (provider, group) but restricts the model,
// and the requested model isn't on the list, so the request is denied.
func TestSelectPolicy_ModelBlockedByAllowlist(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o"))
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
UserID: "user-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "claude-opus-4",
})
require.NoError(t, err)
assert.False(t, res.Allow, "a model outside the only applicable policy's allowlist must be denied")
assert.Equal(t, denyCodeModelBlocked, res.DenyCode, "deny code must be model_blocked")
assert.NotEmpty(t, res.DenyReason, "deny reason must be populated")
}
// TestSelectPolicy_ModelAllowedByAllowlist is the allow counterpart: the model
// is on the applicable policy's allowlist, so selection proceeds normally.
func TestSelectPolicy_ModelAllowedByAllowlist(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o", "claude-opus-4"))
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
UserID: "user-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "claude-opus-4",
})
require.NoError(t, err)
assert.True(t, res.Allow, "a model on the applicable policy's allowlist must be allowed")
assert.Equal(t, "pol-A", res.SelectedPolicyID)
}
// TestSelectPolicy_CaseInsensitiveModelMatch proves the compare tolerates case
// and surrounding whitespace, matching the proxy guardrail's normalisation.
func TestSelectPolicy_CaseInsensitiveModelMatch(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", " GPT-4o "))
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "gpt-4o",
})
require.NoError(t, err)
assert.True(t, res.Allow, "case/whitespace variants must match the allowlist entry")
}
// TestSelectPolicy_UnguardedPolicyIsUnrestricted is the false-deny fix: when two
// policies authorise the same (provider, group) and one has no guardrail, that
// policy makes the request unrestricted — not caught by the other's allowlist.
func TestSelectPolicy_UnguardedPolicyIsUnrestricted(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
restricted := guardedPolicy("pol-restricted", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
open := guardedPolicy("pol-open", "acc-1", []string{"grp-eng"}, "prov-1") // no guardrail
expectPolicies(mockStore, "acc-1", restricted, open)
expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o"))
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "claude-opus-4",
})
require.NoError(t, err)
assert.True(t, res.Allow, "an un-guardrailed policy for the same (provider, group) must leave the request unrestricted")
assert.Equal(t, "pol-open", res.SelectedPolicyID, "the unrestricted policy must be the one that pays")
}
// TestSelectPolicy_AllowlistDoesNotLeakAcrossGroups is the false-allow fix: a
// model allowlisted only for grp-b must not be usable by a grp-a caller. The
// selector considers only policies applicable to the caller's groups.
func TestSelectPolicy_AllowlistDoesNotLeakAcrossGroups(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
polA := guardedPolicy("pol-a", "acc-1", []string{"grp-a"}, "prov-1", "g-a")
polB := guardedPolicy("pol-b", "acc-1", []string{"grp-b"}, "prov-1", "g-b")
expectPolicies(mockStore, "acc-1", polA, polB)
expectGuardrails(mockStore, "acc-1",
allowlistGuardrail("g-a", "acc-1", "gpt-4o"),
allowlistGuardrail("g-b", "acc-1", "claude-opus-4"),
)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-a"},
ProviderID: "prov-1",
Model: "claude-opus-4", // only allowed for grp-b
})
require.NoError(t, err)
assert.False(t, res.Allow, "grp-b's allowlisted model must not leak to a grp-a caller")
assert.Equal(t, denyCodeModelBlocked, res.DenyCode)
}
// TestSelectPolicy_UndeterminedModelFailsClosed proves the fail-closed contract
// mirrors the proxy: with a restricted applicable policy and an empty model
// (e.g. a path-routed shape the parser couldn't map), the request is denied.
func TestSelectPolicy_UndeterminedModelFailsClosed(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o"))
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "", // undetermined
})
require.NoError(t, err)
assert.False(t, res.Allow, "an undetermined model must fail closed against a restricted policy")
assert.Equal(t, denyCodeModelBlocked, res.DenyCode)
}
// TestSelectPolicy_DisabledAllowlistDoesNotRestrict proves a guardrail whose
// model allowlist is disabled imposes no model restriction, even though the
// policy references it.
func TestSelectPolicy_DisabledAllowlistDoesNotRestrict(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
disabled := &types.Guardrail{
ID: "g-1",
AccountID: "acc-1",
Checks: types.GuardrailChecks{
ModelAllowlist: types.GuardrailModelAllowlist{Enabled: false, Models: []string{"gpt-4o"}},
},
}
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1", disabled)
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "anything-goes",
})
require.NoError(t, err)
assert.True(t, res.Allow, "a disabled allowlist must not restrict the model")
assert.Equal(t, "pol-A", res.SelectedPolicyID)
}
// TestSelectPolicy_UnionAcrossPolicyGuardrails proves a policy with multiple
// allowlist guardrails permits the union of their models (not just the first).
func TestSelectPolicy_UnionAcrossPolicyGuardrails(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1", "g-2")
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1",
allowlistGuardrail("g-1", "acc-1", "gpt-4o"),
allowlistGuardrail("g-2", "acc-1", "claude-opus-4"),
)
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "claude-opus-4", // only in the second guardrail's list
})
require.NoError(t, err)
assert.True(t, res.Allow, "a model in any of the policy's allowlist guardrails must be permitted")
assert.Equal(t, "pol-A", res.SelectedPolicyID)
}
// TestSelectPolicy_GuardrailLookupErrorPropagates proves a store failure while
// resolving the candidate policies' guardrails surfaces as an error, not a
// silent allow/deny.
func TestSelectPolicy_GuardrailLookupErrorPropagates(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
expectPolicies(mockStore, "acc-1", policy)
mockStore.EXPECT().
GetAccountAgentNetworkGuardrails(gomock.Any(), gomock.Any(), "acc-1").
Return(nil, errors.New("store unavailable"))
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "gpt-4o",
})
require.Error(t, err, "a guardrail-lookup failure must surface as an error")
assert.Nil(t, res)
}
// TestSelectPolicy_MissingGuardrailReferenceTreatedAsUnrestricted proves a
// policy referencing a guardrail ID absent from the account's set (a stale
// reference) imposes no model restriction — same as no guardrail.
func TestSelectPolicy_MissingGuardrailReferenceTreatedAsUnrestricted(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-missing")
expectPolicies(mockStore, "acc-1", policy)
expectGuardrails(mockStore, "acc-1")
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "anything-goes",
})
require.NoError(t, err)
assert.True(t, res.Allow, "an orphaned guardrail reference must not restrict the model")
assert.Equal(t, "pol-A", res.SelectedPolicyID)
}
// TestSelectPolicy_PartialCandidatesPermittedAfterModelFilter proves the model
// gate narrows candidates before cap scoring: the permitting policy is selected
// even though the blocked one has a larger, more attractive cap.
func TestSelectPolicy_PartialCandidatesPermittedAfterModelFilter(t *testing.T) {
ctrl := gomock.NewController(t)
mgr, mockStore := newSelectorMgr(t, ctrl)
polBig := guardedPolicy("pol-big", "acc-1", []string{"grp-eng"}, "prov-1", "g-restrict")
polBig.Limits = types.PolicyLimits{
TokenLimit: types.PolicyTokenLimit{Enabled: true, GroupCap: 1_000_000, WindowSeconds: 3600},
}
polSmall := guardedPolicy("pol-small", "acc-1", []string{"grp-eng"}, "prov-1", "g-permit")
polSmall.Limits = types.PolicyLimits{
TokenLimit: types.PolicyTokenLimit{Enabled: true, GroupCap: 100, WindowSeconds: 3600},
}
expectPolicies(mockStore, "acc-1", polBig, polSmall)
expectGuardrails(mockStore, "acc-1",
allowlistGuardrail("g-restrict", "acc-1", "gpt-4o"),
allowlistGuardrail("g-permit", "acc-1", "claude-opus-4"),
)
expectConsumptionBatch(mockStore, nil)
res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
AccountID: "acc-1",
GroupIDs: []string{"grp-eng"},
ProviderID: "prov-1",
Model: "claude-opus-4", // only pol-small's guardrail permits this
})
require.NoError(t, err)
assert.True(t, res.Allow)
assert.Equal(t, "pol-small", res.SelectedPolicyID,
"the model filter must exclude pol-big before cap scoring")
}
management/internals/modules/agentnetwork/pricing/defaults.go
+156
View File
@@ -0,0 +1,156 @@
// Package pricing builds the default LLM pricing table the synthesizer
// ships to the proxy's cost_meter middleware. The catalog is the single
// source of default rates: every catalog provider's models are folded
// into the pricing surfaces the provider declares (PricingSurfaces),
// then a small supplemental list adds priced-but-not-operator-selectable
// entries. Management is the sole pricing authority — the proxy carries
// no embedded price list and bills exclusively from the table it is
// sent.
//go:generate go run gen.go
package pricing
import (
"sync"
"sync/atomic"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/catalog"
)
// Entry is a single model's pricing in USD per 1k tokens. This struct IS
// the wire shape: the synthesizer marshals it verbatim into cost_meter's
// ConfigJSON, and the proxy unmarshals the same field names.
//
// A zero rate means "no rate configured" — the proxy bills that cache
// bucket at InputPer1k (identical semantics to the retired proxy-embedded
// table). CachedInputPer1k is the OpenAI shape (cached prompt tokens are
// a subset of input); CacheReadPer1k / CacheCreationPer1k are the
// Anthropic shape (additive buckets).
type Entry struct {
InputPer1k float64 `json:"input_per_1k"`
OutputPer1k float64 `json:"output_per_1k"`
CachedInputPer1k float64 `json:"cached_input_per_1k,omitempty"`
CacheReadPer1k float64 `json:"cache_read_per_1k,omitempty"`
CacheCreationPer1k float64 `json:"cache_creation_per_1k,omitempty"`
}
// supplementalDefaults are (surface, model) entries that are priced but
// deliberately not operator-selectable in the catalog. Each carries a
// reason; when one of these models joins a catalog lineup, delete the
// row here — the collision test fails loudly if the rates ever disagree.
var supplementalDefaults = map[string]map[string]Entry{
"openai": {
// GPT-5 (2025) family — kept for gateway requests using the
// unsuffixed ids; the dashboard offers only the 5.x lineup.
"gpt-5": {InputPer1k: 0.00125, OutputPer1k: 0.01, CachedInputPer1k: 0.000125},
"gpt-5-mini": {InputPer1k: 0.00025, OutputPer1k: 0.002, CachedInputPer1k: 0.000025},
"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 (
compiledOnce sync.Once
compiledTable map[string]map[string]Entry
// mergedTable holds the current live table when a pricing defaults
// file is loaded: the file merged entry-whole over the compiled-in
// base. Nil while no file is loaded (or after the file is removed),
// in which case the compiled-in table serves. Swapped atomically by
// the file loader/reloader; readers never block.
mergedTable atomic.Pointer[map[string]map[string]Entry]
)
// DefaultTable returns the current default pricing table keyed
// surface -> model -> Entry: the management-side defaults file (see
// LoadFile / StartReloader) when one is loaded, merged over the
// compiled-in catalog table, which alone serves as the fallback when no
// file exists. The snapshot may change between calls as the file is
// re-read — consumers (the synthesizer on every reconcile, the catalog
// endpoint on every request) pick up fresh rates automatically. Callers
// must not mutate the returned maps.
func DefaultTable() map[string]map[string]Entry {
if t := mergedTable.Load(); t != nil {
return *t
}
return compiledBase()
}
// compiledBase returns the compiled-in table (catalog + supplementals),
// built once.
func compiledBase() map[string]map[string]Entry {
compiledOnce.Do(func() {
compiledTable = buildDefaultTable()
})
return compiledTable
}
func buildDefaultTable() map[string]map[string]Entry {
out := make(map[string]map[string]Entry)
for _, p := range catalog.All() {
for _, surface := range p.PricingSurfaces {
inner, ok := out[surface]
if !ok {
inner = make(map[string]Entry)
out[surface] = inner
}
for _, m := range p.Models {
// First writer wins; providers contributing the same
// (surface, model) must agree on rates — enforced by
// TestDefaultTable_NoConflictingContributions.
if _, dup := inner[m.ID]; dup {
continue
}
inner[m.ID] = entryFromCatalogModel(m)
}
}
}
for surface, models := range supplementalDefaults {
inner, ok := out[surface]
if !ok {
inner = make(map[string]Entry)
out[surface] = inner
}
for id, e := range models {
if _, dup := inner[id]; dup {
continue
}
inner[id] = e
}
}
return out
}
func entryFromCatalogModel(m catalog.Model) Entry {
return Entry{
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
CachedInputPer1k: m.CachedInputPer1k,
CacheReadPer1k: m.CacheReadPer1k,
CacheCreationPer1k: m.CacheCreationPer1k,
}
}
// LookupDefault returns the default entry for model on the first of the
// given surfaces that prices it. Used by the synthesizer to seed a
// per-provider entry with default cache rates before overlaying the
// operator's stored prices.
func LookupDefault(surfaces []string, model string) (Entry, bool) {
table := DefaultTable()
for _, s := range surfaces {
if e, ok := table[s][model]; ok {
return e, true
}
}
return Entry{}, false
}
management/internals/modules/agentnetwork/pricing/defaults_llm_pricing.example.yaml
+282
View File
@@ -0,0 +1,282 @@
# Default LLM pricing used by NetBird's Agent Network cost metering.
# GENERATED from the management catalog — do not edit this file in the
# repository; regenerate with:
#
# go generate ./management/internals/modules/agentnetwork/pricing
#
# Operators: copy this file to <datadir>/defaults_llm_pricing.yaml (or
# any path configured via management.json:
#
# { "AgentNetwork": { "PricingDefaultsFile": "/path/defaults_llm_pricing.yaml" } }
#
# ) and adjust the entries you want to change. Management re-reads the
# file periodically (mtime poll, every minute): the live table feeds the
# proxies' cost metering and the dashboard's model-price prefill, so
# edits apply without a restart. Your file only needs the entries you
# want to change — but each entry REPLACES the built-in entry for that
# surface+model whole, so repeat the cache rates you want to keep.
# Unknown fields and negative or non-finite rates are rejected: at
# startup that fails boot (for an explicitly configured path); at
# runtime the previous table is kept and a warning is logged. Deleting
# the file reverts to the built-in defaults below.
#
# Top-level keys are pricing surfaces — the parser shape requests are
# metered under: "openai" (also Azure, Mistral, and OpenAI-compatible
# gateways), "anthropic" (also Anthropic-on-Vertex), "bedrock"
# (normalized ids, e.g. anthropic.claude-sonnet-4-5). Model keys must be
# the normalized id the proxy meters (version/region suffixes stripped).
#
# Values are USD per 1_000 tokens. Optional cache fields:
# cached_input_per_1k OpenAI shape: rate for cached prompt tokens
# (a SUBSET of input tokens). Absent -> cached
# portion bills at input_per_1k.
# cache_read_per_1k Anthropic shape: rate for cache_read tokens
# (ADDITIVE to input). Absent -> input rate.
# cache_creation_per_1k Anthropic shape: rate for cache_creation
# tokens (ADDITIVE to input). Absent -> input
# rate.
anthropic:
claude-fable-5:
input_per_1k: 0.01
output_per_1k: 0.05
cache_read_per_1k: 0.001
cache_creation_per_1k: 0.0125
claude-haiku-4-5:
input_per_1k: 0.001
output_per_1k: 0.005
cache_read_per_1k: 0.0001
cache_creation_per_1k: 0.00125
claude-opus-4-1:
input_per_1k: 0.015
output_per_1k: 0.075
cache_read_per_1k: 0.0015
cache_creation_per_1k: 0.01875
claude-opus-4-6:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
claude-opus-4-7:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
claude-opus-4-8:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
claude-opus-5:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
claude-sonnet-4-5:
input_per_1k: 0.003
output_per_1k: 0.015
cache_read_per_1k: 0.0003
cache_creation_per_1k: 0.00375
claude-sonnet-4-6:
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
cached_input_per_1k: 0.0003
cache_read_per_1k: 0.0003
"kimi-k3[1m]":
input_per_1k: 0.003
output_per_1k: 0.015
cache_read_per_1k: 0.0003
bedrock:
amazon.nova-2-lite:
input_per_1k: 0.0003
output_per_1k: 0.0025
amazon.nova-lite:
input_per_1k: 0.00006
output_per_1k: 0.00024
amazon.nova-micro:
input_per_1k: 0.000035
output_per_1k: 0.00014
amazon.nova-pro:
input_per_1k: 0.0008
output_per_1k: 0.0032
anthropic.claude-haiku-4-5:
input_per_1k: 0.001
output_per_1k: 0.005
cache_read_per_1k: 0.0001
cache_creation_per_1k: 0.00125
anthropic.claude-opus-4-1:
input_per_1k: 0.015
output_per_1k: 0.075
cache_read_per_1k: 0.0015
cache_creation_per_1k: 0.01875
anthropic.claude-opus-4-6:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
anthropic.claude-opus-4-7:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
anthropic.claude-opus-4-8:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
anthropic.claude-opus-5:
input_per_1k: 0.005
output_per_1k: 0.025
cache_read_per_1k: 0.0005
cache_creation_per_1k: 0.00625
anthropic.claude-sonnet-4-5:
input_per_1k: 0.003
output_per_1k: 0.015
cache_read_per_1k: 0.0003
cache_creation_per_1k: 0.00375
anthropic.claude-sonnet-4-6:
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
openai:
codestral-2508:
input_per_1k: 0.0003
output_per_1k: 0.0009
codestral-latest:
input_per_1k: 0.001
output_per_1k: 0.003
devstral-medium-latest:
input_per_1k: 0.0004
output_per_1k: 0.002
devstral-small-latest:
input_per_1k: 0.0001
output_per_1k: 0.0003
gpt-3.5-turbo:
input_per_1k: 0.0005
output_per_1k: 0.0015
gpt-35-turbo:
input_per_1k: 0.0005
output_per_1k: 0.0015
gpt-4-turbo:
input_per_1k: 0.01
output_per_1k: 0.03
gpt-4.1:
input_per_1k: 0.002
output_per_1k: 0.008
cached_input_per_1k: 0.0005
gpt-4.1-mini:
input_per_1k: 0.0004
output_per_1k: 0.0016
cached_input_per_1k: 0.0001
gpt-4.1-nano:
input_per_1k: 0.0001
output_per_1k: 0.0004
cached_input_per_1k: 0.000025
gpt-4o:
input_per_1k: 0.0025
output_per_1k: 0.01
cached_input_per_1k: 0.00125
gpt-4o-mini:
input_per_1k: 0.00015
output_per_1k: 0.0006
cached_input_per_1k: 0.000075
gpt-5:
input_per_1k: 0.00125
output_per_1k: 0.01
cached_input_per_1k: 0.000125
gpt-5-mini:
input_per_1k: 0.00025
output_per_1k: 0.002
cached_input_per_1k: 0.000025
gpt-5-nano:
input_per_1k: 0.00005
output_per_1k: 0.0004
cached_input_per_1k: 0.000005
gpt-5.3-chat-latest:
input_per_1k: 0.00175
output_per_1k: 0.014
cached_input_per_1k: 0.000175
gpt-5.3-codex:
input_per_1k: 0.00175
output_per_1k: 0.014
cached_input_per_1k: 0.000175
gpt-5.4:
input_per_1k: 0.0025
output_per_1k: 0.015
cached_input_per_1k: 0.00025
gpt-5.4-mini:
input_per_1k: 0.00075
output_per_1k: 0.0045
cached_input_per_1k: 0.000075
gpt-5.4-nano:
input_per_1k: 0.0002
output_per_1k: 0.00125
cached_input_per_1k: 0.00002
gpt-5.4-pro:
input_per_1k: 0.03
output_per_1k: 0.18
cached_input_per_1k: 0.003
gpt-5.5:
input_per_1k: 0.005
output_per_1k: 0.03
cached_input_per_1k: 0.0005
gpt-5.5-pro:
input_per_1k: 0.03
output_per_1k: 0.18
cached_input_per_1k: 0.003
kimi-k3:
input_per_1k: 0.003
output_per_1k: 0.015
cached_input_per_1k: 0.0003
cache_read_per_1k: 0.0003
magistral-medium-latest:
input_per_1k: 0.002
output_per_1k: 0.005
magistral-small-latest:
input_per_1k: 0.0005
output_per_1k: 0.0015
ministral-3-14b-2512:
input_per_1k: 0.0002
output_per_1k: 0.0002
ministral-3-3b-2512:
input_per_1k: 0.0001
output_per_1k: 0.0001
ministral-8b-latest:
input_per_1k: 0.00015
output_per_1k: 0.00015
mistral-embed:
input_per_1k: 0.0001
output_per_1k: 0
mistral-large-latest:
input_per_1k: 0.0005
output_per_1k: 0.0015
mistral-medium-3-5:
input_per_1k: 0.0015
output_per_1k: 0.0075
mistral-medium-latest:
input_per_1k: 0.0004
output_per_1k: 0.002
mistral-small-latest:
input_per_1k: 0.00006
output_per_1k: 0.00018
o4-mini:
input_per_1k: 0.0011
output_per_1k: 0.0044
cached_input_per_1k: 0.000275
text-embedding-3-large:
input_per_1k: 0.00013
output_per_1k: 0
text-embedding-3-small:
input_per_1k: 0.00002
output_per_1k: 0
management/internals/modules/agentnetwork/pricing/defaults_test.go
+148
View File
@@ -0,0 +1,148 @@
package pricing
import (
"math"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/catalog"
)
// TestDefaultTable_CoversEveryCatalogModel replaces the proxy's old
// hand-maintained coverage list: because the table is built FROM the
// catalog, drift is impossible by construction — this test guards the
// fold itself (every catalog model of every surfaced provider resolves,
// with exactly the catalog's rates).
func TestDefaultTable_CoversEveryCatalogModel(t *testing.T) {
table := DefaultTable()
for _, p := range catalog.All() {
if len(p.PricingSurfaces) == 0 {
assert.Empty(t, p.Models, "catalog entry %s declares models but no pricing surfaces — those models would never be priced", p.ID)
continue
}
for _, surface := range p.PricingSurfaces {
byModel, ok := table[surface]
require.True(t, ok, "surface %q (provider %s) missing from default table", surface, p.ID)
for _, m := range p.Models {
e, ok := byModel[m.ID]
require.True(t, ok, "%s/%s (provider %s) missing from default table", surface, m.ID, p.ID)
assert.Equal(t, m.InputPer1k, e.InputPer1k, "%s/%s input rate", surface, m.ID)
assert.Equal(t, m.OutputPer1k, e.OutputPer1k, "%s/%s output rate", surface, m.ID)
}
}
}
}
// TestDefaultTable_NoConflictingContributions enforces the collision rule
// documented on catalog.Provider.PricingSurfaces: when two catalog
// providers contribute the same (surface, model) pair — azure/vertex
// mirroring openai/anthropic, kimi on both surfaces — their rates must be
// identical, because the surface-keyed table can only hold one entry.
// If a provider ever diverges (e.g. Azure reprices a model), this fails
// and the divergence must move to per-provider-record pricing.
func TestDefaultTable_NoConflictingContributions(t *testing.T) {
type contribution struct {
providerID string
entry Entry
}
seen := map[string]map[string]contribution{}
for _, p := range catalog.All() {
for _, surface := range p.PricingSurfaces {
if seen[surface] == nil {
seen[surface] = map[string]contribution{}
}
for _, m := range p.Models {
e := entryFromCatalogModel(m)
if prev, dup := seen[surface][m.ID]; dup {
assert.Equal(t, prev.entry, e,
"%s/%s: %s and %s contribute different rates", surface, m.ID, prev.providerID, p.ID)
continue
}
seen[surface][m.ID] = contribution{providerID: p.ID, entry: e}
}
}
}
// Supplemental entries must never shadow a catalog-contributed model —
// they exist precisely because the catalog does NOT list them.
for surface, models := range supplementalDefaults {
for id := range models {
_, fromCatalog := seen[surface][id]
assert.False(t, fromCatalog, "supplemental %s/%s is now in the catalog — delete the supplemental row", surface, id)
}
}
}
// TestDefaultTable_AllRatesFiniteNonNegative mirrors the proxy-side
// NewTable validation so a bad catalog edit is caught here, at unit-test
// time, rather than as a chain-build failure on every proxy.
func TestDefaultTable_AllRatesFiniteNonNegative(t *testing.T) {
for surface, models := range DefaultTable() {
for id, e := range models {
for field, v := range map[string]float64{
"input": e.InputPer1k,
"output": e.OutputPer1k,
"cached_input": e.CachedInputPer1k,
"cache_read": e.CacheReadPer1k,
"cache_creation": e.CacheCreationPer1k,
} {
assert.False(t, v < 0 || math.IsNaN(v) || math.IsInf(v, 0),
"%s/%s: %s rate %v must be finite and non-negative", surface, id, field, v)
}
}
}
}
// TestDefaultTable_PinnedRates pins rates that previously drifted or are
// easy to mis-enter (carried over from the proxy's retired
// defaults_coverage_test), plus the supplemental entries.
func TestDefaultTable_PinnedRates(t *testing.T) {
table := DefaultTable()
gpt54 := table["openai"]["gpt-5.4"]
assert.InDelta(t, 0.0025, gpt54.InputPer1k, 1e-9, "gpt-5.4 input")
assert.InDelta(t, 0.015, gpt54.OutputPer1k, 1e-9, "gpt-5.4 output")
assert.InDelta(t, 0.00025, gpt54.CachedInputPer1k, 1e-9, "gpt-5.4 cached input")
sonnet := table["bedrock"]["anthropic.claude-sonnet-4-5"]
assert.InDelta(t, 0.003, sonnet.InputPer1k, 1e-9, "bedrock sonnet-4-5 input")
assert.InDelta(t, 0.015, sonnet.OutputPer1k, 1e-9, "bedrock sonnet-4-5 output")
assert.InDelta(t, 0.0003, sonnet.CacheReadPer1k, 1e-9, "bedrock sonnet-4-5 cache read")
assert.InDelta(t, 0.00375, sonnet.CacheCreationPer1k, 1e-9, "bedrock sonnet-4-5 cache creation")
// Vertex Claude prices under "anthropic" with the bare id.
fable := table["anthropic"]["claude-fable-5"]
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.
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"},
} {
for _, id := range ids {
_, ok := table[surface][id]
assert.True(t, ok, "%s/%s must be priced", surface, id)
}
}
// Embeddings bill input-only — output stays zero.
emb := table["openai"]["text-embedding-3-large"]
assert.Zero(t, emb.OutputPer1k, "embedding output rate must be zero")
assert.Positive(t, emb.InputPer1k, "embedding input rate must be set")
}
func TestLookupDefault_SurfaceOrder(t *testing.T) {
// kimi-k3 exists on both surfaces; first surface in the slice wins.
e, ok := LookupDefault([]string{"openai", "anthropic"}, "kimi-k3")
require.True(t, ok)
assert.InDelta(t, 0.003, e.InputPer1k, 1e-9)
_, ok = LookupDefault([]string{"bedrock"}, "gpt-4o")
assert.False(t, ok, "gpt-4o is not a bedrock model")
_, ok = LookupDefault(nil, "gpt-4o")
assert.False(t, ok, "no surfaces, no match")
}
management/internals/modules/agentnetwork/pricing/exampleyaml.go
+109
View File
@@ -0,0 +1,109 @@
package pricing
import (
"bytes"
"fmt"
"sort"
"strconv"
)
// MarshalDefaultsYAML renders the built-in default pricing table (catalog
// + supplementals, WITHOUT any operator override) as the YAML schema
// LoadOverrideFile consumes. It backs the generated
// defaults_llm_pricing.example.yaml so operators start from a file that
// matches the compiled-in rates exactly; a golden test keeps the two in
// sync. Output is deterministic (sorted surfaces and models).
func MarshalDefaultsYAML() []byte {
var b bytes.Buffer
b.WriteString(exampleHeader)
table := buildDefaultTable()
surfaces := make([]string, 0, len(table))
for s := range table {
surfaces = append(surfaces, s)
}
sort.Strings(surfaces)
for _, surface := range surfaces {
fmt.Fprintf(&b, "\n%s:\n", surface)
models := table[surface]
ids := make([]string, 0, len(models))
for id := range models {
ids = append(ids, id)
}
sort.Strings(ids)
for _, id := range ids {
e := models[id]
fmt.Fprintf(&b, " %s:\n", yamlKey(id))
fmt.Fprintf(&b, " input_per_1k: %s\n", rate(e.InputPer1k))
fmt.Fprintf(&b, " output_per_1k: %s\n", rate(e.OutputPer1k))
if e.CachedInputPer1k > 0 {
fmt.Fprintf(&b, " cached_input_per_1k: %s\n", rate(e.CachedInputPer1k))
}
if e.CacheReadPer1k > 0 {
fmt.Fprintf(&b, " cache_read_per_1k: %s\n", rate(e.CacheReadPer1k))
}
if e.CacheCreationPer1k > 0 {
fmt.Fprintf(&b, " cache_creation_per_1k: %s\n", rate(e.CacheCreationPer1k))
}
}
}
return b.Bytes()
}
// rate renders a USD-per-1k rate without float noise ("0.00015", not
// "0.000150000000...").
func rate(v float64) string {
return strconv.FormatFloat(v, 'f', -1, 64)
}
// yamlKey quotes model ids that YAML would otherwise misparse (e.g.
// "kimi-k3[1m]" starts a flow sequence unquoted).
func yamlKey(id string) string {
for _, r := range id {
switch r {
case '[', ']', '{', '}', ':', '#', ',', '&', '*', '!', '|', '>', '\'', '"', '%', '@', '`':
return strconv.Quote(id)
}
}
return id
}
const exampleHeader = `# Default LLM pricing used by NetBird's Agent Network cost metering.
# GENERATED from the management catalog — do not edit this file in the
# repository; regenerate with:
#
# go generate ./management/internals/modules/agentnetwork/pricing
#
# Operators: copy this file to <datadir>/defaults_llm_pricing.yaml (or
# any path configured via management.json:
#
# { "AgentNetwork": { "PricingDefaultsFile": "/path/defaults_llm_pricing.yaml" } }
#
# ) and adjust the entries you want to change. Management re-reads the
# file periodically (mtime poll, every minute): the live table feeds the
# proxies' cost metering and the dashboard's model-price prefill, so
# edits apply without a restart. Your file only needs the entries you
# want to change — but each entry REPLACES the built-in entry for that
# surface+model whole, so repeat the cache rates you want to keep.
# Unknown fields and negative or non-finite rates are rejected: at
# startup that fails boot (for an explicitly configured path); at
# runtime the previous table is kept and a warning is logged. Deleting
# the file reverts to the built-in defaults below.
#
# Top-level keys are pricing surfaces — the parser shape requests are
# metered under: "openai" (also Azure, Mistral, and OpenAI-compatible
# gateways), "anthropic" (also Anthropic-on-Vertex), "bedrock"
# (normalized ids, e.g. anthropic.claude-sonnet-4-5). Model keys must be
# the normalized id the proxy meters (version/region suffixes stripped).
#
# Values are USD per 1_000 tokens. Optional cache fields:
# cached_input_per_1k OpenAI shape: rate for cached prompt tokens
# (a SUBSET of input tokens). Absent -> cached
# portion bills at input_per_1k.
# cache_read_per_1k Anthropic shape: rate for cache_read tokens
# (ADDITIVE to input). Absent -> input rate.
# cache_creation_per_1k Anthropic shape: rate for cache_creation
# tokens (ADDITIVE to input). Absent -> input
# rate.
`
management/internals/modules/agentnetwork/pricing/gen.go
+20
View File
@@ -0,0 +1,20 @@
//go:build ignore
// Regenerates defaults_llm_pricing.example.yaml from the compiled-in
// default pricing table. Run via:
//
// go generate ./management/internals/modules/agentnetwork/pricing
package main
import (
"log"
"os"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/pricing"
)
func main() {
if err := os.WriteFile("defaults_llm_pricing.example.yaml", pricing.MarshalDefaultsYAML(), 0o644); err != nil {
log.Fatalf("write defaults_llm_pricing.example.yaml: %v", err)
}
}
management/internals/modules/agentnetwork/pricing/override.go
+249
View File
@@ -0,0 +1,249 @@
package pricing
import (
"bytes"
"context"
"errors"
"fmt"
"io"
"io/fs"
"math"
"os"
"sync"
"time"
log "github.com/sirupsen/logrus"
"gopkg.in/yaml.v3"
)
// DefaultFileName is the basename probed under management's datadir when
// AgentNetwork.PricingDefaultsFile doesn't configure an explicit path.
const DefaultFileName = "defaults_llm_pricing.yaml"
// ReloadInterval is the cadence at which the pricing file's mtime is
// polled for changes.
const ReloadInterval = time.Minute
// maxFileBytes bounds the pricing file read so a misconfigured path
// (pointed at a huge file) cannot exhaust process memory.
const maxFileBytes = 4 << 20
// pricingFile mirrors the on-disk YAML schema — the same schema the
// proxy's retired embedded defaults_pricing.yaml used, so files written
// for it keep working. Keys are pricing surfaces ("openai", "anthropic",
// "bedrock"); nested keys are normalized model ids.
type pricingFile map[string]map[string]struct {
InputPer1k float64 `yaml:"input_per_1k"`
OutputPer1k float64 `yaml:"output_per_1k"`
CachedInputPer1k float64 `yaml:"cached_input_per_1k"`
CacheReadPer1k float64 `yaml:"cache_read_per_1k"`
CacheCreationPer1k float64 `yaml:"cache_creation_per_1k"`
}
// fileState tracks the watched pricing file across reloads.
var fileState struct {
mu sync.Mutex
path string
mtime int64
}
// LoadFile loads the management-side pricing defaults file and makes it
// the live table (merged entry-whole over the compiled-in fallback; see
// DefaultTable). The path stays registered for the periodic reloader, so
// later edits — or the file (re)appearing after deletion — are picked up
// without a restart.
//
// required governs the missing-file case: true for an explicitly
// configured path (a typo must fail startup rather than silently bill
// with built-ins the operator believes they replaced), false for the
// conventional <datadir>/defaults_llm_pricing.yaml probe (absent file =
// compiled-in defaults, still watched in case it appears). A file that
// exists but is malformed is always an error at load time.
func LoadFile(path string, required bool) error {
if path == "" {
return nil
}
fileState.mu.Lock()
fileState.path = path
fileState.mu.Unlock()
table, mtime, err := readFile(path)
if err != nil {
if errors.Is(err, fs.ErrNotExist) && !required {
log.Infof("agent-network pricing defaults file %s not present; serving built-in defaults", path)
return nil
}
return err
}
storeFileTable(table, mtime)
log.Infof("agent-network pricing defaults loaded from %s", path)
return nil
}
// StartReloader launches the periodic mtime-poll goroutine for the file
// registered by LoadFile. Runtime failures are lenient — a parse error
// keeps the previously loaded table and logs a warning; a deleted file
// reverts to the compiled-in defaults — so a mid-edit save can never
// take pricing down. Returns immediately when no path was registered.
func StartReloader(ctx context.Context, interval time.Duration) {
fileState.mu.Lock()
path := fileState.path
fileState.mu.Unlock()
if path == "" {
return
}
if interval <= 0 {
interval = ReloadInterval
}
go func() {
t := time.NewTicker(interval)
defer t.Stop()
for {
select {
case <-ctx.Done():
return
case <-t.C:
reload()
}
}
}()
}
// reload performs one mtime check + reload cycle.
func reload() {
fileState.mu.Lock()
path, lastMtime := fileState.path, fileState.mtime
fileState.mu.Unlock()
log.Debugf("agent-network pricing defaults reload: checking %s for changes", path)
st, err := os.Stat(path)
if err != nil {
if errors.Is(err, fs.ErrNotExist) {
// File removed (or not yet created): serve compiled-in
// defaults and reset mtime so a future (re)appearance loads.
if mergedTable.Swap(nil) != nil {
log.Warnf("agent-network pricing defaults file %s removed; reverting to built-in defaults", path)
}
setMtime(0)
return
}
log.Warnf("agent-network pricing defaults reload: stat %s: %v", path, err)
return
}
if st.ModTime().UnixNano() == lastMtime {
log.Debugf("agent-network pricing defaults %s unchanged since last check", path)
return
}
table, mtime, err := readFile(path)
if err != nil {
// Keep the previously loaded table — never blank prices because
// an operator saved mid-edit.
log.Warnf("agent-network pricing defaults reload failed for %s (keeping previous table): %v", path, err)
return
}
storeFileTable(table, mtime)
log.Infof("agent-network pricing defaults reloaded from %s", path)
}
func readFile(path string) (map[string]map[string]Entry, int64, error) {
f, err := os.Open(path)
if err != nil {
return nil, 0, fmt.Errorf("open pricing defaults %s: %w", path, err)
}
defer func() { _ = f.Close() }()
st, err := f.Stat()
if err != nil {
return nil, 0, fmt.Errorf("stat pricing defaults %s: %w", path, err)
}
data, err := io.ReadAll(io.LimitReader(f, maxFileBytes+1))
if err != nil {
return nil, 0, fmt.Errorf("read pricing defaults %s: %w", path, err)
}
if len(data) > maxFileBytes {
return nil, 0, fmt.Errorf("pricing defaults %s exceeds %d bytes", path, maxFileBytes)
}
table, err := parsePricingYAML(data)
if err != nil {
return nil, 0, fmt.Errorf("parse pricing defaults %s: %w", path, err)
}
return table, st.ModTime().UnixNano(), nil
}
// storeFileTable merges the parsed file over the compiled-in base and
// publishes the result as the live table. File entries replace the
// built-in entry for the same (surface, model) whole — they are not
// field-merged — and surfaces/models the file doesn't mention keep the
// built-in rates, so a partial file only needs the entries it changes.
func storeFileTable(table map[string]map[string]Entry, mtime int64) {
base := compiledBase()
merged := make(map[string]map[string]Entry, len(base)+len(table))
for surface, models := range base {
inner := make(map[string]Entry, len(models))
for id, e := range models {
inner[id] = e
}
merged[surface] = inner
}
for surface, models := range table {
inner, ok := merged[surface]
if !ok {
inner = make(map[string]Entry, len(models))
merged[surface] = inner
}
for id, e := range models {
inner[id] = e
}
}
mergedTable.Store(&merged)
setMtime(mtime)
}
func setMtime(v int64) {
fileState.mu.Lock()
fileState.mtime = v
fileState.mu.Unlock()
}
// parsePricingYAML decodes and validates the pricing YAML. Unknown
// fields are rejected (typos surface instead of silently pricing at 0)
// and every rate must be a finite, non-negative USD amount — the same
// constraints the HTTP API enforces on operator per-provider prices.
func parsePricingYAML(data []byte) (map[string]map[string]Entry, error) {
dec := yaml.NewDecoder(bytes.NewReader(data))
dec.KnownFields(true)
var raw pricingFile
if err := dec.Decode(&raw); err != nil && !errors.Is(err, io.EOF) {
return nil, fmt.Errorf("decode yaml: %w", err)
}
out := make(map[string]map[string]Entry, len(raw))
for surface, models := range raw {
inner := make(map[string]Entry, len(models))
for model, e := range models {
for field, v := range map[string]float64{
"input_per_1k": e.InputPer1k,
"output_per_1k": e.OutputPer1k,
"cached_input_per_1k": e.CachedInputPer1k,
"cache_read_per_1k": e.CacheReadPer1k,
"cache_creation_per_1k": e.CacheCreationPer1k,
} {
if v < 0 || math.IsNaN(v) || math.IsInf(v, 0) {
return nil, fmt.Errorf("%s/%s: %s must be a finite, non-negative rate, got %v", surface, model, field, v)
}
}
inner[model] = Entry{
InputPer1k: e.InputPer1k,
OutputPer1k: e.OutputPer1k,
CachedInputPer1k: e.CachedInputPer1k,
CacheReadPer1k: e.CacheReadPer1k,
CacheCreationPer1k: e.CacheCreationPer1k,
}
}
out[surface] = inner
}
return out, nil
}
management/internals/modules/agentnetwork/pricing/override_test.go
+173
View File
@@ -0,0 +1,173 @@
package pricing
import (
"os"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// resetFileState snapshots and restores the package-level file state so
// tests stay order-independent.
func resetFileState(t *testing.T) {
t.Helper()
prevMerged := mergedTable.Load()
fileState.mu.Lock()
prevPath, prevMtime := fileState.path, fileState.mtime
fileState.mu.Unlock()
t.Cleanup(func() {
mergedTable.Store(prevMerged)
fileState.mu.Lock()
fileState.path, fileState.mtime = prevPath, prevMtime
fileState.mu.Unlock()
})
}
func writePricing(t *testing.T, path, yml string) {
t.Helper()
require.NoError(t, os.WriteFile(path, []byte(yml), 0o600))
}
func TestLoadFile_MergesOverCompiledDefaults(t *testing.T) {
resetFileState(t)
path := filepath.Join(t.TempDir(), DefaultFileName)
writePricing(t, path, `
openai:
# Reprice a built-in model. The entry replaces the built-in WHOLE:
# omitting the cache rate here drops the built-in 0.00125 discount.
gpt-4o:
input_per_1k: 0.9
output_per_1k: 1.8
# A model NetBird doesn't know at all.
my-private-ft:
input_per_1k: 0.01
output_per_1k: 0.02
cached_input_per_1k: 0.005
gemini:
gemini-pro:
input_per_1k: 0.00125
output_per_1k: 0.005
`)
require.NoError(t, LoadFile(path, true))
table := DefaultTable()
gpt4o := table["openai"]["gpt-4o"]
assert.InDelta(t, 0.9, gpt4o.InputPer1k, 1e-9, "file rate replaces the compiled-in rate")
assert.Zero(t, gpt4o.CachedInputPer1k, "entries replace whole — omitted cache rate is dropped, not inherited")
ft := table["openai"]["my-private-ft"]
assert.InDelta(t, 0.005, ft.CachedInputPer1k, 1e-9, "unknown models are added to the surface")
_, ok := table["gemini"]["gemini-pro"]
assert.True(t, ok, "a surface the catalog doesn't declare can be added")
// Untouched entries keep compiled-in rates (catalog, other surface,
// supplemental).
assert.InDelta(t, 0.00015, table["openai"]["gpt-4o-mini"].InputPer1k, 1e-9, "unlisted model keeps compiled rate")
assert.InDelta(t, 0.003, table["anthropic"]["claude-sonnet-4-5"].InputPer1k, 1e-9, "unlisted surface untouched")
assert.InDelta(t, 0.00125, table["openai"]["gpt-5"].InputPer1k, 1e-9, "supplemental entries untouched")
// The synthesizer-facing lookup reads the live table too.
e, ok := LookupDefault([]string{"openai"}, "gpt-4o")
require.True(t, ok)
assert.InDelta(t, 0.9, e.InputPer1k, 1e-9, "LookupDefault serves the file-backed rate")
}
func TestLoadFile_MissingPath(t *testing.T) {
resetFileState(t)
missing := filepath.Join(t.TempDir(), DefaultFileName)
require.Error(t, LoadFile(missing, true),
"explicitly configured path that doesn't exist must fail startup")
require.NoError(t, LoadFile(missing, false),
"conventional datadir probe tolerates an absent file (compiled-in defaults serve)")
assert.Nil(t, mergedTable.Load(), "no file, no merged table")
fileState.mu.Lock()
path := fileState.path
fileState.mu.Unlock()
assert.Equal(t, missing, path, "the path stays registered so the reloader picks the file up when it appears")
}
func TestLoadFile_RejectsInvalid(t *testing.T) {
resetFileState(t)
dir := t.TempDir()
cases := map[string]string{
"unknown field (typo)": "openai:\n gpt-4o:\n input_per1k: 0.1\n",
"negative rate": "openai:\n gpt-4o:\n input_per_1k: -0.1\n",
"non-numeric rate": "openai:\n gpt-4o:\n input_per_1k: cheap\n",
"not a mapping": "- just\n- a\n- list\n",
}
for name, yml := range cases {
path := filepath.Join(dir, DefaultFileName)
writePricing(t, path, yml)
assert.Error(t, LoadFile(path, true), "case %q must be rejected", name)
}
}
// TestReload_LifeCycle drives the reloader's single-shot reload through
// its full lifecycle: file edit picked up on mtime change, a broken save
// keeps the previous table, and file removal reverts to the compiled-in
// defaults (then a re-created file loads again).
func TestReload_LifeCycle(t *testing.T) {
resetFileState(t)
path := filepath.Join(t.TempDir(), DefaultFileName)
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: 0.5\n output_per_1k: 1\n")
require.NoError(t, LoadFile(path, true))
require.InDelta(t, 0.5, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9)
// Edit: new mtime, new rates.
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: 0.7\n output_per_1k: 1.4\n")
bumpMtime(t, path)
reload()
assert.InDelta(t, 0.7, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9, "edit must be picked up")
// Broken save: previous table survives.
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: -1\n")
bumpMtime(t, path)
reload()
assert.InDelta(t, 0.7, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9,
"a malformed save must keep the previously loaded table, never blank prices")
// Removal: compiled-in defaults serve again.
require.NoError(t, os.Remove(path))
reload()
assert.InDelta(t, 0.0025, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9,
"file removal reverts to the compiled-in rate")
// Re-created file loads without a restart.
writePricing(t, path, "openai:\n gpt-4o:\n input_per_1k: 0.9\n output_per_1k: 1.8\n")
bumpMtime(t, path)
reload()
assert.InDelta(t, 0.9, DefaultTable()["openai"]["gpt-4o"].InputPer1k, 1e-9,
"a file appearing after removal (or after a missing-probe boot) must load")
}
// bumpMtime pushes the file's mtime forward past the previously recorded
// value — timestamps can otherwise collide within the test's timescale.
func bumpMtime(t *testing.T, path string) {
t.Helper()
st, err := os.Stat(path)
require.NoError(t, err)
next := st.ModTime().Add(2 * 1e9)
require.NoError(t, os.Chtimes(path, next, next))
}
// TestExampleYAML_InSyncWithBuiltins is the golden guard for
// defaults_llm_pricing.example.yaml: the shipped example must stay
// byte-identical to what the compiled-in table renders (catalog edits
// require `go generate ./management/internals/modules/agentnetwork/pricing`)
// and must round-trip through the same parser operators' files go
// through, reproducing the compiled-in table exactly.
func TestExampleYAML_InSyncWithBuiltins(t *testing.T) {
onDisk, err := os.ReadFile("defaults_llm_pricing.example.yaml")
require.NoError(t, err, "example file must exist next to the package")
require.Equal(t, string(MarshalDefaultsYAML()), string(onDisk),
"defaults_llm_pricing.example.yaml is stale — run: go generate ./management/internals/modules/agentnetwork/pricing")
parsed, err := parsePricingYAML(onDisk)
require.NoError(t, err, "the example must be a valid pricing defaults file")
assert.Equal(t, buildDefaultTable(), parsed,
"parsing the example must reproduce the compiled-in table exactly")
}
management/internals/modules/agentnetwork/provider_bootstrap_test.go
+134
View File
@@ -0,0 +1,134 @@
package agentnetwork
import (
"context"
"runtime"
"testing"
"github.com/golang/mock/gomock"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
"github.com/netbirdio/netbird/management/server/account"
"github.com/netbirdio/netbird/management/server/permissions"
"github.com/netbirdio/netbird/management/server/permissions/modules"
"github.com/netbirdio/netbird/management/server/permissions/operations"
"github.com/netbirdio/netbird/management/server/store"
nbtypes "github.com/netbirdio/netbird/management/server/types"
"github.com/netbirdio/netbird/shared/management/status"
)
// bootstrapFixture wires a real sqlite store to a gomock permissions manager
// so tests can grant the provider permission while denying (or never
// expecting) the settings one.
type bootstrapFixture struct {
manager Manager
store store.Store
perms *permissions.MockManager
}
func newBootstrapFixture(t *testing.T) *bootstrapFixture {
t.Helper()
if runtime.GOOS == "windows" {
t.Skip("sqlite store not properly supported on Windows yet")
}
t.Setenv("NETBIRD_STORE_ENGINE", string(nbtypes.SqliteStoreEngine))
st, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
require.NoError(t, err, "test store setup must succeed")
t.Cleanup(cleanUp)
ctrl := gomock.NewController(t)
perms := permissions.NewMockManager(ctrl)
accounts := account.NewMockManager(ctrl)
accounts.EXPECT().StoreEvent(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
accounts.EXPECT().UpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
accounts.EXPECT().BufferUpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
return &bootstrapFixture{
manager: NewManager(st, perms, accounts, nil),
store: st,
perms: perms,
}
}
func (f *bootstrapFixture) expectPermission(accountID, userID string, module modules.Module, op operations.Operation, allowed bool) {
f.perms.EXPECT().
ValidateUserPermissions(gomock.Any(), accountID, userID, module, op).
Return(allowed, context.Background(), nil)
}
func newBootstrapProvider(accountID string) *types.Provider {
p := types.NewProvider(accountID)
p.Name = "openai"
p.UpstreamURL = "https://api.openai.com"
p.APIKey = "sk-test"
p.Enabled = true
return p
}
// TestCreateProviderBootstrapRequiresSettingsPermission pins the gate on the
// one-time settings bootstrap: creating the first provider with a
// bootstrap_cluster pins the account's cluster and subdomain, which is a
// settings write and must not ride on the providers permission alone.
func TestCreateProviderBootstrapRequiresSettingsPermission(t *testing.T) {
ctx := context.Background()
t.Run("denied without settings permission", func(t *testing.T) {
f := newBootstrapFixture(t)
f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
f.expectPermission("account1", "user1", modules.AgentNetworkSettings, operations.Create, false)
_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
require.Error(t, err, "bootstrap without settings permission must fail")
var sErr *status.Error
require.ErrorAs(t, err, &sErr)
assert.Equal(t, status.PermissionDenied, sErr.Type(), "denial should surface as permission denied")
providers, err := f.store.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, "account1")
require.NoError(t, err)
assert.Empty(t, providers, "provider must not be persisted when bootstrap is denied")
_, err = f.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
assert.Error(t, err, "settings row must not be created when bootstrap is denied")
})
t.Run("allowed with settings permission", func(t *testing.T) {
f := newBootstrapFixture(t)
f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
f.expectPermission("account1", "user1", modules.AgentNetworkSettings, operations.Create, true)
created, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
require.NoError(t, err, "bootstrap with both permissions must succeed")
require.NotNil(t, created)
settings, err := f.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
require.NoError(t, err, "bootstrap must create the settings row")
assert.Equal(t, "cluster1.example.com", settings.Cluster, "settings should pin the bootstrap cluster")
})
t.Run("existing settings need no settings permission", func(t *testing.T) {
f := newBootstrapFixture(t)
require.NoError(t, f.store.SaveAgentNetworkSettings(ctx, &types.Settings{
AccountID: "account1",
Cluster: "cluster1.example.com",
Subdomain: "existing",
}), "pre-existing settings row setup must succeed")
// Only the providers permission may be consulted: gomock fails the
// test on any unexpected settings-permission call.
f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
require.NoError(t, err, "create with existing settings must not require the settings permission")
})
t.Run("no bootstrap cluster needs no settings permission", func(t *testing.T) {
f := newBootstrapFixture(t)
f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "")
require.NoError(t, err, "create without bootstrap must not require the settings permission")
})
}
management/internals/modules/agentnetwork/synthesizer.go
+108 -88
View File
@@ -233,9 +233,19 @@ func SynthesizeServices(ctx context.Context, s store.Store, accountID string) ([
return nil, err
}
costMeterJSON, err := buildCostMeterConfigJSON(enabledProviders, groupIndex)
if err != nil {
return nil, err
}
mergedGuardrails := mergeGuardrails(enabledPolicies, guardrailsByID)
applyAccountCollectionControls(&mergedGuardrails, settings)
guardrailJSON, err := marshalGuardrailConfig(mergedGuardrails)
// The proxy guardrail is a per-provider fail-closed backstop; the
// authoritative per-policy/group decision is management's
// SelectPolicyForRequest. A provider lands in this map only when every
// authorising policy restricts models.
providerAllowlists := buildProviderAllowlists(enabledPolicies, guardrailsByID)
guardrailJSON, err := marshalGuardrailConfig(providerAllowlists, mergedGuardrails.PromptCapture)
if err != nil {
return nil, err
}
@@ -243,7 +253,7 @@ func SynthesizeServices(ctx context.Context, s store.Store, accountID string) ([
// Use the merged decision (account settings OR policy-required redaction),
// not the raw account flag, so a policy that mandates PII redaction is
// honored by the capture parsers even when the account toggle is off.
middlewares := buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON, mergedGuardrails.PromptCapture.RedactPii, mergedGuardrails.PromptCapture.Enabled)
middlewares := buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON, costMeterJSON, mergedGuardrails.PromptCapture.RedactPii, mergedGuardrails.PromptCapture.Enabled)
priv, pub, err := pickServiceSessionKeys(enabledProviders)
if err != nil {
@@ -695,7 +705,7 @@ func buildIdentityExtraHeaders(p *types.Provider, extras []catalog.ExtraHeader)
// requests bound for gateways like LiteLLM that key budgets and
// attribution off request headers. CanMutate is required so its
// HeadersAdd / HeadersRemove pass the framework's mutation gate.
func buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON []byte, redactPii, capturePromptContent bool) []rpservice.MiddlewareConfig {
func buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON, costMeterJSON []byte, redactPii, capturePromptContent bool) []rpservice.MiddlewareConfig {
// Both parsers receive an explicit capture flag derived from the account's
// enable_prompt_collection toggle; nil/unset would default to the legacy
// "always emit" behavior in the middleware, which is precisely what we
@@ -764,10 +774,13 @@ func buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON []byt
ConfigJSON: []byte("{}"),
},
{
// Carries the full pricing table (defaults + per-provider
// operator prices) so the proxy bills without an embedded
// price list; see buildCostMeterConfigJSON.
ID: middlewareIDCostMeter,
Enabled: true,
Slot: rpservice.MiddlewareSlotOnResponse,
ConfigJSON: []byte("{}"),
ConfigJSON: costMeterJSON,
},
{
ID: middlewareIDLLMResponseParser,
@@ -780,10 +793,12 @@ func buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON []byt
// guardrailConfig is the JSON shape the proxy-side llm_guardrail
// middleware expects. Mirrors the proxy registration documented in
// the management→proxy contract.
// the management→proxy contract. provider_allowlists is keyed by the
// resolved provider id llm_router stamps; a provider absent from the map is
// unrestricted at the proxy layer.
type guardrailConfig struct {
ModelAllowlist []string `json:"model_allowlist,omitempty"`
PromptCapture guardrailPromptCapture `json:"prompt_capture"`
ProviderAllowlists map[string][]string `json:"provider_allowlists,omitempty"`
PromptCapture guardrailPromptCapture `json:"prompt_capture"`
}
type guardrailPromptCapture struct {
@@ -828,13 +843,10 @@ func applyAccountCollectionControls(merged *MergedGuardrails, settings *types.Se
merged.PromptCapture.RedactPii = settings.RedactPii || merged.PromptCapture.RedactPii
}
func marshalGuardrailConfig(merged MergedGuardrails) ([]byte, error) {
func marshalGuardrailConfig(providerAllowlists map[string][]string, capture MergedPromptCapture) ([]byte, error) {
cfg := guardrailConfig{
ModelAllowlist: merged.ModelAllowlist,
PromptCapture: guardrailPromptCapture{
Enabled: merged.PromptCapture.Enabled,
RedactPii: merged.PromptCapture.RedactPii,
},
ProviderAllowlists: providerAllowlists,
PromptCapture: guardrailPromptCapture(capture),
}
out, err := json.Marshal(cfg)
if err != nil {
@@ -843,6 +855,74 @@ func marshalGuardrailConfig(merged MergedGuardrails) ([]byte, error) {
return out, nil
}
// buildProviderAllowlists returns the proxy's per-provider backstop: a provider
// is included only when every authorising policy restricts models (their union);
// if any leaves it unrestricted it is omitted, so management decides per group.
func buildProviderAllowlists(policies []*types.Policy, byID map[string]*types.Guardrail) map[string][]string {
type providerAcc struct {
models map[string]struct{}
anyUnrestricted bool
}
accs := make(map[string]*providerAcc)
for _, p := range policies {
if p == nil {
continue
}
restricted, models := policyModelAllowlist(p, byID)
for _, providerID := range p.DestinationProviderIDs {
if providerID == "" {
continue
}
acc, ok := accs[providerID]
if !ok {
acc = &providerAcc{models: make(map[string]struct{})}
accs[providerID] = acc
}
if !restricted {
acc.anyUnrestricted = true
continue
}
for _, m := range models {
acc.models[m] = struct{}{}
}
}
}
out := make(map[string][]string, len(accs))
for providerID, acc := range accs {
if acc.anyUnrestricted {
continue
}
models := make([]string, 0, len(acc.models))
for m := range acc.models {
models = append(models, m)
}
sort.Strings(models)
out[providerID] = models
}
return out
}
// policyModelAllowlist reports whether a policy restricts models (has an
// allowlist-enabled guardrail) and the union of allowed models. Models are
// verbatim; the proxy factory lowercases/trims them at decode time.
func policyModelAllowlist(p *types.Policy, byID map[string]*types.Guardrail) (bool, []string) {
restricted := false
var models []string
for _, gID := range p.GuardrailIDs {
g, ok := byID[gID]
if !ok || g == nil || !g.Checks.ModelAllowlist.Enabled {
continue
}
restricted = true
for _, m := range g.Checks.ModelAllowlist.Models {
if m != "" {
models = append(models, m)
}
}
}
return restricted, models
}
// buildAccountService composes the per-account gateway Service. The
// target carries the noop placeholder URL — the router middleware
// rewrites every request to the matched provider's upstream before the
@@ -986,38 +1066,11 @@ func unionSourceGroups(policies []*types.Policy) []string {
return out
}
// MergedGuardrails is the JSON shape passed to the proxy via the
// guardrail middleware's config_json. Mirrors the proxy-side
// expectations and is intentionally distinct from
// types.GuardrailChecks so we can evolve either side independently.
// MergedGuardrails is the synthesiser's fold target. Only prompt capture is
// merged here — the model allowlist is emitted per-provider, and
// token/budget/retention moved onto Policy.Limits and account Settings.
type MergedGuardrails struct {
ModelAllowlist []string `json:"model_allowlist,omitempty"`
TokenLimits MergedTokenLimits `json:"token_limits"`
Budget MergedBudget `json:"budget"`
PromptCapture MergedPromptCapture `json:"prompt_capture"`
Retention MergedRetention `json:"retention"`
}
type MergedTokenLimits struct {
Hourly *MergedTokenWindow `json:"hourly,omitempty"`
Daily *MergedTokenWindow `json:"daily,omitempty"`
Monthly *MergedTokenWindow `json:"monthly,omitempty"`
}
type MergedTokenWindow struct {
MaxInputTokens int `json:"max_input_tokens,omitempty"`
MaxOutputTokens int `json:"max_output_tokens,omitempty"`
}
type MergedBudget struct {
Hourly *MergedBudgetWindow `json:"hourly,omitempty"`
Daily *MergedBudgetWindow `json:"daily,omitempty"`
Monthly *MergedBudgetWindow `json:"monthly,omitempty"`
}
type MergedBudgetWindow struct {
SoftCapUSD float64 `json:"soft_cap_usd,omitempty"`
HardCapUSD float64 `json:"hard_cap_usd,omitempty"`
PromptCapture MergedPromptCapture
}
type MergedPromptCapture struct {
@@ -1025,64 +1078,31 @@ type MergedPromptCapture struct {
RedactPii bool `json:"redact_pii"`
}
type MergedRetention struct {
Enabled bool `json:"enabled"`
Days int `json:"days"`
}
// mergeGuardrails computes the effective guardrail spec applied at the
// proxy, given the referencing policies and the account's guardrail
// catalogue. Policy enabled-ness is the caller's responsibility — only
// enabled policies should be passed in.
// mergeGuardrails folds the referencing policies' guardrails into the
// prompt-capture decision only. The model allowlist is enforced per-policy/group
// in management and shipped per-provider; token/budget/retention live off
// guardrails now.
//
// Merge rules:
// - Model allowlist: union of allowlists across policies that enable it.
// - Token / Budget: most-restrictive (min of non-zero caps) per window.
// - Prompt capture: enabled if any policy enables it; redact_pii sticks
// if any enabling policy turns it on.
// - Retention: enabled if any enables it; smallest non-zero days wins.
// Merge rule — prompt capture: enabled if any policy enables it; redact_pii
// sticks if any enabling policy turns it on.
func mergeGuardrails(policies []*types.Policy, byID map[string]*types.Guardrail) MergedGuardrails {
merged := MergedGuardrails{}
allowlist := make(map[string]struct{})
allowlistEnabled := false
for _, policy := range policies {
for _, gID := range policy.GuardrailIDs {
g, ok := byID[gID]
if !ok || g == nil {
continue
}
mergeGuardrail(g, &merged, allowlist, &allowlistEnabled)
mergeGuardrail(g, &merged)
}
}
if allowlistEnabled {
merged.ModelAllowlist = make([]string, 0, len(allowlist))
for m := range allowlist {
merged.ModelAllowlist = append(merged.ModelAllowlist, m)
}
sort.Strings(merged.ModelAllowlist)
}
return merged
}
// mergeGuardrail folds a single guardrail's enabled checks into the
// running merge: model-allowlist models join the shared set (and flip
// allowlistEnabled), and prompt-capture / redact-pii stick once any
// enabling guardrail turns them on.
//
// TokenLimits, Budget, and Retention have moved off guardrails — token
// and budget caps now live on the Policy itself (Policy.Limits) and
// retention moves to account-level Settings — so they are not merged here.
func mergeGuardrail(g *types.Guardrail, merged *MergedGuardrails, allowlist map[string]struct{}, allowlistEnabled *bool) {
if g.Checks.ModelAllowlist.Enabled {
*allowlistEnabled = true
for _, m := range g.Checks.ModelAllowlist.Models {
if m != "" {
allowlist[m] = struct{}{}
}
}
}
// mergeGuardrail folds a single guardrail's prompt-capture settings into the
// running merge: enabled / redact-pii stick once any enabling guardrail turns
// them on.
func mergeGuardrail(g *types.Guardrail, merged *MergedGuardrails) {
if g.Checks.PromptCapture.Enabled {
merged.PromptCapture.Enabled = true
if g.Checks.PromptCapture.RedactPii {
management/internals/modules/agentnetwork/synthesizer_guardrail_realstore_test.go
+3 -3
View File
@@ -81,8 +81,8 @@ func TestSynthesizeServices_RealStore_PromptCaptureAccountIsSoleControl(t *testi
require.Len(t, services, 1)
cfg := decodeServiceGuardrailConfig(t, services[0])
assert.Equal(t, []string{"gpt-5.4"}, cfg.ModelAllowlist,
"model allowlist is a pure policy guardrail and must always reach the config")
assert.Equal(t, map[string][]string{"prov-1": {"gpt-5.4"}}, cfg.ProviderAllowlists,
"model allowlist is a pure policy guardrail and must reach the per-provider config")
assert.False(t, cfg.PromptCapture.Enabled,
"prompt capture must be off when the account toggle is off, even with a capture-enabled guardrail")
}
@@ -172,7 +172,7 @@ func TestSynthesizeServices_RealStore_NoGuardrail_CaptureOff(t *testing.T) {
require.Len(t, services, 1, "exactly one synth service expected")
cfg := decodeServiceGuardrailConfig(t, services[0])
assert.Empty(t, cfg.ModelAllowlist, "no guardrail → no allowlist")
assert.Empty(t, cfg.ProviderAllowlists, "no guardrail → provider unrestricted (absent from map)")
assert.False(t, cfg.PromptCapture.Enabled, "no guardrail → prompt capture off by default")
assert.False(t, cfg.PromptCapture.RedactPii, "no guardrail → redact off by default")
}
management/internals/modules/agentnetwork/synthesizer_pricing.go
+131
View File
@@ -0,0 +1,131 @@
package agentnetwork
import (
"encoding/json"
"fmt"
"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"
sharedllm "github.com/netbirdio/netbird/shared/llm"
)
// costMeterConfig is the JSON shape the proxy-side cost_meter middleware
// expects (mirror-type pattern, same as routerConfig). The top-level
// "pricing" wrapper is the feature-detection signal: an old proxy's config
// struct ignores it as an unknown field, and a new proxy treats its
// absence as "old management" (skips every cost computation and warns).
type costMeterConfig struct {
Pricing *costMeterPricing `json:"pricing,omitempty"`
}
// costMeterPricing carries the full pricing table:
// - Defaults: surface ("openai"/"anthropic"/"bedrock") -> normalized
// model id -> rates. The full default table ships to every account —
// it is small (~10 KB) and keeps gateway-style providers (which
// enumerate no models) priced for every catalog model.
// - Providers: provider record id (matched against the
// llm.resolved_provider_id metadata llm_router stamps) -> normalized
// model id -> rates. Entries are fully materialized here at synth
// time — default cache rates already folded in — so the proxy does
// two map lookups and no merging.
type costMeterPricing struct {
Defaults map[string]map[string]pricing.Entry `json:"defaults,omitempty"`
Providers map[string]map[string]pricing.Entry `json:"providers,omitempty"`
}
// buildCostMeterConfigJSON assembles the cost_meter middleware config
// from the default pricing table plus the operator's stored per-provider
// model prices. Same orphan rule as the router: a provider no enabled
// policy authorises is unreachable, so its prices are not shipped.
//
// Overlay semantics per model row:
// - The row's model id is normalized exactly the way the proxy's
// request parser normalizes the ids it meters (bedrock ARN/region/
// version stripping, vertex "@version" stripping), so the per-record
// lookup key compares equal to llm.model at billing time.
// - The entry starts from the default entry for that model (when one
// exists) to inherit cache rates the operator didn't state.
// - Operator input/output overlay verbatim — including an explicit 0,
// which prices the model as free (self-hosted / internal endpoints)
// rather than silently reverting to list price.
// - Cache-rate pointers overlay only when non-nil: nil means "inherit
// the default", an explicit 0 means "no discount, bill this bucket
// at the input rate".
func buildCostMeterConfigJSON(providers []*types.Provider, groupIndex map[string][]string) ([]byte, error) {
cfg := costMeterConfig{Pricing: &costMeterPricing{
Defaults: pricing.DefaultTable(),
}}
perRecord := make(map[string]map[string]pricing.Entry)
for _, p := range providers {
if _, hasPolicy := groupIndex[p.ID]; !hasPolicy {
// Orphan: unreachable via the router, so unpriceable.
continue
}
if len(p.Models) == 0 {
// Gateway-style "claim every model" provider: the defaults
// table is its price list.
continue
}
entry, _ := catalog.Lookup(p.ProviderID)
models := make(map[string]pricing.Entry, len(p.Models))
for _, m := range p.Models {
id := normalizePricingModelID(p.ProviderID, m.ID)
if id == "" {
continue
}
if _, dup := models[id]; dup {
// First occurrence wins on post-normalization duplicates,
// matching providerModelIDs' dedup order for routing.
continue
}
models[id] = materializeEntry(entry.PricingSurfaces, id, m)
}
if len(models) > 0 {
perRecord[p.ID] = models
}
}
if len(perRecord) > 0 {
cfg.Pricing.Providers = perRecord
}
out, err := json.Marshal(cfg)
if err != nil {
return nil, fmt.Errorf("marshal cost_meter middleware config: %w", err)
}
return out, nil
}
// normalizePricingModelID maps an operator-entered model id onto the
// normalized id the proxy's request parser emits as llm.model — the key
// the cost meter looks up at billing time.
func normalizePricingModelID(catalogProviderID, modelID string) string {
switch {
case catalog.IsBedrockPathStyle(catalogProviderID):
return sharedllm.NormalizeBedrockModel(modelID)
case catalog.IsVertexPathStyle(catalogProviderID):
return sharedllm.NormalizeVertexModel(modelID)
default:
return modelID
}
}
// materializeEntry folds the default entry for (surfaces, model) — when
// one exists — under the operator's stored prices, producing the fully
// materialized wire entry.
func materializeEntry(surfaces []string, normalizedID string, m types.ProviderModel) pricing.Entry {
e, _ := pricing.LookupDefault(surfaces, normalizedID) // zero Entry on miss
e.InputPer1k = m.InputPer1k
e.OutputPer1k = m.OutputPer1k
if m.CachedInputPer1k != nil {
e.CachedInputPer1k = *m.CachedInputPer1k
}
if m.CacheReadPer1k != nil {
e.CacheReadPer1k = *m.CacheReadPer1k
}
if m.CacheCreationPer1k != nil {
e.CacheCreationPer1k = *m.CacheCreationPer1k
}
return e
}
management/internals/modules/agentnetwork/synthesizer_pricing_test.go
+105
View File
@@ -0,0 +1,105 @@
package agentnetwork
import (
"encoding/json"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
)
func fptr(v float64) *float64 { return &v }
func decodeCostMeterConfig(t *testing.T, raw []byte) costMeterConfig {
t.Helper()
var cfg costMeterConfig
require.NoError(t, json.Unmarshal(raw, &cfg), "cost meter config must round-trip")
require.NotNil(t, cfg.Pricing, "pricing wrapper must be present")
return cfg
}
// TestBuildCostMeterConfig_BedrockModelNormalization: the operator may
// paste region-prefixed, versioned, or ARN-wrapped Bedrock ids; the
// per-record map must be keyed by the normalized id the request parser
// emits as llm.model, or the lookup never hits at billing time.
func TestBuildCostMeterConfig_BedrockModelNormalization(t *testing.T) {
bedrock := &types.Provider{
ID: "prov-bedrock",
ProviderID: "bedrock_api",
Enabled: true,
Models: []types.ProviderModel{
{ID: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", InputPer1k: 0.0033, OutputPer1k: 0.0165},
// Post-normalization duplicate of the row above under a
// different regional spelling — first occurrence wins.
{ID: "us.anthropic.claude-sonnet-4-5-20250929-v1:0", InputPer1k: 9.9, OutputPer1k: 9.9},
},
}
raw, err := buildCostMeterConfigJSON([]*types.Provider{bedrock}, map[string][]string{"prov-bedrock": {"grp"}})
require.NoError(t, err)
cfg := decodeCostMeterConfig(t, raw)
models := cfg.Pricing.Providers["prov-bedrock"]
require.Len(t, models, 1, "both spellings normalize to one model; first row wins")
e, ok := models["anthropic.claude-sonnet-4-5"]
require.True(t, ok, "key must be the normalized id the parser emits, not the operator's raw spelling")
assert.InDelta(t, 0.0033, e.InputPer1k, 1e-9, "first row's rate wins the dedup")
assert.InDelta(t, 0.0003, e.CacheReadPer1k, 1e-9, "cache read inherited from the bedrock default entry")
assert.InDelta(t, 0.00375, e.CacheCreationPer1k, 1e-9, "cache creation inherited from the bedrock default entry")
}
// TestBuildCostMeterConfig_CacheRateNilVsZero pins the pointer semantics:
// nil inherits the default cache rate, explicit 0 clears it (that bucket
// bills at the input rate on the proxy).
func TestBuildCostMeterConfig_CacheRateNilVsZero(t *testing.T) {
p := &types.Provider{
ID: "prov-oai",
ProviderID: "openai_api",
Enabled: true,
Models: []types.ProviderModel{
{ID: "gpt-4o", InputPer1k: 0.002, OutputPer1k: 0.008}, // nil → inherit 0.00125
{ID: "gpt-4o-mini", InputPer1k: 0.0001, OutputPer1k: 0.0005, CachedInputPer1k: fptr(0)}, // explicit 0 → no discount
{ID: "my-custom-ft", InputPer1k: 0.01, OutputPer1k: 0.02, CachedInputPer1k: fptr(0.005)}, // unknown model, explicit rate
},
}
raw, err := buildCostMeterConfigJSON([]*types.Provider{p}, map[string][]string{"prov-oai": {"grp"}})
require.NoError(t, err)
cfg := decodeCostMeterConfig(t, raw)
models := cfg.Pricing.Providers["prov-oai"]
assert.InDelta(t, 0.00125, models["gpt-4o"].CachedInputPer1k, 1e-9, "nil cache pointer inherits the default rate")
assert.Zero(t, models["gpt-4o-mini"].CachedInputPer1k, "explicit 0 overrides the default (0.000075) — bucket bills at input rate")
custom := models["my-custom-ft"]
assert.InDelta(t, 0.005, custom.CachedInputPer1k, 1e-9, "unknown model keeps the operator's explicit cache rate")
assert.Zero(t, custom.CacheReadPer1k, "no default to inherit for a model outside the catalog")
}
// TestBuildCostMeterConfig_OrphanAndGatewayProviders: an orphan (no
// authorising policy) is unreachable so its prices must not ship; a
// gateway with no model rows relies on the defaults table and gets no
// per-record entry.
func TestBuildCostMeterConfig_OrphanAndGatewayProviders(t *testing.T) {
orphan := &types.Provider{
ID: "prov-orphan",
ProviderID: "openai_api",
Enabled: true,
Models: []types.ProviderModel{{ID: "gpt-4o", InputPer1k: 1, OutputPer1k: 1}},
}
gateway := &types.Provider{
ID: "prov-litellm",
ProviderID: "litellm_proxy",
Enabled: true,
Models: []types.ProviderModel{},
}
raw, err := buildCostMeterConfigJSON(
[]*types.Provider{orphan, gateway},
map[string][]string{"prov-litellm": {"grp"}}, // orphan has no policy
)
require.NoError(t, err)
cfg := decodeCostMeterConfig(t, raw)
assert.NotContains(t, cfg.Pricing.Providers, "prov-orphan", "orphan provider prices must not ship")
assert.NotContains(t, cfg.Pricing.Providers, "prov-litellm", "empty-models gateway needs no per-record entry")
assert.NotEmpty(t, cfg.Pricing.Defaults["openai"], "defaults still ship so the gateway's catalog-model traffic is priced")
}
management/internals/modules/agentnetwork/synthesizer_provider_allowlist_test.go
+95
View File
@@ -0,0 +1,95 @@
package agentnetwork
import (
"testing"
"github.com/stretchr/testify/assert"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
)
// policyForProviders builds an enabled policy authorising the given providers
// under the given guardrails (both optional). Groups are irrelevant to
// buildProviderAllowlists, which keys purely on destination provider.
func policyForProviders(id string, guardrailIDs []string, providerIDs ...string) *types.Policy {
return &types.Policy{
ID: id,
Enabled: true,
DestinationProviderIDs: providerIDs,
GuardrailIDs: guardrailIDs,
}
}
func TestBuildProviderAllowlists(t *testing.T) {
byID := map[string]*types.Guardrail{
"g-4o": allowlistGuardrail("g-4o", "acc-1", "gpt-4o"),
"g-opus": allowlistGuardrail("g-opus", "acc-1", "claude-opus-4"),
"g-disabled": {ID: "g-disabled", Checks: types.GuardrailChecks{ModelAllowlist: types.GuardrailModelAllowlist{Enabled: false, Models: []string{"gpt-4o"}}}},
}
t.Run("all authorising policies restrict yields per-provider union", func(t *testing.T) {
policies := []*types.Policy{
policyForProviders("p1", []string{"g-4o"}, "prov-x"),
policyForProviders("p2", []string{"g-opus"}, "prov-x"),
}
got := buildProviderAllowlists(policies, byID)
assert.Equal(t, map[string][]string{"prov-x": {"claude-opus-4", "gpt-4o"}}, got,
"a provider every policy restricts carries the sorted union of their models")
})
t.Run("any un-guardrailed policy leaves the provider unrestricted (omitted)", func(t *testing.T) {
policies := []*types.Policy{
policyForProviders("p1", []string{"g-4o"}, "prov-x"),
policyForProviders("p2", nil, "prov-x"), // no guardrail
}
got := buildProviderAllowlists(policies, byID)
assert.NotContains(t, got, "prov-x",
"a provider reachable by an un-guardrailed policy must be omitted so the proxy treats it as unrestricted")
})
t.Run("a disabled allowlist counts as unrestricted", func(t *testing.T) {
policies := []*types.Policy{
policyForProviders("p1", []string{"g-disabled"}, "prov-x"),
}
got := buildProviderAllowlists(policies, byID)
assert.NotContains(t, got, "prov-x",
"a policy whose only guardrail has a disabled allowlist is unrestricted")
})
t.Run("providers are isolated from one another", func(t *testing.T) {
policies := []*types.Policy{
policyForProviders("p1", []string{"g-4o"}, "prov-x"),
policyForProviders("p2", []string{"g-opus"}, "prov-y"),
}
got := buildProviderAllowlists(policies, byID)
assert.Equal(t, []string{"gpt-4o"}, got["prov-x"], "prov-x keeps only its own model")
assert.Equal(t, []string{"claude-opus-4"}, got["prov-y"], "prov-y keeps only its own model")
})
t.Run("one policy authorising two providers restricts both", func(t *testing.T) {
policies := []*types.Policy{
policyForProviders("p1", []string{"g-4o"}, "prov-x", "prov-y"),
}
got := buildProviderAllowlists(policies, byID)
assert.Equal(t, []string{"gpt-4o"}, got["prov-x"])
assert.Equal(t, []string{"gpt-4o"}, got["prov-y"])
})
t.Run("union across a single policy's guardrails", func(t *testing.T) {
policies := []*types.Policy{
policyForProviders("p1", []string{"g-4o", "g-opus"}, "prov-x"),
}
got := buildProviderAllowlists(policies, byID)
assert.ElementsMatch(t, []string{"claude-opus-4", "gpt-4o"}, got["prov-x"],
"a policy's own multiple allowlist guardrails union together")
})
t.Run("an enabled allowlist with no models denies everything", func(t *testing.T) {
empty := map[string]*types.Guardrail{"g-empty": allowlistGuardrail("g-empty", "acc-1")}
got := buildProviderAllowlists([]*types.Policy{
policyForProviders("p1", []string{"g-empty"}, "prov-x"),
}, empty)
assert.Equal(t, map[string][]string{"prov-x": {}}, got,
"an enabled-but-empty allowlist is restricted with an empty set, not unrestricted")
})
}
management/internals/modules/agentnetwork/synthesizer_test.go
+38 -11
View File
@@ -33,14 +33,17 @@ func newSynthTestSettings() *types.Settings {
func newSynthTestProvider() *types.Provider {
return &types.Provider{
ID: "prov-1",
AccountID: testAccountID,
ProviderID: "openai_api",
Name: "OpenAI",
UpstreamURL: "https://api.openai.com",
APIKey: "sk-test-key",
Enabled: true,
Models: []types.ProviderModel{{ID: "gpt-5.4", InputPer1k: 0.0025, OutputPer1k: 0.015}},
ID: "prov-1",
AccountID: testAccountID,
ProviderID: "openai_api",
Name: "OpenAI",
UpstreamURL: "https://api.openai.com",
APIKey: "sk-test-key",
Enabled: true,
// Prices deliberately differ from the catalog's gpt-5.4 rates
// (0.0025/0.015) so pricing tests can prove the operator's
// stored price overlays the catalog default.
Models: []types.ProviderModel{{ID: "gpt-5.4", InputPer1k: 0.004, OutputPer1k: 0.02}},
SessionPrivateKey: "test-priv-key",
SessionPublicKey: "test-pub-key",
CreatedAt: time.Date(2026, 1, 1, 0, 0, 0, 0, time.UTC),
@@ -214,7 +217,27 @@ func TestSynthesizeServices_HappyPath(t *testing.T) {
assert.Equal(t, middlewareIDCostMeter, mws[6].ID, "seventh middleware is the cost meter")
assert.Equal(t, rpservice.MiddlewareSlotOnResponse, mws[6].Slot, "cost meter runs on_response")
assert.Equal(t, []byte("{}"), mws[6].ConfigJSON, "cost meter carries an explicit empty config")
var costCfg costMeterConfig
require.NoError(t, json.Unmarshal(mws[6].ConfigJSON, &costCfg), "cost meter config must unmarshal")
require.NotNil(t, costCfg.Pricing, "cost meter config must carry the pricing table — its absence tells the proxy management predates config-delivered pricing")
gpt4o, ok := costCfg.Pricing.Defaults["openai"]["gpt-4o"]
require.True(t, ok, "the full default table ships regardless of the account's providers")
assert.InDelta(t, 0.0025, gpt4o.InputPer1k, 1e-9, "default gpt-4o input rate comes from the catalog")
openaiPrices, ok := costCfg.Pricing.Providers[openai.ID]
require.True(t, ok, "operator-priced provider must have a per-record entry")
gpt54, ok := openaiPrices["gpt-5.4"]
require.True(t, ok, "operator's model row keys the per-record map")
assert.InDelta(t, 0.004, gpt54.InputPer1k, 1e-9, "operator input price overlays the catalog default (0.0025)")
assert.InDelta(t, 0.02, gpt54.OutputPer1k, 1e-9, "operator output price overlays the catalog default (0.015)")
assert.InDelta(t, 0.00025, gpt54.CachedInputPer1k, 1e-9, "cache rate the operator didn't state is inherited from the default entry")
opus, ok := costCfg.Pricing.Providers[anthropic.ID]["claude-opus-4-7"]
require.True(t, ok, "anthropic's model row keys its per-record map")
assert.Zero(t, opus.InputPer1k, "operator-stored zero prices ship verbatim — an explicit $0 model bills as free, it does not revert to list price")
assert.InDelta(t, 0.0005, opus.CacheReadPer1k, 1e-9, "cache rates still inherit from the default entry")
assert.Equal(t, middlewareIDLLMResponseParser, mws[7].ID, "eighth middleware is the response parser")
assert.Equal(t, rpservice.MiddlewareSlotOnResponse, mws[7].Slot, "response parser runs on_response")
@@ -1031,8 +1054,12 @@ func TestSynthesizeServices_GuardrailMerge_AllowlistUnion_LimitsRestrictive(t *t
var cfg guardrailConfig
require.NoError(t, json.Unmarshal(guardrailJSON, &cfg), "guardrail config must unmarshal cleanly")
assert.ElementsMatch(t, []string{"gpt-5.4-mini", "gpt-5.4-pro"}, cfg.ModelAllowlist,
"model allowlist union must keep both models")
// Both policies restrict the same provider, so the per-provider backstop
// carries the union of their models — a coarse gate that management's
// per-policy/group check narrows; it only blocks models outside the union
// when management is down.
assert.ElementsMatch(t, []string{"gpt-5.4-mini", "gpt-5.4-pro"}, cfg.ProviderAllowlists["prov-1"],
"per-provider allowlist union must keep both models")
}
func TestSynthesizeServices_BackfillsMissingSessionKeys(t *testing.T) {
management/internals/modules/agentnetwork/types/accesslog.go
+105 -36
View File
@@ -41,8 +41,24 @@ type AgentNetworkAccessLog struct {
InputTokens int64
OutputTokens int64
TotalTokens int64
CostUSD float64
Stream bool
// Prompt-cache buckets: read + write token counts.
CachedInputTokens int64
CacheCreationTokens int64
// Per-bucket cost breakdown — one column per token bucket the provider
// bills separately. These four are the only cost state stored: the total
// and the cache portion are derived on read (TotalCostUSD / CacheCostUSD)
// rather than stored alongside, so a stored aggregate can never drift out
// of step with the components it summarises.
//
// default:0 matters on upgrade: these columns are ALTER TABLE ADD COLUMN
// on an existing table, and without it every historical row holds NULL —
// which a raw SUM()/scan into float64 can't read. The default backfills
// them as 0, so pre-upgrade rows report an unknown split, not an error.
InputCostUSD float64 `gorm:"not null;default:0"`
CachedInputCostUSD float64 `gorm:"not null;default:0"`
CacheCreationCostUSD float64 `gorm:"not null;default:0"`
OutputCostUSD float64 `gorm:"not null;default:0"`
Stream bool
// Prompt capture. Only populated when prompt collection is enabled
// (account master switch AND policy guardrail). Heavy free text.
@@ -60,19 +76,44 @@ type AgentNetworkAccessLog struct {
// the reverse-proxy AccessLogEntry table.
func (AgentNetworkAccessLog) TableName() string { return "agent_network_access_log" }
// CostUSDSQLExpr is the SQL sum of the per-bucket cost columns — the total cost
// of a row. Used wherever a query has to sort or aggregate on total cost now
// that no cost_usd column is stored. Plain arithmetic over NOT NULL columns, so
// it stays portable across SQLite and Postgres.
const CostUSDSQLExpr = "(input_cost_usd + cached_input_cost_usd + cache_creation_cost_usd + output_cost_usd)"
// TotalCostUSD is the request's total cost: the sum of the four per-bucket
// costs. Derived rather than stored so it cannot disagree with the breakdown.
func (a *AgentNetworkAccessLog) TotalCostUSD() float64 {
return a.InputCostUSD + a.CachedInputCostUSD + a.CacheCreationCostUSD + a.OutputCostUSD
}
// CacheCostUSD is the portion of the total billed for prompt-cache buckets:
// cache reads plus cache writes.
func (a *AgentNetworkAccessLog) CacheCostUSD() float64 {
return a.CachedInputCostUSD + a.CacheCreationCostUSD
}
// ToAPIResponse renders the flattened entry as the API representation.
func (a *AgentNetworkAccessLog) ToAPIResponse() api.AgentNetworkAccessLog {
out := api.AgentNetworkAccessLog{
Id: a.ID,
ServiceId: a.ServiceID,
Timestamp: a.Timestamp,
StatusCode: a.StatusCode,
DurationMs: int(a.Duration.Milliseconds()),
InputTokens: a.InputTokens,
OutputTokens: a.OutputTokens,
TotalTokens: a.TotalTokens,
CostUsd: a.CostUSD,
Stream: &a.Stream,
Id: a.ID,
ServiceId: a.ServiceID,
Timestamp: a.Timestamp,
StatusCode: a.StatusCode,
DurationMs: int(a.Duration.Milliseconds()),
InputTokens: a.InputTokens,
OutputTokens: a.OutputTokens,
TotalTokens: a.TotalTokens,
CachedInputTokens: a.CachedInputTokens,
CacheCreationTokens: a.CacheCreationTokens,
InputCostUsd: a.InputCostUSD,
CachedInputCostUsd: a.CachedInputCostUSD,
CacheCreationCostUsd: a.CacheCreationCostUSD,
OutputCostUsd: a.OutputCostUSD,
CostUsd: a.TotalCostUSD(),
CacheCostUsd: a.CacheCostUSD(),
Stream: &a.Stream,
}
out.UserId = strPtr(a.UserID)
@@ -112,20 +153,36 @@ func strPtr(s string) *string {
// summary plus its ordered entries. Assembled in Go from a page of entries — it
// is not a stored table.
type AgentNetworkAccessLogSession struct {
SessionID string // empty for a session-less (singleton) request
UserID string
GroupIDs []string // union of the entries' authorising groups
StartedAt time.Time
EndedAt time.Time
RequestCount int
InputTokens int64
OutputTokens int64
TotalTokens int64
CostUSD float64
Providers []string // distinct vendors seen in the session
Models []string // distinct models seen in the session
Decision string // "deny" if any entry was denied, else "allow"
Entries []*AgentNetworkAccessLog
SessionID string // empty for a session-less (singleton) request
UserID string
GroupIDs []string // union of the entries' authorising groups
StartedAt time.Time
EndedAt time.Time
RequestCount int
InputTokens int64
OutputTokens int64
TotalTokens int64
CachedInputTokens int64
CacheCreationTokens int64
InputCostUSD float64
CachedInputCostUSD float64
CacheCreationCostUSD float64
OutputCostUSD float64
Providers []string // distinct vendors seen in the session
Models []string // distinct models seen in the session
Decision string // "deny" if any entry was denied, else "allow"
Entries []*AgentNetworkAccessLog
}
// TotalCostUSD is the session's total cost: the sum of the four per-bucket
// costs accumulated across its entries.
func (sess *AgentNetworkAccessLogSession) TotalCostUSD() float64 {
return sess.InputCostUSD + sess.CachedInputCostUSD + sess.CacheCreationCostUSD + sess.OutputCostUSD
}
// CacheCostUSD is the session's prompt-cache spend: cache reads plus writes.
func (sess *AgentNetworkAccessLogSession) CacheCostUSD() float64 {
return sess.CachedInputCostUSD + sess.CacheCreationCostUSD
}
// sessionKey is the grouping key for an entry: its session id, or — when the
@@ -205,7 +262,12 @@ func (sess *AgentNetworkAccessLogSession) foldEntry(sk *sessionSeen, e *AgentNet
sess.InputTokens += e.InputTokens
sess.OutputTokens += e.OutputTokens
sess.TotalTokens += e.TotalTokens
sess.CostUSD += e.CostUSD
sess.CachedInputTokens += e.CachedInputTokens
sess.CacheCreationTokens += e.CacheCreationTokens
sess.InputCostUSD += e.InputCostUSD
sess.CachedInputCostUSD += e.CachedInputCostUSD
sess.CacheCreationCostUSD += e.CacheCreationCostUSD
sess.OutputCostUSD += e.OutputCostUSD
if e.Timestamp.Before(sess.StartedAt) {
sess.StartedAt = e.Timestamp
}
@@ -248,15 +310,22 @@ func (sess *AgentNetworkAccessLogSession) ToAPIResponse() api.AgentNetworkAccess
}
out := api.AgentNetworkAccessLogSession{
StartedAt: sess.StartedAt,
EndedAt: sess.EndedAt,
RequestCount: sess.RequestCount,
InputTokens: sess.InputTokens,
OutputTokens: sess.OutputTokens,
TotalTokens: sess.TotalTokens,
CostUsd: sess.CostUSD,
Decision: sess.Decision,
Entries: entries,
StartedAt: sess.StartedAt,
EndedAt: sess.EndedAt,
RequestCount: sess.RequestCount,
InputTokens: sess.InputTokens,
OutputTokens: sess.OutputTokens,
TotalTokens: sess.TotalTokens,
CachedInputTokens: sess.CachedInputTokens,
CacheCreationTokens: sess.CacheCreationTokens,
InputCostUsd: sess.InputCostUSD,
CachedInputCostUsd: sess.CachedInputCostUSD,
CacheCreationCostUsd: sess.CacheCreationCostUSD,
OutputCostUsd: sess.OutputCostUSD,
CostUsd: sess.TotalCostUSD(),
CacheCostUsd: sess.CacheCostUSD(),
Decision: sess.Decision,
Entries: entries,
}
out.SessionId = strPtr(sess.SessionID)
out.UserId = strPtr(sess.UserID)
management/internals/modules/agentnetwork/types/accesslogfilter.go
+2 -2
View File
@@ -54,7 +54,7 @@ var accessLogSortFields = map[string]string{
"provider": "provider",
"status_code": "status_code",
"duration": "duration",
"cost_usd": "cost_usd",
"cost_usd": CostUSDSQLExpr,
"total_tokens": "total_tokens",
"user_id": "user_id",
"decision": "decision",
@@ -70,7 +70,7 @@ var accessLogSortFields = map[string]string{
var sessionSortExprs = map[string]string{ //nolint:gosec // G101 false positive: "total_tokens" sort key, not a credential
"timestamp": "MAX(timestamp)",
"started_at": "MIN(timestamp)",
"cost_usd": "SUM(cost_usd)",
"cost_usd": "SUM" + CostUSDSQLExpr,
"total_tokens": "SUM(total_tokens)",
"duration": "SUM(duration)",
"request_count": "COUNT(*)",
management/internals/modules/agentnetwork/types/cost_test.go
+124
View File
@@ -0,0 +1,124 @@
package types
import (
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// costRow builds an access-log entry carrying only a cost breakdown — the rest
// of the row is irrelevant to the summation identities under test.
func costRow(id, session string, ts time.Time, in, cachedIn, cacheCreate, out float64) *AgentNetworkAccessLog {
return &AgentNetworkAccessLog{
ID: id,
SessionID: session,
Timestamp: ts,
InputCostUSD: in,
CachedInputCostUSD: cachedIn,
CacheCreationCostUSD: cacheCreate,
OutputCostUSD: out,
}
}
// TestAPIResponse_CostComponentsSumToAggregates is the contract a client adding
// up an API response depends on: within a single rendered object, the four
// per-bucket fields sum to cost_usd, and the two cache fields sum to
// cache_cost_usd. Uses rates that are not exactly representable in binary
// floating point, so the identity is checked against real arithmetic rather
// than round numbers.
func TestAPIResponse_CostComponentsSumToAggregates(t *testing.T) {
row := costRow("r1", "s1", time.Now(), 0.000768, 0.0002304, 0.00192, 0.003)
api := row.ToAPIResponse()
assert.InDelta(t, api.InputCostUsd+api.CachedInputCostUsd+api.CacheCreationCostUsd+api.OutputCostUsd,
api.CostUsd, 1e-12, "rendered buckets must sum to the rendered cost_usd")
assert.InDelta(t, api.CachedInputCostUsd+api.CacheCreationCostUsd, api.CacheCostUsd, 1e-12,
"rendered cache buckets must sum to the rendered cache_cost_usd")
assert.InDelta(t, 0.0059184, api.CostUsd, 1e-12, "total is the exact sum, not a separately rounded figure")
assert.InDelta(t, 0.0021504, api.CacheCostUsd, 1e-12, "cache cost is the exact sum of the two cache buckets")
}
// TestSessionSummary_SumsMatchSummedEntries proves a session summary equals the
// sum of the entries it renders: a client that adds up the entries itself must
// land on the same number the summary reports, per bucket and in total.
func TestSessionSummary_SumsMatchSummedEntries(t *testing.T) {
base := time.Date(2026, 5, 5, 10, 0, 0, 0, time.UTC)
entries := []*AgentNetworkAccessLog{
costRow("r1", "s1", base, 0.000768, 0.0002304, 0.00192, 0.003),
costRow("r2", "s1", base.Add(time.Minute), 0.000625, 0.0009375, 0, 0.005),
costRow("r3", "s1", base.Add(2*time.Minute), 0.0000016, 0, 0, 0.0000032),
}
sessions := FoldAccessLogSessions([]string{"s1"}, entries)
require.Len(t, sessions, 1)
sess := sessions[0].ToAPIResponse()
var wantInput, wantCachedInput, wantCacheCreation, wantOutput float64
for _, e := range entries {
wantInput += e.InputCostUSD
wantCachedInput += e.CachedInputCostUSD
wantCacheCreation += e.CacheCreationCostUSD
wantOutput += e.OutputCostUSD
}
assert.InDelta(t, wantInput, sess.InputCostUsd, 1e-12, "session input cost is the sum of its entries")
assert.InDelta(t, wantCachedInput, sess.CachedInputCostUsd, 1e-12, "session cache-read cost is the sum of its entries")
assert.InDelta(t, wantCacheCreation, sess.CacheCreationCostUsd, 1e-12, "session cache-write cost is the sum of its entries")
assert.InDelta(t, wantOutput, sess.OutputCostUsd, 1e-12, "session output cost is the sum of its entries")
assert.InDelta(t, wantInput+wantCachedInput+wantCacheCreation+wantOutput, sess.CostUsd, 1e-12,
"session total equals the summed entry buckets")
// Summing the rendered entries must give the same answer as reading the
// summary — the property a UI relies on when it totals a table itself.
var fromEntries float64
for _, e := range sess.Entries {
fromEntries += e.CostUsd
}
assert.InDelta(t, sess.CostUsd, fromEntries, 1e-12, "summary total must match the summed rendered entries")
// The sub-microdollar row must still contribute; it would vanish under
// 6-decimal quantisation.
assert.Greater(t, sess.InputCostUsd, 0.001393, "small-cost rows must not be quantised away")
}
// TestUsageBuckets_SumsMatchSummedRows proves the same identity one level up:
// a usage bucket equals the sum of the ledger rows folded into it, and the
// buckets together equal the whole range.
func TestUsageBuckets_SumsMatchSummedRows(t *testing.T) {
day1 := time.Date(2026, 5, 5, 9, 0, 0, 0, time.UTC)
day2 := time.Date(2026, 5, 6, 9, 0, 0, 0, time.UTC)
rows := []*AgentNetworkUsage{
{ID: "u1", Timestamp: day1, InputCostUSD: 0.000768, CachedInputCostUSD: 0.0002304, CacheCreationCostUSD: 0.00192, OutputCostUSD: 0.003},
{ID: "u2", Timestamp: day1.Add(time.Hour), InputCostUSD: 0.000625, CachedInputCostUSD: 0.0009375, OutputCostUSD: 0.005},
{ID: "u3", Timestamp: day2, InputCostUSD: 0.0000016, OutputCostUSD: 0.0000032},
}
buckets := AggregateUsageByGranularity(rows, UsageGranularityDay)
require.Len(t, buckets, 2, "two distinct days expected")
var total, cache float64
for _, b := range buckets {
api := b.ToAPIResponse()
assert.InDelta(t, api.InputCostUsd+api.CachedInputCostUsd+api.CacheCreationCostUsd+api.OutputCostUsd,
api.CostUsd, 1e-12, "each bucket's components must sum to its cost_usd")
total += api.CostUsd
cache += api.CacheCostUsd
}
var wantTotal, wantCache float64
for _, r := range rows {
wantTotal += r.TotalCostUSD()
wantCache += r.CacheCostUSD()
}
assert.InDelta(t, wantTotal, total, 1e-12, "buckets must sum to the total across all ledger rows")
assert.InDelta(t, wantCache, cache, 1e-12, "buckets must sum to the cache spend across all ledger rows")
// A month bucket over the same rows must total identically — regrouping
// changes the partition, never the sum.
monthly := AggregateUsageByGranularity(rows, UsageGranularityMonth)
require.Len(t, monthly, 1)
assert.InDelta(t, wantTotal, monthly[0].ToAPIResponse().CostUsd, 1e-12,
"re-bucketing at a different granularity must preserve the total")
}
management/internals/modules/agentnetwork/types/provider.go
+58 -28
View File
@@ -14,10 +14,24 @@ import (
// ProviderModel is one row in the provider's models list. The operator
// pins the per-1k input/output price for cost tracking; ID is the
// model identifier the upstream provider expects on the wire.
//
// The three cache rates are pointers because absence is meaningful: nil
// means "inherit NetBird's default rate for this model" (folded in at
// synthesis time), while an explicit 0 means "no discount — bill this
// cache bucket at the input rate".
type ProviderModel struct {
ID string `json:"id"`
InputPer1k float64 `json:"input_per_1k"`
OutputPer1k float64 `json:"output_per_1k"`
// CachedInputPer1k is the OpenAI-shape rate for cached prompt tokens
// (a subset of input tokens).
CachedInputPer1k *float64 `json:"cached_input_per_1k,omitempty"`
// CacheReadPer1k is the Anthropic-shape rate for cache-read tokens
// (additive to input tokens).
CacheReadPer1k *float64 `json:"cache_read_per_1k,omitempty"`
// CacheCreationPer1k is the Anthropic-shape rate for cache-creation
// tokens (additive to input tokens).
CacheCreationPer1k *float64 `json:"cache_creation_per_1k,omitempty"`
}
// Provider is an Agent Network AI provider record persisted per account.
@@ -128,9 +142,12 @@ func (p *Provider) FromAPIRequest(req *api.AgentNetworkProviderRequest) {
if req.Models != nil {
for _, m := range *req.Models {
p.Models = append(p.Models, ProviderModel{
ID: m.Id,
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
ID: m.Id,
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
CachedInputPer1k: copyFloatPtr(m.CachedInputPer1k),
CacheReadPer1k: copyFloatPtr(m.CacheReadPer1k),
CacheCreationPer1k: copyFloatPtr(m.CacheCreationPer1k),
})
}
}
@@ -147,9 +164,7 @@ func (p *Provider) FromAPIRequest(req *api.AgentNetworkProviderRequest) {
p.MetadataDisabled = *req.MetadataDisabled
}
// Identity-header overrides for catalogs flagged Customizable.
// nil pointer = "field omitted on the wire" → leave the stored
// value untouched (per the openapi description). Empty string is
// an explicit clear that disables stamping for this dimension.
// Empty or omitted disables stamping for this dimension.
if req.IdentityHeaderUserId != nil {
p.IdentityHeaderUserID = strings.TrimSpace(*req.IdentityHeaderUserId)
}
@@ -164,24 +179,31 @@ func (p *Provider) ToAPIResponse() *api.AgentNetworkProvider {
models := make([]api.AgentNetworkProviderModel, 0, len(p.Models))
for _, m := range p.Models {
models = append(models, api.AgentNetworkProviderModel{
Id: m.ID,
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
Id: m.ID,
InputPer1k: m.InputPer1k,
OutputPer1k: m.OutputPer1k,
CachedInputPer1k: copyFloatPtr(m.CachedInputPer1k),
CacheReadPer1k: copyFloatPtr(m.CacheReadPer1k),
CacheCreationPer1k: copyFloatPtr(m.CacheCreationPer1k),
})
}
created := p.CreatedAt
updated := p.UpdatedAt
resp := &api.AgentNetworkProvider{
Id: p.ID,
ProviderId: p.ProviderID,
Name: p.Name,
UpstreamUrl: p.UpstreamURL,
Models: models,
Enabled: p.Enabled,
SkipTlsVerification: p.SkipTLSVerification,
MetadataDisabled: p.MetadataDisabled,
CreatedAt: &created,
UpdatedAt: &updated,
Id: p.ID,
ProviderId: p.ProviderID,
Name: p.Name,
UpstreamUrl: p.UpstreamURL,
Models: models,
// Always present on the wire so an explicitly cleared header
// round-trips as "" instead of vanishing from the response.
IdentityHeaderUserId: p.IdentityHeaderUserID,
IdentityHeaderGroups: p.IdentityHeaderGroups,
Enabled: p.Enabled,
SkipTlsVerification: p.SkipTLSVerification,
MetadataDisabled: p.MetadataDisabled,
CreatedAt: &created,
UpdatedAt: &updated,
}
if len(p.ExtraValues) > 0 {
out := make(map[string]string, len(p.ExtraValues))
@@ -190,22 +212,30 @@ func (p *Provider) ToAPIResponse() *api.AgentNetworkProvider {
}
resp.ExtraValues = &out
}
if p.IdentityHeaderUserID != "" {
v := p.IdentityHeaderUserID
resp.IdentityHeaderUserId = &v
}
if p.IdentityHeaderGroups != "" {
v := p.IdentityHeaderGroups
resp.IdentityHeaderGroups = &v
}
return resp
}
// copyFloatPtr returns a fresh pointer to the same value, or nil. Keeps
// stored models and API payloads from aliasing each other's rate fields.
func copyFloatPtr(v *float64) *float64 {
if v == nil {
return nil
}
out := *v
return &out
}
// Copy returns a deep copy of the provider.
func (p *Provider) Copy() *Provider {
clone := *p
if p.Models != nil {
clone.Models = append([]ProviderModel(nil), p.Models...)
clone.Models = make([]ProviderModel, len(p.Models))
for i, m := range p.Models {
m.CachedInputPer1k = copyFloatPtr(m.CachedInputPer1k)
m.CacheReadPer1k = copyFloatPtr(m.CacheReadPer1k)
m.CacheCreationPer1k = copyFloatPtr(m.CacheCreationPer1k)
clone.Models[i] = m
}
}
if p.ExtraValues != nil {
clone.ExtraValues = make(map[string]string, len(p.ExtraValues))
management/internals/modules/agentnetwork/types/provider_test.go
+38
View File
@@ -77,3 +77,41 @@ func TestProvider_MetadataDisabled_RoundTrip(t *testing.T) {
assert.False(t, p.MetadataDisabled, "explicit false must clear metadata_disabled")
assert.False(t, p.ToAPIResponse().MetadataDisabled, "response must reflect the cleared value")
}
// TestProvider_IdentityHeaders_AlwaysOnWire pins that the identity header
// fields are always present in the API response — an explicitly cleared
// ("") header must round-trip as "" rather than vanish, so API consumers
// (e.g. the Terraform provider) never observe a value other than the one
// they wrote.
func TestProvider_IdentityHeaders_AlwaysOnWire(t *testing.T) {
set := "x-bf-dim-netbird_user_id"
empty := ""
base := func() *api.AgentNetworkProviderRequest {
return &api.AgentNetworkProviderRequest{
ProviderId: "custom",
Name: "bifrost",
UpstreamUrl: "https://bifrost.internal",
}
}
p := NewProvider("acc-1")
resp := p.ToAPIResponse()
assert.Equal(t, "", resp.IdentityHeaderUserId, "unset header must surface as empty string, not be omitted")
assert.Equal(t, "", resp.IdentityHeaderGroups, "unset header must surface as empty string, not be omitted")
req := base()
req.IdentityHeaderUserId = &set
p.FromAPIRequest(req)
assert.Equal(t, set, p.ToAPIResponse().IdentityHeaderUserId, "configured header must round-trip")
// Omitting the field preserves it.
p.FromAPIRequest(base())
assert.Equal(t, set, p.ToAPIResponse().IdentityHeaderUserId, "omitted header must preserve the stored value")
// An explicit "" clears it AND stays visible on the wire.
req = base()
req.IdentityHeaderUserId = &empty
p.FromAPIRequest(req)
assert.Equal(t, "", p.ToAPIResponse().IdentityHeaderUserId, "cleared header must round-trip as empty string")
}
management/internals/modules/agentnetwork/types/settings.go
+39 -9
View File
@@ -1,6 +1,7 @@
package types
import (
"strings"
"time"
"github.com/netbirdio/netbird/shared/management/http/api"
@@ -42,18 +43,34 @@ type Settings struct {
// schema cohesive.
func (Settings) TableName() string { return "agent_network_settings" }
// DefaultSettings returns the settings an account observes before its row is
// bootstrapped: log collection on with the default retention, everything else
// off, and no cluster/subdomain assigned yet. Bootstrap persists exactly these
// values plus the assigned cluster and subdomain, so the pre-bootstrap read
// and the freshly bootstrapped row agree.
func DefaultSettings(accountID string) *Settings {
return &Settings{
AccountID: accountID,
EnableLogCollection: true,
AccessLogRetentionDays: DefaultAccessLogRetentionDays,
}
}
// Endpoint returns the bare hostname agents reach this account at:
// `<subdomain>.<cluster>`.
// `<subdomain>.<cluster>`. Empty until both halves are assigned at bootstrap.
func (s *Settings) Endpoint() string {
if s.Cluster == "" || s.Subdomain == "" {
return ""
}
return s.Subdomain + "." + s.Cluster
}
// ToAPIResponse renders the settings as the API representation.
// ToAPIResponse renders the settings as the API representation. The
// timestamps are omitted while zero — a default (not yet bootstrapped) view
// has no persisted row to date.
func (s *Settings) ToAPIResponse() *api.AgentNetworkSettings {
created := s.CreatedAt
updated := s.UpdatedAt
retention := s.AccessLogRetentionDays
return &api.AgentNetworkSettings{
resp := &api.AgentNetworkSettings{
Cluster: s.Cluster,
Subdomain: s.Subdomain,
Endpoint: s.Endpoint(),
@@ -61,14 +78,27 @@ func (s *Settings) ToAPIResponse() *api.AgentNetworkSettings {
EnablePromptCollection: s.EnablePromptCollection,
RedactPii: s.RedactPii,
AccessLogRetentionDays: &retention,
CreatedAt: &created,
UpdatedAt: &updated,
}
if !s.CreatedAt.IsZero() {
created := s.CreatedAt
resp.CreatedAt = &created
}
if !s.UpdatedAt.IsZero() {
updated := s.UpdatedAt
resp.UpdatedAt = &updated
}
return resp
}
// FromAPIRequest applies the mutable settings fields from the request. Cluster
// and Subdomain are immutable and intentionally not touched here.
// FromAPIRequest applies the request onto the receiver. The mutable
// collection fields are always replaced with the request values. Cluster
// participates only in bootstrap and the immutability check (see
// Manager.UpdateSettings); Subdomain is server-assigned and never taken
// from a request.
func (s *Settings) FromAPIRequest(req *api.AgentNetworkSettingsRequest) {
if req.Cluster != nil {
s.Cluster = strings.TrimSpace(*req.Cluster)
}
s.EnableLogCollection = req.EnableLogCollection
s.EnablePromptCollection = req.EnablePromptCollection
s.RedactPii = req.RedactPii
management/internals/modules/agentnetwork/types/usage.go
+24 -2
View File
@@ -25,8 +25,19 @@ type AgentNetworkUsage struct {
InputTokens int64
OutputTokens int64
TotalTokens int64
CostUSD float64
CreatedAt time.Time
// Prompt-cache buckets: read + write token counts.
CachedInputTokens int64
CacheCreationTokens int64
// Per-bucket cost breakdown, mirroring AgentNetworkAccessLog — the only
// cost state stored; total and cache portion are derived on read. Kept on
// the usage ledger too so spend can be attributed per bucket even for
// accounts with log collection turned off. See AgentNetworkAccessLog for
// why the columns carry a zero default.
InputCostUSD float64 `gorm:"not null;default:0"`
CachedInputCostUSD float64 `gorm:"not null;default:0"`
CacheCreationCostUSD float64 `gorm:"not null;default:0"`
OutputCostUSD float64 `gorm:"not null;default:0"`
CreatedAt time.Time
}
// TableName keeps usage records in their own stripped table. Named
@@ -34,6 +45,17 @@ type AgentNetworkUsage struct {
// agent_network_usage table in a shared database.
func (AgentNetworkUsage) TableName() string { return "agent_network_request_usage" }
// TotalCostUSD is the request's total cost: the sum of the four per-bucket
// costs. Derived rather than stored so it cannot disagree with the breakdown.
func (u *AgentNetworkUsage) TotalCostUSD() float64 {
return u.InputCostUSD + u.CachedInputCostUSD + u.CacheCreationCostUSD + u.OutputCostUSD
}
// CacheCostUSD is the portion of the total billed for prompt-cache buckets.
func (u *AgentNetworkUsage) CacheCostUSD() float64 {
return u.CachedInputCostUSD + u.CacheCreationCostUSD
}
// AgentNetworkUsageGroup is the normalised many-to-many row linking a usage
// record to one authorising group, mirroring AgentNetworkAccessLogGroup so the
// usage overview can filter by group with a `group_id IN (...)` join.
management/internals/modules/agentnetwork/types/usageoverview.go
+40 -11
View File
@@ -33,21 +33,45 @@ func ParseUsageGranularity(s string) UsageGranularity {
// AgentNetworkUsageBucket is one aggregated usage time bucket. PeriodStart is
// the UTC start of the bucket as YYYY-MM-DD.
type AgentNetworkUsageBucket struct {
PeriodStart string
InputTokens int64
OutputTokens int64
TotalTokens int64
CostUSD float64
PeriodStart string
InputTokens int64
OutputTokens int64
TotalTokens int64
CachedInputTokens int64
CacheCreationTokens int64
InputCostUSD float64
CachedInputCostUSD float64
CacheCreationCostUSD float64
OutputCostUSD float64
}
// TotalCostUSD is the bucket's total spend: the sum of the four per-bucket
// costs. Derived rather than accumulated separately so it cannot disagree with
// the components.
func (b *AgentNetworkUsageBucket) TotalCostUSD() float64 {
return b.InputCostUSD + b.CachedInputCostUSD + b.CacheCreationCostUSD + b.OutputCostUSD
}
// CacheCostUSD is the bucket's prompt-cache spend: cache reads plus writes.
func (b *AgentNetworkUsageBucket) CacheCostUSD() float64 {
return b.CachedInputCostUSD + b.CacheCreationCostUSD
}
// ToAPIResponse renders the bucket as the API representation.
func (b *AgentNetworkUsageBucket) ToAPIResponse() api.AgentNetworkUsageBucket {
return api.AgentNetworkUsageBucket{
PeriodStart: b.PeriodStart,
InputTokens: b.InputTokens,
OutputTokens: b.OutputTokens,
TotalTokens: b.TotalTokens,
CostUsd: b.CostUSD,
PeriodStart: b.PeriodStart,
InputTokens: b.InputTokens,
OutputTokens: b.OutputTokens,
TotalTokens: b.TotalTokens,
CachedInputTokens: b.CachedInputTokens,
CacheCreationTokens: b.CacheCreationTokens,
InputCostUsd: b.InputCostUSD,
CachedInputCostUsd: b.CachedInputCostUSD,
CacheCreationCostUsd: b.CacheCreationCostUSD,
OutputCostUsd: b.OutputCostUSD,
CostUsd: b.TotalCostUSD(),
CacheCostUsd: b.CacheCostUSD(),
}
}
@@ -84,7 +108,12 @@ func AggregateUsageByGranularity(rows []*AgentNetworkUsage, g UsageGranularity)
b.InputTokens += r.InputTokens
b.OutputTokens += r.OutputTokens
b.TotalTokens += r.TotalTokens
b.CostUSD += r.CostUSD
b.CachedInputTokens += r.CachedInputTokens
b.CacheCreationTokens += r.CacheCreationTokens
b.InputCostUSD += r.InputCostUSD
b.CachedInputCostUSD += r.CachedInputCostUSD
b.CacheCreationCostUSD += r.CacheCreationCostUSD
b.OutputCostUSD += r.OutputCostUSD
}
out := make([]*AgentNetworkUsageBucket, 0, len(byPeriod))
management/internals/modules/agentnetwork/wire_shape_test.go
+6
View File
@@ -103,6 +103,12 @@ func TestSynthesizedService_WireShape(t *testing.T) {
assert.Equal(t, middlewareIDCostMeter, mws[6].GetId(), "seventh middleware id")
assert.Equal(t, proto.MiddlewareSlot_MIDDLEWARE_SLOT_ON_RESPONSE, mws[6].GetSlot(), "cost meter slot")
var costCfg costMeterConfig
require.NoError(t, json.Unmarshal(mws[6].GetConfigJson(), &costCfg), "cost meter config JSON must decode from the wire")
require.NotNil(t, costCfg.Pricing, "the pricing table must travel on the wire — the proxy has no embedded price list to fall back to")
assert.NotEmpty(t, costCfg.Pricing.Defaults["openai"], "default table rides in every mapping")
assert.NotEmpty(t, costCfg.Pricing.Defaults["anthropic"], "default table covers all surfaces")
assert.NotEmpty(t, costCfg.Pricing.Defaults["bedrock"], "default table covers all surfaces")
assert.Equal(t, middlewareIDLLMResponseParser, mws[7].GetId(), "eighth middleware id")
assert.Equal(t, proto.MiddlewareSlot_MIDDLEWARE_SLOT_ON_RESPONSE, mws[7].GetSlot(), "response parser slot")
management/internals/modules/reverseproxy/proxy/manager/controller.go
+3 -3
View File
@@ -36,7 +36,7 @@ func NewGRPCController(proxyGRPCServer *nbgrpc.ProxyServiceServer, meter metric.
// SendServiceUpdateToCluster sends a service update to a specific proxy cluster.
func (c *GRPCController) SendServiceUpdateToCluster(ctx context.Context, accountID string, update *proto.ProxyMapping, clusterAddr string) {
c.proxyGRPCServer.SendServiceUpdateToCluster(ctx, update, clusterAddr)
c.metrics.IncrementServiceUpdateSendCount(clusterAddr)
c.metrics.IncrementServiceUpdateSendCount()
}
// GetOIDCValidationConfig returns the OIDC validation configuration from the gRPC server.
@@ -53,7 +53,7 @@ func (c *GRPCController) RegisterProxyToCluster(ctx context.Context, clusterAddr
proxySet.(*sync.Map).Store(proxyID, struct{}{})
log.WithContext(ctx).Debugf("Registered proxy %s to cluster %s", proxyID, clusterAddr)
c.metrics.IncrementProxyConnectionCount(clusterAddr)
c.metrics.IncrementProxyConnectionCount()
return nil
}
@@ -67,7 +67,7 @@ func (c *GRPCController) UnregisterProxyFromCluster(ctx context.Context, cluster
proxySet.(*sync.Map).Delete(proxyID)
log.WithContext(ctx).Debugf("Unregistered proxy %s from cluster %s", proxyID, clusterAddr)
c.metrics.DecrementProxyConnectionCount(clusterAddr)
c.metrics.DecrementProxyConnectionCount()
}
return nil
}
management/internals/modules/reverseproxy/proxy/manager/metrics.go
+6 -16
View File
@@ -3,7 +3,6 @@ package manager
import (
"context"
"go.opentelemetry.io/otel/attribute"
"go.opentelemetry.io/otel/metric"
)
@@ -48,25 +47,16 @@ func newMetrics(meter metric.Meter) (*metrics, error) {
}, nil
}
func (m *metrics) IncrementProxyConnectionCount(clusterAddr string) {
m.proxyConnectionCount.Add(context.Background(), 1,
metric.WithAttributes(
attribute.String("cluster", clusterAddr),
))
func (m *metrics) IncrementProxyConnectionCount() {
m.proxyConnectionCount.Add(context.Background(), 1)
}
func (m *metrics) DecrementProxyConnectionCount(clusterAddr string) {
m.proxyConnectionCount.Add(context.Background(), -1,
metric.WithAttributes(
attribute.String("cluster", clusterAddr),
))
func (m *metrics) DecrementProxyConnectionCount() {
m.proxyConnectionCount.Add(context.Background(), -1)
}
func (m *metrics) IncrementServiceUpdateSendCount(clusterAddr string) {
m.serviceUpdateSendCount.Add(context.Background(), 1,
metric.WithAttributes(
attribute.String("cluster", clusterAddr),
))
func (m *metrics) IncrementServiceUpdateSendCount() {
m.serviceUpdateSendCount.Add(context.Background(), 1)
}
func (m *metrics) IncrementProxyHeartbeatCount() {
management/internals/server/boot.go
+7
View File
@@ -203,6 +203,10 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
grpc.ChainStreamInterceptor(realip.StreamServerInterceptorOpts(realipOpts...), streamInterceptor, proxyStream),
}
// Append interceptors contributed by registered gRPC extensions. These
// run after the built-in chain (ChainUnaryInterceptor is additive).
gRPCOpts = appendExtensionInterceptors(gRPCOpts, s.grpcExtensions)
if s.Config.HttpConfig.LetsEncryptDomain != "" {
certManager, err := encryption.CreateCertManager(s.Config.Datadir, s.Config.HttpConfig.LetsEncryptDomain)
if err != nil {
@@ -234,6 +238,9 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
mgmtProto.RegisterProxyServiceServer(gRPCAPIHandler, s.ReverseProxyGRPCServer())
log.Info("ProxyService registered on gRPC server")
// Register services contributed by external modules via the extension seam.
registerExtensions(gRPCAPIHandler, s.grpcExtensions)
return gRPCAPIHandler
})
}
management/internals/server/config/config.go
+21
View File
@@ -55,6 +55,8 @@ type Config struct {
ReverseProxy ReverseProxy
AgentNetwork AgentNetwork
// disable default all-to-all policy
DisableDefaultPolicy bool
@@ -185,6 +187,25 @@ type StoreConfig struct {
Engine types.Engine
}
// AgentNetwork contains agent-network (LLM gateway) configuration.
type AgentNetwork struct {
// PricingDefaultsFile is the path to the YAML file holding the default
// LLM pricing table (defaults_llm_pricing.yaml). A relative path is
// resolved against <Datadir>, so a bare filename lands alongside the
// store. Empty falls back to probing <Datadir>/defaults_llm_pricing.yaml;
// with no file present the compiled-in defaults serve. Schema: surface ("openai"/"anthropic"/
// "bedrock") -> model -> rates in USD per 1k tokens (input_per_1k,
// output_per_1k, and the optional cached_input_per_1k /
// cache_read_per_1k / cache_creation_per_1k). File entries replace the
// compiled-in entry for the same surface+model whole; everything else
// keeps the compiled-in rates. The file is re-read periodically (mtime
// poll), and the live table feeds both the synthesizer (what proxies
// bill with) and the dashboard's catalog endpoint (what model rows
// prefill with). An explicitly configured path that fails to load
// fails startup; runtime reload errors keep the previous table.
PricingDefaultsFile string
}
// ReverseProxy contains reverse proxy configuration in front of management.
type ReverseProxy struct {
// TrustedHTTPProxies represents a list of trusted HTTP proxies by their IP prefixes.
management/internals/server/grpc_extension.go
+74
View File
@@ -0,0 +1,74 @@
package server
import (
"context"
"google.golang.org/grpc"
)
// GRPCExtension bundles an external module's contribution to the management
// gRPC server: the registration of one or more services onto the shared
// grpc.Server, any server-wide interceptors those services require, and an
// optional shutdown hook. It is a generic extension point with no knowledge of
// any specific service.
type GRPCExtension struct {
// Register is invoked with the shared grpc.Server (as a ServiceRegistrar)
// after the built-in services are registered. It may register any number of
// services. May be nil.
Register func(grpc.ServiceRegistrar)
// UnaryInterceptors are appended to the server's unary interceptor chain,
// running after the built-in interceptors. May be empty.
UnaryInterceptors []grpc.UnaryServerInterceptor
// StreamInterceptors are appended to the server's stream interceptor chain,
// running after the built-in interceptors. May be empty.
StreamInterceptors []grpc.StreamServerInterceptor
// Shutdown, if non-nil, is called once during Stop() with the context
// governing server shutdown, which carries a deadline. The hook MUST
// return promptly and MUST abandon its work once that context is
// cancelled or expires: it runs before the rest of Stop()'s cleanup
// (store, event store, embedded IdP) and before Stop() itself checks the
// context's deadline, so a hook that ignores the context will delay all
// of that cleanup and prevent Stop() from returning on time. May be nil.
Shutdown func(ctx context.Context)
}
// RegisterGRPCExtension registers a gRPC extension. Call before the gRPC server
// is first built (i.e. before Start); registrations after that have no effect.
func (s *BaseServer) RegisterGRPCExtension(ext GRPCExtension) {
s.grpcExtensions = append(s.grpcExtensions, ext)
}
// appendExtensionInterceptors appends each extension's interceptors to the gRPC
// server options as additional chained interceptors. grpc.ChainUnaryInterceptor
// and grpc.ChainStreamInterceptor are additive, so the returned options run the
// extension interceptors after any interceptors already present in opts.
func appendExtensionInterceptors(opts []grpc.ServerOption, exts []GRPCExtension) []grpc.ServerOption {
for _, ext := range exts {
if len(ext.UnaryInterceptors) > 0 {
opts = append(opts, grpc.ChainUnaryInterceptor(ext.UnaryInterceptors...))
}
if len(ext.StreamInterceptors) > 0 {
opts = append(opts, grpc.ChainStreamInterceptor(ext.StreamInterceptors...))
}
}
return opts
}
// registerExtensions registers each extension's services onto reg.
func registerExtensions(reg grpc.ServiceRegistrar, exts []GRPCExtension) {
for _, ext := range exts {
if ext.Register != nil {
ext.Register(reg)
}
}
}
// runExtensionShutdownHooks calls each extension's shutdown hook, if set,
// passing ctx through so hooks can honor its deadline/cancellation.
func runExtensionShutdownHooks(ctx context.Context, exts []GRPCExtension) {
for _, ext := range exts {
if ext.Shutdown != nil {
ext.Shutdown(ctx)
}
}
}
management/internals/server/grpc_extension_test.go
+160
View File
@@ -0,0 +1,160 @@
package server
import (
"context"
"net"
"sync/atomic"
"testing"
"google.golang.org/grpc"
"google.golang.org/grpc/credentials/insecure"
"google.golang.org/grpc/health"
healthgrpc "google.golang.org/grpc/health/grpc_health_v1"
"google.golang.org/grpc/test/bufconn"
)
// Test that an extension's interceptors and service registration are actually
// wired onto a real in-process gRPC server via the helpers, and that shutdown
// hooks run. This validates the load-bearing assumption that
// grpc.ChainUnaryInterceptor is additive (extension interceptors run in
// addition to any base chain).
func TestGRPCExtensionAppliedToServer(t *testing.T) {
var unaryCalls atomic.Int32
var streamShutdownCalled atomic.Bool
ext := GRPCExtension{
Register: func(reg grpc.ServiceRegistrar) {
healthgrpc.RegisterHealthServer(reg, health.NewServer())
},
UnaryInterceptors: []grpc.UnaryServerInterceptor{
func(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
unaryCalls.Add(1)
return handler(ctx, req)
},
},
Shutdown: func(ctx context.Context) { streamShutdownCalled.Store(true) },
}
exts := []GRPCExtension{ext}
// Base options mimic GRPCServer(): a pre-existing chain the extension appends to.
var baseUnaryCalls atomic.Int32
opts := []grpc.ServerOption{
grpc.ChainUnaryInterceptor(func(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
baseUnaryCalls.Add(1)
return handler(ctx, req)
}),
}
opts = appendExtensionInterceptors(opts, exts)
srv := grpc.NewServer(opts...)
registerExtensions(srv, exts)
lis := bufconn.Listen(1024 * 1024)
go func() { _ = srv.Serve(lis) }()
t.Cleanup(srv.Stop)
conn, err := grpc.NewClient("passthrough:///bufnet",
grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) { return lis.DialContext(ctx) }),
grpc.WithTransportCredentials(insecure.NewCredentials()))
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = conn.Close() })
_, err = healthgrpc.NewHealthClient(conn).Check(context.Background(), &healthgrpc.HealthCheckRequest{})
if err != nil {
t.Fatalf("health check via extension-registered service failed: %v", err)
}
if baseUnaryCalls.Load() != 1 {
t.Errorf("base interceptor calls = %d, want 1 (base chain must be preserved)", baseUnaryCalls.Load())
}
if unaryCalls.Load() != 1 {
t.Errorf("extension interceptor calls = %d, want 1", unaryCalls.Load())
}
runExtensionShutdownHooks(context.Background(), exts)
if !streamShutdownCalled.Load() {
t.Error("extension shutdown hook was not called")
}
}
// TestGRPCExtensionShutdownHookReceivesCallerContext asserts that each hook receives
// a non-nil context and that it is the very same context the caller passed
// in, so hooks can rely on values/deadlines placed on it by Stop().
func TestGRPCExtensionShutdownHookReceivesCallerContext(t *testing.T) {
type sentinelKey struct{}
want := "shutdown-ctx-sentinel"
ctx := context.WithValue(context.Background(), sentinelKey{}, want)
var called bool
ext := GRPCExtension{
Shutdown: func(hookCtx context.Context) {
called = true
if hookCtx == nil {
t.Fatal("hook received a nil context")
}
got, _ := hookCtx.Value(sentinelKey{}).(string)
if got != want {
t.Errorf("hook context sentinel = %q, want %q (not the caller's context)", got, want)
}
},
}
runExtensionShutdownHooks(ctx, []GRPCExtension{ext})
if !called {
t.Fatal("shutdown hook was not called")
}
}
// TestGRPCExtensionShutdownHookObservesCancellation documents, by test, that
// hooks can honor cancellation/deadlines: a hook given an already-cancelled
// context must see ctx.Err() != nil and a closed Done() channel.
func TestGRPCExtensionShutdownHookObservesCancellation(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
cancel()
var called bool
ext := GRPCExtension{
Shutdown: func(hookCtx context.Context) {
called = true
if hookCtx.Err() == nil {
t.Error("hook context Err() = nil, want non-nil for a cancelled context")
}
select {
case <-hookCtx.Done():
default:
t.Error("hook context Done() channel is not closed for a cancelled context")
}
},
}
runExtensionShutdownHooks(ctx, []GRPCExtension{ext})
if !called {
t.Fatal("shutdown hook was not called")
}
}
// TestGRPCExtensionShutdownHookNilSkipped asserts that an extension
// with a nil Shutdown hook is skipped without panicking, and that hooks for
// other extensions still run.
func TestGRPCExtensionShutdownHookNilSkipped(t *testing.T) {
var called atomic.Bool
exts := []GRPCExtension{
{Shutdown: nil},
{Shutdown: func(context.Context) { called.Store(true) }},
}
runExtensionShutdownHooks(context.Background(), exts)
if !called.Load() {
t.Error("shutdown hook for non-nil extension was not called")
}
}
func TestRegisterGRPCExtensionAccumulates(t *testing.T) {
s := &BaseServer{}
s.RegisterGRPCExtension(GRPCExtension{})
s.RegisterGRPCExtension(GRPCExtension{})
if len(s.grpcExtensions) != 2 {
t.Fatalf("grpcExtensions len = %d, want 2", len(s.grpcExtensions))
}
}
management/internals/server/server.go
+6
View File
@@ -68,6 +68,11 @@ type BaseServer struct {
proxyAuthClose func()
// grpcExtensions holds additional gRPC services, interceptors, and shutdown
// hooks registered by external modules via RegisterGRPCExtension. Populated
// during boot (single-threaded), consumed by GRPCServer() and Stop().
grpcExtensions []GRPCExtension
listener net.Listener
certManager *autocert.Manager
update *version.Update
@@ -257,6 +262,7 @@ func (s *BaseServer) Stop() error {
s.proxyAuthClose()
s.proxyAuthClose = nil
}
runExtensionShutdownHooks(ctx, s.grpcExtensions)
_ = s.Store().Close(ctx)
_ = s.EventStore().Close(ctx)
if s.update != nil {
management/internals/shared/grpc/components_encoder.go
+2
View File
@@ -60,6 +60,8 @@ func EncodeNetworkMapEnvelope(in ComponentsEnvelopeInput) *proto.NetworkMapEnvel
return &proto.NetworkMapEnvelope{
Payload: &proto.NetworkMapEnvelope_Full{
Full: &proto.NetworkMapComponentsFull{
Serial: networkSerial(c.Network),
Network: toAccountNetwork(c.Network),
PeerConfig: in.PeerConfig,
// components.Peers always contains the target peer
Peers: []*proto.PeerCompact{toPeerCompact(c.Peers[c.PeerID])},
management/internals/shared/grpc/components_encoder_test.go
+21 -1
View File
@@ -587,8 +587,19 @@ func TestEncodeNetworkMapEnvelope_ResourceOnlyPolicyShippedAndIndexed(t *testing
require.Len(t, full.Policies, 2, "encoded policies must include both peer-traffic and resource-only")
policyByID := map[string]*proto.PolicyCompact{}
policyIds := make([]string, 0)
for _, p := range full.Policies {
policyByID[p.Id] = p
policyIds = append(policyIds, p.Id)
}
require.Contains(t, policyByID, "10", "original peer-traffic policy id 10")
require.Contains(t, policyByID, "99", "resource-only policy id 99")
require.Contains(t, full.ResourcePoliciesMap, "77")
ids := full.ResourcePoliciesMap["77"].Ids
require.Len(t, ids, 2)
assert.ElementsMatch(t, policyIds, ids,
"resource policies map must reference both wire policy indexes")
}
func TestEncodeNetworkMapEnvelope_NameServerGroups(t *testing.T) {
@@ -772,6 +783,9 @@ func TestEncodeNetworkMapEnvelope_NilComponentsGracefulDegrade(t *testing.T) {
assert.Equal(t, "netbird.cloud", full.DnsDomain)
assert.Len(t, full.Peers, 1)
assert.Empty(t, full.Policies)
require.NotNil(t, full.Network, "client runs Calculate() over the envelope and dereferences Network unconditionally; a nil here would crash the receiver")
assert.Equal(t, "net-empty", full.Network.Identifier)
assert.Equal(t, uint64(9), full.Serial)
}
func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
@@ -790,6 +804,12 @@ func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
func emptyNetworkMapComponents() *types.NetworkMapComponents {
return types.EmptyNetworkMapComponents(
&types.NetworkMapComponents{
PeerID: "peer-id", Peers: map[string]*nmdata.Peer{"peer-id": {}}},
PeerID: "peer-id", Peers: map[string]*nmdata.Peer{"peer-id": {}},
Network: &nmdata.Network{
Identifier: "net-empty",
Net: net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)},
Serial: 9,
},
},
)
}
management/internals/shared/grpc/conversion_test.go
+34
View File
@@ -2,6 +2,7 @@ package grpc
import (
"fmt"
"net"
"net/netip"
"reflect"
"testing"
@@ -14,6 +15,7 @@ import (
"github.com/netbirdio/netbird/management/internals/controllers/network_map"
"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller/cache"
nbconfig "github.com/netbirdio/netbird/management/internals/server/config"
nbpeer "github.com/netbirdio/netbird/management/server/peer"
"github.com/netbirdio/netbird/management/server/types"
"github.com/netbirdio/netbird/shared/management/networkmap"
)
@@ -301,3 +303,35 @@ func TestToNetbirdConfig_RelayInvariant(t *testing.T) {
assert.True(t, nbCfg.Metrics.Enabled, "metrics flag should carry the settings value")
})
}
func TestToPeerConfig_RoutingPeerDNSResolution(t *testing.T) {
network := &types.Network{Net: net.IPNet{IP: net.IPv4(100, 0, 0, 0), Mask: net.CIDRMask(8, 32)}}
newPeer := func(embedded bool) *nbpeer.Peer {
p := &nbpeer.Peer{IP: netip.MustParseAddr("100.0.0.1")}
p.ProxyMeta.Embedded = embedded
return p
}
tests := []struct {
name string
globalFlag bool
embedded bool
forceParam bool
wantEnabled bool
}{
{name: "global off, regular peer, no force", wantEnabled: false},
{name: "global on wins", globalFlag: true, wantEnabled: true},
{name: "embedded proxy peer forced", embedded: true, wantEnabled: true},
{name: "routing peer forced via param", forceParam: true, wantEnabled: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
settings := &types.Settings{RoutingPeerDNSResolutionEnabled: tt.globalFlag}
cfg := toPeerConfig(types.TwinPeer(newPeer(tt.embedded)), types.TwinNetwork(network), "netbird.selfhosted", types.TwinAccountSettings(settings), nil, nil, false, tt.forceParam)
assert.Equal(t, tt.wantEnabled, cfg.RoutingPeerDnsResolutionEnabled,
"RoutingPeerDnsResolutionEnabled should reflect global || embedded || forced")
})
}
}
management/internals/shared/grpc/proxy.go
+2 -1
View File
@@ -29,6 +29,7 @@ import (
"github.com/netbirdio/netbird/shared/management/domain"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
"github.com/netbirdio/netbird/management/internals/modules/peers"
"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
@@ -36,7 +37,6 @@ import (
"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/sessionkey"
"github.com/netbirdio/netbird/management/server/idp"
"github.com/netbirdio/netbird/management/server/peer"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
"github.com/netbirdio/netbird/management/server/types"
"github.com/netbirdio/netbird/management/server/users"
proxyauth "github.com/netbirdio/netbird/proxy/auth"
@@ -285,6 +285,7 @@ func (s *ProxyServiceServer) CheckLLMPolicyLimits(ctx context.Context, req *prot
UserID: req.GetUserId(),
GroupIDs: req.GetGroupIds(),
ProviderID: req.GetProviderId(),
Model: req.GetModel(),
})
if err != nil {
log.WithContext(ctx).Errorf("select policy for request: %v", err)
management/internals/shared/grpc/proxy_llm_policy_limits_test.go
+138
View File
@@ -0,0 +1,138 @@
package grpc
import (
"context"
"errors"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"google.golang.org/grpc/codes"
grpcstatus "google.golang.org/grpc/status"
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
"github.com/netbirdio/netbird/shared/management/proto"
)
// fakeAgentNetworkLimits records the PolicySelectionInput it was invoked with
// and returns a pre-programmed result, so tests can assert what the handler
// forwards to the selector.
type fakeAgentNetworkLimits struct {
gotInput agentnetwork.PolicySelectionInput
result *agentnetwork.PolicySelectionResult
err error
}
func (f *fakeAgentNetworkLimits) SelectPolicyForRequest(_ context.Context, in agentnetwork.PolicySelectionInput) (*agentnetwork.PolicySelectionResult, error) {
f.gotInput = in
if f.err != nil {
return nil, f.err
}
return f.result, nil
}
func (f *fakeAgentNetworkLimits) RecordUsage(_ context.Context, _ agentnetwork.RecordUsageInput) error {
return nil
}
// TestCheckLLMPolicyLimits_ForwardsModelToSelector proves the wiring added here:
// the model the proxy extracted must reach the selector's Model unchanged,
// alongside the account/user/group/provider fields.
func TestCheckLLMPolicyLimits_ForwardsModelToSelector(t *testing.T) {
fake := &fakeAgentNetworkLimits{result: &agentnetwork.PolicySelectionResult{Allow: true, SelectedPolicyID: "pol-1"}}
s := &ProxyServiceServer{}
s.SetAgentNetworkLimitsService(fake)
req := &proto.CheckLLMPolicyLimitsRequest{
AccountId: "acc-1",
UserId: "user-1",
GroupIds: []string{"grp-a", "grp-b"},
ProviderId: "prov-1",
Model: "claude-opus-4",
}
resp, err := s.CheckLLMPolicyLimits(context.Background(), req)
require.NoError(t, err)
require.NotNil(t, resp)
assert.Equal(t, "acc-1", fake.gotInput.AccountID)
assert.Equal(t, "user-1", fake.gotInput.UserID)
assert.Equal(t, []string{"grp-a", "grp-b"}, fake.gotInput.GroupIDs)
assert.Equal(t, "prov-1", fake.gotInput.ProviderID)
assert.Equal(t, "claude-opus-4", fake.gotInput.Model,
"the request's model must be forwarded to the selector")
}
// TestCheckLLMPolicyLimits_EmptyModelForwardedAsEmpty proves an undetermined
// model (empty string) is forwarded as-is; the selector decides how to treat it.
func TestCheckLLMPolicyLimits_EmptyModelForwardedAsEmpty(t *testing.T) {
fake := &fakeAgentNetworkLimits{result: &agentnetwork.PolicySelectionResult{Allow: true}}
s := &ProxyServiceServer{}
s.SetAgentNetworkLimitsService(fake)
req := &proto.CheckLLMPolicyLimitsRequest{
AccountId: "acc-1",
ProviderId: "prov-1",
}
_, err := s.CheckLLMPolicyLimits(context.Background(), req)
require.NoError(t, err)
assert.Equal(t, "", fake.gotInput.Model, "an absent model must be forwarded as empty, not fabricated")
}
// TestCheckLLMPolicyLimits_DenyResponseCarriesModelBlockedCode proves the deny
// envelope surfaces the model-allowlist deny code + reason through the response.
func TestCheckLLMPolicyLimits_DenyResponseCarriesModelBlockedCode(t *testing.T) {
fake := &fakeAgentNetworkLimits{result: &agentnetwork.PolicySelectionResult{
Allow: false,
DenyCode: "llm_policy.model_blocked",
DenyReason: `model "claude-opus-4" is not permitted by any applicable policy allowlist`,
}}
s := &ProxyServiceServer{}
s.SetAgentNetworkLimitsService(fake)
resp, err := s.CheckLLMPolicyLimits(context.Background(), &proto.CheckLLMPolicyLimitsRequest{
AccountId: "acc-1",
ProviderId: "prov-1",
Model: "claude-opus-4",
})
require.NoError(t, err)
require.NotNil(t, resp)
assert.Equal(t, "deny", resp.Decision)
assert.Equal(t, "llm_policy.model_blocked", resp.DenyCode)
assert.NotEmpty(t, resp.DenyReason)
assert.Empty(t, resp.SelectedPolicyId, "a denied request must carry no selected policy")
}
// TestCheckLLMPolicyLimits_SelectorErrorSurfacesAsInternal proves a selector
// failure surfaces as an Internal gRPC error rather than a silent allow.
func TestCheckLLMPolicyLimits_SelectorErrorSurfacesAsInternal(t *testing.T) {
fake := &fakeAgentNetworkLimits{err: errors.New("boom")}
s := &ProxyServiceServer{}
s.SetAgentNetworkLimitsService(fake)
_, err := s.CheckLLMPolicyLimits(context.Background(), &proto.CheckLLMPolicyLimitsRequest{
AccountId: "acc-1",
ProviderId: "prov-1",
Model: "gpt-4o",
})
require.Error(t, err)
st, ok := grpcstatus.FromError(err)
require.True(t, ok)
assert.Equal(t, codes.Internal, st.Code(), "selector errors must never fail open on the hot path")
}
// TestCheckLLMPolicyLimits_UnconfiguredServiceReturnsUnimplemented locks the
// fallback: with no limits service wired the RPC returns Unimplemented.
func TestCheckLLMPolicyLimits_UnconfiguredServiceReturnsUnimplemented(t *testing.T) {
s := &ProxyServiceServer{}
_, err := s.CheckLLMPolicyLimits(context.Background(), &proto.CheckLLMPolicyLimitsRequest{
AccountId: "acc-1",
ProviderId: "prov-1",
})
require.Error(t, err)
st, ok := grpcstatus.FromError(err)
require.True(t, ok)
assert.Equal(t, codes.Unimplemented, st.Code())
}
management/server/agentnetwork_budgetrule_realstack_test.go
+12 -3
View File
@@ -102,11 +102,20 @@ func TestAgentNetwork_UpdateSettings_PreservesImmutableAndTogglesCollection(t *t
require.NotEmpty(t, before.Subdomain, "subdomain pinned at bootstrap")
assert.False(t, before.EnablePromptCollection, "prompt collection defaults off")
// Attempt to flip toggles AND smuggle a different cluster/subdomain — the
// immutable fields must be ignored.
// A cluster different from the one pinned at bootstrap must be rejected
// outright — never silently swapped or ignored.
_, err = mgr.UpdateSettings(ctx, adminUserID, &agenttypes.Settings{
AccountID: accountID,
Cluster: "attacker.cluster",
EnableLogCollection: true,
})
require.Error(t, err, "UpdateSettings with a mismatched cluster must fail")
// Flipping the toggles works with the pinned cluster echoed back (and
// with it omitted); the subdomain is never taken from the request.
updated, err := mgr.UpdateSettings(ctx, adminUserID, &agenttypes.Settings{
AccountID: accountID,
Cluster: "attacker.cluster",
Cluster: clusterAddr,
Subdomain: "evil",
EnableLogCollection: true,
EnablePromptCollection: true,
management/server/group.go
+50
View File
@@ -6,6 +6,8 @@ import (
"fmt"
"slices"
agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
"github.com/rs/xid"
log "github.com/sirupsen/logrus"
@@ -744,6 +746,14 @@ func validateDeleteGroup(ctx context.Context, transaction store.Store, group *ty
return &GroupLinkError{"network router", linkedRouter.ID}
}
if isLinked, linkedService := isGroupLinkedToReverseProxyService(ctx, transaction, group.AccountID, group.ID); isLinked {
return &GroupLinkError{"reverse proxy service", linkedService.Domain}
}
if isLinked, linkedPolicy := isGroupLinkedToAgentNetworkPolicy(ctx, transaction, group.AccountID, group.ID); isLinked {
return &GroupLinkError{"agent network policy", linkedPolicy.Name}
}
return checkGroupLinkedToSettings(ctx, transaction, group)
}
@@ -875,6 +885,46 @@ func isGroupLinkedToNetworkRouter(ctx context.Context, transaction store.Store,
return false, nil
}
// isGroupLinkedToReverseProxyService checks if a group is used as an access group
// of a private reverse proxy service or as a bearer-auth distribution group.
func isGroupLinkedToReverseProxyService(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *service.Service) {
services, err := transaction.GetAccountServices(ctx, store.LockingStrengthNone, accountID)
if err != nil {
log.WithContext(ctx).Errorf("error retrieving reverse proxy services while checking group linkage: %v", err)
return false, nil
}
for _, svc := range services {
if svc.Private && slices.Contains(svc.AccessGroups, groupID) {
return true, svc
}
if svc.Auth.BearerAuth != nil && svc.Auth.BearerAuth.Enabled && slices.Contains(svc.Auth.BearerAuth.DistributionGroups, groupID) {
return true, svc
}
}
return false, nil
}
// isGroupLinkedToAgentNetworkPolicy checks if a group is used as a source group by any
// agent network policy in the account.
func isGroupLinkedToAgentNetworkPolicy(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *agentNetworkTypes.Policy) {
policies, err := transaction.GetAccountAgentNetworkPolicies(ctx, store.LockingStrengthNone, accountID)
if err != nil {
log.WithContext(ctx).Errorf("error retrieving agent network policies while checking group linkage: %v", err)
return false, nil
}
for _, policy := range policies {
if policy == nil {
continue
}
if slices.Contains(policy.SourceGroups, groupID) {
return true, policy
}
}
return false, nil
}
// areGroupChangesAffectPeers checks if any changes to the specified groups will affect peers.
// It fetches each collection once and checks all groupIDs against them in memory.
func areGroupChangesAffectPeers(ctx context.Context, transaction store.Store, accountID string, groupIDs []string) (bool, error) {
management/server/group_test.go
+171
View File
@@ -18,6 +18,8 @@ import (
"golang.org/x/exp/maps"
nbdns "github.com/netbirdio/netbird/dns"
agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
"github.com/netbirdio/netbird/management/server/groups"
"github.com/netbirdio/netbird/management/server/networks"
"github.com/netbirdio/netbird/management/server/networks/resources"
@@ -125,6 +127,21 @@ func TestDefaultAccountManager_DeleteGroup(t *testing.T) {
"grp-for-integration",
"only service users with admin power can delete integration group",
},
{
"agent network policy",
"grp-for-agent-network-policy",
"agent network policy",
},
{
"reverse proxy private service access group",
"grp-for-rp-private",
"reverse proxy service",
},
{
"reverse proxy bearer distribution group",
"grp-for-rp-bearer",
"reverse proxy service",
},
}
for _, testCase := range testCases {
@@ -218,6 +235,17 @@ func TestDefaultAccountManager_DeleteGroups(t *testing.T) {
groupIDs: []string{"grp-for-integration"},
expectedReasons: []string{"only service users with admin power can delete integration group"},
},
{
name: "agent network policy",
groupIDs: []string{"grp-for-agent-network-policy"},
expectedReasons: []string{"agent network policy"},
},
{
name: "reverse proxy services",
groupIDs: []string{"grp-for-rp-private", "grp-for-rp-bearer"},
expectedReasons: []string{"reverse proxy service", "reverse proxy service"},
expectedNotDeleted: []string{"grp-for-rp-private", "grp-for-rp-bearer"},
},
{
name: "successfully delete multiple groups",
groupIDs: []string{"group-1", "group-2"},
@@ -285,6 +313,65 @@ func TestDefaultAccountManager_DeleteGroups(t *testing.T) {
}
}
func TestDefaultAccountManager_DeleteGroupUnlinkedFromReverseProxyService(t *testing.T) {
am, _, err := createManager(t)
require.NoError(t, err, "Failed to create account manager")
_, account, err := initTestGroupAccount(am)
require.NoError(t, err, "Failed to init testing account")
deletableGroups := []*types.Group{
{
ID: "grp-rp-bearer-disabled",
AccountID: account.Id,
Name: "Group only in a disabled bearer auth",
Issued: types.GroupIssuedAPI,
Peers: make([]string, 0),
},
{
ID: "grp-rp-nonprivate-access",
AccountID: account.Id,
Name: "Group only in a non-private service's access groups",
Issued: types.GroupIssuedAPI,
Peers: make([]string, 0),
},
}
for _, group := range deletableGroups {
require.NoError(t, am.CreateGroup(context.Background(), account.Id, groupAdminUserID, group))
}
// Disabled bearer auth and stale access groups on a non-private service
// are inert configuration and must not block group deletion.
services := []*rpservice.Service{
{
ID: "rp-svc-bearer-disabled",
AccountID: account.Id,
Domain: "bearer-disabled.services.example.com",
Auth: rpservice.AuthConfig{
BearerAuth: &rpservice.BearerAuthConfig{
Enabled: false,
DistributionGroups: []string{"grp-rp-bearer-disabled"},
},
},
},
{
ID: "rp-svc-nonprivate-access",
AccountID: account.Id,
Domain: "nonprivate.services.example.com",
Private: false,
AccessGroups: []string{"grp-rp-nonprivate-access"},
},
}
for _, svc := range services {
require.NoError(t, am.Store.CreateService(context.Background(), svc))
}
for _, group := range deletableGroups {
err = am.DeleteGroup(context.Background(), account.Id, groupAdminUserID, group.ID)
assert.NoError(t, err, "group %s is not referenced by an active reverse proxy gate and should be deletable", group.ID)
}
}
func TestDefaultAccountManager_DeleteGroupLinkedToFlowGroup(t *testing.T) {
am, _, err := createManager(t)
require.NoError(t, err)
@@ -406,6 +493,30 @@ func initTestGroupAccount(am *DefaultAccountManager) (*DefaultAccountManager, *t
Peers: make([]string, 0),
}
groupForAgentNetworkPolicy := &types.Group{
ID: "grp-for-agent-network-policy",
AccountID: "account-id",
Name: "Group for agent network policies",
Issued: types.GroupIssuedAPI,
Peers: make([]string, 0),
}
groupForRPPrivate := &types.Group{
ID: "grp-for-rp-private",
AccountID: "account-id",
Name: "Group for private reverse proxy service",
Issued: types.GroupIssuedAPI,
Peers: make([]string, 0),
}
groupForRPBearer := &types.Group{
ID: "grp-for-rp-bearer",
AccountID: "account-id",
Name: "Group for bearer reverse proxy service",
Issued: types.GroupIssuedAPI,
Peers: make([]string, 0),
}
routeResource := &route.Route{
ID: "example route",
Groups: []string{groupForRoute.ID},
@@ -461,6 +572,66 @@ func initTestGroupAccount(am *DefaultAccountManager) (*DefaultAccountManager, *t
_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForSetupKeys)
_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForUsers)
_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForIntegration)
_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForAgentNetworkPolicy)
_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForRPPrivate)
_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForRPBearer)
agentNetworkPolicy := &agentNetworkTypes.Policy{
ID: "example agent network policy",
AccountID: accountID,
Name: "Example agent network policy",
Enabled: true,
SourceGroups: []string{groupForAgentNetworkPolicy.ID},
}
if err := am.Store.SaveAgentNetworkPolicy(context.Background(), agentNetworkPolicy); err != nil {
return nil, nil, err
}
// The decoy services are created first so the linkage check has to scan
// past services that do not reference the groups under test.
rpServices := []*rpservice.Service{
{
ID: "rp-svc-private-decoy",
AccountID: accountID,
Domain: "private-decoy.services.example.com",
Private: true,
AccessGroups: []string{"unrelated-group"},
},
{
ID: "rp-svc-bearer-decoy",
AccountID: accountID,
Domain: "bearer-decoy.services.example.com",
Auth: rpservice.AuthConfig{
BearerAuth: &rpservice.BearerAuthConfig{
Enabled: true,
DistributionGroups: []string{"unrelated-group"},
},
},
},
{
ID: "rp-svc-private",
AccountID: accountID,
Domain: "private.services.example.com",
Private: true,
AccessGroups: []string{groupForRPPrivate.ID},
},
{
ID: "rp-svc-bearer",
AccountID: accountID,
Domain: "bearer.services.example.com",
Auth: rpservice.AuthConfig{
BearerAuth: &rpservice.BearerAuthConfig{
Enabled: true,
DistributionGroups: []string{groupForRPBearer.ID},
},
},
},
}
for _, svc := range rpServices {
if err := am.Store.CreateService(context.Background(), svc); err != nil {
return nil, nil, err
}
}
acc, err := am.Store.GetAccount(context.Background(), account.Id)
if err != nil {
management/server/migration/migration.go
+78
View File
@@ -683,3 +683,81 @@ func BackfillPublicIDs[T any](ctx context.Context, db *gorm.DB) error {
log.WithContext(ctx).Infof("Backfill of empty public_id in table %s completed", tableName)
return nil
}
// FoldCostAggregatesIntoBuckets migrates a per-request cost table from the old
// "stored aggregate" shape (cost_usd + cache_cost_usd columns) to the per-bucket
// breakdown, where the total and cache portion are derived on read instead.
//
// The fold preserves both aggregates exactly for historical rows: the cache
// total moves into cached_input_cost_usd and the remainder into
// input_cost_usd, so a row's derived total and cache cost still match what it
// reported before the upgrade. The finer split is genuinely unknown for those
// rows — the old schema never recorded a read/write or input/output division —
// so it is lumped rather than guessed; only rows written after the upgrade
// carry a true four-way split.
//
// Dropping the columns before folding would zero every historical row's cost,
// so the update runs first and the drop only happens once it succeeds. A table
// with no cost_usd column has already been migrated (or was created fresh) and
// is skipped.
func FoldCostAggregatesIntoBuckets[T any](ctx context.Context, db *gorm.DB) error {
var model T
if !db.Migrator().HasTable(&model) {
log.WithContext(ctx).Debugf("table for %T does not exist, no cost-bucket migration needed", model)
return nil
}
if !db.Migrator().HasColumn(&model, "cost_usd") {
log.WithContext(ctx).Debugf("table for %T has no cost_usd column, cost buckets already migrated", model)
return nil
}
stmt := &gorm.Statement{DB: db}
if err := stmt.Parse(&model); err != nil {
return fmt.Errorf("parse model schema: %w", err)
}
tableName := stmt.Schema.Table
// COALESCE guards rows whose new columns were added as NULL by an earlier
// AutoMigrate run that predates the NOT NULL default.
hasCacheColumn := db.Migrator().HasColumn(&model, "cache_cost_usd")
cacheExpr := "0"
if hasCacheColumn {
cacheExpr = "COALESCE(cache_cost_usd, 0)"
}
if err := db.Transaction(func(tx *gorm.DB) error {
// Only touch rows that carry a legacy total and no breakdown yet, so
// the migration is idempotent and never overwrites a true split.
update := fmt.Sprintf(`UPDATE %s
SET input_cost_usd = COALESCE(cost_usd, 0) - %s,
cached_input_cost_usd = %s,
cache_creation_cost_usd = 0,
output_cost_usd = 0
WHERE COALESCE(cost_usd, 0) <> 0
AND COALESCE(input_cost_usd, 0) = 0
AND COALESCE(cached_input_cost_usd, 0) = 0
AND COALESCE(cache_creation_cost_usd, 0) = 0
AND COALESCE(output_cost_usd, 0) = 0`, tableName, cacheExpr, cacheExpr)
res := tx.Exec(update)
if res.Error != nil {
return fmt.Errorf("fold legacy cost aggregates in %s: %w", tableName, res.Error)
}
log.WithContext(ctx).Infof("folded legacy cost aggregates into per-bucket columns for %d rows in table %s", res.RowsAffected, tableName)
if err := tx.Migrator().DropColumn(&model, "cost_usd"); err != nil {
return fmt.Errorf("drop cost_usd from %s: %w", tableName, err)
}
if hasCacheColumn {
if err := tx.Migrator().DropColumn(&model, "cache_cost_usd"); err != nil {
return fmt.Errorf("drop cache_cost_usd from %s: %w", tableName, err)
}
}
return nil
}); err != nil {
return err
}
log.WithContext(ctx).Infof("migration of stored cost aggregates to per-bucket columns in table %s completed", tableName)
return nil
}
management/server/migration/migration_test.go
+97
View File
@@ -16,6 +16,7 @@ import (
"gorm.io/driver/sqlite"
"gorm.io/gorm"
agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
"github.com/netbirdio/netbird/management/server/migration"
nbpeer "github.com/netbirdio/netbird/management/server/peer"
"github.com/netbirdio/netbird/management/server/testutil"
@@ -639,3 +640,99 @@ func TestCleanupOrphanedResources_SkipsWhenForeignKeyExists(t *testing.T) {
db.Model(&testChildWithFK{}).Count(&count)
assert.Equal(t, int64(2), count, "Both rows should survive — migration must skip when FK constraint exists")
}
// legacyCostRow is the pre-breakdown shape of the usage table: cost was stored
// as a total plus a cache portion, with no per-bucket columns. Used to build a
// realistic pre-upgrade table for the fold migration to run against.
type legacyCostRow struct {
ID string `gorm:"primaryKey"`
AccountID string
Model string
CostUSD float64
CacheCostUSD float64
}
func (legacyCostRow) TableName() string { return "agent_network_request_usage" }
// TestFoldCostAggregatesIntoBuckets_PreservesHistoricalCost covers the upgrade
// path: a table written under the old schema must come out with its per-row
// total and cache cost unchanged, because dropping cost_usd without folding it
// forward would silently zero every historical row's spend.
func TestFoldCostAggregatesIntoBuckets_PreservesHistoricalCost(t *testing.T) {
ctx := context.Background()
db := setupDatabase(t)
// setupDatabase hands back a process-shared database, so start from a clean
// table rather than inheriting rows from another test.
require.NoError(t, db.Migrator().DropTable(&agentNetworkTypes.AgentNetworkUsage{}))
require.NoError(t, db.AutoMigrate(&legacyCostRow{}), "legacy table must be created")
require.NoError(t, db.Create(&legacyCostRow{
ID: "u1", AccountID: "acct-1", Model: "claude-sonnet-4-6", CostUSD: 0.0123, CacheCostUSD: 0.0029,
}).Error)
require.NoError(t, db.Create(&legacyCostRow{
ID: "u2", AccountID: "acct-1", Model: "gpt-4o", CostUSD: 0.5, CacheCostUSD: 0,
}).Error)
// A zero-cost row (denied / unpriced request) must stay zero, not be touched.
require.NoError(t, db.Create(&legacyCostRow{ID: "u3", AccountID: "acct-1", Model: "gw/unpriced"}).Error)
// AutoMigrate adds the per-bucket columns alongside the legacy ones, exactly
// as a real upgrade does before the post-auto migrations run.
require.NoError(t, db.AutoMigrate(&agentNetworkTypes.AgentNetworkUsage{}), "new columns must be added")
require.NoError(t, migration.FoldCostAggregatesIntoBuckets[agentNetworkTypes.AgentNetworkUsage](ctx, db))
assert.False(t, db.Migrator().HasColumn(&agentNetworkTypes.AgentNetworkUsage{}, "cost_usd"),
"legacy cost_usd column must be dropped once folded")
assert.False(t, db.Migrator().HasColumn(&agentNetworkTypes.AgentNetworkUsage{}, "cache_cost_usd"),
"legacy cache_cost_usd column must be dropped once folded")
var rows []*agentNetworkTypes.AgentNetworkUsage
require.NoError(t, db.Order("id").Find(&rows).Error)
require.Len(t, rows, 3)
// u1: total and cache portion both preserved; the read/write and
// input/output splits are unknowable for a legacy row, so the cache total
// lands on cached_input and the remainder on input.
assert.InDelta(t, 0.0123, rows[0].TotalCostUSD(), 1e-9, "historical total must survive the fold")
assert.InDelta(t, 0.0029, rows[0].CacheCostUSD(), 1e-9, "historical cache cost must survive the fold")
assert.InDelta(t, 0.0094, rows[0].InputCostUSD, 1e-9, "non-cache remainder lands on input")
assert.InDelta(t, 0.0029, rows[0].CachedInputCostUSD, 1e-9, "legacy cache total lands on cached input")
assert.Zero(t, rows[0].CacheCreationCostUSD, "legacy rows carry no read/write split to recover")
assert.Zero(t, rows[0].OutputCostUSD, "legacy rows carry no input/output split to recover")
// u2: no cache spend — the whole total is the non-cache remainder.
assert.InDelta(t, 0.5, rows[1].TotalCostUSD(), 1e-9, "cache-free historical total must survive")
assert.Zero(t, rows[1].CacheCostUSD(), "a cache-free row must stay cache-free")
// u3: zero stays zero rather than being rewritten.
assert.Zero(t, rows[2].TotalCostUSD(), "an unpriced row must remain unpriced")
}
// TestFoldCostAggregatesIntoBuckets_SkipsAlreadyMigrated proves the migration is
// safe to re-run: with no legacy column present it is a no-op that leaves a
// true four-way split untouched.
func TestFoldCostAggregatesIntoBuckets_SkipsAlreadyMigrated(t *testing.T) {
ctx := context.Background()
db := setupDatabase(t)
require.NoError(t, db.Migrator().DropTable(&agentNetworkTypes.AgentNetworkUsage{}))
require.NoError(t, db.AutoMigrate(&agentNetworkTypes.AgentNetworkUsage{}))
// Timestamp must be set explicitly: a zero time.Time serialises as
// '0000-00-00 00:00:00', which MySQL rejects under strict mode.
require.NoError(t, db.Create(&agentNetworkTypes.AgentNetworkUsage{
ID: "u1", AccountID: "acct-1", Model: "claude-sonnet-4-6",
Timestamp: time.Date(2026, 5, 5, 9, 0, 0, 0, time.UTC),
InputCostUSD: 0.001, CachedInputCostUSD: 0.002, CacheCreationCostUSD: 0.003, OutputCostUSD: 0.004,
}).Error)
require.NoError(t, migration.FoldCostAggregatesIntoBuckets[agentNetworkTypes.AgentNetworkUsage](ctx, db),
"running against an already-migrated table must be a no-op, not an error")
var row agentNetworkTypes.AgentNetworkUsage
require.NoError(t, db.First(&row, "id = ?", "u1").Error)
assert.InDelta(t, 0.001, row.InputCostUSD, 1e-9, "a true split must not be rewritten")
assert.InDelta(t, 0.002, row.CachedInputCostUSD, 1e-9)
assert.InDelta(t, 0.003, row.CacheCreationCostUSD, 1e-9)
assert.InDelta(t, 0.004, row.OutputCostUSD, 1e-9)
assert.InDelta(t, 0.01, row.TotalCostUSD(), 1e-9, "derived total sums the four buckets")
}
management/server/permissions/manager.go
+20 -2
View File
@@ -82,6 +82,9 @@ func (m *managerImpl) ValidateUserPermissions(
return m.ValidateRoleModuleAccess(ctx, accountID, role, module, operation), ctxEnriched, nil
}
// ValidateRoleModuleAccess resolves an operation against the role's explicit
// grant for the module, then the grant for its parent module when the module
// is a dotted submodule, and finally the role's AutoAllowNew default.
func (m *managerImpl) ValidateRoleModuleAccess(
ctx context.Context,
accountID string,
@@ -89,7 +92,7 @@ func (m *managerImpl) ValidateRoleModuleAccess(
module modules.Module,
operation operations.Operation,
) bool {
if permissions, ok := role.Permissions[module]; ok {
if permissions, ok := lookupModulePermissions(role, module); ok {
if allowed, exists := permissions[operation]; exists {
return allowed
}
@@ -100,6 +103,21 @@ func (m *managerImpl) ValidateRoleModuleAccess(
return role.AutoAllowNew[operation]
}
// lookupModulePermissions returns the role's explicit permission set for the
// module, falling back to the parent module's set for dotted submodules. The
// second return reports whether any explicit set was found.
func lookupModulePermissions(role roles.RolePermissions, module modules.Module) (map[operations.Operation]bool, bool) {
if permissions, ok := role.Permissions[module]; ok {
return permissions, true
}
if parent, hasParent := module.Parent(); hasParent {
if permissions, ok := role.Permissions[parent]; ok {
return permissions, true
}
}
return nil, false
}
func (m *managerImpl) ValidateAccountAccess(ctx context.Context, accountID string, user *types.User, allowOwnerAndAdmin bool) (context.Context, error) {
if user.AccountID != accountID {
return ctx, status.NewUserNotPartOfAccountError()
@@ -119,7 +137,7 @@ func (m *managerImpl) GetPermissionsByRole(ctx context.Context, role types.UserR
permissions := roles.Permissions{}
for k := range modules.All {
if rolePermissions, ok := roleMap.Permissions[k]; ok {
if rolePermissions, ok := lookupModulePermissions(roleMap, k); ok {
permissions[k] = rolePermissions
continue
}
management/server/permissions/manager_test.go
+139
View File
@@ -0,0 +1,139 @@
package permissions
import (
"context"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/netbirdio/netbird/management/server/permissions/modules"
"github.com/netbirdio/netbird/management/server/permissions/operations"
"github.com/netbirdio/netbird/management/server/permissions/roles"
"github.com/netbirdio/netbird/management/server/types"
)
func TestValidateRoleModuleAccessSubmoduleCascade(t *testing.T) {
manager := NewManager(nil)
ctx := context.Background()
fullAccess := map[operations.Operation]bool{
operations.Read: true,
operations.Create: true,
operations.Update: true,
operations.Delete: true,
}
readOnly := map[operations.Operation]bool{
operations.Read: true,
operations.Create: false,
operations.Update: false,
operations.Delete: false,
}
denyAll := map[operations.Operation]bool{
operations.Read: false,
operations.Create: false,
operations.Update: false,
operations.Delete: false,
}
t.Run("parent grant covers submodules", func(t *testing.T) {
role := roles.RolePermissions{
AutoAllowNew: denyAll,
Permissions: roles.Permissions{modules.AgentNetwork: fullAccess},
}
assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Create),
"parent full grant should allow create on a submodule")
assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkLogs, operations.Read),
"parent full grant should allow read on a submodule")
})
t.Run("submodule grant does not leak to parent or siblings", func(t *testing.T) {
role := roles.RolePermissions{
AutoAllowNew: denyAll,
Permissions: roles.Permissions{modules.AgentNetworkUsage: readOnly},
}
assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Read),
"explicit submodule read should be allowed")
assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Create),
"read-only submodule grant should not allow create")
assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetwork, operations.Read),
"submodule grant should not grant the parent module")
assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Read),
"submodule grant should not grant a sibling submodule")
})
t.Run("explicit submodule entry wins over parent grant", func(t *testing.T) {
role := roles.RolePermissions{
AutoAllowNew: denyAll,
Permissions: roles.Permissions{
modules.AgentNetwork: fullAccess,
modules.AgentNetworkLogs: denyAll,
},
}
assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkLogs, operations.Read),
"explicit submodule deny should override the parent grant")
assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Read),
"sibling submodules should still resolve through the parent grant")
})
t.Run("auto allow applies when neither submodule nor parent is granted", func(t *testing.T) {
role := roles.RolePermissions{
AutoAllowNew: readOnly,
}
assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Read),
"auto-allow read should apply to submodules")
assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Delete),
"auto-allow should not grant unlisted operations")
})
}
// TestExistingRolesKeepAgentNetworkBehaviorOnSubmodules pins the behavior the
// submodule split must not change: every built-in role resolves the new
// submodules exactly as it resolved the agent_network module before.
func TestExistingRolesKeepAgentNetworkBehaviorOnSubmodules(t *testing.T) {
manager := NewManager(nil)
ctx := context.Background()
submodules := []modules.Module{
modules.AgentNetworkProviders,
modules.AgentNetworkPolicies,
modules.AgentNetworkGuardrails,
modules.AgentNetworkBudgets,
modules.AgentNetworkUsage,
modules.AgentNetworkLogs,
modules.AgentNetworkSettings,
}
allOperations := []operations.Operation{operations.Read, operations.Create, operations.Update, operations.Delete}
for _, role := range []types.UserRole{types.UserRoleOwner, types.UserRoleAdmin, types.UserRoleAuditor, types.UserRoleNetworkAdmin, types.UserRoleUser} {
rolePermissions, ok := roles.RolesMap[role]
require.True(t, ok, "role %s must exist in RolesMap", role)
for _, sub := range submodules {
for _, op := range allOperations {
expected := manager.ValidateRoleModuleAccess(ctx, "account", rolePermissions, modules.AgentNetwork, op)
actual := manager.ValidateRoleModuleAccess(ctx, "account", rolePermissions, sub, op)
assert.Equal(t, expected, actual, "role %s: %s on %s should match the agent_network module", role, op, sub)
}
}
}
}
func TestGetPermissionsByRoleIncludesSubmodules(t *testing.T) {
manager := NewManager(nil)
ctx := context.Background()
permissions, err := manager.GetPermissionsByRole(ctx, types.UserRoleAuditor)
require.NoError(t, err, "auditor role must resolve")
usage, ok := permissions[modules.AgentNetworkUsage]
require.True(t, ok, "permissions map should contain the usage submodule")
assert.True(t, usage[operations.Read], "auditor should read the usage submodule")
assert.False(t, usage[operations.Update], "auditor should not update the usage submodule")
adminPermissions, err := manager.GetPermissionsByRole(ctx, types.UserRoleAdmin)
require.NoError(t, err, "admin role must resolve")
providers, ok := adminPermissions[modules.AgentNetworkProviders]
require.True(t, ok, "permissions map should contain the providers submodule")
assert.True(t, providers[operations.Delete], "admin should delete on the providers submodule")
}
management/server/permissions/modules/module.go
+30
View File
@@ -1,5 +1,7 @@
package modules
import "strings"
type Module string
const (
@@ -20,6 +22,17 @@ const (
IdentityProviders Module = "identity_providers"
Services Module = "services"
AgentNetwork Module = "agent_network"
// Agent Network submodules. A role may grant one of these directly
// or grant the AgentNetwork parent, which covers all of them (see
// permissions.Manager cascade resolution).
AgentNetworkProviders Module = "agent_network.providers"
AgentNetworkPolicies Module = "agent_network.policies"
AgentNetworkGuardrails Module = "agent_network.guardrails"
AgentNetworkBudgets Module = "agent_network.budgets"
AgentNetworkUsage Module = "agent_network.usage"
AgentNetworkLogs Module = "agent_network.logs"
AgentNetworkSettings Module = "agent_network.settings"
)
var All = map[Module]struct{}{
@@ -40,4 +53,21 @@ var All = map[Module]struct{}{
IdentityProviders: {},
Services: {},
AgentNetwork: {},
AgentNetworkProviders: {},
AgentNetworkPolicies: {},
AgentNetworkGuardrails: {},
AgentNetworkBudgets: {},
AgentNetworkUsage: {},
AgentNetworkLogs: {},
AgentNetworkSettings: {},
}
// Parent returns the module owning a dotted submodule name and true, or the
// module itself and false when it has no parent.
func (m Module) Parent() (Module, bool) {
if i := strings.IndexByte(string(m), '.'); i > 0 {
return Module(string(m)[:i]), true
}
return m, false
}
management/server/store/sql_store.go
+217 -135
View File
@@ -6,6 +6,7 @@ import (
"encoding/json"
"errors"
"fmt"
"math"
"net"
"net/netip"
"net/url"
@@ -2258,117 +2259,30 @@ func (s *SqlStore) getPostureChecks(ctx context.Context, accountID string) ([]*p
return checks, nil
}
func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpservice.Service, error) {
const serviceQuery = `SELECT id, account_id, name, domain, enabled, auth,
meta_created_at, meta_certificate_issued_at, meta_status, proxy_cluster,
pass_host_header, rewrite_redirects, session_private_key, session_public_key,
mode, listen_port, port_auto_assigned, source, source_peer, terminated,
private, access_groups
FROM services WHERE account_id = $1`
// serviceSelectColumns and targetSelectColumns are the column lists the Postgres
// pgx read path scans. They must stay in sync with the rpservice.Service and
// rpservice.Target gorm models; TestPgxServiceColumnsMatchGorm enforces this.
const serviceSelectColumns = `id, account_id, name, domain, enabled, auth, restrictions,
meta_created_at, meta_certificate_issued_at, meta_last_renewed_at, meta_status, proxy_cluster,
pass_host_header, rewrite_redirects, session_private_key, session_public_key,
mode, listen_port, port_auto_assigned, source, source_peer, terminated,
private, access_groups`
const targetsQuery = `SELECT id, account_id, service_id, path, host, port, protocol,
target_id, target_type, enabled
FROM targets WHERE service_id = ANY($1)`
const targetSelectColumns = `id, account_id, service_id, path, host, port, protocol,
target_id, target_type, enabled, proxy_protocol,
skip_tls_verify, request_timeout, session_idle_timeout, path_rewrite, custom_headers,
direct_upstream, middlewares, capture_max_request_bytes, capture_max_response_bytes,
capture_content_types, agent_network, disable_access_log`
func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpservice.Service, error) {
const serviceQuery = `SELECT ` + serviceSelectColumns + ` FROM services WHERE account_id = $1`
serviceRows, err := s.pool.Query(ctx, serviceQuery, accountID)
if err != nil {
return nil, err
}
services, err := pgx.CollectRows(serviceRows, func(row pgx.CollectableRow) (*rpservice.Service, error) {
var s rpservice.Service
var auth []byte
var accessGroups []byte
var createdAt, certIssuedAt sql.NullTime
var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
var mode, source, sourcePeer sql.NullString
var terminated, portAutoAssigned, private sql.NullBool
var listenPort sql.NullInt64
err := row.Scan(
&s.ID,
&s.AccountID,
&s.Name,
&s.Domain,
&s.Enabled,
&auth,
&createdAt,
&certIssuedAt,
&status,
&proxyCluster,
&s.PassHostHeader,
&s.RewriteRedirects,
&sessionPrivateKey,
&sessionPublicKey,
&mode,
&listenPort,
&portAutoAssigned,
&source,
&sourcePeer,
&terminated,
&private,
&accessGroups,
)
if err != nil {
return nil, err
}
if auth != nil {
if err := json.Unmarshal(auth, &s.Auth); err != nil {
return nil, err
}
}
if len(accessGroups) > 0 {
if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
return nil, fmt.Errorf("unmarshal access_groups: %w", err)
}
}
if private.Valid {
s.Private = private.Bool
}
s.Meta = rpservice.Meta{}
if createdAt.Valid {
s.Meta.CreatedAt = createdAt.Time
}
if certIssuedAt.Valid {
t := certIssuedAt.Time
s.Meta.CertificateIssuedAt = &t
}
if status.Valid {
s.Meta.Status = status.String
}
if proxyCluster.Valid {
s.ProxyCluster = proxyCluster.String
}
if sessionPrivateKey.Valid {
s.SessionPrivateKey = sessionPrivateKey.String
}
if sessionPublicKey.Valid {
s.SessionPublicKey = sessionPublicKey.String
}
if mode.Valid {
s.Mode = mode.String
}
if source.Valid {
s.Source = source.String
}
if sourcePeer.Valid {
s.SourcePeer = sourcePeer.String
}
if terminated.Valid {
s.Terminated = terminated.Bool
}
if portAutoAssigned.Valid {
s.PortAutoAssigned = portAutoAssigned.Bool
}
if listenPort.Valid {
s.ListenPort = uint16(listenPort.Int64)
}
s.Targets = []*rpservice.Target{}
return &s, nil
})
services, err := pgx.CollectRows(serviceRows, scanService)
if err != nil {
return nil, err
}
@@ -2379,39 +2293,12 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
serviceIDs := make([]string, len(services))
serviceMap := make(map[string]*rpservice.Service)
for i, s := range services {
serviceIDs[i] = s.ID
serviceMap[s.ID] = s
for i, svc := range services {
serviceIDs[i] = svc.ID
serviceMap[svc.ID] = svc
}
targetRows, err := s.pool.Query(ctx, targetsQuery, serviceIDs)
if err != nil {
return nil, err
}
targets, err := pgx.CollectRows(targetRows, func(row pgx.CollectableRow) (*rpservice.Target, error) {
var t rpservice.Target
var path sql.NullString
err := row.Scan(
&t.ID,
&t.AccountID,
&t.ServiceID,
&path,
&t.Host,
&t.Port,
&t.Protocol,
&t.TargetId,
&t.TargetType,
&t.Enabled,
)
if err != nil {
return nil, err
}
if path.Valid {
t.Path = &path.String
}
return &t, nil
})
targets, err := s.getServiceTargets(ctx, serviceIDs)
if err != nil {
return nil, err
}
@@ -2425,6 +2312,201 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
return services, nil
}
func scanService(row pgx.CollectableRow) (*rpservice.Service, error) {
var s rpservice.Service
var auth []byte
var restrictions []byte
var accessGroups []byte
var createdAt, certIssuedAt, lastRenewedAt sql.NullTime
var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
var mode, source, sourcePeer sql.NullString
var terminated, portAutoAssigned, private sql.NullBool
var listenPort sql.NullInt64
err := row.Scan(
&s.ID,
&s.AccountID,
&s.Name,
&s.Domain,
&s.Enabled,
&auth,
&restrictions,
&createdAt,
&certIssuedAt,
&lastRenewedAt,
&status,
&proxyCluster,
&s.PassHostHeader,
&s.RewriteRedirects,
&sessionPrivateKey,
&sessionPublicKey,
&mode,
&listenPort,
&portAutoAssigned,
&source,
&sourcePeer,
&terminated,
&private,
&accessGroups,
)
if err != nil {
return nil, err
}
if auth != nil {
if err := json.Unmarshal(auth, &s.Auth); err != nil {
return nil, err
}
}
if len(restrictions) > 0 {
if err := json.Unmarshal(restrictions, &s.Restrictions); err != nil {
return nil, fmt.Errorf("unmarshal restrictions: %w", err)
}
}
if len(accessGroups) > 0 {
if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
return nil, fmt.Errorf("unmarshal access_groups: %w", err)
}
}
if private.Valid {
s.Private = private.Bool
}
s.Meta = serviceMetaFromRow(createdAt, certIssuedAt, lastRenewedAt, status)
if proxyCluster.Valid {
s.ProxyCluster = proxyCluster.String
}
if sessionPrivateKey.Valid {
s.SessionPrivateKey = sessionPrivateKey.String
}
if sessionPublicKey.Valid {
s.SessionPublicKey = sessionPublicKey.String
}
if mode.Valid {
s.Mode = mode.String
}
if source.Valid {
s.Source = source.String
}
if sourcePeer.Valid {
s.SourcePeer = sourcePeer.String
}
if terminated.Valid {
s.Terminated = terminated.Bool
}
if portAutoAssigned.Valid {
s.PortAutoAssigned = portAutoAssigned.Bool
}
if listenPort.Valid {
if listenPort.Int64 < 0 || listenPort.Int64 > math.MaxUint16 {
return nil, fmt.Errorf("listen_port %d out of range", listenPort.Int64)
}
s.ListenPort = uint16(listenPort.Int64)
}
s.Targets = []*rpservice.Target{}
return &s, nil
}
func serviceMetaFromRow(createdAt, certIssuedAt, lastRenewedAt sql.NullTime, status sql.NullString) rpservice.Meta {
meta := rpservice.Meta{}
if createdAt.Valid {
meta.CreatedAt = createdAt.Time
}
if certIssuedAt.Valid {
t := certIssuedAt.Time
meta.CertificateIssuedAt = &t
}
if lastRenewedAt.Valid {
t := lastRenewedAt.Time
meta.LastRenewedAt = &t
}
if status.Valid {
meta.Status = status.String
}
return meta
}
func (s *SqlStore) getServiceTargets(ctx context.Context, serviceIDs []string) ([]*rpservice.Target, error) {
const targetsQuery = `SELECT ` + targetSelectColumns + ` FROM targets WHERE service_id = ANY($1)`
rows, err := s.pool.Query(ctx, targetsQuery, serviceIDs)
if err != nil {
return nil, err
}
return pgx.CollectRows(rows, scanTarget)
}
func scanTarget(row pgx.CollectableRow) (*rpservice.Target, error) {
var t rpservice.Target
var path sql.NullString
var pathRewrite sql.NullString
var proxyProtocol, skipTLSVerify, directUpstream, agentNetwork, disableAccessLog sql.NullBool
var requestTimeout, sessionIdleTimeout, captureMaxRequestBytes, captureMaxResponseBytes sql.NullInt64
var customHeaders, middlewares, captureContentTypes []byte
err := row.Scan(
&t.ID,
&t.AccountID,
&t.ServiceID,
&path,
&t.Host,
&t.Port,
&t.Protocol,
&t.TargetId,
&t.TargetType,
&t.Enabled,
&proxyProtocol,
&skipTLSVerify,
&requestTimeout,
&sessionIdleTimeout,
&pathRewrite,
&customHeaders,
&directUpstream,
&middlewares,
&captureMaxRequestBytes,
&captureMaxResponseBytes,
&captureContentTypes,
&agentNetwork,
&disableAccessLog,
)
if err != nil {
return nil, err
}
if path.Valid {
t.Path = &path.String
}
t.ProxyProtocol = proxyProtocol.Bool
t.Options.SkipTLSVerify = skipTLSVerify.Bool
t.Options.RequestTimeout = time.Duration(requestTimeout.Int64)
t.Options.SessionIdleTimeout = time.Duration(sessionIdleTimeout.Int64)
t.Options.PathRewrite = rpservice.PathRewriteMode(pathRewrite.String)
t.Options.DirectUpstream = directUpstream.Bool
t.Options.CaptureMaxRequestBytes = captureMaxRequestBytes.Int64
t.Options.CaptureMaxResponseBytes = captureMaxResponseBytes.Int64
t.Options.AgentNetwork = agentNetwork.Bool
t.Options.DisableAccessLog = disableAccessLog.Bool
if len(customHeaders) > 0 {
if err := json.Unmarshal(customHeaders, &t.Options.CustomHeaders); err != nil {
return nil, fmt.Errorf("unmarshal custom_headers: %w", err)
}
}
if len(middlewares) > 0 {
if err := json.Unmarshal(middlewares, &t.Options.Middlewares); err != nil {
return nil, fmt.Errorf("unmarshal middlewares: %w", err)
}
}
if len(captureContentTypes) > 0 {
if err := json.Unmarshal(captureContentTypes, &t.Options.CaptureContentTypes); err != nil {
return nil, fmt.Errorf("unmarshal capture_content_types: %w", err)
}
}
return &t, nil
}
func (s *SqlStore) getNetworks(ctx context.Context, accountID string) ([]*networkTypes.Network, error) {
const query = `SELECT id, account_id, public_id, name, description FROM networks WHERE account_id = $1`
rows, err := s.pool.Query(ctx, query, accountID)
management/server/store/sql_store_agentnetwork.go
+1 -1
View File
@@ -71,7 +71,7 @@ func (s *SqlStore) GetAgentNetworkMetrics(ctx context.Context) (AgentNetworkMetr
usageRow := db.Model(&agentNetworkTypes.AgentNetworkUsage{}).
Select("COALESCE(SUM(input_tokens), 0) AS input_tokens, " +
"COALESCE(SUM(output_tokens), 0) AS output_tokens, " +
"COALESCE(SUM(cost_usd), 0) AS cost_usd").Row()
"COALESCE(SUM" + agentNetworkTypes.CostUSDSQLExpr + ", 0) AS cost_usd").Row()
if err := usageRow.Scan(&m.InputTokens, &m.OutputTokens, &m.CostUSD); err != nil {
return AgentNetworkMetrics{}, fmt.Errorf("scan agent network usage metrics: %w", err)
}
management/server/store/sql_store_agentnetwork_accesslog_test.go
+6 -6
View File
@@ -37,7 +37,7 @@ func TestAgentNetworkUsage_RealStore_RoundTrip(t *testing.T) {
InputTokens: 1200,
OutputTokens: 640,
TotalTokens: 1840,
CostUSD: 0.0231,
InputCostUSD: 0.0231,
}
usageGroups := []agentNetworkTypes.AgentNetworkUsageGroup{
{UsageID: usage.ID, GroupID: "grp-eng", AccountID: accountID},
@@ -71,7 +71,7 @@ func TestAgentNetworkUsage_RealStore_RoundTrip(t *testing.T) {
InputTokens: 1200,
OutputTokens: 640,
TotalTokens: 1840,
CostUSD: 0.0231,
InputCostUSD: 0.0231,
}
entryGroups := []agentNetworkTypes.AgentNetworkAccessLogGroup{
{LogID: entry.ID, GroupID: "grp-eng", AccountID: accountID},
@@ -127,7 +127,7 @@ func TestAgentNetworkUsageOverview_DailyAggregation(t *testing.T) {
mk := func(id string, ts time.Time, model string, in, out int64, cost float64) *agentNetworkTypes.AgentNetworkUsage {
return &agentNetworkTypes.AgentNetworkUsage{
ID: id, AccountID: accountID, Timestamp: ts, Model: model,
InputTokens: in, OutputTokens: out, TotalTokens: in + out, CostUSD: cost,
InputTokens: in, OutputTokens: out, TotalTokens: in + out, InputCostUSD: cost,
}
}
require.NoError(t, s.CreateAgentNetworkUsage(ctx, mk("u1", day1, "gpt-4o", 100, 50, 0.10), nil))
@@ -143,7 +143,7 @@ func TestAgentNetworkUsageOverview_DailyAggregation(t *testing.T) {
assert.Equal(t, "2026-05-05", buckets[0].PeriodStart, "oldest-first ordering")
assert.Equal(t, int64(300), buckets[0].InputTokens, "same-day input tokens summed")
assert.Equal(t, int64(130), buckets[0].OutputTokens)
assert.InDelta(t, 0.30, buckets[0].CostUSD, 1e-9, "same-day cost summed")
assert.InDelta(t, 0.30, buckets[0].TotalCostUSD(), 1e-9, "same-day cost summed")
assert.Equal(t, "2026-05-06", buckets[1].PeriodStart)
assert.Equal(t, int64(15), buckets[1].TotalTokens)
@@ -174,7 +174,7 @@ func TestAgentNetworkAccessLogSessions_RealStore(t *testing.T) {
ID: id, AccountID: accountID, ServiceID: "svc", Timestamp: ts,
UserID: user, StatusCode: 200, Provider: provider, Model: model,
SessionID: session, Decision: decision,
InputTokens: 100, OutputTokens: 50, TotalTokens: 150, CostUSD: cost,
InputTokens: 100, OutputTokens: 50, TotalTokens: 150, InputCostUSD: cost,
}
}
@@ -207,7 +207,7 @@ func TestAgentNetworkAccessLogSessions_RealStore(t *testing.T) {
s1 := sessions[2]
assert.Equal(t, 2, s1.RequestCount, "s1 has two requests")
assert.Equal(t, int64(300), s1.TotalTokens, "tokens summed across the session")
assert.InDelta(t, 0.30, s1.CostUSD, 1e-9, "cost summed across the session")
assert.InDelta(t, 0.30, s1.TotalCostUSD(), 1e-9, "cost summed across the session")
assert.Equal(t, "alice", s1.UserID)
assert.Equal(t, "allow", s1.Decision)
// SQLite hands times back in time.Local; normalise to UTC so the instant is
management/server/store/sql_store_pgx_parity_test.go
+74
View File
@@ -0,0 +1,74 @@
package store
import (
"strings"
"sync"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"gorm.io/gorm/schema"
rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
)
// TestPgxServiceColumnsMatchGorm guards the Postgres pgx read path against
// drifting from the gorm model. The SQLite/MySQL gorm path loads rows by struct,
// so a new column on a model is picked up automatically, but the hand-written
// pgx SELECT in sql_store.go must be updated by hand. This test fails when a
// gorm column is missing from the pgx column list, which otherwise silently
// returns zero-valued on Postgres with no compile error.
func TestPgxServiceColumnsMatchGorm(t *testing.T) {
tests := []struct {
name string
model any
selectColumns string
// excluded lists gorm columns intentionally not loaded by the pgx path.
excluded map[string]struct{}
}{
{
name: "service",
model: &rpservice.Service{},
selectColumns: serviceSelectColumns,
},
{
name: "target",
model: &rpservice.Target{},
selectColumns: targetSelectColumns,
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
selected := parseColumnList(tc.selectColumns)
for _, col := range gormColumnNames(t, tc.model) {
if _, ok := tc.excluded[col]; ok {
continue
}
_, ok := selected[col]
assert.Truef(t, ok,
"gorm column %q is not read by the Postgres pgx SELECT; add it to %sSelectColumns in sql_store.go (or to the test's excluded set if it is intentionally not loaded)",
col, tc.name)
}
})
}
}
func parseColumnList(cols string) map[string]struct{} {
set := make(map[string]struct{})
for _, c := range strings.Split(cols, ",") {
if c = strings.TrimSpace(c); c != "" {
set[c] = struct{}{}
}
}
return set
}
// gormColumnNames returns the DB column names gorm would migrate for the model,
// using the same default naming strategy the store configures.
func gormColumnNames(t *testing.T, model any) []string {
t.Helper()
sch, err := schema.Parse(model, &sync.Map{}, schema.NamingStrategy{})
require.NoError(t, err)
return sch.DBNames
}
management/server/store/sql_store_service_test.go
+89
View File
@@ -5,6 +5,7 @@ import (
"os"
"runtime"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
@@ -44,3 +45,91 @@ func TestSqlStore_GetAccount_PrivateServiceRoundtrip(t *testing.T) {
assert.Equal(t, []string{"grp-admins", "grp-ops"}, got.AccessGroups)
})
}
// TestSqlStore_GetAccount_ServiceTargetOptionsRoundtrip guards the Postgres pgx
// read path (getServices) against silently dropping columns present on the gorm
// model. Before the fix these fields loaded correctly on SQLite but came back
// zero-valued on Postgres because the hand-written SELECT and scan omitted them.
func TestSqlStore_GetAccount_ServiceTargetOptionsRoundtrip(t *testing.T) {
if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
t.Skip("skip CI tests on darwin and windows")
}
runTestForAllEngines(t, "", func(t *testing.T, store Store) {
ctx := context.Background()
account := newAccountWithId(ctx, "account_svc_opts", "testuser", "")
require.NoError(t, store.SaveAccount(ctx, account))
renewedAt := time.Now().UTC().Truncate(time.Second)
targetPath := "/api"
svc := &rpservice.Service{
ID: "svc-opts",
AccountID: account.Id,
Name: "opts-svc",
Domain: "opts.example",
Enabled: true,
Mode: rpservice.ModeHTTP,
Restrictions: rpservice.AccessRestrictions{
AllowedCIDRs: []string{"10.0.0.0/8"},
BlockedCountries: []string{"XX"},
CrowdSecMode: "block",
},
Meta: rpservice.Meta{
LastRenewedAt: &renewedAt,
},
Targets: []*rpservice.Target{
{
AccountID: account.Id,
ServiceID: "svc-opts",
Path: &targetPath,
Host: "backend.internal",
Port: 8080,
Protocol: "http",
TargetId: "tgt-1",
Enabled: true,
ProxyProtocol: true,
Options: rpservice.TargetOptions{
SkipTLSVerify: true,
RequestTimeout: 30 * time.Second,
SessionIdleTimeout: 5 * time.Minute,
PathRewrite: rpservice.PathRewritePreserve,
CustomHeaders: map[string]string{"X-Foo": "bar"},
DirectUpstream: true,
CaptureMaxRequestBytes: 1024,
CaptureMaxResponseBytes: 2048,
CaptureContentTypes: []string{"application/json"},
AgentNetwork: true,
DisableAccessLog: true,
},
},
},
}
require.NoError(t, store.CreateService(ctx, svc))
loaded, err := store.GetAccount(ctx, account.Id)
require.NoError(t, err)
require.Len(t, loaded.Services, 1)
got := loaded.Services[0]
assert.Equal(t, []string{"10.0.0.0/8"}, got.Restrictions.AllowedCIDRs, "restrictions allowed CIDRs")
assert.Equal(t, []string{"XX"}, got.Restrictions.BlockedCountries, "restrictions blocked countries")
assert.Equal(t, "block", got.Restrictions.CrowdSecMode, "restrictions crowdsec mode")
require.NotNil(t, got.Meta.LastRenewedAt, "meta last renewed at")
assert.WithinDuration(t, renewedAt, *got.Meta.LastRenewedAt, time.Second, "meta last renewed at")
require.Len(t, got.Targets, 1)
tg := got.Targets[0]
assert.True(t, tg.ProxyProtocol, "target proxy protocol")
assert.True(t, tg.Options.SkipTLSVerify, "options skip TLS verify")
assert.Equal(t, 30*time.Second, tg.Options.RequestTimeout, "options request timeout")
assert.Equal(t, 5*time.Minute, tg.Options.SessionIdleTimeout, "options session idle timeout")
assert.Equal(t, rpservice.PathRewritePreserve, tg.Options.PathRewrite, "options path rewrite")
assert.Equal(t, map[string]string{"X-Foo": "bar"}, tg.Options.CustomHeaders, "options custom headers")
assert.True(t, tg.Options.DirectUpstream, "options direct upstream")
assert.Equal(t, int64(1024), tg.Options.CaptureMaxRequestBytes, "options capture max request bytes")
assert.Equal(t, int64(2048), tg.Options.CaptureMaxResponseBytes, "options capture max response bytes")
assert.Equal(t, []string{"application/json"}, tg.Options.CaptureContentTypes, "options capture content types")
assert.True(t, tg.Options.AgentNetwork, "options agent network")
assert.True(t, tg.Options.DisableAccessLog, "options disable access log")
})
}
management/server/store/store.go
+8
View File
@@ -650,6 +650,14 @@ func getMigrationsPostAuto(ctx context.Context) []migrationFunc {
func(db *gorm.DB) error {
return migration.DropIndex[proxy.Proxy](ctx, db, "idx_proxy_account_id_unique")
},
// Post-auto so the per-bucket cost columns already exist when the legacy
// aggregates are folded into them and dropped.
func(db *gorm.DB) error {
return migration.FoldCostAggregatesIntoBuckets[agentNetworkTypes.AgentNetworkAccessLog](ctx, db)
},
func(db *gorm.DB) error {
return migration.FoldCostAggregatesIntoBuckets[agentNetworkTypes.AgentNetworkUsage](ctx, db)
},
}
}
management/server/types/account.go
+23 -3
View File
@@ -1594,14 +1594,34 @@ func (a *Account) injectPrivateServicePolicies(svc *service.Service, proxyPeers
if len(proxyPeers) == 0 {
return
}
// A service's AccessGroups can name groups that no longer exist — persisted
// services and the agent-network synthesiser both carry the ids verbatim from
// their own state. An unresolvable source authorises nothing, so drop it here
// rather than let the network-map assembly resolve it to a nil group.
sources := a.existingGroupIDs(svc.AccessGroups)
if len(sources) == 0 {
return
}
for _, proxyPeer := range proxyPeers {
a.Policies = append(a.Policies, a.createPrivateServicePolicy(svc, proxyPeer))
a.Policies = append(a.Policies, a.createPrivateServicePolicy(svc, proxyPeer, sources))
}
}
func (a *Account) createPrivateServicePolicy(svc *service.Service, proxyPeer *nbpeer.Peer) *Policy {
// existingGroupIDs returns the subset of groupIDs that resolve to a group in the account,
// preserving the input order.
func (a *Account) existingGroupIDs(groupIDs []string) []string {
out := make([]string, 0, len(groupIDs))
for _, groupID := range groupIDs {
if _, ok := a.Groups[groupID]; ok {
out = append(out, groupID)
}
}
return out
}
func (a *Account) createPrivateServicePolicy(svc *service.Service, proxyPeer *nbpeer.Peer, accessGroups []string) *Policy {
policyID := fmt.Sprintf("private-access-%s-%s", svc.ID, proxyPeer.ID)
sources := append([]string(nil), svc.AccessGroups...)
sources := append([]string(nil), accessGroups...)
return &Policy{
ID: policyID,
Name: fmt.Sprintf("Private Access to %s", svc.Name),
management/server/types/account_test.go
+73
View File
@@ -18,6 +18,7 @@ import (
networkTypes "github.com/netbirdio/netbird/management/server/networks/types"
nbpeer "github.com/netbirdio/netbird/management/server/peer"
"github.com/netbirdio/netbird/route"
"github.com/netbirdio/netbird/shared/management/networkmap/nmdata"
)
func setupTestAccount() *Account {
@@ -1237,3 +1238,75 @@ func hasPrivateAccessPolicy(account *Account, serviceID string) bool {
}
return false
}
func TestForcesRoutingPeerDNSResolution(t *testing.T) {
buildAccountRes := func(serviceEnabled, targetEnabled, resourceEnabled bool, targetType service.TargetType, resType resourceTypes.NetworkResourceType) *Account {
return &Account{
Id: "accountID",
Groups: map[string]*Group{
"router-group": {ID: "router-group", Peers: []string{"router-peer-grp"}},
},
NetworkRouters: []*routerTypes.NetworkRouter{
{ID: "r1", NetworkID: "net-1", AccountID: "accountID", Peer: "router-peer", Enabled: true},
{ID: "r2", NetworkID: "net-1", AccountID: "accountID", PeerGroups: []string{"router-group"}, Enabled: true},
},
NetworkResources: []*resourceTypes.NetworkResource{
{ID: "res-domain", AccountID: "accountID", NetworkID: "net-1", Type: resType, Domain: "example.org", Enabled: resourceEnabled},
},
Services: []*service.Service{
{
ID: "svc-1", AccountID: "accountID", Enabled: serviceEnabled,
Targets: []*service.Target{
{TargetId: "res-domain", TargetType: targetType, Enabled: targetEnabled},
},
},
},
}
}
buildAccount := func(serviceEnabled, targetEnabled, resourceEnabled bool, targetType service.TargetType) *Account {
return buildAccountRes(serviceEnabled, targetEnabled, resourceEnabled, targetType, resourceTypes.Domain)
}
forced := func(account *Account, peerID string) bool {
nmd := account.toNetworkMapData(nil, nil, nil, account.GetResourceRoutersMap(), nil)
return nmd.GetPeerNetworkMapComponents(peerID, nmdata.CustomZone{}).ForceRoutingPeerDNSResolution
}
t.Run("router peer for RP-targeted domain resource is forced", func(t *testing.T) {
account := buildAccount(true, true, true, service.TargetTypeDomain)
assert.True(t, forced(account, "router-peer"), "direct router peer should be forced")
assert.True(t, forced(account, "router-peer-grp"), "group-member router peer should be forced")
})
t.Run("non-router peer is not forced", func(t *testing.T) {
account := buildAccount(true, true, true, service.TargetTypeDomain)
assert.False(t, forced(account, "other-peer"))
})
t.Run("not forced when service disabled", func(t *testing.T) {
account := buildAccount(false, true, true, service.TargetTypeDomain)
assert.False(t, forced(account, "router-peer"))
})
t.Run("not forced when target disabled", func(t *testing.T) {
account := buildAccount(true, false, true, service.TargetTypeDomain)
assert.False(t, forced(account, "router-peer"))
})
t.Run("not forced when resource disabled", func(t *testing.T) {
account := buildAccount(true, true, false, service.TargetTypeDomain)
assert.False(t, forced(account, "router-peer"))
})
t.Run("not forced for non-domain target type", func(t *testing.T) {
account := buildAccount(true, true, true, service.TargetTypePeer)
assert.False(t, forced(account, "router-peer"))
})
t.Run("not forced when targeted resource is not a domain", func(t *testing.T) {
account := buildAccountRes(true, true, true, service.TargetTypeDomain, resourceTypes.Host)
assert.False(t, forced(account, "router-peer"),
"a domain target pointing at a non-domain resource must not force resolution")
})
}
management/server/types/networkmap_components_correctness_test.go
+3 -3
View File
@@ -388,7 +388,7 @@ func TestComponents_NetworkSerial(t *testing.T) {
account.Network.Serial = 42
nm := componentsNetworkMap(account, "peer-0", validatedPeers)
require.NotNil(t, nm)
assert.Equal(t, uint64(42), nm.Network.Serial, "network serial should match")
assert.Equal(t, uint64(42), nm.Network.CurrentSerial(), "network serial should match")
}
// ──────────────────────────────────────────────────────────────────────────────
@@ -812,7 +812,7 @@ func TestComponents_AllPeersGetValidMaps(t *testing.T) {
}
nm := componentsNetworkMap(account, peerID, validatedPeers)
require.NotNil(t, nm, "network map should not be nil for %s", peerID)
assert.Equal(t, account.Network.Serial, nm.Network.Serial, "serial mismatch for %s", peerID)
assert.Equal(t, account.Network.Serial, nm.Network.CurrentSerial(), "serial mismatch for %s", peerID)
assert.NotEmpty(t, nm.Peers, "validated peer %s should see other peers", peerID)
}
}
@@ -833,7 +833,7 @@ func TestComponents_LargeScaleMapGeneration(t *testing.T) {
require.NotNil(t, nm, "network map should not be nil for %s", peerID)
assert.NotEmpty(t, nm.Peers, "peer %s should see other peers at scale", peerID)
assert.NotEmpty(t, nm.Routes, "peer %s should have routes at scale", peerID)
assert.Equal(t, account.Network.Serial, nm.Network.Serial, "serial mismatch for %s", peerID)
assert.Equal(t, account.Network.Serial, nm.Network.CurrentSerial(), "serial mismatch for %s", peerID)
}
})
}
management/server/types/proxy_access_token.go
+5 -2
View File
@@ -68,7 +68,7 @@ type ProxyAccessTokenGenerated struct {
// CreateNewProxyAccessToken generates a new proxy access token.
// Returns the token with hashed value stored and plain token for one-time display.
func CreateNewProxyAccessToken(name string, expiresIn time.Duration, accountID *string, createdBy string) (*ProxyAccessTokenGenerated, error) {
hashedToken, plainToken, err := generateProxyToken()
hashedToken, plainToken, err := GenerateProxyToken()
if err != nil {
return nil, err
}
@@ -94,7 +94,10 @@ func CreateNewProxyAccessToken(name string, expiresIn time.Duration, accountID *
}, nil
}
func generateProxyToken() (HashedProxyToken, PlainProxyToken, error) {
// GenerateProxyToken generates a new random proxy token, returning its SHA-256
// hash (for storage) and the one-time plaintext. Exported so external modules
// can mint tokens in the canonical proxy-token format.
func GenerateProxyToken() (HashedProxyToken, PlainProxyToken, error) {
secret, err := b.Random(ProxyTokenSecretLength)
if err != nil {
return "", "", err
management/server/types/proxy_access_token_test.go
+17
View File
@@ -1,6 +1,7 @@
package types
import (
"strings"
"testing"
"time"
@@ -123,6 +124,22 @@ func TestCreateNewProxyAccessToken(t *testing.T) {
})
}
func TestGenerateProxyToken(t *testing.T) {
hashed, plain, err := GenerateProxyToken()
if err != nil {
t.Fatal(err)
}
if err := plain.Validate(); err != nil {
t.Errorf("generated token failed Validate(): %v", err)
}
if plain.Hash() != hashed {
t.Error("returned hashed token does not match Hash(plain)")
}
if !strings.HasPrefix(string(plain), ProxyTokenPrefix) {
t.Errorf("token %q missing prefix %q", plain, ProxyTokenPrefix)
}
}
func TestProxyAccessToken_IsExpired(t *testing.T) {
past := time.Now().Add(-1 * time.Hour)
future := time.Now().Add(1 * time.Hour)
management/server/user.go
+4
View File
@@ -321,6 +321,10 @@ func (am *DefaultAccountManager) DeleteUser(ctx context.Context, accountID, init
return err
}
if targetUser.AccountID != accountID {
return status.NewUserNotFoundError(targetUserID)
}
if targetUser.Role == types.UserRoleOwner {
return status.NewOwnerDeletePermissionError()
}
management/server/user_test.go
+46
View File
@@ -802,6 +802,52 @@ func TestUser_DeleteUser_SelfDelete(t *testing.T) {
}
}
func TestUser_DeleteUser_OtherAccount(t *testing.T) {
testStore, cleanup, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
if err != nil {
t.Fatalf("Error when creating store: %s", err)
}
t.Cleanup(cleanup)
account := newAccountWithId(context.Background(), mockAccountID, mockUserID, "", "", "", false)
if err = testStore.SaveAccount(context.Background(), account); err != nil {
t.Fatalf("Error when saving account: %s", err)
}
otherAccount := newAccountWithId(context.Background(), "otherAccount", "otherOwner", "", "", "", false)
otherAccount.Users["otherRegularUser"] = &types.User{
Id: "otherRegularUser",
AccountID: "otherAccount",
Role: types.UserRoleUser,
}
otherAccount.Users["otherServiceUser"] = &types.User{
Id: "otherServiceUser",
AccountID: "otherAccount",
Role: types.UserRoleUser,
IsServiceUser: true,
ServiceUserName: "otherServiceUser",
}
if err = testStore.SaveAccount(context.Background(), otherAccount); err != nil {
t.Fatalf("Error when saving other account: %s", err)
}
am := DefaultAccountManager{
Store: testStore,
eventStore: &activity.InMemoryEventStore{},
permissionsManager: permissions.NewManager(testStore),
}
for _, targetUserID := range []string{"otherRegularUser", "otherServiceUser"} {
t.Run(targetUserID, func(t *testing.T) {
err := am.DeleteUser(context.Background(), mockAccountID, mockUserID, targetUserID)
assert.Equal(t, status.NewUserNotFoundError(targetUserID), err)
_, err = testStore.GetUserByUserID(context.Background(), store.LockingStrengthNone, targetUserID)
assert.NoError(t, err, "user of another account must not be deleted")
})
}
}
func TestUser_DeleteUser_regularUser(t *testing.T) {
store, cleanup, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
if err != nil {