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

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

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

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

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

The end-to-end work turned up one more: the discovery filter treated any slash
in a model id as a gateway prefix, which would have dropped every self-hosted
"Qwen/..." model from the picker.

proxy/internal/llm/model.go

@@ -13,6 +13,14 @@ func NormalizeBedrockModel(modelID string) string {
 	return sharedllm.NormalizeBedrockModel(modelID)
 }
 
+// NormalizeAnthropicModel strips the trailing "-YYYYMMDD" release-date suffix
+// from an Anthropic model id so a dated id a client pins matches the undated
+// one the operator registered. Thin delegate to shared/llm for the same
+// contract reason as the two below.
+func NormalizeAnthropicModel(modelID string) string {
+	return sharedllm.NormalizeAnthropicModel(modelID)
+}
+
 // NormalizeVertexModel strips the "@version" suffix from a Vertex AI model id
 // so it matches the catalog/pricing key. Thin delegate to shared/llm, kept
 // beside NormalizeBedrockModel for the same contract reason.

proxy/internal/llm/pricing/pricing.go

@@ -10,6 +10,8 @@ package pricing
 import (
 	"fmt"
 	"math"
+
+	sharedllm "github.com/netbirdio/netbird/shared/llm"
 )
 
 // Entry is a single model's input and output pricing, expressed in USD per
@@ -92,7 +94,10 @@ func NewTable(raw map[string]map[string]EntryJSON) (*Table, error) {
 	return &Table{entries: entries}, nil
 }
 
-// Lookup returns the entry for the given provider surface and model.
+// Lookup returns the entry for the given provider surface and model. A
+// dated Anthropic id falls back to its undated form, so a client pinning
+// "claude-sonnet-4-5-20250929" bills at the registered "claude-sonnet-4-5"
+// rate instead of recording no cost at all.
 func (t *Table) Lookup(provider, model string) (Entry, bool) {
 	if t == nil {
 		return Entry{}, false
@@ -101,7 +106,14 @@ func (t *Table) Lookup(provider, model string) (Entry, bool) {
 	if !ok {
 		return Entry{}, false
 	}
-	e, ok := byModel[model]
+	if e, found := byModel[model]; found {
+		return e, true
+	}
+	undated := sharedllm.NormalizeAnthropicModel(model)
+	if undated == model {
+		return Entry{}, false
+	}
+	e, ok := byModel[undated]
 	return e, ok
 }
 

proxy/internal/llm/pricing/pricing_test.go

@@ -175,3 +175,22 @@ func TestNewTable_NilAndEmpty(t *testing.T) {
 	require.NoError(t, err)
 	assert.Empty(t, entries, "nil in, empty (never-matching) map out for the per-record map")
 }
+
+// TestLookup_DatedAnthropicIDFallsBackToUndated covers a client pinning a
+// release date on a model priced under its undated id. Without the
+// fallback the request records no cost at all.
+func TestLookup_DatedAnthropicIDFallsBackToUndated(t *testing.T) {
+	table, err := NewTable(map[string]map[string]EntryJSON{
+		"anthropic": {
+			"claude-sonnet-4-5": {InputPer1K: 0.003, OutputPer1K: 0.015},
+		},
+	})
+	require.NoError(t, err, "table must build from a valid defaults map")
+
+	entry, ok := table.Lookup("anthropic", "claude-sonnet-4-5-20250929")
+	require.True(t, ok, "a dated id must resolve to the undated entry")
+	assert.InDelta(t, 0.003, entry.InputPer1K, 1e-9, "dated id must bill at the registered rate")
+
+	_, ok = table.Lookup("anthropic", "claude-sonnet-9-9-20250929")
+	assert.False(t, ok, "an unknown family must stay unpriced")
+}

proxy/internal/middleware/builtin/cost_meter/middleware.go

@@ -11,6 +11,7 @@ import (
 	"fmt"
 	"strconv"
 
+	"github.com/netbirdio/netbird/proxy/internal/llm"
 	"github.com/netbirdio/netbird/proxy/internal/llm/pricing"
 	"github.com/netbirdio/netbird/proxy/internal/middleware"
 )
@@ -175,13 +176,28 @@ func (m *Middleware) Invoke(_ context.Context, in *middleware.Input) (*middlewar
 // Anthropic route still bills its cache buckets additively.
 func (m *Middleware) lookupCosts(md []middleware.KV, surface, model string, inTokens, outTokens, cachedTokens, cacheCreationTokens int64) (pricing.Costs, bool) {
 	if recordID := lookupKV(md, middleware.KeyLLMResolvedProviderID); recordID != "" {
-		if entry, ok := m.perRecord[recordID][model]; ok {
+		if entry, ok := perRecordEntry(m.perRecord[recordID], model); ok {
 			return pricing.EntryCosts(entry, surface, inTokens, outTokens, cachedTokens, cacheCreationTokens), true
 		}
 	}
 	return m.defaults.Costs(surface, model, inTokens, outTokens, cachedTokens, cacheCreationTokens)
 }
 
+// perRecordEntry resolves the operator's stored price for a model on one
+// provider record, falling back to the undated form of a dated Anthropic id
+// so a client that pins a release date still bills at the registered rate.
+func perRecordEntry(byModel map[string]pricing.Entry, model string) (pricing.Entry, bool) {
+	if entry, ok := byModel[model]; ok {
+		return entry, true
+	}
+	undated := llm.NormalizeAnthropicModel(model)
+	if undated == model {
+		return pricing.Entry{}, false
+	}
+	entry, ok := byModel[undated]
+	return entry, ok
+}
+
 // usd renders a cost as the fixed-precision string every cost.usd_* key
 // carries, so the per-bucket values and the aggregates round identically.
 //

proxy/internal/middleware/builtin/llm_guardrail/middleware.go

@@ -84,8 +84,10 @@ func (m *Middleware) MutationsSupported() bool { return false }
 func (m *Middleware) Invoke(_ context.Context, in *middleware.Input) (*middleware.Output, error) {
 	model, modelPresent := lookupMetadata(in.Metadata, middleware.KeyLLMModel)
 	providerID, _ := lookupMetadata(in.Metadata, middleware.KeyLLMResolvedProviderID)
+	surface, _ := lookupMetadata(in.Metadata, middleware.KeyLLMProvider)
+	nonInference, _ := lookupMetadata(in.Metadata, middleware.KeyLLMNonInference)
 
-	if denial := m.evaluateAllowlist(providerID, model, modelPresent); denial != nil {
+	if denial := m.evaluateAllowlist(providerID, surface, model, modelPresent, nonInference == "true"); denial != nil {
 		return denial, nil
 	}
 
@@ -114,7 +116,7 @@ func (m *Middleware) Close() error { return nil }
 // evaluateAllowlist denies when the resolved provider's allowlist rejects the
 // model; nil means proceed. Scoped to the provider llm_router resolved, so an
 // unrestricted provider (absent from config) is never caught by another's list.
-func (m *Middleware) evaluateAllowlist(providerID, model string, modelPresent bool) *middleware.Output {
+func (m *Middleware) evaluateAllowlist(providerID, surface, model string, modelPresent, nonInference bool) *middleware.Output {
 	if len(m.cfg.ProviderAllowlists) == 0 {
 		return nil
 	}
@@ -122,7 +124,7 @@ func (m *Middleware) evaluateAllowlist(providerID, model string, modelPresent bo
 	// if this request targets a restricted provider — fail closed. llm_router
 	// normally stamps the provider first, so this is a defensive guard.
 	if providerID == "" {
-		return denyModel("", denyCodeModelUnknown, denyMessageModelUnknown, denyReasonModelUnknown)
+		return denyModel(surface, "", denyCodeModelUnknown, denyMessageModelUnknown, denyReasonModelUnknown)
 	}
 	allowlist, restricted := m.cfg.ProviderAllowlists[providerID]
 	if !restricted {
@@ -133,18 +135,29 @@ func (m *Middleware) evaluateAllowlist(providerID, model string, modelPresent bo
 	// Fail closed: with an allowlist in effect for this provider, a request whose
 	// model the parser couldn't extract (absent/empty) is denied. This enforces
 	// the allowlist for path-routed providers (Bedrock, Vertex) with no body model.
+	//
+	// The exception is a non-inference endpoint the router already authorised.
+	// The model listing and the connection-warming probe name no model
+	// anywhere — not in a body, not in the path — so failing closed here
+	// rejected model discovery for exactly the accounts that configured an
+	// allowlist, which is the outage this endpoint is meant to avoid. The
+	// per-model lookup does name one (the router stamps it from the path), so
+	// it still falls through to the allowlist check below.
 	if !modelPresent || normaliseModel(model) == "" {
-		return denyModel("", denyCodeModelUnknown, denyMessageModelUnknown, denyReasonModelUnknown)
+		if nonInference {
+			return nil
+		}
+		return denyModel(surface, "", denyCodeModelUnknown, denyMessageModelUnknown, denyReasonModelUnknown)
 	}
 	if modelInAllowlist(allowlist, model) {
 		return nil
 	}
-	return denyModel(model, denyCodeModel, denyMessageModel, denyReasonModel)
+	return denyModel(surface, model, denyCodeModel, denyMessageModel, denyReasonModel)
 }
 
 // denyModel builds a 403 deny Output for a model-allowlist rejection. model is
 // included in the details only when non-empty.
-func denyModel(model, code, message, reason string) *middleware.Output {
+func denyModel(surface, model, code, message, reason string) *middleware.Output {
 	details := map[string]string{}
 	if model != "" {
 		details["model"] = model
@@ -156,6 +169,7 @@ func denyModel(model, code, message, reason string) *middleware.Output {
 			Code:    code,
 			Message: message,
 			Details: details,
+			Surface: surface,
 		},
 		Metadata: []middleware.KV{
 			{Key: middleware.KeyLLMPolicyDecision, Value: "deny"},

proxy/internal/middleware/builtin/llm_guardrail/middleware_test.go

@@ -343,3 +343,52 @@ func TestFactoryNormalisesAllowlist(t *testing.T) {
 	require.NoError(t, err)
 	assert.Equal(t, middleware.DecisionAllow, out2.Decision, "trimmed entry must still match")
 }
+
+// TestAllowlistSkipsNonInferenceWithoutModel covers the reported regression:
+// GET /v1/models carries no model anywhere, so the fail-closed rule above
+// denied model discovery for exactly the accounts that configured a provider
+// allowlist — the clients that read a 403 here render an empty model picker.
+// The router authorises those endpoints by path before the guardrail sees
+// them, so an absent model there is expected rather than undeterminable.
+func TestAllowlistSkipsNonInferenceWithoutModel(t *testing.T) {
+	mw := New(providerCfg("gpt-4o"))
+	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+		middleware.KV{Key: middleware.KeyLLMNonInference, Value: "true"},
+	))
+	require.NoError(t, err)
+	require.NotNil(t, out)
+	assert.Equal(t, middleware.DecisionAllow, out.Decision,
+		"model discovery must not be refused because it names no model")
+}
+
+// TestAllowlistStillAppliesToNonInferenceWithModel pins that the exemption is
+// scoped to requests that genuinely name nothing. The per-model lookup
+// (GET /v1/models/{id}) is non-inference too, but the router stamps the model
+// from its path, so the allowlist must still decide it — otherwise the
+// exemption becomes a way to confirm a model the policy blocks.
+func TestAllowlistStillAppliesToNonInferenceWithModel(t *testing.T) {
+	mw := New(providerCfg("gpt-4o"))
+
+	t.Run("model in the allowlist", func(t *testing.T) {
+		out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+			middleware.KV{Key: middleware.KeyLLMNonInference, Value: "true"},
+			middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
+		))
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision,
+			"an allowlisted model must stay reachable")
+	})
+
+	t.Run("model outside the allowlist", func(t *testing.T) {
+		out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+			middleware.KV{Key: middleware.KeyLLMNonInference, Value: "true"},
+			middleware.KV{Key: middleware.KeyLLMModel, Value: "claude-opus-5"},
+		))
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionDeny, out.Decision,
+			"non-inference must not become a way past the allowlist")
+		require.NotNil(t, out.DenyReason)
+		assert.Equal(t, "llm_policy.model_blocked", out.DenyReason.Code,
+			"a named but blocked model is blocked, not unknown")
+	})
+}

proxy/internal/middleware/builtin/llm_identity_inject/middleware.go

@@ -217,6 +217,32 @@ func applyHeaderPair(rule *HeaderPairRule, in *middleware.Input) *middleware.Mut
 	return mutations
 }
 
+// bodyInjectableSurfaces are the request-body dialects that accept the
+// OpenAI-standard identity fields this middleware writes. A surface
+// outside this set gets header-only stamping: "user" and "metadata.tags"
+// are not part of the Anthropic Messages schema, which rejects unknown
+// top-level fields and permits only "user_id" under metadata, so writing
+// them into an Anthropic-shaped body turns a working request into a 400.
+// Claude Code speaks that shape through gateway records pinned to the
+// OpenAI parser, so the check keys on the detected surface rather than
+// on the provider record.
+var bodyInjectableSurfaces = map[string]struct{}{
+	"openai": {},
+	// An empty surface means no parser claimed the path (a custom gateway
+	// base). Those upstreams are OpenAI-compatible by convention, so keep
+	// the long-standing behaviour rather than silently dropping identity.
+	"": {},
+}
+
+// bodyAcceptsOpenAIIdentity reports whether the request body may carry the
+// OpenAI-standard identity fields, read from the surface llm_request_parser
+// resolved from the request path.
+func bodyAcceptsOpenAIIdentity(in *middleware.Input) bool {
+	surface, _ := lookupMetadata(in.Metadata, middleware.KeyLLMProvider)
+	_, ok := bodyInjectableSurfaces[surface]
+	return ok
+}
+
 // injectIntoBody parses the request body and writes the supplied
 // identity dimensions into it. Tags land at metadata.tags (creating
 // the metadata object when absent); the user identity lands at the
@@ -225,6 +251,8 @@ func applyHeaderPair(rule *HeaderPairRule, in *middleware.Input) *middleware.Mut
 // was written. Returns ok=false (no mutation) when:
 //
 //   - both inputs are empty (nothing to write);
+//   - the body speaks a dialect without these fields (see
+//     bodyInjectableSurfaces);
 //   - the body is empty or truncated (we don't have the full document
 //     to safely round-trip);
 //   - the body isn't a JSON object (skip silently — this middleware
@@ -245,6 +273,9 @@ func injectIntoBody(in *middleware.Input, tags []string, userID string) ([]byte,
 	if in == nil || len(in.Body) == 0 || in.BodyTruncated {
 		return nil, false
 	}
+	if !bodyAcceptsOpenAIIdentity(in) {
+		return nil, false
+	}
 	var doc map[string]any
 	if err := json.Unmarshal(in.Body, &doc); err != nil {
 		return nil, false

proxy/internal/middleware/builtin/llm_identity_inject/middleware_test.go

@@ -704,3 +704,57 @@ func TestInject_ExtraHeaders_EmptyValueSkipped(t *testing.T) {
 			"empty extra value must not be stamped")
 	}
 }
+
+// TestInject_AnthropicBodyIsNotRewritten pins the shape gate. Claude Code
+// reaches a LiteLLM record on /v1/messages, where "user" is not a
+// permitted top-level field and metadata accepts only "user_id", so
+// writing the OpenAI-standard fields would turn a working request into a
+// 400 naming a field the client never sent. Header stamping still runs, so
+// spend tracking and per-end-user budgets keep working.
+func TestInject_AnthropicBodyIsNotRewritten(t *testing.T) {
+	rule := liteLLMRuleWithBody()
+	rule.HeaderPair.EndUserIDInBody = true
+	mw := New(Config{Providers: []ProviderInjection{rule}})
+
+	in := newInput(litellmProvider, "alice", []string{"grp-eng"})
+	in.UserEmail = "alice@example.com"
+	in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "anthropic"})
+	in.Body = []byte(`{"model":"claude-sonnet-5","messages":[]}`)
+
+	out, err := mw.Invoke(context.Background(), in)
+	require.NoError(t, err)
+	require.NotNil(t, out.Mutations)
+	assert.Empty(t, out.Mutations.BodyReplace,
+		"an Anthropic-shaped body must reach the upstream unmodified")
+
+	var endUser string
+	for _, kv := range out.Mutations.HeadersAdd {
+		if kv.Key == "x-litellm-end-user-id" {
+			endUser = kv.Value
+		}
+	}
+	assert.Equal(t, "alice@example.com", endUser,
+		"header stamping must still carry identity when body inject is skipped")
+}
+
+// TestInject_OpenAIBodyStillRewritten guards the gate against
+// over-reaching: the OpenAI surface must keep its body-level identity,
+// which is the only path LiteLLM's tag-budget check reads.
+func TestInject_OpenAIBodyStillRewritten(t *testing.T) {
+	mw := New(Config{Providers: []ProviderInjection{liteLLMRuleWithBody()}})
+
+	in := newInput(litellmProvider, "alice", []string{"grp-eng"})
+	in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "openai"})
+	in.Body = []byte(`{"model":"gpt-4o-mini","messages":[]}`)
+
+	out, err := mw.Invoke(context.Background(), in)
+	require.NoError(t, err)
+	require.NotNil(t, out.Mutations)
+	require.NotEmpty(t, out.Mutations.BodyReplace, "the OpenAI surface still gets body tags")
+
+	var doc map[string]any
+	require.NoError(t, json.Unmarshal(out.Mutations.BodyReplace, &doc))
+	meta, ok := doc["metadata"].(map[string]any)
+	require.True(t, ok, "metadata must be an object")
+	assert.NotEmpty(t, meta["tags"], "metadata.tags must still be written")
+}

proxy/internal/middleware/builtin/llm_limit_check/middleware.go

@@ -84,6 +84,15 @@ func (m *Middleware) Invoke(ctx context.Context, in *middleware.Input) (*middlew
 		return allowNoAttribution(), nil
 	}
 
+	// Model-listing and other non-inference endpoints carry no model, and
+	// management's per-model allowlist fails closed on an empty one. The
+	// router has already authorised the route against the caller's groups
+	// and the request consumes no tokens, so gating it on a model that
+	// cannot exist would only break gateway model discovery.
+	if lookupKV(in.Metadata, middleware.KeyLLMNonInference) == "true" {
+		return allowNoAttribution(), nil
+	}
+
 	providerID := lookupKV(in.Metadata, middleware.KeyLLMResolvedProviderID)
 	if providerID == "" {
 		// llm_router didn't emit a resolved provider id — usually
@@ -117,7 +126,7 @@ func (m *Middleware) Invoke(ctx context.Context, in *middleware.Input) (*middlew
 	}
 
 	if resp.GetDecision() == "deny" {
-		return denyFromManagement(resp), nil
+		return denyFromManagement(resp, lookupKV(in.Metadata, middleware.KeyLLMProvider)), nil
 	}
 	return allowFromManagement(resp), nil
 }
@@ -161,7 +170,7 @@ func allowFromManagement(resp *proto.CheckLLMPolicyLimitsResponse) *middleware.O
 // envelope. The deny code surfaces verbatim through the framework's
 // fixed JSON template; arbitrary middleware bytes can't reach the
 // wire.
-func denyFromManagement(resp *proto.CheckLLMPolicyLimitsResponse) *middleware.Output {
+func denyFromManagement(resp *proto.CheckLLMPolicyLimitsResponse, surface string) *middleware.Output {
 	code := resp.GetDenyCode()
 	if code == "" {
 		code = "llm_policy.cap_exceeded"
@@ -176,6 +185,7 @@ func denyFromManagement(resp *proto.CheckLLMPolicyLimitsResponse) *middleware.Ou
 		DenyReason: &middleware.DenyReason{
 			Code:    code,
 			Message: denyMessageForCode(code),
+			Surface: surface,
 		},
 		Metadata: []middleware.KV{
 			{Key: middleware.KeyLLMPolicyDecision, Value: "deny"},

proxy/internal/middleware/builtin/llm_limit_check/middleware_test.go

@@ -224,3 +224,35 @@ func TestMetadataKeys_Allowlist(t *testing.T) {
 	}
 	assert.ElementsMatch(t, want, keys)
 }
+
+// TestInvoke_NonInferenceSkipsPreflight covers gateway model discovery:
+// GET /v1/models carries no model, and management's per-model allowlist
+// fails closed on an empty one, so a pre-flight would deny discovery for
+// exactly the accounts that use the model allowlist. The router marks the
+// request non-inference after authorising the route, and the gate must
+// then allow without calling management at all.
+func TestInvoke_NonInferenceSkipsPreflight(t *testing.T) {
+	mgmt := &fakeMgmt{
+		checkResp: &proto.CheckLLMPolicyLimitsResponse{
+			Decision: "deny",
+			DenyCode: "llm_policy.model_blocked",
+		},
+	}
+	m := New(mgmt, nil)
+
+	out := runInvoke(t, m, &middleware.Input{
+		AccountID:  "acc-1",
+		UserID:     "user-bob",
+		UserGroups: []string{"grp-engineers"},
+		Metadata: []middleware.KV{
+			{Key: middleware.KeyLLMResolvedProviderID, Value: "prov-1"},
+			{Key: middleware.KeyLLMNonInference, Value: "true"},
+		},
+	})
+
+	assert.Equal(t, middleware.DecisionAllow, out.Decision, "model-less endpoints must not be gated on a model")
+	assert.Nil(t, mgmt.checkReq, "no pre-flight may be sent for a non-inference request")
+
+	assert.Empty(t, lookupKV(out.Metadata, middleware.KeyLLMSelectedPolicyID),
+		"no policy is attributed when nothing was metered")
+}

proxy/internal/middleware/builtin/llm_request_parser/bedrock_test.go

@@ -1,9 +1,13 @@
 package llm_request_parser
 
 import (
+	"context"
 	"testing"
 
+	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/proxy/internal/middleware"
 )
 
 func TestParseBedrockPath(t *testing.T) {
@@ -36,3 +40,25 @@ func TestParseBedrockPath(t *testing.T) {
 		}
 	}
 }
+
+// TestInvoke_BedrockCountTokens covers the dedicated token-counting
+// endpoint. Denying it does not break the client, it just pushes context
+// counting back onto the inference endpoint, which is billable.
+func TestInvoke_BedrockCountTokens(t *testing.T) {
+	mw := newMiddleware(t)
+
+	out, err := mw.Invoke(context.Background(), &middleware.Input{
+		URL:  "/model/us.anthropic.claude-sonnet-4-5-20250929-v1:0/count-tokens",
+		Body: []byte(`{"input":{"converse":{"messages":[]}}}`),
+	})
+	require.NoError(t, err)
+	require.NotNil(t, out)
+	assert.Equal(t, middleware.DecisionAllow, out.Decision)
+
+	model, ok := metaValue(t, out.Metadata, middleware.KeyLLMModel)
+	require.True(t, ok, "count-tokens carries a model in the path and must emit it")
+	assert.Equal(t, "anthropic.claude-sonnet-4-5", model, "model must be normalized like any other action")
+
+	stream, _ := metaValue(t, out.Metadata, middleware.KeyLLMStream)
+	assert.Equal(t, "false", stream, "count-tokens never streams")
+}

proxy/internal/middleware/builtin/llm_request_parser/middleware.go

@@ -61,6 +61,8 @@ func (middlewareImpl) MetadataKeys() []string {
 		middleware.KeyLLMRequestPromptRaw,
 		middleware.KeyLLMCaptureTruncated,
 		middleware.KeyLLMSessionID,
+		middleware.KeyLLMAgentID,
+		middleware.KeyLLMParentAgentID,
 	}
 }
 
@@ -72,9 +74,9 @@ func (middlewareImpl) Close() error { return nil }
 
 // Invoke detects the LLM provider, parses request facts, and emits
 // metadata. Always returns DecisionAllow; never errors. Provider
-// selection prefers the configured providerID (synthesiser-stamped on
-// agent-network targets) so requests routed to a custom upstream URL
-// still resolve. Falls back to URL sniffing when no providerID is set.
+// selection prefers the request path, falling back to the configured
+// providerID (synthesiser-stamped on agent-network targets) so requests
+// routed to a custom upstream URL still resolve.
 func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middleware.Output, error) {
 	out := &middleware.Output{Decision: middleware.DecisionAllow}
 	if in == nil {
@@ -92,9 +94,14 @@ func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middle
 		return m.invokeBedrock(in, br), nil
 	}
 
-	parser, ok := llm.ParserByName(m.providerID)
+	// A path that names an API surface wins over the configured providerID:
+	// a gateway record pinned to "openai" still serves Claude Code on
+	// /v1/messages, and reading that body with the OpenAI parser loses the
+	// Anthropic usage block and prices the request on the wrong surface.
+	// providerID stays the fallback for upstreams whose path says nothing.
+	parser, ok := llm.DetectParser(extractPath(in.URL))
 	if !ok {
-		parser, ok = llm.DetectParser(extractPath(in.URL))
+		parser, ok = llm.ParserByName(m.providerID)
 	}
 	if !ok {
 		return out, nil
@@ -116,9 +123,9 @@ func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middle
 	}
 	appendSessionID := func(md []middleware.KV) []middleware.KV {
 		if sessionID != "" {
-			return append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
+			md = append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
 		}
-		return md
+		return appendAgentIDs(md, in.Headers)
 	}
 
 	facts, err := parser.ParseRequest(in.Body)
@@ -160,6 +167,41 @@ func (m middlewareImpl) Invoke(_ context.Context, in *middleware.Input) (*middle
 	return out, nil
 }
 
+// agentIDHeader and parentAgentIDHeader carry sub-agent attribution: a
+// coding agent that spawns helpers stamps the spawned agent's id, plus the
+// spawning agent's when that helper is itself nested. Both are opaque
+// identifiers rather than content, so they're emitted regardless of the
+// prompt-collection toggle, the same way the session id is.
+const (
+	agentIDHeader       = "x-claude-code-agent-id"
+	parentAgentIDHeader = "x-claude-code-parent-agent-id"
+)
+
+// appendAgentIDs stamps the sub-agent attribution headers onto the metadata
+// bag, skipping either one the request doesn't carry.
+func appendAgentIDs(md []middleware.KV, headers []middleware.KV) []middleware.KV {
+	for _, pair := range []struct{ key, header string }{
+		{middleware.KeyLLMAgentID, agentIDHeader},
+		{middleware.KeyLLMParentAgentID, parentAgentIDHeader},
+	} {
+		if v := headerValue(headers, pair.header); v != "" {
+			md = append(md, middleware.KV{Key: pair.key, Value: v})
+		}
+	}
+	return md
+}
+
+// headerValue returns the first non-empty value for the named header.
+// Headers arrive in canonical form, so the match is case-insensitive.
+func headerValue(headers []middleware.KV, want string) string {
+	for _, kv := range headers {
+		if strings.EqualFold(kv.Key, want) && kv.Value != "" {
+			return kv.Value
+		}
+	}
+	return ""
+}
+
 // sessionIDHeaders are request header names that may carry a client
 // session identifier, checked in order, case-insensitively. Matching is
 // against Go's canonical header form, so use the hyphenated names the
@@ -173,10 +215,8 @@ var sessionIDHeaders = []string{"x-claude-code-session-id", "session-id", "x-ses
 // canonical form, so the match is case-insensitive.
 func sessionIDFromHeaders(headers []middleware.KV) string {
 	for _, want := range sessionIDHeaders {
-		for _, kv := range headers {
-			if strings.EqualFold(kv.Key, want) && kv.Value != "" {
-				return kv.Value
-			}
+		if v := headerValue(headers, want); v != "" {
+			return v
 		}
 	}
 	return ""
@@ -252,6 +292,12 @@ func parseVertexPath(reqPath string) (vertexRequest, bool) {
 	if c := strings.LastIndex(rest, ":"); c >= 0 {
 		model, action = rest[:c], rest[c+1:]
 	}
+	// Token counting hangs off the model as its own path segment
+	// (".../models/{model}/count-tokens:rawPredict"), so anything past the
+	// first "/" belongs to the method rather than the model id.
+	if slash := strings.Index(model, "/"); slash >= 0 {
+		model = model[:slash]
+	}
 	model = llm.NormalizeVertexModel(model)
 	if model == "" {
 		return vertexRequest{}, false
@@ -298,6 +344,7 @@ func (m middlewareImpl) invokeVertex(in *middleware.Input, vx vertexRequest) *mi
 	if sessionID != "" {
 		md = append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
 	}
+	md = appendAgentIDs(md, in.Headers)
 
 	promptTruncated := false
 	if parser != nil && m.capturePrompt {
@@ -345,7 +392,9 @@ func trimBedrockNamespace(reqPath string) string {
 //
 //	/model/{modelId}/{action}
 //
-// action ∈ {invoke, invoke-with-response-stream, converse, converse-stream}.
+// action ∈ {invoke, invoke-with-response-stream, converse, converse-stream,
+// count-tokens}. Token counting carries a model and no usage, so it routes
+// like any other action and meters to zero.
 // The modelId may be URL-encoded and may carry a cross-region inference-profile
 // prefix and a version suffix; normalizeBedrockModel strips both so the model
 // matches catalog pricing.
@@ -369,7 +418,7 @@ func parseBedrockPath(reqPath string) (bedrockRequest, bool) {
 		return bedrockRequest{}, false
 	}
 	switch action {
-	case "invoke", "converse":
+	case "invoke", "converse", "count-tokens":
 		return bedrockRequest{model: model}, true
 	case "invoke-with-response-stream", "converse-stream":
 		return bedrockRequest{model: model, stream: true}, true
@@ -397,6 +446,7 @@ func (m middlewareImpl) invokeBedrock(in *middleware.Input, br bedrockRequest) *
 	if sessionID != "" {
 		md = append(md, middleware.KV{Key: middleware.KeyLLMSessionID, Value: sessionID})
 	}
+	md = appendAgentIDs(md, in.Headers)
 
 	promptTruncated := false
 	if parser != nil && m.capturePrompt {

proxy/internal/middleware/builtin/llm_request_parser/middleware_test.go

@@ -45,6 +45,8 @@ func TestMiddleware_StaticSurface(t *testing.T) {
 		middleware.KeyLLMRequestPromptRaw,
 		middleware.KeyLLMCaptureTruncated,
 		middleware.KeyLLMSessionID,
+		middleware.KeyLLMAgentID,
+		middleware.KeyLLMParentAgentID,
 	}
 	assert.Equal(t, expected, keys, "metadata key allowlist must match the spec")
 }
@@ -230,6 +232,31 @@ func TestInvoke_ProviderIDConfigBypassesURLSniff(t *testing.T) {
 	assert.Equal(t, "gpt-4o-mini", model)
 }
 
+func TestInvoke_PathSurfaceBeatsProviderIDConfig(t *testing.T) {
+	// Gateway records (LiteLLM, Portkey, OpenRouter) pin provider_id
+	// "openai", but the same record serves Claude Code on /v1/messages.
+	// Parsing that body as OpenAI reads no usage off the Anthropic
+	// response and prices the request on a surface where no claude-*
+	// model exists, so the path has to win.
+	mw, err := Factory{}.New([]byte(`{"provider_id":"openai"}`))
+	require.NoError(t, err, "factory must accept provider_id config")
+
+	out, err := mw.Invoke(context.Background(), &middleware.Input{
+		URL:  "/v1/messages",
+		Body: []byte(`{"model":"claude-sonnet-5","stream":true,"messages":[{"role":"user","content":"Hi"}]}`),
+	})
+	require.NoError(t, err)
+	require.NotNil(t, out)
+
+	provider, ok := metaValue(t, out.Metadata, middleware.KeyLLMProvider)
+	require.True(t, ok, "provider must be emitted")
+	assert.Equal(t, "anthropic", provider, "the /v1/messages path selects the Anthropic surface")
+
+	model, ok := metaValue(t, out.Metadata, middleware.KeyLLMModel)
+	require.True(t, ok, "model must be extracted")
+	assert.Equal(t, "claude-sonnet-5", model)
+}
+
 func TestInvoke_UnknownProviderIDFallsBackToURL(t *testing.T) {
 	mw, err := Factory{}.New([]byte(`{"provider_id":"not-a-real-parser"}`))
 	require.NoError(t, err, "factory must accept any provider_id string")
@@ -416,3 +443,81 @@ func TestInvoke_NilInputAllows(t *testing.T) {
 	assert.Equal(t, middleware.DecisionAllow, out.Decision, "nil input still allows")
 	assert.Empty(t, out.Metadata, "nil input emits no metadata")
 }
+
+// TestParseVertexPath_CountTokensKeepsModel covers Vertex token counting,
+// where the method hangs off the model as its own path segment. Splitting
+// only on the final colon swallowed "/count-tokens" into the model id, so
+// the router saw a model no route could claim.
+func TestParseVertexPath_CountTokensKeepsModel(t *testing.T) {
+	cases := map[string]struct {
+		model  string
+		stream bool
+	}{
+		"/v1/projects/p/locations/global/publishers/anthropic/models/claude-sonnet-5:rawPredict":                       {model: "claude-sonnet-5"},
+		"/v1/projects/p/locations/global/publishers/anthropic/models/claude-sonnet-5:streamRawPredict":                 {model: "claude-sonnet-5", stream: true},
+		"/v1/projects/p/locations/global/publishers/anthropic/models/claude-sonnet-5/count-tokens:rawPredict":          {model: "claude-sonnet-5"},
+		"/v1/projects/p/locations/global/publishers/anthropic/models/claude-sonnet-5@20250929/count-tokens:rawPredict": {model: "claude-sonnet-5"},
+	}
+	for path, want := range cases {
+		vx, ok := parseVertexPath(path)
+		require.True(t, ok, "must parse %q", path)
+		assert.Equal(t, want.model, vx.model, "model for %q", path)
+		assert.Equal(t, want.stream, vx.stream, "stream flag for %q", path)
+		assert.Equal(t, "anthropic", vx.publisher, "publisher for %q", path)
+	}
+}
+
+// TestInvoke_EmitsAgentIDs covers sub-agent attribution: several agents run
+// in parallel inside one session, and without their ids every request in
+// the session attributes to the session alone.
+func TestInvoke_EmitsAgentIDs(t *testing.T) {
+	mw := newMiddleware(t)
+
+	t.Run("spawned agent", func(t *testing.T) {
+		out, err := mw.Invoke(context.Background(), &middleware.Input{
+			URL:  "/v1/messages",
+			Body: []byte(`{"model":"claude-sonnet-5","messages":[]}`),
+			Headers: []middleware.KV{
+				{Key: "X-Claude-Code-Session-Id", Value: "sess-1"},
+				{Key: "X-Claude-Code-Agent-Id", Value: "agent-7"},
+			},
+		})
+		require.NoError(t, err)
+
+		agent, ok := metaValue(t, out.Metadata, middleware.KeyLLMAgentID)
+		require.True(t, ok, "the spawned agent's id must be emitted")
+		assert.Equal(t, "agent-7", agent)
+
+		_, ok = metaValue(t, out.Metadata, middleware.KeyLLMParentAgentID)
+		assert.False(t, ok, "a top-level agent has no parent to emit")
+	})
+
+	t.Run("nested agent", func(t *testing.T) {
+		out, err := mw.Invoke(context.Background(), &middleware.Input{
+			URL:  "/v1/messages",
+			Body: []byte(`{"model":"claude-sonnet-5","messages":[]}`),
+			Headers: []middleware.KV{
+				{Key: "X-Claude-Code-Agent-Id", Value: "agent-9"},
+				{Key: "X-Claude-Code-Parent-Agent-Id", Value: "agent-7"},
+			},
+		})
+		require.NoError(t, err)
+
+		agent, _ := metaValue(t, out.Metadata, middleware.KeyLLMAgentID)
+		assert.Equal(t, "agent-9", agent)
+		parent, ok := metaValue(t, out.Metadata, middleware.KeyLLMParentAgentID)
+		require.True(t, ok, "a nested agent must carry the spawning agent's id")
+		assert.Equal(t, "agent-7", parent)
+	})
+
+	t.Run("absent on a plain request", func(t *testing.T) {
+		out, err := mw.Invoke(context.Background(), &middleware.Input{
+			URL:  "/v1/messages",
+			Body: []byte(`{"model":"claude-sonnet-5","messages":[]}`),
+		})
+		require.NoError(t, err)
+
+		_, ok := metaValue(t, out.Metadata, middleware.KeyLLMAgentID)
+		assert.False(t, ok, "no key is emitted when the client sends no agent id")
+	})
+}

proxy/internal/middleware/builtin/llm_router/bedrock_route_test.go

@@ -1,9 +1,13 @@
 package llm_router
 
 import (
+	"context"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/proxy/internal/middleware"
 )
 
 // TestRouteClaimsModel_BedrockNormalizesCandidate guards the fix for the native
@@ -28,3 +32,86 @@ func TestRouteClaimsModel_BedrockNormalizesCandidate(t *testing.T) {
 	assert.False(t, routeClaimsModel(openai, "us.gpt-4o"),
 		"non-Bedrock routes must not strip a us. prefix")
 }
+
+// TestRouter_BedrockCountTokensRoutes pins that the token-counting action
+// reaches the Bedrock route instead of denying as not-routable.
+func TestRouter_BedrockCountTokensRoutes(t *testing.T) {
+	mw := New(Config{Providers: []ProviderRoute{{
+		ID:              "bedrock-prod",
+		Bedrock:         true,
+		Models:          []string{"anthropic.claude-sonnet-4-5"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "bedrock-runtime.eu-central-1.amazonaws.com",
+	}}})
+
+	in := newInputWithModelAndURL("anthropic.claude-sonnet-4-5",
+		"/model/anthropic.claude-sonnet-4-5-20250929-v1:0/count-tokens")
+	in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "bedrock"})
+
+	out, err := mw.Invoke(context.Background(), in)
+	require.NoError(t, err)
+	require.NotNil(t, out)
+	assert.Equal(t, middleware.DecisionAllow, out.Decision, "count-tokens must route, not deny")
+	require.NotNil(t, out.Mutations)
+	require.NotNil(t, out.Mutations.RewriteUpstream)
+	assert.Equal(t, "bedrock-runtime.eu-central-1.amazonaws.com", out.Mutations.RewriteUpstream.Host)
+}
+
+// TestRouter_BedrockInferenceProfilesRoutes covers the startup lookups a
+// client makes to resolve a configured inference profile. They carry no
+// model, so before they were recognised they denied and wrote a policy
+// rejection into the access log on every session start.
+func TestRouter_BedrockInferenceProfilesRoutes(t *testing.T) {
+	bedrock := ProviderRoute{
+		ID:              "bedrock-prod",
+		Bedrock:         true,
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "bedrock-runtime.eu-central-1.amazonaws.com",
+	}
+	openai := ProviderRoute{
+		ID:              "openai-prod",
+		Models:          []string{"gpt-4o"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "api.openai.com",
+	}
+	mw := New(Config{Providers: []ProviderRoute{openai, bedrock}})
+
+	for _, path := range []string{
+		"/inference-profiles?type=SYSTEM_DEFINED",
+		"/inference-profiles/us.anthropic.claude-sonnet-5",
+	} {
+		out, err := mw.Invoke(context.Background(), newModellessInput(path))
+		require.NoError(t, err)
+		require.NotNil(t, out)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision, "%s must route", path)
+		require.NotNil(t, out.Mutations)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Equal(t, "bedrock-runtime.eu-central-1.amazonaws.com", out.Mutations.RewriteUpstream.Host,
+			"%s must reach the Bedrock provider, not the first authorised one", path)
+
+		nonInference, _ := metaValue(t, out.Metadata, middleware.KeyLLMNonInference)
+		assert.Equal(t, "true", nonInference, "%s carries no model to gate on", path)
+	}
+}
+
+// TestRouter_BedrockNamespacedInferenceProfilesStripsPrefix pins that the
+// optional gateway namespace is removed before the request goes upstream.
+func TestRouter_BedrockNamespacedInferenceProfilesStripsPrefix(t *testing.T) {
+	mw := New(Config{Providers: []ProviderRoute{{
+		ID:              "bedrock-prod",
+		Bedrock:         true,
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "bedrock-runtime.eu-central-1.amazonaws.com",
+	}}})
+
+	out, err := mw.Invoke(context.Background(), newModellessInput("/bedrock/inference-profiles"))
+	require.NoError(t, err)
+	require.NotNil(t, out.Mutations)
+	require.NotNil(t, out.Mutations.RewriteUpstream)
+	assert.Equal(t, "/bedrock", out.Mutations.RewriteUpstream.StripPathPrefix,
+		"the namespace prefix must not reach the real Bedrock endpoint")
+}

proxy/internal/middleware/builtin/llm_router/middleware.go

@@ -109,6 +109,10 @@ func (m *Middleware) MetadataKeys() []string {
 		middleware.KeyLLMAuthorisingGroups,
 		middleware.KeyLLMPolicyDecision,
 		middleware.KeyLLMPolicyReason,
+		middleware.KeyLLMNonInference,
+		// Emitted only for the per-model lookup, whose model lives in the path
+		// rather than a body the parser could read.
+		middleware.KeyLLMModel,
 	}
 }
 
@@ -137,29 +141,26 @@ const (
 // known to a provider that no policy authorises for the caller deny
 // with no_authorised_provider.
 func (m *Middleware) Invoke(_ context.Context, in *middleware.Input) (*middleware.Output, error) {
+	reqPath := requestPath(in.URL)
+	// The caller's API dialect, used to mirror a denial in the vendor's own
+	// error shape so the client can explain it to the user.
+	surface, _ := lookupMetadata(in.Metadata, middleware.KeyLLMProvider)
+	model, _ := lookupMetadata(in.Metadata, middleware.KeyLLMModel)
+
 	// Vertex AI carries the model in the URL path, not the body, and is
 	// selected by path rather than by the model/vendor table. Route it before
 	// the model lookup so a model the parser extracted from the path can't be
 	// claimed by a same-vendor direct provider (e.g. claude-* on api.anthropic.com).
-	reqPath := requestPath(in.URL)
 	if isVertexPath(reqPath) {
-		model, _ := lookupMetadata(in.Metadata, middleware.KeyLLMModel)
 		// The request parser emits no llm.provider for a Vertex publisher it
 		// can't parse (e.g. google/gemini). Forwarding such a request would
 		// bypass token/budget metering, so deny it rather than serve it
 		// unmetered.
-		if vendor, _ := lookupMetadata(in.Metadata, middleware.KeyLLMProvider); vendor == "" {
-			return denyUnmeterable(), nil
+		if surface == "" {
+			return denyUnmeterable(surface), nil
 		}
 		route, outcome := m.matchVertex(reqPath, model, in.UserGroups)
-		switch outcome {
-		case matchOutcomeFound:
-			return m.allowWithRoute(route, in.UserGroups), nil
-		case matchOutcomeUnauthorised:
-			return denyNoAuthorisedRoute(model), nil
-		default:
-			return denyUnknownModel(model), nil
-		}
+		return m.decide(route, outcome, surface, model, in.UserGroups, nil), nil
 	}
 
 	// Bedrock likewise carries the model in the URL path (/model/{id}/{action}),
@@ -167,52 +168,120 @@ func (m *Middleware) Invoke(_ context.Context, in *middleware.Input) (*middlewar
 	// before the model lookup; when the prefix is present, strip it from the
 	// forwarded path so the real Bedrock endpoint receives its native path.
 	if isBedrockPath(reqPath) {
-		model, _ := lookupMetadata(in.Metadata, middleware.KeyLLMModel)
 		native, hadPrefix := splitBedrockNamespace(reqPath)
 		route, outcome := m.matchBedrock(native, model, in.UserGroups)
-		switch outcome {
-		case matchOutcomeFound:
-			out := m.allowWithRoute(route, in.UserGroups)
-			if hadPrefix && out.Mutations != nil && out.Mutations.RewriteUpstream != nil {
-				out.Mutations.RewriteUpstream.StripPathPrefix = bedrockNamespacePrefix
+		return m.decide(route, outcome, surface, model, in.UserGroups, func(out *middleware.Output) {
+			if hadPrefix {
+				stripBedrockNamespace(out)
 			}
-			return out, nil
-		case matchOutcomeUnauthorised:
-			return denyNoAuthorisedRoute(model), nil
-		default:
-			return denyUnknownModel(model), nil
-		}
+		}), nil
 	}
 
-	model, ok := lookupMetadata(in.Metadata, middleware.KeyLLMModel)
-	if !ok || model == "" {
-		// Non-inference endpoints (model listing) carry no model but still
-		// need rewriting from the synth placeholder to a real upstream;
-		// clients such as Codex call GET /v1/models at startup to enumerate
-		// availability and read a 403 as "model unavailable".
-		route, outcome := m.matchModelless(requestPath(in.URL), in.UserGroups)
-		switch outcome {
-		case matchOutcomeFound:
-			return m.allowWithRoute(route, in.UserGroups), nil
-		case matchOutcomeUnauthorised:
-			// A recognised model-less endpoint exists but no provider
-			// authorises the caller — deny as an authorisation failure
-			// rather than masking it as a missing model.
-			return denyNoAuthorisedRoute(model), nil
-		default:
-			return denyMissingModel(), nil
-		}
+	// GET /v1/models/{id} carries no body, so no model reaches the router in
+	// metadata — but the path names one, and answering it confirms a model
+	// exists and is reachable. Authorise it against the model table like any
+	// other per-model request, then mark it non-inference so it still skips
+	// the token pre-flight it would otherwise charge nothing against.
+	if detail, isDetail := modelDetailID(reqPath); isDetail && isNonInferenceMethod(in.Method) {
+		route, outcome := m.matchRoute(detail, surface, reqPath, in.UserGroups)
+		return m.decide(route, outcome, surface, detail, in.UserGroups, func(out *middleware.Output) {
+			markNonInference(out)
+			// The parser reads models from JSON bodies only, and this request
+			// has none, so stamp the one the path names. Without it the
+			// guardrail's own allowlist — a separate, possibly narrower list
+			// than the route's — never sees a model to check.
+			out.Metadata = append(out.Metadata, middleware.KV{Key: middleware.KeyLLMModel, Value: detail})
+		}), nil
 	}
 
-	vendor, _ := lookupMetadata(in.Metadata, middleware.KeyLLMProvider)
-	route, outcome := m.matchRoute(model, vendor, requestPath(in.URL), in.UserGroups)
+	if model == "" {
+		return m.routeModelless(reqPath, surface, in.Method, in.UserGroups), nil
+	}
+
+	route, outcome := m.matchRoute(model, surface, reqPath, in.UserGroups)
+	return m.decide(route, outcome, surface, model, in.UserGroups, nil), nil
+}
+
+// decide turns a per-model match result into the middleware's decision. Every
+// surface that routes by model shares the same two denial arms — a model no
+// route claims is not routable, one that some route claims but none authorises
+// for this caller is an authorisation failure — so they live here once.
+// decorate, when non-nil, adjusts the allow with whatever that surface needs.
+func (m *Middleware) decide(
+	route ProviderRoute,
+	outcome matchOutcome,
+	surface, model string,
+	userGroups []string,
+	decorate func(*middleware.Output),
+) *middleware.Output {
 	switch outcome {
 	case matchOutcomeFound:
-		return m.allowWithRoute(route, in.UserGroups), nil
+		out := m.allowWithRoute(route, surface, userGroups)
+		if decorate != nil {
+			decorate(out)
+		}
+		return out
 	case matchOutcomeUnauthorised:
-		return denyNoAuthorisedRoute(model), nil
+		return denyNoAuthorisedRoute(surface, model)
 	default:
-		return denyUnknownModel(model), nil
+		return denyUnknownModel(surface, model)
+	}
+}
+
+// routeModelless serves the endpoints that name no model at all: the model
+// listing, the connection-warming probe, and the Bedrock inference-profile
+// lookup. They still need rewriting from the synth placeholder to a real
+// upstream — clients such as Codex call GET /v1/models at startup to enumerate
+// availability and read a 403 as "model unavailable".
+func (m *Middleware) routeModelless(reqPath, surface, method string, userGroups []string) *middleware.Output {
+	route, outcome := m.matchModelless(reqPath, method, userGroups)
+	switch outcome {
+	case matchOutcomeFound:
+		out := m.allowWithRoute(route, surface, userGroups)
+		markNonInference(out)
+		if _, hadPrefix := splitBedrockNamespace(reqPath); hadPrefix {
+			stripBedrockNamespace(out)
+		}
+		// A route that enumerates its models bounds what the caller may use,
+		// so the picker must not offer the rest: every entry outside the list
+		// is a request the chain will deny.
+		if reqPath == modelListingPath && len(route.Models) > 0 &&
+			out.Mutations != nil && out.Mutations.RewriteUpstream != nil {
+			out.Mutations.RewriteUpstream.DiscoveryModels = append([]string(nil), route.Models...)
+		}
+		return out
+	case matchOutcomeUnauthorised:
+		// A recognised model-less endpoint exists but no provider authorises
+		// the caller — deny as an authorisation failure rather than masking it
+		// as a missing model.
+		return denyNoAuthorisedRoute(surface, "")
+	default:
+		return denyMissingModel(surface)
+	}
+}
+
+// isNonInferenceMethod reports whether a request method is one the
+// non-inference endpoints actually use: the listing and the per-model lookup
+// are GET, the connection-warming probe is HEAD or GET. The method is the only
+// thing separating "GET /v1/models/{id}" from a POST to the same path carrying
+// an inference body, and the non-inference mark exempts a request from the
+// token pre-flight — so anything else falls through to normal per-model
+// routing, which denies when the request names no model.
+func isNonInferenceMethod(method string) bool {
+	return method == http.MethodGet || method == http.MethodHead
+}
+
+// markNonInference tags an allow as a request that spends no tokens, so the
+// limit check skips the management pre-flight it would charge nothing against.
+func markNonInference(out *middleware.Output) {
+	out.Metadata = append(out.Metadata, middleware.KV{Key: middleware.KeyLLMNonInference, Value: "true"})
+}
+
+// stripBedrockNamespace tells the rewrite to drop the optional "/bedrock"
+// gateway namespace so the upstream receives its native Bedrock path.
+func stripBedrockNamespace(out *middleware.Output) {
+	if out.Mutations != nil && out.Mutations.RewriteUpstream != nil {
+		out.Mutations.RewriteUpstream.StripPathPrefix = bedrockNamespacePrefix
 	}
 }
 
@@ -300,12 +369,60 @@ func (m *Middleware) matchRoute(model, vendor, reqPath string, userGroups []stri
 	return best, matchOutcomeFound
 }
 
-// isModelLessPath reports whether reqPath is a known OpenAI-shaped
-// non-inference endpoint that legitimately carries no model in its
-// request (the model-listing endpoints). These must route to an upstream
-// rather than deny, so model enumeration works end to end.
+// connectionWarmPath is the probe Anthropic clients send before their first
+// inference request to open the upstream connection early. Forwarding it
+// warms the connection the request will actually use; denying it only fills
+// the access log with rejections at every session start.
+const connectionWarmPath = "/api/hello"
+
+// modelListingPath is the endpoint clients read at startup to populate
+// their model picker. Its response is a list the proxy can bound; the
+// per-model "/v1/models/{id}" lookup returns a single object and is left
+// alone.
+const modelListingPath = "/v1/models"
+
+// isModelLessPath reports whether reqPath is a known non-inference endpoint
+// that legitimately carries no model at all: the model listing and the
+// connection-warming probe. These must route to an upstream rather than
+// deny, so model enumeration works end to end. The per-model
+// "/v1/models/{id}" lookup is deliberately excluded — it names a model, so
+// it is authorised against the model table instead (see modelDetailID).
 func isModelLessPath(reqPath string) bool {
-	return reqPath == "/v1/models" || strings.HasPrefix(reqPath, "/v1/models/")
+	return reqPath == modelListingPath || reqPath == connectionWarmPath
+}
+
+// modelDetailID returns the model id named by a "/v1/models/{id}" lookup.
+// reqPath comes from url.URL.Path, which is already percent-decoded, so an
+// id carrying a "/" (a self-hosted "Qwen/Qwen2.5-0.5B-Instruct" sent as
+// "Qwen%2FQwen2.5-...") arrives whole and everything after the prefix is the
+// id, separators included.
+func modelDetailID(reqPath string) (string, bool) {
+	if !strings.HasPrefix(reqPath, modelListingPath+"/") {
+		return "", false
+	}
+	id := strings.TrimPrefix(reqPath, modelListingPath+"/")
+	if id == "" {
+		return "", false
+	}
+	return id, true
+}
+
+// isBedrockModelLessPath reports whether reqPath is a Bedrock
+// inference-profile lookup, optionally behind the "/bedrock" gateway
+// namespace. Clients read these at startup to resolve a configured profile
+// to its underlying model. They carry no model of their own, so they route
+// by path to a Bedrock provider rather than through the model table.
+//
+// On native AWS these live on the control plane ("bedrock.<region>") while a
+// provider's upstream is normally the runtime host ("bedrock-runtime.<region>"),
+// so forwarding yields a 404 there. That is deliberate: a client has one base
+// URL, so pointing it straight at the runtime host 404s identically, and
+// forwarding keeps the proxy transparent instead of inventing a policy denial
+// the client would never otherwise see. Operators whose Bedrock upstream is a
+// gateway that does serve the lookup get a working answer.
+func isBedrockModelLessPath(reqPath string) bool {
+	native, _ := splitBedrockNamespace(reqPath)
+	return native == "/inference-profiles" || strings.HasPrefix(native, "/inference-profiles/")
 }
 
 // isVertexPath reports whether reqPath is a Google Vertex AI publisher
@@ -332,20 +449,33 @@ func splitBedrockNamespace(reqPath string) (string, bool) {
 	return reqPath, false
 }
 
+// bedrockActions are the runtime actions that follow the model id in a
+// Bedrock path. count-tokens is here so a client can price its context
+// against the dedicated endpoint; denying it pushes that work back onto
+// the inference endpoint, which bills for it.
+var bedrockActions = []string{
+	"/invoke",
+	"/invoke-with-response-stream",
+	"/converse",
+	"/converse-stream",
+	"/count-tokens",
+}
+
 // isBedrockPath reports whether reqPath is an AWS Bedrock runtime model
-// endpoint: /model/{modelId}/{action} where action is invoke,
-// invoke-with-response-stream, converse, or converse-stream — optionally behind
-// a "/bedrock" gateway-namespace prefix. The model lives in the path, so these
-// requests are routed by path to the Bedrock provider.
+// endpoint: /model/{modelId}/{action} — optionally behind a "/bedrock"
+// gateway-namespace prefix. The model lives in the path, so these requests
+// are routed by path to the Bedrock provider.
 func isBedrockPath(reqPath string) bool {
 	native, _ := splitBedrockNamespace(reqPath)
 	if !strings.HasPrefix(native, "/model/") {
 		return false
 	}
-	return strings.HasSuffix(native, "/invoke") ||
-		strings.HasSuffix(native, "/invoke-with-response-stream") ||
-		strings.HasSuffix(native, "/converse") ||
-		strings.HasSuffix(native, "/converse-stream")
+	for _, action := range bedrockActions {
+		if strings.HasSuffix(native, action) {
+			return true
+		}
+	}
+	return false
 }
 
 // matchVertex selects the Vertex provider authorised for the caller's groups
@@ -425,19 +555,26 @@ func (m *Middleware) matchPathRoute(reqPath, model string, userGroups []string,
 // declaration order), matchOutcomeUnauthorised when no provider authorises
 // the caller, or matchOutcomeUnknownModel when the path isn't a recognised
 // model-less endpoint.
-func (m *Middleware) matchModelless(reqPath string, userGroups []string) (ProviderRoute, matchOutcome) {
-	if !isModelLessPath(reqPath) {
+func (m *Middleware) matchModelless(reqPath, method string, userGroups []string) (ProviderRoute, matchOutcome) {
+	if !isNonInferenceMethod(method) {
 		return ProviderRoute{}, matchOutcomeUnknownModel
 	}
-	var candidates []ProviderRoute
-	for _, route := range m.cfg.Providers {
+	var eligible func(ProviderRoute) bool
+	switch {
+	case isBedrockModelLessPath(reqPath):
+		eligible = func(r ProviderRoute) bool { return r.Bedrock }
+	case isModelLessPath(reqPath):
 		// Vertex/Bedrock are path-routed and don't serve OpenAI-style
 		// model-listing endpoints; including them here could rewrite a
 		// GET /v1/models to an upstream that 404s it.
-		if route.Vertex || route.Bedrock {
-			continue
-		}
-		if routeAuthorisesGroups(route, userGroups) {
+		eligible = func(r ProviderRoute) bool { return !r.Vertex && !r.Bedrock }
+	default:
+		return ProviderRoute{}, matchOutcomeUnknownModel
+	}
+
+	var candidates []ProviderRoute
+	for _, route := range m.cfg.Providers {
+		if eligible(route) && routeAuthorisesGroups(route, userGroups) {
 			candidates = append(candidates, route)
 		}
 	}
@@ -564,6 +701,16 @@ func routeClaimsModel(route ProviderRoute, model string) bool {
 		if route.Bedrock && llm.NormalizeBedrockModel(candidate) == model {
 			return true
 		}
+		// A client may pin a dated Anthropic id ("claude-sonnet-4-5-20250929")
+		// where the operator registered the undated one. Only an undated
+		// registration absorbs a dated request: normalising both sides would
+		// let a route pinned to one dated release claim a different one, so an
+		// operator who deliberately pinned a build would silently serve
+		// another — and with several such routes, ordering would decide which.
+		if candidate == llm.NormalizeAnthropicModel(candidate) &&
+			candidate == llm.NormalizeAnthropicModel(model) {
+			return true
+		}
 	}
 	return false
 }
@@ -612,7 +759,7 @@ func requestPath(raw string) string {
 // provider id so identity-stamping middlewares (llm_identity_inject)
 // tag the request with ONLY the groups that authorised this specific
 // route — not every group the peer happens to be in.
-func (m *Middleware) allowWithRoute(route ProviderRoute, userGroups []string) *middleware.Output {
+func (m *Middleware) allowWithRoute(route ProviderRoute, surface string, userGroups []string) *middleware.Output {
 	rewrite := &middleware.UpstreamRewrite{
 		Scheme: route.UpstreamScheme,
 		Host:   route.UpstreamHost,
@@ -634,7 +781,7 @@ func (m *Middleware) allowWithRoute(route ProviderRoute, userGroups []string) *m
 		// request time (cached + auto-refreshed) instead of a static value.
 		bearer, err := m.gcpBearer(route.GCPServiceAccountKeyB64)
 		if err != nil {
-			return denyUpstreamAuth()
+			return denyUpstreamAuth(surface)
 		}
 		authValue = bearer
 	}
@@ -704,11 +851,12 @@ func (m *Middleware) gcpTokenSource(saKeyB64 string) (oauth2.TokenSource, error)
 // denyUpstreamAuth is returned when the router cannot obtain the upstream
 // credential (e.g. a malformed service-account key or an unreachable token
 // endpoint). It surfaces as a 502 — an upstream problem, not a policy denial.
-func denyUpstreamAuth() *middleware.Output {
+func denyUpstreamAuth(surface string) *middleware.Output {
 	return &middleware.Output{
 		Decision:   middleware.DecisionDeny,
 		DenyStatus: 502,
 		DenyReason: &middleware.DenyReason{
+			Surface: surface,
 			Code:    denyCodeUpstreamAuth,
 			Message: "could not obtain upstream credential",
 		},
@@ -722,11 +870,12 @@ func denyUpstreamAuth() *middleware.Output {
 // denyUnmeterable returns the deny envelope for a path-routed request whose
 // publisher has no parser surface, so its usage can't be metered. Serving it
 // would bypass token/budget caps, so it is rejected with a 403.
-func denyUnmeterable() *middleware.Output {
+func denyUnmeterable(surface string) *middleware.Output {
 	return &middleware.Output{
 		Decision:   middleware.DecisionDeny,
 		DenyStatus: 403,
 		DenyReason: &middleware.DenyReason{
+			Surface: surface,
 			Code:    denyCodeUnmeterable,
 			Message: "request publisher is not supported for metering",
 		},
@@ -739,11 +888,12 @@ func denyUnmeterable() *middleware.Output {
 
 // denyMissingModel returns the deny envelope for a request whose
 // envelope has no llm.model metadata.
-func denyMissingModel() *middleware.Output {
+func denyMissingModel(surface string) *middleware.Output {
 	return &middleware.Output{
 		Decision:   middleware.DecisionDeny,
 		DenyStatus: 403,
 		DenyReason: &middleware.DenyReason{
+			Surface: surface,
 			Code:    denyCodeNotRoutable,
 			Message: "missing llm.model on request envelope",
 		},
@@ -756,11 +906,12 @@ func denyMissingModel() *middleware.Output {
 
 // denyUnknownModel returns the deny envelope for a model that no
 // configured provider claims.
-func denyUnknownModel(model string) *middleware.Output {
+func denyUnknownModel(surface, model string) *middleware.Output {
 	return &middleware.Output{
 		Decision:   middleware.DecisionDeny,
 		DenyStatus: 403,
 		DenyReason: &middleware.DenyReason{
+			Surface: surface,
 			Code:    denyCodeNotRoutable,
 			Message: fmt.Sprintf("no provider configured for model %s", model),
 			Details: map[string]string{"model": model},
@@ -775,11 +926,12 @@ func denyUnknownModel(model string) *middleware.Output {
 // denyNoAuthorisedRoute returns the deny envelope for a model that one
 // or more providers claim, but where no policy authorises the caller's
 // groups for any of those providers.
-func denyNoAuthorisedRoute(model string) *middleware.Output {
+func denyNoAuthorisedRoute(surface, model string) *middleware.Output {
 	return &middleware.Output{
 		Decision:   middleware.DecisionDeny,
 		DenyStatus: 403,
 		DenyReason: &middleware.DenyReason{
+			Surface: surface,
 			Code:    denyCodeNoAuthorisedRoute,
 			Message: fmt.Sprintf("no policy authorises model %s for the caller's groups", model),
 			Details: map[string]string{"model": model},

proxy/internal/middleware/builtin/llm_router/middleware_test.go

@@ -2,6 +2,7 @@ package llm_router
 
 import (
 	"context"
+	"net/http"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -60,6 +61,8 @@ func TestMiddlewareIdentity(t *testing.T) {
 		[]string{
 			middleware.KeyLLMResolvedProviderID,
 			middleware.KeyLLMAuthorisingGroups,
+			middleware.KeyLLMNonInference,
+			middleware.KeyLLMModel,
 			middleware.KeyLLMPolicyDecision,
 			middleware.KeyLLMPolicyReason,
 		},
@@ -171,8 +174,12 @@ func TestRouter_MissingModel(t *testing.T) {
 // from which a model could be parsed). UserGroups matches defaultTestGroup.
 func newModellessInput(reqURL string) *middleware.Input {
 	return &middleware.Input{
-		Slot:       middleware.SlotOnRequest,
-		URL:        reqURL,
+		Slot: middleware.SlotOnRequest,
+		URL:  reqURL,
+		// The non-inference endpoints are read requests; the method is what
+		// separates them from an inference body posted to the same path, so
+		// state it rather than leaning on the zero value.
+		Method:     http.MethodGet,
 		UserGroups: []string{defaultTestGroup},
 	}
 }
@@ -197,6 +204,12 @@ func TestRouter_ModelLessPath_RoutesToAuthorisedProvider(t *testing.T) {
 
 	provider, _ := metaValue(t, out.Metadata, middleware.KeyLLMResolvedProviderID)
 	assert.Equal(t, "openai-prod", provider, "resolved provider must be the authorised route")
+
+	// The limits gate reads this to tell "no model applies here" from
+	// "the model could not be determined", which fails closed.
+	nonInference, ok := metaValue(t, out.Metadata, middleware.KeyLLMNonInference)
+	require.True(t, ok, "model-less allow must mark the request non-inference")
+	assert.Equal(t, "true", nonInference)
 }
 
 func TestRouter_ModelLessPath_MultiProviderDeclarationOrder(t *testing.T) {
@@ -873,3 +886,262 @@ func TestRouter_EmptyModelsClaimsAnyModel(t *testing.T) {
 	resolved, _ := metaValue(t, out.Metadata, middleware.KeyLLMResolvedProviderID)
 	assert.Equal(t, "litellm", resolved)
 }
+
+// TestRouter_DatedAnthropicModelRoutes covers a client pinning a release
+// date on a model the operator registered undated. Exact matches still win,
+// so an operator who registers both dated releases keeps them distinct.
+func TestRouter_DatedAnthropicModelRoutes(t *testing.T) {
+	mw := New(Config{Providers: []ProviderRoute{{
+		ID:              "anthropic-prod",
+		Vendor:          "anthropic",
+		Models:          []string{"claude-sonnet-4-5"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "api.anthropic.com",
+	}}})
+
+	in := newInputWithModelAndURL("claude-sonnet-4-5-20250929", "/v1/messages")
+	in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "anthropic"})
+
+	out, err := mw.Invoke(context.Background(), in)
+	require.NoError(t, err)
+	require.NotNil(t, out)
+	assert.Equal(t, middleware.DecisionAllow, out.Decision, "a dated id must route to the undated registration")
+	require.NotNil(t, out.Mutations)
+	require.NotNil(t, out.Mutations.RewriteUpstream)
+	assert.Equal(t, "api.anthropic.com", out.Mutations.RewriteUpstream.Host)
+}
+
+// TestRouter_ConnectionWarmProbeRoutes covers the HEAD /api/hello probe an
+// Anthropic client sends before its first request. Forwarding it warms the
+// connection that request will use; denying it only wrote a rejection into
+// the access log at every session start.
+func TestRouter_ConnectionWarmProbeRoutes(t *testing.T) {
+	mw := New(Config{Providers: []ProviderRoute{{
+		ID:              "anthropic-prod",
+		Vendor:          "anthropic",
+		Models:          []string{"claude-sonnet-5"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "api.anthropic.com",
+	}}})
+
+	in := newModellessInput("/api/hello")
+	in.Method = http.MethodHead
+
+	out, err := mw.Invoke(context.Background(), in)
+	require.NoError(t, err)
+	require.NotNil(t, out)
+	assert.Equal(t, middleware.DecisionAllow, out.Decision, "the warm-up probe must reach the upstream")
+	require.NotNil(t, out.Mutations)
+	require.NotNil(t, out.Mutations.RewriteUpstream)
+	assert.Equal(t, "api.anthropic.com", out.Mutations.RewriteUpstream.Host)
+
+	nonInference, _ := metaValue(t, out.Metadata, middleware.KeyLLMNonInference)
+	assert.Equal(t, "true", nonInference, "the probe carries no model to gate on")
+}
+
+// TestRouter_ModelListingCarriesAuthorisedModels pins the list the proxy
+// bounds the discovery response with. A catch-all route enumerates nothing,
+// so it must not bound the upstream's list at all.
+func TestRouter_ModelListingCarriesAuthorisedModels(t *testing.T) {
+	enumerated := ProviderRoute{
+		ID:              "anthropic-prod",
+		Models:          []string{"claude-sonnet-5", "claude-haiku-4-5"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "api.anthropic.com",
+	}
+
+	t.Run("enumerated route bounds the listing", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{enumerated}})
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models"))
+		require.NoError(t, err)
+		require.NotNil(t, out.Mutations)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Equal(t, []string{"claude-sonnet-5", "claude-haiku-4-5"},
+			out.Mutations.RewriteUpstream.DiscoveryModels,
+			"the picker must be bounded by what the route authorises")
+	})
+
+	t.Run("catch-all route leaves the listing alone", func(t *testing.T) {
+		catchAll := enumerated
+		catchAll.Models = nil
+		mw := New(Config{Providers: []ProviderRoute{catchAll}})
+
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models"))
+		require.NoError(t, err)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Empty(t, out.Mutations.RewriteUpstream.DiscoveryModels,
+			"a route that claims every model cannot bound the upstream's list")
+	})
+
+	t.Run("per-model lookup is not a listing", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{enumerated}})
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models/claude-sonnet-5"))
+		require.NoError(t, err)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Empty(t, out.Mutations.RewriteUpstream.DiscoveryModels,
+			"the single-object lookup has no data array to filter")
+	})
+}
+
+// TestRouter_ModelDetailHonoursAllowlist pins that GET /v1/models/{id} is
+// authorised against the model table. It carries no body model, so treating
+// it as a model-less endpoint would let a caller confirm a model the route
+// does not list — the listing itself is bounded to the allowlist, so the
+// detail lookup must be too.
+func TestRouter_ModelDetailHonoursAllowlist(t *testing.T) {
+	enumerated := ProviderRoute{
+		ID:              "anthropic-prod",
+		Models:          []string{"claude-sonnet-5"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "api.anthropic.com",
+	}
+
+	t.Run("allowlisted model routes and skips metering", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{enumerated}})
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models/claude-sonnet-5"))
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision)
+		require.NotNil(t, out.Mutations)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Equal(t, "api.anthropic.com", out.Mutations.RewriteUpstream.Host)
+
+		nonInference, _ := metaValue(t, out.Metadata, middleware.KeyLLMNonInference)
+		assert.Equal(t, "true", nonInference, "a detail lookup spends no tokens")
+	})
+
+	t.Run("model outside the allowlist denies", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{enumerated}})
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models/claude-opus-5"))
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionDeny, out.Decision,
+			"a model no route lists must not be confirmed by the detail lookup")
+	})
+
+	t.Run("dated id matches its undated registration", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{enumerated}})
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models/claude-sonnet-5-20250929"))
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision,
+			"a pinned release of an allowlisted family stays reachable")
+	})
+
+	t.Run("catch-all route still answers every lookup", func(t *testing.T) {
+		catchAll := enumerated
+		catchAll.Models = nil
+		mw := New(Config{Providers: []ProviderRoute{catchAll}})
+
+		out, err := mw.Invoke(context.Background(), newModellessInput("/v1/models/anything-at-all"))
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision,
+			"a gateway that enumerates nothing cannot refuse a lookup")
+	})
+}
+
+// TestRouter_NonInferenceRequiresReadMethod pins that the non-inference mark —
+// which exempts a request from the token pre-flight — is reachable only by the
+// read methods these endpoints actually use. A POST to the same path could
+// carry an inference body, so it must not buy the exemption; it falls through
+// to normal per-model routing instead, which denies when no model is named.
+func TestRouter_NonInferenceRequiresReadMethod(t *testing.T) {
+	route := ProviderRoute{
+		ID:              "gateway",
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "gateway.example.com",
+	}
+
+	for _, path := range []string{"/v1/models", "/v1/models/claude-sonnet-5", "/api/hello"} {
+		t.Run("POST "+path, func(t *testing.T) {
+			mw := New(Config{Providers: []ProviderRoute{route}})
+
+			in := newModellessInput(path)
+			in.Method = http.MethodPost
+
+			out, err := mw.Invoke(context.Background(), in)
+			require.NoError(t, err)
+			assert.Equal(t, middleware.DecisionDeny, out.Decision,
+				"a write to a non-inference path must not route unmetered")
+
+			nonInference, _ := metaValue(t, out.Metadata, middleware.KeyLLMNonInference)
+			assert.NotEqual(t, "true", nonInference,
+				"only a read method may skip the token pre-flight")
+		})
+	}
+
+	t.Run("HEAD keeps the warm probe working", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{route}})
+
+		in := newModellessInput(connectionWarmPath)
+		in.Method = http.MethodHead
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision,
+			"the HEAD warm probe must still reach the upstream")
+
+		nonInference, _ := metaValue(t, out.Metadata, middleware.KeyLLMNonInference)
+		assert.Equal(t, "true", nonInference,
+			"the HEAD warm probe carries no model to meter")
+	})
+}
+
+// TestRouter_PinnedDatedModelStaysDistinct pins that a route registered
+// against one dated Anthropic release does not claim another. Normalising
+// both sides of the comparison made every dated build of a family
+// interchangeable, so an operator who deliberately pinned a build would have
+// served a different one — and with several such routes, declaration or path
+// order would have decided which.
+func TestRouter_PinnedDatedModelStaysDistinct(t *testing.T) {
+	pinned := ProviderRoute{
+		ID:              "anthropic-pinned",
+		Vendor:          "anthropic",
+		Models:          []string{"claude-sonnet-4-5-20250101"},
+		AllowedGroupIDs: []string{defaultTestGroup},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "pinned.example.com",
+	}
+
+	t.Run("a different dated release is not claimed", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{pinned}})
+		in := newInputWithModelAndURL("claude-sonnet-4-5-20250202", "/v1/messages")
+		in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "anthropic"})
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionDeny, out.Decision,
+			"a route pinned to one dated build must not serve another")
+	})
+
+	t.Run("its own dated release still routes", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{pinned}})
+		in := newInputWithModelAndURL("claude-sonnet-4-5-20250101", "/v1/messages")
+		in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "anthropic"})
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		assert.Equal(t, middleware.DecisionAllow, out.Decision, "the exact match must still route")
+	})
+
+	t.Run("two pinned builds each route to their own provider", func(t *testing.T) {
+		other := pinned
+		other.ID = "anthropic-pinned-newer"
+		other.Models = []string{"claude-sonnet-4-5-20250202"}
+		other.UpstreamHost = "newer.example.com"
+		mw := New(Config{Providers: []ProviderRoute{pinned, other}})
+
+		in := newInputWithModelAndURL("claude-sonnet-4-5-20250202", "/v1/messages")
+		in.Metadata = append(in.Metadata, middleware.KV{Key: middleware.KeyLLMProvider, Value: "anthropic"})
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		require.Equal(t, middleware.DecisionAllow, out.Decision)
+		require.NotNil(t, out.Mutations)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Equal(t, "newer.example.com", out.Mutations.RewriteUpstream.Host,
+			"declaration order must not decide between two deliberately pinned builds")
+	})
+}

proxy/internal/middleware/decision.go

@@ -11,11 +11,78 @@ var codeRegex = regexp.MustCompile(`^[a-z][a-z0-9._-]{0,63}$`)
 // denyResponse is the on-wire shape rendered by RenderDenyResponse.
 // Keeping this as a typed struct ensures we never leak
 // middleware-supplied bytes outside known fields.
+//
+// Type and Error mirror the denial in the vendor's own error shape when
+// the request reached a known LLM surface. LLM clients only parse their
+// provider's envelope, so without the mirror a budget stop reaches the
+// user as an unexplained API error. The NetBird fields stay where they
+// were, so the body is a superset and existing consumers are unaffected.
 type denyResponse struct {
 	Code       string            `json:"code"`
 	Message    string            `json:"message,omitempty"`
 	Details    map[string]string `json:"details,omitempty"`
 	Middleware string            `json:"middleware,omitempty"`
+	Type       string            `json:"type,omitempty"`
+	Error      *providerError    `json:"error,omitempty"`
+}
+
+// providerError is the nested error object both vendor envelopes carry.
+type providerError struct {
+	Type    string `json:"type"`
+	Message string `json:"message,omitempty"`
+	Code    string `json:"code,omitempty"`
+}
+
+// Vendor error types keyed by HTTP status, per each provider's published
+// error reference.
+const (
+	anthropicErrInvalidRequest = "invalid_request_error"
+	anthropicErrPermission     = "permission_error"
+	anthropicErrRateLimit      = "rate_limit_error"
+	anthropicErrAPI            = "api_error"
+	openAIErrInvalidRequest    = "invalid_request_error"
+	openAIErrRateLimit         = "rate_limit_error"
+)
+
+// providerEnvelope returns the vendor-shaped mirror for a denial on the
+// given surface, or nil when the surface has no envelope we can speak.
+// message is the already-redacted public message.
+func providerEnvelope(surface, code, message string, status int) (string, *providerError) {
+	switch surface {
+	case "anthropic":
+		return "error", &providerError{
+			Type:    anthropicErrorType(status),
+			Message: message,
+		}
+	case "openai":
+		return "", &providerError{
+			Type:    openAIErrorType(status),
+			Message: message,
+			Code:    code,
+		}
+	default:
+		return "", nil
+	}
+}
+
+func anthropicErrorType(status int) string {
+	switch status {
+	case http.StatusForbidden:
+		return anthropicErrPermission
+	case http.StatusTooManyRequests:
+		return anthropicErrRateLimit
+	case http.StatusBadRequest:
+		return anthropicErrInvalidRequest
+	default:
+		return anthropicErrAPI
+	}
+}
+
+func openAIErrorType(status int) string {
+	if status == http.StatusTooManyRequests {
+		return openAIErrRateLimit
+	}
+	return openAIErrInvalidRequest
 }
 
 // RenderDenyResponse writes a structured JSON deny body. Status is
@@ -36,6 +103,7 @@ func RenderDenyResponse(w http.ResponseWriter, middlewareID string, reason *Deny
 		Message:    truncate(Scan(reason.Message), 256),
 		Middleware: truncate(Scan(middlewareID), 64),
 	}
+	resp.Type, resp.Error = providerEnvelope(reason.Surface, resp.Code, resp.Message, status)
 	if n := len(reason.Details); n > 0 {
 		resp.Details = make(map[string]string, min(n, 8))
 		for k, v := range reason.Details {

proxy/internal/middleware/decision_test.go

@@ -0,0 +1,92 @@
+package middleware
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// decodeDeny renders a denial and returns the parsed body plus the status.
+func decodeDeny(t *testing.T, reason *DenyReason, status int) (map[string]any, int) {
+	t.Helper()
+	rec := httptest.NewRecorder()
+	RenderDenyResponse(rec, "llm_limit_check", reason, status)
+
+	var body map[string]any
+	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &body), "deny body must be valid JSON")
+	return body, rec.Code
+}
+
+// TestRenderDeny_AnthropicSurfaceMirrorsVendorShape covers a budget stop
+// reaching Claude Code. The client only parses the Anthropic envelope, so
+// without the mirror the user sees an unexplained API error instead of the
+// reason their request was refused.
+func TestRenderDeny_AnthropicSurfaceMirrorsVendorShape(t *testing.T) {
+	body, status := decodeDeny(t, &DenyReason{
+		Code:    "llm_policy.budget_cap_exceeded",
+		Message: "LLM policy limit exceeded",
+		Surface: "anthropic",
+	}, http.StatusForbidden)
+
+	assert.Equal(t, http.StatusForbidden, status)
+	assert.Equal(t, "error", body["type"], "Anthropic errors carry type=error at the top level")
+
+	errObj, ok := body["error"].(map[string]any)
+	require.True(t, ok, "error must be an object")
+	assert.Equal(t, "permission_error", errObj["type"], "403 maps to permission_error")
+	assert.Equal(t, "LLM policy limit exceeded", errObj["message"])
+
+	// The NetBird fields stay put so existing consumers keep working.
+	assert.Equal(t, "llm_policy.budget_cap_exceeded", body["code"])
+	assert.Equal(t, "LLM policy limit exceeded", body["message"])
+	assert.Equal(t, "llm_limit_check", body["middleware"])
+}
+
+// TestRenderDeny_OpenAISurfaceMirrorsVendorShape pins the OpenAI envelope,
+// which nests the code and carries no top-level type.
+func TestRenderDeny_OpenAISurfaceMirrorsVendorShape(t *testing.T) {
+	body, _ := decodeDeny(t, &DenyReason{
+		Code:    "llm_policy.model_blocked",
+		Message: "model is not in the policy allowlist",
+		Surface: "openai",
+	}, http.StatusForbidden)
+
+	assert.NotContains(t, body, "type", "OpenAI errors have no top-level type")
+
+	errObj, ok := body["error"].(map[string]any)
+	require.True(t, ok, "error must be an object")
+	assert.Equal(t, "invalid_request_error", errObj["type"])
+	assert.Equal(t, "llm_policy.model_blocked", errObj["code"], "the NetBird code rides in the vendor code field")
+	assert.Equal(t, "model is not in the policy allowlist", errObj["message"])
+}
+
+// TestRenderDeny_RateLimitStatusMapsToVendorRateLimit pins the mapping a
+// client's backoff keys on.
+func TestRenderDeny_RateLimitStatusMapsToVendorRateLimit(t *testing.T) {
+	body, status := decodeDeny(t, &DenyReason{
+		Code:    "llm_policy.token_cap_exceeded",
+		Message: "LLM policy limit exceeded",
+		Surface: "anthropic",
+	}, http.StatusTooManyRequests)
+
+	assert.Equal(t, http.StatusTooManyRequests, status, "429 must survive the status clamp")
+	errObj := body["error"].(map[string]any)
+	assert.Equal(t, "rate_limit_error", errObj["type"])
+}
+
+// TestRenderDeny_NoSurfaceKeepsLegacyShape guards non-LLM middlewares and
+// denials raised before a surface is known.
+func TestRenderDeny_NoSurfaceKeepsLegacyShape(t *testing.T) {
+	body, _ := decodeDeny(t, &DenyReason{
+		Code:    "llm_policy.model_not_routable",
+		Message: "no provider configured for model x",
+	}, http.StatusForbidden)
+
+	assert.NotContains(t, body, "type", "no surface means no vendor mirror")
+	assert.NotContains(t, body, "error", "no surface means no vendor mirror")
+	assert.Equal(t, "llm_policy.model_not_routable", body["code"])
+}

proxy/internal/middleware/keys.go

@@ -22,6 +22,15 @@ const (
 	// body. Empty for clients that don't send one.
 	KeyLLMSessionID = "llm.session_id"
 
+	// Sub-agent attribution (emitted by llm_request_parser from the
+	// client's request headers). A coding agent that spawns helpers
+	// stamps the spawned agent's id, and the spawning agent's id when
+	// the helper is itself nested, so cost within one session can be
+	// split across the agents that ran in parallel. These identify an
+	// agent, not a person or a device: never treat them as a user id.
+	KeyLLMAgentID       = "llm.agent_id"
+	KeyLLMParentAgentID = "llm.parent_agent_id"
+
 	// LLM response-side metadata (emitted by llm_response_parser).
 	//nolint:gosec // metadata key name, not a credential
 	KeyLLMInputTokens = "llm.input_tokens"
@@ -66,6 +75,14 @@ const (
 	// downstream gateways' spend logs.
 	KeyLLMAuthorisingGroups = "llm.authorising_groups"
 
+	// LLM non-inference marker (emitted by llm_router on the allow path
+	// for endpoints that legitimately carry no model, such as model
+	// listing). The router still authorises these against the caller's
+	// groups; the marker only tells the limits gate that a per-model
+	// allowlist has nothing to evaluate, so an empty model must not be
+	// read as an undetermined one. Never derived from client input.
+	KeyLLMNonInference = "llm.non_inference"
+
 	// LLM policy attribution (emitted by llm_limit_check on the allow
 	// path). Names the policy that paid for this request and the
 	// dimension counters the post-flight llm_limit_record middleware

proxy/internal/middleware/types.go

@@ -179,6 +179,12 @@ type DenyReason struct {
 	Code    string
 	Message string
 	Details map[string]string
+	// Surface names the LLM API dialect the caller speaks (the
+	// llm.provider value), so the rendered body can mirror the denial in
+	// that vendor's error shape alongside the NetBird fields. Empty for
+	// non-LLM middlewares and for denials raised before a surface was
+	// resolved; the body then carries the NetBird fields alone.
+	Surface string
 }
 
 // Output is the value each middleware returns to the dispatcher. The
@@ -247,6 +253,12 @@ type UpstreamRewrite struct {
 	// without verifying its TLS certificate. Set by llm_router from the
 	// provider's skip_tls_verification for self-hosted / internal gateways.
 	SkipTLSVerify bool
+	// DiscoveryModels, when non-empty, is the set of model ids the resolved
+	// route authorises, and the proxy drops everything else from the
+	// model-listing response. Empty leaves the upstream's list untouched,
+	// which is what a route that claims every model wants. Set by
+	// llm_router on a model-listing request only.
+	DiscoveryModels []string
 }
 
 // AuthHeader is a single name/value pair the proxy injects on the

proxy/internal/proxy/discovery_filter.go

@@ -0,0 +1,215 @@
+package proxy
+
+import (
+	"bytes"
+	"encoding/json"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+
+	sharedllm "github.com/netbirdio/netbird/shared/llm"
+)
+
+// maxDiscoveryBodyBytes bounds the model-listing response the filter will
+// buffer. A listing is a few kilobytes of ids; anything larger is not a
+// listing we recognise, and buffering it to rewrite would cost more than
+// the filtering is worth.
+const maxDiscoveryBodyBytes = 1 << 20
+
+// modelDiscoveryFilter returns a ModifyResponse hook that drops models the
+// caller's policy does not authorise from a model-listing response, then
+// delegates to next (which may be nil).
+//
+// Clients populate their model picker from this endpoint, so an unfiltered
+// list offers models the very next request denies. The filter is
+// best-effort: a response it cannot safely rewrite passes through
+// untouched rather than reaching the client corrupted.
+func modelDiscoveryFilter(allowed []string, next func(*http.Response) error) func(*http.Response) error {
+	permitted := make(map[string]struct{}, len(allowed)*2)
+	for _, id := range allowed {
+		permitted[id] = struct{}{}
+		permitted[sharedllm.NormalizeAnthropicModel(id)] = struct{}{}
+	}
+
+	return func(resp *http.Response) error {
+		if err := filterModelListing(resp, permitted); err != nil {
+			return err
+		}
+		if next == nil {
+			return nil
+		}
+		return next(resp)
+	}
+}
+
+// filterModelListing rewrites the response body in place, keeping only the
+// entries whose id the policy authorises. Responses that are not a plain
+// JSON listing are left alone.
+func filterModelListing(resp *http.Response, permitted map[string]struct{}) error {
+	if !isPlainJSONListing(resp) {
+		return nil
+	}
+
+	// One byte past the cap, so an oversized body is detectable without
+	// buffering all of it.
+	body, err := io.ReadAll(io.LimitReader(resp.Body, maxDiscoveryBodyBytes+1))
+	if err != nil {
+		_ = resp.Body.Close()
+		return err
+	}
+	if len(body) > maxDiscoveryBodyBytes {
+		// Too large to filter. Put the bytes already read back in front of the
+		// unread remainder and forward the response exactly as the upstream
+		// sent it, headers included. Buffering what was read and closing here
+		// would truncate the body at the cap and hand the client a short,
+		// invalid listing — worse than not filtering at all.
+		resp.Body = spliceBody(body, resp.Body)
+		return nil
+	}
+	if err := resp.Body.Close(); err != nil {
+		return err
+	}
+
+	filtered, ok := filterListingBody(body, permitted)
+	if !ok {
+		restoreBody(resp, body)
+		return nil
+	}
+	restoreBody(resp, filtered)
+	return nil
+}
+
+// isPlainJSONListing reports whether the response is a JSON body the filter
+// can parse. A content-encoded body is skipped: the transport only
+// transparently decompresses what it negotiated itself, and the client
+// negotiates its own encoding on this request.
+func isPlainJSONListing(resp *http.Response) bool {
+	if resp == nil || resp.Body == nil {
+		return false
+	}
+	if resp.StatusCode != http.StatusOK {
+		return false
+	}
+	if enc := resp.Header.Get("Content-Encoding"); enc != "" && !strings.EqualFold(enc, "identity") {
+		return false
+	}
+	return strings.Contains(strings.ToLower(resp.Header.Get("Content-Type")), "application/json")
+}
+
+// filterListingBody returns the listing with unauthorised entries removed.
+// ok is false when the body is not a listing shape, in which case the
+// caller must forward the original bytes.
+func filterListingBody(body []byte, permitted map[string]struct{}) ([]byte, bool) {
+	var doc map[string]json.RawMessage
+	if err := json.Unmarshal(body, &doc); err != nil {
+		return nil, false
+	}
+	raw, present := doc["data"]
+	if !present {
+		return nil, false
+	}
+	var entries []map[string]json.RawMessage
+	if err := json.Unmarshal(raw, &entries); err != nil {
+		return nil, false
+	}
+
+	kept := make([]map[string]json.RawMessage, 0, len(entries))
+	for _, entry := range entries {
+		if entryPermitted(entry, permitted) {
+			kept = append(kept, entry)
+		}
+	}
+
+	encoded, err := json.Marshal(kept)
+	if err != nil {
+		return nil, false
+	}
+	doc["data"] = encoded
+	out, err := json.Marshal(doc)
+	if err != nil {
+		return nil, false
+	}
+	return out, true
+}
+
+// entryPermitted reports whether a listing entry names a model the policy
+// authorises, trying every form the same model is written in.
+func entryPermitted(entry map[string]json.RawMessage, permitted map[string]struct{}) bool {
+	raw, ok := entry["id"]
+	if !ok {
+		return false
+	}
+	var id string
+	if err := json.Unmarshal(raw, &id); err != nil {
+		return false
+	}
+	for _, candidate := range modelIDForms(id) {
+		if _, ok := permitted[candidate]; ok {
+			return true
+		}
+	}
+	return false
+}
+
+// gatewayNamespaces are the provider prefixes a gateway prepends to a model
+// it re-exports: LiteLLM lists a Bedrock model the operator registered as
+// "anthropic.claude-opus-5" under "bedrock/anthropic.claude-opus-5". Only
+// these are stripped before matching.
+//
+// A slash is not by itself a namespace separator. Self-hosted backends ship
+// ids that carry one ("Qwen/Qwen2.5-0.5B-Instruct"), and an upstream is free
+// to scope ids per tenant ("tenant-b/claude-sonnet-5"). Treating every slash
+// as a prefix let any such id match an allowed model by its tail, so the
+// picker offered models the policy never named.
+var gatewayNamespaces = map[string]struct{}{
+	"anthropic": {},
+	"azure":     {},
+	"bedrock":   {},
+	"mistral":   {},
+	"openai":    {},
+	"vertex_ai": {},
+}
+
+// modelIDForms returns the forms a single model id may be written in: the id
+// itself, its undated form, and — when the id is namespaced by a gateway we
+// recognise — the same two with that namespace removed
+// ("vertex_ai/claude-sonnet-5"). The bare id is always tried first.
+//
+// The namespace is what precedes the FIRST slash: it is a prefix the gateway
+// put in front of the whole id, and everything after it is the id the
+// operator would have registered, separators included.
+func modelIDForms(id string) []string {
+	if id == "" {
+		return nil
+	}
+	forms := []string{id, sharedllm.NormalizeAnthropicModel(id)}
+	if slash := strings.Index(id, "/"); slash > 0 {
+		if _, ok := gatewayNamespaces[id[:slash]]; ok {
+			tail := id[slash+1:]
+			forms = append(forms, tail, sharedllm.NormalizeAnthropicModel(tail))
+		}
+	}
+	return forms
+}
+
+// restoreBody puts body back on the response and fixes the length headers
+// so the client reads exactly what is there.
+// spliceBody returns a ReadCloser that yields prefix followed by whatever is
+// left in rest, closing rest when closed. It lets the filter put back bytes it
+// consumed while deciding, without owning the rest of the stream.
+func spliceBody(prefix []byte, rest io.ReadCloser) io.ReadCloser {
+	return struct {
+		io.Reader
+		io.Closer
+	}{
+		Reader: io.MultiReader(bytes.NewReader(prefix), rest),
+		Closer: rest,
+	}
+}
+
+func restoreBody(resp *http.Response, body []byte) {
+	resp.Body = io.NopCloser(bytes.NewReader(body))
+	resp.ContentLength = int64(len(body))
+	resp.Header.Set("Content-Length", strconv.Itoa(len(body)))
+}

proxy/internal/proxy/discovery_filter_test.go

@@ -0,0 +1,235 @@
+package proxy
+
+import (
+	"bytes"
+	"encoding/json"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// jsonListingResponse builds a 200 model-listing response with the given
+// body, as an upstream would return it.
+func jsonListingResponse(body string) *http.Response {
+	resp := &http.Response{
+		StatusCode:    http.StatusOK,
+		Header:        http.Header{},
+		Body:          io.NopCloser(strings.NewReader(body)),
+		ContentLength: int64(len(body)),
+	}
+	resp.Header.Set("Content-Type", "application/json")
+	return resp
+}
+
+// listedIDs runs the filter and returns the ids left in the response.
+func listedIDs(t *testing.T, allowed []string, body string) []string {
+	t.Helper()
+	resp := jsonListingResponse(body)                            //nolint:bodyclose // in-memory body, replaced by the filter
+	require.NoError(t, modelDiscoveryFilter(allowed, nil)(resp)) //nolint:bodyclose // in-memory body, replaced by the filter
+
+	raw, err := io.ReadAll(resp.Body)
+	require.NoError(t, err)
+
+	var doc struct {
+		Data []struct {
+			ID string `json:"id"`
+		} `json:"data"`
+	}
+	require.NoError(t, json.Unmarshal(raw, &doc), "filtered body must stay valid JSON")
+
+	ids := make([]string, 0, len(doc.Data))
+	for _, entry := range doc.Data {
+		ids = append(ids, entry.ID)
+	}
+	return ids
+}
+
+// TestModelDiscoveryFilter_KeepsOnlyAuthorisedModels covers the picker a
+// developer sees: an unfiltered upstream list offers every model the shared
+// key can reach, and each one the policy excludes is a request the chain
+// denies a moment later.
+func TestModelDiscoveryFilter_KeepsOnlyAuthorisedModels(t *testing.T) {
+	ids := listedIDs(t, []string{"claude-sonnet-5", "claude-haiku-4-5"}, `{
+		"data": [
+			{"id": "claude-opus-5", "display_name": "Claude Opus 5"},
+			{"id": "claude-sonnet-5", "display_name": "Claude Sonnet 5"},
+			{"id": "claude-haiku-4-5"}
+		],
+		"has_more": false
+	}`)
+
+	assert.Equal(t, []string{"claude-sonnet-5", "claude-haiku-4-5"}, ids,
+		"only the models the route authorises may reach the picker")
+}
+
+// TestModelDiscoveryFilter_MatchesDatedAndPrefixedIDs pins the two id forms
+// a gateway returns for a model the operator registered plainly.
+func TestModelDiscoveryFilter_MatchesDatedAndPrefixedIDs(t *testing.T) {
+	ids := listedIDs(t, []string{"claude-sonnet-4-5", "anthropic.claude-opus-5"}, `{
+		"data": [
+			{"id": "claude-sonnet-4-5-20250929"},
+			{"id": "bedrock/anthropic.claude-opus-5"},
+			{"id": "gpt-4o"}
+		]
+	}`)
+
+	assert.Equal(t, []string{"claude-sonnet-4-5-20250929", "bedrock/anthropic.claude-opus-5"}, ids,
+		"a dated or provider-prefixed id must match its registered form")
+}
+
+// TestModelDiscoveryFilter_PreservesEnvelopeFields guards the rest of the
+// document: clients read paging fields alongside data.
+func TestModelDiscoveryFilter_PreservesEnvelopeFields(t *testing.T) {
+	resp := jsonListingResponse(`{"data":[{"id":"claude-sonnet-5"}],"has_more":true,"first_id":"x"}`) //nolint:bodyclose // in-memory body, replaced by the filter
+	require.NoError(t, modelDiscoveryFilter([]string{"claude-sonnet-5"}, nil)(resp))                  //nolint:bodyclose // in-memory body, replaced by the filter
+
+	raw, err := io.ReadAll(resp.Body)
+	require.NoError(t, err)
+
+	var doc map[string]any
+	require.NoError(t, json.Unmarshal(raw, &doc))
+	assert.Equal(t, true, doc["has_more"], "paging fields must survive the rewrite")
+	assert.Equal(t, "x", doc["first_id"])
+	assert.Equal(t, strconv.Itoa(len(raw)), resp.Header.Get("Content-Length"),
+		"Content-Length must match the rewritten body")
+}
+
+// TestModelDiscoveryFilter_PassesThroughUnfilterable covers the responses
+// the filter must not touch: a compressed body it cannot parse, a non-JSON
+// body, an error status, and a document with no data array.
+func TestModelDiscoveryFilter_PassesThroughUnfilterable(t *testing.T) {
+	cases := map[string]func() *http.Response{
+		"compressed": func() *http.Response {
+			resp := jsonListingResponse(`{"data":[{"id":"gpt-4o"}]}`)
+			resp.Header.Set("Content-Encoding", "gzip")
+			return resp
+		},
+		"not json": func() *http.Response {
+			resp := jsonListingResponse(`{"data":[{"id":"gpt-4o"}]}`)
+			resp.Header.Set("Content-Type", "text/html")
+			return resp
+		},
+		"error status": func() *http.Response {
+			resp := jsonListingResponse(`{"data":[{"id":"gpt-4o"}]}`)
+			resp.StatusCode = http.StatusInternalServerError
+			return resp
+		},
+		"no data array": func() *http.Response {
+			return jsonListingResponse(`{"object":"list"}`)
+		},
+	}
+
+	for name, build := range cases {
+		t.Run(name, func(t *testing.T) {
+			resp := build() //nolint:bodyclose // in-memory body, replaced by the filter
+			original, err := io.ReadAll(resp.Body)
+			require.NoError(t, err)
+			resp.Body = io.NopCloser(bytes.NewReader(original))
+
+			require.NoError(t, modelDiscoveryFilter([]string{"claude-sonnet-5"}, nil)(resp)) //nolint:bodyclose // in-memory body, replaced by the filter
+
+			got, err := io.ReadAll(resp.Body)
+			require.NoError(t, err)
+			assert.Equal(t, string(original), string(got), "an unfilterable response must reach the client unchanged")
+		})
+	}
+}
+
+// TestModelDiscoveryFilter_RunsNextHook pins that an existing
+// ModifyResponse hook still runs after filtering.
+func TestModelDiscoveryFilter_RunsNextHook(t *testing.T) {
+	called := false
+	next := func(*http.Response) error {
+		called = true
+		return nil
+	}
+
+	resp := jsonListingResponse(`{"data":[{"id":"claude-sonnet-5"}]}`)                //nolint:bodyclose // in-memory body, replaced by the filter
+	require.NoError(t, modelDiscoveryFilter([]string{"claude-sonnet-5"}, next)(resp)) //nolint:bodyclose // in-memory body, replaced by the filter
+	assert.True(t, called, "the chained hook must still run")
+}
+
+// TestModelDiscoveryFilter_KeepsSlashBearingIDs covers self-hosted backends
+// whose model ids carry a slash of their own. Treating the slash as a
+// gateway prefix and keeping only the tail dropped every such model from
+// the picker even though the policy named it exactly.
+func TestModelDiscoveryFilter_KeepsSlashBearingIDs(t *testing.T) {
+	ids := listedIDs(t, []string{"Qwen/Qwen2.5-0.5B-Instruct"}, `{
+		"object": "list",
+		"data": [
+			{"id": "Qwen/Qwen2.5-0.5B-Instruct"},
+			{"id": "Qwen/Qwen2.5-7B-Instruct"}
+		]
+	}`)
+
+	assert.Equal(t, []string{"Qwen/Qwen2.5-0.5B-Instruct"}, ids,
+		"a slash inside the model id is part of the id, not a provider prefix")
+}
+
+// TestModelDiscoveryFilter_RejectsTailMatchOnUnknownNamespace covers the id
+// an upstream scopes with a prefix of its own. "tenant-b/claude-sonnet-5"
+// ends in a model the policy permits, but it is a different model on a
+// different tenant, and the guardrail denies that string outright — so
+// offering it hands the picker an entry the next request refuses.
+func TestModelDiscoveryFilter_RejectsTailMatchOnUnknownNamespace(t *testing.T) {
+	ids := listedIDs(t, []string{"claude-sonnet-5"}, `{
+		"data": [
+			{"id": "claude-sonnet-5"},
+			{"id": "tenant-b/claude-sonnet-5"},
+			{"id": "Qwen/claude-sonnet-5"}
+		]
+	}`)
+
+	assert.Equal(t, []string{"claude-sonnet-5"}, ids,
+		"only a namespace a gateway is known to prepend may be stripped before matching")
+}
+
+// TestModelDiscoveryFilter_ForwardsOversizedBodyIntact covers a listing past
+// the buffering cap. The filter reads one byte beyond the cap to detect the
+// size; forwarding only what it read would hand the client a body truncated
+// at exactly 1 MiB — valid-looking, short, and unparseable as JSON. The bytes
+// already read must be spliced back in front of the unread remainder so the
+// response reaches the client exactly as the upstream sent it.
+func TestModelDiscoveryFilter_ForwardsOversizedBodyIntact(t *testing.T) {
+	// A well-formed listing whose single entry pads the body past the cap.
+	padding := strings.Repeat("x", maxDiscoveryBodyBytes)
+	body := `{"object":"list","data":[{"id":"gpt-4o","note":"` + padding + `"}]}`
+	require.Greater(t, len(body), maxDiscoveryBodyBytes+1,
+		"the fixture must exceed the cap by more than the one-byte probe")
+
+	resp := jsonListingResponse(body)                        //nolint:bodyclose // in-memory body
+	require.NoError(t, modelDiscoveryFilter(nil, nil)(resp)) //nolint:bodyclose // in-memory body
+
+	got, err := io.ReadAll(resp.Body)
+	require.NoError(t, err)
+	assert.Equal(t, len(body), len(got),
+		"an oversized listing must reach the client whole, not truncated at the cap")
+	assert.Equal(t, body, string(got), "the forwarded bytes must be the upstream's own")
+
+	var doc map[string]json.RawMessage
+	assert.NoError(t, json.Unmarshal(got, &doc),
+		"the forwarded body must still parse as JSON")
+}
+
+// TestModelDiscoveryFilter_OversizedBodyKeepsUpstreamHeaders pins that the
+// oversized path leaves the response metadata alone. Rewriting Content-Length
+// to the truncated prefix is what made the corruption invisible to the client
+// until it tried to parse.
+func TestModelDiscoveryFilter_OversizedBodyKeepsUpstreamHeaders(t *testing.T) {
+	padding := strings.Repeat("x", maxDiscoveryBodyBytes)
+	body := `{"object":"list","data":[{"id":"gpt-4o","note":"` + padding + `"}]}`
+
+	resp := jsonListingResponse(body) //nolint:bodyclose // in-memory body
+	resp.Header.Set("Content-Length", strconv.Itoa(len(body)))
+	require.NoError(t, modelDiscoveryFilter(nil, nil)(resp)) //nolint:bodyclose // in-memory body
+
+	assert.Equal(t, int64(len(body)), resp.ContentLength,
+		"ContentLength must keep describing the body the client receives")
+	assert.Equal(t, strconv.Itoa(len(body)), resp.Header.Get("Content-Length"),
+		"the Content-Length header must not be rewritten to the truncated prefix")
+}

proxy/internal/proxy/reverseproxy.go

@@ -363,6 +363,9 @@ func (p *ReverseProxy) forwardUpstream(respWriter http.ResponseWriter, r *http.R
 	if result.rewriteRedirects {
 		rp.ModifyResponse = p.rewriteLocationFunc(effectiveURL, rewriteMatchedPath, r) //nolint:bodyclose
 	}
+	if upstreamRewrite != nil && len(upstreamRewrite.DiscoveryModels) > 0 {
+		rp.ModifyResponse = modelDiscoveryFilter(upstreamRewrite.DiscoveryModels, rp.ModifyResponse) //nolint:bodyclose // the hook replaces the body and closes the original
+	}
 	rp.ServeHTTP(respWriter, r.WithContext(ctx))
 }
 

proxy/server.go

@@ -2074,9 +2074,17 @@ func (s *Server) updateMapping(ctx context.Context, mapping *proto.ProxyMapping)
 		return fmt.Errorf("auth setup for domain %s: %w", mapping.GetDomain(), err)
 	}
 	m := s.protoToMapping(ctx, mapping)
-	s.proxy.AddMapping(m)
+	// The chain is published before the route that leads to it. A request
+	// arriving at a target whose chain has not been rebuilt yet is served
+	// straight through, so a provider update that added the route first left a
+	// window in which an inference could complete unrouted and unmetered.
+	// Rebuilding first inverts that: the worst a request in the window meets is
+	// the new chain in front of the previous target, which is still counted.
+	if err := s.rebuildMiddlewareChains(svcID, m); err != nil {
+		return err
+	}
 	s.meter.AddMapping(m)
-	s.rebuildMiddlewareChains(svcID, m)
+	s.proxy.AddMapping(m)
 	return nil
 }
 
@@ -2114,15 +2122,21 @@ func (s *Server) initMiddlewareManager(ctx context.Context) error {
 }
 
 // rebuildMiddlewareChains converts m into per-path bindings and calls
-// Manager.Rebuild. Short-circuits when the middleware manager is unset.
-func (s *Server) rebuildMiddlewareChains(svcID types.ServiceID, m proxy.Mapping) {
+// Manager.Rebuild. Short-circuits when the middleware manager is unset, which
+// is a deployment without middleware rather than a failure to install it.
+//
+// A rebuild that fails is reported rather than logged: the caller publishes
+// the route once this returns, and a route published over chains that were
+// not installed serves requests with no policy enforcement and no metering.
+func (s *Server) rebuildMiddlewareChains(svcID types.ServiceID, m proxy.Mapping) error {
 	if s.middlewareManager == nil {
-		return
+		return nil
 	}
 	bindings := buildMiddlewareBindings(svcID, m)
 	if err := s.middlewareManager.Rebuild(string(svcID), bindings); err != nil {
-		s.Logger.WithError(err).WithField("service_id", svcID).Error("failed to rebuild middleware chains")
+		return fmt.Errorf("rebuild middleware chains for service %s: %w", svcID, err)
 	}
+	return nil
 }
 
 // isLiveService reports whether svcID is currently present in the live