[proxy,management] Bound model discovery to the caller's own policies (#7239)

[proxy,management] Bound model discovery to the caller's own policies GET /v1/models was bounded by the provider record's enumerated models, which is the right bound only while a single policy reaches a provider. Where two teams share one provider under different allowlists, every caller was offered the union — each model outside their own policy being a request the guardrail refuses a moment later. A gateway record enumerating nothing was worse: it offered the upstream's entire catalogue however narrow the policy was. Each route now carries one rule per authorising policy — its source groups and the models it permits — instead of a single flattened list. At request time the router keeps the rules whose groups intersect the caller's, unions their models, and intersects that with what the provider serves. nil and [] stay distinct end to end: a policy setting no allowlist reaches the router as nil and lifts the restriction for the groups it binds, while an enabled allowlist with no models arrives as [] and permits nothing. Collapsing them would let a listing that should offer nothing fall open to everything. The guardrail's own per-provider allowlist is untouched. It is a fail-closed backstop that cannot tell who is asking, so discovery is now narrower than the backstop rather than wider.
2026-08-24 16:41:30 +02:00 · 2026-08-23 20:13:35 +02:00
parent 766fcae3f8
commit 7be45c2dd8
9 changed files with 993 additions and 25 deletions
--- a/e2e/agentnetwork/custom_pricing_test.go
+++ b/e2e/agentnetwork/custom_pricing_test.go
@@ -174,7 +174,12 @@ func chatOnce(t *testing.T, ctx context.Context, env pricedEnv, model, sessionID

 // accessLogIngestWindow is how long a single request's access-log row is given
 // to appear before the caller gives up on it.
-const accessLogIngestWindow = 30 * time.Second
+// accessLogIngestWindow bounds how long a row may take to appear after its
+// request returned. The proxy streams each entry to management with a 10s send
+// timeout of its own, so a request whose send hits one full timeout and is
+// retried has not yet missed anything real — 30s left barely three send
+// attempts of headroom and lost the race on a loaded runner.
+const accessLogIngestWindow = 60 * time.Second

 // accessLogPollInterval is how long the lookup waits between pages. Ingest is
 // asynchronous, so the row lands somewhere inside the window rather than on
--- a/e2e/agentnetwork/discovery_live_test.go
+++ b/e2e/agentnetwork/discovery_live_test.go
@@ -0,0 +1,400 @@
+//go:build e2e
+
+package agentnetwork
+
+import (
+	"context"
+	"encoding/json"
+	"os"
+	"sort"
+	"strconv"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/e2e/harness"
+	sharedllm "github.com/netbirdio/netbird/shared/llm"
+	"github.com/netbirdio/netbird/shared/management/http/api"
+)
+
+// TestLiveModelDiscovery drives model discovery against the REAL vendor
+// endpoints — OpenAI, Anthropic, Bedrock and Vertex — rather than the mock.
+//
+// The mock upstream proves the filter's mechanics: it advertises ids we chose,
+// so a listing narrowing to the ones we authorised is arithmetic we already
+// controlled both sides of. What it cannot prove is that the filter survives
+// contact with a real catalogue — ids we never enumerated, dated builds whose
+// suffix the vendor picks, surfaces that answer a listing request with
+// something other than a listing. That is what this covers, and it is the part
+// a QA engineer would otherwise have to walk through by hand.
+//
+// One proxy serves every case. Each provider gets its own group, policy and
+// client, because a model-less request matches exactly ONE route
+// (matchModelless): with two providers authorised for the same caller, the
+// listing would go to whichever won the tiebreak and the other would go
+// untested. Group-scoping the caller makes each provider the only candidate
+// for its own client.
+func TestLiveModelDiscovery(t *testing.T) {
+	cases := liveDiscoveryCases()
+	if len(cases) == 0 {
+		t.Skip("no provider keys set; source ~/.llm-keys to run live model discovery")
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Minute)
+	defer cancel()
+
+	t.Logf("[discovery] live matrix: %s", strings.Join(caseNames(cases), ", "))
+
+	// Provision every provider, group and policy before the proxy starts: the
+	// proxy takes a configuration snapshot at connect time and does not
+	// reconcile provider changes made afterwards.
+	keys := make(map[string]string, len(cases))
+	for i := range cases {
+		keys[cases[i].name] = provisionLiveDiscovery(t, ctx, &cases[i])
+	}
+
+	endpoint, firstIP, firstClient, px := connectClient(t, ctx, "disc-live", keys[cases[0].name])
+	clients := map[string]*harness.Client{cases[0].name: firstClient}
+	ips := map[string]string{cases[0].name: firstIP}
+	for _, tc := range cases[1:] {
+		cl := joinClient(t, ctx, px, endpoint, keys[tc.name])
+		ip, err := cl.ResolveProxyIP(ctx, endpoint)
+		require.NoError(t, err, "resolve endpoint from the %s client", tc.name)
+		clients[tc.name] = cl
+		ips[tc.name] = ip
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			runLiveDiscoveryCase(t, ctx, tc, clients[tc.name], endpoint, ips[tc.name])
+		})
+	}
+}
+
+// discoveryOutcome is what a discovery request must produce end to end. The
+// three are genuinely different contracts, not degrees of success: only the
+// first puts a bounded listing in front of the caller.
+type discoveryOutcome int
+
+const (
+	// outcomeFiltered: the proxy routes the request and bounds the response to
+	// what the caller may use.
+	outcomeFiltered discoveryOutcome = iota
+	// outcomeDenied: no provider of this shape can serve the surface, so the
+	// proxy refuses rather than rewriting the request onto an upstream that
+	// would 404 it. The caller gets a NetBird error, not a vendor one.
+	outcomeDenied
+	// outcomeUpstreamNoListing: the proxy routes the request to the configured
+	// upstream, and the vendor does not implement the endpoint there. Proxy
+	// side correct, product side a dead end — see the Bedrock case.
+	outcomeUpstreamNoListing
+)
+
+// liveDiscoveryCase is one provider's discovery surface and what the proxy
+// must make of it.
+type liveDiscoveryCase struct {
+	name      string
+	catalogID string
+	upstream  string
+	apiKey    string
+
+	// path is the discovery endpoint the client calls. Not every surface uses
+	// /v1/models: Bedrock lists inference profiles instead.
+	path string
+	// headers the vendor requires on a bare GET (Anthropic versions its API
+	// through a header, and rejects a request without one).
+	headers []string
+
+	// models the provider record enumerates. Empty models a gateway record,
+	// which enumerates nothing and claims everything.
+	models []string
+	// allowlist, when non-empty, is a guardrail narrowing the policy below the
+	// provider's own enumeration — the second of the two bounds discovery
+	// applies, and the only one a provider record alone cannot demonstrate.
+	allowlist []string
+
+	// outcome is what this surface must produce end to end.
+	outcome discoveryOutcome
+
+	// permitted is every id allowed to survive filtering, in the form the
+	// provider record registers it. A surviving id counts as permitted when it
+	// matches one of these outright or after Anthropic date-normalisation.
+	permitted []string
+	// wantHidden are ids the upstream is known to advertise and the bound must
+	// remove. Only set where we enumerate the model ourselves, so the
+	// expectation cannot rot when a vendor changes its catalogue.
+	wantHidden []string
+}
+
+// liveDiscoveryCases builds the matrix from whichever provider credentials are
+// present, mirroring availableProviders' env-var gating so a partial key set
+// still yields partial coverage.
+func liveDiscoveryCases() []liveDiscoveryCase {
+	var cases []liveDiscoveryCase
+
+	// OpenAI enumerates TWO real models and the policy permits one. That is
+	// the only case here where both bounds are observable at once: the
+	// upstream advertises dozens of ids, the provider record cuts them to two,
+	// and the guardrail cuts those to one.
+	if k := os.Getenv("OPENAI_TOKEN"); k != "" {
+		cases = append(cases, liveDiscoveryCase{
+			name: "openai", catalogID: "openai_api", upstream: "https://api.openai.com", apiKey: k,
+			path:       "/v1/models",
+			models:     []string{"gpt-4o-mini", "gpt-4o"},
+			allowlist:  []string{"gpt-4o-mini"},
+			outcome:    outcomeFiltered,
+			permitted:  []string{"gpt-4o-mini"},
+			wantHidden: []string{"gpt-4o"},
+		})
+	}
+
+	// Anthropic is the surface Claude Code actually calls. Its listing returns
+	// DATED build ids (claude-haiku-4-5-20251001) while the provider record
+	// registers the undated id, so this is the case that proves the filter's
+	// date-normalisation against ids the vendor chose rather than ids we wrote.
+	if k := os.Getenv("ANTHROPIC_TOKEN"); k != "" {
+		cases = append(cases, liveDiscoveryCase{
+			name: "anthropic", catalogID: "anthropic_api", upstream: "https://api.anthropic.com", apiKey: k,
+			path:      "/v1/models",
+			headers:   []string{"anthropic-version: 2023-06-01"},
+			models:    []string{"claude-haiku-4-5"},
+			outcome:   outcomeFiltered,
+			permitted: []string{"claude-haiku-4-5"},
+		})
+	}
+
+	// Bedrock lists inference profiles, not models: matchModelless routes
+	// /inference-profiles to a Bedrock route and refuses /v1/models for one.
+	//
+	// The request reaches AWS and AWS refuses it — bedrock-runtime answers
+	// <UnknownOperationException/>, because ListInferenceProfiles is a CONTROL
+	// PLANE operation served by bedrock.<region>.amazonaws.com, not the runtime
+	// host. A provider record carries one upstream and it has to be the runtime
+	// host for InvokeModel to work, so no Bedrock record can serve a listing as
+	// the model stands today.
+	//
+	// The mock upstream hides this entirely: it answers /inference-profiles on
+	// the same listener as everything else, so the routing test passes there
+	// while the real endpoint 404s. That is the whole reason this file exists,
+	// so the case is kept, asserting what actually happens.
+	if k := os.Getenv("AWS_BEARER_TOKEN_BEDROCK"); k != "" {
+		region := os.Getenv("AWS_REGION")
+		if region == "" {
+			region = "eu-central-1"
+		}
+		model := os.Getenv("AWS_BEDROCK_MODEL")
+		if model == "" {
+			model = "global.anthropic.claude-sonnet-4-6"
+		}
+		cases = append(cases, liveDiscoveryCase{
+			name: "bedrock", catalogID: "bedrock_api",
+			upstream: "https://bedrock-runtime." + region + ".amazonaws.com", apiKey: k,
+			path:    "/inference-profiles",
+			models:  []string{sharedllm.NormalizeAnthropicModel(strings.TrimPrefix(model, "global."))},
+			outcome: outcomeUpstreamNoListing,
+		})
+	}
+
+	// Vertex carries the model in the rawPredict path and serves no listing
+	// endpoint at all, so the proxy must refuse discovery rather than rewrite
+	// it onto an upstream that would 404.
+	if sa := os.Getenv("GOOGLE_VERTEX_SA_BASE64"); sa != "" {
+		if project := os.Getenv("GOOGLE_VERTEX_PROJECT"); project != "" {
+			region := os.Getenv("GOOGLE_VERTEX_REGION")
+			if region == "" {
+				region = "global"
+			}
+			host := "aiplatform.googleapis.com"
+			if region != "global" {
+				host = region + "-aiplatform.googleapis.com"
+			}
+			cases = append(cases, liveDiscoveryCase{
+				name: "vertex", catalogID: "vertex_ai_api", upstream: "https://" + host,
+				apiKey:  "keyfile::" + sa,
+				path:    "/v1/models",
+				outcome: outcomeDenied,
+			})
+		}
+	}
+
+	return cases
+}
+
+// provisionLiveDiscovery creates the group, provider, optional guardrail and
+// policy for one case, and returns the setup key a client joins that group
+// with. Scoping each provider to its own group is what keeps it the only
+// candidate for its own client's model-less request.
+func provisionLiveDiscovery(t *testing.T, ctx context.Context, tc *liveDiscoveryCase) string {
+	t.Helper()
+
+	grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-disc-live-" + tc.name})
+	require.NoError(t, err, "create group for %s", tc.name)
+	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) })
+
+	ephemeral := false
+	sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
+		Name:       "e2e-disc-live-" + tc.name,
+		Type:       "reusable",
+		ExpiresIn:  86400,
+		UsageLimit: 0,
+		AutoGroups: []string{grp.Id},
+		Ephemeral:  &ephemeral,
+	})
+	require.NoError(t, err, "mint setup key for %s", tc.name)
+	require.NotEmpty(t, sk.Key, "setup key plaintext for %s", tc.name)
+
+	req := api.AgentNetworkProviderRequest{
+		Name:        "e2e-disc-live-" + tc.name,
+		ProviderId:  tc.catalogID,
+		UpstreamUrl: tc.upstream,
+		ApiKey:      &tc.apiKey,
+		Enabled:     ptr(true),
+	}
+	if len(tc.models) > 0 {
+		models := make([]api.AgentNetworkProviderModel, 0, len(tc.models))
+		for _, id := range tc.models {
+			models = append(models, api.AgentNetworkProviderModel{Id: id, InputPer1k: 0.001, OutputPer1k: 0.002})
+		}
+		req.Models = &models
+	}
+	prov, err := srv.CreateProvider(ctx, req)
+	require.NoError(t, err, "create provider %s", tc.name)
+	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
+
+	polReq := api.AgentNetworkPolicyRequest{
+		Name:                   "e2e-disc-live-" + tc.name,
+		Enabled:                ptr(true),
+		SourceGroups:           []string{grp.Id},
+		DestinationProviderIds: []string{prov.Id},
+	}
+	if len(tc.allowlist) > 0 {
+		var gr api.AgentNetworkGuardrailRequest
+		gr.Name = "e2e-disc-live-" + tc.name
+		gr.Checks.ModelAllowlist.Enabled = true
+		gr.Checks.ModelAllowlist.Models = tc.allowlist
+		g, gerr := srv.CreateGuardrail(ctx, gr)
+		require.NoError(t, gerr, "create guardrail for %s", tc.name)
+		t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) })
+		polReq.GuardrailIds = &[]string{g.Id}
+	}
+	pol, err := srv.CreatePolicy(ctx, polReq)
+	require.NoError(t, err, "create policy for %s", tc.name)
+	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) })
+
+	return sk.Key
+}
+
+// runLiveDiscoveryCase issues the discovery request and reports everything the
+// vendor said before asserting on any of it. The log is the point on the first
+// run: a live catalogue is the one input we do not control, so a failure has to
+// arrive with the response that caused it rather than just a count.
+func runLiveDiscoveryCase(t *testing.T, ctx context.Context, tc liveDiscoveryCase, cl *harness.Client, endpoint, proxyIP string) {
+	t.Helper()
+
+	// A single request is enough for the two non-listing outcomes, and retrying
+	// them would burn the retry window waiting for a status that is never
+	// coming.
+	if tc.outcome != outcomeFiltered {
+		code, body, err := cl.Get(ctx, endpoint, proxyIP, tc.path, tc.headers)
+		require.NoError(t, err, "request must reach the proxy")
+		t.Logf("[discovery] %s GET %s -> %d; body: %s", tc.name, tc.path, code, truncate(body, 2000))
+		assert.NotEqual(t, 200, code,
+			"%s serves no bounded listing, so a 200 here would mean the caller was handed a picker nothing narrows; body: %s",
+			tc.name, truncate(body, 2000))
+
+		// Which side refused is the whole distinction between these two
+		// outcomes, and a NetBird error is the thing that tells them apart: the
+		// middleware chain stamps its own name on anything it generates.
+		if tc.outcome == outcomeDenied {
+			assert.True(t, isProxyError(body),
+				"%s serves no listing endpoint at all, so the proxy must refuse the request itself rather than forward it to an upstream that would answer for us; body: %s",
+				tc.name, truncate(body, 2000))
+			return
+		}
+		assert.False(t, isProxyError(body),
+			"%s discovery must be routed to the configured upstream and refused by the vendor, not blocked by the proxy; body: %s",
+			tc.name, truncate(body, 2000))
+		return
+	}
+
+	code, body := callUntil(t, func() (int, string, error) {
+		return cl.Get(ctx, endpoint, proxyIP, tc.path, tc.headers)
+	}, 200)
+	t.Logf("[discovery] %s GET %s -> %d; body: %s", tc.name, tc.path, code, truncate(body, 4000))
+	require.Equal(t, 200, code, "%s discovery must be served; body: %s", tc.name, truncate(body, 2000))
+
+	ids, ok := listingIDs(body)
+	require.Truef(t, ok,
+		"%s answered discovery with something other than a {\"data\":[{\"id\":…}]} listing, which the filter forwards untouched — the caller would get an unbounded picker; body: %s",
+		tc.name, truncate(body, 2000))
+	sort.Strings(ids)
+	t.Logf("[discovery] %s: %d ids after filtering: %s", tc.name, len(ids), strings.Join(ids, ", "))
+
+	require.NotEmpty(t, ids, "%s filtered the listing down to nothing; the caller would see an empty picker", tc.name)
+
+	permitted := make(map[string]struct{}, len(tc.permitted)*2)
+	for _, id := range tc.permitted {
+		permitted[id] = struct{}{}
+		permitted[sharedllm.NormalizeAnthropicModel(id)] = struct{}{}
+	}
+	for _, id := range ids {
+		_, direct := permitted[id]
+		_, normalised := permitted[sharedllm.NormalizeAnthropicModel(id)]
+		assert.Truef(t, direct || normalised,
+			"%s offered %q, which no policy on this route permits — every entry the picker shows must be a request the guardrail would allow", tc.name, id)
+	}
+	for _, hidden := range tc.wantHidden {
+		assert.NotContainsf(t, ids, hidden,
+			"%s offered %q, which the provider enumerates but the policy does not permit", tc.name, hidden)
+	}
+}
+
+// isProxyError reports whether a response body was generated by the middleware
+// chain rather than forwarded from a vendor. Every chain-generated error names
+// the middleware that raised it, which no upstream's error body does — so this
+// separates "the proxy refused" from "the proxy routed it and the vendor
+// refused", the two failures that otherwise look alike from the client side.
+func isProxyError(body string) bool {
+	return strings.Contains(body, `"middleware":`)
+}
+
+// listingIDs pulls the model ids out of a listing response. ok is false when
+// the body is not the {"data":[{"id":…}]} shape the filter recognises.
+func listingIDs(body string) ([]string, bool) {
+	var doc struct {
+		Data []struct {
+			ID string `json:"id"`
+		} `json:"data"`
+	}
+	if err := json.Unmarshal([]byte(body), &doc); err != nil {
+		return nil, false
+	}
+	if doc.Data == nil {
+		return nil, false
+	}
+	ids := make([]string, 0, len(doc.Data))
+	for _, entry := range doc.Data {
+		ids = append(ids, entry.ID)
+	}
+	return ids, true
+}
+
+func caseNames(cases []liveDiscoveryCase) []string {
+	names := make([]string, 0, len(cases))
+	for _, c := range cases {
+		names = append(names, c.name)
+	}
+	return names
+}
+
+// truncate bounds a logged response body. A live catalogue can run to tens of
+// kilobytes, and the useful part is the front.
+func truncate(s string, limit int) string {
+	if len(s) <= limit {
+		return s
+	}
+	return s[:limit] + "… (" + strconv.Itoa(len(s)-limit) + " more bytes)"
+}
--- a/e2e/agentnetwork/discovery_multipolicy_test.go
+++ b/e2e/agentnetwork/discovery_multipolicy_test.go
@@ -0,0 +1,170 @@
+//go:build e2e
+
+package agentnetwork
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/e2e/harness"
+	"github.com/netbirdio/netbird/shared/management/http/api"
+)
+
+// TestDiscoveryBoundToCallersPolicies covers a model listing on a provider two
+// teams reach under different allowlists.
+//
+// Bounding the listing by the provider's enumerated models alone is not enough
+// once more than one policy is in play: the caller would be offered every model
+// any team may use, and each one outside their own policy is a request the
+// guardrail refuses a moment later — the empty-or-wrong picker this endpoint
+// exists to avoid, just moved one level up.
+//
+// The client joins the main group only. Both models are enumerated by the same
+// provider and both are advertised by the upstream, so a listing that leaked
+// the other team's model would visibly contain it.
+func TestDiscoveryBoundToCallersPolicies(t *testing.T) {
+	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
+	defer cancel()
+
+	vllm, err := harness.StartVLLM(ctx, srv)
+	require.NoError(t, err, "start mock upstream")
+	t.Cleanup(func() { _ = vllm.Terminate(context.Background()) })
+
+	grpMain, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-disc-mp-main"})
+	require.NoError(t, err, "create main group")
+	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpMain.Id) })
+
+	grpOther, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-disc-mp-other"})
+	require.NoError(t, err, "create other group")
+	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpOther.Id) })
+
+	ephemeral := false
+	mkKey := func(name, groupID string) string {
+		sk, kerr := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
+			Name:       name,
+			Type:       "reusable",
+			ExpiresIn:  86400,
+			UsageLimit: 0,
+			AutoGroups: []string{groupID},
+			Ephemeral:  &ephemeral,
+		})
+		require.NoError(t, kerr, "mint setup key %s", name)
+		require.NotEmpty(t, sk.Key, "setup key plaintext")
+		return sk.Key
+	}
+	// One client per group. The second is what makes the first assertion mean
+	// something: without a client that DOES see the other team's model, its
+	// absence from the main client's listing could equally be a policy that
+	// never propagated.
+	keyMain := mkKey("e2e-disc-mp-main-client", grpMain.Id)
+	keyOther := mkKey("e2e-disc-mp-other-client", grpOther.Id)
+
+	// One provider enumerating both models the upstream advertises, so the
+	// listing is narrowed by policy rather than by what the provider serves.
+	staticKey := "static-e2e-token"
+	prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
+		Name:        "e2e-disc-mp",
+		ProviderId:  "openai_api",
+		UpstreamUrl: vllm.URL,
+		ApiKey:      &staticKey,
+		Enabled:     ptr(true),
+		Models: &[]api.AgentNetworkProviderModel{
+			{Id: harness.VLLMModel, InputPer1k: 0.001, OutputPer1k: 0.001},
+			{Id: harness.VLLMUnlistedModel, InputPer1k: 0.001, OutputPer1k: 0.001},
+		},
+	})
+	require.NoError(t, err, "create provider")
+	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
+
+	mkGuardrail := func(name, model string) api.AgentNetworkGuardrail {
+		var gr api.AgentNetworkGuardrailRequest
+		gr.Name = name
+		gr.Checks.ModelAllowlist.Enabled = true
+		gr.Checks.ModelAllowlist.Models = []string{model}
+		g, gerr := srv.CreateGuardrail(ctx, gr)
+		require.NoError(t, gerr, "create guardrail %s", name)
+		t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) })
+		return g
+	}
+	gMain := mkGuardrail("e2e-disc-mp-main", harness.VLLMModel)
+	gOther := mkGuardrail("e2e-disc-mp-other", harness.VLLMUnlistedModel)
+
+	enabled := true
+	polMain, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
+		Name:                   "e2e-disc-mp-main",
+		Enabled:                &enabled,
+		SourceGroups:           []string{grpMain.Id},
+		DestinationProviderIds: []string{prov.Id},
+		GuardrailIds:           &[]string{gMain.Id},
+	})
+	require.NoError(t, err, "create main policy")
+	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polMain.Id) })
+
+	// The other team's policy, on the same provider, permitting the model the
+	// client must never be offered.
+	polOther, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
+		Name:                   "e2e-disc-mp-other",
+		Enabled:                &enabled,
+		SourceGroups:           []string{grpOther.Id},
+		DestinationProviderIds: []string{prov.Id},
+		GuardrailIds:           &[]string{gOther.Id},
+	})
+	require.NoError(t, err, "create other policy")
+	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polOther.Id) })
+
+	endpoint, proxyIP, clMain, px := connectClient(t, ctx, "disc-mp", keyMain)
+	clOther := joinClient(t, ctx, px, endpoint, keyOther)
+
+	listing := func(t *testing.T, cl *harness.Client, ip string) string {
+		t.Helper()
+		code, body := callUntil(t, func() (int, string, error) {
+			return cl.Get(ctx, endpoint, ip, "/v1/models?limit=1000", nil)
+		}, 200)
+		require.Equal(t, 200, code, "discovery must be served; body: %s", body)
+		return body
+	}
+
+	otherIP, err := clOther.ResolveProxyIP(ctx, endpoint)
+	require.NoError(t, err, "resolve endpoint from the other client")
+
+	// The other team's client first: seeing its own model proves polOther is
+	// live, so the main client's listing is narrowed by policy scoping rather
+	// than by the other policy having failed to apply at all.
+	otherBody := listing(t, clOther, otherIP)
+	assert.Contains(t, otherBody, harness.VLLMUnlistedModel,
+		"the other group's policy must be in force, or this test proves nothing")
+	assert.NotContains(t, otherBody, harness.VLLMModel,
+		"and it must not be offered the main group's model either — isolation runs both ways")
+
+	mainBody := listing(t, clMain, proxyIP)
+	assert.Contains(t, mainBody, harness.VLLMModel,
+		"the model the caller's own policy permits must reach the picker")
+	assert.NotContains(t, mainBody, harness.VLLMUnlistedModel,
+		"a model only another group's policy permits must not be offered to this caller")
+}
+
+// joinClient starts a second tunnel client against an already-running proxy, so
+// a test can drive the same endpoint as two different group memberships without
+// paying for a second proxy.
+func joinClient(t *testing.T, ctx context.Context, px *harness.Proxy, endpoint, setupKey string) *harness.Client {
+	t.Helper()
+
+	cl, err := harness.StartClient(ctx, srv, setupKey)
+	require.NoError(t, err, "start second client")
+	t.Cleanup(func() { _ = cl.Terminate(context.Background()) })
+
+	require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "second client must connect to management")
+	_, err = cl.ResolveProxyIP(ctx, endpoint)
+	require.NoError(t, err, "second client could not resolve the endpoint")
+	// Guarded rather than passed straight to require: px.Logs pulls the whole
+	// proxy container log, which is only worth fetching when the wait failed.
+	if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil {
+		require.NoError(t, err, "second client did not see the proxy peer\n=== proxy logs ===\n%s",
+			px.Logs(context.Background()))
+	}
+	return cl
+}
--- a/e2e/harness/client.go
+++ b/e2e/harness/client.go
@@ -200,12 +200,18 @@ func (cl *Client) pollStatus(ctx context.Context, timeout time.Duration, want st
 const (
 	// curlExitCouldNotResolve is curl's exit code for a DNS resolution failure, distinct from connection-level failures.
 	curlExitCouldNotResolve = 6
-	// dnsProbeRetryWindow bounds DNS-failure retries: the synthesized zone lands a beat after management connects, so early NXDOMAIN is propagation; a zone still absent after this window is a real failure.
-	dnsProbeRetryWindow   = 30 * time.Second
-	dnsProbeRetryInterval = 2 * time.Second
+	// curlExitCouldNotConnect is curl's exit code for a connection that never
+	// established. The probe exists to WAKE the lazy proxy peer, so the first
+	// attempt legitimately arrives before WireGuard has brought the tunnel up
+	// and fails here — which is propagation, exactly like an early NXDOMAIN,
+	// and belongs inside the retry window rather than failing the test outright.
+	curlExitCouldNotConnect = 7
+	// endpointProbeRetryWindow bounds retries of the transient failures above: the synthesized zone and the tunnel both land a beat after management connects. Still failing after this window is a real failure.
+	endpointProbeRetryWindow   = 30 * time.Second
+	endpointProbeRetryInterval = 2 * time.Second
 )

-// ResolveProxyIP GETs https://<endpoint>/ from the client's netns: any HTTP status proves DNS + tunnel and wakes the lazy proxy peer; only DNS failures retry, within dnsProbeRetryWindow. Returns the connected IP for --resolve pinning.
+// ResolveProxyIP GETs https://<endpoint>/ from the client's netns: any HTTP status proves DNS + tunnel and wakes the lazy proxy peer; DNS and connect failures retry, within endpointProbeRetryWindow. Returns the connected IP for --resolve pinning.
 func (cl *Client) ResolveProxyIP(ctx context.Context, endpoint string) (string, error) {
 	args := []string{
 		"run", "--rm",
@@ -216,7 +222,7 @@ func (cl *Client) ResolveProxyIP(ctx context.Context, endpoint string) (string,
 		"-w", "%{remote_ip}",
 		"https://" + endpoint + "/",
 	}
-	deadline := time.Now().Add(dnsProbeRetryWindow)
+	deadline := time.Now().Add(endpointProbeRetryWindow)
 	for {
 		cmd := exec.CommandContext(ctx, "docker", args...)
 		var stdout, stderr strings.Builder
@@ -232,21 +238,29 @@ func (cl *Client) ResolveProxyIP(ctx context.Context, endpoint string) (string,
 		}

 		var exitErr *exec.ExitError
-		if !errors.As(err, &exitErr) || exitErr.ExitCode() != curlExitCouldNotResolve {
+		if !errors.As(err, &exitErr) || !isTransientProbeExit(exitErr.ExitCode()) {
 			return "", fmt.Errorf("no HTTP response from %s: %w (%s)", endpoint, err, strings.TrimSpace(stderr.String()))
 		}
-		dnsErr := fmt.Errorf("DNS resolution failed for %s: %s", endpoint, strings.TrimSpace(stderr.String()))
-		if time.Until(deadline) < dnsProbeRetryInterval {
-			return "", dnsErr
+		probeErr := fmt.Errorf("endpoint %s not reachable yet: %s", endpoint, strings.TrimSpace(stderr.String()))
+		if time.Until(deadline) < endpointProbeRetryInterval {
+			return "", probeErr
 		}
 		select {
 		case <-ctx.Done():
-			return "", fmt.Errorf("%w (%w)", dnsErr, ctx.Err())
-		case <-time.After(dnsProbeRetryInterval):
+			return "", fmt.Errorf("%w (%w)", probeErr, ctx.Err())
+		case <-time.After(endpointProbeRetryInterval):
 		}
 	}
 }

+// isTransientProbeExit reports whether a curl exit code describes a state the
+// endpoint is expected to pass THROUGH on its way up, rather than a settled
+// failure. Anything else — TLS refusal, a protocol error, a bad argument —
+// would still be failing after the retry window, so it fails immediately.
+func isTransientProbeExit(code int) bool {
+	return code == curlExitCouldNotResolve || code == curlExitCouldNotConnect
+}
+
 // Wire shapes for Chat.
 const (
 	// WireChat is the OpenAI-compatible /v1/chat/completions shape.
--- a/management/internals/modules/agentnetwork/synthesizer.go
+++ b/management/internals/modules/agentnetwork/synthesizer.go
@@ -211,7 +211,19 @@ func SynthesizeServices(ctx context.Context, s store.Store, accountID string) ([

 	groupIndex := indexProviderGroups(enabledPolicies)

-	routerCfgJSON, err := buildRouterConfigJSON(enabledProviders, groupIndex)
+	// The proxy guardrail is a per-provider fail-closed backstop; the
+	// authoritative per-policy/group decision is management's
+	// SelectPolicyForRequest. A provider lands in that map only when every
+	// authorising policy restricts models.
+	providerAllowlists := buildProviderAllowlists(enabledPolicies, guardrailsByID)
+
+	// Discovery gets the finer view: per policy rather than flattened per
+	// provider, so a listing can be bounded to what the calling groups may
+	// actually use instead of the union across everyone who reaches the
+	// provider.
+	modelPolicies := buildModelPolicies(enabledPolicies, guardrailsByID)
+
+	routerCfgJSON, err := buildRouterConfigJSON(enabledProviders, groupIndex, modelPolicies)
 	if err != nil {
 		return nil, err
 	}
@@ -228,11 +240,6 @@ func SynthesizeServices(ctx context.Context, s store.Store, accountID string) ([

 	mergedGuardrails := mergeGuardrails(enabledPolicies, guardrailsByID)
 	applyAccountCollectionControls(&mergedGuardrails, settings)
-	// The proxy guardrail is a per-provider fail-closed backstop; the
-	// authoritative per-policy/group decision is management's
-	// SelectPolicyForRequest. A provider lands in this map only when every
-	// authorising policy restricts models.
-	providerAllowlists := buildProviderAllowlists(enabledPolicies, guardrailsByID)
 	guardrailJSON, err := marshalGuardrailConfig(providerAllowlists, mergedGuardrails.PromptCapture)
 	if err != nil {
 		return nil, err
@@ -351,6 +358,11 @@ type routerProviderRoute struct {
 	AuthHeaderName  string   `json:"auth_header_name"`
 	AuthHeaderValue string   `json:"auth_header_value"`
 	AllowedGroupIDs []string `json:"allowed_group_ids,omitempty"`
+	// ModelPolicies is one entry per enabled policy authorising this provider,
+	// carrying that policy's source groups and the models it permits. The
+	// router bounds a model listing with it, so a provider two groups reach
+	// under different allowlists offers each only its own.
+	ModelPolicies []routerModelPolicy `json:"model_policies,omitempty"`
 	// Vertex marks a Google Vertex AI provider, whose requests carry the
 	// model in the URL path. The router selects it by path, bypassing the
 	// model/vendor table.
@@ -422,7 +434,7 @@ func indexProviderGroups(policies []*types.Policy) map[string][]string {
 // path-prefix tiebreak. Providers no enabled policy authorises
 // (orphans) are intentionally OMITTED so the router never observes a
 // route with an empty ACL.
-func buildRouterConfigJSON(providers []*types.Provider, groupIndex map[string][]string) ([]byte, error) {
+func buildRouterConfigJSON(providers []*types.Provider, groupIndex map[string][]string, modelPolicies map[string][]routerModelPolicy) ([]byte, error) {
 	cfg := routerConfig{Providers: make([]routerProviderRoute, 0, len(providers))}
 	for _, p := range providers {
 		groups, hasPolicy := groupIndex[p.ID]
@@ -449,6 +461,7 @@ func buildRouterConfigJSON(providers []*types.Provider, groupIndex map[string][]
 			AuthHeaderName:          headerName,
 			AuthHeaderValue:         headerValue,
 			AllowedGroupIDs:         groups,
+			ModelPolicies:           modelPolicies[p.ID],
 			Vertex:                  catalog.IsVertexPathStyle(p.ProviderID),
 			Bedrock:                 catalog.IsBedrockPathStyle(p.ProviderID),
 			GCPServiceAccountKeyB64: gcpSAKeyB64,
@@ -1098,3 +1111,46 @@ func mergeGuardrail(g *types.Guardrail, merged *MergedGuardrails) {
 		}
 	}
 }
+
+// routerModelPolicy mirrors the router's ModelPolicyRule: one authorising
+// policy's source groups plus the models it permits. Models is nil for a
+// policy that sets no model allowlist, which lifts the restriction for the
+// groups it binds — so nil and empty must survive the round trip distinctly.
+type routerModelPolicy struct {
+	GroupIDs []string `json:"group_ids"`
+	Models   []string `json:"models"`
+}
+
+// buildModelPolicies indexes, per provider, one rule for each enabled policy
+// authorising it: the policy's source groups and the models its guardrail
+// permits.
+//
+// This is deliberately finer than buildProviderAllowlists, which flattens the
+// same inputs into one list per provider for the proxy's fail-closed guardrail.
+// A flattened list cannot answer "what may THIS caller see", so a provider two
+// teams reach under different allowlists would offer each team the other's
+// models — a picker full of entries the next request refuses. Keeping the
+// source groups alongside the models lets the router answer it at request time,
+// where it knows the caller's groups.
+func buildModelPolicies(policies []*types.Policy, byID map[string]*types.Guardrail) map[string][]routerModelPolicy {
+	out := make(map[string][]routerModelPolicy)
+	for _, p := range policies {
+		if p == nil || len(p.SourceGroups) == 0 {
+			continue
+		}
+		restricted, models := policyModelAllowlist(p, byID)
+		rule := routerModelPolicy{GroupIDs: append([]string(nil), p.SourceGroups...)}
+		if restricted {
+			// Never nil when restricted: an allowlist permitting nothing must
+			// stay distinguishable from no allowlist at all.
+			rule.Models = append([]string{}, models...)
+		}
+		for _, providerID := range p.DestinationProviderIDs {
+			if providerID == "" {
+				continue
+			}
+			out[providerID] = append(out[providerID], rule)
+		}
+	}
+	return out
+}
--- a/management/internals/modules/agentnetwork/synthesizer_provider_allowlist_test.go
+++ b/management/internals/modules/agentnetwork/synthesizer_provider_allowlist_test.go
@@ -4,6 +4,7 @@ import (
 	"testing"

 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"

 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
 )
@@ -93,3 +94,75 @@ func TestBuildProviderAllowlists(t *testing.T) {
 			"an enabled-but-empty allowlist is restricted with an empty set, not unrestricted")
 	})
 }
+
+// policyForGroups builds an enabled policy binding the given source groups to
+// the given providers under an optional guardrail.
+func policyForGroups(id string, groups []string, guardrailIDs []string, providerIDs ...string) *types.Policy {
+	return &types.Policy{
+		ID:                     id,
+		Enabled:                true,
+		SourceGroups:           groups,
+		DestinationProviderIDs: providerIDs,
+		GuardrailIDs:           guardrailIDs,
+	}
+}
+
+// TestBuildModelPolicies covers the finer index discovery needs. Where
+// buildProviderAllowlists flattens every authorising policy into one list per
+// provider — enough for a fail-closed backstop, but blind to who is asking —
+// this keeps each policy's source groups beside its models so the router can
+// bound a listing to the calling groups.
+func TestBuildModelPolicies(t *testing.T) {
+	byID := map[string]*types.Guardrail{
+		"g-4o":       allowlistGuardrail("g-4o", "acc-1", "gpt-4o"),
+		"g-opus":     allowlistGuardrail("g-opus", "acc-1", "claude-opus-4"),
+		"g-disabled": {ID: "g-disabled", Checks: types.GuardrailChecks{ModelAllowlist: types.GuardrailModelAllowlist{Enabled: false, Models: []string{"gpt-4o"}}}},
+	}
+
+	t.Run("each policy keeps its own groups and models", func(t *testing.T) {
+		policies := []*types.Policy{
+			policyForGroups("p1", []string{"grp-eng"}, []string{"g-4o"}, "prov-x"),
+			policyForGroups("p2", []string{"grp-sales"}, []string{"g-opus"}, "prov-x"),
+		}
+		got := buildModelPolicies(policies, byID)
+		assert.Equal(t, []routerModelPolicy{
+			{GroupIDs: []string{"grp-eng"}, Models: []string{"gpt-4o"}},
+			{GroupIDs: []string{"grp-sales"}, Models: []string{"claude-opus-4"}},
+		}, got["prov-x"],
+			"the two policies must stay separable so neither group is offered the other's models")
+	})
+
+	t.Run("an unrestricted policy carries nil models", func(t *testing.T) {
+		policies := []*types.Policy{
+			policyForGroups("p1", []string{"grp-eng"}, []string{"g-4o"}, "prov-x"),
+			policyForGroups("p2", []string{"grp-admin"}, nil, "prov-x"),
+		}
+		got := buildModelPolicies(policies, byID)
+		assert.Nil(t, got["prov-x"][1].Models,
+			"no allowlist must reach the router as nil, which lifts the restriction for its groups")
+	})
+
+	t.Run("a disabled allowlist is not a restriction", func(t *testing.T) {
+		policies := []*types.Policy{policyForGroups("p1", []string{"grp-eng"}, []string{"g-disabled"}, "prov-x")}
+		got := buildModelPolicies(policies, byID)
+		assert.Nil(t, got["prov-x"][0].Models,
+			"a guardrail with the allowlist check off restricts nothing")
+	})
+
+	t.Run("an enabled allowlist with no models permits nothing", func(t *testing.T) {
+		byIDEmpty := map[string]*types.Guardrail{
+			"g-empty": {ID: "g-empty", Checks: types.GuardrailChecks{ModelAllowlist: types.GuardrailModelAllowlist{Enabled: true}}},
+		}
+		policies := []*types.Policy{policyForGroups("p1", []string{"grp-eng"}, []string{"g-empty"}, "prov-x")}
+		got := buildModelPolicies(policies, byIDEmpty)
+		require.NotNil(t, got["prov-x"][0].Models,
+			"an empty allowlist must not arrive as nil — that would read as unrestricted")
+		assert.Empty(t, got["prov-x"][0].Models)
+	})
+
+	t.Run("a policy binding no groups is skipped", func(t *testing.T) {
+		policies := []*types.Policy{policyForGroups("p1", nil, []string{"g-4o"}, "prov-x")}
+		assert.Empty(t, buildModelPolicies(policies, byID),
+			"a policy with no source groups authorises nobody, so it bounds nobody's listing")
+	})
+}
--- a/proxy/internal/middleware/builtin/llm_router/factory.go
+++ b/proxy/internal/middleware/builtin/llm_router/factory.go
@@ -44,6 +44,12 @@ type ProviderRoute struct {
 	AuthHeaderName  string   `json:"auth_header_name"`
 	AuthHeaderValue string   `json:"auth_header_value"`
 	AllowedGroupIDs []string `json:"allowed_group_ids"`
+	// ModelPolicies carries, per authorising policy, the source groups it
+	// binds and the models it permits. The router uses it to bound a model
+	// listing to what THIS caller may use: a provider reachable by two groups
+	// under different allowlists must not offer either group the other's
+	// models. Empty means no policy restricts models on this route.
+	ModelPolicies []ModelPolicyRule `json:"model_policies,omitempty"`
 	// Vertex marks a Google Vertex AI provider. Vertex requests carry the
 	// model in the URL path, so the router selects this route by path
 	// (isVertexPath) and bypasses the model/vendor table entirely.
@@ -65,6 +71,18 @@ type ProviderRoute struct {
 	SkipTLSVerify bool `json:"skip_tls_verify,omitempty"`
 }

+// ModelPolicyRule is one authorising policy's contribution to what a caller
+// may use on a route: the source groups it binds, and the models it permits.
+//
+// Models is nil when the policy sets no model allowlist — an unrestricted
+// policy, which lifts the restriction for the groups it binds. That is why
+// nil and empty must stay distinct: an empty list is a guardrail that permits
+// nothing, and collapsing the two would let a listing fail open.
+type ModelPolicyRule struct {
+	GroupIDs []string `json:"group_ids"`
+	Models   []string `json:"models"`
+}
+
 // Config is the on-wire configuration accepted by the factory. An
 // empty Providers slice yields a router that denies every request as
 // not-routable; the synthesiser is responsible for stamping the
--- a/proxy/internal/middleware/builtin/llm_router/middleware.go
+++ b/proxy/internal/middleware/builtin/llm_router/middleware.go
@@ -242,12 +242,13 @@ func (m *Middleware) routeModelless(reqPath, surface, method string, userGroups
 		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...)
+		// What the caller may actually use bounds what the picker may offer:
+		// every entry outside it is a request the chain will deny a moment
+		// later.
+		if reqPath == modelListingPath && out.Mutations != nil && out.Mutations.RewriteUpstream != nil {
+			if models, bounded := discoverableModels(route, userGroups); bounded {
+				out.Mutations.RewriteUpstream.DiscoveryModels = models
+			}
 		}
 		return out
 	case matchOutcomeUnauthorised:
@@ -271,6 +272,96 @@ func isNonInferenceMethod(method string) bool {
 	return method == http.MethodGet || method == http.MethodHead
 }

+// discoverableModels returns the model ids a caller in userGroups may actually
+// use on this route, and whether the listing should be bounded to them at all.
+//
+// Two things narrow a listing, and both must apply or the picker offers models
+// the very next request refuses:
+//
+//   - the provider's own enumerated models, when it lists any (a gateway record
+//     enumerates nothing and claims everything);
+//   - the model allowlists of the policies that authorise THIS caller. A
+//     provider reachable by two groups under different allowlists must not
+//     offer either group the other's models, which is why the rules carry their
+//     source groups rather than arriving pre-flattened.
+//
+// A policy that sets no allowlist lifts the restriction for the groups it
+// binds, so a caller holding one unrestricted policy sees the provider's full
+// list. bounded is false when nothing narrows the listing — an unrestricted
+// caller on a route that enumerates nothing — in which case the upstream's own
+// answer passes through untouched.
+func discoverableModels(route ProviderRoute, userGroups []string) ([]string, bool) {
+	permitted, restricted := policyPermittedModels(route, userGroups)
+
+	switch {
+	case !restricted && len(route.Models) == 0:
+		return nil, false
+	case !restricted:
+		return append([]string(nil), route.Models...), true
+	case len(route.Models) == 0:
+		// A gateway record enumerates nothing, so the allowlist is the whole
+		// bound — previously such a record offered the upstream's entire
+		// catalogue however narrow the policy was.
+		return sortedModels(permitted), true
+	}
+
+	// Both bound: only what the provider serves and the policy permits.
+	intersection := make(map[string]struct{}, len(route.Models))
+	for _, m := range route.Models {
+		if _, ok := permitted[m]; ok {
+			intersection[m] = struct{}{}
+		}
+	}
+	return sortedModels(intersection), true
+}
+
+// policyPermittedModels folds the rules whose groups intersect the caller's
+// into the set of models they permit. restricted is false when the caller
+// holds at least one authorising policy that sets no allowlist, or when no
+// rule binds them at all.
+func policyPermittedModels(route ProviderRoute, userGroups []string) (map[string]struct{}, bool) {
+	permitted := make(map[string]struct{})
+	restricted := false
+	for _, rule := range route.ModelPolicies {
+		if !groupsIntersect(rule.GroupIDs, userGroups) {
+			continue
+		}
+		if rule.Models == nil {
+			// An unrestricted policy the caller holds lifts the restriction
+			// entirely, whatever the others say.
+			return nil, false
+		}
+		restricted = true
+		for _, m := range rule.Models {
+			permitted[m] = struct{}{}
+		}
+	}
+	return permitted, restricted
+}
+
+// groupsIntersect reports whether the two group-id sets share a member.
+func groupsIntersect(a, b []string) bool {
+	for _, x := range a {
+		for _, y := range b {
+			if x == y {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+// sortedModels flattens a model set into a stable slice so the bound the proxy
+// applies — and any test asserting on it — does not depend on map order.
+func sortedModels(set map[string]struct{}) []string {
+	out := make([]string, 0, len(set))
+	for m := range set {
+		out = append(out, m)
+	}
+	sort.Strings(out)
+	return out
+}
+
 // 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) {
--- a/proxy/internal/middleware/builtin/llm_router/middleware_test.go
+++ b/proxy/internal/middleware/builtin/llm_router/middleware_test.go
@@ -1145,3 +1145,144 @@ func TestRouter_PinnedDatedModelStaysDistinct(t *testing.T) {
 			"declaration order must not decide between two deliberately pinned builds")
 	})
 }
+
+// TestRouter_DiscoveryBoundToCallersPolicies pins that a model listing is
+// bounded by the policies that authorise the caller, not by the union across
+// everyone who can reach the provider. Two teams sharing one provider record
+// under different allowlists is the case that makes the difference visible: a
+// flattened per-provider list would offer each team the other's models, and
+// every one of those entries is a request the guardrail then refuses.
+func TestRouter_DiscoveryBoundToCallersPolicies(t *testing.T) {
+	const (
+		eng   = "grp-eng"
+		sales = "grp-sales"
+	)
+	route := ProviderRoute{
+		ID:              "shared-gateway",
+		Models:          []string{"claude-sonnet-5", "claude-haiku-4-5", "gpt-4o"},
+		AllowedGroupIDs: []string{eng, sales},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "gateway.example.com",
+		ModelPolicies: []ModelPolicyRule{
+			{GroupIDs: []string{eng}, Models: []string{"claude-sonnet-5"}},
+			{GroupIDs: []string{sales}, Models: []string{"gpt-4o"}},
+		},
+	}
+
+	listingFor := func(t *testing.T, group string) []string {
+		t.Helper()
+		mw := New(Config{Providers: []ProviderRoute{route}})
+		in := newModellessInput(modelListingPath)
+		in.UserGroups = []string{group}
+
+		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)
+		return out.Mutations.RewriteUpstream.DiscoveryModels
+	}
+
+	t.Run("each group sees only its own policy's models", func(t *testing.T) {
+		assert.Equal(t, []string{"claude-sonnet-5"}, listingFor(t, eng),
+			"engineering must not be offered the model only sales may use")
+		assert.Equal(t, []string{"gpt-4o"}, listingFor(t, sales),
+			"sales must not be offered the model only engineering may use")
+	})
+
+	t.Run("a model no policy allows is offered to nobody", func(t *testing.T) {
+		for _, group := range []string{eng, sales} {
+			assert.NotContains(t, listingFor(t, group), "claude-haiku-4-5",
+				"the provider serves it, but no policy permits it")
+		}
+	})
+}
+
+// TestRouter_DiscoveryUnrestrictedPolicy covers the lifting rule: a caller
+// holding one policy without a model allowlist sees everything the provider
+// enumerates, whatever the other policies say.
+func TestRouter_DiscoveryUnrestrictedPolicy(t *testing.T) {
+	const (
+		eng   = "grp-eng"
+		admin = "grp-admin"
+	)
+	route := ProviderRoute{
+		ID:              "shared-gateway",
+		Models:          []string{"claude-sonnet-5", "gpt-4o"},
+		AllowedGroupIDs: []string{eng, admin},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "gateway.example.com",
+		ModelPolicies: []ModelPolicyRule{
+			{GroupIDs: []string{eng}, Models: []string{"claude-sonnet-5"}},
+			// nil Models: a policy that sets no allowlist at all.
+			{GroupIDs: []string{admin}},
+		},
+	}
+	mw := New(Config{Providers: []ProviderRoute{route}})
+
+	in := newModellessInput(modelListingPath)
+	in.UserGroups = []string{eng, admin}
+
+	out, err := mw.Invoke(context.Background(), in)
+	require.NoError(t, err)
+	require.NotNil(t, out.Mutations.RewriteUpstream)
+	assert.ElementsMatch(t, []string{"claude-sonnet-5", "gpt-4o"},
+		out.Mutations.RewriteUpstream.DiscoveryModels,
+		"an unrestricted policy the caller holds lifts the restriction")
+}
+
+// TestRouter_DiscoveryOnGatewayRecord covers a record that enumerates no
+// models. It previously offered the upstream's whole catalogue however narrow
+// the policy was, because there was nothing to intersect against; the policy
+// allowlist is now the bound on its own.
+func TestRouter_DiscoveryOnGatewayRecord(t *testing.T) {
+	const eng = "grp-eng"
+	base := ProviderRoute{
+		ID:              "litellm",
+		AllowedGroupIDs: []string{eng},
+		UpstreamScheme:  "https",
+		UpstreamHost:    "litellm.internal",
+	}
+
+	t.Run("a policy allowlist bounds it", func(t *testing.T) {
+		route := base
+		route.ModelPolicies = []ModelPolicyRule{{GroupIDs: []string{eng}, Models: []string{"gpt-4o"}}}
+		mw := New(Config{Providers: []ProviderRoute{route}})
+
+		in := newModellessInput(modelListingPath)
+		in.UserGroups = []string{eng}
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		assert.Equal(t, []string{"gpt-4o"}, out.Mutations.RewriteUpstream.DiscoveryModels,
+			"a catch-all record must still be bounded by what policy permits")
+	})
+
+	t.Run("an allowlist permitting nothing offers nothing", func(t *testing.T) {
+		route := base
+		route.ModelPolicies = []ModelPolicyRule{{GroupIDs: []string{eng}, Models: []string{}}}
+		mw := New(Config{Providers: []ProviderRoute{route}})
+
+		in := newModellessInput(modelListingPath)
+		in.UserGroups = []string{eng}
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Empty(t, out.Mutations.RewriteUpstream.DiscoveryModels,
+			"an empty allowlist permits nothing, and must not be read as unrestricted")
+	})
+
+	t.Run("no policy restriction leaves the listing alone", func(t *testing.T) {
+		mw := New(Config{Providers: []ProviderRoute{base}})
+
+		in := newModellessInput(modelListingPath)
+		in.UserGroups = []string{eng}
+
+		out, err := mw.Invoke(context.Background(), in)
+		require.NoError(t, err)
+		require.NotNil(t, out.Mutations.RewriteUpstream)
+		assert.Nil(t, out.Mutations.RewriteUpstream.DiscoveryModels,
+			"nothing narrows the listing, so the upstream's own answer passes through")
+	})
+}