hexis: re-vendor the client so a configured token is actually sent

The vendored copy of github.com/kami/hexis predated Client.WithToken:
no token field, no setter, no header hook, and an unexported httpClient,
so there was no way to attach auth from outside the package. wireEcosystem
handled that by refusing to wire Hexis at all when a token was configured,
which was the honest reading of the code but left the deployment silently
without its executing service.

go.mod already replaces the module with /home/kami/apps/hexis, and that
source has had WithToken and the Bearer header for a while. Only the
checked-in vendor/ copy was stale. Refreshed it (client.go plus the new
capability.go) and wired Hexis like Nexus and Praxis.

Two tests cover the outcome the refusal was standing in for: a configured
token reaches the wire as Authorization, and no token still wires unauthed,
because Hexis without auth is a valid deployment on a trusted box.

Also corrected the discoverCapabilities comment. It claimed the client
stamped the correlation header on Execute only; do() stamps it on every
request, and did before the re-vendor too.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX

cmd/mavend/ecosystem.go

@@ -396,18 +396,8 @@ func wireEcosystem(cfg *config.Config) *ecosystemWiring {
 
 	// Hexis capability service
 	if cfg.Hexis != nil && cfg.Hexis.URL != "" {
-		if cfg.Hexis.Token != "" {
-			// Upstream hexis grew Client.WithToken, but the copy vendored here
-			// predates it, so the token cannot be sent. Hexis is the only one
-			// of the three that executes anything, and configuring auth on the
-			// executing service is not a best-effort request: refuse to wire it
-			// rather than execute unauthenticated for weeks behind one boot-time
-			// log line.
-			log.Printf("ecosystem: hexis token configured but the vendored hexis client cannot send it — hexis stays disabled; re-vendor github.com/kami/hexis to enable bearer auth")
-		} else {
-			w.hexis = hexisclient.New(cfg.Hexis.URL)
-			log.Printf("ecosystem: hexis at %s", cfg.Hexis.URL)
-		}
+		w.hexis = hexisclient.New(cfg.Hexis.URL).WithToken(cfg.Hexis.Token)
+		log.Printf("ecosystem: hexis at %s", cfg.Hexis.URL)
 	} else {
 		log.Printf("ecosystem: hexis not configured")
 	}
@@ -472,10 +462,11 @@ func (w *ecosystemWiring) resolveEntityReference(ctx context.Context, text strin
 // not conflate the two: a dependency failure must not silently read as "no
 // capabilities" and fall through to unrelated local execution.
 //
-// The vendored Hexis client stamps a correlation header on Execute only, so
-// discovery and execution cannot be joined on the Hexis side. Maven's own
-// traces still share one ID for both hops; the gap is on the far side and
-// closes when the client is re-vendored.
+// The correlation header is stamped in the client's do(), so discovery and
+// execution can be joined on the Hexis side as long as both hops carry the
+// same ID through ctx. (This used to say the header went out on Execute only;
+// that was never true of the vendored code and is not true after the 2026-08-01
+// re-vendor.)
 func (w *ecosystemWiring) discoverCapabilities(ctx context.Context, entityID string) ([]hexisclient.Capability, error) {
 	if w == nil || w.hexis == nil || entityID == "" {
 		return nil, nil

cmd/mavend/ecosystem_auth_test.go

@@ -0,0 +1,65 @@
+package main
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/kami/maven/internal/config"
+)
+
+// TestWireEcosystem_HexisToken — a configured Hexis token reaches the wire.
+//
+// This is the regression that closes the 2026-08-01 re-vendor. The copy of
+// github.com/kami/hexis checked into vendor/ used to predate Client.WithToken,
+// so a configured token could not be sent at all; wireEcosystem refused to wire
+// Hexis rather than execute unauthenticated. Both halves of that are gone. The
+// test asserts the outcome the refusal was standing in for: the header goes
+// out, so nobody has to trust a boot log to know auth is on.
+func TestWireEcosystem_HexisToken(t *testing.T) {
+	var gotAuth string
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotAuth = r.Header.Get("Authorization")
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`[]`))
+	}))
+	defer srv.Close()
+
+	cfg := &config.Config{Hexis: &config.HexisConfig{URL: srv.URL, Token: "s3cret"}}
+	w := wireEcosystem(cfg)
+	if w.hexis == nil {
+		t.Fatal("hexis not wired with a token configured")
+	}
+	if _, err := w.discoverCapabilities(context.Background(), "entity-1"); err != nil {
+		t.Fatalf("discoverCapabilities: %v", err)
+	}
+	if want := "Bearer s3cret"; gotAuth != want {
+		t.Errorf("Authorization = %q; want %q", gotAuth, want)
+	}
+}
+
+// TestWireEcosystem_HexisNoToken — no token configured still wires, unauthed.
+// Hexis without auth is a valid deployment on a trusted box, and the re-vendor
+// must not have turned the token into a requirement.
+func TestWireEcosystem_HexisNoToken(t *testing.T) {
+	var sawAuth bool
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		sawAuth = r.Header.Get("Authorization") != ""
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`[]`))
+	}))
+	defer srv.Close()
+
+	cfg := &config.Config{Hexis: &config.HexisConfig{URL: srv.URL}}
+	w := wireEcosystem(cfg)
+	if w.hexis == nil {
+		t.Fatal("hexis not wired without a token")
+	}
+	if _, err := w.discoverCapabilities(context.Background(), "entity-1"); err != nil {
+		t.Fatalf("discoverCapabilities: %v", err)
+	}
+	if sawAuth {
+		t.Error("Authorization header sent with no token configured")
+	}
+}