fix(ingestion): authenticate the REST API; confine ingest paths to brain/raw/ (#149) (#152)

Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/cmd/server/main.go

@@ -503,20 +503,10 @@ func main() {
 		logger.Info("embed sync started", "interval_s", embedSyncInterval)
 	}
 
-	mux := http.NewServeMux()
-	mux.HandleFunc("POST /query", h.Query)
-	mux.HandleFunc("POST /write", h.Write)
-	mux.HandleFunc("POST /index", h.Index)
-	mux.HandleFunc("POST /ingest", h.Ingest)
-	mux.HandleFunc("POST /ingest-path", h.IngestPath)
-	mux.HandleFunc("POST /ingest-raw", h.IngestRaw)
-	mux.HandleFunc("POST /backfill-refs", h.BackfillRefs)
-	mux.HandleFunc("GET /pending", h.Pending)
-	mux.HandleFunc("POST /promote", h.Promote)
-	mux.HandleFunc("POST /backfill-embeddings", h.BackfillEmbeddings)
-	mux.HandleFunc("GET /pass-rate", h.PassRate)
+	// Public routes only; buildMux mounts the authenticated REST API (#149).
+	public := map[string]http.Handler{}
 	if webhookHandler != nil {
-		mux.Handle("POST /webhooks/brain-sync", webhookHandler)
+		public["POST /webhooks/brain-sync"] = webhookHandler
 	}
 	// Resource-metadata URL is only emitted on 401 when Dex OAuth is
 	// configured. Static-Bearer-only deployments leave this empty so
@@ -524,14 +514,14 @@ func main() {
 	var resourceMetadataURL string
 	if dexURL := os.Getenv("DEX_ISSUER_URL"); dexURL != "" {
 		resourceURL := os.Getenv("MCP_RESOURCE_URL")
-		mux.HandleFunc("GET /.well-known/oauth-protected-resource",
+		public["GET /.well-known/oauth-protected-resource"] = http.HandlerFunc(
 			chassisauth.ProtectedResourceHandler(resourceURL, dexURL))
 		if resourceURL != "" {
 			resourceMetadataURL = strings.TrimRight(resourceURL, "/") + "/.well-known/oauth-protected-resource"
 		}
 	}
 
-	mux.Handle("/mcp", chassisauth.BearerMiddleware(mcpToken, jwtValidator, "brain", resourceMetadataURL, mcpSrv))
+	public["/mcp"] = chassisauth.BearerMiddleware(mcpToken, jwtValidator, "brain", resourceMetadataURL, mcpSrv)
 
 	// POST /capture (#53/#54): the uniform capture REST door. Needs a ticket
 	// tracker to file action items, so it only mounts when Gitea is
@@ -553,7 +543,7 @@ func main() {
 		sovereign := splitList(os.Getenv("BRAIN_CAPTURE_SOVEREIGN_PRINCIPALS"))
 		resolver := capturehttp.NewOriginResolver(sovereign)
 		captureH := capturehttp.New(captureSvc, jwtValidator, mcpToken, "local-cli", resolver)
-		mux.Handle("POST /capture", captureH)
+		public["POST /capture"] = captureH
 		// Same use-case behind the MCP `capture` tool (#55 relay) so MCP-native
 		// harnesses (claude.ai, Crush, Pi, LLM Council) reach capture through
 		// the existing /mcp OAuth connector. mcpSrv is already wrapped above;
@@ -583,9 +573,9 @@ func main() {
 			logger.Error("OAUTH_CLIENT_ID/SECRET set but MCP_RESOURCE_URL is empty; cannot derive issuer")
 			os.Exit(1)
 		}
-		mux.HandleFunc("GET /.well-known/oauth-authorization-server",
+		public["GET /.well-known/oauth-authorization-server"] = http.HandlerFunc(
 			oauth.MetadataHandler(issuer))
-		mux.HandleFunc("POST /oauth/token", oauth.TokenHandler(oauth.TokenConfig{
+		public["POST /oauth/token"] = http.HandlerFunc(oauth.TokenHandler(oauth.TokenConfig{
 			ClientID:     oauthID,
 			ClientSecret: oauthSecret,
 			AccessToken:  mcpToken,
@@ -604,7 +594,17 @@ func main() {
 	// real request latency. /metrics itself is excluded from its own
 	// observation by registering it on the outer mux (post-wrap).
 	reg := metrics.New()
-	mux.HandleFunc("GET /metrics", reg.Handler())
+	public["GET /metrics"] = http.HandlerFunc(reg.Handler())
+
+	// The whole router, built in one place so the test of buildMux is a test
+	// of production wiring (PR #152 review). The REST API's credential is the
+	// same as /mcp's.
+	mux, err := buildMux(restAuth{token: mcpToken, validator: jwtValidator, realm: "brain",
+		resourceMetadataURL: resourceMetadataURL}, h, public)
+	if err != nil {
+		logger.Error("build router", "err", err)
+		os.Exit(1)
+	}
 	logger.Info("metrics endpoint registered", "path", "/metrics")
 
 	addr := ":" + port

ingestion/cmd/server/routes.go

@@ -0,0 +1,77 @@
+package main
+
+import (
+	"errors"
+	"fmt"
+	"net/http"
+
+	chassisauth "git.d-ma.be/mathias/mcp-chassis/auth"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/api"
+)
+
+// publicRoutes is the complete set of patterns allowed on the outer mux,
+// outside the REST API's auth (hyperguild#149). Each authenticates itself or is
+// meant to be open: /mcp (bearer/JWT), /capture (bearer/JWT), the webhook
+// (HMAC), /oauth/token (client secret), OAuth metadata and /metrics (open).
+// A REST pattern added here would beat the authenticated catch-all by
+// specificity and ship open, which is why buildMux refuses anything else.
+var publicRoutes = map[string]bool{
+	"/mcp":                      true,
+	"POST /capture":             true,
+	"POST /webhooks/brain-sync": true,
+	"GET /.well-known/oauth-protected-resource":   true,
+	"GET /.well-known/oauth-authorization-server": true,
+	"POST /oauth/token":                           true,
+	"GET /metrics":                                true,
+}
+
+// restAuth is the credential the REST API checks: the same as /mcp's.
+type restAuth struct {
+	token               string
+	validator           *chassisauth.JWTValidator
+	realm               string
+	resourceMetadataURL string
+}
+
+// buildMux is the server's whole router. The REST API is mounted at "/"
+// behind bearer auth that buildMux constructs itself, so a caller cannot pass
+// a no-op; public handlers are registered as given, and only for patterns on
+// the publicRoutes allowlist. It returns an http.Handler, not the
+// *ServeMux, so nothing can register a route on the result afterwards and
+// bypass the allowlist.
+func buildMux(auth restAuth, h *api.Handler, public map[string]http.Handler) (http.Handler, error) {
+	if auth.token == "" {
+		return nil, errors.New("buildMux: REST auth needs a token")
+	}
+	mux := http.NewServeMux()
+	for pattern, handler := range public {
+		if !publicRoutes[pattern] {
+			return nil, fmt.Errorf("buildMux: %q is not an allowed public route", pattern)
+		}
+		mux.Handle(pattern, handler)
+	}
+	mountREST(mux, h, func(next http.Handler) http.Handler {
+		return chassisauth.BearerMiddleware(auth.token, auth.validator, auth.realm, auth.resourceMetadataURL, next)
+	})
+	return mux, nil
+}
+
+// mountREST registers the REST API on its own mux and mounts it at "/" behind
+// auth: anything not registered as public lands here and is authenticated,
+// including routes added later.
+func mountREST(mux *http.ServeMux, h *api.Handler, auth func(http.Handler) http.Handler) {
+	rest := http.NewServeMux()
+	rest.HandleFunc("POST /query", h.Query)
+	rest.HandleFunc("POST /write", h.Write)
+	rest.HandleFunc("POST /index", h.Index)
+	rest.HandleFunc("POST /ingest", h.Ingest)
+	rest.HandleFunc("POST /ingest-path", h.IngestPath)
+	rest.HandleFunc("POST /ingest-raw", h.IngestRaw)
+	rest.HandleFunc("POST /backfill-refs", h.BackfillRefs)
+	rest.HandleFunc("GET /pending", h.Pending)
+	rest.HandleFunc("POST /promote", h.Promote)
+	rest.HandleFunc("POST /backfill-embeddings", h.BackfillEmbeddings)
+	rest.HandleFunc("GET /pass-rate", h.PassRate)
+	mux.Handle("/", auth(rest))
+}

ingestion/cmd/server/routes_test.go

@@ -0,0 +1,106 @@
+package main
+
+import (
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/mathiasbq/hyperguild/ingestion/internal/api"
+	"github.com/mathiasbq/hyperguild/ingestion/internal/pipeline"
+)
+
+const routesTok = "routes-test-token"
+
+func okHandler(body string) http.Handler {
+	return http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) { _, _ = w.Write([]byte(body)) })
+}
+
+// testMux builds the router exactly as main does: buildMux with the full
+// public set main registers (stub handlers) and real bearer config.
+// hyperguild#149: the REST API is authenticated as a whole; the PR #152
+// review showed a test of a COPY of the router let main.go regress unseen.
+func testMux(t *testing.T) http.Handler {
+	t.Helper()
+	h := api.NewHandler(t.TempDir(), slog.New(slog.NewTextHandler(os.Stderr, nil)), pipeline.Config{})
+	public := map[string]http.Handler{}
+	for p := range publicRoutes {
+		public[p] = okHandler("public " + p)
+	}
+	mux, err := buildMux(restAuth{token: routesTok, realm: "brain"}, h, public)
+	require.NoError(t, err)
+	return mux
+}
+
+func do(t *testing.T, h http.Handler, method, path, authz string) (int, string) {
+	t.Helper()
+	req := httptest.NewRequest(method, path, strings.NewReader(`{"query":"x"}`))
+	if authz != "" {
+		req.Header.Set("Authorization", authz)
+	}
+	rec := httptest.NewRecorder()
+	h.ServeHTTP(rec, req)
+	return rec.Code, rec.Body.String()
+}
+
+func TestBuildMuxRefusesRESTRoutesWithoutAValidToken(t *testing.T) {
+	r := testMux(t)
+	for _, rt := range []struct{ method, path string }{
+		{"POST", "/query"}, {"POST", "/write"}, {"POST", "/index"}, {"POST", "/ingest"},
+		{"POST", "/ingest-path"}, {"POST", "/ingest-raw"}, {"POST", "/backfill-refs"},
+		{"GET", "/pending"}, {"POST", "/promote"}, {"POST", "/backfill-embeddings"}, {"GET", "/pass-rate"},
+	} {
+		code, _ := do(t, r, rt.method, rt.path, "")
+		assert.Equal(t, http.StatusUnauthorized, code, "%s %s without a token", rt.method, rt.path)
+		code, _ = do(t, r, rt.method, rt.path, "Bearer wrong")
+		assert.Equal(t, http.StatusUnauthorized, code, "%s %s with a wrong token", rt.method, rt.path)
+	}
+}
+
+func TestBuildMuxServesRESTRoutesToAValidToken(t *testing.T) {
+	r := testMux(t)
+	code, _ := do(t, r, "GET", "/pending", "Bearer "+routesTok)
+	assert.Equal(t, http.StatusOK, code)
+}
+
+func TestBuildMuxAuthenticatesAnUnregisteredPath(t *testing.T) {
+	code, _ := do(t, testMux(t), "POST", "/some-future-route", "")
+	assert.Equal(t, http.StatusUnauthorized, code)
+}
+
+// buildMux registers public handlers as given, without adding auth: each
+// public route owns its own (bearer on /mcp, HMAC on the webhook, client
+// secret on /oauth/token) or is meant to be open (/metrics, OAuth metadata).
+func TestBuildMuxDoesNotWrapPublicRoutes(t *testing.T) {
+	r := testMux(t)
+	for p := range publicRoutes {
+		method, path, ok := strings.Cut(p, " ")
+		if !ok {
+			method, path = "GET", p
+		}
+		code, body := do(t, r, method, path, "")
+		assert.Equal(t, http.StatusOK, code, p)
+		assert.Equal(t, "public "+p, body, p)
+	}
+}
+
+// The allowlist is the control: a REST pattern registered as public would win
+// over the authenticated catch-all (more specific pattern), so it is refused.
+func TestBuildMuxRefusesAPublicPatternOffTheAllowlist(t *testing.T) {
+	h := api.NewHandler(t.TempDir(), slog.New(slog.NewTextHandler(os.Stderr, nil)), pipeline.Config{})
+	for _, p := range []string{"POST /query", "GET /pending", "/", "POST /metrics"} {
+		_, err := buildMux(restAuth{token: routesTok, realm: "brain"}, h, map[string]http.Handler{p: okHandler("x")})
+		assert.Error(t, err, "public pattern %q must be refused", p)
+	}
+}
+
+func TestBuildMuxRefusesAnEmptyToken(t *testing.T) {
+	h := api.NewHandler(t.TempDir(), slog.New(slog.NewTextHandler(os.Stderr, nil)), pipeline.Config{})
+	_, err := buildMux(restAuth{token: "", realm: "brain"}, h, nil)
+	assert.Error(t, err)
+}