fix(server+android): DIDL-Lite metadata for Sonos UPnP (error 1023)

After the X-Forwarded-Proto fix Sonos now gets a clean https:// URL
but returns vendor error 1023 - empty CurrentURIMetaData. Sonos
requires DIDL-Lite metadata with at minimum <res protocolInfo>
carrying the audio MIME type so it can validate the source before
playback. The original spec said 'Sonos accepts empty DIDL; recoverable
if a device rejects' - that was wrong for Sonos.

Server (cast_token.go):
- Look up the track and return mime (from tracks.file_format) +
  title in the cast-token response. mimeForFormat covers the common
  formats - mp3, flac, m4a/aac, ogg, opus, wav - falling through to
  audio/mpeg for unknowns.
- Missing track returns 404 (apierror.NotFound) instead of letting the
  caller mint a token for nothing.

Client (CastApi.kt, AVTransportClient.kt, OutputPickerController.kt):
- StreamTokenResponse gains mime + title (defaulted so old contracts
  stay parseable).
- AVTransportClient.setAVTransportURIWithMetadata builds minimal Sonos-
  acceptable DIDL-Lite around the URL + MIME + title. xml-escaped.
- selectUpnp calls the new overload; Timber.i now logs the MIME so the
  next on-device test shows it.

Generic UPnP renderers tolerate the DIDL shape too - no downside to
sending it everywhere.

internal/api/cast_token.go

@@ -3,9 +3,11 @@ package api
 import (
 	"net/http"
 	"strconv"
+	"strings"
 	"time"
 
 	"git.fabledsword.com/bvandeusen/minstrel/internal/apierror"
+	"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
 )
 
 const (
@@ -23,6 +25,36 @@ type castTokenResponse struct {
 	Token string `json:"token"`
 	Exp   int64  `json:"exp"`
 	URL   string `json:"url"`
+	// MIME and Title let the client build proper DIDL-Lite metadata for
+	// SetAVTransportURI. Sonos rejects empty DIDL with vendor error 1023;
+	// passing back the track's MIME + title here lets the client populate
+	// `<res protocolInfo>` and `<dc:title>` without a follow-up round trip.
+	MIME  string `json:"mime"`
+	Title string `json:"title"`
+}
+
+// mimeForFormat maps the tracks.file_format column to an HTTP audio
+// MIME type. Sonos requires the protocolInfo MIME on DIDL-Lite to match
+// what the URL actually serves; "audio/*" wildcard is silently rejected.
+// Unknown formats fall back to audio/mpeg — most Sonos firmware probes
+// the URL anyway and recovers from a small MIME mismatch.
+func mimeForFormat(format string) string {
+	switch strings.ToLower(strings.TrimSpace(format)) {
+	case "mp3", "mpeg":
+		return "audio/mpeg"
+	case "flac":
+		return "audio/flac"
+	case "aac", "m4a", "mp4":
+		return "audio/mp4"
+	case "ogg", "vorbis":
+		return "audio/ogg"
+	case "opus":
+		return "audio/opus"
+	case "wav", "wave":
+		return "audio/wav"
+	default:
+		return "audio/mpeg"
+	}
 }
 
 // handleCastStreamToken issues a short-lived HMAC stream token for the
@@ -52,6 +84,14 @@ func (h *handlers) handleCastStreamToken(w http.ResponseWriter, r *http.Request)
 		writeErr(w, apierror.BadRequest("invalid_track_id", "trackId must be a UUID"))
 		return
 	}
+	// Track lookup for the DIDL-Lite metadata the client builds for
+	// SetAVTransportURI. A missing track is a 404 — there's nothing to
+	// cast in that case.
+	track, err := dbq.New(h.pool).GetTrackByID(r.Context(), trackUUID)
+	if err != nil {
+		writeErr(w, apierror.NotFound("track"))
+		return
+	}
 	expSec := clampExpSeconds(req.ExpSeconds)
 	exp := time.Now().Add(time.Duration(expSec) * time.Second).Unix()
 	token := SignStreamToken(h.streamSecret, req.TrackID, exp)
@@ -77,7 +117,13 @@ func (h *handlers) handleCastStreamToken(w http.ResponseWriter, r *http.Request)
 	url := scheme + "://" + host + "/api/tracks/" + req.TrackID +
 		"/stream?token=" + token + "&exp=" + strconv.FormatInt(exp, 10)
 
-	writeJSON(w, http.StatusOK, castTokenResponse{Token: token, Exp: exp, URL: url})
+	writeJSON(w, http.StatusOK, castTokenResponse{
+		Token: token,
+		Exp:   exp,
+		URL:   url,
+		MIME:  mimeForFormat(track.FileFormat),
+		Title: track.Title,
+	})
 }
 
 // clampExpSeconds applies the [60, 86400] window with a 6h default for