Spec for MSC3077

Specs https://github.com/matrix-org/matrix-spec-proposals/pull/3077

content/client-server-api/modules/voip_events.md

@@ -171,18 +171,34 @@ In response to an incoming invite, a client may do one of several things:
 
 ##### Streams
 
-Clients are expected to send one stream with one track of kind `audio` (creating a
+Clients may send more than one stream in a VoIP call. Metadata can be included in
-voice call). They can optionally send a second track in the same stream of kind
+the `m.call.invite`, `m.call.answer` and `m.call.negotiate` events to describe the
-`video` (creating a video call).
+streams being sent. This is the `sdp_stream_metadata` field.
-
+
-Clients implementing this specification use the first stream and will ignore
+This field is an object in which each key is one stream `id` in the session
-any streamless tracks. Note that in the JavaScript WebRTC API, this means
+description. The values are objects with the following fields:
-`addTrack()` must be passed two parameters: a track and a stream, not just a
+
-track, and in a video call the stream must be the same for both audio and video
+ * `purpose` - a string indicating the purpose of the stream. For compatibility
-track.
+   between client the following values are defined:
-
+   *  `m.usermedia` - stream that contains the webcam and/or microphone tracks
-A client may send other streams and tracks but the behaviour of the other party
+   *  `m.screenshare` - stream with the screen-sharing tracks
-with respect to presenting such streams and tracks is undefined.
+
+If an incoming stream is not described in `sdp_stream_metadata` and
+`sdp_stream_metadata` is present, the stream should be ignored. If a stream has
+a `purpose` of an unknown type (i.e. not `m.usermedia` or `m.screenshare`), it
+should be ignored.
+
+Clients implementing this specification will ignore any streamless tracks. Note
+that in the JavaScript WebRTC API, this means `addTrack()` must be passed two
+parameters: a track and a stream, not just a track, and in a video call the
+stream must be the same for both audio and video track.
+
+During the initial invite and answer exchange clients find out if the field
+`sdp_stream_metadata` is missing. For backwards compatibility if it is not
+present in the event sent by the opponent, the client should ignore any new
+incoming streams (i.e. it should use the first one) and it shouldn't send more
+than one stream (i.e. clients cannot send a video feed and a screenshare at the
+same time, as is the case in current clients).
 
 ##### Invitees
 The `invitee` field should be added whenever the call is intended for one

data/event-schemas/schema/m.call.answer.yaml

@@ -27,6 +27,23 @@
                         }
                     },
                     "required": ["type", "sdp"]
+                },
+                "sdp_stream_metadata": {
+                    "type": "object",
+                    "title": "SDP Stream Metadata",
+                    "x-addedInMatrixVersion": "1.7",
+                    "description": "Object describing the streams that will be sent",
+                    "additionalProperties": {
+                        "type": "object",
+                        "title": "Stream Metadata Block",
+                        "properties": {
+                            "purpose": {
+                              "type": "string",
+                              "enum": ["m.usermedia", "m.screenshare"]
+                            }
+                        },
+                        "required": ["purpose"]
+                    }
                 }
             },
             "required": ["answer"]

data/event-schemas/schema/m.call.invite.yaml

@@ -35,7 +35,24 @@
                 "invitee": {
                     "type": "string",
                     "description": "The ID of the user being called. If omitted, any user in the room can answer.",
+                    "x-addedInMatrixVersion": "1.7"
+                },
+                "sdp_stream_metadata": {
+                    "type": "object",
+                    "title": "SDP Stream Metadata",
                     "x-addedInMatrixVersion": "1.7",
+                    "description": "Object describing the streams that will be sent",
+                    "additionalProperties": {
+                        "type": "object",
+                        "title": "Stream Metadata Block",
+                        "properties": {
+                            "purpose": {
+                              "type": "string",
+                              "enum": ["m.usermedia", "m.screenshare"]
+                            }
+                        },
+                        "required": ["purpose"]
+                    }
                 }
             },
             "required": ["offer", "lifetime"]

data/event-schemas/schema/m.call.negotiate.yaml

@@ -64,6 +64,23 @@ properties:
           Once the invite age exceeds this value, clients should discard it.
           They should also no longer show the call as awaiting an answer in the
           UI.
+      sdp_stream_metadata:
+        type: object
+        title: SDP Stream Metadata
+        x-addedInMatrixVersion: '1.7'
+        description: Object describing the streams that will be sent
+        additionalProperties:
+          type: object
+          title: Stream Metadata Block
+          properties:
+            purpose:
+              type: string
+              enum:
+              - m.usermedia
+              - m.screenshare
+    required:
+    - purpose
+
     required:
     - offer
     - lifetime