fix(webrtc): make WebRTC FFmpeg stream maps configurable (closes #2)

BuildArgs hardcoded -map 0✌️0 / -map 0🅰️0 for the two RTP legs.
Correct for production RTMP/SRT publishers (single combined input),
but breaks any process whose audio lives on a different input index
— multi-input lavfi test scaffolds, multi-camera pipelines, SDI +
file-audio mixes, etc.

Adds VideoMap and AudioMap fields to ConfigWebRTC (and the API DTO),
defaulting to the prior literals so existing deployments are
unaffected. BuildArgs reads them.

Tests:
- TestBuildArgs_DefaultMaps locks the empty-string default behavior
- TestBuildArgs_CustomMaps drives the multi-input override path
- TestProcessConfigWebRTCMapsRoundtrip extends the DTO roundtrip

Closes #2.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app/webrtc/ffmpeg_args.go

@@ -32,7 +32,16 @@ func BuildArgs(cfg appcfg.ConfigWebRTC, videoPort int) []string {
 		acopy = []string{"-c:a", "libopus", "-b:a", "96k"}
 	}
 
-	args := []string{"-map", "0:v:0"}
+	videoMap := cfg.VideoMap
+	if videoMap == "" {
+		videoMap = "0:v:0"
+	}
+	audioMap := cfg.AudioMap
+	if audioMap == "" {
+		audioMap = "0:a:0"
+	}
+
+	args := []string{"-map", videoMap}
 	args = append(args, vcopy...)
 	args = append(args,
 		"-payload_type", fmt.Sprint(cfg.VideoPT),
@@ -40,7 +49,7 @@ func BuildArgs(cfg appcfg.ConfigWebRTC, videoPort int) []string {
 		fmt.Sprintf("udp://127.0.0.1:%d?pkt_size=1316", videoPort),
 	)
 
-	args = append(args, "-map", "0:a:0")
+	args = append(args, "-map", audioMap)
 	args = append(args, acopy...)
 	args = append(args,
 		"-payload_type", fmt.Sprint(cfg.AudioPT),

app/webrtc/ffmpeg_args_test.go

@@ -87,3 +87,46 @@ func any(haystack []string, prefix string) bool {
 	}
 	return false
 }
+
+// TestBuildArgs_DefaultMaps confirms 0:v:0 / 0:a:0 are emitted when
+// VideoMap / AudioMap are empty (regression on the fix for issue #2 —
+// the prior version had these as hardcoded literals; if VideoMap is
+// ever empty unexpectedly, BuildArgs must still produce a working
+// command line).
+func TestBuildArgs_DefaultMaps(t *testing.T) {
+	cfg := appcfg.ConfigWebRTC{Enabled: true, VideoPT: 102, AudioPT: 111}
+	got := BuildArgs(cfg, 50000)
+	if !contains(got, "-map", "0:v:0") {
+		t.Fatalf("expected default video map 0:v:0, got %v", got)
+	}
+	if !contains(got, "-map", "0:a:0") {
+		t.Fatalf("expected default audio map 0:a:0, got %v", got)
+	}
+}
+
+// TestBuildArgs_CustomMaps drives the issue-#2 fix: when the user
+// configures a multi-input pipeline (audio on input #1, etc.), the
+// emitted -map values must follow the user's choice rather than the
+// "0:v:0"/"0:a:0" assumption.
+func TestBuildArgs_CustomMaps(t *testing.T) {
+	cfg := appcfg.ConfigWebRTC{
+		Enabled:  true,
+		VideoPT:  102,
+		AudioPT:  111,
+		VideoMap: "0:v:1",
+		AudioMap: "1:a:0",
+	}
+	got := BuildArgs(cfg, 50000)
+	if !contains(got, "-map", "0:v:1") {
+		t.Fatalf("expected custom video map 0:v:1, got %v", got)
+	}
+	if !contains(got, "-map", "1:a:0") {
+		t.Fatalf("expected custom audio map 1:a:0, got %v", got)
+	}
+	// The default literals should NOT appear when overridden.
+	for _, opt := range got {
+		if opt == "0:v:0" || opt == "0:a:0" {
+			t.Errorf("expected no default maps in output, found %q in %v", opt, got)
+		}
+	}
+}

http/api/process.go

@@ -44,10 +44,12 @@ type ProcessConfigLimits struct {
 
 // ProcessConfig represents the configuration of an ffmpeg process
 type ProcessConfigWebRTC struct {
-	Enabled        bool  `json:"enabled"`
+	Enabled        bool   `json:"enabled"`
-	VideoPT        uint8 `json:"video_pt,omitempty"`
+	VideoPT        uint8  `json:"video_pt,omitempty"`
-	AudioPT        uint8 `json:"audio_pt,omitempty"`
+	AudioPT        uint8  `json:"audio_pt,omitempty"`
-	ForceTranscode bool  `json:"force_transcode,omitempty"`
+	ForceTranscode bool   `json:"force_transcode,omitempty"`
+	VideoMap       string `json:"video_map,omitempty"`
+	AudioMap       string `json:"audio_map,omitempty"`
 }
 
 type ProcessConfig struct {
@@ -83,6 +85,8 @@ func (cfg *ProcessConfig) Marshal() *app.Config {
 			VideoPT:        cfg.WebRTC.VideoPT,
 			AudioPT:        cfg.WebRTC.AudioPT,
 			ForceTranscode: cfg.WebRTC.ForceTranscode,
+			VideoMap:       cfg.WebRTC.VideoMap,
+			AudioMap:       cfg.WebRTC.AudioMap,
 		},
 	}
 
@@ -168,6 +172,8 @@ func (cfg *ProcessConfig) Unmarshal(c *app.Config) {
 	cfg.WebRTC.VideoPT = c.WebRTC.VideoPT
 	cfg.WebRTC.AudioPT = c.WebRTC.AudioPT
 	cfg.WebRTC.ForceTranscode = c.WebRTC.ForceTranscode
+	cfg.WebRTC.VideoMap = c.WebRTC.VideoMap
+	cfg.WebRTC.AudioMap = c.WebRTC.AudioMap
 
 	cfg.Options = make([]string, len(c.Options))
 	copy(cfg.Options, c.Options)

http/api/process_webrtc_test.go

@@ -79,3 +79,31 @@ func TestProcessConfigWebRTCDefaults(t *testing.T) {
 		t.Fatalf("default should be disabled, got %+v", cfg.WebRTC)
 	}
 }
+
+// TestProcessConfigWebRTCMapsRoundtrip extends the WebRTC DTO
+// roundtrip with the issue-#2 VideoMap/AudioMap fields so the
+// regression doesn't repeat: a multi-input pipeline that sets
+// `audio_map: "1:a:0"` must reach the restream config layer
+// unchanged.
+func TestProcessConfigWebRTCMapsRoundtrip(t *testing.T) {
+	body := []byte(`{
+	  "id":"p","input":[{"id":"i","address":"x"}],"output":[{"id":"o","address":"-"}],
+	  "webrtc":{"enabled":true,"video_map":"0:v:1","audio_map":"1:a:0"}
+	}`)
+	var dto ProcessConfig
+	if err := json.Unmarshal(body, &dto); err != nil {
+		t.Fatalf("unmarshal: %v", err)
+	}
+	if dto.WebRTC.VideoMap != "0:v:1" || dto.WebRTC.AudioMap != "1:a:0" {
+		t.Fatalf("DTO maps lost: %+v", dto.WebRTC)
+	}
+	cfg := dto.Marshal()
+	if cfg.WebRTC.VideoMap != "0:v:1" || cfg.WebRTC.AudioMap != "1:a:0" {
+		t.Fatalf("app.Config maps lost: %+v", cfg.WebRTC)
+	}
+	var back ProcessConfig
+	back.Unmarshal(cfg)
+	if back.WebRTC.VideoMap != "0:v:1" || back.WebRTC.AudioMap != "1:a:0" {
+		t.Fatalf("Unmarshal lost maps: %+v", back.WebRTC)
+	}
+}

restream/app/process.go

@@ -25,10 +25,18 @@ type ConfigIO struct {
 // RTP to a loopback UDP port the subsystem allocates. The subsystem reads
 // that RTP and fans it out to WHEP subscribers.
 type ConfigWebRTC struct {
-	Enabled        bool  `json:"enabled"`
+	Enabled        bool   `json:"enabled"`
-	VideoPT        uint8 `json:"video_pt"`
+	VideoPT        uint8  `json:"video_pt"`
-	AudioPT        uint8 `json:"audio_pt"`
+	AudioPT        uint8  `json:"audio_pt"`
-	ForceTranscode bool  `json:"force_transcode"`
+	ForceTranscode bool   `json:"force_transcode"`
+
+	// VideoMap / AudioMap select which input stream the WebRTC RTP
+	// legs draw from. Defaults are "0:v:0" and "0:a:0" — correct for
+	// any RTMP / SRT publisher (single input, both A and V on input
+	// 0). For multi-input pipelines (lavfi test sources, SDI capture
+	// fed alongside file audio, etc.) the operator can override.
+	VideoMap string `json:"video_map,omitempty"`
+	AudioMap string `json:"audio_map,omitempty"`
 }
 
 // Clone returns a deep copy of the WebRTC config (currently a value copy;