feat(transcription): add shared voice input support (#4232)

* feat(webui): add voice transcription input

* feat(webui): render ANSI output in code blocks

* refactor(webui): isolate voice recorder logic

* refactor(transcription): keep websocket ingress thin

* refactor(transcription): resolve channel audio settings on demand

* style(webui): neutralize voice waveform color

* feat(webui): add voice input tooltip

* feat(webui): add voice input keyboard shortcut

* fix(webui): distinguish voice shortcut platforms

* fix(webui): place voice button after model selector

* refactor(webui): share voice hold recording helpers

* fix(desktop): allow microphone voice input

* fix(webui): stabilize token usage month labels

* feat(webui): show voice input on settings overview

* fix(webui): label voice capability as recognition

* fix(webui): align capability overview status

* refactor(webui): isolate transcription socket handling

* fix(webui): soften silent voice waveform

* refactor(audio): clarify transcription service location

* docs(transcription): clarify audio and provider boundaries

* fix(exec): reduce session output polling flake

nanobot/channels/websocket.py

@@ -45,6 +45,7 @@ from nanobot.webui.http_utils import (
     query_first as _query_first,
 )
 from nanobot.webui.mcp_presets_api import normalize_mcp_preset_mentions
+from nanobot.webui.transcription_ws import webui_transcription_event
 from nanobot.webui.websocket_logging import websockets_server_logger
 
 
@@ -235,7 +236,7 @@ _VIDEO_MIME_ALLOWED: frozenset[str] = frozenset({
 
 _UPLOAD_MIME_ALLOWED: frozenset[str] = _IMAGE_MIME_ALLOWED | _VIDEO_MIME_ALLOWED
 
-_DATA_URL_MIME_RE = re.compile(r"^data:([^;]+);base64,", re.DOTALL)
+_DATA_URL_MIME_RE = re.compile(r"^data:([^;,]+)(?:;[^,]*)*;base64,", re.DOTALL)
 
 
 def _extract_data_url_mime(url: str) -> str | None:
@@ -419,7 +420,6 @@ class WebSocketChannel(BaseChannel):
         return None
 
     # -- Server lifecycle and connection ingress ---------------------------
-    # -- Server lifecycle and connection ingress ---------------------------
 
     async def start(self) -> None:
         from nanobot.utils.logging_bridge import redirect_lib_logging
@@ -703,6 +703,10 @@ class WebSocketChannel(BaseChannel):
                 workspace_scope=scope.payload(),
             )
             return
+        if t == "transcribe_audio":
+            event, payload = await webui_transcription_event(envelope)
+            await self._send_event(connection, event, **payload)
+            return
         if t == "message":
             cid = envelope.get("chat_id")
             content = envelope.get("content")