René's URL Explorer Experiment

{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"Qwen-Omni Realtime API - Invalid session.finish event, session failure on ws.close(), and VAD token consumption inquiry","articleBody":"### Context / Background\n\nI am using the **Qwen3.5-Omni-Flash-Realtime** model over a WebSocket connection. I reviewed the sample implementation provided in your repository at:\n`https://github.com/aliyun/alibabacloud-bailian-speech-demo/blob/master/samples/conversation/omni/python/run_server_vad.py`\n\n### Problem 1: Invalid `session.finish` event \u0026 Missing Graceful Shutdown\n\nWhen attempting to gracefully shut down the WebSocket connection, I tried sending a `session.finish` event type, same as the sdk of Realtime API specifications:\n\n```json\n{\n    \"event_id\": \"...\",\n    \"type\": \"session.finish\"\n}\n\n```\n\nHowever, the server returns an error stating that this is an **invalid event type**.\n\nLooking closely at your sample code (`run_server_vad.py`), it only calls `conversation.close()`, which internally just executes `ws.close()`. This abruptly terminates the WebSocket connection without a proper higher-level elegant handshake or session termination event.\n\n### Problem 2: Dashboard showing \"Failed\" sessions \u0026 Token usage tracking\n\nBecause the connection is abruptly killed via `ws.close()`, every single one of my Realtime API sessions is marked as **\"Failed\"** in my Qwen Cloud Console / DashScope Dashboard. This makes it extremely difficult to track my exact token usage, session histories, and accurate analytics.\n\n\u003cimg width=\"851\" height=\"527\" alt=\"Image\" src=\"https://github.com/user-attachments/assets/c8c27fd5-5043-4b29-ac24-953268221dbd\" /\u003e\n\n\u003cimg width=\"452\" height=\"685\" alt=\"Image\" src=\"https://github.com/user-attachments/assets/78feb200-61c3-4826-be89-1304775da247\" /\u003e\n\n* Is the rejection of `session.finish` expected behavior, or is there another protocol-compliant event to gracefully close a session?\n* Is there a bug on the server side that records abrupt `ws.close()` actions as session failures?\n\n---\n\n### Question 3: VAD Token Consumption\n\nAdditionally, I have a question regarding the Voice Activity Detection (VAD) mode.\nWhen VAD is enabled, **does the server consume any tokens during the idle state** (i.e., when the client is streaming background silence/noise before the actual speech or user message is triggered/recognized)?\n\n### Environment\n\n* Model: Qwen3.5-Omni-Flash-Realtime\n\nAny clarification or guidance on how to properly perform a graceful shutdown and understand VAD token mechanics would be greatly appreciated. Thank you!\n","author":{"url":"https://github.com/ptaejoon","@type":"Person","name":"ptaejoon"},"datePublished":"2026-06-15T10:21:21.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":4},"url":"https://github.com/140/dashscope-sdk-python/issues/140"}