# GPT-Live 1: diagnosing an early AgentSession startup error before session.started (Python SDK 1.8.8) **URL:** \ **Category:** Agents\ **Tags:** agent-sdk-python\ **Created:** [October 21, 2026, 12:33am UTC](https://community.livekit.io/t/gpt-live-1-diagnosing-an-early-agentsession-startup-error-before-session-started-python-sdk-1-8-8/2319 "2026-10-21T00:33:56Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![medianza](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/medianza/32/2873_2.png) [@medianza](https://community.livekit.io/u/medianza)\ **Post date:** [October 21, 2026, 12:33am UTC](https://community.livekit.io/t/gpt-live-1-diagnosing-an-early-agentsession-startup-error-before-session-started-python-sdk-1-8-8/2319/1 "2026-10-21T00:33:56Z")
I am troubleshooting a small browser-only voice prototype using a local Python agent and LiveKit Cloud. This is direct OpenAI GPT-Live, not OpenAI Realtime and not LiveKit Inference. No SIP/PSTN is involved in these tests. Environment: - macOS, Python 3.14.7 - livekit-agents 1.8.8, livekit-plugins-openai 1.8.8, openai 3.35.1 - GPTLiveModel: gpt-live-1, voice marin, delegation client, max\_retry=0 - Official OpenAI Live WebSocket endpoint; SDK-generated PCM 24 kHz configuration - AgentSession.start with record=False, capture\_run=False and session\_host=False - Local deterministic backend with synthetic data, no additional model calls Observed in two previous short attempts: - The browser and local agent both became active participants. - The local session emitted a generic SESSION\_ERROR during AgentSession startup. - We did not confirm OpenAI session.started or model output audio; a browser audio-track/playing event alone did not establish audible speech. - The agent then disconnected with CLIENT\_INITIATED and the browser left with ROOM\_DELETED, consistent with our cleanup. These departure reasons do not identify the original fault. - Agent Insights contained no observability data. - Our previous instrumentation did not retain the original nested exception, HTTP status, request ID or OpenAI session ID. We cannot claim whether the original WebSocket handshake completed. Offline investigation only, since then: - Actual installed SDK protocol/orchestrator tests with an in-memory WebSocket can initialize successfully. This does not validate real provider access or RoomIO audio. - Simulated HTTP/transport errors demonstrate nested SDK wrapping. Simulated early server error events can also be lost if our observer is attached after startup, so our local instrumentation now attaches at session creation and persists fixed redacted error categories. These synthetic errors are NOT evidence that the original failure was authentication, quota, permissions, TLS or any particular category. Questions: 1. Is this SDK/Python combination supported for GPTLiveModel with a locally run AgentSession and browser room participant? Are there known startup compatibility issues, particularly on Python 3.14? 2. Is there a supported pre-start diagnostic hook for distinguishing room IO initialization, OpenAI WebSocket handshake rejection and Live session configuration errors without enabling recordings or retaining raw prompts, tokens or audio? 3. Are record=False, capture\_run=False and session\_host=False expected to work together in this local setup, and what observability remains available? 4. What minimal sanitized diagnostic fields would maintainers need to narrow this down before any further live attempt? I am requesting configuration/instrumentation guidance, not reporting a critical ongoing outage. No further real voice test is currently authorized. Please do not request public API keys, project/session identifiers, private logs, audio or customer data. Thanks. ---
**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\ **Post date:** [October 21, 2026, 10:25am UTC](https://community.livekit.io/t/gpt-live-1-diagnosing-an-early-agentsession-startup-error-before-session-started-python-sdk-1-8-8/2319/2 "2026-10-21T10:25:20Z")
Before getting too deep in the weeds, I recommend trying with this known-working sample I provided in response to this user: > [@GPT Live 1 Livekit Inference Not Working?](https://community.livekit.io/t/gpt-live-1-livekit-inference-not-working/2297/2): > > I just tested with the attached, and it seems to work: [agent.py](https://community.livekit.io/uploads/short-url/fHWmrAxTpaOHwNeH2yUvPqQOqVe.py) (5.8 KB) There haven’t been any outages that could explain the 503, which I assume would have been an issue between our backend and OpenAI. Did you specify inference.DuplexModel ? Your issue is not the same root cause, I just reference that thread as it contains the `agent.py` download. Instructions: - Run through the quick start guide, to the point where you are speaking with an agent: - Replace the agent.py file in that agent with the one linked above - Then re-run locally with `lk agent console` or `lk agent dev` > [@medianza](#): > > - Agent Insights contained no observability data. That is a separate issue, you don’t have observability enabled on your project. > [@medianza](#): > > I am requesting configuration/instrumentation guidance, not reporting a critical ongoing outage. No further real voice test is currently authorized. Please do not request public API keys, project/session identifiers, private logs, audio or customer data. Thanks. Joking aside, your agent would definitely benefit from our tooling support, based on its observations and investigation so far: [Coding agent support and tools | LiveKit Documentation](https://docs.livekit.io/intro/coding-agents/).