mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-24 21:41:04 +02:00
Runner.run_streamed starts the run eagerly; without an explicit cancel, a consumer that breaks out of the stream (or a disconnected SSE client) left the remaining turns — and their LLM calls — running to completion in the background with no way to stop them. The cloud query_stream already handled this; the local path now does too. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| cloud.py | ||
| local.py | ||
| protocol.py | ||