Oliver/semblance-dev
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
semblance-dev/backend/app
History
michael 45c7a52aeb Fix asyncio event loop mismatch in LLM service 
The genai.Client and AsyncOpenAI clients were being created at module
import time, before the Quart/Hypercorn event loop existed. This caused
"Future attached to a different loop" errors when async calls were made,
resulting in autonomous focus group conversations stopping with
"excessive_silence".

Changed to lazy initialization - clients are now created on first use
within the running event loop context via get_gemini_client() and
get_openai_client() helper functions.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-19 13:24:23 -06:00
..
__pycache__ made long actions cancellable (like persona generation, etc.), increased variety of persona generation with prompt changes and temperature variable, reduced length of key theme quotes, bug fixes 2025-09-10 16:24:05 -05:00
auth added full persona profile export in bulk actions menu (CSV, JSON and Markdown formats) 2025-09-10 22:38:35 -05:00
models Remove unused eventlet import and dead emit_with_ack function 2025-12-09 11:51:23 -06:00
routes Add LLM-generated one-line summaries for focus groups in list view 2025-12-04 08:51:28 -06:00
services Fix asyncio event loop mismatch in LLM service 2025-12-19 13:24:23 -06:00
utils refactored image/asset attachment to discussion guide and discussion messages to avoid back end filenames being displayed to user - use metadata system instead. Also added a detailed persona export to markdown. Also, bug fixes 2025-08-12 15:43:34 -05:00
.DS_Store converted message polling to websockets 2025-08-10 18:08:34 -05:00
__init__.py made long actions cancellable (like persona generation, etc.), increased variety of persona generation with prompt changes and temperature variable, reduced length of key theme quotes, bug fixes 2025-09-10 16:24:05 -05:00
db.py major refactor of entire application - migrate sync -> async including pymongo -> motor, flask -> quart, google-generativeai -> google-genai 2025-08-27 15:20:56 -05:00
extensions.py major refactor of entire application - migrate sync -> async including pymongo -> motor, flask -> quart, google-generativeai -> google-genai 2025-08-27 15:20:56 -05:00
utils.py Replace flask_jwt_extended imports with quart_jwt 2025-12-09 11:49:22 -06:00
websocket_debug_tap.py converted message polling to websockets 2025-08-10 18:08:34 -05:00
websocket_manager.py Replace flask_jwt_extended imports with quart_jwt 2025-12-09 11:49:22 -06:00
websocket_manager_async.py Replace flask_jwt_extended imports with quart_jwt 2025-12-09 11:49:22 -06:00