modcomms/backend/app
Vadym Samoilenko 74585c5c18 Fix Gemini timeout by using HTTP-level timeout on separate clients
asyncio.wait_for cannot reliably cancel SDK-internal HTTP connections.
Replace with two genai.Client instances — one per model — each configured
with http_options={'timeout': N} so the TCP connection is actually torn
down when the deadline is reached.

Primary model: 45s, Fallback model: 150s

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 12:49:11 +00:00
..
agents Standardise Issue/Recommendation formatting across all agents 2026-02-19 10:17:08 -06:00
api Grant oversight_admin read-only access to User Management 2026-02-24 13:35:07 -06:00
dependencies Add 4-tier RBAC backend: auth dependencies, role enforcement, agency filtering 2026-02-19 08:28:23 -06:00
models Add user change history audit trail for compliance 2026-02-22 08:41:16 -06:00
repositories Fix MissingGreenlet 500 error on GET /api/campaigns 2026-03-02 12:17:12 +00:00
services Fix Gemini timeout by using HTTP-level timeout on separate clients 2026-03-02 12:49:11 +00:00
websocket Fix missing Submitter/Agency on Auditing Errors tab 2026-03-01 18:21:10 +00:00
__init__.py permissions changes 2025-12-18 16:51:27 +00:00
config.py Add Knowledge Base management system for AI agent specs 2026-02-12 15:00:36 -06:00
main.py Handle WebSocket disconnect gracefully during analysis 2026-03-02 12:30:51 +00:00