Hartmut 502e2d0387 fix: use max_completion_tokens instead of max_tokens for GPT-4o ...

Azure OpenAI GPT-4o and newer models require 'max_completion_tokens'
instead of 'max_tokens'. Fixed in all 3 services:
- chat_service.py (2 call sites)
- azure_ai.py (validation service)
- tenants/router.py (test connection endpoint)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-15 14:20:40 +01:00

..

__init__.py

feat(B2): add tenant model + migrations 035/036 + RLS policies

2026-03-06 16:30:41 +01:00

models.py

feat(azure-ai+gpu-ui): per-tenant Azure AI config + GPU health panel

2026-03-08 21:04:09 +01:00

router.py

fix: use max_completion_tokens instead of max_tokens for GPT-4o

2026-03-15 14:20:40 +01:00

schemas.py

feat(azure-ai+gpu-ui): per-tenant Azure AI config + GPU health panel

2026-03-08 21:04:09 +01:00

service.py

feat(B2): add tenant model + migrations 035/036 + RLS policies

2026-03-06 16:30:41 +01:00