HartOMat

Files

T

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

api

feat: tenant AI chat agent with function calling

2026-03-15 12:46:21 +01:00

core

feat: performance optimizations + part-materials validation

2026-03-13 11:53:14 +01:00

data

feat: material alias seeds expansion, bulk product delete, dashboard stats widgets

2026-03-14 12:45:41 +01:00

domains

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