salman/igny8
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fixes of ai toke limit standrd 8192

Browse Source
This commit is contained in:
IGNY8 VPS (Salman)
2025-12-17 00:36:18 +00:00
parent 69c0fd8b69
commit 9656643f0f
7 changed files with 262 additions and 1872 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
backend/igny8_core/ai/settings.py
View File

@@ -99,8 +99,8 @@ def get_model_config(function_name: str, account) -> Dict[str, Any]:
# MODEL_RATES not available - skip validation
pass
# Get max_tokens and temperature from config (with reasonable defaults for API)
max_tokens = config.get('max_tokens', 16384) # Maximum for long-form content generation (2000-3000 words)
# Get max_tokens and temperature from config (standardized to 8192)
max_tokens = config.get('max_tokens', 8192) # Standardized across entire codebase
temperature = config.get('temperature', 0.7) # Reasonable default
# Build response format based on model (JSON mode for supported models)