torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Support for allowed model restrictions per provider

Browse Source 
Tool escalation added to `analyze` to a graceful switch over to codereview is made when absolutely necessary
This commit is contained in:
Fahad
2025-06-14 10:56:53 +04:00
parent ac9c58ce61
commit 23353734cd
14 changed files with 1037 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
.env.example
View File

@@ -32,7 +32,7 @@ CUSTOM_API_KEY= # Empty for Ollama (no auth
CUSTOM_MODEL_NAME=llama3.2 # Default model name
# Optional: Default model to use
# Options: 'auto' (Claude picks best model), 'pro', 'flash', 'o3', 'o3-mini'
# Options: 'auto' (Claude picks best model), 'pro', 'flash', 'o3', 'o3-mini', 'o4-mini', 'o4-mini-high' etc
# When set to 'auto', Claude will select the best model for each task
# Defaults to 'auto' if not specified
DEFAULT_MODEL=auto
@@ -49,6 +49,35 @@ DEFAULT_MODEL=auto
# Defaults to 'high' if not specified
DEFAULT_THINKING_MODE_THINKDEEP=high
# Optional: Model usage restrictions
# Limit which models can be used from each provider for cost control, compliance, or standardization
# Format: Comma-separated list of allowed model names (case-insensitive, whitespace tolerant)
# Empty or unset = all models allowed (default behavior)
# If you want to disable a provider entirely, don't set its API key
#
# Supported OpenAI models:
# - o3 (200K context, high reasoning)
# - o3-mini (200K context, balanced)
# - o4-mini (200K context, latest balanced, temperature=1.0 only)
# - o4-mini-high (200K context, enhanced reasoning, temperature=1.0 only)
# - mini (shorthand for o4-mini)
#
# Supported Google/Gemini models:
# - gemini-2.5-flash-preview-05-20 (1M context, fast, supports thinking)
# - gemini-2.5-pro-preview-06-05 (1M context, powerful, supports thinking)
# - flash (shorthand for gemini-2.5-flash-preview-05-20)
# - pro (shorthand for gemini-2.5-pro-preview-06-05)
#
# Examples:
# OPENAI_ALLOWED_MODELS=o3-mini,o4-mini,mini # Only allow mini models (cost control)
# GOOGLE_ALLOWED_MODELS=flash # Only allow Flash (fast responses)
# OPENAI_ALLOWED_MODELS=o4-mini # Single model standardization
# GOOGLE_ALLOWED_MODELS=flash,pro # Allow both Gemini models
#
# Note: These restrictions apply even in 'auto' mode - Claude will only pick from allowed models
# OPENAI_ALLOWED_MODELS=
# GOOGLE_ALLOWED_MODELS=
# Optional: Custom model configuration file path
# Override the default location of custom_models.json
# CUSTOM_MODELS_CONFIG_PATH=/path/to/your/custom_models.json