You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am currently configuring Forge for my project and using the DeepSeek v4 Flash model.
I want the model to generate responses without outputting its internal reasoning/thinking tokens to my terminal. However, despite applying the following configuration in my ~/.forge/.forge.toml file, the model continues to output its chain-of-thought blocks:
I also tried setting enabled = false and effort = "none", but the reasoning tokens are still being rendered in the console.
Could you please guide me on how to properly suppress or exclude the reasoning output for DeepSeek v4 Flash in Forge? Is there a specific configuration parameter or custom agent rule I should use for this model?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Hi.
I am currently configuring Forge for my project and using the DeepSeek v4 Flash model.
I want the model to generate responses without outputting its internal reasoning/thinking tokens to my terminal. However, despite applying the following configuration in my
~/.forge/.forge.tomlfile, the model continues to output its chain-of-thought blocks:I also tried setting
enabled = falseandeffort = "none", but the reasoning tokens are still being rendered in the console.Could you please guide me on how to properly suppress or exclude the reasoning output for DeepSeek v4 Flash in Forge? Is there a specific configuration parameter or custom agent rule I should use for this model?
Thanks!
All reactions