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 found that the current built-in DeepSeek configuration still sends deepseek-chat for every AI polish and grammar request. DeepSeek now rejects that retired model identifier and accepts deepseek-v4-flash or deepseek-v4-pro.
The repository currently restricts both Issue and PR creation for my account, so GitHub rejected the PR request. Could you please enable external PR submissions for this repository, or invite Zzy-min as a collaborator so I can submit this one-line fix for review?
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.
DeepSeek API model update
I found that the current built-in DeepSeek configuration still sends
deepseek-chatfor every AI polish and grammar request. DeepSeek now rejects that retired model identifier and acceptsdeepseek-v4-flashordeepseek-v4-pro.I prepared and verified the minimal fix:
src/config/ai.ts:deepseek-chat->deepseek-v4-flashpnpm buildpassedThe repository currently restricts both Issue and PR creation for my account, so GitHub rejected the PR request. Could you please enable external PR submissions for this repository, or invite
Zzy-minas a collaborator so I can submit this one-line fix for review?All reactions