feat: Nvidia API direkt-Anbindung mit Thinking-Mode Support
Neues Server-Setting NvidiaApiKey – wenn gesetzt, wird direkt integrate.api.nvidia.com verwendet statt g4f.space Proxy. Thinking-Modelle (kimi-k2, qwq, deepseek-r1) erhalten automatisch chat_template_kwargs und reasoning-Output wird als klappbare Denkprozess-Bubble im Chat angezeigt. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
1 parent
1101bb83a0
commit
4960b57ec7
6 files changed
+176
-3
No files matched your search
@@ -1126,6 +1126,16 @@
|
||||
}
|
||||
}
|
||||
|
||||
/* Thinking Box (Nvidia Reasoning) */
|
||||
|
||||
.thinking-box .tool-box-header .tool-name {
|
||||
color: var(--warning);
|
||||
}
|
||||
|
||||
.thinking-box .thinking-content {
|
||||
padding: var(--box-padding);
|
||||
}
|
||||
|
||||
/* Review Bubbles */
|
||||
|
||||
.review-bubble {
|
||||
|
||||
Reference in new issue
Block a user