mancitrus/system-prompts-and-models-of-ai-tools
1
0
Fork 0
mirror of https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git synced 2026-06-18 15:29:36 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #2 from mohammedhadeez/fix-thinking-config-example-1878267473057973130

Browse Source 
Fix thinkingConfig usage in AI Studio vibe-coder example
This commit is contained in:
hyperisum 2026-03-27 01:07:43 +03:00 committed by GitHub
commit 7e277ac278
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
Google/Gemini/AI Studio vibe-coder.txt
View File

@ -568,7 +568,7 @@ const response = await ai.models.generateContent({
console.log(response.text); console.log(response.text);
``` ```
**Incorrect Example for Setting `maxOutputTokens` without `thinkingBudget`** **Example for Setting `maxOutputTokens` with low `thinkingBudget`**
```ts ```ts
import { GoogleGenAI } from "@google/genai"; import { GoogleGenAI } from "@google/genai";
@ -577,9 +577,9 @@ const response = await ai.models.generateContent({
model: "gemini-2.5-flash", model: "gemini-2.5-flash",
contents: "Tell me a story.", contents: "Tell me a story.",
config: { config: {
// Problem: The response will be empty since all the tokens are consumed by thinking. // We limit thinking usage to 25 tokens so that we have 25 tokens left for the response (50 - 25).
// Fix: Add `thinkingConfig: { thinkingBudget: 25 }` to limit thinking usage.
maxOutputTokens: 50, maxOutputTokens: 50,
thinkingConfig: { thinkingBudget: 25 },
}, },
}); });
console.log(response.text); console.log(response.text);