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 2026-06-17 23:09:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix thinkingConfig usage in AI Studio vibe-coder example

Browse Source 
The example demonstrating `maxOutputTokens` without `thinkingBudget` was originally labeled as incorrect. This change applies the fix suggested in the comments (adding a `thinkingBudget`) and updates the section header and comments to present it as a correct example of handling low token limits.
This commit is contained in:
google-labs-jules[bot] 2026-01-16 02:19:40 +00:00
parent 6b2157ca3e
commit f40a372cd5
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);
```
**Incorrect Example for Setting `maxOutputTokens` without `thinkingBudget`**
**Example for Setting `maxOutputTokens` with low `thinkingBudget`**
```ts
import { GoogleGenAI } from "@google/genai";
@ -577,9 +577,9 @@ const response = await ai.models.generateContent({
model: "gemini-2.5-flash",
contents: "Tell me a story.",
config: {
// Problem: The response will be empty since all the tokens are consumed by thinking.
// Fix: Add `thinkingConfig: { thinkingBudget: 25 }` to limit thinking usage.
// We limit thinking usage to 25 tokens so that we have 25 tokens left for the response (50 - 25).
maxOutputTokens: 50,
thinkingConfig: { thinkingBudget: 25 },
},
});
console.log(response.text);