HeyPuter/puter

Investigate & possible fix metering for gemini models search and caching

Open

#3,132 创建于 2026年5月19日

在 GitHub 查看
 (1 评论) (0 反应) (1 负责人)JavaScript (41,281 star) (3,752 fork)batch import
AIBackendTypeScriptenhancementhelp wanted

描述

Newer gemini models support things like grounded searches and timed caching. However openai compatible api might not expose these costs in the input/output tokens the way claude api does.

verify that metering for this is valid, and fix if not

贡献者指南

技术栈
javascriptnodejs
领域
backendapi
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-2 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
blocked
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
Familiarity with Puter's codebaseUnderstanding of OpenAI compatible API meteringKnowledge of Gemini models features
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
25
研究方向
Start by examining the existing metering implementation for OpenAI compatible API endpoints, likely in the backend's API handling code. Look for how token counts are calculated for Gemini models and whether search and caching costs are included. Check the Gemini SDK's response for any custom usage fields and compare with Claude's approach mentioned in the issue. If needed, adjust the metering logic to account for these additional costs.
Investigate & possible fix metering for gemini models search and caching · HeyPuter/puter#3132 | Good First Issue