Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

pydantic-ai: capture web-search and grounding counts from `RequestUsage.details`

未关闭
#866 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
3/5
预计耗时
1-2 天
新手友好度
72/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
python
领域
observability

调研方向

Start in py/src/braintrust/integrations/pydantic_ai/tracing.py around lines 1388–1428, where RequestUsage.details currently provides reasoning and cached-token data. Review the existing cassette-backed integration tests and add coverage for a web-search tool run. Confirm that web-search and grounding counts are captured without breaking compatibility with the listed older pydantic-ai versions, and verify the workspace metadata behavior if included.

由索引模型根据 Issue 内容生成。

描述

feature python

pydantic-ai 2.52–2.54 started counting OpenAI native web searches (#8310) and Google grounding queries (#8891) in RequestUsage.details.

The usage extractor in py/src/braintrust/integrations/pydantic_ai/tracing.py (around lines 1388–1428) only reads reasoning and cached tokens from details.

Proposal

  • Record the new counts as metrics (or metadata if they aren't token counts), read defensively so older versions (0.1.9, 1.0.1, 1.10.0) are unaffected.
  • Optionally record the new workspace= run kwarg's kind in metadata (_AGENT_INPUT_ALLOWLIST already keeps the object itself out of spans).
  • Add cassette-backed coverage with a web-search tool run.

Parent: #858 (found while reviewing the 2026-10-05 weekly dependency update, #849).

🤖 Generated with Claude Code

主要语言
Python
星标
21
派生
23
平均合并
20 小时 8 分钟
30 天内合并 PR
94

环境准备

  • 提供 Dockerfile 或 Docker Compose 文件
  • 没有 Pull Request 模板
  • 阅读贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

braintrustdata/braintrust-sdk-python 的其他 Issue

查看 braintrustdata/braintrust-sdk-python 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。