🐛 fix: correct totalOutputTokens calculation for XAI provider

[bbbugg]

💻 变更类型 | Change Type

• ✨ feat
• 🐛 fix
• ♻️ refactor
• 💄 style
• 👷 build
• ⚡️ perf
• ✅ test
• 📝 docs
• 🔨 chore

🔀 变更说明 | Description of Change

变更背景

• 问题：Grok（xAI）返回的 completion_tokens 不包含 reasoning_tokens，在费用计算中的总输出费用（totalOutputCredit = totalOutputTokens × output 单价）不含思考 token，进而影响总计消耗。
• 现象：UI 的 Usage 明细中虽然会显示 “深度思考” 分项，但“总计消耗”未包含 reasoning，和期望不符。

变更内容

• 在 packages/model-runtime/src/utils/usageConverter.ts 的 convertUsage 中，对 provider === 'xai' 增加一处归一化处理：
  • totalOutputTokensNormalized = completion_tokens + reasoning_tokens（仅 xAI）
  • outputTextTokens 的计算保持不变：对 xAI 仍不减去 reasoning token（xAI 的 completion_tokens 本身不含 reasoning），只减去音频token。
  • 返回数据中将 totalOutputTokens 替换为 totalOutputTokensNormalized，其它字段不变。
• test修改

修改之前 ：输出和总计消耗中未包含深度思考

修改之后：输出和总计消耗中已包含深度思考

📝 补充信息 | Additional Information

token收取费用说明

Summary by Sourcery

Include reasoning tokens when calculating total output tokens for xAI provider and update related tests.

Bug Fixes:

• Add reasoning_tokens to totalOutputTokens for xAI in usageConverter to correctly reflect costs.

Tests:

• Update convertUsage tests to expect normalized totalOutputTokens including reasoning tokens for xAI.

[vercel]

@bbbugg is attempting to deploy a commit to the LobeHub OSS Team on Vercel.

A member of the Team first needs to authorize it.

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Corrects the total output token count for the xAI provider by including reasoning tokens in the calculation, adjusting the usageConverter logic and its corresponding tests.

File-Level Changes

Change	Details	Files
Introduce normalized totalOutputTokens for xAI by adding reasoning tokens	Define totalOutputTokensNormalized to sum completion_tokens and reasoning_tokens when provider is xAI Use totalOutputTokensNormalized in the returned usage instead of raw totalOutputTokens	packages/model-runtime/src/utils/usageConverter.ts
Update test expectations for xAI token calculation	Change expected totalOutputTokens from 66 to 447 in the xAI test case Document that reasoning_tokens are priced the same as completion_tokens	packages/model-runtime/src/utils/usageConverter.test.ts

Possibly linked issues

• build(deps-dev): bump @types/node from 18.16.13 to 20.2.1 #1: The PR corrects Grok's total output token calculation by including reasoning tokens, directly resolving the issue of negative usage.

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[lobehubbot]

👍 @bbbugg

Thank you for raising your pull request and contributing to our Community
Please make sure you have followed our contributing guidelines. We will review it as soon as possible.
If you encounter any problems, please feel free to connect with us.
非常感谢您提出拉取请求并为我们的社区做出贡献，请确保您已经遵循了我们的贡献指南，我们会尽快审查它。
如果您遇到任何问题，请随时与我们联系。

[gru-agent]

TestGru Assignment

Summary

Link	CommitId	Status	Reason
Detail	9c3e147	✅ Finished

History Assignment

Files

File	Pull Request
packages/model-runtime/src/utils/usageConverter.ts	❌ Failed (I failed to setup the environment.)

Tip

You can @gru-agent and leave your feedback. TestGru will make adjustments based on your input

[sourcery-ai]

Hey there - I've reviewed your changes and they look great!

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 84.04%. Comparing base (85f9ca5) to head (9c3e147).
⚠️ Report is 7 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff            @@
##             main    #8984     +/-   ##
=========================================
  Coverage   84.04%   84.04%             
=========================================
  Files         870      870             
  Lines       70571    70594     +23     
  Branches     4889     6503   +1614     
=========================================
+ Hits        59309    59332     +23     
  Misses      11256    11256             
  Partials        6        6             

Flag	Coverage Δ
app	85.99% <ø> (+<0.01%)	⬆️
database	96.26% <ø> (ø)
packages/electron-server-ipc	74.61% <ø> (ø)
packages/file-loaders	83.59% <ø> (ø)
packages/model-runtime	74.21% <100.00%> (+<0.01%)	⬆️
packages/prompts	100.00% <ø> (ø)
packages/utils	61.07% <ø> (ø)
packages/web-crawler	59.57% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Components	Coverage Δ
Store	68.86% <ø> (ø)
Services	61.95% <ø> (ø)
Server	66.35% <ø> (ø)
Libs	46.10% <ø> (ø)
Utils	70.63% <ø> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[lobehubbot]

❤️ Great PR @bbbugg ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.
项目的成长离不开用户反馈和贡献，感谢您的贡献! 如果您对 LobeHub 开发者社区感兴趣，请加入我们的 discord，然后私信 @arvinxx 或 @canisminor1990。他们会邀请您加入我们的私密开发者频道。我们将会讨论关于 Lobe Chat 的开发，分享和讨论全球范围内的 AI 消息。

[lobehubbot]

🎉 This PR is included in version 1.118.3 🎉

The release is available on:

• npm package (@latest dist-tag)
• GitHub release

Your semantic-release bot 📦🚀