🐛 fix: Improve stability of Cloudflare Workers AI

[BrandonStudio]

💻 变更类型 | Change Type

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

🔀 变更说明 | Description of Change

Skip data chunk when response is missing

📝 补充信息 | Additional Information

This does not fix error in Cloudflare Workers AI. The primary reason of truncation is max_tokens limit, which defaults to 256.
I'm not sure whether it is good to arbitratrily set a larger limit, say 2048, because it may still be short, and it may overflow to the context window.
I believe the best solution is to give an option in frontend, enabling users to set the max_tokens by themselves. @arvinxx

There's another issue with reasoning models in Cloudflare: missing of opening <think> tag. This is an expected behaviour by design, see https://discord.com/channels/595317990191398933/1105477009964027914/1354837625554604143. However, this behaviour may change, so I'm not going to prefix <think> for now

[vercel]

@BrandonStudio is attempting to deploy a commit to the LobeChat Community Team on Vercel.

A member of the Team first needs to authorize it.

[lobehubbot]

👍 @BrandonStudio

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	2c36e86	🚫 Skipped	No files need to be tested {"src/libs/agent-runtime/utils/cloudflareHelpers.ts":"target file(src/libs/agent-runtime/utils/cloudflareHelpers.ts) not in work scope \n include: src/utils,src/server,src/database,src/services,src/store,packages//src/ \n exclude: node_modules,/*.test.ts,/.test.tsx,**/.spec.ts,/*.spec.tsx,/.d.ts,**/.test.js,**/*.spec.js,src/database/server"}

Tip

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

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 89.49%. Comparing base (b6d2c31) to head (2c36e86).
Report is 65 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #7450   +/-   ##
=======================================
  Coverage   89.49%   89.49%           
=======================================
  Files         760      760           
  Lines       54191    54193    +2     
  Branches     3466     3467    +1     
=======================================
+ Hits        48500    48502    +2     
  Misses       5691     5691           

Flag	Coverage Δ
app	89.49% <100.00%> (+<0.01%)	⬆️
server	95.74% <ø> (ø)

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

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 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 @BrandonStudio ❤️

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 1.82.6 🎉

The release is available on:

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

Your semantic-release bot 📦🚀