💄 style: update SiliconCloud reasoning models

[AnotiaWang]

💻 变更类型 | Change Type

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

🔀 变更说明 | Description of Change

改进 SiliconCloud 的 model-runtime 实现，支持配置更多模型的思考开关和 thinking budget。

支持快慢思考的模型：

仅支持慢思考的模型：

📝 补充信息 | Additional Information

Summary by Sourcery

Enable advanced reasoning controls for SiliconCloud models by exposing reasoningBudgetToken and enableReasoning settings in model definitions and updating the runtime provider to apply and validate these parameters dynamically.

New Features:

• Expose reasoningBudgetToken and enableReasoning as configurable extendParams in SiliconCloud model cards

Enhancements:

• Refactor model-runtime logic to dynamically assign enable_thinking and thinking_budget based on model patterns with proper bounds checking

[vercel]

@AnotiaWang is attempting to deploy a commit to the LobeHub Community Team on Vercel.

A member of the Team first needs to authorize it.

[lobehubbot]

👍 @AnotiaWang

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。

[sourcery-ai]

Reviewer's Guide

Updates SiliconCloud model configurations to support reasoning toggles and budget parameters in model definitions, and refactors the runtime provider to dynamically apply and clamp thinking settings based on model patterns.

Class diagram for updated SiliconCloud model configuration

classDiagram
class AIChatModelCard {
  releasedAt: string
  settings: object
  type: string
}
class Settings {
  extendParams: string[]
}
AIChatModelCard --> Settings : has
Settings : extendParams = ["enableReasoning", "reasoningBudgetToken"]

Loading

Class diagram for SiliconCloud runtime provider changes

classDiagram
class LobeSiliconCloudAI {
  createOpenAICompatibleRuntime()
}
LobeSiliconCloudAI : - thinkingBudget
LobeSiliconCloudAI : - hybridThinkingModels
LobeSiliconCloudAI : + enable_thinking
LobeSiliconCloudAI : + thinking_budget
LobeSiliconCloudAI : + max_tokens
LobeSiliconCloudAI : + model

Loading

Flow diagram for dynamic thinking settings in SiliconCloud runtime

flowchart TD
    A["Input: model, thinking, max_tokens, rest"] --> B["Determine thinkingBudget"]
    B --> C["Create result object with rest, max_tokens, model"]
    C --> D{"Is thinking defined?"}
    D -- Yes --> E["Check if model matches hybridThinkingModels"]
    E -- Yes --> F["Set enable_thinking based on thinking.type"]
    D -- Yes --> G["If thinkingBudget defined, clamp and set thinking_budget"]
    D -- No --> H["Return result"]
    F --> G
    G --> H
    D -- No --> H

Loading

File-Level Changes

Change	Details	Files
Add reasoning configuration options to AI model cards	Insert settings.extendParams with reasoningBudgetToken for chat models Enable enableReasoning flag in settings for select models	packages/model-bank/src/aiModels/siliconcloud.ts
Refactor thinking parameter handling in runtime provider	Replace inline conditional with result builder and remove hard-coded model checks Introduce hybridThinkingModels regex list for selective enable_thinking support Clamp thinking_budget to valid range and assign enable_thinking based on type	packages/model-runtime/src/providers/siliconcloud/index.ts

Possibly linked issues

• build(deps-dev): bump @types/node from 18.16.13 to 20.2.1 #1: The PR adds 'enableReasoning' and 'reasoningBudgetToken' to SiliconCloud models, enabling the chain-of-thought switching functionality requested in the issue.

---

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.

[gru-agent]

TestGru Assignment

Summary

Link	CommitId	Status	Reason
Detail	81deafc	🚫 Skipped	No files need to be tested {"packages/model-bank/src/aiModels/siliconcloud.ts":"source code too long","packages/model-runtime/src/providers/siliconcloud/index.ts":"Can not find valuable test target.\nLobeSiliconCloudAI: Out of scope - This exported constant is created via a factory function and represents a runtime object for a model provider. It does not export any functions or classes directly, and its internal logic is more suitable for integration testing rather than unit testing."}

History Assignment

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!

Prompt for AI Agents

Please address the comments from this code review:

## Individual Comments

### Comment 1
<location> `packages/model-runtime/src/providers/siliconcloud/index.ts:61-62` </location>
<code_context>
+          /DeepSeek-V3\.1/,
+          /Hunyuan-A13B-Instruct/,
+        ];
+        if (hybridThinkingModels.some((regexp) => regexp.test(model))) {
+          result.enable_thinking = thinking.type === 'enabled';
+        }
+        if (typeof thinkingBudget !== 'undefined') {
</code_context>

<issue_to_address>
**issue:** Potential case sensitivity issue in model matching.

Consider normalizing the model string or using case-insensitive regexes to prevent mismatches due to case sensitivity.
</issue_to_address>

### Comment 2
<location> `packages/model-bank/src/aiModels/siliconcloud.ts:87-88` </location>
<code_context>
       ],
     },
     releasedAt: '2025-08-20',
+    settings: {
+      extendParams: ['reasoningBudgetToken'],
+    },
     type: 'chat',
</code_context>

<issue_to_address>
**question:** Inconsistent extendParams for similar models.

If the difference in extendParams is intentional, please document the reasoning to help future maintainers.
</issue_to_address>

---

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.}

[sourcery-ai]

issue: Potential case sensitivity issue in model matching.

Consider normalizing the model string or using case-insensitive regexes to prevent mismatches due to case sensitivity.

[sourcery-ai]

question: Inconsistent extendParams for similar models.

If the difference in extendParams is intentional, please document the reasoning to help future maintainers.

[codecov]

Codecov Report

❌ Patch coverage is 0% with 17 lines in your changes missing coverage. Please review.
✅ Project coverage is 79.80%. Comparing base (28f84d5) to head (81deafc).
⚠️ Report is 3 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #9287      +/-   ##
==========================================
- Coverage   79.81%   79.80%   -0.01%     
==========================================
  Files         819      819              
  Lines       52930    52936       +6     
  Branches     5482     5482              
==========================================
  Hits        42246    42246              
- Misses      10684    10690       +6     

Flag	Coverage Δ
app	78.15% <ø> (ø)
database	98.29% <ø> (ø)
packages/agent-runtime	62.53% <ø> (ø)
packages/context-engine	62.29% <ø> (ø)
packages/electron-server-ipc	93.76% <ø> (ø)
packages/file-loaders	88.00% <ø> (ø)
packages/model-bank	100.00% <ø> (ø)
packages/model-runtime	77.37% <0.00%> (-0.06%)	⬇️
packages/prompts	100.00% <ø> (ø)
packages/utils	94.92% <ø> (ø)
packages/web-crawler	97.07% <ø> (ø)

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

Components	Coverage Δ
Store	71.97% <ø> (ø)
Services	62.39% <ø> (ø)
Server	65.14% <ø> (ø)
Libs	51.60% <ø> (ø)
Utils	75.00% <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.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
lobe-chat-preview	Ready	Preview	Comment	Sep 16, 2025 11:07am

[lobehubbot]

❤️ Great PR @AnotiaWang ❤️

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 1.129.1 🎉

The release is available on:

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

Your semantic-release bot 📦🚀