Skip to content

docs: add README cards and tighten overview#65

Merged
Disaster-Terminator merged 4 commits intomainfrom
docs/readme-cards-and-polish
May 6, 2026
Merged

docs: add README cards and tighten overview#65
Disaster-Terminator merged 4 commits intomainfrom
docs/readme-cards-and-polish

Conversation

@Disaster-Terminator
Copy link
Copy Markdown
Owner

@Disaster-Terminator Disaster-Terminator commented May 5, 2026

Summary

  • add Shields.io README cards for project status, entry model, LiteLLM compatibility, and privacy posture
  • tighten the first-screen Chinese overview around model=semantic-router -> route_id -> target_model
  • keep the English README aligned with the same positioning and operational gates

Notes

The README card API used here is Shields.io, for example:

<img alt="status: local validation" src="https://img.shields.io/badge/status-local_validation-f59e0b?style=for-the-badge">

No repository metadata, secrets, runtime config, or code paths are changed.

Summary by Sourcery

刷新中文版和英文版 README,以突出 model=semantic-router -> route_id -> target_model 的整体流程和当前「本地验证」状态,并添加可视化的状态/集成徽章。

Documentation:

  • 添加来自 Shields.io 的 README 徽章,用于突出项目状态、入口模型、LiteLLM 兼容性以及日志隐私策略。
  • 重写两个版本 README 的开头部分,改为「一句话概览 + 功能表格」形式,重点强调意图路由、低侵入的 LiteLLM 集成,以及各类运行控制阈值。
  • 在中英文中都明确项目边界和路由流水线(model=semantic-router -> route_id -> target_model -> LiteLLM model group),包括示例路由如何映射到 LiteLLM 模型组。
  • 通过表格和更精炼的措辞提升快速上手和生命周期章节的可读性,同时反复说明结构化日志行为与隐私保证。
Original summary in English

Summary by Sourcery

Refresh Chinese and English READMEs to emphasize the model=semantic-router -> route_id -> target_model flow and current local-validation status, and add visual status/integration badges.

Documentation:

  • Add Shields.io README badges to highlight project status, entry model, LiteLLM compatibility, and log privacy posture.
  • Rework the opening sections of both READMEs into concise one-line overviews plus feature tables emphasizing intent routing, low-intrusion LiteLLM integration, and operational gates.
  • Clarify project boundaries and routing pipeline (model=semantic-router -> route_id -> target_model -> LiteLLM model group) in both languages, including how sample routes map to LiteLLM model groups.
  • Improve readability of quick-start and lifecycle sections with tables and tightened wording, while reiterating structured-logging behavior and privacy guarantees.

@qodo-code-review
Copy link
Copy Markdown

ⓘ You've reached your Qodo monthly free-tier limit. Reviews pause until next month — upgrade your plan to continue now, or link your paid account if you already have one.

@sourcery-ai
Copy link
Copy Markdown

sourcery-ai Bot commented May 5, 2026

Reviewer's Guide

更新中文和英文 README,在不修改任何运行时代码或配置的前提下,通过 Shields.io 引入可视化的状态/入口/隐私卡片,并收紧、对齐对 IntentMux 路由模型、边界以及与 LiteLLM 集成流程的高层解释。

通过 semantic_router 进行 IntentMux LiteLLM 路由的时序图

sequenceDiagram
    actor Client
    participant LiteLLM
    participant IntentMux
    participant EmbeddingService
    participant LiteLLM_Model_Group

    Client->>LiteLLM: POST /v1/chat model=semantic-router
    LiteLLM->>IntentMux: Forward request model=semantic-router
    IntentMux->>EmbeddingService: Compute embedding for request
    EmbeddingService-->>IntentMux: Embedding vector
    IntentMux->>IntentMux: Select route_id from intent
    IntentMux->>IntentMux: Resolve route_id to target_model
    IntentMux-->>LiteLLM: Return model=target_model
    LiteLLM->>LiteLLM_Model_Group: Route to configured model group
    LiteLLM_Model_Group-->>LiteLLM: Upstream response
    LiteLLM-->>Client: Chat completion response
Loading

File-Level Changes

Change Details Files
在两个 README 顶部添加 Shields.io 徽章,汇总项目状态、入口模型、LiteLLM 兼容性以及日志/隐私姿态。
  • 在中文 README 主标题下插入一个居中的 HTML

    块,其中包含四个 Shields.io 图像徽章。

  • 在英文 README 中插入一个等效的居中 HTML

    块,使用同样的四个 Shields.io 图像徽章。

README.md
README.en.md
重构开头的概览部分,使其聚焦 model=semantic-router -> route_id -> target_model 流程,并在两种语言中澄清项目定位和边界。
  • 用一个 ## 一句话 的单段描述,加上一张两行的 HTML 表格,替换现有的中文概览表格,突出意图路由、低侵入式集成、可审计日志及生产验证闸门。
  • 在中文中新增一个 ## 项目边界 部分,显式说明路由链 model=semantic-router -> route_id -> target_model -> LiteLLM model group,澄清对其他模型的透传行为,并解释示例 route id 和 target model。
  • 用一个 ## One Line 描述和一张两行的 HTML 表格替换英文简介表格,在意图路由、集成方式、日志和运维闸门等关键点上与中文保持镜像。
  • 新增英文 ## Project Boundary 章节,在路由链说明、透传语义以及 route id 到 LiteLLM 模型组的示例配置映射等方面与中文保持一致。
README.md
README.en.md
在保持语义和行为描述不变的前提下,优化现有 README 的措辞和结构。
  • 将若干中文段落改写得更为精炼,将原先换行拆开的句子合并为单行,但不改变含义(例如:集成说明、配置校验规则、运行时依赖说明、生命周期与状态章节)。
  • 把中文默认端点列表改成 Markdown 表格,并将环境变量列表标题改为“常用环境变量”。
  • 重新排版中文的 LiteLLM 集成部分,使关键短语保持在同一行,并明确说明 semantic-router 与 LiteLLM 的 smart-router 是两个不同的入口点。
  • 同样收紧英文文案,将拆行的句子合并,澄清 semantic-router 是一个入口名,区别于产品名以及 LiteLLM 的 smart-router,在保持日志/决策预览描述语义不变的前提下使其更紧凑。
  • 将英文默认端点列表改为 Markdown 表格,并在“Status”等章节进行少量文字润色,以提高可读性而不改变所描述的行为。
README.md
README.en.md

Tips and commands

Interacting with Sourcery

  • 触发新评审: 在 pull request 中评论 @sourcery-ai review
  • 继续讨论: 直接回复 Sourcery 的评审评论。
  • 从评审评论生成 GitHub issue: 通过回复某条评审评论,要求 Sourcery 基于该评论创建一个 issue。你也可以在评审评论中回复 @sourcery-ai issue 来从该评论创建 issue。
  • 生成 pull request 标题: 在 pull request 标题的任意位置写上 @sourcery-ai,即可随时生成标题。你也可以在 pull request 中评论 @sourcery-ai title 来(重新)生成标题。
  • 生成 pull request 摘要: 在 pull request 正文任意位置写上 @sourcery-ai summary,即可在指定位置随时生成 PR 摘要。你也可以在 pull request 中评论 @sourcery-ai summary 来(重新)生成摘要。
  • 生成评审指南: 在 pull request 中评论 @sourcery-ai guide,即可随时(重新)生成评审指南。
  • 解决所有 Sourcery 评论: 在 pull request 中评论 @sourcery-ai resolve 来一次性解决所有 Sourcery 评论。如果你已经处理完所有评论且不想再看到它们,这会很有用。
  • 清除所有 Sourcery 评审: 在 pull request 中评论 @sourcery-ai dismiss 来清除所有现有的 Sourcery 评审。尤其适用于你想从头开始新的评审时——别忘了再评论一次 @sourcery-ai review 来触发新评审!

Customizing Your Experience

访问你的 控制面板 以:

  • 启用或禁用评审功能,例如 Sourcery 自动生成的 pull request 摘要、评审指南等。
  • 修改评审语言。
  • 添加、删除或编辑自定义评审说明。
  • 调整其他评审设置。

Getting Help

Original review guide in English

Reviewer's Guide

Updates both Chinese and English READMEs to introduce visual status/entry/privacy cards via Shields.io and to tighten and align the high-level explanation of the IntentMux routing model, boundaries, and integration flow with LiteLLM, without touching any runtime code or configuration.

Sequence diagram for IntentMux LiteLLM routing via semantic_router

sequenceDiagram
    actor Client
    participant LiteLLM
    participant IntentMux
    participant EmbeddingService
    participant LiteLLM_Model_Group

    Client->>LiteLLM: POST /v1/chat model=semantic-router
    LiteLLM->>IntentMux: Forward request model=semantic-router
    IntentMux->>EmbeddingService: Compute embedding for request
    EmbeddingService-->>IntentMux: Embedding vector
    IntentMux->>IntentMux: Select route_id from intent
    IntentMux->>IntentMux: Resolve route_id to target_model
    IntentMux-->>LiteLLM: Return model=target_model
    LiteLLM->>LiteLLM_Model_Group: Route to configured model group
    LiteLLM_Model_Group-->>LiteLLM: Upstream response
    LiteLLM-->>Client: Chat completion response
Loading

File-Level Changes

Change Details Files
Add Shields.io README badges summarizing project status, entry model, LiteLLM compatibility, and logging/privacy posture at the top of both READMEs.
  • Insert a centered HTML

    block containing four Shields.io image badges below the main title in the Chinese README.

  • Insert an equivalent centered HTML

    block with the same four Shields.io image badges in the English README.

README.md
README.en.md
Refactor the initial overview sections to focus on the model=semantic-router -> route_id -> target_model flow and clarify project positioning and boundaries in both languages.
  • Replace the initial Chinese overview table with a ## 一句话 one-paragraph description plus a two-row HTML table highlighting intent routing, low-intrusion integration, auditable logs, and production-validation gates.
  • Introduce a ## 项目边界 section in Chinese that explicitly documents the routing chain model=semantic-router -> route_id -> target_model -> LiteLLM model group, clarifies pass-through behavior for other models, and explains sample route ids and target models.
  • Replace the English intro table with a ## One Line description and a two-row HTML table mirroring the Chinese key points around intent routing, integration, logging, and operational gates.
  • Add an English ## Project Boundary section mirroring the Chinese description of the routing chain, pass-through semantics, and example config mapping of route ids to LiteLLM model groups.
README.md
README.en.md
Tighten wording and improve structure in existing README sections while keeping semantics and behavior descriptions unchanged.
  • Reword several Chinese paragraphs for concision, joining previously wrapped sentences into single lines without changing meaning (e.g., integration description, config validation rules, runtime dependency notes, lifecycle and status sections).
  • Convert the Chinese default endpoint list into a markdown table and retitle the environment variable list as “常用环境变量”.
  • Reformat the Chinese LiteLLM integration section to keep key phrases on a single line and clarify that semantic-router and LiteLLM smart-router are distinct entry points.
  • Similarly tighten English prose by collapsing wrapped sentences, clarifying that semantic-router is an entry name separate from the product name and LiteLLM's smart-router, and keeping log/decision-preview descriptions semantically identical but more compact.
  • Convert the English default endpoint list into a markdown table and make minor copyedits in “Status” and other sections for readability without altering described behavior.
README.md
README.en.md

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

Copy link
Copy Markdown

@sourcery-ai sourcery-ai Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

嗨——我已经review了你的改动,看起来非常棒!


Sourcery 对开源项目是免费的——如果你觉得我们的 review 有帮助,请考虑分享 ✨
帮我变得更有用!请在每条评论上点击 👍 或 👎,我会根据你的反馈来改进后续的 review。
Original comment in English

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


Sourcery is free for open source - if you like our reviews please consider sharing them ✨
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.

@Disaster-Terminator Disaster-Terminator merged commit dd75dff into main May 6, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant