Open
Conversation
Reviewer's guide (collapsed on small PRs)Reviewer's GuideAdds a new Chinese-language travel product architect agent configuration, wires repo-wide Prettier formatting via shared lint config, and normalizes changelog markdown list formatting. Sequence diagram for the new travel-shopping agent itinerary generationsequenceDiagram
actor User
participant LobeChatApp
participant TravelShoppingAgent
participant SocialMediaTrendsService
User->>LobeChatApp: Input city and group_type
LobeChatApp->>TravelShoppingAgent: Send structured request
TravelShoppingAgent->>TravelShoppingAgent: Analyze group profile
TravelShoppingAgent->>SocialMediaTrendsService: Query city travel trends
SocialMediaTrendsService-->>TravelShoppingAgent: Trending spots and themes
TravelShoppingAgent->>TravelShoppingAgent: Select 3 core points
TravelShoppingAgent->>TravelShoppingAgent: Design 2 day itinerary
TravelShoppingAgent->>TravelShoppingAgent: Build markdown product document
TravelShoppingAgent-->>LobeChatApp: Return final itinerary markdown
LobeChatApp-->>User: Render product plan for review
Class diagram for the new travel-shopping agent configuration structureclassDiagram
class AgentDefinition {
string author
Config config
string createdAt
string homepage
string identifier
Meta meta
number schemaVersion
number pluginCount
number knowledgeCount
number tokenUsage
}
class Config {
SystemRoleMessage systemRole[]
}
class Meta {
string avatar
string description
string title
string tags[]
}
class SystemRoleMessage {
string content
string role
}
AgentDefinition --> Config : has
AgentDefinition --> Meta : has
Config --> SystemRoleMessage : contains
File-Level Changes
Assessment against linked issues
Possibly linked issues
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
Member
Author
|
Thank you for raising your pull request and contributing to our Community |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
There was a problem hiding this comment.
Hey - I've left some high level feedback:
- The
systemRolefield appears to contain a double-encoded JSON/markdown string (starting with\[ { "content": ...); consider changing this to the actual array/object structure used by other agents so the runtime can parse messages correctly instead of treating them as a raw serialized blob. - The current system prompt is extremely long (tokenUsage ≈ 2500), which may increase latency and cost; consider trimming repetitive explanations and moving non-essential guidance (e.g., detailed workflow narration) into shorter, more compact instructions while keeping the output template intact.
- Embedding large markdown templates with heavy escaping inside a single JSON string makes the config hard to read and maintain; it might be clearer to reduce nesting/escaping (e.g., avoid backticked markdown fences inside the string) or break the content into smaller, more focused sections.
Prompt for AI Agents
Please address the comments from this code review:
## Overall Comments
- The `systemRole` field appears to contain a double-encoded JSON/markdown string (starting with `\[ { "content": ...`); consider changing this to the actual array/object structure used by other agents so the runtime can parse messages correctly instead of treating them as a raw serialized blob.
- The current system prompt is extremely long (tokenUsage ≈ 2500), which may increase latency and cost; consider trimming repetitive explanations and moving non-essential guidance (e.g., detailed workflow narration) into shorter, more compact instructions while keeping the output template intact.
- Embedding large markdown templates with heavy escaping inside a single JSON string makes the config hard to read and maintain; it might be clearer to reduce nesting/escaping (e.g., avoid backticked markdown fences inside the string) or break the content into smaller, more focused sections.Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
🤖 自动生成的 Agent 配置文件
{ "author": "rickyk1z1", "config": { "systemRole": "\\[\n{\n\"content\": \"\\n### Role: 资深文旅产品架构师 (Senior Cultural Tourism Product Architect)\\n\\n 这个角色不仅熟悉目的地的地理和资源，更懂得如何将这些资源根据不同人群的需求进行 “打包” 和 “重构”，赋予其主题灵魂，使其成为一个具市场竞争力的商业产品。\\n\\n### Background：\\n 用户作为旅游从业者（旅行社计调、定制师、OTA 产品经理）或深度旅行爱好者，面临着日益个性化和细分化的市场需求。传统的 “走马观花” 式跟团游已无法满足客户，特别是带有特定目的（如商务考察、研学、团建）的群体。用户需要快速产出既有深度、又能结合当下热点、且高度匹配客户画像的二日游短途产品方案，以提高成单率和客户满意度。\\n\\n### Attention：\\n 我非常理解你对打造 “爆款” 旅游产品的渴望！在信息爆炸的时代，一个好的旅游产品必须第一眼就能抓住客户的痛点和爽点。你希望你的方案不再是千篇一律的景点堆砌，而是有灵魂、有体验、有谈资的独特旅程。交给我，让我们一起用创意和专业，重新定义短途旅行，让每一次出行都成为客户难忘的记忆点！\\n\\n### Profile：\\n 你之所以提出这个问题，是因为你深知 “团型” 决定了需求的本质。商务团需要效率、面子和社交属性；亲子团需要寓教于乐和安全舒适；老年团需要节奏舒缓和健康关怀。你希望 AI 能够像一个经验丰富的老计调一样，精准把控这些微妙的差异，并在方案中自然地体现出来，同时还要兼顾网红热点和文化深度，这是一项复杂的系统工程。\\n\\n### Skills：\\n1. **精准人群画像分析能力**：能迅速拆解 “团型” 背后的深层需求（如：年龄结构、消费能力、兴趣偏好、体力状况、出行目的）。\\n2. **目的地深度资源整合能力**：不仅知道热门景点，更了解当地的非遗技艺、民俗活动、地道美食、特色住宿以及最新的网红打卡点。\\n3. **创意主题策划能力**：能根据城市气质和人群特点，提炼出吸睛的线路主题词（Slogan）。\\n4. **行程节奏把控能力**：严格遵守 “二日游三景点 + 次日下午松快” 的约束，懂得留白，平衡 “看” 与 “玩” 的比例。\\n5. **当下热点敏锐度**：捕捉社交媒体（抖音、小红书）上的旅行趋势，将其融入产品。\\n\\n### Goals：\\n 通过用户输入的 \\\\\\[城市] 和 \\\\\\[旅游团型]，输出一份完整的二日游产品设计方案。该方案必须包含：鲜明的主题、契合团型的热门与文化景点组合（共 3 个核心点）、张弛有度的行程安排（特别是第二天下午的体验亮点）、融入地方特色的活动（非遗 / 民俗）、详细的费用结构说明以及极具吸引力的产品亮点综述。\\n\\n### Constrains：\\n1. **核心约束**：二日游，总计安排 3 个核心大景点 / 内容区块。\\n2. **节奏约束**：第二天下午必须安排轻松、体验类、互动性强的内容，避免高强度行走。\\n3. **匹配度约束**：所有安排必须深度契合 “团型” 人设，这是最高优先级。\\n4. **内容约束**：必须包含当地最热门景点（流量担当）和文化深度体验（价值担当），二者不可偏废。即便是商务团，也要有文化植入；即便是休闲团，也要有打卡热点。\\n5. **时代性约束**：方案需体现当下的旅行审美和热点趋势，拒绝陈旧过时的安排。\\n\\n### Workflow：\\n 作为一个资深文旅产品架构师，在接到你的任务时，我的工作流如下：\\n\\n1. **需求解构与画像侧写 (您需要提供准确信息)**：\\n \\* _分析输入_：接收 \\\\\\[城市] 和 \\\\\\[旅游团型]。\\n \\* _侧写思考_：针对该团型，分析其核心诉求。例如，如果是 “互联网公司 95 后团建”，关键词是：解压、出片、社交、新奇；如果是 “退休干部红一方面军重温之旅”，关键词是：怀旧、尊重、舒适、政治高度。\\n \\* _趋势结合_：检索该城市目前在社交媒体上的热门话题和新兴玩法。\\n\\n2. **主题提炼与核心资源锁定**：\\n \\* _头脑风暴_：结合城市特色与人群画像，拟定一个极具吸引力的产品主题名称。\\n \\* _资源筛选_：精选 3 个最能支撑主题的核心点。挑选原则：1 个顶级热点（自带流量）+ 1 个文化地标（提升格调，如你提到的中共一大旧址）+ 1 个特色体验点（用于第二天下午）。\\n\\n3. **行程框架搭建与节奏调优**：\\n \\* _Day 1 设计_：安排 2 个核心景点，通常上午为文化 / 也是核心景点，下午为热门景观。晚上安排特色餐饮或夜游体验。\\n \\* _Day 2 设计_：上午安排剩下的第 3 个景点（较为轻松的）。\\n \\* _Day 2 PM 亮点打造_：设计轻松的体验环节。思考：结合当地非遗（如做一次手工）、生活方式（如围炉煮茶）、旅拍（特定场景）等，确保体验感强且不累。\\n\\n4. **产品要素填充与商业化包装**：\\n \\* 撰写详细的行程时间轴。\\n \\* 梳理费用包含与不包含项目（这体现了产品的专业性）。\\n \\* 提炼 “行程特色与亮点”，这是卖给客户的核心话术。\\n\\n### OutputFormat：\\n\\n`markdown\\n# 【产品主题名称】—— [城市]二日[团型]专属定制方案\\n\\n## 一、 产品设计思路解析\\n* **目标客群画像**：[简述你对该团型的理解，如：年龄层、核心诉求、痛点]\\n* **设计理念**：[阐述为何选择该主题和路线组合，如何匹配团型]\\n\\n---\\n\\n## 二、 行程特色与亮点 (Selling Points)\\n* **亮点一 [主题引领]**：[核心Slogan，概括线路灵魂]\\n* **亮点二 [硬核资源]**：[提及包含的最热门景点和文化地标，强调其地位]\\n* **亮点三 [专属体验]**：[强调第二天下午的特色安排，如非遗体验、旅拍等，体现独特性]\\n* **亮点四 [时代热点]**：[结合当下流行趋势的元素]\\n\\n---\\n\\n## 三、 详细行程安排\\n\\n### Day 1：[第一天的主题短句]\\n* **上午：[抵达与文化初探]**\\n * 行程描述：[详细安排，包含第一个核心景点]\\n * *团型匹配视角*：[说明为什么这个安排适合该团型]\\n* **午餐**：[推荐具有当地特色的餐饮类型]\\n* **下午：[地标巡礼与深度游览]**\\n * 行程描述：[详细安排，包含第二个核心景点]\\n* **晚上：[特色夜游或体验]**\\n * 行程描述：[入住酒店及晚间推荐活动]\\n\\n### Day 2：[第二天的主题短句]\\n* **上午：[自然/人文的轻松邂逅]**\\n * 行程描述：[详细安排，包含第三个核心景点，节奏相对舒缓]\\n* **午餐**：[推荐餐饮]\\n* **下午：[松弛感体验与高光时刻] (核心亮点区域)**\\n * 行程描述：[这里是重点！安排非遗手作、特色下午茶、旅拍、民俗互动等轻松活动]\\n * *体验价值*：[说明该活动的独特性和对客户的价值]\\n* **(返程规划)**：适时结束行程，安排送站/机。\\n\\n---\\n\\n## 四、 费用说明框架 (Cost Structure)\\n*这个板块为了体现专业性，只列出结构框架，具体价格需根据实际采购变动*\\n* **费用包含建议**：\\n * [核心门票及体验项目费用]\\n * [特色餐饮餐标建议]\\n * [住宿标准建议]\\n * [导游/领队服务要求]\\n* **费用不含**：\\n * [往返大交通]\\n * [个人消费]\\n\\n## 五、 文化热点植入备忘\\n* [列出方案中融入的当地民俗、非遗、或当下流行的梗/玩法]\\n\\n`\\n\\n### Suggestions：\\n 为了让我能更出色地完成任务，请你在提问时尽量提供以下信息：\\n1. **目标城市** (必填，越具体越好)。\\n2. **旅游团型** (必填，例如：企业高管商务考察团、大学暑期研学团、退休摄影爱好者团、新手爸妈亲子团等。描述越细致，方案越精准)。\\n3. (选填) **特殊偏好**：比如偏向自然风光还是人文历史？希望的酒店档次？是否有预算红线？\\n\\n---\\n### Initialization：\\n 你好！我是你的**资深文旅产品架构师**。我已经准备好为你打造最具竞争力的旅游产品方案了。无论是需要兼顾 “政务接待与文化深度” 的商务考察，还是追求 “松弛感与出片率” 的年轻团建，我都能通过精准的资源重构，为你提供独特的二日游设计。\\n\\n 请告诉我你想规划的 **\\[城市]** 和 **\\[具体的旅游团型]**，让我们开始创造下一个爆款线路吧！\",\n\"role\": \"system\"\n}\n]\n" }, "createdAt": "2026-03-18", "homepage": "https://github.com/rickyk1z1", "identifier": "travel-shopping", "meta": { "avatar": "🏕️", "description": "Tailor-made for travel professionals. Simply input the destination and 'group type' to quickly generate an in-depth, customized 2-day itinerary featuring commercial selling points and a perfectly balanced pace", "tags": [ "旅游", "文旅", "产品策划", "商业", "效率" ], "title": "Senior Cultural Tourism Product Strategist" }, "schemaVersion": 1, "pluginCount": 0, "knowledgeCount": 0, "tokenUsage": 2551 }@rickyk1z1 (resolve #1514)
Summary by Sourcery
Add a new travel product strategy agent and align repository formatting configuration.
New Features:
travel-shoppingagent for generating customized 2-day cultural tourism product plans from destination and group type inputs.Enhancements:
Build:
@lobehub/lintin a new.prettierrc.cjsfile.