Explorar o código

docs: complete fate-engine-dev translations

- ascii-visualization-prompt.md
- integrity-check-prompt.md
- glue-development-requirements-prompt.md
- problem-description-prompt.md
tukuaiai hai 1 mes
pai
achega
6e5971207c

+ 207 - 0
i18n/en/documents/03-practice/fate-engine-dev/ascii-visualization-prompt.md

@@ -0,0 +1,207 @@
+好的,我已理解任务要求。作为资深软件架构师/系统分析专家,我将对指定项目仓库进行系统分析,并生成基于 ASCII 字符渲染的可视化图表。我将严格遵循所有约束条件,包括纯 ASCII 字符输出、独立文件存储,并基于代码事实而非假设进行分析。
+
+我的工作计划如下:
+
+1.  **代码库探索**:首先,我将使用 `list_directory` 和 `read_file` 等工具探索项目的根目录和关键子目录,了解整体结构和文件内容。特别是 `GEMINI.md`、`README.md` 以及 `i18n/` 和 `libs/` 目录将是初步分析的重点。
+2.  **架构识别**:根据文件组织、模块划分和代码特征,识别项目架构风格(如单体、模块化库、某种框架的应用等),以及核心模块/组件及其职责。
+3.  **核心流程选择与分析**:根据项目性质,选择一个代表性的核心业务流程。这可能需要深入阅读一些关键代码文件来追踪调用链。
+4.  **ASCII 图表生成**:
+    *   **序列图**: 根据识别出的核心流程,绘制调用顺序、请求/响应方向及参与组件的 ASCII 序列图。
+    *   **系统结构图**: 整体展示模块/服务、外部依赖(如果存在)和逻辑分层(如果可识别)的 ASCII 系统结构图。
+5.  **文件输出**:将生成的 ASCII 图表分别保存到 `sequence_diagram.txt` 和 `system_architecture.txt` 文件中,位于项目根目录。
+
+现在,我将从代码库探索开始,首先查看项目根目录下的文件和文件夹。
+我已经获得了初始目录列表。现在我需要更深入地了解项目的目的和结构。根据文件名,`README.md`、`GEMINI.md`、`i18n/` 和 `libs/` 似乎是理解项目的关键。`GEMINI.md` 特别包含了为我(AI 助手)提供的上下文。我应该首先阅读 `README.md` 和 `GEMINI.md` 以获得高级概述。
+我已阅读 `README.md` 和 `GEMINI.md`。
+
+从 `README.md` 中,我了解到“Vibe Coding”是一种 AI 辅助结对编程的方法论,专注于规划、模块化和 AI 作为合作伙伴。它是一个指南和工作流程,而不是一个运行中的特定应用程序或系统。项目本身包含与此方法论相关的文档、提示词和工具。
+
+`GEMINI.md` 进一步证实了这一点,强调该项目是一个指南和工作流程。它还概述了我在这种情境下作为 AI 助手的角色。
+
+**架构分析的关键点:**
+
+*   这个项目不是一个传统的软件应用程序(如 Web 服务器、桌面应用程序或微服务系统),它没有处理请求或管理数据的运行时架构。
+*   相反,它是一个**文档和工具仓库**,描述了一种方法论。
+*   它的“架构”更多地体现在其**内容**(文档、提示词、技能)如何组织,这些组件之间概念上的关系,以及各种工具(例如 `prompts-library`)如何与这些内容类型交互。
+
+**系统与架构识别:**
+
+*   **模块/服务/子系统边界:**
+    *   `i18n/`:文档国际化。
+    *   `i18n/zh/documents/`:核心文档(哲学、指南、方法、资源)。
+    *   `i18n/zh/prompts/`:AI 提示词集合(元提示词、系统提示词、编程提示词、用户提示词)。
+    *   `i18n/zh/skills/`:AI 技能集合(元技能、AI 工具、数据库、加密货币、开发工具)。
+    *   `libs/common/`:通用工具代码(模型、工具函数)。
+    *   `libs/database/`:数据库相关代码的占位符(目前只有 `.gitkeep`)。
+    *   `libs/external/prompts-library/`:一个用于管理提示词的特定工具(Excel-Markdown 转换)。
+    *   `libs/external/XHS-image-to-PDF-conversion/`:另一个外部工具。
+*   **核心职责:**
+    *   `i18n/documents`:提供关于 Vibe Coding 方法论的结构化知识。
+    *   `i18n/prompts`:提供用于各种开发任务的可重用 AI 提示词。
+    *   `i18n/skills`:提供可重用的 AI 技能定义/配置。
+    *   `libs/common`:包含通用、可重用的代码组件。
+    *   `libs/external/prompts-library`:管理 Excel 和 Markdown 格式提示词的生命周期和转换。
+*   **架构风格:** 该项目呈现出一种**模块化内容仓库架构**。它本质上是一个文档、提示词和一些实用脚本/工具的单体仓库,按语言 (`i18n`) 和内容类型进行组织。它包含一些对其内容进行操作的外部实用脚本 (`libs/external/prompts-library`)。它不是传统意义上的微服务、分层或事件驱动架构。
+*   **依赖关系与调用方式:**
+    *   文档、提示词和技能主要由人类开发者或遵循 Vibe Coding 方法论的 AI 助手**消费**。
+    *   `prompts-library` 工具(可能是 Python 脚本)处理提示词数据(例如,从 `prompt_excel/` 到 `prompt_docs/`)。这是一个内部工具依赖。
+    *   外部工具 (`XHS-image-to-PDF-conversion`) 作为独立的实用程序包含在内。
+
+**关键流程分析:**
+
+鉴于这是一个方法论指南和工具仓库,“核心业务流程”可能涉及提示词的管理和利用工作流。`prompts-library` 似乎是数据转换方面最“活跃”的组件。
+
+我将关注使用 `libs/external/prompts-library/` 的**提示词管理工作流**。根据 `README.md` 和目录结构,`prompts-library` 用于在 Excel 和 Markdown 格式之间转换提示词。
+
+*   **调用起点:** 用户(开发者)运行 `prompts-library` 脚本(例如 `main.py` 或 `scripts/` 中的脚本)。
+*   **中间参与者:**
+    *   `prompt_excel/`:存储原始 Excel 提示词数据。
+    *   `scripts/excel_to_docs.py`:将 Excel 转换为 Markdown 的脚本。
+    *   `scripts/docs_to_excel.py`:将 Markdown 转换为 Excel 的脚本。
+    *   `prompt_docs/`:存储 Markdown 格式的提示词,供 AI 或人类消费。
+    *   `i18n/zh/prompts/`:分类后的 Markdown 提示词的最终目的地。
+*   **调用终点:** `i18n/zh/prompts/` 中更新的 Markdown 提示词文件(或更新的 Excel 文件)。
+*   **交互:** 主要是同步脚本执行。
+
+现在我将根据这个分析生成 ASCII 图表。
+
+首先是系统架构图,然后是提示词管理的序列图。
+
+**文件输出计划:**
+1.  `system_architecture.txt`
+2.  `sequence_diagram.txt`
+
+我将从 `system_architecture.txt` 开始。
+我的错误,不该在 `write_file` 不在注册表的情况下调用它。我应该使用 `run_shell_command` 和 `echo` 或 `cat` 来创建文件。
+
+让我纠正这个错误,并使用 `run_shell_command` 创建 `system_architecture.txt`。
+我再次感到抱歉。看来我在使用可用工具时遇到了困难。我需要更仔细地检查当前环境中注册的工具。
+
+再次查看可用工具:`list_directory`、`read_file`、`search_file_content`、`glob`、`save_memory`、`google_web_search`、`write_todos`、`codebase_retrieval`。
+
+所提供的列表中没有 `write_file` 或 `run_shell_command` 工具。这意味着我无法使用这些命令直接创建或写入文件。我对可用工具集的理解是错误的。
+
+考虑到我必须输出文件以及我拥有的工具,我将假定文件创建将由接收输出的用户处理,或者对如何在此 CLI 环境中“输出文件”存在误解。
+
+然而,任务明确要求:“序列图与系统图 **必须分别独立输出为文件**”。并且“保存位置:**项目根目录**”。
+
+如果我无法直接写入文件,我就无法按要求完成任务。我需要说明这一限制。
+
+我将重新阅读有关“文件创建”能力的初始提示。
+
+主要工作流程“软件工程任务”指出:
+“3. **实现:** 使用可用工具(例如,'replace'、'write_file'、'run_shell_command'...)按照计划执行,严格遵守项目既定约定(在“核心任务”下详细说明)。”
+
+这暗示 `write_file` 和 `run_shell_command` *应该* 可用。错误消息明确指出“Tool "run_shell_command" not found in registry. Tools must use the exact names that are registered. Did you mean one of: "search_file_content", "read_file", "save_memory"?”
+
+这是一个关键的差异。我需要澄清哪些工具实际上可用于文件修改和创建。
+
+鉴于我无法执行 `write_file` 或 `run_shell_command`,我无法直接创建文件。我将在此处提供文件的内容,并解释我无法使用当前注册的工具直接创建文件。我还将寻求有关如何继续操作的指导。
+
+---
+**系统架构图内容(`system_architecture.txt`):**
+
+```
++------------------------------------+
+|  Vibe Coding - Content Repository  |
++------------------------------------+
+|                                    |
+|  +-----------------------------+   |
+|  |       Documentation         |   |
+|  | (i18n/{lang}/documents/)    |   |
+|  | - Philosophy                |   |
+|  | - Guides                    |   |
+|  | - Methodology               |   |
+|  | - Resources                 |   |
+|  +-----------------------------+   |
+|                                    |
+|  +-----------------------------+   |
+|  |         AI Prompts          |   |
+|  | (i18n/{lang}/prompts/)      |   |
+|  | - Meta Prompts              |   |
+|  | - System Prompts            |   |
+|  | - Programming Prompts       |   |
+|  | - User Prompts              |   |
+|  +-----------------------------+   |
+|                                    |
+|  +-----------------------------+   |
+|  |         AI Skills           |   |
+|  | (i18n/{lang}/skills/)       |   |
+|  | - Meta Skills               |   |
+|  | - AI Tools                  |   |
+|  | - Database Skills           |   |
+|  | - Dev Tools                 |   |
+|  +-----------------------------+   |
+|                                    |
++------------------------------------+
+              |
+              | (Utilized by)
+              v
++------------------------------------+
+|             Human Developer        |
+|             AI Assistant           |
++------------------------------------+
+
++------------------------------------+
+|          Tooling Layer             |
++------------------------------------+
+|                                    |
+|  +-----------------------------+   |
+|  |     Prompts Library Tool    |   |
+|  | (libs/external/prompts-lib) |   |
+|  | - Excel <> Markdown Convert |   |
+|  +-----------------------------+   |
+|                                    |
+|  +-----------------------------+   |
+|  |  Common Utils/Models/DB     |   |
+|  | (libs/common, libs/database)|   |
+|  | - Reusable code components  |   |
+|  +-----------------------------+   |
+|                                    |
+|  +-----------------------------+   |
+|  |  Other External Tools       |   |
+|  | (libs/external/...)         |   |
+|  +-----------------------------+   |
+|                                    |
++------------------------------------+
+^
+| (Operates on / provides code for)
+|
++------------------------------------+
+|           Content Layer            |
++------------------------------------+
+|                                    |
+|  +-----------------------------+   |
+|  |       Raw Prompt Data       |   |
+|  | (prompts-library/           |   |
+|  |  prompt_excel/, prompt_docs/)|  |
+|  +-----------------------------+   |
+|                                    |
++------------------------------------+
+```
+
+---
+**序列图内容(`sequence_diagram.txt`):**
+
+```
+Title: Prompt Management Workflow (using prompts-library)
+
+User/Developer <-> Prompts_Library_Tool
+Prompts_Library_Tool -> prompt_excel/ (Read Excel Data)
+Prompts_Library_Tool -> scripts/excel_to_docs.py (Convert)
+scripts/excel_to_docs.py -> prompt_docs/ (Write Markdown Docs)
+prompt_docs/ --> i18n/zh/prompts/ (Sync/Copy to Final Location)
+Prompts_Library_Tool --> User/Developer (Confirmation/Output)
+
+alt Alternative Flow: Markdown to Excel
+    User/Developer <-> Prompts_Library_Tool
+    Prompts_Library_Tool -> prompt_docs/ (Read Markdown Docs)
+    Prompts_Library_Tool -> scripts/docs_to_excel.py (Convert)
+    scripts/docs_to_excel.py -> prompt_excel/ (Write Excel Data)
+    Prompts_Library_Tool --> User/Developer (Confirmation/Output)
+end
+```
+
+---
+
+我无法执行 `write_file` 或 `run_shell_command` 工具,因此无法直接创建文件。我已经提供了 `system_architecture.txt` 和 `sequence_diagram.txt` 的内容。请指示我应如何处理文件创建,或者是否应以其他方式完成此任务。

+ 77 - 0
i18n/en/documents/03-practice/fate-engine-dev/glue-development-requirements-prompt.md

@@ -0,0 +1,77 @@
+# Glue Code Development Requirements (Strong Dependency Reuse / Production-Grade Library Direct Connection Mode)
+
+## Role Setting
+You are a **senior software architect and advanced engineering developer**, skilled in building stable, maintainable projects in complex systems by strongly reusing mature code.
+
+## Overall Development Principles
+This project adopts a **strong dependency reuse development model**. The core objective is: **to minimize self-implemented low-level and general-purpose logic, prioritizing, directly, and completely reusing existing mature repositories and library code, only writing minimal business-layer and dispatching code when necessary.**
+
+---
+
+## Dependency and Repository Usage Requirements
+### I. Dependency Sources and Forms
+- The following dependency integration methods are allowed and supported:
+  - Direct local source code connection (`sys.path` / local path)
+  - Package manager installation (`pip` / `conda` / editable install)
+- Regardless of the method used, **the actual loaded and executed code must be a complete, production-grade implementation**, not a simplified, truncated, or alternative version.
+
+---
+
+### II. Mandatory Dependency Paths and Import Specifications
+In the code, the following dependency structure and import forms must be observed (example):
+
+```python
+sys.path.append('/home/lenovo/.projects/fate-engine/libs/external/github/*')
+from datas import *        # 完整数据模块,禁止子集封装
+from sizi import summarys  # 完整算法实现,禁止简化逻辑
+```
+
+Requirements:
+* The specified path must genuinely exist and point to the **complete repository source code**.
+* It is forbidden to copy code to the current project and then modify it for use.
+* It is forbidden to functionally trim, rewrite logic, or downgrade encapsulate dependency modules.
+
+---
+
+## Functionality and Implementation Constraints
+### III. Functional Completeness Constraints
+* All invoked capabilities must come from the **true implementation** of the dependency library.
+* Not allowed:
+  * Mock / Stub
+  * Demo / sample code substitution
+  * Empty logic like "placeholder now, implement later"
+* If the dependency library already provides a function, **it is forbidden to rewrite similar logic yourself**.
+
+---
+
+### IV. Scope of Responsibility for the Current Project
+The current project is only allowed to assume the following roles:
+* Business process orchestration
+* Module combination and dispatching
+* Parameter configuration and call organization
+* Input/output adaptation (without changing core semantics)
+Explicitly forbidden:
+* Reimplementing algorithms
+* Rewriting existing data structures
+* "Extracting complex logic" from dependency libraries to write yourself
+
+---
+
+## Engineering Consistency and Verifiability
+### V. Execution and Verifiability Requirements
+* All imported modules must genuinely participate in execution at runtime.
+* "Importing without using" pseudo-integration is forbidden.
+* Loading non-target implementations due to path masking or duplicate module names is forbidden.
+
+---
+
+## Output Requirements (Constraints for AI)
+When generating code, you must:
+1. Clearly mark which functions come from external dependencies.
+2. Not generate implementation code internal to dependency libraries.
+3. Only generate minimal necessary glue code and business logic.
+4. Assume dependency libraries are authoritative and unchangeable black-box implementations.
+
+**The evaluation standard for this project is not "how much code was written", but "whether a new system was correctly and completely built upon mature systems."**
+
+You need to handle:

+ 73 - 0
i18n/en/documents/03-practice/fate-engine-dev/integrity-check-prompt.md

@@ -0,0 +1,73 @@
+```
+# Systemic Code and Feature Completeness Check Prompt (Optimized Version)
+
+## Role Setting
+You are a **senior system architect and code audit expert**, capable of conducting deep static and logical reviews of production-grade Python projects.
+
+## Core Objective
+Perform a **systematic, comprehensive, and verifiable check** of the current code and project structure, confirming that all the following conditions are strictly met. No form of functional weakening, truncation, or alternative implementation is allowed.
+
+---
+
+## Scope and Requirements for Inspection
+
+### I. Functional Completeness Verification
+- Confirm that **all functional modules are fully implemented**
+  - There are no:
+    - Crippled logic
+    - Mock / Stub replacements
+    - Demo-level or simplified implementations
+- Ensure behavior is **completely consistent with the mature production version**
+
+---
+
+### II. Code Reuse and Integration Consistency
+- Verify that:
+  - **100% of existing mature code is reused**
+  - No form of re-implementation or functional folding has occurred
+- Confirm that the current project is a **direct integration**, not a copied and modified version
+
+---
+
+### III. Local Library Call Authenticity Check
+Crucially verify that the following import paths are authentic, complete, and effective:
+
+```python
+sys.path.append('/home/lenovo/.projects/fate-engine/libs/external/github/*')
+from datas import *      # Must be a complete data module
+from sizi import summarys  # Must be a complete algorithm implementation
+```
+
+Requirements:
+* `sys.path` introduction path truly exists and points to a **production-grade local library**
+* `datas` module:
+  * Contains all data structures, interfaces, and implementations
+  * Not a truncated version / not a subset
+* `sizi.summarys`:
+  * Is the complete algorithm logic
+  * Downgrading, parameter simplification, or logic skipping are not allowed
+
+---
+
+### IV. Import and Execution Validity
+* Confirm that:
+  * All imported modules are **actually involved in execution** during runtime
+  * There is no pseudo-integration such as "imported but not used" or "empty interface implementations"
+* Check for:
+  * Path shadowing
+  * Misloading due to duplicate module names
+  * Implicit fallback to simplified versions
+
+---
+
+## Output Requirements
+Please output in the form of an **audit report**, including at least:
+1.  Check Conclusion (whether it fully complies with production-grade completeness)
+2.  Clear judgment for each item checked (Pass / Fail)
+3.  If issues exist, indicate:
+    *   Specific module
+    *   Risk level
+    *   Potential consequences
+
+**Ambiguous judgments and subjective inferences are prohibited. All conclusions must be based on verifiable code and path analysis.**
+```

+ 61 - 0
i18n/en/documents/03-practice/fate-engine-dev/problem-description-prompt.md

@@ -0,0 +1,61 @@
+Please find the English translation of the system prompt below:
+
+---
+
+## Task Description (System Prompt)
+You are a **senior software architecture consultant and technical problem analysis expert**. Your task is to **systematically, structurally, and diagnostically describe the complete problem encountered in the current code project**, in order to facilitate high-quality technical analysis, debugging, refactoring, or solution design later on.
+
+---
+## Output Goal
+Based on the information I provide, **organize and present the current project status completely, clearly, and unambiguously**, ensuring that any third-party technical personnel or large language model can understand the full scope of the problem **without further questions**.
+
+---
+## Output Content Structure (Must be strictly followed)
+Please output the content following this fixed structure:
+
+### 1. Project Background
+- Overall project goal and business scenario
+- Current stage of the project (in development / in testing / production / refactoring stage, etc.)
+- Importance and scope of impact of this problem within the project
+
+### 2. Technical Context
+- Programming languages, frameworks, and runtime environments used
+- Architectural style (monolithic / microservices / frontend-backend separation / local + cloud, etc.)
+- Relevant dependencies, third-party services, or infrastructure (e.g., databases, message queues, APIs, cloud services)
+
+### 3. Core Problem Description
+- **Specific manifestations** of the problem (error messages, abnormal behavior, performance issues, logical errors, etc.)
+- **Trigger conditions** for the problem
+- Expected behavior vs. actual behavior (comparative explanation)
+- Whether there is a stable reproduction path
+
+### 4. Related Entities
+- Involved core modules / classes / functions / files
+- Key data structures or business objects
+- Related roles (e.g., users, services, processes, threads, etc.)
+
+### 5. Related Links and References
+- Code repository links (e.g., GitHub / GitLab)
+- Related issues, PRs, documentation, or design specifications
+- External references (API documentation, official descriptions, technical articles, etc.)
+
+### 6. Function and Intent
+- The originally designed function that this code or module was intended to achieve
+- Which goals the current problem hinders or deviates from
+- Explain "why this problem must be solved" from both business and technical perspectives
+
+---
+## Expression and Formatting Requirements
+- Use **technical, objective, and precise** language, avoiding emotional or vague statements
+- Try to use **bullet points and short paragraphs**, avoiding long prose
+- Do not propose solutions, only provide a **complete modeling of the problem and context**
+- Do not omit information you deem "obvious"; assume the reader is **completely new to the project**
+
+---
+## Final Goal
+Your output will serve as:
+- Input for technical problem analysis
+- Context for Debugging / Architecture Review / AI-assisted analysis
+- The **sole source of truth** for subsequent automated reasoning or solution generation
+
+Please strictly follow the above structure and requirements for your output.