ok Merge branch 'main' of github.com:modelscope/ms-agent into release/1.5

Author: wangxingjun778

README.md

@@ -60,14 +60,17 @@ MS-Agent is a lightweight framework designed to empower agents with autonomous e
   - Support financial data collection via [Akshare](https://github.com/akfamily/akshare) and [Baostock](http://baostock.com/mainContent?file=home.md)
   - Support DagWorkflow for workflow orchestration
   - Optimize the DeepResearch workflow for stability and efficiency
+  - FinResearch official documentation: [FinResearch Doc](https://ms-agent-en.readthedocs.io/en/latest/Projects/FinResearch.html)
+  - DEMO: [FinResearchStudio](https://modelscope.cn/studios/ms-agent/FinResearch)
+  - Examples: [FinResearchExamples](https://www.modelscope.cn/models/ms-agent/fin_research_examples)
 
 * 🚀 Nov 07, 2025: Release MS-Agent v1.4.0, which includes the following updates:
   - 🔥 We present [**MS-Agent Skills**](projects/agent_skills/README.md), an **Implementation** of [Anthropic-Agent-Skills](https://docs.claude.com/en/docs/agents-and-tools/agent-skills) Protocol.
   - 🔥 Add [Docs](https://ms-agent-en.readthedocs.io/en) and [中文文档](https://ms-agent.readthedocs.io/zh-cn)
   - 🔥 Support Sandbox Framework [ms-enclave](https://github.com/modelscope/ms-enclave)
 
 * 🚀 Sep 22, 2025: Release MS-Agent v1.3.0, which includes the following updates:
-  - 🔥 Support [Code Scratch](projects/code_scratch/README.md)
+  - 🔥 Support [Code Scratch](projects/code_genesis/README.md)
   - Support `Memory` for building agents with long-term and short-term memory
   - Enhance the DeepResearch workflow
   - Support RAY for accelerating document information extraction
@@ -408,7 +411,7 @@ This project provides a framework for **Code Scratch**, enabling agents to auton
 Generate a complete ai workspace homepage with the following command:
 
 ```shell
-PYTHONPATH=. openai_api_key=your-api-key openai_base_url=your-api-url python ms_agent/cli/cli.py run --config projects/code_scratch --query 'Build a comprehensive AI workspace homepage' --trust_remote_code true
+PYTHONPATH=. openai_api_key=your-api-key openai_base_url=your-api-url python ms_agent/cli/cli.py run --config projects/code_genesis --query 'Build a comprehensive AI workspace homepage' --trust_remote_code true
 ```
 
 The generated code will be output to the `output` folder in the current directory.
@@ -418,7 +421,7 @@ The generated code will be output to the `output` folder in the current director
 - **Coding Phase**: Execute coding tasks in intelligent file groups → Generate complete code structure
 - **Refine Phase**: Auto-compilation → Error analysis → Iterative bug fixing → Human evaluation loop
 
-For more details, refer to [Code Scratch](projects/code_scratch/README.md).
+For more details, refer to [Code Scratch](projects/code_genesis/README.md).
 
 <br>
 
@@ -523,7 +526,7 @@ OPENAI_API_KEY=xxx-xxx T2I_API_KEY=ms-xxx-xxx MANIM_TEST_API_KEY=xxx-xxx ms-agen
 
 #### References
 
-- [Complete Documentation](./docs/zh/Projects/短视频生成.md)
+- [Complete Documentation](./docs/zh/Projects/video-generation)
 
 
 <br>
@@ -546,7 +549,7 @@ We are committed to continuously improving and expanding the MS-Agent framework
   - [ ] Improve stabilises
 - [ ] **Multimodal Agentic Search** – Supporting large-scale multimodal document retrieval and generation of search results combining text and images.
 - [ ] Enhanced **Agent Skills** – Providing a richer set of predefined skills and tools to expand agent capabilities and enabling multi-skill collaboration for complex task execution.
-- [ ] **Agent-Workstation** - An unified WebUI with one-click local deployment support with combining all agent capabilities of MS-Agent, such as AgentChat, MCP, AgentSkills, DeepResearch, DocResearch, CodeScratch, etc.
+- [ ] **Agent-Workstation** - An unified WebUI with one-click local deployment support with combining all agent capabilities of MS-Agent, such as AgentChat, MCP, AgentSkills, DeepResearch, DocResearch, CodeGenesis, etc.
 
 
 ## License

README_ZH.md

@@ -58,14 +58,17 @@ MS-Agent是一个轻量级框架，旨在为智能体提供自主探索能力。
   - 支持基于[Akshare](https://github.com/akfamily/akshare)和[Baostock](http://baostock.com/mainContent?file=home.md)的金融数据获取工具
   - 支持以Dag形式编排工作流
   - 优化DeepResearch稳定性与效率
+  - 官方文档： [金融深度研究](https://ms-agent.readthedocs.io/zh-cn/latest/Projects/fin-research.html)
+  - 魔搭创空间DEMO: [FinResearchStudio](https://modelscope.cn/studios/ms-agent/FinResearch)
+  - 报告样例: [FinResearchExamples](https://www.modelscope.cn/models/ms-agent/fin_research_examples)
 
 * 🚀 2025.11.07：发布MS-Agent v1.4.0，包含以下更新：
   - 🔥 新增 [**MS-Agent Skills**](projects/agent_skills/README.md), 基于 [**Anthropic-Agent-Skills**](https://docs.claude.com/en/docs/agents-and-tools/agent-skills) 协议实现.
   - 🔥 新增 [中文文档](https://ms-agent.readthedocs.io/zh-cn)和[英文文档](https://ms-agent-en.readthedocs.io/en)
   - 🔥 支持沙箱框架 [ms-enclave](https://github.com/modelscope/ms-enclave)
 
 * 🚀 2025.9.22：发布MS-Agent v1.3.0，包含以下更新：
-  - 🔥 支持[Code Scratch](projects/code_scratch/README.md)
+  - 🔥 支持[Code Scratch](projects/code_genesis/README.md)
   - 支持`Memory`用于构建具有长期和短期记忆的智能体
   - 增强DeepResearch工作流
   - 支持RAY加速文档信息提取
@@ -404,7 +407,7 @@ pip install ms-agent
 使用以下命令生成完整的 AI 工作空间主页：
 
 ```shell
-PYTHONPATH=. openai_api_key=your-api-key openai_base_url=your-api-url python ms_agent/cli/cli.py run --config projects/code_scratch --query 'Build a comprehensive AI workspace homepage' --trust_remote_code true
+PYTHONPATH=. openai_api_key=your-api-key openai_base_url=your-api-url python ms_agent/cli/cli.py run --config projects/code_genesis --query 'Build a comprehensive AI workspace homepage' --trust_remote_code true
 ```
 
 生成的代码将输出到当前目录的 `output` 文件夹中。
@@ -414,7 +417,7 @@ PYTHONPATH=. openai_api_key=your-api-key openai_base_url=your-api-url python ms_
 - **编码阶段**：在智能文件组中执行编码任务 → 生成完整的代码结构
 - **完善阶段**：自动编译 → 错误分析 → 迭代错误修复 → 人工评估循环
 
-更多详情，请参考 [Code Scratch](projects/code_scratch/README.md)。
+更多详情，请参考 [Code Scratch](projects/code_genesis/README.md)。
 
 <br>
 
@@ -521,7 +524,7 @@ OPENAI_API_KEY=xxx-xxx T2I_API_KEY=ms-xxx-xxx MANIM_TEST_API_KEY=xxx-xxx ms-agen
 
 #### 3) 参考文档
 
-- [完整文档](./docs/zh/Projects/短视频生成.md)
+- [完整文档](./docs/zh/Projects/video-generation)
 
 <br>
 
@@ -543,7 +546,7 @@ OPENAI_API_KEY=xxx-xxx T2I_API_KEY=ms-xxx-xxx MANIM_TEST_API_KEY=xxx-xxx ms-agen
   - [ ] 提升稳定度
 - [ ] 多模态检索增强生成 **Multimodal Agentic Search** - 支持大规模多模态文档检索和图文检索结果生成。
 - [ ] 增强的 **Agent Skills** - 提供更多预定义的技能和工具，提升智能体技能边界，并支持多技能协作，完成复杂任务执行。
-- [ ] 统一的WebUI **Agent-Workstation**，支持本地一键部署，集成了 MS-Agent 的所有智能体能力，如 AgentChat、MCP、AgentSkills、DeepResearch、DocResearch、CodeScratch 等。
+- [ ] 统一的WebUI **Agent-Workstation**，支持本地一键部署，集成了 MS-Agent 的所有智能体能力，如 AgentChat、MCP、AgentSkills、DeepResearch、DocResearch、CodeGenesis 等。
 
 
 ## 许可证

docs/en/Components/Config.md

@@ -1,3 +1,9 @@
+---
+slug: Config
+title: Config & Parameters
+description: Ms-Agent Configuration & Parameters
+---
+
 # Config
 
 MS-Agent uses a yaml file for configuration management, typically named `agent.yaml`, which allows different scenarios to read different configuration files. The specific fields contained in this file are:
@@ -98,7 +104,7 @@ tools:
       - map_geo
 ```
 
-For the complete list of supported tools and custom tools, please refer to [here](./工具.md)
+For the complete list of supported tools and custom tools, please refer to [here](./Tools.md)
 
 ## Others
 

docs/en/Components/ContributorGuide.md

@@ -1,3 +1,9 @@
+---
+slug: ContributorGuide
+title: Contributor Guide
+description: Ms-Agent Contributor Guide
+---
+
 # Contributor Guide
 
 ## Workflow Contribution

docs/en/Components/LLMAgent.md

@@ -1,3 +1,9 @@
+---
+slug: LLMAgent
+title: LLMAgent for basic usage
+description: Ms-Agent LLMAgent for basic usage
+---
+
 # LLM Agent
 
 The basic agent class in MS-Agent is [LLMAgent](https://github.com/modelscope/ms-agent/blob/main/ms_agent/agent/llm_agent.py). MS-Agent's conversational capabilities and tool invocation are all handled through this class. The diagram is as follows:
@@ -81,4 +87,4 @@ In this case, agent.yaml will use your custom agent class instead of loading the
 
 1. A basic agent.yaml: https://www.modelscope.cn/models/ms-agent/simple_agent
 2. Agent with external code: https://www.modelscope.cn/models/ms-agent/simple_agent_code
-3. Using callbacks to complete complex workflows: https://github.com/modelscope/ms-agent/tree/main/projects/code_scratch
+3. Using callbacks to complete complex workflows: https://github.com/modelscope/ms-agent/tree/main/projects/code_genesis

docs/en/Components/SupportedModels.md

@@ -1,3 +1,9 @@
+---
+slug: SupportedModels
+title: Supported Models
+description: Ms-Agent Supported Models
+---
+
 # Supported Models
 
 MS-Agent supports large model APIs with the standard OpenAI interface. In addition, to facilitate usage by different model providers, it also provides distinct configuration keys in YAML.

docs/en/Components/Tools.md

@@ -1,3 +1,9 @@
+---
+slug: Tools
+title: Tools
+description: Ms-Agent Tools
+---
+
 # Tools
 
 ## Tool List
@@ -145,7 +151,7 @@ ms-agent run --config xxx/xxx --mcp_server_file ./mcp.json
 
 ### Configuring yaml file
 
-Additional tools can be added in tools within yaml. Refer to [Configuration and Parameters](./Config.md#Tool%20Configuration)
+Additional tools can be added in tools within yaml. Refer to [Configuration and Parameters](./Config.md) for details.
 
 ### Writing new tools
 
@@ -207,12 +213,7 @@ class CustomTool(ToolBase):
                     }),
             ]
         }
-        return {
-            'custom_tool': [
-                t for t in tools['custom_tool']
-                if t['tool_name'] not in self.exclude_functions
-            ]
-        }
+        return tools
 
     async def foo(self, foo_arg1) -> str:
         ...

docs/en/Components/Workflow.md

@@ -1,8 +1,14 @@
+---
+slug: Workflow
+title: Workflow
+description: Ms-Agent Workflow
+---
+
 # Workflow
 
 MS-Agent supports workflow execution. Workflows are also configured by yaml files. Workflows are composed of different Agents to complete more complex tasks. Currently, MS-Agent's workflow supports two types of Agents:
 
-- LLMAgent: This Agent is introduced in [Basic Agent](./Basic%20Agent.md), which is a basic Agent loop that integrates LLM reasoning
+- LLMAgent: This Agent is introduced in [Basic Agent](./LLMAgent.md), which is a basic Agent loop that integrates LLM reasoning
 - CodeAgent: Contains only a run method, which is a pure code execution process that can provide custom code implementation
 
 ## ChainWorkFlow

docs/en/GetStarted/Installation.md

@@ -1,3 +1,9 @@
+---
+slug: Installation
+title: Installation
+description: Ms-Agent Installation Guide
+---
+
 # Installation
 
 ## Wheel Package Installation
@@ -18,7 +24,7 @@ cd ms-agent
 pip install -e .
 ```
 
-If using DeepResearch or CodeScratch, there may be additional dependencies. Please install according to the corresponding README documentation.
+If using DeepResearch or CodeGenesis, there may be additional dependencies. Please install according to the corresponding README documentation.
 
 ## Images
 

docs/en/GetStarted/Introduction.md

@@ -1,11 +1,17 @@
+---
+slug: Introduction
+title: Introduction
+description: Ms-Agent Introduction
+---
+
 # Quick Start
 
 MS-Agent is the official Agent framework launched by the ModelScope community. This framework is committed to using a clear and simple universal capability framework to solve proprietary problems in several domains.
 
 Currently, the domains we are exploring include:
 
 - DeepResearch: Generate in-depth research reports in the scientific research field
-- CodeScratch: Generate runnable software project code from requirements
+- CodeGenesis: Generate runnable software project code from requirements
 - General domain: MS-Agent adapts to general LLM conversation scenarios and is compatible with MCP tool calling
 
 MS-Agent is also the backend agent framework for [mcp-playground](https://modelscope.cn/mcp/playground) on the ModelScope official website. If developers are interested in the above domains, or hope to learn Agent technology principles and conduct secondary development, welcome to use MS-Agent.
@@ -56,4 +62,4 @@ The above two examples have the same effect and both can conduct multi-turn conv
 
 - A [more comprehensive example](https://github.com/modelscope/ms-agent/tree/main/examples)
 - DeepResearch [example](https://github.com/modelscope/ms-agent/tree/main/projects/deep_research)
-- CodeScratch [example](https://github.com/modelscope/ms-agent/blob/main/projects/code_scratch/README.md)
+- CodeGenesis [example](https://github.com/modelscope/ms-agent/blob/main/projects/code_genesis/README.md)