Feat: refine tools

.gitignore

@@ -31,6 +31,8 @@ wheels/
 /package
 /temp
 **/tmp/
+.env*
+.claude-trace/
 /apps/agentfabric/tmp/
 MANIFEST
 
@@ -148,6 +150,7 @@ apps/agentfabric/config/local_user/*
 *.pt
 .run/
 .run/*
+.claude*
 
 # ast template
 ast_index_file.py

.pre-commit-config.yaml

@@ -1,24 +1,23 @@
-
-
-
+default_language_version:
+  python: python3.11
 repos:
   - repo: https://github.com/pycqa/flake8.git
-    rev: 4.0.0
+    rev: 7.3.0
     hooks:
       - id: flake8
         exclude: ^(thirdparty/|examples/|tests/|projects/agent_skills/|projects/fin_research/examples/|ms_agent/utils/prompts\.py)
   - repo: https://github.com/PyCQA/isort.git
-    rev: 4.3.21
+    rev: 5.13.2
     hooks:
       - id: isort
         exclude: ^(examples/|projects/fin_research/examples/|projects/agent_skills/|tests/)
   - repo: https://github.com/pre-commit/mirrors-yapf.git
-    rev: v0.30.0
+    rev: v0.32.0
     hooks:
       - id: yapf
         exclude: ^(thirdparty/|examples/|projects/fin_research/examples/|projects/agent_skills/|tests/)
   - repo: https://github.com/pre-commit/pre-commit-hooks.git
-    rev: v3.1.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
         exclude: ^(thirdparty/|tests/|projects/fin_research/examples/|projects/agent_skills/)

docs/en/Components/Config.md

@@ -102,6 +102,14 @@ tools:
     url: https://mcp.api-inference.modelscope.net/xxx/sse
     exclude:
       - map_geo
+  # Local codebase / document search (sirchmunk), exposed as the `localsearch` tool
+  localsearch:
+    paths:
+      - ./src
+      - ./docs
+    work_path: ./.sirchmunk
+    mode: FAST
+    # Optional: llm_api_key, llm_base_url, llm_model_name (else inherited from `llm`)
 ```
 
 For the complete list of supported tools and custom tools, please refer to [here](./Tools.md)
@@ -220,19 +228,19 @@ In addition to yaml configuration, MS-Agent also supports several additional com
 
 > Any configuration in agent.yaml can be passed in with new values via command line, and also supports reading from environment variables with the same name (case insensitive), for example `--llm.modelscope_api_key xxx-xxx`.
 
-- knowledge_search_paths: Knowledge search paths, comma-separated multiple paths. When provided, automatically enables SirchmunkSearch for knowledge retrieval, with LLM configuration automatically inherited from the `llm` module.
+- knowledge_search_paths: Comma-separated local search paths. Merges into `tools.localsearch.paths` and registers the **`localsearch`** tool (sirchmunk) for on-demand use by the model—not automatic per-turn injection. LLM settings are inherited from the `llm` module unless you set `tools.localsearch.llm_*` fields.
 
 ### Quick Start for Knowledge Search
 
-Use the `--knowledge_search_paths` parameter to quickly enable knowledge search based on local documents:
+Use `--knowledge_search_paths` or define `tools.localsearch` in yaml so the model can call `localsearch` when needed:
 
 ```bash
 # Using default agent.yaml configuration, automatically reuses LLM settings
-ms-agent run --query "How to implement user authentication?" --knowledge_search_paths "./src,./docs"
+ms-agent run --query "How to implement user authentication?" --knowledge_search_paths "/path/to/docs"
 
 # Specify configuration file
 ms-agent run --config /path/to/agent.yaml --query "your question" --knowledge_search_paths "/path/to/docs"
 ```
 
 LLM-related parameters (api_key, base_url, model) are automatically inherited from the `llm` module in the configuration file, no need to configure them repeatedly.
-If you need to use independent LLM configuration in the `knowledge_search` module, you can explicitly configure `knowledge_search.llm_api_key` and other parameters in the yaml.
+For a dedicated sirchmunk LLM, set `tools.localsearch.llm_api_key`, `llm_base_url`, and `llm_model_name` in yaml. Legacy top-level `knowledge_search` with the same keys is still read for backward compatibility.

docs/zh/Components/config.md

@@ -102,6 +102,14 @@ tools:
     url: https://mcp.api-inference.modelscope.net/xxx/sse
     exclude:
       - map_geo
+  # 本地代码库/文档搜索（sirchmunk），对应模型可调用的 `localsearch` 工具
+  localsearch:
+    paths:
+      - ./src
+      - ./docs
+    work_path: ./.sirchmunk
+    mode: FAST
+    # 可选：llm_api_key、llm_base_url、llm_model_name（不填则从 `llm` 继承）
 ```
 
 支持的完整工具列表，以及自定义工具请参考 [这里](./tools)
@@ -218,13 +226,13 @@ handler: custom_handler
       }
     }
     ```
-- knowledge_search_paths: 知识搜索路径，逗号分隔的多个路径。传入后会自动启用 SirchmunkSearch 进行知识检索，LLM 配置自动从 `llm` 模块复用
+- knowledge_search_paths: 知识搜索路径，逗号分隔。会合并到 `tools.localsearch.paths` 并注册 **`localsearch`** 工具（sirchmunk），由模型按需调用，不再在每轮自动注入上下文；除非配置 `tools.localsearch.llm_*`，否则 LLM 从 `llm` 模块复用
 
 > agent.yaml 中的任意一个配置，都可以使用命令行传入新的值，也支持从同名（大小写不敏感）环境变量中读取，例如 `--llm.modelscope_api_key xxx-xxx`。
 
 ### 知识搜索快速使用
 
-通过 `--knowledge_search_paths` 参数，可以快速启用基于本地文档的知识搜索：
+通过 `--knowledge_search_paths` 或在 yaml 中配置 `tools.localsearch`，启用本地知识搜索（模型按需调用 `localsearch`）：
 
 ```bash
 # 使用默认 agent.yaml 配置，自动复用 LLM 设置
@@ -235,4 +243,4 @@ ms-agent run --config /path/to/agent.yaml --query "你的问题" --knowledge_sea
 ```
 
 LLM 相关参数（api_key, base_url, model）会自动从配置文件的 `llm` 模块继承，无需重复配置。
-如果需要在 `knowledge_search` 模块中使用独立的 LLM 配置，可以在 yaml 中显式配置 `knowledge_search.llm_api_key` 等参数。
+若 sirchmunk 需独立 LLM，可在 yaml 的 `tools.localsearch` 下设置 `llm_api_key`、`llm_base_url`、`llm_model_name`。仍支持旧版顶层 `knowledge_search` 相同字段，以便迁移。

ms-agent-skills/scripts/check_ms_agent.py

@@ -1,9 +1,8 @@
 # Copyright (c) ModelScope Contributors. All rights reserved.
+import json
 import subprocess
 import sys
 
-import json
-
 
 def check_import() -> dict:
     """Check that ms_agent is importable."""

ms_agent/agent/base.py

@@ -1,12 +1,12 @@
 # Copyright (c) ModelScope Contributors. All rights reserved.
 import os
 from abc import ABC, abstractmethod
+from omegaconf import DictConfig
 from typing import Any, AsyncGenerator, List, Tuple, Union
 
 from ms_agent.llm import Message
 from ms_agent.utils import read_history, save_history
 from ms_agent.utils.constants import DEFAULT_OUTPUT_DIR, DEFAULT_RETRY_COUNT
-from omegaconf import DictConfig
 
 
 class Agent(ABC):
@@ -74,6 +74,15 @@ def save_history(self, messages: Any, **kwargs):
             return
         save_history(self.output_dir, self.tag, self.config, messages)
 
+    def list_snapshots(self) -> list:
+        """Return snapshots for this agent's output_dir, most recent first."""
+        from ms_agent.utils.snapshot import list_snapshots
+        return list_snapshots(self.output_dir)
+
+    def rollback(self, commit_hash: str) -> bool:
+        """Restore output_dir to a previous snapshot and truncate history."""
+        raise NotImplementedError()
+
     def next_flow(self, idx: int) -> int:
         """Used in workflow, decide which agent goes next."""
         return idx + 1

ms_agent/agent/code_agent.py

@@ -1,9 +1,8 @@
 # Copyright (c) ModelScope Contributors. All rights reserved.
+from omegaconf import DictConfig
 from typing import Any, List, Union
 
 from ms_agent.llm import Message
-from omegaconf import DictConfig
-
 from .base import Agent