Merge branch 'lorenze/feat/grep-tool' of github.com:crewAIInc/crewAI into lorenze/feat/file-discovery-tools

lib/crewai-tools/src/crewai_tools/__init__.py

@@ -77,6 +77,7 @@ from crewai_tools.tools.generate_crewai_automation_tool.generate_crewai_automati
     GenerateCrewaiAutomationTool,
 )
 from crewai_tools.tools.github_search_tool.github_search_tool import GithubSearchTool
+from crewai_tools.tools.grep_tool.grep_tool import GrepTool
 from crewai_tools.tools.hyperbrowser_load_tool.hyperbrowser_load_tool import (
     HyperbrowserLoadTool,
 )
@@ -230,6 +231,7 @@ __all__ = [
     "FirecrawlSearchTool",
     "GenerateCrewaiAutomationTool",
     "GithubSearchTool",
+    "GrepTool",
     "HyperbrowserLoadTool",
     "InvokeCrewAIAutomationTool",
     "JSONSearchTool",

lib/crewai-tools/src/crewai_tools/tools/__init__.py

@@ -66,6 +66,7 @@ from crewai_tools.tools.generate_crewai_automation_tool.generate_crewai_automati
     GenerateCrewaiAutomationTool,
 )
 from crewai_tools.tools.github_search_tool.github_search_tool import GithubSearchTool
+from crewai_tools.tools.grep_tool.grep_tool import GrepTool
 from crewai_tools.tools.hyperbrowser_load_tool.hyperbrowser_load_tool import (
     HyperbrowserLoadTool,
 )
@@ -214,6 +215,7 @@ __all__ = [
     "FirecrawlSearchTool",
     "GenerateCrewaiAutomationTool",
     "GithubSearchTool",
+    "GrepTool",
     "HyperbrowserLoadTool",
     "InvokeCrewAIAutomationTool",
     "JSONSearchTool",

lib/crewai-tools/src/crewai_tools/tools/grep_tool/__init__.py

@@ -0,0 +1,3 @@
+from crewai_tools.tools.grep_tool.grep_tool import GrepTool
+
+__all__ = ["GrepTool"]

lib/crewai-tools/src/crewai_tools/tools/grep_tool/grep_tool.py

@@ -2,33 +2,33 @@
 
 from __future__ import annotations
 
-from dataclasses import dataclass, field
 import os
-from pathlib import Path
 import re
+from dataclasses import dataclass, field
+from pathlib import Path
 from typing import Literal
 
+from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
 
-from crewai.tools.base_tool import BaseTool
-
-
 MAX_OUTPUT_CHARS = 50_000
 MAX_FILES = 10_000
 MAX_MATCHES_PER_FILE = 200
 MAX_LINE_LENGTH = 500
 BINARY_CHECK_SIZE = 8192
 
-SKIP_DIRS = frozenset({
-    ".git",
-    "__pycache__",
-    "node_modules",
-    ".venv",
-    "venv",
-    ".tox",
-    ".mypy_cache",
-    ".pytest_cache",
-})
+SKIP_DIRS = frozenset(
+    {
+        ".git",
+        "__pycache__",
+        "node_modules",
+        ".venv",
+        "venv",
+        ".tox",
+        ".mypy_cache",
+        ".pytest_cache",
+    }
+)
 
 
 @dataclass
@@ -52,7 +52,9 @@ class FileSearchResult:
 class GrepToolSchema(BaseModel):
     """Schema for grep tool arguments."""
 
-    pattern: str = Field(..., description="Regex pattern to search for in file contents")
+    pattern: str = Field(
+        ..., description="Regex pattern to search for in file contents"
+    )
     path: str | None = Field(
         default=None,
         description="File or directory to search in. Defaults to current working directory.",
@@ -84,13 +86,23 @@ class GrepTool(BaseTool):
 
     Recursively searches files in a directory for lines matching a regex pattern.
     Supports glob filtering, context lines, and multiple output modes.
+
+    Example:
+        >>> tool = GrepTool()
+        >>> result = tool.run(pattern="def.*main", path="/path/to/project")
+        >>> result = tool.run(
+        ...     pattern="TODO",
+        ...     path="/path/to/project",
+        ...     glob_pattern="*.py",
+        ...     context_lines=2,
+        ... )
     """
 
-    name: str = "grep"
+    name: str = "Search file contents"
     description: str = (
-        "Search file contents on disk using regex patterns. "
+        "A tool that searches file contents on disk using regex patterns. "
         "Recursively searches files in a directory for matching lines. "
-        "Returns matching content, file paths, or match counts."
+        "Returns matching content with line numbers, file paths only, or match counts."
     )
     args_schema: type[BaseModel] = GrepToolSchema
 
@@ -154,7 +166,10 @@ class GrepTool(BaseTool):
 
         # Truncate if needed
         if len(output) > MAX_OUTPUT_CHARS:
-            output = output[:MAX_OUTPUT_CHARS] + "\n\n... Output truncated. Try a narrower search pattern or glob filter."
+            output = (
+                output[:MAX_OUTPUT_CHARS]
+                + "\n\n... Output truncated. Try a narrower search pattern or glob filter."
+            )
 
         return output
 
@@ -255,11 +270,13 @@ class GrepTool(BaseTool):
                 text = lines[i].rstrip("\n\r")
                 if len(text) > MAX_LINE_LENGTH:
                     text = text[:MAX_LINE_LENGTH] + "..."
-                current_group.append(MatchLine(
-                    line_number=i + 1,  # 1-indexed
-                    text=text,
-                    is_match=(i in match_line_nums),
-                ))
+                current_group.append(
+                    MatchLine(
+                        line_number=i + 1,  # 1-indexed
+                        text=text,
+                        is_match=(i in match_line_nums),
+                    )
+                )
 
             prev_end = end
 

lib/crewai-tools/tests/tools/grep_tool_test.py

@@ -4,7 +4,7 @@ from pathlib import Path
 
 import pytest
 
-from crewai.tools.agent_tools.grep_tool import GrepTool
+from crewai_tools import GrepTool
 
 
 @pytest.fixture
@@ -69,7 +69,7 @@ class TestGrepTool:
 
     def test_tool_metadata(self) -> None:
         """Test tool has correct name and description."""
-        assert self.tool.name == "grep"
+        assert self.tool.name == "Search file contents"
         assert "search" in self.tool.description.lower() or "Search" in self.tool.description
 
     def test_args_schema(self) -> None:

lib/crewai-tools/tool.specs.json

@@ -8360,6 +8360,126 @@
         "type": "object"
       }
     },
+    {
+      "description": "A tool that searches file contents on disk using regex patterns. Recursively searches files in a directory for matching lines. Returns matching content with line numbers, file paths only, or match counts.",
+      "env_vars": [],
+      "humanized_name": "Search file contents",
+      "init_params_schema": {
+        "$defs": {
+          "EnvVar": {
+            "properties": {
+              "default": {
+                "anyOf": [
+                  {
+                    "type": "string"
+                  },
+                  {
+                    "type": "null"
+                  }
+                ],
+                "default": null,
+                "title": "Default"
+              },
+              "description": {
+                "title": "Description",
+                "type": "string"
+              },
+              "name": {
+                "title": "Name",
+                "type": "string"
+              },
+              "required": {
+                "default": true,
+                "title": "Required",
+                "type": "boolean"
+              }
+            },
+            "required": [
+              "name",
+              "description"
+            ],
+            "title": "EnvVar",
+            "type": "object"
+          }
+        },
+        "description": "Tool for searching file contents on disk using regex patterns.\n\nRecursively searches files in a directory for lines matching a regex pattern.\nSupports glob filtering, context lines, and multiple output modes.\n\nExample:\n    >>> tool = GrepTool()\n    >>> result = tool.run(pattern=\"def.*main\", path=\"/path/to/project\")\n    >>> result = tool.run(\n    ...     pattern=\"TODO\",\n    ...     path=\"/path/to/project\",\n    ...     glob_pattern=\"*.py\",\n    ...     context_lines=2,\n    ... )",
+        "properties": {},
+        "title": "GrepTool",
+        "type": "object"
+      },
+      "name": "GrepTool",
+      "package_dependencies": [],
+      "run_params_schema": {
+        "description": "Schema for grep tool arguments.",
+        "properties": {
+          "case_insensitive": {
+            "default": false,
+            "description": "Whether to perform case-insensitive matching",
+            "title": "Case Insensitive",
+            "type": "boolean"
+          },
+          "context_lines": {
+            "default": 0,
+            "description": "Number of lines to show before and after each match",
+            "title": "Context Lines",
+            "type": "integer"
+          },
+          "glob_pattern": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "description": "Glob pattern to filter files (e.g. '*.py', '*.{ts,tsx}')",
+            "title": "Glob Pattern"
+          },
+          "include_line_numbers": {
+            "default": true,
+            "description": "Whether to prefix matching lines with line numbers",
+            "title": "Include Line Numbers",
+            "type": "boolean"
+          },
+          "output_mode": {
+            "default": "content",
+            "description": "Output mode: 'content' shows matching lines, 'files_with_matches' shows only file paths, 'count' shows match counts per file",
+            "enum": [
+              "content",
+              "files_with_matches",
+              "count"
+            ],
+            "title": "Output Mode",
+            "type": "string"
+          },
+          "path": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "description": "File or directory to search in. Defaults to current working directory.",
+            "title": "Path"
+          },
+          "pattern": {
+            "description": "Regex pattern to search for in file contents",
+            "title": "Pattern",
+            "type": "string"
+          }
+        },
+        "required": [
+          "pattern"
+        ],
+        "title": "GrepToolSchema",
+        "type": "object"
+      }
+    },
     {
       "description": "Scrape or crawl a website using Hyperbrowser and return the contents in properly formatted markdown or html",
       "env_vars": [