chore: remove max_retries reference from docs

feat: add system event types and handler

chore: add tests and improve signal-related error logging

.env.test

@@ -0,0 +1,161 @@
+# =============================================================================
+# Test Environment Variables
+# =============================================================================
+# This file contains all environment variables needed to run tests locally
+# in a way that mimics the GitHub Actions CI environment.
+
+# =============================================================================
+
+# -----------------------------------------------------------------------------
+# LLM Provider API Keys
+# -----------------------------------------------------------------------------
+OPENAI_API_KEY=fake-api-key
+ANTHROPIC_API_KEY=fake-anthropic-key
+GEMINI_API_KEY=fake-gemini-key
+AZURE_API_KEY=fake-azure-key
+OPENROUTER_API_KEY=fake-openrouter-key
+
+# -----------------------------------------------------------------------------
+# AWS Credentials
+# -----------------------------------------------------------------------------
+AWS_ACCESS_KEY_ID=fake-aws-access-key
+AWS_SECRET_ACCESS_KEY=fake-aws-secret-key
+AWS_DEFAULT_REGION=us-east-1
+AWS_REGION_NAME=us-east-1
+
+# -----------------------------------------------------------------------------
+# Azure OpenAI Configuration
+# -----------------------------------------------------------------------------
+AZURE_ENDPOINT=https://fake-azure-endpoint.openai.azure.com
+AZURE_OPENAI_ENDPOINT=https://fake-azure-endpoint.openai.azure.com
+AZURE_OPENAI_API_KEY=fake-azure-openai-key
+AZURE_API_VERSION=2024-02-15-preview
+OPENAI_API_VERSION=2024-02-15-preview
+
+# -----------------------------------------------------------------------------
+# Google Cloud Configuration
+# -----------------------------------------------------------------------------
+#GOOGLE_CLOUD_PROJECT=fake-gcp-project
+#GOOGLE_CLOUD_LOCATION=us-central1
+
+# -----------------------------------------------------------------------------
+# OpenAI Configuration
+# -----------------------------------------------------------------------------
+OPENAI_BASE_URL=https://api.openai.com/v1
+OPENAI_API_BASE=https://api.openai.com/v1
+
+# -----------------------------------------------------------------------------
+# Search & Scraping Tool API Keys
+# -----------------------------------------------------------------------------
+SERPER_API_KEY=fake-serper-key
+EXA_API_KEY=fake-exa-key
+BRAVE_API_KEY=fake-brave-key
+FIRECRAWL_API_KEY=fake-firecrawl-key
+TAVILY_API_KEY=fake-tavily-key
+SERPAPI_API_KEY=fake-serpapi-key
+SERPLY_API_KEY=fake-serply-key
+LINKUP_API_KEY=fake-linkup-key
+PARALLEL_API_KEY=fake-parallel-key
+
+# -----------------------------------------------------------------------------
+# Exa Configuration
+# -----------------------------------------------------------------------------
+EXA_BASE_URL=https://api.exa.ai
+
+# -----------------------------------------------------------------------------
+# Web Scraping & Automation
+# -----------------------------------------------------------------------------
+BRIGHT_DATA_API_KEY=fake-brightdata-key
+BRIGHT_DATA_ZONE=fake-zone
+BRIGHTDATA_API_URL=https://api.brightdata.com
+BRIGHTDATA_DEFAULT_TIMEOUT=600
+BRIGHTDATA_DEFAULT_POLLING_INTERVAL=1
+
+OXYLABS_USERNAME=fake-oxylabs-user
+OXYLABS_PASSWORD=fake-oxylabs-pass
+
+SCRAPFLY_API_KEY=fake-scrapfly-key
+SCRAPEGRAPH_API_KEY=fake-scrapegraph-key
+
+BROWSERBASE_API_KEY=fake-browserbase-key
+BROWSERBASE_PROJECT_ID=fake-browserbase-project
+
+HYPERBROWSER_API_KEY=fake-hyperbrowser-key
+MULTION_API_KEY=fake-multion-key
+APIFY_API_TOKEN=fake-apify-token
+
+# -----------------------------------------------------------------------------
+# Database & Vector Store Credentials
+# -----------------------------------------------------------------------------
+SINGLESTOREDB_URL=mysql://fake:fake@localhost:3306/fake
+SINGLESTOREDB_HOST=localhost
+SINGLESTOREDB_PORT=3306
+SINGLESTOREDB_USER=fake-user
+SINGLESTOREDB_PASSWORD=fake-password
+SINGLESTOREDB_DATABASE=fake-database
+SINGLESTOREDB_CONNECT_TIMEOUT=30
+
+SNOWFLAKE_USER=fake-snowflake-user
+SNOWFLAKE_PASSWORD=fake-snowflake-password
+SNOWFLAKE_ACCOUNT=fake-snowflake-account
+SNOWFLAKE_WAREHOUSE=fake-snowflake-warehouse
+SNOWFLAKE_DATABASE=fake-snowflake-database
+SNOWFLAKE_SCHEMA=fake-snowflake-schema
+
+WEAVIATE_URL=http://localhost:8080
+WEAVIATE_API_KEY=fake-weaviate-key
+
+EMBEDCHAIN_DB_URI=sqlite:///test.db
+
+# Databricks Credentials
+DATABRICKS_HOST=https://fake-databricks.cloud.databricks.com
+DATABRICKS_TOKEN=fake-databricks-token
+DATABRICKS_CONFIG_PROFILE=fake-profile
+
+# MongoDB Credentials
+MONGODB_URI=mongodb://fake:fake@localhost:27017/fake
+
+# -----------------------------------------------------------------------------
+# CrewAI Platform & Enterprise
+# -----------------------------------------------------------------------------
+# setting CREWAI_PLATFORM_INTEGRATION_TOKEN causes these test to fail:
+#=========================== short test summary info ============================
+#FAILED tests/test_context.py::TestPlatformIntegrationToken::test_platform_context_manager_basic_usage - AssertionError: assert 'fake-platform-token' is None
+# +  where 'fake-platform-token' = get_platform_integration_token()
+#FAILED tests/test_context.py::TestPlatformIntegrationToken::test_context_var_isolation_between_tests - AssertionError: assert 'fake-platform-token' is None
+# +  where 'fake-platform-token' = get_platform_integration_token()
+#FAILED tests/test_context.py::TestPlatformIntegrationToken::test_multiple_sequential_context_managers - AssertionError: assert 'fake-platform-token' is None
+# +  where 'fake-platform-token' = get_platform_integration_token()
+#CREWAI_PLATFORM_INTEGRATION_TOKEN=fake-platform-token
+CREWAI_PERSONAL_ACCESS_TOKEN=fake-personal-token
+CREWAI_PLUS_URL=https://fake.crewai.com
+
+# -----------------------------------------------------------------------------
+# Other Service API Keys
+# -----------------------------------------------------------------------------
+ZAPIER_API_KEY=fake-zapier-key
+PATRONUS_API_KEY=fake-patronus-key
+MINDS_API_KEY=fake-minds-key
+HF_TOKEN=fake-hf-token
+
+# -----------------------------------------------------------------------------
+# Feature Flags/Testing Modes
+# -----------------------------------------------------------------------------
+CREWAI_DISABLE_TELEMETRY=true
+OTEL_SDK_DISABLED=true
+CREWAI_TESTING=true
+CREWAI_TRACING_ENABLED=false
+
+# -----------------------------------------------------------------------------
+# Testing/CI Configuration
+# -----------------------------------------------------------------------------
+# VCR recording mode: "none" (default), "new_episodes", "all", "once"
+PYTEST_VCR_RECORD_MODE=none
+
+# Set to "true" by GitHub when running in GitHub Actions
+# GITHUB_ACTIONS=false
+
+# -----------------------------------------------------------------------------
+# Python Configuration
+# -----------------------------------------------------------------------------
+PYTHONUNBUFFERED=1

.github/workflows/tests.yml

@@ -5,18 +5,6 @@ on: [pull_request]
 permissions:
   contents: read
 
-env:
-  OPENAI_API_KEY: fake-api-key
-  PYTHONUNBUFFERED: 1
-  BRAVE_API_KEY: fake-brave-key
-  SNOWFLAKE_USER: fake-snowflake-user
-  SNOWFLAKE_PASSWORD: fake-snowflake-password
-  SNOWFLAKE_ACCOUNT: fake-snowflake-account
-  SNOWFLAKE_WAREHOUSE: fake-snowflake-warehouse
-  SNOWFLAKE_DATABASE: fake-snowflake-database
-  SNOWFLAKE_SCHEMA: fake-snowflake-schema
-  EMBEDCHAIN_DB_URI: sqlite:///test.db
-
 jobs:
   tests:
     name: tests (${{ matrix.python-version }})
@@ -84,26 +72,20 @@ jobs:
           # fi
 
           cd lib/crewai && uv run pytest \
-            --block-network \
-            --timeout=30 \
             -vv \
             --splits 8 \
             --group ${{ matrix.group }} \
             $DURATIONS_ARG \
             --durations=10 \
-            -n auto \
             --maxfail=3
 
       - name: Run tool tests (group ${{ matrix.group }} of 8)
         run: |
           cd lib/crewai-tools && uv run pytest \
-            --block-network \
-            --timeout=30 \
             -vv \
             --splits 8 \
             --group ${{ matrix.group }} \
             --durations=10 \
-            -n auto \
             --maxfail=3
 
 

conftest.py

@@ -0,0 +1,167 @@
+"""Pytest configuration for crewAI workspace."""
+
+from collections.abc import Generator
+import os
+from pathlib import Path
+import tempfile
+from typing import Any
+
+from dotenv import load_dotenv
+import pytest
+from vcr.request import Request  # type: ignore[import-untyped]
+
+
+env_test_path = Path(__file__).parent / ".env.test"
+load_dotenv(env_test_path, override=True)
+load_dotenv(override=True)
+
+
+@pytest.fixture(autouse=True, scope="function")
+def cleanup_event_handlers() -> Generator[None, Any, None]:
+    """Clean up event bus handlers after each test to prevent test pollution."""
+    yield
+
+    try:
+        from crewai.events.event_bus import crewai_event_bus
+
+        with crewai_event_bus._rwlock.w_locked():
+            crewai_event_bus._sync_handlers.clear()
+            crewai_event_bus._async_handlers.clear()
+    except Exception:  # noqa: S110
+        pass
+
+
+@pytest.fixture(autouse=True, scope="function")
+def setup_test_environment() -> Generator[None, Any, None]:
+    """Setup test environment for crewAI workspace."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        storage_dir = Path(temp_dir) / "crewai_test_storage"
+        storage_dir.mkdir(parents=True, exist_ok=True)
+
+        if not storage_dir.exists() or not storage_dir.is_dir():
+            raise RuntimeError(
+                f"Failed to create test storage directory: {storage_dir}"
+            )
+
+        try:
+            test_file = storage_dir / ".permissions_test"
+            test_file.touch()
+            test_file.unlink()
+        except (OSError, IOError) as e:
+            raise RuntimeError(
+                f"Test storage directory {storage_dir} is not writable: {e}"
+            ) from e
+
+        os.environ["CREWAI_STORAGE_DIR"] = str(storage_dir)
+        os.environ["CREWAI_TESTING"] = "true"
+
+        try:
+            yield
+        finally:
+            os.environ.pop("CREWAI_TESTING", "true")
+            os.environ.pop("CREWAI_STORAGE_DIR", None)
+            os.environ.pop("CREWAI_DISABLE_TELEMETRY", "true")
+            os.environ.pop("OTEL_SDK_DISABLED", "true")
+            os.environ.pop("OPENAI_BASE_URL", "https://api.openai.com/v1")
+            os.environ.pop("OPENAI_API_BASE", "https://api.openai.com/v1")
+
+
+HEADERS_TO_FILTER = {
+    "authorization": "AUTHORIZATION-XXX",
+    "content-security-policy": "CSP-FILTERED",
+    "cookie": "COOKIE-XXX",
+    "set-cookie": "SET-COOKIE-XXX",
+    "permissions-policy": "PERMISSIONS-POLICY-XXX",
+    "referrer-policy": "REFERRER-POLICY-XXX",
+    "strict-transport-security": "STS-XXX",
+    "x-content-type-options": "X-CONTENT-TYPE-XXX",
+    "x-frame-options": "X-FRAME-OPTIONS-XXX",
+    "x-permitted-cross-domain-policies": "X-PERMITTED-XXX",
+    "x-request-id": "X-REQUEST-ID-XXX",
+    "x-runtime": "X-RUNTIME-XXX",
+    "x-xss-protection": "X-XSS-PROTECTION-XXX",
+    "x-stainless-arch": "X-STAINLESS-ARCH-XXX",
+    "x-stainless-os": "X-STAINLESS-OS-XXX",
+    "x-stainless-read-timeout": "X-STAINLESS-READ-TIMEOUT-XXX",
+    "cf-ray": "CF-RAY-XXX",
+    "etag": "ETAG-XXX",
+    "Strict-Transport-Security": "STS-XXX",
+    "access-control-expose-headers": "ACCESS-CONTROL-XXX",
+    "openai-organization": "OPENAI-ORG-XXX",
+    "openai-project": "OPENAI-PROJECT-XXX",
+    "x-ratelimit-limit-requests": "X-RATELIMIT-LIMIT-REQUESTS-XXX",
+    "x-ratelimit-limit-tokens": "X-RATELIMIT-LIMIT-TOKENS-XXX",
+    "x-ratelimit-remaining-requests": "X-RATELIMIT-REMAINING-REQUESTS-XXX",
+    "x-ratelimit-remaining-tokens": "X-RATELIMIT-REMAINING-TOKENS-XXX",
+    "x-ratelimit-reset-requests": "X-RATELIMIT-RESET-REQUESTS-XXX",
+    "x-ratelimit-reset-tokens": "X-RATELIMIT-RESET-TOKENS-XXX",
+    "x-goog-api-key": "X-GOOG-API-KEY-XXX",
+}
+
+
+def _filter_request_headers(request: Request) -> Request:  # type: ignore[no-any-unimported]
+    """Filter sensitive headers from request before recording."""
+    for header_name, replacement in HEADERS_TO_FILTER.items():
+        for variant in [header_name, header_name.upper(), header_name.title()]:
+            if variant in request.headers:
+                request.headers[variant] = [replacement]
+    return request
+
+
+def _filter_response_headers(response: dict[str, Any]) -> dict[str, Any]:
+    """Filter sensitive headers from response before recording."""
+    for header_name, replacement in HEADERS_TO_FILTER.items():
+        for variant in [header_name, header_name.upper(), header_name.title()]:
+            if variant in response["headers"]:
+                response["headers"][variant] = [replacement]
+    return response
+
+
+@pytest.fixture(scope="module")
+def vcr_cassette_dir(request: Any) -> str:
+    """Generate cassette directory path based on test module location.
+
+    Organizes cassettes to mirror test directory structure within each package:
+    lib/crewai/tests/llms/google/test_google.py -> lib/crewai/tests/cassettes/llms/google/
+    lib/crewai-tools/tests/tools/test_search.py -> lib/crewai-tools/tests/cassettes/tools/
+    """
+    test_file = Path(request.fspath)
+
+    for parent in test_file.parents:
+        if parent.name in ("crewai", "crewai-tools") and parent.parent.name == "lib":
+            package_root = parent
+            break
+    else:
+        package_root = test_file.parent
+
+    tests_root = package_root / "tests"
+    test_dir = test_file.parent
+
+    if test_dir != tests_root:
+        relative_path = test_dir.relative_to(tests_root)
+        cassette_dir = tests_root / "cassettes" / relative_path
+    else:
+        cassette_dir = tests_root / "cassettes"
+
+    cassette_dir.mkdir(parents=True, exist_ok=True)
+
+    return str(cassette_dir)
+
+
+@pytest.fixture(scope="module")
+def vcr_config(vcr_cassette_dir: str) -> dict[str, Any]:
+    """Configure VCR with organized cassette storage."""
+    config = {
+        "cassette_library_dir": vcr_cassette_dir,
+        "record_mode": os.getenv("PYTEST_VCR_RECORD_MODE", "once"),
+        "filter_headers": [(k, v) for k, v in HEADERS_TO_FILTER.items()],
+        "before_record_request": _filter_request_headers,
+        "before_record_response": _filter_response_headers,
+        "filter_query_parameters": ["key"],
+        "match_on": ["method", "scheme", "host", "port", "path"],
+    }
+
+    if os.getenv("GITHUB_ACTIONS") == "true":
+        config["record_mode"] = "none"
+
+    return config

docs/docs.json

@@ -326,7 +326,7 @@
             ]
           },
           {
-            "tab": "AMP",
+            "tab": "AOP",
             "icon": "briefcase",
             "groups": [
               {
@@ -753,7 +753,7 @@
             ]
           },
           {
-            "tab": "AMP",
+            "tab": "AOP",
             "icon": "briefcase",
             "groups": [
               {

docs/en/concepts/tasks.mdx

@@ -63,10 +63,6 @@ crew = Crew(
 | **Guardrails** _(optional)_       | `guardrails`       | `Optional[List[Callable] | List[str]]` | List of guardrails to validate task output before proceeding to next task.                                      |
 | **Guardrail Max Retries** _(optional)_ | `guardrail_max_retries` | `Optional[int]`     | Maximum number of retries when guardrail validation fails. Defaults to 3.                                         |
 
-<Note type="warning" title="Deprecated: max_retries">
-  The task attribute `max_retries` is deprecated and will be removed in v1.0.0.
-  Use `guardrail_max_retries` instead to control retry attempts when a guardrail fails.
-</Note>
 
 ## Creating Tasks
 

docs/en/enterprise/introduction.mdx

@@ -7,7 +7,7 @@ mode: "wide"
 
 ## Introduction
 
-CrewAI AOP(Agent Management Platform) provides a platform for deploying, monitoring, and scaling your crews and agents in a production environment.
+CrewAI AOP(Agent Operations Platform) provides a platform for deploying, monitoring, and scaling your crews and agents in a production environment.
 
 <Frame>
   <img src="/images/enterprise/crewai-enterprise-dashboard.png" alt="CrewAI AOP Dashboard" />

docs/ko/enterprise/introduction.mdx

@@ -7,7 +7,7 @@ mode: "wide"
 
 ## 소개
 
-CrewAI AOP(Agent Management Platform)는 프로덕션 환경에서 crew와 agent를 배포, 모니터링, 확장할 수 있는 플랫폼을 제공합니다.
+CrewAI AOP(Agent Operation Platform)는 프로덕션 환경에서 crew와 agent를 배포, 모니터링, 확장할 수 있는 플랫폼을 제공합니다.
 
 <Frame>
   <img src="/images/enterprise/crewai-enterprise-dashboard.png" alt="CrewAI AOP Dashboard" />

docs/pt-BR/enterprise/introduction.mdx

@@ -7,7 +7,7 @@ mode: "wide"
 
 ## Introdução
 
-CrewAI AOP(Agent Management Platform) fornece uma plataforma para implementar, monitorar e escalar seus crews e agentes em um ambiente de produção.
+CrewAI AOP(Agent Operation Platform) fornece uma plataforma para implementar, monitorar e escalar seus crews e agentes em um ambiente de produção.
 
 <Frame>
   <img src="/images/enterprise/crewai-enterprise-dashboard.png" alt="CrewAI AOP Dashboard" />

lib/crewai-tools/BUILDING_TOOLS.md

@@ -218,7 +218,7 @@ Update the root `README.md` only if the tool introduces a new category or notabl
 
 ## Discovery and specs
 
-Our internal tooling discovers classes whose names end with `Tool`. Keep your class exported from the module path under `crewai_tools/tools/...` to be picked up by scripts like `generate_tool_specs.py`.
+Our internal tooling discovers classes whose names end with `Tool`. Keep your class exported from the module path under `crewai_tools/tools/...` to be picked up by scripts like `crewai_tools.generate_tool_specs.py`.
 
 ---
 

lib/crewai-tools/pyproject.toml

@@ -8,17 +8,17 @@ authors = [
 ]
 requires-python = ">=3.10, <3.14"
 dependencies = [
-    "lancedb>=0.5.4",
-    "pytube>=15.0.0",
-    "requests>=2.32.5",
-    "docker>=7.1.0",
-    "crewai==1.5.0",
-    "lancedb>=0.5.4",
-    "tiktoken>=0.8.0",
-    "beautifulsoup4>=4.13.4",
-    "pypdf>=5.9.0",
-    "python-docx>=1.2.0",
-    "youtube-transcript-api>=1.2.2",
+    "lancedb~=0.5.4",
+    "pytube~=15.0.0",
+    "requests~=2.32.5",
+    "docker~=7.1.0",
+    "crewai==1.6.1",
+    "lancedb~=0.5.4",
+    "tiktoken~=0.8.0",
+    "beautifulsoup4~=4.13.4",
+    "python-docx~=1.2.0",
+    "youtube-transcript-api~=1.2.2",
+    "pymupdf~=1.26.6",
 ]
 
 

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

@@ -291,4 +291,4 @@ __all__ = [
     "ZapierActionTools",
 ]
 
-__version__ = "1.5.0"
+__version__ = "1.6.1"

lib/crewai-tools/src/crewai_tools/adapters/crewai_rag_adapter.py

@@ -3,8 +3,7 @@
 from __future__ import annotations
 
 import hashlib
-from pathlib import Path
-from typing import TYPE_CHECKING, Any, TypeAlias, TypedDict, cast
+from typing import TYPE_CHECKING, Any, cast
 import uuid
 
 from crewai.rag.config.types import RagConfigType
@@ -19,15 +18,13 @@ from typing_extensions import TypeIs, Unpack
 from crewai_tools.rag.data_types import DataType
 from crewai_tools.rag.misc import sanitize_metadata_for_chromadb
 from crewai_tools.tools.rag.rag_tool import Adapter
+from crewai_tools.tools.rag.types import AddDocumentParams, ContentItem
 
 
 if TYPE_CHECKING:
     from crewai.rag.qdrant.config import QdrantConfig
 
 
-ContentItem: TypeAlias = str | Path | dict[str, Any]
-
-
 def _is_qdrant_config(config: Any) -> TypeIs[QdrantConfig]:
     """Check if config is a QdrantConfig using safe duck typing.
 
@@ -46,19 +43,6 @@ def _is_qdrant_config(config: Any) -> TypeIs[QdrantConfig]:
         return False
 
 
-class AddDocumentParams(TypedDict, total=False):
-    """Parameters for adding documents to the RAG system."""
-
-    data_type: DataType
-    metadata: dict[str, Any]
-    website: str
-    url: str
-    file_path: str | Path
-    github_url: str
-    youtube_url: str
-    directory_path: str | Path
-
-
 class CrewAIRagAdapter(Adapter):
     """Adapter that uses CrewAI's native RAG system.
 
@@ -131,13 +115,26 @@ class CrewAIRagAdapter(Adapter):
     def add(self, *args: ContentItem, **kwargs: Unpack[AddDocumentParams]) -> None:
         """Add content to the knowledge base.
 
-        This method handles various input types and converts them to documents
-        for the vector database. It supports the data_type parameter for
-        compatibility with existing tools.
-
         Args:
             *args: Content items to add (strings, paths, or document dicts)
-            **kwargs: Additional parameters including data_type, metadata, etc.
+            **kwargs: Additional parameters including:
+                - data_type: DataType enum or string (e.g., "file", "pdf_file", "text")
+                - path: Path to file or directory (alternative to positional arg)
+                - file_path: Alias for path
+                - metadata: Additional metadata to attach to documents
+                - url: URL to fetch content from
+                - website: Website URL to scrape
+                - github_url: GitHub repository URL
+                - youtube_url: YouTube video URL
+                - directory_path: Path to directory
+
+        Examples:
+            rag_tool.add("path/to/document.pdf", data_type=DataType.PDF_FILE)
+
+            rag_tool.add(path="path/to/document.pdf", data_type="file")
+            rag_tool.add(file_path="path/to/document.pdf", data_type="pdf_file")
+
+            rag_tool.add("path/to/document.pdf")  # auto-detects PDF
         """
         import os
 
@@ -146,10 +143,54 @@ class CrewAIRagAdapter(Adapter):
         from crewai_tools.rag.source_content import SourceContent
 
         documents: list[BaseRecord] = []
-        data_type: DataType | None = kwargs.get("data_type")
+        raw_data_type = kwargs.get("data_type")
         base_metadata: dict[str, Any] = kwargs.get("metadata", {})
 
-        for arg in args:
+        data_type: DataType | None = None
+        if raw_data_type is not None:
+            if isinstance(raw_data_type, DataType):
+                if raw_data_type != DataType.FILE:
+                    data_type = raw_data_type
+            elif isinstance(raw_data_type, str):
+                if raw_data_type != "file":
+                    try:
+                        data_type = DataType(raw_data_type)
+                    except ValueError:
+                        raise ValueError(
+                            f"Invalid data_type: '{raw_data_type}'. "
+                            f"Valid values are: 'file' (auto-detect), or one of: "
+                            f"{', '.join(dt.value for dt in DataType)}"
+                        ) from None
+
+        content_items: list[ContentItem] = list(args)
+
+        path_value = kwargs.get("path") or kwargs.get("file_path")
+        if path_value is not None:
+            content_items.append(path_value)
+
+        if url := kwargs.get("url"):
+            content_items.append(url)
+        if website := kwargs.get("website"):
+            content_items.append(website)
+        if github_url := kwargs.get("github_url"):
+            content_items.append(github_url)
+        if youtube_url := kwargs.get("youtube_url"):
+            content_items.append(youtube_url)
+        if directory_path := kwargs.get("directory_path"):
+            content_items.append(directory_path)
+
+        file_extensions = {
+            ".pdf",
+            ".txt",
+            ".csv",
+            ".json",
+            ".xml",
+            ".docx",
+            ".mdx",
+            ".md",
+        }
+
+        for arg in content_items:
             source_ref: str
             if isinstance(arg, dict):
                 source_ref = str(arg.get("source", arg.get("content", "")))
@@ -157,6 +198,14 @@ class CrewAIRagAdapter(Adapter):
                 source_ref = str(arg)
 
             if not data_type:
+                ext = os.path.splitext(source_ref)[1].lower()
+                is_url = source_ref.startswith(("http://", "https://", "file://"))
+                if (
+                    ext in file_extensions
+                    and not is_url
+                    and not os.path.isfile(source_ref)
+                ):
+                    raise FileNotFoundError(f"File does not exist: {source_ref}")
                 data_type = DataTypes.from_content(source_ref)
 
             if data_type == DataType.DIRECTORY:

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

@@ -4,17 +4,20 @@ from collections.abc import Mapping
 import inspect
 import json
 from pathlib import Path
-from typing import Any, cast
+from typing import Any
 
 from crewai.tools.base_tool import BaseTool, EnvVar
-from crewai_tools import tools
 from pydantic import BaseModel
 from pydantic.json_schema import GenerateJsonSchema
 from pydantic_core import PydanticOmit
 
+from crewai_tools import tools
+
 
 class SchemaGenerator(GenerateJsonSchema):
-    def handle_invalid_for_json_schema(self, schema, error_info):
+    def handle_invalid_for_json_schema(
+        self, schema: Any, error_info: Any
+    ) -> dict[str, Any]:
         raise PydanticOmit
 
 
@@ -73,7 +76,7 @@ class ToolSpecExtractor:
 
     @staticmethod
     def _extract_field_default(
-        field: dict | None, fallback: str | list[Any] = ""
+        field: dict[str, Any] | None, fallback: str | list[Any] = ""
     ) -> str | list[Any] | int:
         if not field:
             return fallback
@@ -83,7 +86,7 @@ class ToolSpecExtractor:
         return default if isinstance(default, (list, str, int)) else fallback
 
     @staticmethod
-    def _extract_params(args_schema_field: dict | None) -> dict[str, Any]:
+    def _extract_params(args_schema_field: dict[str, Any] | None) -> dict[str, Any]:
         if not args_schema_field:
             return {}
 
@@ -94,15 +97,15 @@ class ToolSpecExtractor:
         ):
             return {}
 
-        # Cast to type[BaseModel] after runtime check
-        schema_class = cast(type[BaseModel], args_schema_class)
         try:
-            return schema_class.model_json_schema(schema_generator=SchemaGenerator)
+            return args_schema_class.model_json_schema(schema_generator=SchemaGenerator)
         except Exception:
             return {}
 
     @staticmethod
-    def _extract_env_vars(env_vars_field: dict | None) -> list[dict[str, Any]]:
+    def _extract_env_vars(
+        env_vars_field: dict[str, Any] | None,
+    ) -> list[dict[str, Any]]:
         if not env_vars_field:
             return []
 

lib/crewai-tools/src/crewai_tools/rag/data_types.py

@@ -1,6 +1,8 @@
 from enum import Enum
+from importlib import import_module
 import os
 from pathlib import Path
+from typing import cast
 from urllib.parse import urlparse
 
 from crewai_tools.rag.base_loader import BaseLoader
@@ -8,6 +10,7 @@ from crewai_tools.rag.chunkers.base_chunker import BaseChunker
 
 
 class DataType(str, Enum):
+    FILE = "file"
     PDF_FILE = "pdf_file"
     TEXT_FILE = "text_file"
     CSV = "csv"
@@ -15,22 +18,14 @@ class DataType(str, Enum):
     XML = "xml"
     DOCX = "docx"
     MDX = "mdx"
-
-    # Database types
     MYSQL = "mysql"
     POSTGRES = "postgres"
-
-    # Repository types
     GITHUB = "github"
     DIRECTORY = "directory"
-
-    # Web types
     WEBSITE = "website"
     DOCS_SITE = "docs_site"
     YOUTUBE_VIDEO = "youtube_video"
     YOUTUBE_CHANNEL = "youtube_channel"
-
-    # Raw types
     TEXT = "text"
 
     def get_chunker(self) -> BaseChunker:
@@ -63,13 +58,11 @@ class DataType(str, Enum):
 
         try:
             module = import_module(module_path)
-            return getattr(module, class_name)()
+            return cast(BaseChunker, getattr(module, class_name)())
         except Exception as e:
             raise ValueError(f"Error loading chunker for {self}: {e}") from e
 
     def get_loader(self) -> BaseLoader:
-        from importlib import import_module
-
         loaders = {
             DataType.PDF_FILE: ("pdf_loader", "PDFLoader"),
             DataType.TEXT_FILE: ("text_loader", "TextFileLoader"),
@@ -98,7 +91,7 @@ class DataType(str, Enum):
         module_path = f"crewai_tools.rag.loaders.{module_name}"
         try:
             module = import_module(module_path)
-            return getattr(module, class_name)()
+            return cast(BaseLoader, getattr(module, class_name)())
         except Exception as e:
             raise ValueError(f"Error loading loader for {self}: {e}") from e
 

lib/crewai-tools/src/crewai_tools/rag/loaders/pdf_loader.py

@@ -2,70 +2,112 @@
 
 import os
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
+from urllib.parse import urlparse
+import urllib.request
 
 from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
 from crewai_tools.rag.source_content import SourceContent
 
 
 class PDFLoader(BaseLoader):
-    """Loader for PDF files."""
+    """Loader for PDF files and URLs."""
 
-    def load(self, source: SourceContent, **kwargs) -> LoaderResult:  # type: ignore[override]
-        """Load and extract text from a PDF file.
+    @staticmethod
+    def _is_url(path: str) -> bool:
+        """Check if the path is a URL."""
+        try:
+            parsed = urlparse(path)
+            return parsed.scheme in ("http", "https")
+        except Exception:
+            return False
+
+    @staticmethod
+    def _download_pdf(url: str) -> bytes:
+        """Download PDF content from a URL.
 
         Args:
-            source: The source content containing the PDF file path
+            url: The URL to download from.
 
         Returns:
-            LoaderResult with extracted text content
+            The PDF content as bytes.
 
         Raises:
-            FileNotFoundError: If the PDF file doesn't exist
-            ImportError: If required PDF libraries aren't installed
+            ValueError: If the download fails.
+        """
+
+        try:
+            with urllib.request.urlopen(url, timeout=30) as response:  # noqa: S310
+                return cast(bytes, response.read())
+        except Exception as e:
+            raise ValueError(f"Failed to download PDF from {url}: {e!s}") from e
+
+    def load(self, source: SourceContent, **kwargs: Any) -> LoaderResult:  # type: ignore[override]
+        """Load and extract text from a PDF file or URL.
+
+        Args:
+            source: The source content containing the PDF file path or URL.
+
+        Returns:
+            LoaderResult with extracted text content.
+
+        Raises:
+            FileNotFoundError: If the PDF file doesn't exist.
+            ImportError: If required PDF libraries aren't installed.
+            ValueError: If the PDF cannot be read or downloaded.
         """
         try:
-            import pypdf
-        except ImportError:
-            try:
-                import PyPDF2 as pypdf  # type: ignore[import-not-found,no-redef]  # noqa: N813
-            except ImportError as e:
-                raise ImportError(
-                    "PDF support requires pypdf or PyPDF2. Install with: uv add pypdf"
-                ) from e
+            import pymupdf  # type: ignore[import-untyped]
+        except ImportError as e:
+            raise ImportError(
+                "PDF support requires pymupdf. Install with: uv add pymupdf"
+            ) from e
 
         file_path = source.source
+        is_url = self._is_url(file_path)
 
-        if not os.path.isfile(file_path):
-            raise FileNotFoundError(f"PDF file not found: {file_path}")
+        if is_url:
+            source_name = Path(urlparse(file_path).path).name or "downloaded.pdf"
+        else:
+            source_name = Path(file_path).name
 
-        text_content = []
+        text_content: list[str] = []
         metadata: dict[str, Any] = {
-            "source": str(file_path),
-            "file_name": Path(file_path).name,
+            "source": file_path,
+            "file_name": source_name,
             "file_type": "pdf",
         }
 
         try:
-            with open(file_path, "rb") as file:
-                pdf_reader = pypdf.PdfReader(file)
-                metadata["num_pages"] = len(pdf_reader.pages)
+            if is_url:
+                pdf_bytes = self._download_pdf(file_path)
+                doc = pymupdf.open(stream=pdf_bytes, filetype="pdf")
+            else:
+                if not os.path.isfile(file_path):
+                    raise FileNotFoundError(f"PDF file not found: {file_path}")
+                doc = pymupdf.open(file_path)
 
-                for page_num, page in enumerate(pdf_reader.pages, 1):
-                    page_text = page.extract_text()
-                    if page_text.strip():
-                        text_content.append(f"Page {page_num}:\n{page_text}")
+            metadata["num_pages"] = len(doc)
+
+            for page_num, page in enumerate(doc, 1):
+                page_text = page.get_text()
+                if page_text.strip():
+                    text_content.append(f"Page {page_num}:\n{page_text}")
+
+            doc.close()
+        except FileNotFoundError:
+            raise
         except Exception as e:
-            raise ValueError(f"Error reading PDF file {file_path}: {e!s}") from e
+            raise ValueError(f"Error reading PDF from {file_path}: {e!s}") from e
 
         if not text_content:
-            content = f"[PDF file with no extractable text: {Path(file_path).name}]"
+            content = f"[PDF file with no extractable text: {source_name}]"
         else:
             content = "\n\n".join(text_content)
 
         return LoaderResult(
             content=content,
-            source=str(file_path),
+            source=file_path,
             metadata=metadata,
-            doc_id=self.generate_doc_id(source_ref=str(file_path), content=content),
+            doc_id=self.generate_doc_id(source_ref=file_path, content=content),
         )

lib/crewai-tools/src/crewai_tools/tools/rag/rag_tool.py

@@ -14,9 +14,14 @@ from pydantic import (
     field_validator,
     model_validator,
 )
-from typing_extensions import Self
+from typing_extensions import Self, Unpack
 
-from crewai_tools.tools.rag.types import RagToolConfig, VectorDbConfig
+from crewai_tools.tools.rag.types import (
+    AddDocumentParams,
+    ContentItem,
+    RagToolConfig,
+    VectorDbConfig,
+)
 
 
 def _validate_embedding_config(
@@ -72,6 +77,8 @@ def _validate_embedding_config(
 
 
 class Adapter(BaseModel, ABC):
+    """Abstract base class for RAG adapters."""
+
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
     @abstractmethod
@@ -86,8 +93,8 @@ class Adapter(BaseModel, ABC):
     @abstractmethod
     def add(
         self,
-        *args: Any,
-        **kwargs: Any,
+        *args: ContentItem,
+        **kwargs: Unpack[AddDocumentParams],
     ) -> None:
         """Add content to the knowledge base."""
 
@@ -102,7 +109,11 @@ class RagTool(BaseTool):
         ) -> str:
             raise NotImplementedError
 
-        def add(self, *args: Any, **kwargs: Any) -> None:
+        def add(
+            self,
+            *args: ContentItem,
+            **kwargs: Unpack[AddDocumentParams],
+        ) -> None:
             raise NotImplementedError
 
     name: str = "Knowledge base"
@@ -207,9 +218,34 @@ class RagTool(BaseTool):
 
     def add(
         self,
-        *args: Any,
-        **kwargs: Any,
+        *args: ContentItem,
+        **kwargs: Unpack[AddDocumentParams],
     ) -> None:
+        """Add content to the knowledge base.
+
+
+        Args:
+            *args: Content items to add (strings, paths, or document dicts)
+            data_type: DataType enum or string (e.g., "file", "pdf_file", "text")
+            path: Path to file or directory, alias to positional arg
+            file_path: Alias for path
+            metadata: Additional metadata to attach to documents
+            url: URL to fetch content from
+            website: Website URL to scrape
+            github_url: GitHub repository URL
+            youtube_url: YouTube video URL
+            directory_path: Path to directory
+
+        Examples:
+            rag_tool.add("path/to/document.pdf", data_type=DataType.PDF_FILE)
+
+            # Keyword argument (documented API)
+            rag_tool.add(path="path/to/document.pdf", data_type="file")
+            rag_tool.add(file_path="path/to/document.pdf", data_type="pdf_file")
+
+            # Auto-detect type from extension
+            rag_tool.add("path/to/document.pdf")  # auto-detects PDF
+        """
         self.adapter.add(*args, **kwargs)
 
     def _run(

lib/crewai-tools/src/crewai_tools/tools/rag/types.py

@@ -1,10 +1,50 @@
 """Type definitions for RAG tool configuration."""
 
-from typing import Any, Literal
+from pathlib import Path
+from typing import Any, Literal, TypeAlias
 
 from crewai.rag.embeddings.types import ProviderSpec
 from typing_extensions import TypedDict
 
+from crewai_tools.rag.data_types import DataType
+
+
+DataTypeStr: TypeAlias = Literal[
+    "file",
+    "pdf_file",
+    "text_file",
+    "csv",
+    "json",
+    "xml",
+    "docx",
+    "mdx",
+    "mysql",
+    "postgres",
+    "github",
+    "directory",
+    "website",
+    "docs_site",
+    "youtube_video",
+    "youtube_channel",
+    "text",
+]
+
+ContentItem: TypeAlias = str | Path | dict[str, Any]
+
+
+class AddDocumentParams(TypedDict, total=False):
+    """Parameters for adding documents to the RAG system."""
+
+    data_type: DataType | DataTypeStr
+    metadata: dict[str, Any]
+    path: str | Path
+    file_path: str | Path
+    website: str
+    url: str
+    github_url: str
+    youtube_url: str
+    directory_path: str | Path
+
 
 class VectorDbConfig(TypedDict):
     """Configuration for vector database provider.

lib/crewai-tools/tests/it/tools/conftest.py

@@ -1,21 +0,0 @@
-import pytest
-
-
-def pytest_configure(config):
-    """Register custom markers."""
-    config.addinivalue_line("markers", "integration: mark test as an integration test")
-    config.addinivalue_line("markers", "asyncio: mark test as an async test")
-
-    # Set the asyncio loop scope through ini configuration
-    config.inicfg["asyncio_mode"] = "auto"
-
-
-@pytest.fixture(scope="function")
-def event_loop():
-    """Create an instance of the default event loop for each test case."""
-    import asyncio
-
-    loop = asyncio.new_event_loop()
-    asyncio.set_event_loop(loop)
-    yield loop
-    loop.close()

lib/crewai-tools/tests/test_generate_tool_specs.py

@@ -2,7 +2,7 @@ import json
 from unittest import mock
 
 from crewai.tools.base_tool import BaseTool, EnvVar
-from generate_tool_specs import ToolSpecExtractor
+from crewai_tools.generate_tool_specs import ToolSpecExtractor
 from pydantic import BaseModel, Field
 import pytest
 
@@ -61,8 +61,8 @@ def test_unwrap_schema(extractor):
 @pytest.fixture
 def mock_tool_extractor(extractor):
     with (
-        mock.patch("generate_tool_specs.dir", return_value=["MockTool"]),
-        mock.patch("generate_tool_specs.getattr", return_value=MockTool),
+        mock.patch("crewai_tools.generate_tool_specs.dir", return_value=["MockTool"]),
+        mock.patch("crewai_tools.generate_tool_specs.getattr", return_value=MockTool),
     ):
         extractor.extract_all_tools()
         assert len(extractor.tools_spec) == 1

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

@@ -4,7 +4,7 @@ from crewai_tools.tools.firecrawl_crawl_website_tool.firecrawl_crawl_website_too
     FirecrawlCrawlWebsiteTool,
 )
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_firecrawl_crawl_tool_integration():
     tool = FirecrawlCrawlWebsiteTool(config={
         "limit": 2,

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

@@ -4,7 +4,7 @@ from crewai_tools.tools.firecrawl_scrape_website_tool.firecrawl_scrape_website_t
     FirecrawlScrapeWebsiteTool,
 )
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_firecrawl_scrape_tool_integration():
     tool = FirecrawlScrapeWebsiteTool()
     result = tool.run(url="https://firecrawl.dev")

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

@@ -3,7 +3,7 @@ import pytest
 from crewai_tools.tools.firecrawl_search_tool.firecrawl_search_tool import FirecrawlSearchTool
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_firecrawl_search_tool_integration():
     tool = FirecrawlSearchTool()
     result = tool.run(query="firecrawl")

lib/crewai-tools/tests/tools/rag/test_rag_tool_add_data_type.py

@@ -0,0 +1,471 @@
+"""Tests for RagTool.add() method with various data_type values."""
+
+from pathlib import Path
+from tempfile import TemporaryDirectory
+from unittest.mock import MagicMock, Mock, patch
+
+import pytest
+
+from crewai_tools.rag.data_types import DataType
+from crewai_tools.tools.rag.rag_tool import RagTool
+
+
+@pytest.fixture
+def mock_rag_client() -> MagicMock:
+    """Create a mock RAG client for testing."""
+    mock_client = MagicMock()
+    mock_client.get_or_create_collection = MagicMock(return_value=None)
+    mock_client.add_documents = MagicMock(return_value=None)
+    mock_client.search = MagicMock(return_value=[])
+    return mock_client
+
+
+@pytest.fixture
+def rag_tool(mock_rag_client: MagicMock) -> RagTool:
+    """Create a RagTool instance with mocked client."""
+    with (
+        patch(
+            "crewai_tools.adapters.crewai_rag_adapter.get_rag_client",
+            return_value=mock_rag_client,
+        ),
+        patch(
+            "crewai_tools.adapters.crewai_rag_adapter.create_client",
+            return_value=mock_rag_client,
+        ),
+    ):
+        return RagTool()
+
+
+class TestDataTypeFileAlias:
+    """Tests for data_type='file' alias."""
+
+    def test_file_alias_with_existing_file(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test that data_type='file' works with existing files."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("Test content for file alias.")
+
+            rag_tool.add(path=str(test_file), data_type="file")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_file_alias_with_nonexistent_file_raises_error(
+        self, rag_tool: RagTool
+    ) -> None:
+        """Test that data_type='file' raises FileNotFoundError for missing files."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent/path/to/file.pdf", data_type="file")
+
+    def test_file_alias_with_path_keyword(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test that path keyword argument works with data_type='file'."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "document.txt"
+            test_file.write_text("Content via path keyword.")
+
+            rag_tool.add(data_type="file", path=str(test_file))
+
+            assert mock_rag_client.add_documents.called
+
+    def test_file_alias_with_file_path_keyword(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test that file_path keyword argument works with data_type='file'."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "document.txt"
+            test_file.write_text("Content via file_path keyword.")
+
+            rag_tool.add(data_type="file", file_path=str(test_file))
+
+            assert mock_rag_client.add_documents.called
+
+
+class TestDataTypeStringValues:
+    """Tests for data_type as string values matching DataType enum."""
+
+    def test_pdf_file_string(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type='pdf_file' with existing PDF file."""
+        with TemporaryDirectory() as tmpdir:
+            # Create a minimal valid PDF file
+            test_file = Path(tmpdir) / "test.pdf"
+            test_file.write_bytes(
+                b"%PDF-1.4\n1 0 obj\n<<\n/Type /Catalog\n>>\nendobj\ntrailer\n"
+                b"<<\n/Root 1 0 R\n>>\n%%EOF"
+            )
+
+            # Mock the PDF loader to avoid actual PDF parsing
+            with patch(
+                "crewai_tools.adapters.crewai_rag_adapter.DataType.get_loader"
+            ) as mock_loader:
+                mock_loader_instance = MagicMock()
+                mock_loader_instance.load.return_value = MagicMock(
+                    content="PDF content", metadata={}, doc_id="test-id"
+                )
+                mock_loader.return_value = mock_loader_instance
+
+                rag_tool.add(path=str(test_file), data_type="pdf_file")
+
+                assert mock_rag_client.add_documents.called
+
+    def test_text_file_string(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type='text_file' with existing text file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("Plain text content.")
+
+            rag_tool.add(path=str(test_file), data_type="text_file")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_csv_string(self, rag_tool: RagTool, mock_rag_client: MagicMock) -> None:
+        """Test data_type='csv' with existing CSV file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.csv"
+            test_file.write_text("name,value\nfoo,1\nbar,2")
+
+            rag_tool.add(path=str(test_file), data_type="csv")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_json_string(self, rag_tool: RagTool, mock_rag_client: MagicMock) -> None:
+        """Test data_type='json' with existing JSON file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.json"
+            test_file.write_text('{"key": "value", "items": [1, 2, 3]}')
+
+            rag_tool.add(path=str(test_file), data_type="json")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_xml_string(self, rag_tool: RagTool, mock_rag_client: MagicMock) -> None:
+        """Test data_type='xml' with existing XML file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.xml"
+            test_file.write_text('<?xml version="1.0"?><root><item>value</item></root>')
+
+            rag_tool.add(path=str(test_file), data_type="xml")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_mdx_string(self, rag_tool: RagTool, mock_rag_client: MagicMock) -> None:
+        """Test data_type='mdx' with existing MDX file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.mdx"
+            test_file.write_text("# Heading\n\nSome markdown content.")
+
+            rag_tool.add(path=str(test_file), data_type="mdx")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_text_string(self, rag_tool: RagTool, mock_rag_client: MagicMock) -> None:
+        """Test data_type='text' with raw text content."""
+        rag_tool.add("This is raw text content.", data_type="text")
+
+        assert mock_rag_client.add_documents.called
+
+    def test_directory_string(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type='directory' with existing directory."""
+        with TemporaryDirectory() as tmpdir:
+            # Create some files in the directory
+            (Path(tmpdir) / "file1.txt").write_text("Content 1")
+            (Path(tmpdir) / "file2.txt").write_text("Content 2")
+
+            rag_tool.add(path=tmpdir, data_type="directory")
+
+            assert mock_rag_client.add_documents.called
+
+
+class TestDataTypeEnumValues:
+    """Tests for data_type as DataType enum values."""
+
+    def test_datatype_file_enum_with_existing_file(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type=DataType.FILE with existing file (auto-detect)."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("File enum auto-detect content.")
+
+            rag_tool.add(str(test_file), data_type=DataType.FILE)
+
+            assert mock_rag_client.add_documents.called
+
+    def test_datatype_file_enum_with_nonexistent_file_raises_error(
+        self, rag_tool: RagTool
+    ) -> None:
+        """Test data_type=DataType.FILE raises FileNotFoundError for missing files."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add("nonexistent/file.pdf", data_type=DataType.FILE)
+
+    def test_datatype_pdf_file_enum(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type=DataType.PDF_FILE with existing file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.pdf"
+            test_file.write_bytes(
+                b"%PDF-1.4\n1 0 obj\n<<\n/Type /Catalog\n>>\nendobj\ntrailer\n"
+                b"<<\n/Root 1 0 R\n>>\n%%EOF"
+            )
+
+            with patch(
+                "crewai_tools.adapters.crewai_rag_adapter.DataType.get_loader"
+            ) as mock_loader:
+                mock_loader_instance = MagicMock()
+                mock_loader_instance.load.return_value = MagicMock(
+                    content="PDF content", metadata={}, doc_id="test-id"
+                )
+                mock_loader.return_value = mock_loader_instance
+
+                rag_tool.add(str(test_file), data_type=DataType.PDF_FILE)
+
+                assert mock_rag_client.add_documents.called
+
+    def test_datatype_text_file_enum(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type=DataType.TEXT_FILE with existing file."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("Text file content.")
+
+            rag_tool.add(str(test_file), data_type=DataType.TEXT_FILE)
+
+            assert mock_rag_client.add_documents.called
+
+    def test_datatype_text_enum(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type=DataType.TEXT with raw text."""
+        rag_tool.add("Raw text using enum.", data_type=DataType.TEXT)
+
+        assert mock_rag_client.add_documents.called
+
+    def test_datatype_directory_enum(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test data_type=DataType.DIRECTORY with existing directory."""
+        with TemporaryDirectory() as tmpdir:
+            (Path(tmpdir) / "file.txt").write_text("Directory file content.")
+
+            rag_tool.add(tmpdir, data_type=DataType.DIRECTORY)
+
+            assert mock_rag_client.add_documents.called
+
+
+class TestInvalidDataType:
+    """Tests for invalid data_type values."""
+
+    def test_invalid_string_data_type_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that invalid string data_type raises ValueError."""
+        with pytest.raises(ValueError, match="Invalid data_type"):
+            rag_tool.add("some content", data_type="invalid_type")
+
+    def test_invalid_data_type_error_message_contains_valid_values(
+        self, rag_tool: RagTool
+    ) -> None:
+        """Test that error message lists valid data_type values."""
+        with pytest.raises(ValueError) as exc_info:
+            rag_tool.add("some content", data_type="not_a_type")
+
+        error_message = str(exc_info.value)
+        assert "file" in error_message
+        assert "pdf_file" in error_message
+        assert "text_file" in error_message
+
+
+class TestFileExistenceValidation:
+    """Tests for file existence validation."""
+
+    def test_pdf_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent PDF file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.pdf", data_type="pdf_file")
+
+    def test_text_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent text file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.txt", data_type="text_file")
+
+    def test_csv_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent CSV file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.csv", data_type="csv")
+
+    def test_json_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent JSON file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.json", data_type="json")
+
+    def test_xml_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent XML file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.xml", data_type="xml")
+
+    def test_docx_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent DOCX file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.docx", data_type="docx")
+
+    def test_mdx_file_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent MDX file raises FileNotFoundError."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add(path="nonexistent.mdx", data_type="mdx")
+
+    def test_directory_not_found_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that non-existent directory raises ValueError."""
+        with pytest.raises(ValueError, match="Directory does not exist"):
+            rag_tool.add(path="nonexistent/directory", data_type="directory")
+
+
+class TestKeywordArgumentVariants:
+    """Tests for different keyword argument combinations."""
+
+    def test_positional_argument_with_data_type(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test positional argument with data_type."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("Positional arg content.")
+
+            rag_tool.add(str(test_file), data_type="text_file")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_path_keyword_with_data_type(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test path keyword argument with data_type."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("Path keyword content.")
+
+            rag_tool.add(path=str(test_file), data_type="text_file")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_file_path_keyword_with_data_type(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test file_path keyword argument with data_type."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("File path keyword content.")
+
+            rag_tool.add(file_path=str(test_file), data_type="text_file")
+
+            assert mock_rag_client.add_documents.called
+
+    def test_directory_path_keyword(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test directory_path keyword argument."""
+        with TemporaryDirectory() as tmpdir:
+            (Path(tmpdir) / "file.txt").write_text("Directory content.")
+
+            rag_tool.add(directory_path=tmpdir)
+
+            assert mock_rag_client.add_documents.called
+
+
+class TestAutoDetection:
+    """Tests for auto-detection of data type from content."""
+
+    def test_auto_detect_nonexistent_file_raises_error(self, rag_tool: RagTool) -> None:
+        """Test that auto-detection raises FileNotFoundError for missing files."""
+        with pytest.raises(FileNotFoundError, match="File does not exist"):
+            rag_tool.add("path/to/document.pdf")
+
+    def test_auto_detect_txt_file(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test auto-detection of .txt file type."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "auto.txt"
+            test_file.write_text("Auto-detected text file.")
+
+            # No data_type specified - should auto-detect
+            rag_tool.add(str(test_file))
+
+            assert mock_rag_client.add_documents.called
+
+    def test_auto_detect_csv_file(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test auto-detection of .csv file type."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "auto.csv"
+            test_file.write_text("col1,col2\nval1,val2")
+
+            rag_tool.add(str(test_file))
+
+            assert mock_rag_client.add_documents.called
+
+    def test_auto_detect_json_file(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test auto-detection of .json file type."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "auto.json"
+            test_file.write_text('{"auto": "detected"}')
+
+            rag_tool.add(str(test_file))
+
+            assert mock_rag_client.add_documents.called
+
+    def test_auto_detect_directory(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test auto-detection of directory type."""
+        with TemporaryDirectory() as tmpdir:
+            (Path(tmpdir) / "file.txt").write_text("Auto-detected directory.")
+
+            rag_tool.add(tmpdir)
+
+            assert mock_rag_client.add_documents.called
+
+    def test_auto_detect_raw_text(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test auto-detection of raw text (non-file content)."""
+        rag_tool.add("Just some raw text content")
+
+        assert mock_rag_client.add_documents.called
+
+
+class TestMetadataHandling:
+    """Tests for metadata handling with data_type."""
+
+    def test_metadata_passed_to_documents(
+        self, rag_tool: RagTool, mock_rag_client: MagicMock
+    ) -> None:
+        """Test that metadata is properly passed to documents."""
+        with TemporaryDirectory() as tmpdir:
+            test_file = Path(tmpdir) / "test.txt"
+            test_file.write_text("Content with metadata.")
+
+            rag_tool.add(
+                path=str(test_file),
+                data_type="text_file",
+                metadata={"custom_key": "custom_value"},
+            )
+
+            assert mock_rag_client.add_documents.called
+            call_args = mock_rag_client.add_documents.call_args
+            documents = call_args.kwargs.get("documents", call_args.args[0] if call_args.args else [])
+
+            # Check that at least one document has the custom metadata
+            assert any(
+                doc.get("metadata", {}).get("custom_key") == "custom_value"
+                for doc in documents
+            )

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

@@ -23,15 +23,13 @@ from crewai_tools.tools.rag.rag_tool import Adapter
 import pytest
 
 
-pytestmark = [pytest.mark.vcr(filter_headers=["authorization"])]
-
-
 @pytest.fixture
 def mock_adapter():
     mock_adapter = MagicMock(spec=Adapter)
     return mock_adapter
 
 
+@pytest.mark.vcr()
 def test_directory_search_tool():
     with tempfile.TemporaryDirectory() as temp_dir:
         test_file = Path(temp_dir) / "test.txt"
@@ -65,6 +63,7 @@ def test_pdf_search_tool(mock_adapter):
     )
 
 
+@pytest.mark.vcr()
 def test_txt_search_tool():
     with tempfile.NamedTemporaryFile(suffix=".txt", delete=False) as temp_file:
         temp_file.write(b"This is a test file for txt search")
@@ -102,6 +101,7 @@ def test_docx_search_tool(mock_adapter):
     )
 
 
+@pytest.mark.vcr()
 def test_json_search_tool():
     with tempfile.NamedTemporaryFile(suffix=".json", delete=False) as temp_file:
         temp_file.write(b'{"test": "This is a test JSON file"}')
@@ -127,6 +127,7 @@ def test_xml_search_tool(mock_adapter):
     )
 
 
+@pytest.mark.vcr()
 def test_csv_search_tool():
     with tempfile.NamedTemporaryFile(suffix=".csv", delete=False) as temp_file:
         temp_file.write(b"name,description\ntest,This is a test CSV file")
@@ -141,6 +142,7 @@ def test_csv_search_tool():
         os.unlink(temp_file_path)
 
 
+@pytest.mark.vcr()
 def test_mdx_search_tool():
     with tempfile.NamedTemporaryFile(suffix=".mdx", delete=False) as temp_file:
         temp_file.write(b"# Test MDX\nThis is a test MDX file")

lib/crewai/pyproject.toml

@@ -9,35 +9,35 @@ authors = [
 requires-python = ">=3.10, <3.14"
 dependencies = [
     # Core Dependencies
-    "pydantic>=2.11.9",
-    "openai>=1.13.3",
+    "pydantic~=2.11.9",
+    "openai~=1.83.0",
     "instructor>=1.3.3",
     # Text Processing
-    "pdfplumber>=0.11.4",
-    "regex>=2024.9.11",
+    "pdfplumber~=0.11.4",
+    "regex~=2024.9.11",
     # Telemetry and Monitoring
-    "opentelemetry-api>=1.30.0",
-    "opentelemetry-sdk>=1.30.0",
-    "opentelemetry-exporter-otlp-proto-http>=1.30.0",
+    "opentelemetry-api~=1.34.0",
+    "opentelemetry-sdk~=1.34.0",
+    "opentelemetry-exporter-otlp-proto-http~=1.34.0",
     # Data Handling
     "chromadb~=1.1.0",
-    "tokenizers>=0.20.3",
-    "openpyxl>=3.1.5",
+    "tokenizers~=0.20.3",
+    "openpyxl~=3.1.5",
     # Authentication and Security
-    "python-dotenv>=1.1.1",
-    "pyjwt>=2.9.0",
+    "python-dotenv~=1.1.1",
+    "pyjwt~=2.9.0",
     # Configuration and Utils
-    "click>=8.1.7",
-    "appdirs>=1.4.4",
-    "jsonref>=1.1.0",
-    "json-repair==0.25.2",
-    "uv>=0.4.25",
-    "tomli-w>=1.1.0",
-    "tomli>=2.0.2",
-    "json5>=0.10.0",
-    "portalocker==2.7.0",
-    "pydantic-settings>=2.10.1",
-    "mcp>=1.16.0",
+    "click~=8.1.7",
+    "appdirs~=1.4.4",
+    "jsonref~=1.1.0",
+    "json-repair~=0.25.2",
+    "tomli-w~=1.1.0",
+    "tomli~=2.0.2",
+    "json5~=0.10.0",
+    "portalocker~=2.7.0",
+    "pydantic-settings~=2.10.1",
+    "mcp~=1.16.0",
+    "uv~=0.9.13",
 ]
 
 [project.urls]
@@ -48,55 +48,52 @@ Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
 tools = [
-    "crewai-tools==1.5.0",
+    "crewai-tools==1.6.1",
 ]
 embeddings = [
     "tiktoken~=0.8.0"
 ]
-pdfplumber = [
-    "pdfplumber>=0.11.4",
-]
 pandas = [
-    "pandas>=2.2.3",
+    "pandas~=2.2.3",
 ]
 openpyxl = [
-    "openpyxl>=3.1.5",
+    "openpyxl~=3.1.5",
 ]
-mem0 = ["mem0ai>=0.1.94"]
+mem0 = ["mem0ai~=0.1.94"]
 docling = [
-    "docling>=2.12.0",
+    "docling~=2.63.0",
 ]
 qdrant = [
-    "qdrant-client[fastembed]>=1.14.3",
+    "qdrant-client[fastembed]~=1.14.3",
 ]
 aws = [
-    "boto3>=1.40.38",
+    "boto3~=1.40.38",
 ]
 watson = [
-    "ibm-watsonx-ai>=1.3.39",
+    "ibm-watsonx-ai~=1.3.39",
 ]
 voyageai = [
-    "voyageai>=0.3.5",
+    "voyageai~=0.3.5",
 ]
 litellm = [
-    "litellm>=1.74.9",
+    "litellm~=1.74.9",
 ]
 bedrock = [
-    "boto3>=1.40.45",
+    "boto3~=1.40.45",
 ]
 google-genai = [
-    "google-genai>=1.2.0",
+    "google-genai~=1.2.0",
 ]
 azure-ai-inference = [
-    "azure-ai-inference>=1.0.0b9",
+    "azure-ai-inference~=1.0.0b9",
 ]
 anthropic = [
-    "anthropic>=0.69.0",
+    "anthropic~=0.71.0",
 ]
- a2a = [
+a2a = [
      "a2a-sdk~=0.3.10",
-     "httpx-auth>=0.23.1",
-     "httpx-sse>=0.4.0",
+     "httpx-auth~=0.23.1",
+     "httpx-sse~=0.4.0",
 ]
 
 

lib/crewai/src/crewai/__init__.py

@@ -40,7 +40,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:
 
 _suppress_pydantic_deprecation_warnings()
 
-__version__ = "1.5.0"
+__version__ = "1.6.1"
 _telemetry_submitted = False
 
 

lib/crewai/src/crewai/cli/config.py

@@ -73,6 +73,7 @@ CLI_SETTINGS_KEYS = [
     "oauth2_audience",
     "oauth2_client_id",
     "oauth2_domain",
+    "oauth2_extra",
 ]
 
 # Default values for CLI settings
@@ -82,6 +83,7 @@ DEFAULT_CLI_SETTINGS = {
     "oauth2_audience": CREWAI_ENTERPRISE_DEFAULT_OAUTH2_AUDIENCE,
     "oauth2_client_id": CREWAI_ENTERPRISE_DEFAULT_OAUTH2_CLIENT_ID,
     "oauth2_domain": CREWAI_ENTERPRISE_DEFAULT_OAUTH2_DOMAIN,
+    "oauth2_extra": {},
 }
 
 # Readonly settings - cannot be set by the user

lib/crewai/src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.5.0"
+    "crewai[tools]==1.6.1"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]==1.5.0"
+    "crewai[tools]==1.6.1"
 ]
 
 [project.scripts]

lib/crewai/src/crewai/events/listeners/tracing/trace_batch_manager.py

@@ -76,7 +76,7 @@ class TraceBatchManager:
         use_ephemeral: bool = False,
     ) -> TraceBatch:
         """Initialize a new trace batch (thread-safe)"""
-        with self._init_lock:
+        with self._batch_ready_cv:
             if self.current_batch is not None:
                 logger.debug(
                     "Batch already initialized, skipping duplicate initialization"
@@ -99,7 +99,6 @@ class TraceBatchManager:
                 self.backend_initialized = True
 
             self._batch_ready_cv.notify_all()
-
             return self.current_batch
 
     def _initialize_backend_batch(
@@ -107,7 +106,7 @@ class TraceBatchManager:
         user_context: dict[str, str],
         execution_metadata: dict[str, Any],
         use_ephemeral: bool = False,
-    ):
+    ) -> None:
         """Send batch initialization to backend"""
 
         if not is_tracing_enabled_in_context():
@@ -204,7 +203,7 @@ class TraceBatchManager:
                     return False
         return True
 
-    def add_event(self, trace_event: TraceEvent):
+    def add_event(self, trace_event: TraceEvent) -> None:
         """Add event to buffer"""
         self.event_buffer.append(trace_event)
 
@@ -300,7 +299,7 @@ class TraceBatchManager:
 
         return finalized_batch
 
-    def _finalize_backend_batch(self, events_count: int = 0):
+    def _finalize_backend_batch(self, events_count: int = 0) -> None:
         """Send batch finalization to backend
 
         Args:
@@ -366,7 +365,7 @@ class TraceBatchManager:
             logger.error(f"❌ Error finalizing trace batch: {e}")
             self.plus_api.mark_trace_batch_as_failed(self.trace_batch_id, str(e))
 
-    def _cleanup_batch_data(self):
+    def _cleanup_batch_data(self) -> None:
         """Clean up batch data after successful finalization to free memory"""
         try:
             if hasattr(self, "event_buffer") and self.event_buffer:
@@ -411,7 +410,7 @@ class TraceBatchManager:
                 lambda: self.current_batch is not None, timeout=timeout
             )
 
-    def record_start_time(self, key: str):
+    def record_start_time(self, key: str) -> None:
         """Record start time for duration calculation"""
         self.execution_start_times[key] = datetime.now(timezone.utc)
 

lib/crewai/src/crewai/events/listeners/tracing/trace_listener.py

@@ -71,6 +71,7 @@ from crewai.events.types.reasoning_events import (
     AgentReasoningFailedEvent,
     AgentReasoningStartedEvent,
 )
+from crewai.events.types.system_events import SignalEvent, on_signal
 from crewai.events.types.task_events import (
     TaskCompletedEvent,
     TaskFailedEvent,
@@ -159,6 +160,7 @@ class TraceCollectionListener(BaseEventListener):
         self._register_flow_event_handlers(crewai_event_bus)
         self._register_context_event_handlers(crewai_event_bus)
         self._register_action_event_handlers(crewai_event_bus)
+        self._register_system_event_handlers(crewai_event_bus)
 
         self._listeners_setup = True
 
@@ -458,6 +460,15 @@ class TraceCollectionListener(BaseEventListener):
         ) -> None:
             self._handle_action_event("knowledge_query_failed", source, event)
 
+    def _register_system_event_handlers(self, event_bus: CrewAIEventsBus) -> None:
+        """Register handlers for system signal events (SIGTERM, SIGINT, etc.)."""
+
+        @on_signal
+        def handle_signal(source: Any, event: SignalEvent) -> None:
+            """Flush trace batch on system signals to prevent data loss."""
+            if self.batch_manager.is_batch_initialized():
+                self.batch_manager.finalize_batch()
+
     def _initialize_crew_batch(self, source: Any, event: Any) -> None:
         """Initialize trace batch.
 

lib/crewai/src/crewai/events/types/system_events.py

@@ -0,0 +1,102 @@
+"""System signal event types for CrewAI.
+
+This module contains event types for system-level signals like SIGTERM,
+allowing listeners to perform cleanup operations before process termination.
+"""
+
+from collections.abc import Callable
+from enum import IntEnum
+import signal
+from typing import Annotated, Literal, TypeVar
+
+from pydantic import Field, TypeAdapter
+
+from crewai.events.base_events import BaseEvent
+
+
+class SignalType(IntEnum):
+    """Enumeration of supported system signals."""
+
+    SIGTERM = signal.SIGTERM
+    SIGINT = signal.SIGINT
+    SIGHUP = signal.SIGHUP
+    SIGTSTP = signal.SIGTSTP
+    SIGCONT = signal.SIGCONT
+
+
+class SigTermEvent(BaseEvent):
+    """Event emitted when SIGTERM is received."""
+
+    type: Literal["SIGTERM"] = "SIGTERM"
+    signal_number: SignalType = SignalType.SIGTERM
+    reason: str | None = None
+
+
+class SigIntEvent(BaseEvent):
+    """Event emitted when SIGINT is received."""
+
+    type: Literal["SIGINT"] = "SIGINT"
+    signal_number: SignalType = SignalType.SIGINT
+    reason: str | None = None
+
+
+class SigHupEvent(BaseEvent):
+    """Event emitted when SIGHUP is received."""
+
+    type: Literal["SIGHUP"] = "SIGHUP"
+    signal_number: SignalType = SignalType.SIGHUP
+    reason: str | None = None
+
+
+class SigTStpEvent(BaseEvent):
+    """Event emitted when SIGTSTP is received.
+
+    Note: SIGSTOP cannot be caught - it immediately suspends the process.
+    """
+
+    type: Literal["SIGTSTP"] = "SIGTSTP"
+    signal_number: SignalType = SignalType.SIGTSTP
+    reason: str | None = None
+
+
+class SigContEvent(BaseEvent):
+    """Event emitted when SIGCONT is received."""
+
+    type: Literal["SIGCONT"] = "SIGCONT"
+    signal_number: SignalType = SignalType.SIGCONT
+    reason: str | None = None
+
+
+SignalEvent = Annotated[
+    SigTermEvent | SigIntEvent | SigHupEvent | SigTStpEvent | SigContEvent,
+    Field(discriminator="type"),
+]
+
+signal_event_adapter: TypeAdapter[SignalEvent] = TypeAdapter(SignalEvent)
+
+SIGNAL_EVENT_TYPES: tuple[type[BaseEvent], ...] = (
+    SigTermEvent,
+    SigIntEvent,
+    SigHupEvent,
+    SigTStpEvent,
+    SigContEvent,
+)
+
+
+T = TypeVar("T", bound=Callable[[object, SignalEvent], None])
+
+
+def on_signal(func: T) -> T:
+    """Decorator to register a handler for all signal events.
+
+    Args:
+        func: Handler function that receives (source, event) arguments.
+
+    Returns:
+        The original function, registered for all signal event types.
+    """
+    from crewai.events.event_bus import crewai_event_bus
+
+    for event_type in SIGNAL_EVENT_TYPES:
+        crewai_event_bus.on(event_type)(func)
+    return func

lib/crewai/src/crewai/llm.py

@@ -406,46 +406,100 @@ class LLM(BaseLLM):
         instance.is_litellm = True
         return instance
 
+    @classmethod
+    def _matches_provider_pattern(cls, model: str, provider: str) -> bool:
+        """Check if a model name matches provider-specific patterns.
+
+        This allows supporting models that aren't in the hardcoded constants list,
+        including "latest" versions and new models that follow provider naming conventions.
+
+        Args:
+            model: The model name to check
+            provider: The provider to check against (canonical name)
+
+        Returns:
+            True if the model matches the provider's naming pattern, False otherwise
+        """
+        model_lower = model.lower()
+
+        if provider == "openai":
+            return any(
+                model_lower.startswith(prefix)
+                for prefix in ["gpt-", "o1", "o3", "o4", "whisper-"]
+            )
+
+        if provider == "anthropic" or provider == "claude":
+            return any(
+                model_lower.startswith(prefix) for prefix in ["claude-", "anthropic."]
+            )
+
+        if provider == "gemini" or provider == "google":
+            return any(
+                model_lower.startswith(prefix)
+                for prefix in ["gemini-", "gemma-", "learnlm-"]
+            )
+
+        if provider == "bedrock":
+            return "." in model_lower
+
+        if provider == "azure":
+            return any(
+                model_lower.startswith(prefix)
+                for prefix in ["gpt-", "gpt-35-", "o1", "o3", "o4", "azure-"]
+            )
+
+        return False
+
     @classmethod
     def _validate_model_in_constants(cls, model: str, provider: str) -> bool:
-        """Validate if a model name exists in the provider's constants.
+        """Validate if a model name exists in the provider's constants or matches provider patterns.
+
+        This method first checks the hardcoded constants list for known models.
+        If not found, it falls back to pattern matching to support new models,
+        "latest" versions, and models that follow provider naming conventions.
 
         Args:
             model: The model name to validate
             provider: The provider to check against (canonical name)
 
         Returns:
-            True if the model exists in the provider's constants, False otherwise
+            True if the model exists in constants or matches provider patterns, False otherwise
         """
-        if provider == "openai":
-            return model in OPENAI_MODELS
+        if provider == "openai" and model in OPENAI_MODELS:
+            return True
 
-        if provider == "anthropic" or provider == "claude":
-            return model in ANTHROPIC_MODELS
+        if (
+            provider == "anthropic" or provider == "claude"
+        ) and model in ANTHROPIC_MODELS:
+            return True
 
-        if provider == "gemini":
-            return model in GEMINI_MODELS
+        if (provider == "gemini" or provider == "google") and model in GEMINI_MODELS:
+            return True
 
-        if provider == "bedrock":
-            return model in BEDROCK_MODELS
+        if provider == "bedrock" and model in BEDROCK_MODELS:
+            return True
 
         if provider == "azure":
             # azure does not provide a list of available models, determine a better way to handle this
             return True
 
-        return False
+        # Fallback to pattern matching for models not in constants
+        return cls._matches_provider_pattern(model, provider)
 
     @classmethod
     def _infer_provider_from_model(cls, model: str) -> str:
         """Infer the provider from the model name.
 
+        This method first checks the hardcoded constants list for known models.
+        If not found, it uses pattern matching to infer the provider from model name patterns.
+        This allows supporting new models and "latest" versions without hardcoding.
+
         Args:
             model: The model name without provider prefix
 
         Returns:
             The inferred provider name, defaults to "openai"
         """
-
         if model in OPENAI_MODELS:
             return "openai"
 
@@ -1699,12 +1753,14 @@ class LLM(BaseLLM):
             max_tokens=self.max_tokens,
             presence_penalty=self.presence_penalty,
             frequency_penalty=self.frequency_penalty,
-            logit_bias=copy.deepcopy(self.logit_bias, memo)
-            if self.logit_bias
-            else None,
-            response_format=copy.deepcopy(self.response_format, memo)
-            if self.response_format
-            else None,
+            logit_bias=(
+                copy.deepcopy(self.logit_bias, memo) if self.logit_bias else None
+            ),
+            response_format=(
+                copy.deepcopy(self.response_format, memo)
+                if self.response_format
+                else None
+            ),
             seed=self.seed,
             logprobs=self.logprobs,
             top_logprobs=self.top_logprobs,

lib/crewai/src/crewai/llms/constants.py

@@ -182,6 +182,8 @@ OPENAI_MODELS: list[OpenAIModels] = [
 
 
 AnthropicModels: TypeAlias = Literal[
+    "claude-opus-4-5-20251101",
+    "claude-opus-4-5",
     "claude-3-7-sonnet-latest",
     "claude-3-7-sonnet-20250219",
     "claude-3-5-haiku-latest",
@@ -208,6 +210,8 @@ AnthropicModels: TypeAlias = Literal[
     "claude-3-haiku-20240307",
 ]
 ANTHROPIC_MODELS: list[AnthropicModels] = [
+    "claude-opus-4-5-20251101",
+    "claude-opus-4-5",
     "claude-3-7-sonnet-latest",
     "claude-3-7-sonnet-20250219",
     "claude-3-5-haiku-latest",
@@ -252,6 +256,7 @@ GeminiModels: TypeAlias = Literal[
     "gemini-2.5-flash-preview-tts",
     "gemini-2.5-pro-preview-tts",
     "gemini-2.5-computer-use-preview-10-2025",
+    "gemini-2.5-pro-exp-03-25",
     "gemini-2.0-flash",
     "gemini-2.0-flash-001",
     "gemini-2.0-flash-exp",
@@ -305,6 +310,7 @@ GEMINI_MODELS: list[GeminiModels] = [
     "gemini-2.5-flash-preview-tts",
     "gemini-2.5-pro-preview-tts",
     "gemini-2.5-computer-use-preview-10-2025",
+    "gemini-2.5-pro-exp-03-25",
     "gemini-2.0-flash",
     "gemini-2.0-flash-001",
     "gemini-2.0-flash-exp",
@@ -452,6 +458,7 @@ BedrockModels: TypeAlias = Literal[
     "anthropic.claude-3-sonnet-20240229-v1:0:28k",
     "anthropic.claude-haiku-4-5-20251001-v1:0",
     "anthropic.claude-instant-v1:2:100k",
+    "anthropic.claude-opus-4-5-20251101-v1:0",
     "anthropic.claude-opus-4-1-20250805-v1:0",
     "anthropic.claude-opus-4-20250514-v1:0",
     "anthropic.claude-sonnet-4-20250514-v1:0",
@@ -524,6 +531,7 @@ BEDROCK_MODELS: list[BedrockModels] = [
     "anthropic.claude-3-sonnet-20240229-v1:0:28k",
     "anthropic.claude-haiku-4-5-20251001-v1:0",
     "anthropic.claude-instant-v1:2:100k",
+    "anthropic.claude-opus-4-5-20251101-v1:0",
     "anthropic.claude-opus-4-1-20250805-v1:0",
     "anthropic.claude-opus-4-20250514-v1:0",
     "anthropic.claude-sonnet-4-20250514-v1:0",

lib/crewai/src/crewai/llms/providers/azure/completion.py

@@ -8,6 +8,7 @@ from typing import TYPE_CHECKING, Any
 from pydantic import BaseModel
 
 from crewai.utilities.agent_utils import is_context_length_exceeded
+from crewai.utilities.converter import generate_model_description
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededError,
 )
@@ -26,6 +27,7 @@ try:
     from azure.ai.inference.models import (
         ChatCompletions,
         ChatCompletionsToolCall,
+        JsonSchemaFormat,
         StreamingChatCompletionsUpdate,
     )
     from azure.core.credentials import (
@@ -278,13 +280,16 @@ class AzureCompletion(BaseLLM):
         }
 
         if response_model and self.is_openai_model:
-            params["response_format"] = {
-                "type": "json_schema",
-                "json_schema": {
-                    "name": response_model.__name__,
-                    "schema": response_model.model_json_schema(),
-                },
-            }
+            model_description = generate_model_description(response_model)
+            json_schema_info = model_description["json_schema"]
+            json_schema_name = json_schema_info["name"]
+
+            params["response_format"] = JsonSchemaFormat(
+                name=json_schema_name,
+                schema=json_schema_info["schema"],
+                description=f"Schema for {json_schema_name}",
+                strict=json_schema_info["strict"],
+            )
 
         # Only include model parameter for non-Azure OpenAI endpoints
         # Azure OpenAI endpoints have the deployment name in the URL
@@ -310,6 +315,14 @@ class AzureCompletion(BaseLLM):
             params["tools"] = self._convert_tools_for_interference(tools)
             params["tool_choice"] = "auto"
 
+        additional_params = self.additional_params
+        additional_drop_params = additional_params.get("additional_drop_params")
+        drop_params = additional_params.get("drop_params")
+
+        if drop_params and isinstance(additional_drop_params, list):
+            for drop_param in additional_drop_params:
+                params.pop(drop_param, None)
+
         return params
 
     def _convert_tools_for_interference(

lib/crewai/src/crewai/mcp/transports/sse.py

@@ -66,7 +66,6 @@ class SSETransport(BaseTransport):
             self._transport_context = sse_client(
                 self.url,
                 headers=self.headers if self.headers else None,
-                terminate_on_close=True,
             )
 
             read, write = await self._transport_context.__aenter__()

lib/crewai/src/crewai/memory/storage/rag_storage.py

@@ -16,6 +16,7 @@ from crewai.utilities.paths import db_storage_path
 
 
 if TYPE_CHECKING:
+    from crewai.crew import Crew
     from crewai.rag.core.base_client import BaseClient
     from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
     from crewai.rag.embeddings.types import ProviderSpec
@@ -32,16 +33,16 @@ class RAGStorage(BaseRAGStorage):
         self,
         type: str,
         allow_reset: bool = True,
-        embedder_config: ProviderSpec | BaseEmbeddingsProvider | None = None,
-        crew: Any = None,
+        embedder_config: ProviderSpec | BaseEmbeddingsProvider[Any] | None = None,
+        crew: Crew | None = None,
         path: str | None = None,
     ) -> None:
         super().__init__(type, allow_reset, embedder_config, crew)
-        agents = crew.agents if crew else []
-        agents = [self._sanitize_role(agent.role) for agent in agents]
-        agents = "_".join(agents)
-        self.agents = agents
-        self.storage_file_name = self._build_storage_file_name(type, agents)
+        crew_agents = crew.agents if crew else []
+        sanitized_roles = [self._sanitize_role(agent.role) for agent in crew_agents]
+        agents_str = "_".join(sanitized_roles)
+        self.agents = agents_str
+        self.storage_file_name = self._build_storage_file_name(type, agents_str)
 
         self.type = type
         self._client: BaseClient | None = None
@@ -96,6 +97,10 @@ class RAGStorage(BaseRAGStorage):
                         ChromaEmbeddingFunctionWrapper, embedding_function
                     )
                 )
+
+            if self.path:
+                config.settings.persist_directory = self.path
+
             self._client = create_client(config)
 
     def _get_client(self) -> BaseClient:

lib/crewai/src/crewai/project/annotations.py

@@ -2,8 +2,10 @@
 
 from __future__ import annotations
 
+import asyncio
 from collections.abc import Callable
 from functools import wraps
+import inspect
 from typing import TYPE_CHECKING, Any, Concatenate, ParamSpec, TypeVar, overload
 
 from crewai.project.utils import memoize
@@ -156,6 +158,23 @@ def cache_handler(meth: Callable[P, R]) -> CacheHandlerMethod[P, R]:
     return CacheHandlerMethod(memoize(meth))
 
 
+def _call_method(method: Callable[..., Any], *args: Any, **kwargs: Any) -> Any:
+    """Call a method, awaiting it if async and running in an event loop."""
+    result = method(*args, **kwargs)
+    if inspect.iscoroutine(result):
+        try:
+            loop = asyncio.get_running_loop()
+        except RuntimeError:
+            loop = None
+        if loop and loop.is_running():
+            import concurrent.futures
+
+            with concurrent.futures.ThreadPoolExecutor() as pool:
+                return pool.submit(asyncio.run, result).result()
+        return asyncio.run(result)
+    return result
+
+
 @overload
 def crew(
     meth: Callable[Concatenate[SelfT, P], Crew],
@@ -198,7 +217,7 @@ def crew(
 
         # Instantiate tasks in order
         for _, task_method in tasks:
-            task_instance = task_method(self)
+            task_instance = _call_method(task_method, self)
             instantiated_tasks.append(task_instance)
             agent_instance = getattr(task_instance, "agent", None)
             if agent_instance and agent_instance.role not in agent_roles:
@@ -207,7 +226,7 @@ def crew(
 
         # Instantiate agents not included by tasks
         for _, agent_method in agents:
-            agent_instance = agent_method(self)
+            agent_instance = _call_method(agent_method, self)
             if agent_instance.role not in agent_roles:
                 instantiated_agents.append(agent_instance)
                 agent_roles.add(agent_instance.role)
@@ -215,7 +234,7 @@ def crew(
         self.agents = instantiated_agents
         self.tasks = instantiated_tasks
 
-        crew_instance = meth(self, *args, **kwargs)
+        crew_instance: Crew = _call_method(meth, self, *args, **kwargs)
 
         def callback_wrapper(
             hook: Callable[Concatenate[CrewInstance, P2], R2], instance: CrewInstance

lib/crewai/src/crewai/project/utils.py

@@ -1,7 +1,8 @@
 """Utility functions for the crewai project module."""
 
-from collections.abc import Callable
+from collections.abc import Callable, Coroutine
 from functools import wraps
+import inspect
 from typing import Any, ParamSpec, TypeVar, cast
 
 from pydantic import BaseModel
@@ -37,8 +38,8 @@ def _make_hashable(arg: Any) -> Any:
 def memoize(meth: Callable[P, R]) -> Callable[P, R]:
     """Memoize a method by caching its results based on arguments.
 
-    Handles Pydantic BaseModel instances by converting them to JSON strings
-    before hashing for cache lookup.
+    Handles both sync and async methods. Pydantic BaseModel instances are
+    converted to JSON strings before hashing for cache lookup.
 
     Args:
         meth: The method to memoize.
@@ -46,18 +47,16 @@ def memoize(meth: Callable[P, R]) -> Callable[P, R]:
     Returns:
         A memoized version of the method that caches results.
     """
+    if inspect.iscoroutinefunction(meth):
+        return cast(Callable[P, R], _memoize_async(meth))
+    return _memoize_sync(meth)
+
+
+def _memoize_sync(meth: Callable[P, R]) -> Callable[P, R]:
+    """Memoize a synchronous method."""
 
     @wraps(meth)
     def wrapper(*args: P.args, **kwargs: P.kwargs) -> R:
-        """Wrapper that converts arguments to hashable form before caching.
-
-        Args:
-            *args: Positional arguments to the memoized method.
-            **kwargs: Keyword arguments to the memoized method.
-
-        Returns:
-            The result of the memoized method call.
-        """
         hashable_args = tuple(_make_hashable(arg) for arg in args)
         hashable_kwargs = tuple(
             sorted((k, _make_hashable(v)) for k, v in kwargs.items())
@@ -73,3 +72,27 @@ def memoize(meth: Callable[P, R]) -> Callable[P, R]:
         return result
 
     return cast(Callable[P, R], wrapper)
+
+
+def _memoize_async(
+    meth: Callable[P, Coroutine[Any, Any, R]],
+) -> Callable[P, Coroutine[Any, Any, R]]:
+    """Memoize an async method."""
+
+    @wraps(meth)
+    async def wrapper(*args: P.args, **kwargs: P.kwargs) -> R:
+        hashable_args = tuple(_make_hashable(arg) for arg in args)
+        hashable_kwargs = tuple(
+            sorted((k, _make_hashable(v)) for k, v in kwargs.items())
+        )
+        cache_key = str((hashable_args, hashable_kwargs))
+
+        cached_result: R | None = cache.read(tool=meth.__name__, input=cache_key)
+        if cached_result is not None:
+            return cached_result
+
+        result = await meth(*args, **kwargs)
+        cache.add(tool=meth.__name__, input=cache_key, output=result)
+        return result
+
+    return wrapper

lib/crewai/src/crewai/project/wrappers.py

@@ -2,8 +2,10 @@
 
 from __future__ import annotations
 
+import asyncio
 from collections.abc import Callable
 from functools import partial
+import inspect
 from pathlib import Path
 from typing import (
     TYPE_CHECKING,
@@ -132,6 +134,22 @@ class CrewClass(Protocol):
     crew: Callable[..., Crew]
 
 
+def _resolve_result(result: Any) -> Any:
+    """Resolve a potentially async result to its value."""
+    if inspect.iscoroutine(result):
+        try:
+            loop = asyncio.get_running_loop()
+        except RuntimeError:
+            loop = None
+        if loop and loop.is_running():
+            import concurrent.futures
+
+            with concurrent.futures.ThreadPoolExecutor() as pool:
+                return pool.submit(asyncio.run, result).result()
+        return asyncio.run(result)
+    return result
+
+
 class DecoratedMethod(Generic[P, R]):
     """Base wrapper for methods with decorator metadata.
 
@@ -162,7 +180,12 @@ class DecoratedMethod(Generic[P, R]):
         """
         if obj is None:
             return self
-        bound = partial(self._meth, obj)
+        inner = partial(self._meth, obj)
+
+        def _bound(*args: Any, **kwargs: Any) -> R:
+            result: R = _resolve_result(inner(*args, **kwargs))  # type: ignore[call-arg]
+            return result
+
         for attr in (
             "is_agent",
             "is_llm",
@@ -174,8 +197,8 @@ class DecoratedMethod(Generic[P, R]):
             "is_crew",
         ):
             if hasattr(self, attr):
-                setattr(bound, attr, getattr(self, attr))
-        return bound
+                setattr(_bound, attr, getattr(self, attr))
+        return _bound
 
     def __call__(self, *args: P.args, **kwargs: P.kwargs) -> R:
         """Call the wrapped method.
@@ -236,6 +259,7 @@ class BoundTaskMethod(Generic[TaskResultT]):
             The task result with name ensured.
         """
         result = self._task_method.unwrap()(self._obj, *args, **kwargs)
+        result = _resolve_result(result)
         return self._task_method.ensure_task_name(result)
 
 
@@ -292,7 +316,9 @@ class TaskMethod(Generic[P, TaskResultT]):
         Returns:
             The task instance with name set if not already provided.
         """
-        return self.ensure_task_name(self._meth(*args, **kwargs))
+        result = self._meth(*args, **kwargs)
+        result = _resolve_result(result)
+        return self.ensure_task_name(result)
 
     def unwrap(self) -> Callable[P, TaskResultT]:
         """Get the original unwrapped method.

lib/crewai/src/crewai/task.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from collections.abc import Callable
 from concurrent.futures import Future
 from copy import copy as shallow_copy
 import datetime
@@ -10,6 +11,7 @@ import logging
 from pathlib import Path
 import threading
 from typing import (
+    TYPE_CHECKING,
     Any,
     ClassVar,
     cast,
@@ -17,11 +19,11 @@ from typing import (
     get_origin,
 )
 import uuid
-import warnings
 
 from pydantic import (
     UUID4,
     BaseModel,
+    ConfigDict,
     Field,
     PrivateAttr,
     field_validator,
@@ -37,6 +39,7 @@ from crewai.events.types.task_events import (
     TaskFailedEvent,
     TaskStartedEvent,
 )
+from crewai.llms.base_llm import BaseLLM
 from crewai.security import Fingerprint, SecurityConfig
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
@@ -57,6 +60,9 @@ from crewai.utilities.printer import Printer
 from crewai.utilities.string_utils import interpolate_only
 
 
+if TYPE_CHECKING:
+    from crewai.agent.core import Agent
+
 _printer = Printer()
 
 
@@ -101,17 +107,17 @@ class Task(BaseModel):
         description="Configuration for the agent",
         default=None,
     )
-    callback: Any | None = Field(
+    callback: Callable[[TaskOutput], None] | None = Field(
         description="Callback to be executed after the task is completed.", default=None
     )
-    agent: BaseAgent | None = Field(
+    agent: Agent | None = Field(
         description="Agent responsible for execution the task.", default=None
     )
     context: list[Task] | None | _NotSpecified = Field(
         description="Other tasks that will have their output used as context for this task.",
         default=NOT_SPECIFIED,
     )
-    async_execution: bool | None = Field(
+    async_execution: bool = Field(
         description="Whether the task should be executed asynchronously or not.",
         default=False,
     )
@@ -151,11 +157,11 @@ class Task(BaseModel):
         frozen=True,
         description="Unique identifier for the object, not set by user.",
     )
-    human_input: bool | None = Field(
+    human_input: bool = Field(
         description="Whether the task should have a human review the final answer of the agent",
         default=False,
     )
-    markdown: bool | None = Field(
+    markdown: bool = Field(
         description="Whether the task should instruct the agent to return the final answer formatted in Markdown",
         default=False,
     )
@@ -172,11 +178,6 @@ class Task(BaseModel):
         default=None,
         description="List of guardrails to validate task output before proceeding to next task. Also supports a single guardrail function or string description of a guardrail to validate task output before proceeding to next task",
     )
-
-    max_retries: int | None = Field(
-        default=None,
-        description="[DEPRECATED] Maximum number of retries when guardrail fails. Use guardrail_max_retries instead. Will be removed in v1.0.0",
-    )
     guardrail_max_retries: int = Field(
         default=3, description="Maximum number of retries when guardrail fails"
     )
@@ -187,8 +188,8 @@ class Task(BaseModel):
     end_time: datetime.datetime | None = Field(
         default=None, description="End time of the task execution"
     )
-    allow_crewai_trigger_context: bool | None = Field(
-        default=None,
+    allow_crewai_trigger_context: bool = Field(
+        default=False,
         description="Whether this task should append 'Trigger Payload: {crewai_trigger_payload}' to the task description when crewai_trigger_payload exists in crew inputs.",
     )
     _guardrail: GuardrailCallable | None = PrivateAttr(default=None)
@@ -202,7 +203,9 @@ class Task(BaseModel):
     _original_expected_output: str | None = PrivateAttr(default=None)
     _original_output_file: str | None = PrivateAttr(default=None)
     _thread: threading.Thread | None = PrivateAttr(default=None)
-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
 
     @field_validator("guardrail")
     @classmethod
@@ -288,15 +291,16 @@ class Task(BaseModel):
             if self.agent is None:
                 raise ValueError("Agent is required to use LLMGuardrail")
 
-            self._guardrail = cast(
-                GuardrailCallable,
-                LLMGuardrail(description=self.guardrail, llm=self.agent.llm),
+            self._guardrail = LLMGuardrail(
+                description=self.guardrail, llm=cast(BaseLLM, self.agent.llm)
             )
 
         return self
 
     @model_validator(mode="after")
     def ensure_guardrails_is_list_of_callables(self) -> Task:
+        from crewai.tasks.llm_guardrail import LLMGuardrail
+
         guardrails = []
         if self.guardrails is not None:
             if isinstance(self.guardrails, (list, tuple)):
@@ -309,14 +313,11 @@ class Task(BaseModel):
                                 raise ValueError(
                                     "Agent is required to use non-programmatic guardrails"
                                 )
-                            from crewai.tasks.llm_guardrail import LLMGuardrail
 
                             guardrails.append(
-                                cast(
-                                    GuardrailCallable,
-                                    LLMGuardrail(
-                                        description=guardrail, llm=self.agent.llm
-                                    ),
+                                LLMGuardrail(
+                                    description=guardrail,
+                                    llm=cast(BaseLLM, self.agent.llm),
                                 )
                             )
                         else:
@@ -329,14 +330,11 @@ class Task(BaseModel):
                         raise ValueError(
                             "Agent is required to use non-programmatic guardrails"
                         )
-                    from crewai.tasks.llm_guardrail import LLMGuardrail
 
                     guardrails.append(
-                        cast(
-                            GuardrailCallable,
-                            LLMGuardrail(
-                                description=self.guardrails, llm=self.agent.llm
-                            ),
+                        LLMGuardrail(
+                            description=self.guardrails,
+                            llm=cast(BaseLLM, self.agent.llm),
                         )
                     )
                 else:
@@ -436,21 +434,9 @@ class Task(BaseModel):
             )
         return self
 
-    @model_validator(mode="after")
-    def handle_max_retries_deprecation(self) -> Self:
-        if self.max_retries is not None:
-            warnings.warn(
-                "The 'max_retries' parameter is deprecated and will be removed in CrewAI v1.0.0. "
-                "Please use 'guardrail_max_retries' instead.",
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            self.guardrail_max_retries = self.max_retries
-        return self
-
     def execute_sync(
         self,
-        agent: BaseAgent | None = None,
+        agent: Agent | None = None,
         context: str | None = None,
         tools: list[BaseTool] | None = None,
     ) -> TaskOutput:
@@ -488,9 +474,9 @@ class Task(BaseModel):
 
     def _execute_task_async(
         self,
-        agent: BaseAgent | None,
+        agent: Agent | None,
         context: str | None,
-        tools: list[Any] | None,
+        tools: list[BaseTool] | None,
         future: Future[TaskOutput],
     ) -> None:
         """Execute the task asynchronously with context handling."""
@@ -499,9 +485,9 @@ class Task(BaseModel):
 
     def _execute_core(
         self,
-        agent: BaseAgent | None,
+        agent: Agent | None,
         context: str | None,
-        tools: list[Any] | None,
+        tools: list[BaseTool] | None,
     ) -> TaskOutput:
         """Run the core execution logic of the task."""
         try:
@@ -611,8 +597,6 @@ class Task(BaseModel):
                 if trigger_payload is not None:
                     description += f"\n\nTrigger Payload: {trigger_payload}"
 
-        tasks_slices = [description]
-
         output = self.i18n.slice("expected_output").format(
             expected_output=self.expected_output
         )
@@ -715,7 +699,7 @@ Follow these guidelines:
             self.processed_by_agents.add(agent_name)
         self.delegations += 1
 
-    def copy(  # type: ignore
+    def copy(  # type: ignore[override]
         self, agents: list[BaseAgent], task_mapping: dict[str, Task]
     ) -> Task:
         """Creates a deep copy of the Task while preserving its original class type.
@@ -859,7 +843,7 @@ Follow these guidelines:
     def _invoke_guardrail_function(
         self,
         task_output: TaskOutput,
-        agent: BaseAgent,
+        agent: Agent,
         tools: list[BaseTool],
         guardrail: GuardrailCallable | None,
         guardrail_index: int | None = None,

lib/crewai/src/crewai/tasks/llm_guardrail.py

@@ -2,7 +2,7 @@ from typing import Any
 
 from pydantic import BaseModel, Field
 
-from crewai.agent import Agent
+from crewai.agent.core import Agent
 from crewai.lite_agent_output import LiteAgentOutput
 from crewai.llms.base_llm import BaseLLM
 from crewai.tasks.task_output import TaskOutput
@@ -38,7 +38,9 @@ class LLMGuardrail:
 
         self.llm: BaseLLM = llm
 
-    def _validate_output(self, task_output: TaskOutput) -> LiteAgentOutput:
+    def _validate_output(
+        self, task_output: TaskOutput | LiteAgentOutput
+    ) -> LiteAgentOutput:
         agent = Agent(
             role="Guardrail Agent",
             goal="Validate the output of the task",
@@ -64,18 +66,17 @@ class LLMGuardrail:
 
         return agent.kickoff(query, response_format=LLMGuardrailResult)
 
-    def __call__(self, task_output: TaskOutput) -> tuple[bool, Any]:
+    def __call__(self, task_output: TaskOutput | LiteAgentOutput) -> tuple[bool, Any]:
         """Validates the output of a task based on specified criteria.
 
         Args:
-            task_output (TaskOutput): The output to be validated.
+            task_output: The output to be validated.
 
         Returns:
-            Tuple[bool, Any]: A tuple containing:
+            A tuple containing:
                 - bool: True if validation passed, False otherwise
                 - Any: The validation result or error message
         """
-
         try:
             result = self._validate_output(task_output)
             if not isinstance(result.pydantic, LLMGuardrailResult):

lib/crewai/src/crewai/telemetry/telemetry.py

@@ -9,12 +9,14 @@ data is collected. Users can opt-in to share more complete data using the
 from __future__ import annotations
 
 import asyncio
+import atexit
 from collections.abc import Callable
 from importlib.metadata import version
 import json
 import logging
 import os
 import platform
+import signal
 import threading
 from typing import TYPE_CHECKING, Any
 
@@ -31,6 +33,14 @@ from opentelemetry.sdk.trace.export import (
 from opentelemetry.trace import Span
 from typing_extensions import Self
 
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.system_events import (
+    SigContEvent,
+    SigHupEvent,
+    SigIntEvent,
+    SigTStpEvent,
+    SigTermEvent,
+)
 from crewai.telemetry.constants import (
     CREWAI_TELEMETRY_BASE_URL,
     CREWAI_TELEMETRY_SERVICE_NAME,
@@ -121,6 +131,7 @@ class Telemetry:
             )
 
             self.provider.add_span_processor(processor)
+            self._register_shutdown_handlers()
             self.ready = True
         except Exception as e:
             if isinstance(
@@ -155,6 +166,71 @@ class Telemetry:
                 self.ready = False
                 self.trace_set = False
 
+    def _register_shutdown_handlers(self) -> None:
+        """Register handlers for graceful shutdown on process exit and signals."""
+        atexit.register(self._shutdown)
+
+        self._original_handlers: dict[int, Any] = {}
+
+        self._register_signal_handler(signal.SIGTERM, SigTermEvent, shutdown=True)
+        self._register_signal_handler(signal.SIGINT, SigIntEvent, shutdown=True)
+        self._register_signal_handler(signal.SIGHUP, SigHupEvent, shutdown=False)
+        self._register_signal_handler(signal.SIGTSTP, SigTStpEvent, shutdown=False)
+        self._register_signal_handler(signal.SIGCONT, SigContEvent, shutdown=False)
+
+    def _register_signal_handler(
+        self,
+        sig: signal.Signals,
+        event_class: type,
+        shutdown: bool = False,
+    ) -> None:
+        """Register a signal handler that emits an event.
+
+        Args:
+            sig: The signal to handle.
+            event_class: The event class to instantiate and emit.
+            shutdown: Whether to trigger shutdown on this signal.
+        """
+        try:
+            original_handler = signal.getsignal(sig)
+            self._original_handlers[sig] = original_handler
+
+            def handler(signum: int, frame: Any) -> None:
+                crewai_event_bus.emit(self, event_class())
+
+                if shutdown:
+                    self._shutdown()
+
+                if original_handler not in (signal.SIG_DFL, signal.SIG_IGN, None):
+                    if callable(original_handler):
+                        original_handler(signum, frame)
+                elif shutdown:
+                    raise SystemExit(0)
+
+            signal.signal(sig, handler)
+        except ValueError as e:
+            logger.warning(
+                f"Cannot register {sig.name} handler: not running in main thread",
+                exc_info=e,
+            )
+        except OSError as e:
+            logger.warning(f"Cannot register {sig.name} handler: {e}", exc_info=e)
+
+    def _shutdown(self) -> None:
+        """Flush and shutdown the telemetry provider on process exit.
+
+        Uses a short timeout to avoid blocking process shutdown.
+        """
+        if not self.ready:
+            return
+
+        try:
+            self.provider.force_flush(timeout_millis=5000)
+            self.provider.shutdown()
+            self.ready = False
+        except Exception as e:
+            logger.debug(f"Telemetry shutdown failed: {e}")
+
     def _safe_telemetry_operation(
         self, operation: Callable[[], Span | None]
     ) -> Span | None:

lib/crewai/tests/agents/test_agent.py

@@ -147,7 +147,7 @@ def test_custom_llm():
     assert agent.llm.model == "gpt-4"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execution():
     agent = Agent(
         role="test role",
@@ -166,7 +166,7 @@ def test_agent_execution():
     assert output == "1 + 1 is 2"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execution_with_tools():
     @tool
     def multiplier(first_number: int, second_number: int) -> float:
@@ -211,7 +211,7 @@ def test_agent_execution_with_tools():
     assert received_events[0].tool_args == {"first_number": 3, "second_number": 4}
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_logging_tool_usage():
     @tool
     def multiplier(first_number: int, second_number: int) -> float:
@@ -245,7 +245,7 @@ def test_logging_tool_usage():
     assert agent.tools_handler.last_used_tool.arguments == tool_usage.arguments
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_cache_hitting():
     @tool
     def multiplier(first_number: int, second_number: int) -> float:
@@ -325,7 +325,7 @@ def test_cache_hitting():
     assert received_events[0].output == "12"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_disabling_cache_for_agent():
     @tool
     def multiplier(first_number: int, second_number: int) -> float:
@@ -389,7 +389,7 @@ def test_disabling_cache_for_agent():
         read.assert_not_called()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execution_with_specific_tools():
     @tool
     def multiplier(first_number: int, second_number: int) -> float:
@@ -412,7 +412,7 @@ def test_agent_execution_with_specific_tools():
     assert output == "The result of the multiplication is 12."
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_powered_by_new_o_model_family_that_allows_skipping_tool():
     @tool
     def multiplier(first_number: int, second_number: int) -> float:
@@ -438,7 +438,7 @@ def test_agent_powered_by_new_o_model_family_that_allows_skipping_tool():
     assert output == "12"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_powered_by_new_o_model_family_that_uses_tool():
     @tool
     def comapny_customer_data() -> str:
@@ -464,7 +464,7 @@ def test_agent_powered_by_new_o_model_family_that_uses_tool():
     assert output == "42"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_custom_max_iterations():
     @tool
     def get_final_answer() -> float:
@@ -509,7 +509,7 @@ def test_agent_custom_max_iterations():
     assert call_count == 2
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 @pytest.mark.timeout(30)
 def test_agent_max_iterations_stops_loop():
     """Test that agent execution terminates when max_iter is reached."""
@@ -546,7 +546,7 @@ def test_agent_max_iterations_stops_loop():
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_repeated_tool_usage(capsys):
     """Test that agents handle repeated tool usage appropriately.
 
@@ -595,7 +595,7 @@ def test_agent_repeated_tool_usage(capsys):
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_repeated_tool_usage_check_even_with_disabled_cache(capsys):
     @tool
     def get_final_answer(anything: str) -> float:
@@ -638,7 +638,7 @@ def test_agent_repeated_tool_usage_check_even_with_disabled_cache(capsys):
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_moved_on_after_max_iterations():
     @tool
     def get_final_answer() -> float:
@@ -665,7 +665,7 @@ def test_agent_moved_on_after_max_iterations():
     assert output == "42"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_respect_the_max_rpm_set(capsys):
     @tool
     def get_final_answer() -> float:
@@ -699,7 +699,7 @@ def test_agent_respect_the_max_rpm_set(capsys):
         moveon.assert_called()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_respect_the_max_rpm_set_over_crew_rpm(capsys):
     from unittest.mock import patch
 
@@ -737,7 +737,7 @@ def test_agent_respect_the_max_rpm_set_over_crew_rpm(capsys):
         moveon.assert_not_called()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_without_max_rpm_respects_crew_rpm(capsys):
     from unittest.mock import patch
 
@@ -797,7 +797,7 @@ def test_agent_without_max_rpm_respects_crew_rpm(capsys):
         moveon.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_error_on_parsing_tool(capsys):
     from unittest.mock import patch
 
@@ -840,7 +840,7 @@ def test_agent_error_on_parsing_tool(capsys):
     assert "Error on parsing tool." in captured.out
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_remembers_output_format_after_using_tools_too_many_times():
     from unittest.mock import patch
 
@@ -875,7 +875,7 @@ def test_agent_remembers_output_format_after_using_tools_too_many_times():
         remember_format.assert_called()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_use_specific_tasks_output_as_context(capsys):
     agent1 = Agent(role="test role", goal="test goal", backstory="test backstory")
     agent2 = Agent(role="test role2", goal="test goal2", backstory="test backstory2")
@@ -902,7 +902,7 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
     assert "hi" in result.raw.lower() or "hello" in result.raw.lower()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_step_callback():
     class StepCallback:
         def callback(self, step):
@@ -936,7 +936,7 @@ def test_agent_step_callback():
         callback.assert_called()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_function_calling_llm():
     from crewai.llm import LLM
     llm = LLM(model="gpt-4o", is_litellm=True)
@@ -983,7 +983,7 @@ def test_agent_function_calling_llm():
         mock_original_tool_calling.assert_called()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
     from crewai.tools import BaseTool
 
@@ -1013,7 +1013,7 @@ def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
     assert result.raw == "Howdy!"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_tool_usage_information_is_appended_to_agent():
     from crewai.tools import BaseTool
 
@@ -1068,7 +1068,7 @@ def test_agent_definition_based_on_dict():
 
 
 # test for human input
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_human_input():
     # Agent configuration
     config = {
@@ -1216,7 +1216,7 @@ Thought:<|eot_id|>
         assert mock_format_prompt.return_value == expected_prompt
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_task_allow_crewai_trigger_context():
     from crewai import Crew
 
@@ -1237,7 +1237,7 @@ def test_task_allow_crewai_trigger_context():
     assert "Trigger Payload: Important context data" in prompt
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_task_without_allow_crewai_trigger_context():
     from crewai import Crew
 
@@ -1260,7 +1260,7 @@ def test_task_without_allow_crewai_trigger_context():
     assert "Important context data" not in prompt
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_task_allow_crewai_trigger_context_no_payload():
     from crewai import Crew
 
@@ -1282,7 +1282,7 @@ def test_task_allow_crewai_trigger_context_no_payload():
     assert "Trigger Payload:" not in prompt
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_do_not_allow_crewai_trigger_context_for_first_task_hierarchical():
     from crewai import Crew
 
@@ -1311,7 +1311,7 @@ def test_do_not_allow_crewai_trigger_context_for_first_task_hierarchical():
     assert "Trigger Payload: Initial context data" not in first_prompt
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_first_task_auto_inject_trigger():
     from crewai import Crew
 
@@ -1344,7 +1344,7 @@ def test_first_task_auto_inject_trigger():
     assert "Trigger Payload:" not in second_prompt
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_ensure_first_task_allow_crewai_trigger_context_is_false_does_not_inject():
     from crewai import Crew
 
@@ -1549,7 +1549,7 @@ def test_agent_with_additional_kwargs():
     assert agent.llm.frequency_penalty == 0.1
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_llm_call():
     llm = LLM(model="gpt-3.5-turbo")
     messages = [{"role": "user", "content": "Say 'Hello, World!'"}]
@@ -1558,7 +1558,7 @@ def test_llm_call():
     assert "Hello, World!" in response
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_llm_call_with_error():
     llm = LLM(model="non-existent-model")
     messages = [{"role": "user", "content": "This should fail"}]
@@ -1567,7 +1567,7 @@ def test_llm_call_with_error():
         llm.call(messages)
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_handle_context_length_exceeds_limit():
     # Import necessary modules
     from crewai.utilities.agent_utils import handle_context_length
@@ -1620,7 +1620,7 @@ def test_handle_context_length_exceeds_limit():
         mock_summarize.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_handle_context_length_exceeds_limit_cli_no():
     agent = Agent(
         role="test role",
@@ -1695,7 +1695,7 @@ def test_agent_with_all_llm_attributes():
     assert agent.llm.api_key == "sk-your-api-key-here"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_llm_call_with_all_attributes():
     llm = LLM(
         model="gpt-3.5-turbo",
@@ -1712,7 +1712,7 @@ def test_llm_call_with_all_attributes():
     assert "STOP" not in response
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_ollama_llama3():
     agent = Agent(
         role="test role",
@@ -1733,7 +1733,7 @@ def test_agent_with_ollama_llama3():
     assert "Llama3" in response or "AI" in response or "language model" in response
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_llm_call_with_ollama_llama3():
     llm = LLM(
         model="ollama/llama3.2:3b",
@@ -1752,7 +1752,7 @@ def test_llm_call_with_ollama_llama3():
     assert "Llama3" in response or "AI" in response or "language model" in response
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execute_task_basic():
     agent = Agent(
         role="test role",
@@ -1771,7 +1771,7 @@ def test_agent_execute_task_basic():
     assert "4" in result
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execute_task_with_context():
     agent = Agent(
         role="test role",
@@ -1793,7 +1793,7 @@ def test_agent_execute_task_with_context():
     assert "fox" in result.lower() and "dog" in result.lower()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execute_task_with_tool():
     @tool
     def dummy_tool(query: str) -> str:
@@ -1818,7 +1818,7 @@ def test_agent_execute_task_with_tool():
     assert "Dummy result for: test query" in result
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execute_task_with_custom_llm():
     agent = Agent(
         role="test role",
@@ -1839,7 +1839,7 @@ def test_agent_execute_task_with_custom_llm():
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_execute_task_with_ollama():
     agent = Agent(
         role="test role",
@@ -1859,7 +1859,7 @@ def test_agent_execute_task_with_ollama():
     assert "AI" in result or "artificial intelligence" in result.lower()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_sources():
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
@@ -1891,7 +1891,7 @@ def test_agent_with_knowledge_sources():
             assert "red" in result.raw.lower()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold():
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
@@ -1939,7 +1939,7 @@ def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold():
             )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_default():
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
@@ -1988,7 +1988,7 @@ def test_agent_with_knowledge_sources_with_query_limit_and_score_threshold_defau
             )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_sources_extensive_role():
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
@@ -2024,7 +2024,7 @@ def test_agent_with_knowledge_sources_extensive_role():
         assert "red" in result.raw.lower()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_sources_works_with_copy():
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
@@ -2063,7 +2063,7 @@ def test_agent_with_knowledge_sources_works_with_copy():
             assert isinstance(agent_copy.llm, BaseLLM)
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_sources_generate_search_query():
     content = "Brandon's favorite color is red and he likes Mexican food."
     string_source = StringKnowledgeSource(content=content)
@@ -2116,7 +2116,7 @@ def test_agent_with_knowledge_sources_generate_search_query():
         assert "red" in result.raw.lower()
 
 
-@pytest.mark.vcr(record_mode="none", filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_knowledge_with_no_crewai_knowledge():
     mock_knowledge = MagicMock(spec=Knowledge)
 
@@ -2143,7 +2143,7 @@ def test_agent_with_knowledge_with_no_crewai_knowledge():
     mock_knowledge.query.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_with_only_crewai_knowledge():
     mock_knowledge = MagicMock(spec=Knowledge)
 
@@ -2168,7 +2168,7 @@ def test_agent_with_only_crewai_knowledge():
     mock_knowledge.query.assert_called_once()
 
 
-@pytest.mark.vcr(record_mode="none", filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_knowledege_with_crewai_knowledge():
     crew_knowledge = MagicMock(spec=Knowledge)
     agent_knowledge = MagicMock(spec=Knowledge)
@@ -2197,7 +2197,7 @@ def test_agent_knowledege_with_crewai_knowledge():
     crew_knowledge.query.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_litellm_auth_error_handling():
     """Test that LiteLLM authentication errors are handled correctly and not retried."""
     from litellm import AuthenticationError as LiteLLMAuthenticationError
@@ -2326,7 +2326,7 @@ def test_litellm_anthropic_error_handling():
     mock_llm_call.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_get_knowledge_search_query():
     """Test that _get_knowledge_search_query calls the LLM with the correct prompts."""
     from crewai.utilities.i18n import I18N

lib/crewai/tests/agents/test_lite_agent.py

@@ -70,7 +70,7 @@ class ResearchResult(BaseModel):
     sources: list[str] = Field(description="List of sources used")
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 @pytest.mark.parametrize("verbose", [True, False])
 def test_lite_agent_created_with_correct_parameters(monkeypatch, verbose):
     """Test that LiteAgent is created with the correct parameters when Agent.kickoff() is called."""
@@ -130,7 +130,7 @@ def test_lite_agent_created_with_correct_parameters(monkeypatch, verbose):
     assert created_lite_agent["response_format"] == TestResponse
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_lite_agent_with_tools():
     """Test that Agent can use tools."""
     # Create a LiteAgent with tools
@@ -174,7 +174,7 @@ def test_lite_agent_with_tools():
     assert event.tool_name == "search_web"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_lite_agent_structured_output():
     """Test that Agent can return a simple structured output."""
 
@@ -217,7 +217,7 @@ def test_lite_agent_structured_output():
     return result
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_lite_agent_returns_usage_metrics():
     """Test that LiteAgent returns usage metrics."""
     llm = LLM(model="gpt-4o-mini")
@@ -238,7 +238,7 @@ def test_lite_agent_returns_usage_metrics():
     assert result.usage_metrics["total_tokens"] > 0
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_lite_agent_output_includes_messages():
     """Test that LiteAgentOutput includes messages from agent execution."""
     llm = LLM(model="gpt-4o-mini")
@@ -259,7 +259,7 @@ def test_lite_agent_output_includes_messages():
     assert len(result.messages) > 0
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 @pytest.mark.asyncio
 async def test_lite_agent_returns_usage_metrics_async():
     """Test that LiteAgent returns usage metrics when run asynchronously."""
@@ -354,9 +354,9 @@ def test_sets_parent_flow_when_inside_flow():
     assert captured_agent.parent_flow is flow
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_guardrail_is_called_using_string():
-    guardrail_events = defaultdict(list)
+    guardrail_events: dict[str, list] = defaultdict(list)
     from crewai.events.event_types import (
         LLMGuardrailCompletedEvent,
         LLMGuardrailStartedEvent,
@@ -369,35 +369,33 @@ def test_guardrail_is_called_using_string():
         guardrail="""Only include Brazilian players, both women and men""",
     )
 
-    all_events_received = threading.Event()
+    condition = threading.Condition()
 
     @crewai_event_bus.on(LLMGuardrailStartedEvent)
     def capture_guardrail_started(source, event):
         assert isinstance(source, LiteAgent)
         assert source.original_agent == agent
-        guardrail_events["started"].append(event)
-        if (
-            len(guardrail_events["started"]) == 2
-            and len(guardrail_events["completed"]) == 2
-        ):
-            all_events_received.set()
+        with condition:
+            guardrail_events["started"].append(event)
+            condition.notify()
 
     @crewai_event_bus.on(LLMGuardrailCompletedEvent)
     def capture_guardrail_completed(source, event):
         assert isinstance(source, LiteAgent)
         assert source.original_agent == agent
-        guardrail_events["completed"].append(event)
-        if (
-            len(guardrail_events["started"]) == 2
-            and len(guardrail_events["completed"]) == 2
-        ):
-            all_events_received.set()
+        with condition:
+            guardrail_events["completed"].append(event)
+            condition.notify()
 
     result = agent.kickoff(messages="Top 10 best players in the world?")
 
-    assert all_events_received.wait(timeout=10), (
-        "Timeout waiting for all guardrail events"
-    )
+    with condition:
+        success = condition.wait_for(
+            lambda: len(guardrail_events["started"]) >= 2
+            and len(guardrail_events["completed"]) >= 2,
+            timeout=10,
+        )
+    assert success, "Timeout waiting for all guardrail events"
     assert len(guardrail_events["started"]) == 2
     assert len(guardrail_events["completed"]) == 2
     assert not guardrail_events["completed"][0].success
@@ -408,33 +406,27 @@ def test_guardrail_is_called_using_string():
     )
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_guardrail_is_called_using_callable():
-    guardrail_events = defaultdict(list)
+    guardrail_events: dict[str, list] = defaultdict(list)
     from crewai.events.event_types import (
         LLMGuardrailCompletedEvent,
         LLMGuardrailStartedEvent,
     )
 
-    all_events_received = threading.Event()
+    condition = threading.Condition()
 
     @crewai_event_bus.on(LLMGuardrailStartedEvent)
     def capture_guardrail_started(source, event):
-        guardrail_events["started"].append(event)
-        if (
-            len(guardrail_events["started"]) == 1
-            and len(guardrail_events["completed"]) == 1
-        ):
-            all_events_received.set()
+        with condition:
+            guardrail_events["started"].append(event)
+            condition.notify()
 
     @crewai_event_bus.on(LLMGuardrailCompletedEvent)
     def capture_guardrail_completed(source, event):
-        guardrail_events["completed"].append(event)
-        if (
-            len(guardrail_events["started"]) == 1
-            and len(guardrail_events["completed"]) == 1
-        ):
-            all_events_received.set()
+        with condition:
+            guardrail_events["completed"].append(event)
+            condition.notify()
 
     agent = Agent(
         role="Sports Analyst",
@@ -445,42 +437,40 @@ def test_guardrail_is_called_using_callable():
 
     result = agent.kickoff(messages="Top 1 best players in the world?")
 
-    assert all_events_received.wait(timeout=10), (
-        "Timeout waiting for all guardrail events"
-    )
+    with condition:
+        success = condition.wait_for(
+            lambda: len(guardrail_events["started"]) >= 1
+            and len(guardrail_events["completed"]) >= 1,
+            timeout=10,
+        )
+    assert success, "Timeout waiting for all guardrail events"
     assert len(guardrail_events["started"]) == 1
     assert len(guardrail_events["completed"]) == 1
     assert guardrail_events["completed"][0].success
     assert "Pelé - Santos, 1958" in result.raw
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_guardrail_reached_attempt_limit():
-    guardrail_events = defaultdict(list)
+    guardrail_events: dict[str, list] = defaultdict(list)
     from crewai.events.event_types import (
         LLMGuardrailCompletedEvent,
         LLMGuardrailStartedEvent,
     )
 
-    all_events_received = threading.Event()
+    condition = threading.Condition()
 
     @crewai_event_bus.on(LLMGuardrailStartedEvent)
     def capture_guardrail_started(source, event):
-        guardrail_events["started"].append(event)
-        if (
-            len(guardrail_events["started"]) == 3
-            and len(guardrail_events["completed"]) == 3
-        ):
-            all_events_received.set()
+        with condition:
+            guardrail_events["started"].append(event)
+            condition.notify()
 
     @crewai_event_bus.on(LLMGuardrailCompletedEvent)
     def capture_guardrail_completed(source, event):
-        guardrail_events["completed"].append(event)
-        if (
-            len(guardrail_events["started"]) == 3
-            and len(guardrail_events["completed"]) == 3
-        ):
-            all_events_received.set()
+        with condition:
+            guardrail_events["completed"].append(event)
+            condition.notify()
 
     agent = Agent(
         role="Sports Analyst",
@@ -498,9 +488,13 @@ def test_guardrail_reached_attempt_limit():
     ):
         agent.kickoff(messages="Top 10 best players in the world?")
 
-    assert all_events_received.wait(timeout=10), (
-        "Timeout waiting for all guardrail events"
-    )
+    with condition:
+        success = condition.wait_for(
+            lambda: len(guardrail_events["started"]) >= 3
+            and len(guardrail_events["completed"]) >= 3,
+            timeout=10,
+        )
+    assert success, "Timeout waiting for all guardrail events"
     assert len(guardrail_events["started"]) == 3  # 2 retries + 1 initial call
     assert len(guardrail_events["completed"]) == 3  # 2 retries + 1 initial call
     assert not guardrail_events["completed"][0].success
@@ -508,7 +502,7 @@ def test_guardrail_reached_attempt_limit():
     assert not guardrail_events["completed"][2].success
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_output_when_guardrail_returns_base_model():
     class Player(BaseModel):
         name: str
@@ -599,7 +593,7 @@ def test_lite_agent_with_custom_llm_and_guardrails():
     assert result2.raw == "Modified by guardrail"
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_lite_agent_with_invalid_llm():
     """Test that LiteAgent raises proper error when create_llm returns None."""
     with patch("crewai.lite_agent.create_llm", return_value=None):
@@ -615,7 +609,7 @@ def test_lite_agent_with_invalid_llm():
 
 @patch.dict("os.environ", {"CREWAI_PLATFORM_INTEGRATION_TOKEN": "test_token"})
 @patch("crewai_tools.tools.crewai_platform_tools.crewai_platform_tool_builder.requests.get")
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_kickoff_with_platform_tools(mock_get):
     """Test that Agent.kickoff() properly integrates platform tools with LiteAgent"""
     mock_response = Mock()
@@ -657,7 +651,7 @@ def test_agent_kickoff_with_platform_tools(mock_get):
 
 @patch.dict("os.environ", {"EXA_API_KEY": "test_exa_key"})
 @patch("crewai.agent.Agent._get_external_mcp_tools")
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr()
 def test_agent_kickoff_with_mcp_tools(mock_get_mcp_tools):
     """Test that Agent.kickoff() properly integrates MCP tools with LiteAgent"""
     # Setup mock MCP tools - create a proper BaseTool instance

lib/crewai/tests/cassettes/TestTraceListenerSetup.test_trace_listener_ephemeral_batch.yaml

@@ -1,126 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are Test Agent. Test backstory\nYour
-      personal goal is: Test goal\nTo give my best complete final answer to the task
-      respond using the exact following format:\n\nThought: I now can give a great
-      answer\nFinal Answer: Your final answer must be the great and the most complete
-      as possible, it must be outcome described.\n\nI MUST use these formats, my job
-      depends on it!"}, {"role": "user", "content": "\nCurrent Task: Say hello to
-      the world\n\nThis is the expected criteria for your final answer: hello world\nyou
-      MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
-      This is VERY important to you, use the tools available and give your best Final
-      Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop":
-      ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate, zstd
-      connection:
-      - keep-alive
-      content-length:
-      - '825'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.93.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.93.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-read-timeout:
-      - '600.0'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.9
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: !!binary |
-        H4sIAAAAAAAAAwAAAP//jFJdi9swEHz3r1j0HBc7ZydXvx1HC0evhT6UUtrDKNLa1lXWqpJ8aTjy
-        34vsXOz0A/pi8M7OaGZ3nxMApiSrgImOB9Fbnd4Why/v79HeePeD37/Zfdx8evf5+rY4fNjdPbJV
-        ZNDuEUV4Yb0S1FuNQZGZYOGQB4yq+bYsr7J1nhcj0JNEHWmtDWlBaa+MStfZukizbZpfn9gdKYGe
-        VfA1AQB4Hr/Rp5H4k1WQrV4qPXrPW2TVuQmAOdKxwrj3ygduAlvNoCAT0IzW78DQHgQ30KonBA5t
-        tA3c+D06gG/mrTJcw834X0GHWhPsyWm5FHTYDJ7HUGbQegFwYyjwOJQxysMJOZ7Na2qto53/jcoa
-        ZZTvaofck4lGfSDLRvSYADyMQxoucjPrqLehDvQdx+fycjvpsXk3C/TqBAYKXC/q29NoL/VqiYEr
-        7RdjZoKLDuVMnXfCB6loASSL1H+6+Zv2lFyZ9n/kZ0AItAFlbR1KJS4Tz20O4+n+q+085dEw8+ie
-        lMA6KHRxExIbPujpoJg/+IB93SjTorNOTVfV2LrcZLzZYFm+Zskx+QUAAP//AwB1vYZ+YwMAAA==
-    headers:
-      CF-RAY:
-      - 96fc9f29dea3cf1f-SJC
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 15 Aug 2025 23:55:15 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=oA9oTa3cE0ZaEUDRf0hCpnarSAQKzrVUhl6qDS4j09w-1755302115-1.0.1.1-gUUDl4ZqvBQkg7244DTwOmSiDUT2z_AiQu0P1xUaABjaufSpZuIlI5G0H7OSnW.ldypvpxjj45NGWesJ62M_2U7r20tHz_gMmDFw6D5ZiNc;
-        path=/; expires=Sat, 16-Aug-25 00:25:15 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=ICenEGMmOE5jaOjwD30bAOwrF8.XRbSIKTBl1EyWs0o-1755302115700-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Strict-Transport-Security:
-      - max-age=31536000; includeSubDomains; preload
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '735'
-      openai-project:
-      - proj_xitITlrFeen7zjNSzML82h9x
-      openai-version:
-      - '2020-10-01'
-      x-envoy-upstream-service-time:
-      - '753'
-      x-ratelimit-limit-project-tokens:
-      - '150000000'
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-project-tokens:
-      - '149999830'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999827'
-      x-ratelimit-reset-project-tokens:
-      - 0s
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_212fde9d945a462ba0d89ea856131dce
-    status:
-      code: 200
-      message: OK
-version: 1