Merge branch 'main' of github.com:crewAIInc/crewAI into lorenze/agent-query-for-knowledge

This commit introduces a new test, `test_get_knowledge_search_query`, to verify that the `_get_knowledge_search_query` method in the Agent class correctly interacts with the LLM using the appropriate prompts. Additionally, a VCR cassette is added to record the interactions with the OpenAI API for this test, ensuring consistent and reliable test results.

.github/security.md

@@ -1,27 +1,19 @@
-## CrewAI Security Vulnerability Reporting Policy
+CrewAI takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organization.
+If you believe you have found a security vulnerability in any CrewAI product or service, please report it to us as described below.
 
-CrewAI prioritizes the security of our software products, services, and GitHub repositories. To promptly address vulnerabilities, follow these steps for reporting security issues:
+ ## Reporting a Vulnerability
+ Please do not report security vulnerabilities through public GitHub issues.
+ To report a vulnerability, please email us at security@crewai.com.
+ Please include the requested information listed below so that we can triage your report more quickly
 
-### Reporting Process
-Do **not** report vulnerabilities via public GitHub issues.
+ - Type of issue (e.g. SQL injection, cross-site scripting, etc.)
+ - Full paths of source file(s) related to the manifestation of the issue
+ - The location of the affected source code (tag/branch/commit or direct URL)
+ - Any special configuration required to reproduce the issue
+ - Step-by-step instructions to reproduce the issue (please include screenshots if needed)
+ - Proof-of-concept or exploit code (if possible)
+ - Impact of the issue, including how an attacker might exploit the issue
 
-Email all vulnerability reports directly to:  
-**security@crewai.com**
+ Once we have received your report, we will respond to you at the email address you provide. If the issue is confirmed, we will release a patch as soon as possible depending on the complexity of the issue.
 
-### Required Information
-To help us quickly validate and remediate the issue, your report must include:
-
-- **Vulnerability Type:** Clearly state the vulnerability type (e.g., SQL injection, XSS, privilege escalation).
-- **Affected Source Code:** Provide full file paths and direct URLs (branch, tag, or commit).
-- **Reproduction Steps:** Include detailed, step-by-step instructions. Screenshots are recommended.
-- **Special Configuration:** Document any special settings or configurations required to reproduce.
-- **Proof-of-Concept (PoC):** Provide exploit or PoC code (if available).
-- **Impact Assessment:** Clearly explain the severity and potential exploitation scenarios.
-
-### Our Response
-- We will acknowledge receipt of your report promptly via your provided email.
-- Confirmed vulnerabilities will receive priority remediation based on severity.
-- Patches will be released as swiftly as possible following verification.
-
-### Reward Notice
-Currently, we do not offer a bug bounty program. Rewards, if issued, are discretionary.
+ At this time, we are not offering a bug bounty program. Any rewards will be at our discretion.

docs/concepts/llms.mdx

@@ -169,55 +169,19 @@ In this section, you'll find detailed examples that help you select, configure,
     ```
   </Accordion>
 
-  <Accordion title="Google (Gemini API)">
-    Set your API key in your `.env` file. If you need a key, or need to find an
-    existing key, check [AI Studio](https://aistudio.google.com/apikey).
+  <Accordion title="Google">
+    Set the following environment variables in your `.env` file:
 
-    ```toml .env
+    ```toml Code
+    # Option 1: Gemini accessed with an API key.
     # https://ai.google.dev/gemini-api/docs/api-key
     GEMINI_API_KEY=<your-api-key>
+
+    # Option 2: Vertex AI IAM credentials for Gemini, Anthropic, and Model Garden.
+    # https://cloud.google.com/vertex-ai/generative-ai/docs/overview
     ```
 
-    Example usage in your CrewAI project:
-    ```python Code
-    from crewai import LLM
-
-    llm = LLM(
-        model="gemini/gemini-2.0-flash",
-        temperature=0.7,
-    )
-    ```
-
-    ### Gemini models
-
-    Google offers a range of powerful models optimized for different use cases.
-
-    | Model                          | Context Window | Best For                                                          |
-    |--------------------------------|----------------|-------------------------------------------------------------------|
-    | gemini-2.5-flash-preview-04-17 | 1M tokens      | Adaptive thinking, cost efficiency                                |
-    | gemini-2.5-pro-preview-05-06   | 1M tokens      | Enhanced thinking and reasoning, multimodal understanding, advanced coding, and more |
-    | gemini-2.0-flash               | 1M tokens      | Next generation features, speed, thinking, and realtime streaming |
-    | gemini-2.0-flash-lite          | 1M tokens      | Cost efficiency and low latency                                   |
-    | gemini-1.5-flash               | 1M tokens      | Balanced multimodal model, good for most tasks                    |
-    | gemini-1.5-flash-8B            | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
-    | gemini-1.5-pro                 | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
-
-    The full list of models is available in the [Gemini model docs](https://ai.google.dev/gemini-api/docs/models).
-
-    ### Gemma
-
-    The Gemini API also allows you to use your API key to access [Gemma models](https://ai.google.dev/gemma/docs) hosted on Google infrastructure.
-
-    | Model          | Context Window |
-    |----------------|----------------|
-    | gemma-3-1b-it  | 32k tokens     |
-    | gemma-3-4b-it  | 32k tokens     |
-    | gemma-3-12b-it | 32k tokens     |
-    | gemma-3-27b-it | 128k tokens    |
-
-  </Accordion>
-  <Accordion title="Google (Vertex AI)">
-    Get credentials from your Google Cloud Console and save it to a JSON file, then load it with the following code:
+    Get credentials from your Google Cloud Console and save it to a JSON file with the following code:
     ```python Code
     import json
 
@@ -241,18 +205,14 @@ In this section, you'll find detailed examples that help you select, configure,
         vertex_credentials=vertex_credentials_json
     )
     ```
-
     Google offers a range of powerful models optimized for different use cases:
 
-    | Model                          | Context Window | Best For                                                          |
-    |--------------------------------|----------------|-------------------------------------------------------------------|
-    | gemini-2.5-flash-preview-04-17 | 1M tokens      | Adaptive thinking, cost efficiency                                |
-    | gemini-2.5-pro-preview-05-06   | 1M tokens      | Enhanced thinking and reasoning, multimodal understanding, advanced coding, and more |
-    | gemini-2.0-flash               | 1M tokens      | Next generation features, speed, thinking, and realtime streaming |
-    | gemini-2.0-flash-lite          | 1M tokens      | Cost efficiency and low latency                                   |
-    | gemini-1.5-flash               | 1M tokens      | Balanced multimodal model, good for most tasks                    |
-    | gemini-1.5-flash-8B            | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
-    | gemini-1.5-pro                 | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+    | Model                  | Context Window | Best For                                                          |
+    |-----------------------|----------------|------------------------------------------------------------------|
+    | gemini-2.0-flash-exp  | 1M tokens      | Higher quality at faster speed, multimodal model, good for most tasks |
+    | gemini-1.5-flash      | 1M tokens      | Balanced multimodal model, good for most tasks                    |
+    | gemini-1.5-flash-8B   | 1M tokens      | Fastest, most cost-efficient, good for high-frequency tasks       |
+    | gemini-1.5-pro        | 2M tokens      | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
   </Accordion>
 
   <Accordion title="Azure">

docs/how-to/arize-phoenix-observability.mdx

@@ -68,13 +68,7 @@ We'll create a CrewAI application where two agents collaborate to research and w
 ```python
 from crewai import Agent, Crew, Process, Task
 from crewai_tools import SerperDevTool
-from openinference.instrumentation.crewai import CrewAIInstrumentor
-from phoenix.otel import register
 
-# setup monitoring for your crew
-tracer_provider = register(
-    endpoint="http://localhost:6006/v1/traces")
-CrewAIInstrumentor().instrument(skip_dep_check=True, tracer_provider=tracer_provider)
 search_tool = SerperDevTool()
 
 # Define your agents with roles and goals

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.119.0"
+version = "0.118.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools~=0.44.0"]
+tools = ["crewai-tools~=0.42.2"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]

src/crewai/__init__.py

@@ -17,7 +17,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.119.0"
+__version__ = "0.118.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/cli/constants.py

@@ -13,7 +13,7 @@ ENV_VARS = {
     ],
     "gemini": [
         {
-            "prompt": "Enter your GEMINI API key from https://ai.dev/apikey (press Enter to skip)",
+            "prompt": "Enter your GEMINI API key (press Enter to skip)",
             "key_name": "GEMINI_API_KEY",
         }
     ],

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,<3.13"
 dependencies = [
-    "crewai[tools]>=0.119.0,<1.0.0"
+    "crewai[tools]>=0.118.0,<1.0.0"
 ]
 
 [project.scripts]

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,<3.13"
 dependencies = [
-    "crewai[tools]>=0.119.0,<1.0.0",
+    "crewai[tools]>=0.118.0,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.119.0"
+    "crewai[tools]>=0.118.0"
 ]
 
 [tool.crewai]

src/crewai/llm.py

@@ -246,9 +246,6 @@ class AccumulatedToolArgs(BaseModel):
 
 
 class LLM(BaseLLM):
-    ANTHROPIC_PREFIXES = ("anthropic/", "claude-", "claude/")
-    GEMINI_IDENTIFIERS = ("gemini", "gemma-")
-    
     def __init__(
         self,
         model: str,
@@ -322,55 +319,8 @@ class LLM(BaseLLM):
         Returns:
             bool: True if the model is from Anthropic, False otherwise.
         """
-        if not isinstance(model, str):
-            return False
-        return any(prefix in model.lower() for prefix in self.ANTHROPIC_PREFIXES)
-
-    def _is_gemini_model(self, model: str) -> bool:
-        """Determine if the model is from Google Gemini provider.
-
-        Args:
-            model: The model identifier string.
-
-        Returns:
-            bool: True if the model is from Gemini, False otherwise.
-        """
-        if not isinstance(model, str):
-            return False
-        return any(identifier in model.lower() for identifier in self.GEMINI_IDENTIFIERS)
-
-    def _normalize_gemini_model(self, model: str) -> str:
-        """Normalize Gemini model name to the format expected by LiteLLM.
-        
-        Handles formats like "models/gemini-pro" or "gemini-pro" and converts
-        them to "gemini/gemini-pro" format.
-
-        Args:
-            model: The model identifier string.
-
-        Returns:
-            str: Normalized model name.
-            
-        Raises:
-            ValueError: If model is not a string or is empty.
-        """
-        if not isinstance(model, str):
-            raise ValueError(f"Model must be a string, got {type(model)}")
-        
-        if not model.strip():
-            raise ValueError("Model name cannot be empty")
-            
-        if model.startswith("gemini/"):
-            return model
-            
-        if model.startswith("models/"):
-            model_name = model.split("/", 1)[1]
-            return f"gemini/{model_name}"
-            
-        if self._is_gemini_model(model) and "/" not in model:
-            return f"gemini/{model}"
-            
-        return model
+        ANTHROPIC_PREFIXES = ("anthropic/", "claude-", "claude/")
+        return any(prefix in model.lower() for prefix in ANTHROPIC_PREFIXES)
 
     def _prepare_completion_params(
         self,
@@ -393,23 +343,9 @@ class LLM(BaseLLM):
             messages = [{"role": "user", "content": messages}]
         formatted_messages = self._format_messages_for_provider(messages)
 
-        model = self.model
-        if self._is_gemini_model(model):
-            try:
-                model = self._normalize_gemini_model(model)
-                logging.info(f"Normalized Gemini model name from '{self.model}' to '{model}'")
-                
-                # --- 2.1) Map GOOGLE_API_KEY to GEMINI_API_KEY if needed
-                if not os.environ.get("GEMINI_API_KEY") and os.environ.get("GOOGLE_API_KEY"):
-                    os.environ["GEMINI_API_KEY"] = os.environ["GOOGLE_API_KEY"]
-                    logging.info("Mapped GOOGLE_API_KEY to GEMINI_API_KEY for Gemini model")
-            except ValueError as e:
-                logging.error(f"Error normalizing Gemini model: {str(e)}")
-                model = self.model
-
-        # --- 3) Prepare the parameters for the completion call
+        # --- 2) Prepare the parameters for the completion call
         params = {
-            "model": model,
+            "model": self.model,
             "messages": formatted_messages,
             "timeout": self.timeout,
             "temperature": self.temperature,

tests/llm_test.py

@@ -220,37 +220,6 @@ def test_get_custom_llm_provider_gemini():
     assert llm._get_custom_llm_provider() == "gemini"
 
 
-def test_is_gemini_model():
-    """Test the _is_gemini_model method with various model names."""
-    llm = LLM(model="gpt-4")  # Model doesn't matter for this test
-    
-    assert llm._is_gemini_model("gemini-pro") == True
-    assert llm._is_gemini_model("gemini/gemini-1.5-pro") == True
-    assert llm._is_gemini_model("models/gemini-pro") == True
-    assert llm._is_gemini_model("gemma-7b") == True
-    
-    # Should not identify as Gemini models
-    assert llm._is_gemini_model("gpt-4") == False
-    assert llm._is_gemini_model("claude-3") == False
-    assert llm._is_gemini_model("mistral-7b") == False
-
-
-def test_normalize_gemini_model():
-    """Test the _normalize_gemini_model method with various model formats."""
-    llm = LLM(model="gpt-4")  # Model doesn't matter for this test
-    
-    assert llm._normalize_gemini_model("gemini/gemini-1.5-pro") == "gemini/gemini-1.5-pro"
-    
-    assert llm._normalize_gemini_model("models/gemini-pro") == "gemini/gemini-pro"
-    assert llm._normalize_gemini_model("models/gemini-1.5-flash") == "gemini/gemini-1.5-flash"
-    
-    assert llm._normalize_gemini_model("gemini-pro") == "gemini/gemini-pro"
-    assert llm._normalize_gemini_model("gemini-1.5-flash") == "gemini/gemini-1.5-flash"
-    
-    assert llm._normalize_gemini_model("gpt-4") == "gpt-4"
-    assert llm._normalize_gemini_model("claude-3") == "claude-3"
-
-
 def test_get_custom_llm_provider_openai():
     llm = LLM(model="gpt-4")
     assert llm._get_custom_llm_provider() == None
@@ -305,82 +274,6 @@ def test_gemini_models(model):
     assert "Paris" in result
 
 
-@pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
-@pytest.mark.parametrize(
-    "model",
-    [
-        "models/gemini-pro",  # Format from issue #2803
-        "gemini-pro",         # Format without provider prefix
-    ],
-)
-def test_gemini_model_normalization(model):
-    """Test that different Gemini model formats are normalized correctly."""
-    llm = LLM(model=model)
-    
-    with patch("litellm.completion") as mock_completion:
-        # Create mocks for response structure
-        mock_message = MagicMock()
-        mock_message.content = "Paris"
-        mock_choice = MagicMock()
-        mock_choice.message = mock_message
-        mock_response = MagicMock()
-        mock_response.choices = [mock_choice]
-        
-        # Set up the mocked completion to return the mock response
-        mock_completion.return_value = mock_response
-        
-        llm.call("What is the capital of France?")
-        
-        # Check that the model was normalized correctly in the call to litellm
-        args, kwargs = mock_completion.call_args
-        assert kwargs["model"].startswith("gemini/")
-        assert "gemini-pro" in kwargs["model"]
-
-
-@pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
-def test_gemini_api_key_mapping():
-    """Test that GOOGLE_API_KEY is mapped to GEMINI_API_KEY for Gemini models."""
-    original_google_api_key = os.environ.get("GOOGLE_API_KEY")
-    original_gemini_api_key = os.environ.get("GEMINI_API_KEY")
-    
-    try:
-        # Set up test environment
-        test_api_key = "test_google_api_key"
-        os.environ["GOOGLE_API_KEY"] = test_api_key
-        if "GEMINI_API_KEY" in os.environ:
-            del os.environ["GEMINI_API_KEY"]
-        
-        llm = LLM(model="gemini-pro")
-        
-        with patch("litellm.completion") as mock_completion:
-            # Create mocks for response structure
-            mock_message = MagicMock()
-            mock_message.content = "Paris"
-            mock_choice = MagicMock()
-            mock_choice.message = mock_message
-            mock_response = MagicMock()
-            mock_response.choices = [mock_choice]
-            
-            # Set up the mocked completion to return the mock response
-            mock_completion.return_value = mock_response
-            
-            llm.call("What is the capital of France?")
-            
-            # Check that GEMINI_API_KEY was set from GOOGLE_API_KEY
-            assert os.environ.get("GEMINI_API_KEY") == test_api_key
-    
-    finally:
-        if original_google_api_key is not None:
-            os.environ["GOOGLE_API_KEY"] = original_google_api_key
-        else:
-            os.environ.pop("GOOGLE_API_KEY", None)
-            
-        if original_gemini_api_key is not None:
-            os.environ["GEMINI_API_KEY"] = original_gemini_api_key
-        else:
-            os.environ.pop("GEMINI_API_KEY", None)
-
-
 @pytest.mark.vcr(filter_headers=["authorization"], filter_query_parameters=["key"])
 @pytest.mark.parametrize(
     "model",

uv.lock

@@ -738,7 +738,7 @@ wheels = [
 
 [[package]]
 name = "crewai"
-version = "0.119.0"
+version = "0.118.0"
 source = { editable = "." }
 dependencies = [
     { name = "appdirs" },
@@ -828,7 +828,7 @@ requires-dist = [
     { name = "blinker", specifier = ">=1.9.0" },
     { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.44.0" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = "~=0.42.2" },
     { name = "docling", marker = "extra == 'docling'", specifier = ">=2.12.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
@@ -879,7 +879,7 @@ dev = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.44.0"
+version = "0.42.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "chromadb" },
@@ -894,9 +894,9 @@ dependencies = [
     { name = "pytube" },
     { name = "requests" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b8/1f/2977dc72628c1225bf5788ae22a65e5a53df384d19b197646d2c4760684e/crewai_tools-0.44.0.tar.gz", hash = "sha256:44e0c26079396503a326efdd9ff34bf369d410cbf95c362cc523db65b18f3c3a", size = 892004 }
+sdist = { url = "https://files.pythonhosted.org/packages/17/34/9e63e2db53d8f5c30353f271a3240687a48e55204bbd176a057c0b7658c8/crewai_tools-0.42.2.tar.gz", hash = "sha256:69365ffb168cccfea970e09b308905aa5007cfec60024d731ffac1362a0153c0", size = 754967 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ba/80/b91aa837d06edbb472445ea3c92d7619518894fd3049d480e5fffbf0c21b/crewai_tools-0.44.0-py3-none-any.whl", hash = "sha256:119e2365fe66ee16e18a5e8e222994b19f76bafcc8c1bb87f61609c1e39b2463", size = 583462 },
+    { url = "https://files.pythonhosted.org/packages/4e/43/0f70b95350084e5cb1e1d74e9acb9e18a89ba675b1d579c787c2662baba7/crewai_tools-0.42.2-py3-none-any.whl", hash = "sha256:13727fb68f0efefd21edeb281be3d66ff2f5a3b5029d4e6adef388b11fd5846a", size = 583933 },
 ]
 
 [[package]]