merge: Merge main branch into task-guardrails branch

Co-Authored-By: Joe Moura <joao@crewai.com>

.github/workflows/stale.yml

@@ -1,5 +1,10 @@
 name: Mark stale issues and pull requests
 
+permissions:
+  contents: write
+  issues: write
+  pull-requests: write
+
 on:
   schedule:
     - cron: '10 12 * * *'
@@ -8,9 +13,6 @@ on:
 jobs:
   stale:
     runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
     steps:
     - uses: actions/stale@v9
       with:

README.md

@@ -44,7 +44,7 @@ To get started with CrewAI, follow these simple steps:
 
 ### 1. Installation
 
-Ensure you have Python >=3.10 <=3.12 installed on your system. CrewAI uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <3.13 installed on your system. CrewAI uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, install CrewAI:
 

docs/concepts/llms.mdx

@@ -29,7 +29,7 @@ Large Language Models (LLMs) are the core intelligence behind CrewAI agents. The
 
 ## Available Models and Their Capabilities
 
-Here's a detailed breakdown of supported models and their capabilities, you can compare performance at [lmarena.ai](https://lmarena.ai/):
+Here's a detailed breakdown of supported models and their capabilities, you can compare performance at [lmarena.ai](https://lmarena.ai/?leaderboard) and [artificialanalysis.ai](https://artificialanalysis.ai/):
 
 <Tabs>
   <Tab title="OpenAI">
@@ -121,12 +121,18 @@ Here's a detailed breakdown of supported models and their capabilities, you can
   <Tab title="Gemini">
     | Model | Context Window | Best For |
     |-------|---------------|-----------|
-    | Gemini 1.5 Flash | 1M tokens | Balanced multimodal model, good for most tasks |
+    | gemini-2.0-flash-exp | 1M tokens | Higher quality at faster speed, 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-flash | 1M tokens | Balanced multimodal model, good for most tasks |
-    | Gemini 1.5 Pro | 2M tokens | Best performing, wide variety of reasoning tasks including logical reasoning, coding, and creative collaboration |
+    | 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 |
 
     <Tip>
       Google's Gemini models are all multimodal, supporting audio, images, video and text, supporting context caching, json schema, function calling, etc.
+
+      These models are available via API_KEY from 
+      [The Gemini API](https://ai.google.dev/gemini-api/docs) and also from 
+      [Google Cloud Vertex](https://cloud.google.com/vertex-ai/generative-ai/docs/migrate/migrate-google-ai) as part of the
+      [Model Garden](https://cloud.google.com/vertex-ai/generative-ai/docs/model-garden/explore-models).
     </Tip>
   </Tab>
   <Tab title="Groq">
@@ -135,7 +141,6 @@ Here's a detailed breakdown of supported models and their capabilities, you can
     | Llama 3.1 70B/8B | 131,072 tokens | High-performance, large context tasks |
     | Llama 3.2 Series | 8,192 tokens | General-purpose tasks |
     | Mixtral 8x7B | 32,768 tokens | Balanced performance and context |
-    | Gemma Series | 8,192 tokens | Efficient, smaller-scale tasks |
 
     <Tip>
       Groq is known for its fast inference speeds, making it suitable for real-time applications.
@@ -146,7 +151,7 @@ Here's a detailed breakdown of supported models and their capabilities, you can
     |----------|---------------|--------------|
     | Deepseek Chat | 128,000 tokens | Specialized in technical discussions |
     | Claude 3 | Up to 200K tokens | Strong reasoning, code understanding |
-    | Gemini | Varies by model | Multimodal capabilities |
+    | Gemma Series | 8,192 tokens | Efficient, smaller-scale tasks |
 
     <Info>
       Provider selection should consider factors like:

docs/installation.mdx

@@ -7,7 +7,7 @@ icon: wrench
 <Note>
   **Python Version Requirements**
   
-  CrewAI requires `Python >=3.10 and <=3.12`. Here's how to check your version:
+  CrewAI requires `Python >=3.10 and <3.13`. Here's how to check your version:
   ```bash
   python3 --version
   ```

pyproject.toml

@@ -3,7 +3,7 @@ name = "crewai"
 version = "0.86.0"
 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,<=3.12"
+requires-python = ">=3.10,<3.13"
 authors = [
     { name = "Joao Moura", email = "joao@crewai.com" }
 ]
@@ -26,7 +26,7 @@ dependencies = [
     "uv>=0.4.25",
     "tomli-w>=1.1.0",
     "tomli>=2.0.2",
-    "chromadb>=0.5.18",
+    "chromadb>=0.5.23",
     "pdfplumber>=0.11.4",
     "openpyxl>=3.1.5",
     "blinker>=1.9.0",
@@ -38,7 +38,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.14.0"]
+tools = ["crewai-tools>=0.17.0"]
 agentops = ["agentops>=0.3.0"]
 fastembed = ["fastembed>=0.4.1"]
 pdfplumber = [
@@ -64,7 +64,7 @@ dev-dependencies = [
     "mkdocs-material-extensions>=1.3.1",
     "pillow>=10.2.0",
     "cairosvg>=2.7.1",
-    "crewai-tools>=0.14.0",
+    "crewai-tools>=0.17.0",
     "pytest>=8.0.0",
     "pytest-vcr>=1.0.2",
     "python-dotenv>=1.0.0",

src/crewai/agent.py

@@ -23,27 +23,19 @@ from crewai.utilities.converter import generate_model_description
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
+agentops = None
 
-def mock_agent_ops_provider():
+try:
-    def track_agent(*args, **kwargs):
+    import agentops  # type: ignore # Name "agentops" is already defined
+    from agentops import track_agent  # type: ignore
+except ImportError:
+
+    def track_agent():
         def noop(f):
             return f
 
         return noop
 
-    return track_agent
-
-
-agentops = None
-
-if os.environ.get("AGENTOPS_API_KEY"):
-    try:
-        from agentops import track_agent
-    except ImportError:
-        track_agent = mock_agent_ops_provider()
-else:
-    track_agent = mock_agent_ops_provider()
-
 
 @track_agent()
 class Agent(BaseAgent):

src/crewai/cli/cli.py

@@ -1,7 +1,7 @@
+from importlib.metadata import version as get_version
 from typing import Optional
 
 import click
-import pkg_resources
 
 from crewai.cli.add_crew_to_flow import add_crew_to_flow
 from crewai.cli.create_crew import create_crew
@@ -25,7 +25,7 @@ from .update_crew import update_crew
 
 
 @click.group()
-@click.version_option(pkg_resources.get_distribution("crewai").version)
+@click.version_option(get_version("crewai"))
 def crewai():
     """Top-level command group for crewai."""
 
@@ -52,16 +52,16 @@ def create(type, name, provider, skip_provider=False):
 def version(tools):
     """Show the installed version of crewai."""
     try:
-        crewai_version = pkg_resources.get_distribution("crewai").version
+        crewai_version = get_version("crewai")
     except Exception:
         crewai_version = "unknown version"
     click.echo(f"crewai version: {crewai_version}")
 
     if tools:
         try:
-            tools_version = pkg_resources.get_distribution("crewai-tools").version
+            tools_version = get_version("crewai")
             click.echo(f"crewai tools version: {tools_version}")
-        except pkg_resources.DistributionNotFound:
+        except Exception:
             click.echo("crewai tools not installed")
 
 

src/crewai/cli/templates/crew/README.md

@@ -4,7 +4,7 @@ Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.co
 
 ## Installation
 
-Ensure you have Python >=3.10 <=3.12 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <3.13 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, if you haven't already, install uv:
 

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

@@ -3,7 +3,7 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
-requires-python = ">=3.10,<=3.12"
+requires-python = ">=3.10,<3.13"
 dependencies = [
     "crewai[tools]>=0.86.0,<1.0.0"
 ]
@@ -18,3 +18,6 @@ test = "{{folder_name}}.main:test"
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
+
+[tool.crewai]
+type = "crew"

src/crewai/cli/templates/crew/tools/custom_tool.py

@@ -10,7 +10,7 @@ class MyCustomToolInput(BaseModel):
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
     description: str = (
-        "Clear description for what this tool is useful for, you agent will need this information to use it."
+        "Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     args_schema: Type[BaseModel] = MyCustomToolInput
 

src/crewai/cli/templates/flow/README.md

@@ -4,7 +4,7 @@ Welcome to the {{crew_name}} Crew project, powered by [crewAI](https://crewai.co
 
 ## Installation
 
-Ensure you have Python >=3.10 <=3.12 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
+Ensure you have Python >=3.10 <3.13 installed on your system. This project uses [UV](https://docs.astral.sh/uv/) for dependency management and package handling, offering a seamless setup and execution experience.
 
 First, if you haven't already, install uv:
 

src/crewai/cli/templates/flow/main.py

@@ -5,7 +5,7 @@ from pydantic import BaseModel
 
 from crewai.flow.flow import Flow, listen, start
 
-from .crews.poem_crew.poem_crew import PoemCrew
+from {{folder_name}}.crews.poem_crew.poem_crew import PoemCrew
 
 
 class PoemState(BaseModel):

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

@@ -3,7 +3,7 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
-requires-python = ">=3.10,<=3.12"
+requires-python = ">=3.10,<3.13"
 dependencies = [
     "crewai[tools]>=0.86.0,<1.0.0",
 ]
@@ -15,3 +15,6 @@ plot = "{{folder_name}}.main:plot"
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
+
+[tool.crewai]
+type = "flow"

src/crewai/cli/templates/flow/tools/custom_tool.py

@@ -13,7 +13,7 @@ class MyCustomToolInput(BaseModel):
 class MyCustomTool(BaseTool):
     name: str = "Name of my tool"
     description: str = (
-        "Clear description for what this tool is useful for, you agent will need this information to use it."
+        "Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     args_schema: Type[BaseModel] = MyCustomToolInput
 

src/crewai/cli/templates/tool/README.md

@@ -5,7 +5,7 @@ custom tools to power up your crews.
 
 ## Installing
 
-Ensure you have Python >=3.10 <=3.12 installed on your system. This project
+Ensure you have Python >=3.10 <3.13 installed on your system. This project
 uses [UV](https://docs.astral.sh/uv/) for dependency management and package
 handling, offering a seamless setup and execution experience.
 

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

@@ -3,8 +3,10 @@ name = "{{folder_name}}"
 version = "0.1.0"
 description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
-requires-python = ">=3.10,<=3.12"
+requires-python = ">=3.10,<3.13"
 dependencies = [
     "crewai[tools]>=0.86.0"
 ]
 
+[tool.crewai]
+type = "tool"

src/crewai/crew.py

@@ -1,6 +1,5 @@
 import asyncio
 import json
-import os
 import uuid
 import warnings
 from concurrent.futures import Future
@@ -49,12 +48,10 @@ from crewai.utilities.planning_handler import CrewPlanner
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
-agentops = None
+try:
-if os.environ.get("AGENTOPS_API_KEY"):
+    import agentops  # type: ignore
-    try:
+except ImportError:
-        import agentops  # type: ignore
+    agentops = None
-    except ImportError:
-        pass
 
 
 warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")

src/crewai/knowledge/storage/knowledge_storage.py

@@ -124,43 +124,60 @@ class KnowledgeStorage(BaseKnowledgeStorage):
         documents: List[str],
         metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None,
     ):
-        if self.collection:
+        if not self.collection:
-            try:
-                if metadata is None:
-                    metadatas: Optional[OneOrMany[chromadb.Metadata]] = None
-                elif isinstance(metadata, list):
-                    metadatas = [cast(chromadb.Metadata, m) for m in metadata]
-                else:
-                    metadatas = cast(chromadb.Metadata, metadata)
-
-                ids = [
-                    hashlib.sha256(doc.encode("utf-8")).hexdigest() for doc in documents
-                ]
-
-                self.collection.upsert(
-                    documents=documents,
-                    metadatas=metadatas,
-                    ids=ids,
-                )
-            except chromadb.errors.InvalidDimensionException as e:
-                Logger(verbose=True).log(
-                    "error",
-                    "Embedding dimension mismatch. This usually happens when mixing different embedding models. Try resetting the collection using `crewai reset-memories -a`",
-                    "red",
-                )
-                raise ValueError(
-                    "Embedding dimension mismatch. Make sure you're using the same embedding model "
-                    "across all operations with this collection."
-                    "Try resetting the collection using `crewai reset-memories -a`"
-                ) from e
-            except Exception as e:
-                Logger(verbose=True).log(
-                    "error", f"Failed to upsert documents: {e}", "red"
-                )
-                raise
-        else:
             raise Exception("Collection not initialized")
 
+        try:
+            # Create a dictionary to store unique documents
+            unique_docs = {}
+
+            # Generate IDs and create a mapping of id -> (document, metadata)
+            for idx, doc in enumerate(documents):
+                doc_id = hashlib.sha256(doc.encode("utf-8")).hexdigest()
+                doc_metadata = None
+                if metadata is not None:
+                    if isinstance(metadata, list):
+                        doc_metadata = metadata[idx]
+                    else:
+                        doc_metadata = metadata
+                unique_docs[doc_id] = (doc, doc_metadata)
+
+            # Prepare filtered lists for ChromaDB
+            filtered_docs = []
+            filtered_metadata = []
+            filtered_ids = []
+
+            # Build the filtered lists
+            for doc_id, (doc, meta) in unique_docs.items():
+                filtered_docs.append(doc)
+                filtered_metadata.append(meta)
+                filtered_ids.append(doc_id)
+
+            # If we have no metadata at all, set it to None
+            final_metadata: Optional[OneOrMany[chromadb.Metadata]] = (
+                None if all(m is None for m in filtered_metadata) else filtered_metadata
+            )
+
+            self.collection.upsert(
+                documents=filtered_docs,
+                metadatas=final_metadata,
+                ids=filtered_ids,
+            )
+        except chromadb.errors.InvalidDimensionException as e:
+            Logger(verbose=True).log(
+                "error",
+                "Embedding dimension mismatch. This usually happens when mixing different embedding models. Try resetting the collection using `crewai reset-memories -a`",
+                "red",
+            )
+            raise ValueError(
+                "Embedding dimension mismatch. Make sure you're using the same embedding model "
+                "across all operations with this collection."
+                "Try resetting the collection using `crewai reset-memories -a`"
+            ) from e
+        except Exception as e:
+            Logger(verbose=True).log("error", f"Failed to upsert documents: {e}", "red")
+            raise
+
     def _create_default_embedding_function(self):
         from chromadb.utils.embedding_functions.openai_embedding_function import (
             OpenAIEmbeddingFunction,

src/crewai/llm.py

@@ -44,6 +44,7 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "o1-preview": 128000,
     "o1-mini": 128000,
     # gemini
+    "gemini-2.0-flash": 1048576,
     "gemini-1.5-pro": 2097152,
     "gemini-1.5-flash": 1048576,
     "gemini-1.5-flash-8b": 1048576,

src/crewai/telemetry/telemetry.py

@@ -6,6 +6,7 @@ import os
 import platform
 import warnings
 from contextlib import contextmanager
+from importlib.metadata import version
 from typing import TYPE_CHECKING, Any, Optional
 
 
@@ -16,10 +17,6 @@ def suppress_warnings():
         yield
 
 
-with suppress_warnings():
-    import pkg_resources
-
-
 from opentelemetry import trace  # noqa: E402
 from opentelemetry.exporter.otlp.proto.http.trace_exporter import (
     OTLPSpanExporter,  # noqa: E402
@@ -106,7 +103,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "python_version", platform.python_version())
             self._add_attribute(span, "crew_key", crew.key)
@@ -308,7 +305,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "tool_name", tool_name)
             self._add_attribute(span, "attempts", attempts)
@@ -328,7 +325,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "tool_name", tool_name)
             self._add_attribute(span, "attempts", attempts)
@@ -348,7 +345,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             if llm:
                 self._add_attribute(span, "llm", llm.model)
@@ -367,7 +364,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "crew_key", crew.key)
             self._add_attribute(span, "crew_id", str(crew.id))
@@ -393,7 +390,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "crew_key", crew.key)
             self._add_attribute(span, "crew_id", str(crew.id))
@@ -474,7 +471,7 @@ class Telemetry:
             self._add_attribute(
                 span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(span, "crew_key", crew.key)
             self._add_attribute(span, "crew_id", str(crew.id))
@@ -543,7 +540,7 @@ class Telemetry:
             self._add_attribute(
                 crew._execution_span,
                 "crewai_version",
-                pkg_resources.get_distribution("crewai").version,
+                version("crewai"),
             )
             self._add_attribute(
                 crew._execution_span, "crew_output", final_string_output

src/crewai/tools/tool_usage.py

@@ -1,6 +1,5 @@
 import ast
 import datetime
-import os
 import time
 from difflib import SequenceMatcher
 from textwrap import dedent
@@ -15,12 +14,10 @@ from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.tools.tool_usage_events import ToolUsageError, ToolUsageFinished
 from crewai.utilities import I18N, Converter, ConverterError, Printer
 
-agentops = None
+try:
-if os.environ.get("AGENTOPS_API_KEY"):
+    import agentops  # type: ignore
-    try:
+except ImportError:
-        import agentops  # type: ignore
+    agentops = None
-    except ImportError:
-        pass
 
 OPENAI_BIGGER_MODELS = ["gpt-4", "gpt-4o", "o1-preview", "o1-mini"]
 
@@ -422,9 +419,10 @@ class ToolUsage:
                 elif value.lower() in [
                     "true",
                     "false",
-                    "null",
                 ]:  # Check for boolean and null values
-                    value = value.lower()
+                    value = value.lower().capitalize()
+                elif value.lower() == "null":
+                    value = "None"
                 else:
                     # Assume the value is a string and needs quotes
                     value = '"' + value.replace('"', '\\"') + '"'

src/crewai/translations/en.json

@@ -12,7 +12,7 @@
     "tools": "\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\n{tools}\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [{tool_names}], just the name, exactly as it's written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n",
     "no_tools": "\nTo give my best complete final answer to the task use 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!",
     "format": "I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. To Use the following format:\n\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action, dictionary enclosed in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\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\n",
-    "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfy the expect criteria, use the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n",
+    "final_answer_format": "If you don't need to use any more tools, you must give your best complete final answer, make sure it satisfies the expected criteria, use the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete final answer to the task.\n\n",
     "format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nI just remembered the expected format I must follow:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\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\n",
     "task_with_context": "{task}\n\nThis is the context you're working with:\n{context}",
     "expected_output": "\nThis is the expect criteria for your final answer: {expected_output}\nyou MUST return the actual complete content as the final answer, not a summary.",

src/crewai/utilities/crew_json_encoder.py

@@ -1,6 +1,7 @@
 import json
 from datetime import date, datetime
 from decimal import Decimal
+from enum import Enum
 from uuid import UUID
 
 from pydantic import BaseModel
@@ -10,7 +11,7 @@ class CrewJSONEncoder(json.JSONEncoder):
     def default(self, obj):
         if isinstance(obj, BaseModel):
             return self._handle_pydantic_model(obj)
-        elif isinstance(obj, UUID) or isinstance(obj, Decimal):
+        elif isinstance(obj, UUID) or isinstance(obj, Decimal) or isinstance(obj, Enum):
             return str(obj)
 
         elif isinstance(obj, datetime) or isinstance(obj, date):

src/crewai/utilities/evaluators/task_evaluator.py

@@ -1,4 +1,3 @@
-import os
 from typing import List
 
 from pydantic import BaseModel, Field
@@ -6,27 +5,17 @@ from pydantic import BaseModel, Field
 from crewai.utilities import Converter
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
+agentops = None
+try:
+    from agentops import track_agent  # type: ignore
+except ImportError:
 
-def mock_agent_ops_provider():
+    def track_agent(name):
-    def track_agent(*args, **kwargs):
         def noop(f):
             return f
 
         return noop
 
-    return track_agent
-
-
-agentops = None
-
-if os.environ.get("AGENTOPS_API_KEY"):
-    try:
-        from agentops import track_agent
-    except ImportError:
-        track_agent = mock_agent_ops_provider()
-else:
-    track_agent = mock_agent_ops_provider()
-
 
 class Entity(BaseModel):
     name: str = Field(description="The name of the entity.")

tests/agent_test.py

@@ -1595,19 +1595,15 @@ def test_agent_execute_task_with_ollama():
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_with_knowledge_sources():
     # Create a knowledge source with some content
-    content = "Brandon's favorite color is blue and he likes Mexican food."
+    content = "Brandon's favorite color is red and he likes Mexican food."
-    string_source = StringKnowledgeSource(
+    string_source = StringKnowledgeSource(content=content)
-        content=content, metadata={"preference": "personal"}
-    )
 
     with patch(
         "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
     ) as MockKnowledge:
         mock_knowledge_instance = MockKnowledge.return_value
         mock_knowledge_instance.sources = [string_source]
-        mock_knowledge_instance.query.return_value = [
+        mock_knowledge_instance.query.return_value = [{"content": content}]
-            {"content": content, "metadata": {"preference": "personal"}}
-        ]
 
         agent = Agent(
             role="Information Agent",
@@ -1628,4 +1624,4 @@ def test_agent_with_knowledge_sources():
         result = crew.kickoff()
 
         # Assert that the agent provides the correct information
-        assert "blue" in result.raw.lower()
+        assert "red" in result.raw.lower()

tests/cassettes/test_agent_function_calling_llm.yaml

@@ -26237,7 +26237,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}], "model": "gpt-4o"}'
     headers:
@@ -26590,7 +26590,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -26941,7 +26941,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -27292,7 +27292,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -27647,7 +27647,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28005,7 +28005,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28364,7 +28364,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28718,7 +28718,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29082,7 +29082,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29441,7 +29441,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29802,7 +29802,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30170,7 +30170,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30533,7 +30533,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30907,7 +30907,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -31273,7 +31273,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -31644,7 +31644,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -32015,7 +32015,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the

tests/cassettes/test_agent_powered_by_new_o_model_family_that_allows_skipping_tool.yaml

@@ -247,7 +247,7 @@ interactions:
       {"role": "user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
       after ''Thought:''. I will do right next, and don''t use a tool I have already
       used.\n\nIf you don''t need to use any more tools, you must give your best complete
-      final answer, make sure it satisfy the expect criteria, use the EXACT format
+      final answer, make sure it satisfies the expected criteria, use the EXACT format
       below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
       final answer to the task.\n\n"}], "model": "o1-preview"}'
     headers:

tests/cli/deploy/test_deploy_main.py

@@ -231,7 +231,7 @@ class TestDeployCommand(unittest.TestCase):
         [project]
         name = "test_project"
         version = "0.1.0"
-        requires-python = ">=3.10,<=3.12"
+        requires-python = ">=3.10,<3.13"
         dependencies = ["crewai"]
         """,
     )
@@ -250,7 +250,7 @@ class TestDeployCommand(unittest.TestCase):
     [project]
     name = "test_project"
     version = "0.1.0"
-    requires-python = ">=3.10,<=3.12"
+    requires-python = ">=3.10,<3.13"
     dependencies = ["crewai"]
     """,
     )

tests/task_test.py

@@ -686,7 +686,7 @@ def test_increment_tool_errors():
     with patch.object(Task, "increment_tools_errors") as increment_tools_errors:
         increment_tools_errors.return_value = None
         crew.kickoff()
-        assert len(increment_tools_errors.mock_calls) == 12
+        assert len(increment_tools_errors.mock_calls) > 0
 
 
 def test_task_definition_based_on_dict():

tests/tools/test_base_tool.py

@@ -6,14 +6,14 @@ from crewai.tools import BaseTool, tool
 def test_creating_a_tool_using_annotation():
     @tool("Name of my tool")
     def my_tool(question: str) -> str:
-        """Clear description for what this tool is useful for, you agent will need this information to use it."""
+        """Clear description for what this tool is useful for, your agent will need this information to use it."""
         return question
 
     # Assert all the right attributes were defined
     assert my_tool.name == "Name of my tool"
     assert (
         my_tool.description
-        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     assert my_tool.args_schema.schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
@@ -27,7 +27,7 @@ def test_creating_a_tool_using_annotation():
 
     assert (
         converted_tool.description
-        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     assert converted_tool.args_schema.schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
@@ -41,7 +41,7 @@ def test_creating_a_tool_using_annotation():
 def test_creating_a_tool_using_baseclass():
     class MyCustomTool(BaseTool):
         name: str = "Name of my tool"
-        description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
+        description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
 
         def _run(self, question: str) -> str:
             return question
@@ -52,7 +52,7 @@ def test_creating_a_tool_using_baseclass():
 
     assert (
         my_tool.description
-        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     assert my_tool.args_schema.schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
@@ -64,7 +64,7 @@ def test_creating_a_tool_using_baseclass():
 
     assert (
         converted_tool.description
-        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, you agent will need this information to use it."
+        == "Tool Name: Name of my tool\nTool Arguments: {'question': {'description': None, 'type': 'str'}}\nTool Description: Clear description for what this tool is useful for, your agent will need this information to use it."
     )
     assert converted_tool.args_schema.schema()["properties"] == {
         "question": {"title": "Question", "type": "string"}
@@ -78,7 +78,7 @@ def test_creating_a_tool_using_baseclass():
 def test_setting_cache_function():
     class MyCustomTool(BaseTool):
         name: str = "Name of my tool"
-        description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
+        description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
         cache_function: Callable = lambda: False
 
         def _run(self, question: str) -> str:
@@ -92,7 +92,7 @@ def test_setting_cache_function():
 def test_default_cache_function_is_true():
     class MyCustomTool(BaseTool):
         name: str = "Name of my tool"
-        description: str = "Clear description for what this tool is useful for, you agent will need this information to use it."
+        description: str = "Clear description for what this tool is useful for, your agent will need this information to use it."
 
         def _run(self, question: str) -> str:
             return question

uv.lock

@@ -1,9 +1,10 @@
 version = 1
-requires-python = ">=3.10, <=3.12"
+requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version < '3.11'",
     "python_full_version == '3.11.*'",
-    "python_full_version >= '3.12'",
+    "python_full_version >= '3.12' and python_full_version < '3.12.4'",
+    "python_full_version >= '3.12.4'",
 ]
 
 [[package]]
@@ -479,7 +480,7 @@ wheels = [
 
 [[package]]
 name = "chromadb"
-version = "0.5.18"
+version = "0.5.23"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "bcrypt" },
@@ -511,9 +512,9 @@ dependencies = [
     { name = "typing-extensions" },
     { name = "uvicorn", extra = ["standard"] },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/15/95/d1a3f14c864e37d009606b82bd837090902b5e5a8e892fcab07eeaec0438/chromadb-0.5.18.tar.gz", hash = "sha256:cfbb3e5aeeb1dd532b47d80ed9185e8a9886c09af41c8e6123edf94395d76aec", size = 33620708 }
+sdist = { url = "https://files.pythonhosted.org/packages/42/64/28daa773f784bcd18de944fe26ed301de844d6ee17188e26a9d6b4baf122/chromadb-0.5.23.tar.gz", hash = "sha256:360a12b9795c5a33cb1f839d14410ccbde662ef1accd36153b0ae22312edabd1", size = 33700455 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/82/85/4d2f8b9202153105ad4514ae09e9fe6f3b353a45e44e0ef7eca03dd8b9dc/chromadb-0.5.18-py3-none-any.whl", hash = "sha256:9dd3827b5e04b4ff0a5ea0df28a78bac88a09f45be37fcd7fe20f879b57c43cf", size = 615499 },
+    { url = "https://files.pythonhosted.org/packages/92/8c/a9eb95a28e6c35a0122417976a9d435eeaceb53f596a8973e33b3dd4cfac/chromadb-0.5.23-py3-none-any.whl", hash = "sha256:ffe5bdd7276d12cb682df0d38a13aa37573e6a3678e71889ac45f539ae05ad7e", size = 628347 },
 ]
 
 [[package]]
@@ -648,9 +649,9 @@ requires-dist = [
     { name = "appdirs", specifier = ">=1.4.4" },
     { name = "auth0-python", specifier = ">=4.7.1" },
     { name = "blinker", specifier = ">=1.9.0" },
-    { name = "chromadb", specifier = ">=0.5.18" },
+    { name = "chromadb", specifier = ">=0.5.23" },
     { name = "click", specifier = ">=8.1.7" },
-    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.14.0" },
+    { name = "crewai-tools", marker = "extra == 'tools'", specifier = ">=0.17.0" },
     { name = "fastembed", marker = "extra == 'fastembed'", specifier = ">=0.4.1" },
     { name = "instructor", specifier = ">=1.3.3" },
     { name = "json-repair", specifier = ">=0.25.2" },
@@ -678,7 +679,7 @@ requires-dist = [
 [package.metadata.requires-dev]
 dev = [
     { name = "cairosvg", specifier = ">=2.7.1" },
-    { name = "crewai-tools", specifier = ">=0.14.0" },
+    { name = "crewai-tools", specifier = ">=0.17.0" },
     { name = "mkdocs", specifier = ">=1.4.3" },
     { name = "mkdocs-material", specifier = ">=9.5.7" },
     { name = "mkdocs-material-extensions", specifier = ">=1.3.1" },