Merge branch 'main' into main

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 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 |
+    | 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 |
 
     <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" }
 ]

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/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/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/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/tools/tool_usage.py

@@ -419,9 +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.",

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"]
     """,
     )

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]]