Merge branch 'main' of github.com:crewAIInc/crewAI into feat/sliding-context-window

src/crewai/agent.py

@@ -55,8 +55,6 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
-            allow_code_execution: Enable code execution for the agent.
-            max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
     """
 
     _times_executed: int = PrivateAttr(default=0)
@@ -262,6 +260,7 @@ class Agent(BaseAgent):
             "tools_handler": self.tools_handler,
             "function_calling_llm": self.function_calling_llm,
             "callbacks": self.callbacks,
+            "max_tokens": self.max_tokens,
         }
 
         if self._rpm_controller:

src/crewai/agents/agent_builder/base_agent.py

@@ -45,6 +45,7 @@ class BaseAgent(ABC, BaseModel):
         i18n (I18N): Internationalization settings.
         cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
         tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
+        max_tokens: Maximum number of tokens for the agent to generate in a response.
 
 
     Methods:
@@ -118,6 +119,9 @@ class BaseAgent(ABC, BaseModel):
     tools_handler: InstanceOf[ToolsHandler] = Field(
         default=None, description="An instance of the ToolsHandler class."
     )
+    max_tokens: Optional[int] = Field(
+        default=None, description="Maximum number of tokens for the agent's execution."
+    )
 
     _original_role: str | None = None
     _original_goal: str | None = None

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -4,7 +4,6 @@ from typing import TYPE_CHECKING, Optional
 
 from crewai.memory.entity.entity_memory_item import EntityMemoryItem
 from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
-from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.utilities.converter import ConverterError
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities import I18N
@@ -40,18 +39,17 @@ class CrewAgentExecutorMixin:
             and "Action: Delegate work to coworker" not in output.log
         ):
             try:
-                memory = ShortTermMemoryItem(
-                    data=output.log,
-                    agent=self.crew_agent.role,
-                    metadata={
-                        "observation": self.task.description,
-                    },
-                )
                 if (
                     hasattr(self.crew, "_short_term_memory")
                     and self.crew._short_term_memory
                 ):
-                    self.crew._short_term_memory.save(memory)
+                    self.crew._short_term_memory.save(
+                        value=output.log,
+                        metadata={
+                            "observation": self.task.description,
+                        },
+                        agent=self.crew_agent.role,
+                    )
             except Exception as e:
                 print(f"Failed to add to short term memory: {e}")
                 pass

src/crewai/cli/cli.py

@@ -6,9 +6,9 @@ from crewai.memory.storage.kickoff_task_outputs_storage import (
 )
 
 from .create_crew import create_crew
+from .evaluate_crew import evaluate_crew
 from .replay_from_task import replay_task_command
 from .reset_memories_command import reset_memories_command
-from .test_crew import test_crew
 from .train_crew import train_crew
 
 
@@ -144,7 +144,7 @@ def reset_memories(long, short, entities, kickoff_outputs, all):
 def test(n_iterations: int, model: str):
     """Test the crew and evaluate the results."""
     click.echo(f"Testing the crew for {n_iterations} iterations with model {model}")
-    test_crew(n_iterations, model)
+    evaluate_crew(n_iterations, model)
 
 
 if __name__ == "__main__":

src/crewai/cli/evaluate_crew.py

@@ -3,9 +3,9 @@ import subprocess
 import click
 
 
-def test_crew(n_iterations: int, model: str) -> None:
+def evaluate_crew(n_iterations: int, model: str) -> None:
     """
-    Test the crew by running a command in the Poetry environment.
+    Test and Evaluate the crew by running a command in the Poetry environment.
 
     Args:
         n_iterations (int): The number of iterations to test the crew.

src/crewai/cli/reset_memories_command.py

@@ -9,10 +9,14 @@ from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandle
 
 def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
     """
-    Replay the crew execution from a specific task.
+    Reset the crew memories.
 
     Args:
-      task_id (str): The ID of the task to replay from.
+      long (bool): Whether to reset the long-term memory.
+      short (bool): Whether to reset the short-term memory.
+      entity (bool): Whether to reset the entity memory.
+      kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
+      all (bool): Whether to reset all memories.
     """
 
     try:

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.41.1" }
+crewai = { extras = ["tools"], version = "^0.46.0" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/memory/short_term/short_term_memory.py

@@ -1,3 +1,4 @@
+from typing import Any, Dict, Optional
 from crewai.memory.memory import Memory
 from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.memory.storage.rag_storage import RAGStorage
@@ -18,8 +19,15 @@ class ShortTermMemory(Memory):
         )
         super().__init__(storage)
 
-    def save(self, item: ShortTermMemoryItem) -> None:
-        super().save(item.data, item.metadata, item.agent)
+    def save(
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
+
+        super().save(value=item.data, metadata=item.metadata, agent=item.agent)
 
     def search(self, query: str, score_threshold: float = 0.35):
         return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters

src/crewai/memory/short_term/short_term_memory_item.py

@@ -3,7 +3,10 @@ from typing import Any, Dict, Optional
 
 class ShortTermMemoryItem:
     def __init__(
-        self, data: Any, agent: str, metadata: Optional[Dict[str, Any]] = None
+        self,
+        data: Any,
+        agent: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ):
         self.data = data
         self.agent = agent

src/crewai/memory/storage/interface.py

@@ -4,7 +4,7 @@ from typing import Any, Dict
 class Storage:
     """Abstract base class defining the storage interface"""
 
-    def save(self, key: str, value: Any, metadata: Dict[str, Any]) -> None:
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         pass
 
     def search(self, key: str) -> Dict[str, Any]:  # type: ignore

src/crewai/task.py

@@ -1,3 +1,4 @@
+import datetime
 import json
 import os
 import threading
@@ -107,6 +108,7 @@ class Task(BaseModel):
     _original_description: str | None = None
     _original_expected_output: str | None = None
     _thread: threading.Thread | None = None
+    _execution_time: float | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -120,9 +122,15 @@ class Task(BaseModel):
                 "may_not_set_field", "This field is not to be set by the user.", {}
             )
 
+    def _set_start_execution_time(self) -> float:
+        return datetime.datetime.now().timestamp()
+
+    def _set_end_execution_time(self, start_time: float) -> None:
+        self._execution_time = datetime.datetime.now().timestamp() - start_time
+
     @field_validator("output_file")
     @classmethod
-    def output_file_validattion(cls, value: str) -> str:
+    def output_file_validation(cls, value: str) -> str:
         """Validate the output file path by removing the / from the beginning of the path."""
         if value.startswith("/"):
             return value[1:]
@@ -216,6 +224,7 @@ class Task(BaseModel):
                 f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
             )
 
+        start_time = self._set_start_execution_time()
         self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
 
         self.prompt_context = context
@@ -239,6 +248,7 @@ class Task(BaseModel):
         )
         self.output = task_output
 
+        self._set_end_execution_time(start_time)
         if self.callback:
             self.callback(self.output)
 
@@ -250,7 +260,9 @@ class Task(BaseModel):
             content = (
                 json_output
                 if json_output
-                else pydantic_output.model_dump_json() if pydantic_output else result
+                else pydantic_output.model_dump_json()
+                if pydantic_output
+                else result
             )
             self._save_file(content)
 
@@ -355,13 +367,21 @@ class Task(BaseModel):
         return OutputFormat.RAW
 
     def _save_file(self, result: Any) -> None:
+        if self.output_file is None:
+            raise ValueError("output_file is not set.")
+
         directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
 
         if directory and not os.path.exists(directory):
             os.makedirs(directory)
 
-        with open(self.output_file, "w", encoding="utf-8") as file:  # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
-            file.write(result)
+        with open(self.output_file, "w", encoding="utf-8") as file:
+            if isinstance(result, dict):
+                import json
+
+                json.dump(result, file, ensure_ascii=False, indent=2)
+            else:
+                file.write(str(result))
         return None
 
     def __repr__(self):

src/crewai/telemetry/telemetry.py

@@ -40,7 +40,7 @@ class Telemetry:
     - Roles of agents in a crew
     - Tools names available
 
-    Users can opt-in to sharing more complete data suing the `share_crew`
+    Users can opt-in to sharing more complete data using the `share_crew`
     attribute in the Crew class.
     """
 

src/crewai/tools/tool_usage.py

@@ -86,7 +86,8 @@ class ToolUsage:
     ) -> str:
         if isinstance(calling, ToolUsageErrorException):
             error = calling.message
-            self._printer.print(content=f"\n\n{error}\n", color="red")
+            if self.agent.verbose:
+                self._printer.print(content=f"\n\n{error}\n", color="red")
             self.task.increment_tools_errors()
             return error
 
@@ -96,7 +97,8 @@ class ToolUsage:
         except Exception as e:
             error = getattr(e, "message", str(e))
             self.task.increment_tools_errors()
-            self._printer.print(content=f"\n\n{error}\n", color="red")
+            if self.agent.verbose:
+                self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
         return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
 
@@ -112,7 +114,8 @@ class ToolUsage:
                 result = self._i18n.errors("task_repeated_usage").format(
                     tool_names=self.tools_names
                 )
-                self._printer.print(content=f"\n\n{result}\n", color="purple")
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{result}\n", color="purple")
                 self._telemetry.tool_repeated_usage(
                     llm=self.function_calling_llm,
                     tool_name=tool.name,
@@ -168,7 +171,10 @@ class ToolUsage:
                         f'\n{error_message}.\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                     ).message
                     self.task.increment_tools_errors()
-                    self._printer.print(content=f"\n\n{error_message}\n", color="red")
+                    if self.agent.verbose:
+                        self._printer.print(
+                            content=f"\n\n{error_message}\n", color="red"
+                        )
                     return error  # type: ignore # No return value expected
 
                 self.task.increment_tools_errors()
@@ -192,7 +198,8 @@ class ToolUsage:
                     calling=calling, output=result, should_cache=should_cache
                 )
 
-        self._printer.print(content=f"\n\n{result}\n", color="purple")
+        if self.agent.verbose:
+            self._printer.print(content=f"\n\n{result}\n", color="purple")
         if agentops:
             agentops.record(tool_event)
         self._telemetry.tool_usage(
@@ -346,7 +353,8 @@ class ToolUsage:
             if self._run_attempts > self._max_parsing_attempts:
                 self._telemetry.tool_usage_error(llm=self.function_calling_llm)
                 self.task.increment_tools_errors()
-                self._printer.print(content=f"\n\n{e}\n", color="red")
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{e}\n", color="red")
                 return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
                     f'{self._i18n.errors("tool_usage_error").format(error=e)}\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                 )

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -28,6 +28,7 @@ class CrewEvaluator:
     """
 
     tasks_scores: defaultdict = defaultdict(list)
+    run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
     def __init__(self, crew, openai_model_name: str):
@@ -40,9 +41,6 @@ class CrewEvaluator:
         for task in self.crew.tasks:
             task.callback = self.evaluate
 
-    def set_iteration(self, iteration: int) -> None:
-        self.iteration = iteration
-
     def _evaluator_agent(self):
         return Agent(
             role="Task Execution Evaluator",
@@ -71,6 +69,9 @@ class CrewEvaluator:
             output_pydantic=TaskEvaluationPydanticOutput,
         )
 
+    def set_iteration(self, iteration: int) -> None:
+        self.iteration = iteration
+
     def print_crew_evaluation_result(self) -> None:
         """
         Prints the evaluation result of the crew in a table.
@@ -119,6 +120,16 @@ class CrewEvaluator:
         ]
         table.add_row("Crew", *map(str, crew_scores), f"{crew_average:.1f}")
 
+        run_exec_times = [
+            int(sum(tasks_exec_times))
+            for _, tasks_exec_times in self.run_execution_times.items()
+        ]
+        execution_time_avg = int(sum(run_exec_times) / len(run_exec_times))
+        table.add_row(
+            "Execution Time (s)",
+            *map(str, run_exec_times),
+            f"{execution_time_avg}",
+        )
         # Display the table in the terminal
         console = Console()
         console.print(table)
@@ -145,5 +156,8 @@ class CrewEvaluator:
 
         if isinstance(evaluation_result.pydantic, TaskEvaluationPydanticOutput):
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
+            self.run_execution_times[self.iteration].append(
+                current_task._execution_time
+            )
         else:
             raise ValueError("Evaluation result is not in the expected format")

src/crewai/utilities/evaluators/task_evaluator.py

@@ -54,12 +54,12 @@ class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm
 
-    def evaluate(self, task, ouput) -> TaskEvaluation:
+    def evaluate(self, task, output) -> TaskEvaluation:
         evaluation_query = (
             f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"
             f"Task Description:\n{task.description}\n\n"
             f"Expected Output:\n{task.expected_output}\n\n"
-            f"Actual Output:\n{ouput}\n\n"
+            f"Actual Output:\n{output}\n\n"
             "Please provide:\n"
             "- Bullet points suggestions to improve future similar tasks\n"
             "- A score from 0 to 10 evaluating on completion, quality, and overall performance"

src/crewai/utilities/parser.py

@@ -1,17 +1,28 @@
 import re
 
-
 class YamlParser:
+    @staticmethod
     def parse(file):
+        """
+        Parses a YAML file, modifies specific patterns, and checks for unsupported 'context' usage.
+        Args:
+            file (file object): The YAML file to parse.
+        Returns:
+            str: The modified content of the YAML file.
+        Raises:
+            ValueError: If 'context:' is used incorrectly.
+        """
         content = file.read()
+
         # Replace single { and } with doubled ones, while leaving already doubled ones intact and the other special characters {# and {%
         modified_content = re.sub(r"(?<!\{){(?!\{)(?!\#)(?!\%)", "{{", content)
-        modified_content = re.sub(
-            r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content
-        )
+        modified_content = re.sub(r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content)
+
         # Check for 'context:' not followed by '[' and raise an error
         if re.search(r"context:(?!\s*\[)", modified_content):
             raise ValueError(
-                "Context is currently only supported in code when creating a task. Please use the 'context' key in the task configuration."
+                "Context is currently only supported in code when creating a task. "
+                "Please use the 'context' key in the task configuration."
             )
+
         return modified_content