[BUG] Recall Memory Tool fails with missing required positional argument

[MatthiasHowellYopp]

Description

I've got a simple crew running against the main branch. When I run it I'm seeing this error in the output:
Tool search_memory executed with result: Error executing tool: RecallMemoryTool._run() missing 1 required positional argument: 'queries'...
╭──────────────────────────────────────────────────────────────────────────── 🔧 Tool Error (#1) ─────────────────────────────────────────────────────────────────────────────╮
│ │
│ Tool Failed │
│ Tool: search_memory │
│ Iteration: 1 │
│ Attempt: 0 │
│ Error: RecallMemoryTool._run() missing 1 required positional argument: 'queries'

Steps to Reproduce

Using the main branch, I've created a new crew.

from crewai import Agent, Crew, Process, Task, LLM
from crewai.project import CrewBase, agent, crew, task
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai_tools import FileReadTool
from typing import List
import os

# If you want to run a snippet of code before or after the crew starts,
# you can use the @before_kickoff and @after_kickoff decorators
# https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators

@CrewBase
class ValkeyResearchDemo():
    """ValkeyResearchDemo crew"""

    agents: List[BaseAgent]
    tasks: List[Task]
    
    llm = LLM(
        model=os.getenv('MODEL'), 
        aws_region_name="us-east-2",
        aws_profile_name=os.getenv("AWS_PROFILE", "default"),  # Uses AWS CLI profile
        temperature=0.2,
        top_p=None
    )


    # Learn more about YAML configuration files here:
    # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
    # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
    
    # If you would like to add tools to your agents, you can learn more about it here:
    # https://docs.crewai.com/concepts/agents#agent-tools
    @agent
    def researcher(self) -> Agent:
        return Agent(
            config=self.agents_config['researcher'], # type: ignore[index]
            tools=[FileReadTool()],
            llm=self.llm,
            verbose=True
        )

    @agent
    def analyzer(self) -> Agent:
        return Agent(
            config=self.agents_config['analyzer'], # type: ignore[index]
            llm=self.llm,
            verbose=True
        )

    @agent
    def reporting_analyst(self) -> Agent:
        return Agent(
            config=self.agents_config['reporting_analyst'], # type: ignore[index]
            llm=self.llm,
            verbose=True
        )

    # To learn more about structured task outputs,
    # task dependencies, and task callbacks, check out the documentation:
    # https://docs.crewai.com/concepts/tasks#overview-of-a-task
    @task
    def research_task(self) -> Task:
        return Task(
            config=self.tasks_config['research_task'], # type: ignore[index]
        )

    @task
    def analysis_task(self) -> Task:
        return Task(
            config=self.tasks_config['analysis_task'], # type: ignore[index]
        )

    @task
    def reporting_task(self) -> Task:
        return Task(
            config=self.tasks_config['reporting_task'], # type: ignore[index]
            output_file='report.md'
        )

    @crew
    def crew(self) -> Crew:
        """Creates the ValkeyResearchDemo crew with LanceDB storage (testing without Valkey)"""
        from crewai.memory.storage.lancedb_storage import LanceDBStorage
        from crewai.memory import Memory
        
        # Use LanceDB storage (same backend as Valkey) with Bedrock embeddings
        lancedb_storage = LanceDBStorage(
            path="./lancedb_test"
        )
        
        # Wrap storage in Memory with embedder config
        memory = Memory(
            storage=lancedb_storage,
            llm=self.llm,
            embedder={
                "provider": "amazon-bedrock",
                "config": {"model": "amazon.titan-embed-text-v2:0"}
            }
        )
        
        print("✓ Using LanceDB storage with Bedrock embeddings (testing core crewai main branch)")
        
        return Crew(
            agents=self.agents, # Automatically created by the @agent decorator
            tasks=self.tasks, # Automatically created by the @task decorator
            process=Process.sequential,
            memory=memory,  # Use Memory with LanceDB storage
            llm=self.llm,
            verbose=True,
            # process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
        )

With agents as

researcher:
  role: >
    {topic} Senior Data Researcher
  goal: >
    Uncover cutting-edge developments in {topic}
  backstory: >
    You're a seasoned researcher with a knack for uncovering the latest
    developments in {topic}. Known for your ability to find the most relevant
    information and present it in a clear and concise manner.

analyzer:
  role: >
    {topic} Data Analyzer
  goal: >
    Analyze research findings and identify key patterns, trends, and insights about {topic}
  backstory: >
    You're an expert data analyst who excels at synthesizing complex information.
    You can quickly identify patterns, validate findings, and determine which
    insights are most valuable for decision-making.

reporting_analyst:
  role: >
    {topic} Reporting Analyst
  goal: >
    Create detailed reports based on {topic} data analysis and research findings
  backstory: >
    You're a meticulous analyst with a keen eye for detail. You're known for
    your ability to turn complex data into clear and concise reports, making
    it easy for others to understand and act on the information you provide.

and tasks as

researcher:
  role: >
    {topic} Senior Data Researcher
  goal: >
    Uncover cutting-edge developments in {topic}
  backstory: >
    You're a seasoned researcher with a knack for uncovering the latest
    developments in {topic}. Known for your ability to find the most relevant
    information and present it in a clear and concise manner.

analyzer:
  role: >
    {topic} Data Analyzer
  goal: >
    Analyze research findings and identify key patterns, trends, and insights about {topic}
  backstory: >
    You're an expert data analyst who excels at synthesizing complex information.
    You can quickly identify patterns, validate findings, and determine which
    insights are most valuable for decision-making.

reporting_analyst:
  role: >
    {topic} Reporting Analyst
  goal: >
    Create detailed reports based on {topic} data analysis and research findings
  backstory: >
    You're a meticulous analyst with a keen eye for detail. You're known for
    your ability to turn complex data into clear and concise reports, making
    it easy for others to understand and act on the information you provide.

This crew references my local copy of the main branch, not a released version

I run crewai run and all my search_memory tools generate the error Tool search_memory executed with result: Error executing tool: RecallMemoryTool._run() missing 1 required positional argument: 'queries'...

Expected behavior

I expect there to be no error

Screenshots/Code snippets

Operating System

Other (specify in additional context)

Python Version

3.11

crewAI Version

main branch - still happening as of commit 09e3b81

crewAI Tools Version

main branch, commit 09e3b81

Virtual Environment

Venv

Evidence

Possible Solution

None

Additional context

MacOs Tahoe,

I'm working on building a valkey implementation of the new Storage Backend and working on testing it to make sure it works. This example code is using lancedb instead to simplify the crew to reproduce the error - though I was getting it in my valkey-supported version. The error occurs with both the main branch and my feature branch , which suggests it is unrelated to my feature branch. I know that this is bleeding edge. I'm wondering if this is a known issue with a timeline, or a not-yet known issue.