Fix import sorting in test_kickoff_for_each_parallel.py

Co-Authored-By: Joe Moura <joao@crewai.com>
Improve kickoff_for_each_parallel based on PR feedback
2026-01-08 15:48:29 +00:00 · 2025-03-19 17:12:18 +00:00 · 2025-03-19 17:12:09 +00:00 · 2025-03-19 17:05:25 +00:00 · 2025-03-19 17:05:14 +00:00
32 changed files with 1108 additions and 1163 deletions
--- a/docs/changelog.mdx
+++ b/docs/changelog.mdx
@@ -1,187 +0,0 @@
---
-title: Changelog
-description: View the latest updates and changes to CrewAI
-icon: timeline
---
-
-<Update label="2024-03-17" description="v0.108.0">
-  **Features**
-  - Converted tabs to spaces in `crew.py` template
-  - Enhanced LLM Streaming Response Handling and Event System
-  - Included `model_name`
-  - Enhanced Event Listener with rich visualization and improved logging
-  - Added fingerprints
-
-  **Bug Fixes**
-  - Fixed Mistral issues
-  - Fixed a bug in documentation
-  - Fixed type check error in fingerprint property
-
-  **Documentation Updates**
-  - Improved tool documentation
-  - Updated installation guide for the `uv` tool package
-  - Added instructions for upgrading crewAI with the `uv` tool
-  - Added documentation for `ApifyActorsTool`
-</Update>
-
-<Update label="2024-03-10" description="v0.105.0">
-  **Core Improvements & Fixes**
-  - Fixed issues with missing template variables and user memory configuration
-  - Improved async flow support and addressed agent response formatting
-  - Enhanced memory reset functionality and fixed CLI memory commands
-  - Fixed type issues, tool calling properties, and telemetry decoupling
-
-  **New Features & Enhancements**
-  - Added Flow state export and improved state utilities
-  - Enhanced agent knowledge setup with optional crew embedder
-  - Introduced event emitter for better observability and LLM call tracking
-  - Added support for Python 3.10 and ChatOllama from langchain_ollama
-  - Integrated context window size support for the o3-mini model
-  - Added support for multiple router calls
-
-  **Documentation & Guides**
-  - Improved documentation layout and hierarchical structure
-  - Added QdrantVectorSearchTool guide and clarified event listener usage
-  - Fixed typos in prompts and updated Amazon Bedrock model listings
-</Update>
-
-<Update label="2024-02-12" description="v0.102.0">
-  **Core Improvements & Fixes**
-  - Enhanced LLM Support: Improved structured LLM output, parameter handling, and formatting for Anthropic models
-  - Crew & Agent Stability: Fixed issues with cloning agents/crews using knowledge sources, multiple task outputs in conditional tasks, and ignored Crew task callbacks
-  - Memory & Storage Fixes: Fixed short-term memory handling with Bedrock, ensured correct embedder initialization, and added a reset memories function in the crew class
-  - Training & Execution Reliability: Fixed broken training and interpolation issues with dict and list input types
-
-  **New Features & Enhancements**
-  - Advanced Knowledge Management: Improved naming conventions and enhanced embedding configuration with custom embedder support
-  - Expanded Logging & Observability: Added JSON format support for logging and integrated MLflow tracing documentation
-  - Data Handling Improvements: Updated excel_knowledge_source.py to process multi-tab files
-  - General Performance & Codebase Clean-Up: Streamlined enterprise code alignment and resolved linting issues
-  - Adding new tool: `QdrantVectorSearchTool`
-
-  **Documentation & Guides**
-  - Updated AI & Memory Docs: Improved Bedrock, Google AI, and long-term memory documentation
-  - Task & Workflow Clarity: Added "Human Input" row to Task Attributes, Langfuse guide, and FileWriterTool documentation
-  - Fixed Various Typos & Formatting Issues
-</Update>
-
-<Update label="2024-01-28" description="v0.100.0">
-  **Features**
-  - Add Composio docs
-  - Add SageMaker as a LLM provider
-  
-  **Fixes**
-  - Overall LLM connection issues
-  - Using safe accessors on training
-  - Add version check to crew_chat.py
-  
-  **Documentation**
-  - New docs for crewai chat
-  - Improve formatting and clarity in CLI and Composio Tool docs
-</Update>
-
-<Update label="2024-01-20" description="v0.98.0">
-  **Features**
-  - Conversation crew v1
-  - Add unique ID to flow states
-  - Add @persist decorator with FlowPersistence interface
-  
-  **Integrations**
-  - Add SambaNova integration
-  - Add NVIDIA NIM provider in cli
-  - Introducing VoyageAI
-  
-  **Fixes**
-  - Fix API Key Behavior and Entity Handling in Mem0 Integration
-  - Fixed core invoke loop logic and relevant tests
-  - Make tool inputs actual objects and not strings
-  - Add important missing parts to creating tools
-  - Drop litellm version to prevent windows issue
-  - Before kickoff if inputs are none
-  - Fixed typos, nested pydantic model issue, and docling issues
-</Update>
-
-<Update label="2024-01-04" description="v0.95.0">
-  **New Features**
-  - Adding Multimodal Abilities to Crew
-  - Programatic Guardrails
-  - HITL multiple rounds
-  - Gemini 2.0 Support
-  - CrewAI Flows Improvements
-  - Add Workflow Permissions
-  - Add support for langfuse with litellm
-  - Portkey Integration with CrewAI
-  - Add interpolate_only method and improve error handling
-  - Docling Support
-  - Weviate Support
-  
-  **Fixes**
-  - output_file not respecting system path
-  - disk I/O error when resetting short-term memory
-  - CrewJSONEncoder now accepts enums
-  - Python max version
-  - Interpolation for output_file in Task
-  - Handle coworker role name case/whitespace properly
-  - Add tiktoken as explicit dependency and document Rust requirement
-  - Include agent knowledge in planning process
-  - Change storage initialization to None for KnowledgeStorage
-  - Fix optional storage checks
-  - include event emitter in flows
-  - Docstring, Error Handling, and Type Hints Improvements
-  - Suppressed userWarnings from litellm pydantic issues
-</Update>
-
-<Update label="2023-12-05" description="v0.86.0">
-  **Changes**
-  - Remove all references to pipeline and pipeline router
-  - Add Nvidia NIM as provider in Custom LLM
-  - Add knowledge demo + improve knowledge docs
-  - Add HITL multiple rounds of followup
-  - New docs about yaml crew with decorators
-  - Simplify template crew
-</Update>
-
-<Update label="2023-12-04" description="v0.85.0">
-  **Features**
-  - Added knowledge to agent level
-  - Feat/remove langchain
-  - Improve typed task outputs
-  - Log in to Tool Repository on crewai login
-  
-  **Fixes**
-  - Fixes issues with result as answer not properly exiting LLM loop
-  - Fix missing key name when running with ollama provider
-  - Fix spelling issue found
-  
-  **Documentation**
-  - Update readme for running mypy
-  - Add knowledge to mint.json
-  - Update Github actions
-  - Update Agents docs to include two approaches for creating an agent
-  - Improvements to LLM Configuration and Usage
-</Update>
-
-<Update label="2023-11-25" description="v0.83.0">
-  **New Features**
-  - New before_kickoff and after_kickoff crew callbacks
-  - Support to pre-seed agents with Knowledge
-  - Add support for retrieving user preferences and memories using Mem0
-  
-  **Fixes**
-  - Fix Async Execution
-  - Upgrade chroma and adjust embedder function generator
-  - Update CLI Watson supported models + docs
-  - Reduce level for Bandit
-  - Fixing all tests
-  
-  **Documentation**
-  - Update Docs
-</Update>
-
-<Update label="2023-11-13" description="v0.80.0">
-  **Fixes**
-  - Fixing Tokens callback replacement bug
-  - Fixing Step callback issue
-  - Add cached prompt tokens info on usage metrics
-  - Fix crew_train_success test
-</Update>
--- a/docs/concepts/knowledge.mdx
+++ b/docs/concepts/knowledge.mdx
@@ -150,8 +150,6 @@ result = crew.kickoff(

 Here are examples of how to use different types of knowledge sources:

-Note: Please ensure that you create the ./knowldge folder. All source files (e.g., .txt, .pdf, .xlsx, .json) should be placed in this folder for centralized management.
-
 ### Text File Knowledge Source
 ```python
 from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
@@ -462,12 +460,12 @@ class SpaceNewsKnowledgeSource(BaseKnowledgeSource):
            data = response.json()
            articles = data.get('results', [])

-            formatted_data = self.validate_content(articles)
+            formatted_data = self._format_articles(articles)
            return {self.api_endpoint: formatted_data}
        except Exception as e:
            raise ValueError(f"Failed to fetch space news: {str(e)}")

-    def validate_content(self, articles: list) -> str:
+    def _format_articles(self, articles: list) -> str:
        """Format articles into readable text."""
        formatted = "Space News Articles:\n\n"
        for article in articles:
--- a/docs/concepts/llms.mdx
+++ b/docs/concepts/llms.mdx
@@ -59,7 +59,7 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
        goal: Conduct comprehensive research and analysis
        backstory: A dedicated research professional with years of experience
        verbose: true
-        llm: openai/gpt-4o-mini # your model here
+        llm: openai/gpt-4o-mini # your model here 
        # (see provider configuration examples below for more)
    ```

@@ -111,7 +111,7 @@ There are three ways to configure LLMs in CrewAI. Choose the method that best fi
 ## Provider Configuration Examples


-CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities.
+CrewAI supports a multitude of LLM providers, each offering unique features, authentication methods, and model capabilities. 
 In this section, you'll find detailed examples that help you select, configure, and optimize the LLM that best fits your project's needs.

 <AccordionGroup>
@@ -121,7 +121,7 @@ In this section, you'll find detailed examples that help you select, configure,
    ```toml Code
    # Required
    OPENAI_API_KEY=sk-...
-
+    
    # Optional
    OPENAI_API_BASE=<custom-base-url>
    OPENAI_ORGANIZATION=<your-org-id>
@@ -158,11 +158,7 @@ In this section, you'll find detailed examples that help you select, configure,

  <Accordion title="Anthropic">
    ```toml Code
-    # Required
    ANTHROPIC_API_KEY=sk-ant-...
-
-    # Optional
-    ANTHROPIC_API_BASE=<custom-base-url>
    ```

    Example usage in your CrewAI project:
@@ -226,7 +222,7 @@ In this section, you'll find detailed examples that help you select, configure,
    AZURE_API_KEY=<your-api-key>
    AZURE_API_BASE=<your-resource-url>
    AZURE_API_VERSION=<api-version>
-
+    
    # Optional
    AZURE_AD_TOKEN=<your-azure-ad-token>
    AZURE_API_TYPE=<your-azure-api-type>
@@ -254,42 +250,8 @@ In this section, you'll find detailed examples that help you select, configure,
        model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
    )
    ```
-
-    Before using Amazon Bedrock, make sure you have boto3 installed in your environment
-
-    [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-regions.html) is a managed service that provides access to multiple foundation models from top AI companies through a unified API, enabling secure and responsible AI application development.
-
-    | Model                   | Context Window       | Best For                                                          |
-    |-------------------------|----------------------|-------------------------------------------------------------------|
-    | Amazon Nova Pro         | Up to 300k tokens    | High-performance, model balancing accuracy, speed, and cost-effectiveness across diverse tasks. |
-    | Amazon Nova Micro       | Up to 128k tokens    | High-performance, cost-effective text-only model optimized for lowest latency responses. |
-    | Amazon Nova Lite        | Up to 300k tokens    | High-performance, affordable multimodal processing for images, video, and text with real-time capabilities. |
-    | Claude 3.7 Sonnet       | Up to 128k tokens    | High-performance, best for complex reasoning, coding & AI agents |
-    | Claude 3.5 Sonnet v2    | Up to 200k tokens    | State-of-the-art model specialized in software engineering, agentic capabilities, and computer interaction at optimized cost. |
-    | Claude 3.5 Sonnet       | Up to 200k tokens    | High-performance model delivering superior intelligence and reasoning across diverse tasks with optimal speed-cost balance. |
-    | Claude 3.5 Haiku        | Up to 200k tokens    | Fast, compact multimodal model optimized for quick responses and seamless human-like interactions |
-    | Claude 3 Sonnet         | Up to 200k tokens    | Multimodal model balancing intelligence and speed for high-volume deployments. |
-    | Claude 3 Haiku          | Up to 200k tokens    | Compact, high-speed multimodal model optimized for quick responses and natural conversational interactions |
-    | Claude 3 Opus           | Up to 200k tokens    | Most advanced multimodal model exceling at complex tasks with human-like reasoning and superior contextual understanding. |
-    | Claude 2.1              | Up to 200k tokens    | Enhanced version with expanded context window, improved reliability, and reduced hallucinations for long-form and RAG applications |
-    | Claude                  | Up to 100k tokens    | Versatile model excelling in sophisticated dialogue, creative content, and precise instruction following. |
-    | Claude Instant          | Up to 100k tokens    | Fast, cost-effective model for everyday tasks like dialogue, analysis, summarization, and document Q&A |
-    | Llama 3.1 405B Instruct | Up to 128k tokens    | Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks. |
-    | Llama 3.1 70B Instruct  | Up to 128k tokens    | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
-    | Llama 3.1 8B Instruct   | Up to 128k tokens    | Advanced state-of-the-art model with language understanding, superior reasoning, and text generation. |
-    | Llama 3 70B Instruct    | Up to 8k tokens      | Powers complex conversations with superior contextual understanding, reasoning and text generation. |
-    | Llama 3 8B Instruct     | Up to 8k tokens      | Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation. |
-    | Titan Text G1 - Lite    | Up to 4k tokens      | Lightweight, cost-effective model optimized for English tasks and fine-tuning with focus on summarization and content generation. |
-    | Titan Text G1 - Express | Up to 8k tokens      | Versatile model for general language tasks, chat, and RAG applications with support for English and 100+ languages. |
-    | Cohere Command          | Up to 4k tokens      | Model specialized in following user commands and delivering practical enterprise solutions. |
-    | Jurassic-2 Mid          | Up to 8,191 tokens   | Cost-effective model balancing quality and affordability for diverse language tasks like Q&A, summarization, and content generation. |
-    | Jurassic-2 Ultra        | Up to 8,191 tokens   | Model for advanced text generation and comprehension, excelling in complex tasks like analysis and content creation. |
-    | Jamba-Instruct          | Up to 256k tokens    | Model with extended context window optimized for cost-effective text generation, summarization, and Q&A. |
-    | Mistral 7B Instruct     | Up to 32k tokens     | This LLM follows instructions, completes requests, and generates creative text. |
-    | Mistral 8x7B Instruct   | Up to 32k tokens     | An MOE LLM that follows instructions, completes requests, and generates creative text. |
-
  </Accordion>
-
+  
  <Accordion title="Amazon SageMaker">
    ```toml Code
    AWS_ACCESS_KEY_ID=<your-access-key>
@@ -406,46 +368,6 @@ In this section, you'll find detailed examples that help you select, configure,
    | baichuan-inc/baichuan2-13b-chat                                  | 4,096 tokens   | Support Chinese and English chat, coding, math, instruction following, solving quizzes |
  </Accordion>

-  <Accordion title="Local NVIDIA NIM Deployed using WSL2">
-    
-    NVIDIA NIM enables you to run powerful LLMs locally on your Windows machine using WSL2 (Windows Subsystem for Linux). 
-    This approach allows you to leverage your NVIDIA GPU for private, secure, and cost-effective AI inference without relying on cloud services. 
-    Perfect for development, testing, or production scenarios where data privacy or offline capabilities are required.
-    
-    Here is a step-by-step guide to setting up a local NVIDIA NIM model:
-    
-    1. Follow installation instructions from [NVIDIA Website](https://docs.nvidia.com/nim/wsl2/latest/getting-started.html)
-
-    2. Install the local model. For Llama 3.1-8b follow [instructions](https://build.nvidia.com/meta/llama-3_1-8b-instruct/deploy)
-
-    3. Configure your crewai local models:
-  
-    ```python Code
-    from crewai.llm import LLM
-
-    local_nvidia_nim_llm = LLM(
-        model="openai/meta/llama-3.1-8b-instruct", # it's an openai-api compatible model
-        base_url="http://localhost:8000/v1",
-        api_key="<your_api_key|any text if you have not configured it>", # api_key is required, but you can use any text
-    )
-
-    # Then you can use it in your crew:
-
-    @CrewBase
-    class MyCrew():
-        # ...
-
-        @agent
-        def researcher(self) -> Agent:
-            return Agent(
-                config=self.agents_config['researcher'],
-                llm=local_nvidia_nim_llm
-            )
-        
-        # ...
-    ```
-  </Accordion>
-
  <Accordion title="Groq">
    Set the following environment variables in your `.env` file:

@@ -474,7 +396,7 @@ In this section, you'll find detailed examples that help you select, configure,
    WATSONX_URL=<your-url>
    WATSONX_APIKEY=<your-apikey>
    WATSONX_PROJECT_ID=<your-project-id>
-
+    
    # Optional
    WATSONX_TOKEN=<your-token>
    WATSONX_DEPLOYMENT_SPACE_ID=<your-space-id>
@@ -491,7 +413,7 @@ In this section, you'll find detailed examples that help you select, configure,

  <Accordion title="Ollama (Local LLMs)">
    1. Install Ollama: [ollama.ai](https://ollama.ai/)
-    2. Run a model: `ollama run llama3`
+    2. Run a model: `ollama run llama2`
    3. Configure:

    ```python Code
@@ -600,7 +522,7 @@ In this section, you'll find detailed examples that help you select, configure,
    ```toml Code
    OPENROUTER_API_KEY=<your-api-key>
    ```
-
+    
    Example usage in your CrewAI project:
    ```python Code
    llm = LLM(
@@ -723,7 +645,7 @@ Learn how to get the most out of your LLM configuration:
        - Small tasks (up to 4K tokens): Standard models
        - Medium tasks (between 4K-32K): Enhanced models
        - Large tasks (over 32K): Large context models
-
+        
        ```python
        # Configure model with appropriate settings
        llm = LLM(
@@ -760,11 +682,11 @@ Learn how to get the most out of your LLM configuration:
    <Warning>
      Most authentication issues can be resolved by checking API key format and environment variable names.
    </Warning>
-
+    
    ```bash
    # OpenAI
    OPENAI_API_KEY=sk-...
-
+    
    # Anthropic
    ANTHROPIC_API_KEY=sk-ant-...
    ```
@@ -773,11 +695,11 @@ Learn how to get the most out of your LLM configuration:
    <Check>
      Always include the provider prefix in model names
    </Check>
-
+    
    ```python
    # Correct
    llm = LLM(model="openai/gpt-4")
-
+    
    # Incorrect
    llm = LLM(model="gpt-4")
    ```
@@ -787,9 +709,4 @@ Learn how to get the most out of your LLM configuration:
      Use larger context models for extensive tasks
    </Tip>
    
-    ```python
-    # Large context model
-    llm = LLM(model="openai/gpt-4o")  # 128K tokens
    ```
-  </Tab>
-</Tabs>
--- a/docs/concepts/memory.mdx
+++ b/docs/concepts/memory.mdx
@@ -60,8 +60,7 @@ my_crew = Crew(
 ```python Code
 from crewai import Crew, Process
 from crewai.memory import LongTermMemory, ShortTermMemory, EntityMemory
-from crewai.memory.storage.rag_storage import RAGStorage
-from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
+from crewai.memory.storage import LTMSQLiteStorage, RAGStorage
 from typing import List, Optional

 # Assemble your crew with memory capabilities
@@ -120,7 +119,7 @@ Example using environment variables:
 import os
 from crewai import Crew
 from crewai.memory import LongTermMemory
-from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
+from crewai.memory.storage import LTMSQLiteStorage

 # Configure storage path using environment variable
 storage_path = os.getenv("CREWAI_STORAGE_DIR", "./storage")
@@ -149,7 +148,7 @@ crew = Crew(memory=True)  # Uses default storage locations
 ```python
 from crewai import Crew
 from crewai.memory import LongTermMemory
-from crewai.memory.storage.ltm_sqlite_storage import LTMSQLiteStorage
+from crewai.memory.storage import LTMSQLiteStorage

 # Configure custom storage paths
 crew = Crew(
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -1,223 +0,0 @@
-{
-  "$schema": "https://mintlify.com/docs.json",
-  "theme": "palm",
-  "name": "CrewAI",
-  "colors": {
-    "primary": "#EB6658",
-    "light": "#F3A78B",
-    "dark": "#C94C3C"
-  },
-  "favicon": "favicon.svg",
-  "navigation": {
-    "tabs": [
-      {
-        "tab": "Get Started",
-        "groups": [
-          {
-            "group": "Get Started",
-            "pages": [
-              "introduction",
-              "installation",
-              "quickstart",
-              "changelog"
-            ]
-          },
-          {
-            "group": "Guides",
-            "pages": [
-              {
-                "group": "Concepts",
-                "pages": [
-                  "guides/concepts/evaluating-use-cases"
-                ]
-              },
-              {
-                "group": "Agents",
-                "pages": [
-                  "guides/agents/crafting-effective-agents"
-                ]
-              },
-              {
-                "group": "Crews",
-                "pages": [
-                  "guides/crews/first-crew"
-                ]
-              },
-              {
-                "group": "Flows",
-                "pages": [
-                  "guides/flows/first-flow",
-                  "guides/flows/mastering-flow-state"
-                ]
-              },
-              {
-                "group": "Advanced",
-                "pages": [
-                  "guides/advanced/customizing-prompts",
-                  "guides/advanced/fingerprinting"
-                ]
-              }
-            ]
-          },
-          {
-            "group": "Core Concepts",
-            "pages": [
-              "concepts/agents",
-              "concepts/tasks",
-              "concepts/crews",
-              "concepts/flows",
-              "concepts/knowledge",
-              "concepts/llms",
-              "concepts/processes",
-              "concepts/collaboration",
-              "concepts/training",
-              "concepts/memory",
-              "concepts/planning",
-              "concepts/testing",
-              "concepts/cli",
-              "concepts/tools",
-              "concepts/event-listener",
-              "concepts/langchain-tools",
-              "concepts/llamaindex-tools"
-            ]
-          },
-          {
-            "group": "How to Guides",
-            "pages": [
-              "how-to/create-custom-tools",
-              "how-to/sequential-process",
-              "how-to/hierarchical-process",
-              "how-to/custom-manager-agent",
-              "how-to/llm-connections",
-              "how-to/customizing-agents",
-              "how-to/multimodal-agents",
-              "how-to/coding-agents",
-              "how-to/force-tool-output-as-result",
-              "how-to/human-input-on-execution",
-              "how-to/kickoff-async",
-              "how-to/kickoff-for-each",
-              "how-to/replay-tasks-from-latest-crew-kickoff",
-              "how-to/conditional-tasks",
-              "how-to/agentops-observability",
-              "how-to/langtrace-observability",
-              "how-to/mlflow-observability",
-              "how-to/openlit-observability",
-              "how-to/portkey-observability",
-              "how-to/langfuse-observability"
-            ]
-          },
-          {
-            "group": "Tools",
-            "pages": [
-              "tools/aimindtool",
-              "tools/apifyactorstool",
-              "tools/bravesearchtool",
-              "tools/browserbaseloadtool",
-              "tools/codedocssearchtool",
-              "tools/codeinterpretertool",
-              "tools/composiotool",
-              "tools/csvsearchtool",
-              "tools/dalletool",
-              "tools/directorysearchtool",
-              "tools/directoryreadtool",
-              "tools/docxsearchtool",
-              "tools/exasearchtool",
-              "tools/filereadtool",
-              "tools/filewritetool",
-              "tools/firecrawlcrawlwebsitetool",
-              "tools/firecrawlscrapewebsitetool",
-              "tools/firecrawlsearchtool",
-              "tools/githubsearchtool",
-              "tools/hyperbrowserloadtool",
-              "tools/linkupsearchtool",
-              "tools/llamaindextool",
-              "tools/serperdevtool",
-              "tools/s3readertool",
-              "tools/s3writertool",
-              "tools/scrapegraphscrapetool",
-              "tools/scrapeelementfromwebsitetool",
-              "tools/jsonsearchtool",
-              "tools/mdxsearchtool",
-              "tools/mysqltool",
-              "tools/multiontool",
-              "tools/nl2sqltool",
-              "tools/patronustools",
-              "tools/pdfsearchtool",
-              "tools/pgsearchtool",
-              "tools/qdrantvectorsearchtool",
-              "tools/ragtool",
-              "tools/scrapewebsitetool",
-              "tools/scrapflyscrapetool",
-              "tools/seleniumscrapingtool",
-              "tools/snowflakesearchtool",
-              "tools/spidertool",
-              "tools/txtsearchtool",
-              "tools/visiontool",
-              "tools/weaviatevectorsearchtool",
-              "tools/websitesearchtool",
-              "tools/xmlsearchtool",
-              "tools/youtubechannelsearchtool",
-              "tools/youtubevideosearchtool"
-            ]
-          },
-          {
-            "group": "Telemetry",
-            "pages": [
-              "telemetry"
-            ]
-          }
-        ]
-      },
-      {
-        "tab": "Examples",
-        "groups": [
-          {
-            "group": "Examples",
-            "pages": [
-              "examples/example"
-            ]
-          }
-        ]
-      }
-    ],
-    "global": {
-      "anchors": [
-        {
-          "anchor": "Community",
-          "href": "https://community.crewai.com",
-          "icon": "discourse"
-        }
-      ]
-    }
-  },
-  "logo": {
-    "light": "crew_only_logo.png",
-    "dark": "crew_only_logo.png"
-  },
-  "appearance": {
-    "default": "dark",
-    "strict": false
-  },
-  "navbar": {
-    "primary": {
-      "type": "github",
-      "href": "https://github.com/crewAIInc/crewAI"
-    }
-  },
-  "search": {
-    "prompt": "Search CrewAI docs"
-  },
-  "seo": {
-    "indexing": "navigable"
-  },
-  "footer": {
-    "socials": {
-      "website": "https://crewai.com",
-      "x": "https://x.com/crewAIInc",
-      "github": "https://github.com/crewAIInc/crewAI",
-      "linkedin": "https://www.linkedin.com/company/crewai-inc",
-      "youtube": "https://youtube.com/@crewAIInc",
-      "reddit": "https://www.reddit.com/r/crewAIInc/"
-    }
-  }
-}
--- a/docs/guides/advanced/customizing-prompts.mdx
+++ b/docs/guides/advanced/customizing-prompts.mdx
@@ -1,5 +1,4 @@
---
-title: Customizing Prompts
+---title: Customizing Prompts
 description: Dive deeper into low-level prompt customization for CrewAI, enabling super custom and complex use cases for different models and languages.
 icon: message-pen
 ---
--- a/docs/mint.json
+++ b/docs/mint.json
@@ -0,0 +1,225 @@
+{
+  "name": "CrewAI",
+  "theme": "venus",
+  "logo": {
+    "dark": "crew_only_logo.png",
+    "light": "crew_only_logo.png"
+  },
+  "favicon": "favicon.svg",
+  "colors": {
+    "primary": "#EB6658",
+    "light": "#F3A78B",
+    "dark": "#C94C3C",
+    "anchors": {
+      "from": "#737373",
+      "to": "#EB6658"
+    }
+  },
+  "seo": {
+    "indexHiddenPages": false
+  },
+  "modeToggle": {
+    "default": "dark",
+    "isHidden": false
+  },
+  "feedback": {
+    "suggestEdit": true,
+    "raiseIssue": true,
+    "thumbsRating": true
+  },
+  "topbarCtaButton": {
+    "type": "github",
+    "url": "https://github.com/crewAIInc/crewAI"
+  },
+  "primaryTab": {
+    "name": "Get Started"
+  },
+  "tabs": [
+    {
+      "name": "Examples",
+      "url": "examples"
+    }
+  ],
+  "anchors": [
+    {
+      "name": "Community",
+      "icon": "discourse",
+      "url": "https://community.crewai.com"
+    },
+    {
+      "name": "Changelog",
+      "icon": "timeline",
+      "url": "https://github.com/crewAIInc/crewAI/releases"
+    }
+  ],
+  "navigation": [
+    {
+      "group": "Get Started",
+      "pages": [
+        "introduction",
+        "installation",
+        "quickstart"
+      ]
+    },
+    {
+      "group": "Guides",
+      "pages": [
+        {
+          "group": "Concepts",
+          "pages": [
+            "guides/concepts/evaluating-use-cases"
+          ]
+        },
+        {
+          "group": "Agents",
+          "pages": [
+            "guides/agents/crafting-effective-agents"
+          ]
+        },
+        {
+          "group": "Crews",
+          "pages": [
+            "guides/crews/first-crew"
+          ]
+        },
+        {
+          "group": "Flows",
+          "pages": [
+            "guides/flows/first-flow",
+            "guides/flows/mastering-flow-state"
+          ]
+        },
+        {
+          "group": "Advanced",
+          "pages": [
+            "guides/advanced/customizing-prompts",
+            "guides/advanced/fingerprinting"
+          ]
+        }
+      ]
+    },
+    {
+      "group": "Core Concepts",
+      "pages": [
+        "concepts/agents",
+        "concepts/tasks",
+        "concepts/crews",
+        "concepts/flows",
+        "concepts/knowledge",
+        "concepts/llms",
+        "concepts/processes",
+        "concepts/collaboration",
+        "concepts/training",
+        "concepts/memory",
+        "concepts/planning",
+        "concepts/testing",
+        "concepts/cli",
+        "concepts/tools",
+        "concepts/event-listener",
+        "concepts/langchain-tools",
+        "concepts/llamaindex-tools"
+      ]
+    },
+    {
+      "group": "How to Guides",
+      "pages": [
+        "how-to/create-custom-tools",
+        "how-to/sequential-process",
+        "how-to/hierarchical-process",
+        "how-to/custom-manager-agent",
+        "how-to/llm-connections",
+        "how-to/customizing-agents",
+        "how-to/multimodal-agents",
+        "how-to/coding-agents",
+        "how-to/force-tool-output-as-result",
+        "how-to/human-input-on-execution",
+        "how-to/kickoff-async",
+        "how-to/kickoff-for-each",
+        "how-to/replay-tasks-from-latest-crew-kickoff",
+        "how-to/conditional-tasks",
+        "how-to/agentops-observability",
+        "how-to/langtrace-observability",
+        "how-to/mlflow-observability",
+        "how-to/openlit-observability",
+        "how-to/portkey-observability",
+        "how-to/langfuse-observability"
+      ]
+    },
+    {
+      "group": "Examples",
+      "pages": [
+        "examples/example"
+      ]
+    },
+    {
+      "group": "Tools",
+      "pages": [
+        "tools/aimindtool",
+        "tools/apifyactorstool",
+        "tools/bravesearchtool",
+        "tools/browserbaseloadtool",
+        "tools/codedocssearchtool",
+        "tools/codeinterpretertool",
+        "tools/composiotool",
+        "tools/csvsearchtool",
+        "tools/dalletool",
+        "tools/directorysearchtool",
+        "tools/directoryreadtool",
+        "tools/docxsearchtool",
+        "tools/exasearchtool",
+        "tools/filereadtool",
+        "tools/filewritetool",
+        "tools/firecrawlcrawlwebsitetool",
+        "tools/firecrawlscrapewebsitetool",
+        "tools/firecrawlsearchtool",
+        "tools/githubsearchtool",
+        "tools/hyperbrowserloadtool",
+        "tools/linkupsearchtool",
+        "tools/llamaindextool",
+        "tools/serperdevtool",
+        "tools/s3readertool",
+        "tools/s3writertool",
+        "tools/scrapegraphscrapetool",
+        "tools/scrapeelementfromwebsitetool",
+        "tools/jsonsearchtool",
+        "tools/mdxsearchtool",
+        "tools/mysqltool",
+        "tools/multiontool",
+        "tools/nl2sqltool",
+        "tools/patronustools",
+        "tools/pdfsearchtool",
+        "tools/pgsearchtool",
+        "tools/qdrantvectorsearchtool",
+        "tools/ragtool",
+        "tools/scrapewebsitetool",
+        "tools/scrapflyscrapetool",
+        "tools/seleniumscrapingtool",
+        "tools/snowflakesearchtool",
+        "tools/spidertool",
+        "tools/txtsearchtool",
+        "tools/visiontool",
+        "tools/weaviatevectorsearchtool",
+        "tools/websitesearchtool",
+        "tools/xmlsearchtool",
+        "tools/youtubechannelsearchtool",
+        "tools/youtubevideosearchtool"
+      ]
+    },
+    {
+      "group": "Telemetry",
+      "pages": [
+        "telemetry"
+      ]
+    }
+  ],
+  "search": {
+    "prompt": "Search CrewAI docs"
+  },
+  "footerSocials": {
+    "website": "https://crewai.com",
+    "x": "https://x.com/crewAIInc",
+    "github": "https://github.com/crewAIInc/crewAI",
+    "linkedin": "https://www.linkedin.com/company/crewai-inc",
+    "youtube": "https://youtube.com/@crewAIInc"
+  }
+}
--- a/docs/quickstart.mdx
+++ b/docs/quickstart.mdx
@@ -300,7 +300,7 @@ email_summarizer:
 ```

 <Tip>
-  Note how we use the same name for the task in the `tasks.yaml` (`email_summarizer_task`) file as the method name in the `crew.py` (`email_summarizer_task`) file.
+  Note how we use the same name for the agent in the `tasks.yaml` (`email_summarizer_task`) file as the method name in the `crew.py` (`email_summarizer_task`) file.
 </Tip>

 ```yaml tasks.yaml
--- a/docs/tools/jsonsearchtool.mdx
+++ b/docs/tools/jsonsearchtool.mdx
@@ -7,10 +7,8 @@ icon: file-code
 # `JSONSearchTool`

 <Note>
-  The JSONSearchTool is currently in an experimental phase. This means the tool
-  is under active development, and users might encounter unexpected behavior or
-  changes. We highly encourage feedback on any issues or suggestions for
-  improvements.
+    The JSONSearchTool is currently in an experimental phase. This means the tool is under active development, and users might encounter unexpected behavior or changes. 
+    We highly encourage feedback on any issues or suggestions for improvements.
 </Note>

 ## Description
@@ -62,7 +60,7 @@ tool = JSONSearchTool(
                # stream=true,
            },
        },
-        "embedding_model": {
+        "embedder": {
            "provider": "google", # or openai, ollama, ...
            "config": {
                "model": "models/embedding-001",
@@ -72,4 +70,4 @@ tool = JSONSearchTool(
        },
    }
 )
-```
+```
--- a/docs/tools/ragtool.mdx
+++ b/docs/tools/ragtool.mdx
@@ -8,8 +8,8 @@ icon: vector-square

 ## Description

-The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through EmbedChain.
-It provides a dynamic knowledge base that can be queried to retrieve relevant information from various data sources.
+The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through EmbedChain. 
+It provides a dynamic knowledge base that can be queried to retrieve relevant information from various data sources. 
 This tool is particularly useful for applications that require access to a vast array of information and need to provide contextually relevant answers.

 ## Example
@@ -138,7 +138,7 @@ config = {
            "model": "gpt-4",
        }
    },
-    "embedding_model": {
+    "embedder": {
        "provider": "openai",
        "config": {
            "model": "text-embedding-ada-002"
@@ -151,4 +151,4 @@ rag_tool = RagTool(config=config, summarize=True)

 ## Conclusion

-The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses.
+The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses. 
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -17,9 +17,9 @@ dependencies = [
    "pdfplumber>=0.11.4",
    "regex>=2024.9.11",
    # Telemetry and Monitoring
-    "opentelemetry-api>=1.30.0",
-    "opentelemetry-sdk>=1.30.0",
-    "opentelemetry-exporter-otlp-proto-http>=1.30.0",
+    "opentelemetry-api>=1.22.0",
+    "opentelemetry-sdk>=1.22.0",
+    "opentelemetry-exporter-otlp-proto-http>=1.22.0",
    # Data Handling
    "chromadb>=0.5.23",
    "openpyxl>=3.1.5",
--- a/src/crewai/agents/parser.py
+++ b/src/crewai/agents/parser.py
@@ -124,9 +124,9 @@ class CrewAgentParser:
            )

    def _extract_thought(self, text: str) -> str:
-        thought_index = text.find("\nAction")
+        thought_index = text.find("\n\nAction")
        if thought_index == -1:
-            thought_index = text.find("\nFinal Answer")
+            thought_index = text.find("\n\nFinal Answer")
        if thought_index == -1:
            return ""
        thought = text[:thought_index].strip()
@@ -136,7 +136,7 @@ class CrewAgentParser:

    def _clean_action(self, text: str) -> str:
        """Clean action string by removing non-essential formatting characters."""
-        return text.strip().strip("*").strip()
+        return re.sub(r"^\s*\*+\s*|\s*\*+\s*$", "", text).strip()

    def _safe_repair_json(self, tool_input: str) -> str:
        UNABLE_TO_REPAIR_JSON_RESULTS = ['""', "{}"]
--- a/src/crewai/cli/git.py
+++ b/src/crewai/cli/git.py
@@ -1,5 +1,4 @@
 import subprocess
-from functools import lru_cache


 class Repository:
@@ -36,7 +35,6 @@ class Repository:
            encoding="utf-8",
        ).strip()

-    @lru_cache(maxsize=None)
    def is_git_repo(self) -> bool:
        """Check if the current directory is a git repository."""
        try:
--- a/src/crewai/cli/templates/flow/pyproject.toml
+++ b/src/crewai/cli/templates/flow/pyproject.toml
@@ -10,7 +10,6 @@ dependencies = [

 [project.scripts]
 kickoff = "{{folder_name}}.main:kickoff"
-run_crew = "{{folder_name}}.main:kickoff"
 plot = "{{folder_name}}.main:plot"

 [build-system]
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -1,4 +1,5 @@
 import asyncio
+import concurrent.futures
 import json
 import re
 import uuid
@@ -6,7 +7,7 @@ import warnings
 from concurrent.futures import Future
 from copy import copy as shallow_copy
 from hashlib import md5
-from typing import Any, Callable, Dict, List, Optional, Set, Tuple, Union
+from typing import Any, Callable, Dict, List, Optional, Sequence, Set, Tuple, Union

 from pydantic import (
    UUID4,
@@ -707,6 +708,65 @@ class Crew(BaseModel):
        self.usage_metrics = total_usage_metrics
        self._task_output_handler.reset()
        return results
+        
+    def kickoff_for_each_parallel(self, inputs: Sequence[Dict[str, Any]], max_workers: Optional[int] = None) -> List[CrewOutput]:
+        """Executes the Crew's workflow for each input in the list in parallel using ThreadPoolExecutor.
+        
+        Args:
+            inputs: Sequence of input dictionaries to be passed to each crew execution.
+            max_workers: Maximum number of worker threads to use. If None, uses the default
+                        ThreadPoolExecutor behavior (typically min(32, os.cpu_count() + 4)).
+        
+        Returns:
+            List of CrewOutput objects, one for each input.
+        """
+        from concurrent.futures import ThreadPoolExecutor, as_completed
+        
+        if not isinstance(inputs, (list, tuple)):
+            raise TypeError(f"Inputs must be a list of dictionaries. Received {type(inputs).__name__} instead.")
+        
+        if not inputs:
+            return []
+        
+        results: List[CrewOutput] = []
+        
+        # Initialize the parent crew's usage metrics
+        total_usage_metrics = UsageMetrics()
+        
+        # Create a copy of the crew for each input to avoid state conflicts
+        crew_copies = [self.copy() for _ in inputs]
+        
+        # Execute each crew in parallel
+        try:
+            with ThreadPoolExecutor(max_workers=max_workers) as executor:
+                # Submit all tasks to the executor
+                future_to_crew = {
+                    executor.submit(crew_copies[i].kickoff, inputs[i]): i 
+                    for i in range(len(inputs))
+                }
+                
+                # Process results as they complete
+                for future in as_completed(future_to_crew):
+                    crew_index = future_to_crew[future]
+                    try:
+                        output = future.result()
+                        results.append(output)
+                        
+                        # Aggregate usage metrics
+                        if crew_copies[crew_index].usage_metrics:
+                            total_usage_metrics.add_usage_metrics(crew_copies[crew_index].usage_metrics)
+                    except Exception as exc:
+                        # Re-raise the exception to maintain consistent behavior with kickoff_for_each
+                        raise exc
+        finally:
+            # Clean up to assist garbage collection
+            crew_copies.clear()
+        
+        # Set the aggregated metrics on the parent crew
+        self.usage_metrics = total_usage_metrics
+        self._task_output_handler.reset()
+        
+        return results

    def _handle_crew_planning(self):
        """Handles the Crew planning."""
--- a/src/crewai/llm.py
+++ b/src/crewai/llm.py
@@ -114,60 +114,6 @@ LLM_CONTEXT_WINDOW_SIZES = {
    "Llama-3.2-11B-Vision-Instruct": 16384,
    "Meta-Llama-3.2-3B-Instruct": 4096,
    "Meta-Llama-3.2-1B-Instruct": 16384,
-    # bedrock
-    "us.amazon.nova-pro-v1:0": 300000,
-    "us.amazon.nova-micro-v1:0": 128000,
-    "us.amazon.nova-lite-v1:0": 300000,
-    "us.anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
-    "us.anthropic.claude-3-5-haiku-20241022-v1:0": 200000,
-    "us.anthropic.claude-3-5-sonnet-20241022-v2:0": 200000,
-    "us.anthropic.claude-3-7-sonnet-20250219-v1:0": 200000,
-    "us.anthropic.claude-3-sonnet-20240229-v1:0": 200000,
-    "us.anthropic.claude-3-opus-20240229-v1:0": 200000,
-    "us.anthropic.claude-3-haiku-20240307-v1:0": 200000,
-    "us.meta.llama3-2-11b-instruct-v1:0": 128000,
-    "us.meta.llama3-2-3b-instruct-v1:0": 131000,
-    "us.meta.llama3-2-90b-instruct-v1:0": 128000,
-    "us.meta.llama3-2-1b-instruct-v1:0": 131000,
-    "us.meta.llama3-1-8b-instruct-v1:0": 128000,
-    "us.meta.llama3-1-70b-instruct-v1:0": 128000,
-    "us.meta.llama3-3-70b-instruct-v1:0": 128000,
-    "us.meta.llama3-1-405b-instruct-v1:0": 128000,
-    "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
-    "eu.anthropic.claude-3-sonnet-20240229-v1:0": 200000,
-    "eu.anthropic.claude-3-haiku-20240307-v1:0": 200000,
-    "eu.meta.llama3-2-3b-instruct-v1:0": 131000,
-    "eu.meta.llama3-2-1b-instruct-v1:0": 131000,
-    "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
-    "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": 200000,
-    "apac.anthropic.claude-3-sonnet-20240229-v1:0": 200000,
-    "apac.anthropic.claude-3-haiku-20240307-v1:0": 200000,
-    "amazon.nova-pro-v1:0": 300000,
-    "amazon.nova-micro-v1:0": 128000,
-    "amazon.nova-lite-v1:0": 300000,
-    "anthropic.claude-3-5-sonnet-20240620-v1:0": 200000,
-    "anthropic.claude-3-5-haiku-20241022-v1:0": 200000,
-    "anthropic.claude-3-5-sonnet-20241022-v2:0": 200000,
-    "anthropic.claude-3-7-sonnet-20250219-v1:0": 200000,
-    "anthropic.claude-3-sonnet-20240229-v1:0": 200000,
-    "anthropic.claude-3-opus-20240229-v1:0": 200000,
-    "anthropic.claude-3-haiku-20240307-v1:0": 200000,
-    "anthropic.claude-v2:1": 200000,
-    "anthropic.claude-v2": 100000,
-    "anthropic.claude-instant-v1": 100000,
-    "meta.llama3-1-405b-instruct-v1:0": 128000,
-    "meta.llama3-1-70b-instruct-v1:0": 128000,
-    "meta.llama3-1-8b-instruct-v1:0": 128000,
-    "meta.llama3-70b-instruct-v1:0": 8000,
-    "meta.llama3-8b-instruct-v1:0": 8000,
-    "amazon.titan-text-lite-v1": 4000,
-    "amazon.titan-text-express-v1": 8000,
-    "cohere.command-text-v14": 4000,
-    "ai21.j2-mid-v1": 8191,
-    "ai21.j2-ultra-v1": 8191,
-    "ai21.jamba-instruct-v1:0": 256000,
-    "mistral.mistral-7b-instruct-v0:2": 32000,
-    "mistral.mixtral-8x7b-instruct-v0:1": 32000,
    # mistral
    "mistral-tiny": 32768,
    "mistral-small-latest": 32768,
--- a/src/crewai/memory/storage/mem0_storage.py
+++ b/src/crewai/memory/storage/mem0_storage.py
@@ -1,7 +1,7 @@
 import os
 from typing import Any, Dict, List

-from mem0 import Memory, MemoryClient
+from mem0 import MemoryClient

 from crewai.memory.storage.interface import Storage

@@ -32,16 +32,13 @@ class Mem0Storage(Storage):
        mem0_org_id = config.get("org_id")
        mem0_project_id = config.get("project_id")

-        # Initialize MemoryClient or Memory based on the presence of the mem0_api_key
-        if mem0_api_key:
-            if mem0_org_id and mem0_project_id:
-                self.memory = MemoryClient(
-                    api_key=mem0_api_key, org_id=mem0_org_id, project_id=mem0_project_id
-                )
-            else:
-                self.memory = MemoryClient(api_key=mem0_api_key)
+        # Initialize MemoryClient with available parameters
+        if mem0_org_id and mem0_project_id:
+            self.memory = MemoryClient(
+                api_key=mem0_api_key, org_id=mem0_org_id, project_id=mem0_project_id
+            )
        else:
-            self.memory = Memory()  # Fallback to Memory if no Mem0 API key is provided
+            self.memory = MemoryClient(api_key=mem0_api_key)

    def _sanitize_role(self, role: str) -> str:
        """
--- a/src/crewai/task.py
+++ b/src/crewai/task.py
@@ -19,8 +19,6 @@ from typing import (
    Tuple,
    Type,
    Union,
-    get_args,
-    get_origin,
 )

 from pydantic import (
@@ -180,29 +178,15 @@ class Task(BaseModel):
        """
        if v is not None:
            sig = inspect.signature(v)
-            positional_args = [
-                param
-                for param in sig.parameters.values()
-                if param.default is inspect.Parameter.empty
-            ]
-            if len(positional_args) != 1:
+            if len(sig.parameters) != 1:
                raise ValueError("Guardrail function must accept exactly one parameter")

            # Check return annotation if present, but don't require it
            return_annotation = sig.return_annotation
            if return_annotation != inspect.Signature.empty:
-
-                return_annotation_args = get_args(return_annotation)
                if not (
-                    get_origin(return_annotation) is tuple
-                    and len(return_annotation_args) == 2
-                    and return_annotation_args[0] is bool
-                    and (
-                        return_annotation_args[1] is Any
-                        or return_annotation_args[1] is str
-                        or return_annotation_args[1] is TaskOutput
-                        or return_annotation_args[1] == Union[str, TaskOutput]
-                    )
+                    return_annotation == Tuple[bool, Any]
+                    or str(return_annotation) == "Tuple[bool, Any]"
                ):
                    raise ValueError(
                        "If return type is annotated, it must be Tuple[bool, Any]"
--- a/src/crewai/telemetry/telemetry.py
+++ b/src/crewai/telemetry/telemetry.py
@@ -281,16 +281,8 @@ class Telemetry:
        return self._safe_telemetry_operation(operation)

    def task_ended(self, span: Span, task: Task, crew: Crew):
-        """Records the completion of a task execution in a crew.
+        """Records task execution in a crew."""

-        Args:
-            span (Span): The OpenTelemetry span tracking the task execution
-            task (Task): The task that was completed
-            crew (Crew): The crew context in which the task was executed
-
-        Note:
-            If share_crew is enabled, this will also record the task output
-        """
        def operation():
            if crew.share_crew:
                self._add_attribute(
@@ -305,13 +297,8 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def tool_repeated_usage(self, llm: Any, tool_name: str, attempts: int):
-        """Records when a tool is used repeatedly, which might indicate an issue.
+        """Records the repeated usage 'error' of a tool by an agent."""

-        Args:
-            llm (Any): The language model being used
-            tool_name (str): Name of the tool being repeatedly used
-            attempts (int): Number of attempts made with this tool
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Tool Repeated Usage")
@@ -330,13 +317,8 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def tool_usage(self, llm: Any, tool_name: str, attempts: int):
-        """Records the usage of a tool by an agent.
+        """Records the usage of a tool by an agent."""

-        Args:
-            llm (Any): The language model being used
-            tool_name (str): Name of the tool being used
-            attempts (int): Number of attempts made with this tool
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Tool Usage")
@@ -355,11 +337,8 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def tool_usage_error(self, llm: Any):
-        """Records when a tool usage results in an error.
+        """Records the usage of a tool by an agent."""

-        Args:
-            llm (Any): The language model being used when the error occurred
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Tool Usage Error")
@@ -378,14 +357,6 @@ class Telemetry:
    def individual_test_result_span(
        self, crew: Crew, quality: float, exec_time: int, model_name: str
    ):
-        """Records individual test results for a crew execution.
-
-        Args:
-            crew (Crew): The crew being tested
-            quality (float): Quality score of the execution
-            exec_time (int): Execution time in seconds
-            model_name (str): Name of the model used
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Crew Individual Test Result")
@@ -412,14 +383,6 @@ class Telemetry:
        inputs: dict[str, Any] | None,
        model_name: str,
    ):
-        """Records the execution of a test suite for a crew.
-
-        Args:
-            crew (Crew): The crew being tested
-            iterations (int): Number of test iterations
-            inputs (dict[str, Any] | None): Input parameters for the test
-            model_name (str): Name of the model used in testing
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Crew Test Execution")
@@ -445,7 +408,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def deploy_signup_error_span(self):
-        """Records when an error occurs during the deployment signup process."""
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Deploy Signup Error")
@@ -455,11 +417,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def start_deployment_span(self, uuid: Optional[str] = None):
-        """Records the start of a deployment process.
-
-        Args:
-            uuid (Optional[str]): Unique identifier for the deployment
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Start Deployment")
@@ -471,7 +428,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def create_crew_deployment_span(self):
-        """Records the creation of a new crew deployment."""
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Create Crew Deployment")
@@ -481,12 +437,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def get_crew_logs_span(self, uuid: Optional[str], log_type: str = "deployment"):
-        """Records the retrieval of crew logs.
-
-        Args:
-            uuid (Optional[str]): Unique identifier for the crew
-            log_type (str, optional): Type of logs being retrieved. Defaults to "deployment".
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Get Crew Logs")
@@ -499,11 +449,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def remove_crew_span(self, uuid: Optional[str] = None):
-        """Records the removal of a crew.
-
-        Args:
-            uuid (Optional[str]): Unique identifier for the crew being removed
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Remove Crew")
@@ -629,11 +574,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def flow_creation_span(self, flow_name: str):
-        """Records the creation of a new flow.
-
-        Args:
-            flow_name (str): Name of the flow being created
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Flow Creation")
@@ -644,12 +584,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def flow_plotting_span(self, flow_name: str, node_names: list[str]):
-        """Records flow visualization/plotting activity.
-
-        Args:
-            flow_name (str): Name of the flow being plotted
-            node_names (list[str]): List of node names in the flow
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Flow Plotting")
@@ -661,12 +595,6 @@ class Telemetry:
        self._safe_telemetry_operation(operation)

    def flow_execution_span(self, flow_name: str, node_names: list[str]):
-        """Records the execution of a flow.
-
-        Args:
-            flow_name (str): Name of the flow being executed
-            node_names (list[str]): List of nodes being executed in the flow
-        """
        def operation():
            tracer = trace.get_tracer("crewai.telemetry")
            span = tracer.start_span("Flow Execution")
--- a/src/crewai/tools/tool_usage.py
+++ b/src/crewai/tools/tool_usage.py
@@ -244,7 +244,6 @@ class ToolUsage:
            tool_calling=calling,
            from_cache=from_cache,
            started_at=started_at,
-            result=result,  # Pass the result
        )

        if (
@@ -456,7 +455,7 @@ class ToolUsage:

        # Attempt 4: Repair JSON
        try:
-            repaired_input = repair_json(tool_input, skip_json_loads=True)
+            repaired_input = repair_json(tool_input)
            self._printer.print(
                content=f"Repaired JSON: {repaired_input}", color="blue"
            )
@@ -493,18 +492,8 @@ class ToolUsage:
        crewai_event_bus.emit(self, ToolUsageErrorEvent(**{**event_data, "error": e}))

    def on_tool_use_finished(
-        self, tool: Any, tool_calling: ToolCalling, from_cache: bool, started_at: float, 
-        result: Any = None
+        self, tool: Any, tool_calling: ToolCalling, from_cache: bool, started_at: float
    ) -> None:
-        """Handle tool usage completion event.
-        
-        Args:
-            tool: The tool that was used
-            tool_calling: The tool calling information
-            from_cache: Whether the result was retrieved from cache
-            started_at: Timestamp when the tool execution started
-            result: The execution result of the tool
-        """
        finished_at = time.time()
        event_data = self._prepare_event_data(tool, tool_calling)
        event_data.update(
@@ -512,7 +501,6 @@ class ToolUsage:
                "started_at": datetime.datetime.fromtimestamp(started_at),
                "finished_at": datetime.datetime.fromtimestamp(finished_at),
                "from_cache": from_cache,
-                "result": result,  # Tool execution result
            }
        )
        crewai_event_bus.emit(self, ToolUsageFinishedEvent(**event_data))
--- a/src/crewai/utilities/events/crewai_event_bus.py
+++ b/src/crewai/utilities/events/crewai_event_bus.py
@@ -67,13 +67,16 @@ class CrewAIEventsBus:
            source: The object emitting the event
            event: The event instance to emit
        """
-        for event_type, handlers in self._handlers.items():
-            if isinstance(event, event_type):
-                for handler in handlers:
-                    handler(source, event)
-
+        event_type = type(event)
+        if event_type in self._handlers:
+            for handler in self._handlers[event_type]:
+                handler(source, event)
        self._signal.send(source, event=event)

+    def clear_handlers(self) -> None:
+        """Clear all registered event handlers - useful for testing"""
+        self._handlers.clear()
+
    def register_handler(
        self, event_type: Type[EventTypes], handler: Callable[[Any, EventTypes], None]
    ) -> None:
--- a/src/crewai/utilities/events/tool_usage_events.py
+++ b/src/crewai/utilities/events/tool_usage_events.py
@@ -1,5 +1,5 @@
 from datetime import datetime
-from typing import Any, Callable, Dict, Optional, Union
+from typing import Any, Callable, Dict

 from .base_events import CrewEvent

@@ -25,16 +25,11 @@ class ToolUsageStartedEvent(ToolUsageEvent):


 class ToolUsageFinishedEvent(ToolUsageEvent):
-    """Event emitted when a tool execution is completed
-    
-    This event contains the result of the tool execution, allowing listeners
-    to access the output directly without implementing workarounds.
-    """
+    """Event emitted when a tool execution is completed"""

    started_at: datetime
    finished_at: datetime
    from_cache: bool = False
-    result: Any = None  # Tool execution result
    type: str = "tool_usage_finished"


--- a/src/crewai/utilities/planning_handler.py
+++ b/src/crewai/utilities/planning_handler.py
@@ -96,10 +96,6 @@ class CrewPlanner:
        tasks_summary = []
        for idx, task in enumerate(self.tasks):
            knowledge_list = self._get_agent_knowledge(task)
-            agent_tools = (
-                f"[{', '.join(str(tool) for tool in task.agent.tools)}]" if task.agent and task.agent.tools else '"agent has no tools"',
-                f',\n                "agent_knowledge": "[\\"{knowledge_list[0]}\\"]"' if knowledge_list and str(knowledge_list) != "None" else ""
-            )
            task_summary = f"""
                Task Number {idx + 1} - {task.description}
                "task_description": {task.description}
@@ -107,7 +103,10 @@ class CrewPlanner:
                "agent": {task.agent.role if task.agent else "None"}
                "agent_goal": {task.agent.goal if task.agent else "None"}
                "task_tools": {task.tools}
-                "agent_tools": {"".join(agent_tools)}"""
+                "agent_tools": %s%s""" % (
+                    f"[{', '.join(str(tool) for tool in task.agent.tools)}]" if task.agent and task.agent.tools else '"agent has no tools"',
+                    f',\n                "agent_knowledge": "[\\"{knowledge_list[0]}\\"]"' if knowledge_list and str(knowledge_list) != "None" else ""
+                )

            tasks_summary.append(task_summary)
        return " ".join(tasks_summary)
--- a/tests/cassettes/test_kickoff_for_each_parallel_max_workers.yaml
+++ b/tests/cassettes/test_kickoff_for_each_parallel_max_workers.yaml
@@ -0,0 +1,254 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are dog Researcher. You
+      have a lot of experience with dog.\nYour personal goal is: Express hot takes
+      on dog.\nTo give my best complete final answer to the task respond using 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!"},
+      {"role": "user", "content": "\nCurrent Task: Give me an analysis around dog.\n\nThis
+      is the expected criteria for your final answer: 1 bullet point about dog that''s
+      under 15 words.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '914'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-proj-********************************************************************************************************************************************************sLcA.
+      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 922e88ad5d8d2805-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:49 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_9f1aa8c42b31f8139e80f67a71b11af3
+    http_version: HTTP/1.1
+    status_code: 401
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
+      You have a lot of experience with apple.\nYour personal goal is: Express hot
+      takes on apple.\nTo give my best complete final answer to the task respond using
+      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!"}, {"role": "user", "content": "\nCurrent Task: Give me an analysis around
+      apple.\n\nThis is the expected criteria for your final answer: 1 bullet point
+      about apple that''s under 15 words.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\n\nBegin! This is VERY important to you,
+      use the tools available and give your best Final Answer, your job depends on
+      it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '924'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-proj-********************************************************************************************************************************************************sLcA.
+      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 922e88adcdfe2805-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:49 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_2a94d77754a61f5f38f74f0648bf38af
+    http_version: HTTP/1.1
+    status_code: 401
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are cat Researcher. You
+      have a lot of experience with cat.\nYour personal goal is: Express hot takes
+      on cat.\nTo give my best complete final answer to the task respond using 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!"},
+      {"role": "user", "content": "\nCurrent Task: Give me an analysis around cat.\n\nThis
+      is the expected criteria for your final answer: 1 bullet point about cat that''s
+      under 15 words.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '914'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-proj-********************************************************************************************************************************************************sLcA.
+      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 922e88adabe3f8d9-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:49 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_e06cdb71cffc47ee28b267ed083c3a6b
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1
--- a/tests/cassettes/test_kickoff_for_each_parallel_multiple_inputs.yaml
+++ b/tests/cassettes/test_kickoff_for_each_parallel_multiple_inputs.yaml
@@ -0,0 +1,254 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are dog Researcher. You
+      have a lot of experience with dog.\nYour personal goal is: Express hot takes
+      on dog.\nTo give my best complete final answer to the task respond using 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!"},
+      {"role": "user", "content": "\nCurrent Task: Give me an analysis around dog.\n\nThis
+      is the expected criteria for your final answer: 1 bullet point about dog that''s
+      under 15 words.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '914'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-proj-********************************************************************************************************************************************************sLcA.
+      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 922e88a8e9432805-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:48 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_d00f966d049ee99fde6e9e7bf652afa2
+    http_version: HTTP/1.1
+    status_code: 401
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are apple Researcher.
+      You have a lot of experience with apple.\nYour personal goal is: Express hot
+      takes on apple.\nTo give my best complete final answer to the task respond using
+      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!"}, {"role": "user", "content": "\nCurrent Task: Give me an analysis around
+      apple.\n\nThis is the expected criteria for your final answer: 1 bullet point
+      about apple that''s under 15 words.\nyou MUST return the actual complete content
+      as the final answer, not a summary.\n\nBegin! This is VERY important to you,
+      use the tools available and give your best Final Answer, your job depends on
+      it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '924'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-proj-********************************************************************************************************************************************************sLcA.
+      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 922e88a91a59c4c8-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:48 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_6e9a5fd1d83c6eac8070b4e9b9b94f10
+    http_version: HTTP/1.1
+    status_code: 401
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are cat Researcher. You
+      have a lot of experience with cat.\nYour personal goal is: Express hot takes
+      on cat.\nTo give my best complete final answer to the task respond using 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!"},
+      {"role": "user", "content": "\nCurrent Task: Give me an analysis around cat.\n\nThis
+      is the expected criteria for your final answer: 1 bullet point about cat that''s
+      under 15 words.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '914'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - x64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - Linux
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
+      sk-proj-********************************************************************************************************************************************************sLcA.
+      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
+      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
+      \"invalid_api_key\"\n    }\n}\n"
+    headers:
+      CF-RAY:
+      - 922e88a91f2ef8d9-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:48 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      vary:
+      - Origin
+      x-request-id:
+      - req_d0ddaee2449c771a230de2b6362c8d99
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1
--- a/tests/utilities/cassettes/test_tools_emits_finished_events_with_string_result.yaml
+++ b/tests/utilities/cassettes/test_tools_emits_finished_events_with_string_result.yaml
@@ -1,21 +1,17 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
-      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
-      ONLY have access to the following tools, and should NEVER make up tools that
-      are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
-      Say hi\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
-      you should always think about what to do\nAction: the action to take, only one
-      name of [say_hi], just the name, exactly as it''s written.\nAction Input: the
-      input to the action, just a simple JSON object, enclosed in curly braces, using
-      \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
-      all necessary information is gathered, return the following format:\n\n```\nThought:
-      I now know the final answer\nFinal Answer: the final answer to the original
-      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Just say
-      hi\n\nThis is the expected criteria for your final answer: hi\nyou MUST return
-      the actual complete content as the final answer, not a summary.\n\nBegin! This
-      is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    body: '{"messages": [{"role": "system", "content": "You are dog Researcher. You
+      have a lot of experience with dog.\nYour personal goal is: Express hot takes
+      on dog.\nTo give my best complete final answer to the task respond using 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!"},
+      {"role": "user", "content": "\nCurrent Task: Give me an analysis around dog.\n\nThis
+      is the expected criteria for your final answer: 1 bullet point about dog that''s
+      under 15 words.\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
@@ -24,7 +20,7 @@ interactions:
      connection:
      - keep-alive
      content-length:
-      - '1277'
+      - '914'
      content-type:
      - application/json
      host:
@@ -59,7 +55,7 @@ interactions:
      \"invalid_api_key\"\n    }\n}\n"
    headers:
      CF-RAY:
-      - 9241c014df27b9d9-SEA
+      - 922e88a1b9ef2805-SEA
      Connection:
      - keep-alive
      Content-Length:
@@ -67,14 +63,14 @@ interactions:
      Content-Type:
      - application/json; charset=utf-8
      Date:
-      - Sat, 22 Mar 2025 01:00:07 GMT
+      - Wed, 19 Mar 2025 17:01:47 GMT
      Server:
      - cloudflare
      Set-Cookie:
-      - __cf_bm=KV5GuGyEdKrxlT_rqmqKhQ9TUxeMz_ccZ5K3Xu.mfLc-1742605207-1.0.1.1-1aSRm5P8hBtB3zVmHWH3LcYPoXvhsezGomR1uazQeGCEWL_uUIGP1x3dMkviSWrjf88WKm1snQNn.Eyy8_qewmd7NT7lqUt0MgRWVgfCOAY;
-        path=/; expires=Sat, 22-Mar-25 01:30:07 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=xOCSjxqrC.2f2I2kISNioXWWErqIIGNKPkTsoEzcVRY-1742403707-1.0.1.1-bG9XNEXc7EBBNdNl9ff975bzPeeXgfmzAyYN1AesFIuQ2gEcmP67jHmnN6ABv.JJVDhw9oF5SREuZ3PUkYA8Xu6UQeWnIQxKi10X_40KN38;
+        path=/; expires=Wed, 19-Mar-25 17:31:47 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
-      - _cfuvid=1KExsJlCZ0R2Kp3gV2Y71_SiQ0R2D9rAbONnmJq7tjk-1742605207873-0.0.1.1-604800000;
+      - _cfuvid=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      X-Content-Type-Options:
      - nosniff
@@ -87,7 +83,7 @@ interactions:
      vary:
      - Origin
      x-request-id:
-      - req_b2233dbbb60c3ebb5717c05ec5150588
+      - req_5980db57b01be333b0f977bb03a15bca
    http_version: HTTP/1.1
    status_code: 401
 version: 1
--- a/tests/task_test.py
+++ b/tests/task_test.py
@@ -3,8 +3,6 @@
 import hashlib
 import json
 import os
-from functools import partial
-from typing import Tuple, Union
 from unittest.mock import MagicMock, patch

 import pytest
@@ -217,75 +215,6 @@ def test_multiple_output_type_error():
        )


-def test_guardrail_type_error():
-    desc = "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting."
-    expected_output = "Bullet point list of 5 interesting ideas."
-    # Lambda function
-    Task(
-        description=desc,
-        expected_output=expected_output,
-        guardrail=lambda x: (True, x),
-    )
-
-    # Function
-    def guardrail_fn(x: TaskOutput) -> tuple[bool, TaskOutput]:
-        return (True, x)
-
-    Task(
-        description=desc,
-        expected_output=expected_output,
-        guardrail=guardrail_fn,
-    )
-
-    class Object:
-        def guardrail_fn(self, x: TaskOutput) -> tuple[bool, TaskOutput]:
-            return (True, x)
-
-        @classmethod
-        def guardrail_class_fn(cls, x: TaskOutput) -> tuple[bool, str]:
-            return (True, x)
-
-        @staticmethod
-        def guardrail_static_fn(x: TaskOutput) -> tuple[bool, Union[str, TaskOutput]]:
-            return (True, x)
-
-    obj = Object()
-    # Method
-    Task(
-        description=desc,
-        expected_output=expected_output,
-        guardrail=obj.guardrail_fn,
-    )
-    # Class method
-    Task(
-        description=desc,
-        expected_output=expected_output,
-        guardrail=Object.guardrail_class_fn,
-    )
-    # Static method
-    Task(
-        description=desc,
-        expected_output=expected_output,
-        guardrail=Object.guardrail_static_fn,
-    )
-
-    def error_fn(x: TaskOutput, y: bool) -> Tuple[bool, TaskOutput]:
-        return (y, x)
-
-    Task(
-        description=desc,
-        expected_output=expected_output,
-        guardrail=partial(error_fn, y=True),
-    )
-
-    with pytest.raises(ValidationError):
-        Task(
-            description=desc,
-            expected_output=expected_output,
-            guardrail=error_fn,
-        )
-
-
@pytest.mark.vcr(filter_headers=["authorization"])
 def test_output_pydantic_sequential():
    class ScoreOutput(BaseModel):
--- a/tests/test_kickoff_for_each_parallel.py
+++ b/tests/test_kickoff_for_each_parallel.py
@@ -0,0 +1,209 @@
+"""Test for the kickoff_for_each_parallel method in Crew class."""
+
+import concurrent.futures
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from crewai.agent import Agent
+from crewai.crew import Crew
+from crewai.crews.crew_output import CrewOutput
+from crewai.task import Task
+
+
+def test_kickoff_for_each_parallel_single_input():
+    """Tests if kickoff_for_each_parallel works with a single input."""
+    
+    inputs = [{"topic": "dog"}]
+    
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+    
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    
+    # Mock the kickoff method to avoid API calls
+    expected_output = CrewOutput(raw="Dogs are loyal companions.")
+    with patch.object(Crew, "kickoff", return_value=expected_output):
+        results = crew.kickoff_for_each_parallel(inputs=inputs)
+        
+        assert len(results) == 1
+        assert results[0].raw == "Dogs are loyal companions."
+
+
+def test_kickoff_for_each_parallel_multiple_inputs():
+    """Tests if kickoff_for_each_parallel works with multiple inputs."""
+    
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+    
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+    
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    
+    # Mock the kickoff method to avoid API calls
+    expected_outputs = [
+        CrewOutput(raw="Dogs are loyal companions."),
+        CrewOutput(raw="Cats are independent pets."),
+        CrewOutput(raw="Apples are nutritious fruits."),
+    ]
+    
+    with patch.object(Crew, "copy") as mock_copy:
+        # Setup mock crew copies
+        crew_copies = []
+        for i in range(len(inputs)):
+            crew_copy = MagicMock()
+            crew_copy.kickoff.return_value = expected_outputs[i]
+            crew_copies.append(crew_copy)
+        mock_copy.side_effect = crew_copies
+        
+        results = crew.kickoff_for_each_parallel(inputs=inputs)
+        
+        assert len(results) == len(inputs)
+        # Since ThreadPoolExecutor returns results in completion order, not input order,
+        # we just check that all expected outputs are in the results
+        result_texts = [result.raw for result in results]
+        expected_texts = [output.raw for output in expected_outputs]
+        for expected_text in expected_texts:
+            assert expected_text in result_texts
+
+
+def test_kickoff_for_each_parallel_empty_input():
+    """Tests if kickoff_for_each_parallel handles an empty input list."""
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+    
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    results = crew.kickoff_for_each_parallel(inputs=[])
+    assert results == []
+
+
+def test_kickoff_for_each_parallel_invalid_input():
+    """Tests if kickoff_for_each_parallel raises TypeError for invalid input types."""
+    
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+    
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    
+    # No need to mock here since we're testing input validation which happens before any API calls
+    with pytest.raises(TypeError):
+        # Pass a string instead of a list
+        crew.kickoff_for_each_parallel("invalid input")
+
+
+def test_kickoff_for_each_parallel_error_handling():
+    """Tests error handling in kickoff_for_each_parallel when kickoff raises an error."""
+    
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+    
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+    
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    
+    with patch.object(Crew, "copy") as mock_copy:
+        # Setup mock crew copies
+        crew_copies = []
+        for i in range(len(inputs)):
+            crew_copy = MagicMock()
+            # Make the third crew copy raise an exception
+            if i == 2:
+                crew_copy.kickoff.side_effect = Exception("Simulated kickoff error")
+            else:
+                crew_copy.kickoff.return_value = f"Output for {inputs[i]['topic']}"
+            crew_copies.append(crew_copy)
+        mock_copy.side_effect = crew_copies
+        
+        with pytest.raises(Exception, match="Simulated kickoff error"):
+            crew.kickoff_for_each_parallel(inputs=inputs)
+
+
+def test_kickoff_for_each_parallel_max_workers():
+    """Tests if kickoff_for_each_parallel respects the max_workers parameter."""
+    
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+    
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+    
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    
+    # Mock both ThreadPoolExecutor and crew.copy to avoid API calls
+    with patch.object(concurrent.futures, "ThreadPoolExecutor", wraps=concurrent.futures.ThreadPoolExecutor) as mock_executor:
+        with patch.object(Crew, "copy") as mock_copy:
+            # Setup mock crew copies
+            crew_copies = []
+            for _ in range(len(inputs)):
+                crew_copy = MagicMock()
+                crew_copy.kickoff.return_value = CrewOutput(raw="Test output")
+                crew_copies.append(crew_copy)
+            mock_copy.side_effect = crew_copies
+            
+            crew.kickoff_for_each_parallel(inputs=inputs, max_workers=2)
+            mock_executor.assert_called_once_with(max_workers=2)
--- a/tests/utilities/cassettes/test_tools_emits_finished_events_with_dict_result.yaml
+++ b/tests/utilities/cassettes/test_tools_emits_finished_events_with_dict_result.yaml
@@ -1,92 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
-      a helpful assistant that returns structured data\nYour personal goal is: Return
-      a dictionary result\nYou ONLY have access to the following tools, and should
-      NEVER make up tools that are not listed here:\n\nTool Name: dict_result\nTool
-      Arguments: {}\nTool Description: Return a dictionary result\n\nIMPORTANT: Use
-      the following format in your response:\n\n```\nThought: you should always think
-      about what to do\nAction: the action to take, only one name of [dict_result],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
-      values.\nObservation: the result of the action\n```\n\nOnce all necessary information
-      is gathered, return the following format:\n\n```\nThought: I now know the final
-      answer\nFinal Answer: the final answer to the original input question\n```"},
-      {"role": "user", "content": "\nCurrent Task: Return a dictionary result\n\nThis
-      is the expected criteria for your final answer: Dictionary with message and
-      data\nyou MUST return the actual complete content as the final answer, not a
-      summary.\n\nBegin! This is VERY important to you, use the tools available and
-      give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
-      "gpt-4o-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1378'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=KV5GuGyEdKrxlT_rqmqKhQ9TUxeMz_ccZ5K3Xu.mfLc-1742605207-1.0.1.1-1aSRm5P8hBtB3zVmHWH3LcYPoXvhsezGomR1uazQeGCEWL_uUIGP1x3dMkviSWrjf88WKm1snQNn.Eyy8_qewmd7NT7lqUt0MgRWVgfCOAY;
-        _cfuvid=1KExsJlCZ0R2Kp3gV2Y71_SiQ0R2D9rAbONnmJq7tjk-1742605207873-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 9241c01b0df3b9d9-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Sat, 22 Mar 2025 01:00:08 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_d0eae92c72f0f64514d32384a7f27a9a
-    http_version: HTTP/1.1
-    status_code: 401
-version: 1
--- a/tests/utilities/cassettes/test_tools_emits_finished_events_with_none_result.yaml
+++ b/tests/utilities/cassettes/test_tools_emits_finished_events_with_none_result.yaml
@@ -1,91 +0,0 @@
-interactions:
- request:
-    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
-      a helpful assistant that returns None\nYour personal goal is: Return None as
-      result\nYou ONLY have access to the following tools, and should NEVER make up
-      tools that are not listed here:\n\nTool Name: none_result\nTool Arguments: {}\nTool
-      Description: Return None as result\n\nIMPORTANT: Use the following format in
-      your response:\n\n```\nThought: you should always think about what to do\nAction:
-      the action to take, only one name of [none_result], just the name, exactly as
-      it''s written.\nAction Input: the input to the action, just a simple JSON object,
-      enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
-      result of the action\n```\n\nOnce all necessary information is gathered, return
-      the following format:\n\n```\nThought: I now know the final answer\nFinal Answer:
-      the final answer to the original input question\n```"}, {"role": "user", "content":
-      "\nCurrent Task: Return None as result\n\nThis is the expected criteria for
-      your final answer: None\nyou MUST return the actual complete content as the
-      final answer, not a summary.\n\nBegin! This is VERY important to you, use the
-      tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],
-      "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '1324'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=KV5GuGyEdKrxlT_rqmqKhQ9TUxeMz_ccZ5K3Xu.mfLc-1742605207-1.0.1.1-1aSRm5P8hBtB3zVmHWH3LcYPoXvhsezGomR1uazQeGCEWL_uUIGP1x3dMkviSWrjf88WKm1snQNn.Eyy8_qewmd7NT7lqUt0MgRWVgfCOAY;
-        _cfuvid=1KExsJlCZ0R2Kp3gV2Y71_SiQ0R2D9rAbONnmJq7tjk-1742605207873-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.61.0
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.61.0
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n    \"error\": {\n        \"message\": \"Incorrect API key provided:
-      sk-proj-********************************************************************************************************************************************************sLcA.
-      You can find your API key at https://platform.openai.com/account/api-keys.\",\n
-      \       \"type\": \"invalid_request_error\",\n        \"param\": null,\n        \"code\":
-      \"invalid_api_key\"\n    }\n}\n"
-    headers:
-      CF-RAY:
-      - 9241c01eea3db9d9-SEA
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '414'
-      Content-Type:
-      - application/json; charset=utf-8
-      Date:
-      - Sat, 22 Mar 2025 01:00:09 GMT
-      Server:
-      - cloudflare
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      cf-cache-status:
-      - DYNAMIC
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      vary:
-      - Origin
-      x-request-id:
-      - req_00b89378d512de492b7c90876d0e3c8a
-    http_version: HTTP/1.1
-    status_code: 401
-version: 1
--- a/tests/utilities/events/test_crewai_event_bus.py
+++ b/tests/utilities/events/test_crewai_event_bus.py
@@ -1,34 +0,0 @@
-from unittest.mock import Mock
-
-from crewai.utilities.events.base_events import CrewEvent
-from crewai.utilities.events.crewai_event_bus import crewai_event_bus
-
-
-class TestEvent(CrewEvent):
-    pass
-
-
-def test_specific_event_handler():
-    mock_handler = Mock()
-
-    @crewai_event_bus.on(TestEvent)
-    def handler(source, event):
-        mock_handler(source, event)
-
-    event = TestEvent(type="test_event")
-    crewai_event_bus.emit("source_object", event)
-
-    mock_handler.assert_called_once_with("source_object", event)
-
-
-def test_wildcard_event_handler():
-    mock_handler = Mock()
-
-    @crewai_event_bus.on(CrewEvent)
-    def handler(source, event):
-        mock_handler(source, event)
-
-    event = TestEvent(type="test_event")
-    crewai_event_bus.emit("source_object", event)
-
-    mock_handler.assert_called_once_with("source_object", event)
--- a/tests/utilities/test_events.py
+++ b/tests/utilities/test_events.py
@@ -12,7 +12,6 @@ from crewai.flow.flow import Flow, listen, start
 from crewai.llm import LLM
 from crewai.task import Task
 from crewai.tools.base_tool import BaseTool
-from crewai.tools.tool_calling import ToolCalling
 from crewai.utilities.events.agent_events import (
    AgentExecutionCompletedEvent,
    AgentExecutionErrorEvent,
@@ -330,137 +329,35 @@ class SayHiTool(BaseTool):
        return "hi"


-class DictResultTool(BaseTool):
-    name: str = Field(default="dict_result", description="The name of the tool")
-    description: str = Field(
-        default="Return a dictionary result", 
-        description="The description of the tool"
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_tools_emits_finished_events():
+    received_events = []
+
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def handle_tool_end(source, event):
+        received_events.append(event)
+
+    agent = Agent(
+        role="base_agent",
+        goal="Just say hi",
+        backstory="You are a helpful assistant that just says hi",
+        tools=[SayHiTool()],
    )

-    def _run(self) -> dict:
-        return {"message": "success", "data": {"value": 42}}
-
-
-class NoneResultTool(BaseTool):
-    name: str = Field(default="none_result", description="The name of the tool")
-    description: str = Field(
-        default="Return None as result", 
-        description="The description of the tool"
+    task = Task(
+        description="Just say hi",
+        expected_output="hi",
+        agent=agent,
    )
-
-    def _run(self) -> None:
-        return None
-
-
-def test_tools_emits_finished_events_with_string_result():
-    received_events = []
-
-    @crewai_event_bus.on(ToolUsageFinishedEvent)
-    def handle_tool_end(source, event):
-        received_events.append(event)
-
-    # Create a mock event with string result
-    tool = SayHiTool()
-    tool_calling = ToolCalling(tool_name=tool.name, arguments={}, log="")
-    event_data = {
-        "agent_key": "test_agent_key",
-        "agent_role": "test_agent_role",
-        "tool_name": tool.name,
-        "tool_args": {},
-        "tool_class": tool.__class__.__name__,
-        "started_at": datetime.now(),
-        "finished_at": datetime.now(),
-        "from_cache": False,
-        "result": "hi"
-    }
-    
-    # Emit the event
-    crewai_event_bus.emit(None, ToolUsageFinishedEvent(**event_data))
-    
-    # Verify the event was received with the correct result
+    crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
+    crew.kickoff()
    assert len(received_events) == 1
-    assert received_events[0].agent_key == "test_agent_key"
-    assert received_events[0].agent_role == "test_agent_role"
-    assert received_events[0].tool_name == tool.name
+    assert received_events[0].agent_key == agent.key
+    assert received_events[0].agent_role == agent.role
+    assert received_events[0].tool_name == SayHiTool().name
    assert received_events[0].tool_args == {}
    assert received_events[0].type == "tool_usage_finished"
    assert isinstance(received_events[0].timestamp, datetime)
-    assert received_events[0].result == "hi"
-
-
-def test_tools_emits_finished_events_with_dict_result():
-    received_events = []
-
-    @crewai_event_bus.on(ToolUsageFinishedEvent)
-    def handle_tool_end(source, event):
-        received_events.append(event)
-
-    # Create a mock event with dictionary result
-    tool = DictResultTool()
-    tool_calling = ToolCalling(tool_name=tool.name, arguments={}, log="")
-    dict_result = {"message": "success", "data": {"value": 42}}
-    event_data = {
-        "agent_key": "test_agent_key",
-        "agent_role": "test_agent_role",
-        "tool_name": tool.name,
-        "tool_args": {},
-        "tool_class": tool.__class__.__name__,
-        "started_at": datetime.now(),
-        "finished_at": datetime.now(),
-        "from_cache": False,
-        "result": dict_result
-    }
-    
-    # Emit the event
-    crewai_event_bus.emit(None, ToolUsageFinishedEvent(**event_data))
-    
-    # Verify the event was received with the correct result
-    assert len(received_events) == 1
-    assert received_events[0].agent_key == "test_agent_key"
-    assert received_events[0].agent_role == "test_agent_role"
-    assert received_events[0].tool_name == tool.name
-    assert received_events[0].tool_args == {}
-    assert received_events[0].type == "tool_usage_finished"
-    assert isinstance(received_events[0].timestamp, datetime)
-    assert isinstance(received_events[0].result, dict)
-    assert received_events[0].result["message"] == "success"
-    assert received_events[0].result["data"]["value"] == 42
-
-
-def test_tools_emits_finished_events_with_none_result():
-    received_events = []
-
-    @crewai_event_bus.on(ToolUsageFinishedEvent)
-    def handle_tool_end(source, event):
-        received_events.append(event)
-
-    # Create a mock event with None result
-    tool = NoneResultTool()
-    tool_calling = ToolCalling(tool_name=tool.name, arguments={}, log="")
-    event_data = {
-        "agent_key": "test_agent_key",
-        "agent_role": "test_agent_role",
-        "tool_name": tool.name,
-        "tool_args": {},
-        "tool_class": tool.__class__.__name__,
-        "started_at": datetime.now(),
-        "finished_at": datetime.now(),
-        "from_cache": False,
-        "result": None
-    }
-    
-    # Emit the event
-    crewai_event_bus.emit(None, ToolUsageFinishedEvent(**event_data))
-    
-    # Verify the event was received with the correct result
-    assert len(received_events) == 1
-    assert received_events[0].agent_key == "test_agent_key"
-    assert received_events[0].agent_role == "test_agent_role"
-    assert received_events[0].tool_name == tool.name
-    assert received_events[0].tool_args == {}
-    assert received_events[0].type == "tool_usage_finished"
-    assert isinstance(received_events[0].timestamp, datetime)
-    assert received_events[0].result is None


@pytest.mark.vcr(filter_headers=["authorization"])
Author	SHA1	Message	Date
Devin AI	d58a24950c	Fix import sorting in test_kickoff_for_each_parallel.py Co-Authored-By: Joe Moura <joao@crewai.com>	2025-03-19 17:12:18 +00:00
Devin AI	15d59cfc34	Improve kickoff_for_each_parallel based on PR feedback Co-Authored-By: Joe Moura <joao@crewai.com>	2025-03-19 17:12:09 +00:00
Devin AI	fd18bdfabb	Add test cassettes for kickoff_for_each_parallel tests Co-Authored-By: Joe Moura <joao@crewai.com>	2025-03-19 17:05:25 +00:00
Devin AI	c77ac31db6	Add kickoff_for_each_parallel method using ThreadPoolExecutor to fix issue #2406 Co-Authored-By: Joe Moura <joao@crewai.com>	2025-03-19 17:05:14 +00:00