Fix import sorting in test_kickoff_for_each_parallel.py

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

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."""

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

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

tests/cassettes/test_kickoff_for_each_parallel_single_input.yaml

@@ -0,0 +1,89 @@
+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
+      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:
+      - 922e88a1b9ef2805-SEA
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '414'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 19 Mar 2025 17:01:47 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __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=RypiiyRYeZ0ZoVTLFkoT3v1Yzk.qiNfGEnh9gk4.bYg-1742403707485-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      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_5980db57b01be333b0f977bb03a15bca
+    http_version: HTTP/1.1
+    status_code: 401
+version: 1

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)