Merge branch 'main' into lg-allow-remove-stop

This commit adds a new crew field called parent_flow, evaluated when the Crew
instance is instantiated. The stacktrace is traversed to look up if the caller
is an instance of Flow, and if so, it fills in the field.

Other alternatives were considered, such as a global context or even a new
field to be manually filled, however, this is the most magical solution that
was thread-safe and did not require public API changes.

src/crewai/cli/reset_memories_command.py

@@ -2,7 +2,7 @@ import subprocess
 
 import click
 
-from crewai.cli.utils import get_crew
+from crewai.cli.utils import get_crews
 
 
 def reset_memories_command(
@@ -26,35 +26,47 @@ def reset_memories_command(
     """
 
     try:
-        crew = get_crew()
-        if not crew:
-            raise ValueError("No crew found.")
-        if all:
-            crew.reset_memories(command_type="all")
-            click.echo("All memories have been reset.")
-            return
-
-        if not any([long, short, entity, kickoff_outputs, knowledge]):
+        if not any([long, short, entity, kickoff_outputs, knowledge, all]):
             click.echo(
                 "No memory type specified. Please specify at least one type to reset."
             )
             return
 
-        if long:
-            crew.reset_memories(command_type="long")
-            click.echo("Long term memory has been reset.")
-        if short:
-            crew.reset_memories(command_type="short")
-            click.echo("Short term memory has been reset.")
-        if entity:
-            crew.reset_memories(command_type="entity")
-            click.echo("Entity memory has been reset.")
-        if kickoff_outputs:
-            crew.reset_memories(command_type="kickoff_outputs")
-            click.echo("Latest Kickoff outputs stored has been reset.")
-        if knowledge:
-            crew.reset_memories(command_type="knowledge")
-            click.echo("Knowledge has been reset.")
+        crews = get_crews()
+        if not crews:
+            raise ValueError("No crew found.")
+        for crew in crews:
+            if all:
+                crew.reset_memories(command_type="all")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Reset memories command has been completed."
+                )
+                continue
+            if long:
+                crew.reset_memories(command_type="long")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Long term memory has been reset."
+                )
+            if short:
+                crew.reset_memories(command_type="short")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Short term memory has been reset."
+                )
+            if entity:
+                crew.reset_memories(command_type="entity")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Entity memory has been reset."
+                )
+            if kickoff_outputs:
+                crew.reset_memories(command_type="kickoff_outputs")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Latest Kickoff outputs stored has been reset."
+                )
+            if knowledge:
+                crew.reset_memories(command_type="knowledge")
+                click.echo(
+                    f"[Crew ({crew.name if crew.name else crew.id})] Knowledge has been reset."
+                )
 
     except subprocess.CalledProcessError as e:
         click.echo(f"An error occurred while resetting the memories: {e}", err=True)

src/crewai/cli/utils.py

@@ -2,7 +2,8 @@ import os
 import shutil
 import sys
 from functools import reduce
-from typing import Any, Dict, List
+from inspect import isfunction, ismethod
+from typing import Any, Dict, List, get_type_hints
 
 import click
 import tomli
@@ -10,6 +11,7 @@ from rich.console import Console
 
 from crewai.cli.constants import ENV_VARS
 from crewai.crew import Crew
+from crewai.flow import Flow
 
 if sys.version_info >= (3, 11):
     import tomllib
@@ -250,11 +252,11 @@ def write_env_file(folder_path, env_vars):
             file.write(f"{key}={value}\n")
 
 
-def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
-    """Get the crew instance from the crew.py file."""
+def get_crews(crew_path: str = "crew.py", require: bool = False) -> list[Crew]:
+    """Get the crew instances from the a file."""
+    crew_instances = []
     try:
         import importlib.util
-        import os
 
         for root, _, files in os.walk("."):
             if crew_path in files:
@@ -271,12 +273,10 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                         spec.loader.exec_module(module)
 
                         for attr_name in dir(module):
-                            attr = getattr(module, attr_name)
-                            try:
-                                if callable(attr) and hasattr(attr, "crew"):
-                                    crew_instance = attr().crew()
-                                    return crew_instance
+                            module_attr = getattr(module, attr_name)
 
+                            try:
+                                crew_instances.extend(fetch_crews(module_attr))
                             except Exception as e:
                                 print(f"Error processing attribute {attr_name}: {e}")
                                 continue
@@ -286,7 +286,6 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                         import traceback
 
                         print(f"Traceback: {traceback.format_exc()}")
-
                 except (ImportError, AttributeError) as e:
                     if require:
                         console.print(
@@ -300,7 +299,6 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
         if require:
             console.print("No valid Crew instance found in crew.py", style="bold red")
             raise SystemExit
-        return None
 
     except Exception as e:
         if require:
@@ -308,4 +306,36 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                 f"Unexpected error while loading crew: {str(e)}", style="bold red"
             )
             raise SystemExit
+    return crew_instances
+
+
+def get_crew_instance(module_attr) -> Crew | None:
+    if (
+        callable(module_attr)
+        and hasattr(module_attr, "is_crew_class")
+        and module_attr.is_crew_class
+    ):
+        return module_attr().crew()
+    if (ismethod(module_attr) or isfunction(module_attr)) and get_type_hints(
+        module_attr
+    ).get("return") is Crew:
+        return module_attr()
+    elif isinstance(module_attr, Crew):
+        return module_attr
+    else:
         return None
+
+
+def fetch_crews(module_attr) -> list[Crew]:
+    crew_instances: list[Crew] = []
+
+    if crew_instance := get_crew_instance(module_attr):
+        crew_instances.append(crew_instance)
+
+    if isinstance(module_attr, type) and issubclass(module_attr, Flow):
+        instance = module_attr()
+        for attr_name in dir(instance):
+            attr = getattr(instance, attr_name)
+            if crew_instance := get_crew_instance(attr):
+                crew_instances.append(crew_instance)
+    return crew_instances

src/crewai/crew.py

@@ -6,7 +6,17 @@ 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, cast
+from typing import (
+    Any,
+    Callable,
+    Dict,
+    List,
+    Optional,
+    Set,
+    Tuple,
+    Union,
+    cast,
+)
 
 from pydantic import (
     UUID4,
@@ -24,6 +34,7 @@ from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache import CacheHandler
 from crewai.crews.crew_output import CrewOutput
+from crewai.flow.flow_trackable import FlowTrackable
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.llm import LLM, BaseLLM
@@ -69,7 +80,7 @@ from crewai.utilities.training_handler import CrewTrainingHandler
 warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
 
-class Crew(BaseModel):
+class Crew(FlowTrackable, BaseModel):
     """
     Represents a group of agents, defining how they should collaborate and the tasks they should perform.
 
@@ -304,7 +315,9 @@ class Crew(BaseModel):
         """Initialize private memory attributes."""
         self._external_memory = (
             # External memory doesn’t support a default value since it was designed to be managed entirely externally
-            self.external_memory.set_crew(self) if self.external_memory else None
+            self.external_memory.set_crew(self)
+            if self.external_memory
+            else None
         )
 
         self._long_term_memory = self.long_term_memory
@@ -333,6 +346,7 @@ class Crew(BaseModel):
                         embedder=self.embedder,
                         collection_name="crew",
                     )
+                    self.knowledge.add_sources()
 
             except Exception as e:
                 self._logger.log(
@@ -1369,8 +1383,6 @@ class Crew(BaseModel):
             else:
                 self._reset_specific_memory(command_type)
 
-            self._logger.log("info", f"{command_type} memory has been reset")
-
         except Exception as e:
             error_msg = f"Failed to reset {command_type} memory: {str(e)}"
             self._logger.log("error", error_msg)
@@ -1391,8 +1403,14 @@ class Crew(BaseModel):
             if system is not None:
                 try:
                     system.reset()
+                    self._logger.log(
+                        "info",
+                        f"[Crew ({self.name if self.name else self.id})] {name} memory has been reset",
+                    )
                 except Exception as e:
-                    raise RuntimeError(f"Failed to reset {name} memory") from e
+                    raise RuntimeError(
+                        f"[Crew ({self.name if self.name else self.id})] Failed to reset {name} memory: {str(e)}"
+                    ) from e
 
     def _reset_specific_memory(self, memory_type: str) -> None:
         """Reset a specific memory system.
@@ -1421,5 +1439,11 @@ class Crew(BaseModel):
 
         try:
             memory_system.reset()
+            self._logger.log(
+                "info",
+                f"[Crew ({self.name if self.name else self.id})] {name} memory has been reset",
+            )
         except Exception as e:
-            raise RuntimeError(f"Failed to reset {name} memory") from e
+            raise RuntimeError(
+                f"[Crew ({self.name if self.name else self.id})] Failed to reset {name} memory: {str(e)}"
+            ) from e

src/crewai/flow/flow_trackable.py

@@ -0,0 +1,44 @@
+import inspect
+from typing import Optional
+
+from pydantic import BaseModel, Field, InstanceOf, model_validator
+
+from crewai.flow import Flow
+
+
+class FlowTrackable(BaseModel):
+    """Mixin that tracks the Flow instance that instantiated the object, e.g. a
+    Flow instance that created a Crew or Agent.
+
+    Automatically finds and stores a reference to the parent Flow instance by
+    inspecting the call stack.
+    """
+
+    parent_flow: Optional[InstanceOf[Flow]] = Field(
+        default=None,
+        description="The parent flow of the instance, if it was created inside a flow.",
+    )
+
+    @model_validator(mode="after")
+    def _set_parent_flow(self, max_depth: int = 5) -> "FlowTrackable":
+        frame = inspect.currentframe()
+
+        try:
+            if frame is None:
+                return self
+
+            frame = frame.f_back
+            for _ in range(max_depth):
+                if frame is None:
+                    break
+
+                candidate = frame.f_locals.get("self")
+                if isinstance(candidate, Flow):
+                    self.parent_flow = candidate
+                    break
+
+                frame = frame.f_back
+        finally:
+            del frame
+
+        return self

src/crewai/knowledge/knowledge.py

@@ -41,7 +41,6 @@ class Knowledge(BaseModel):
             )
         self.sources = sources
         self.storage.initialize_knowledge_storage()
-        self._add_sources()
 
     def query(
         self, query: List[str], results_limit: int = 3, score_threshold: float = 0.35
@@ -63,7 +62,7 @@ class Knowledge(BaseModel):
         )
         return results
 
-    def _add_sources(self):
+    def add_sources(self):
         try:
             for source in self.sources:
                 source.storage = self.storage

src/crewai/lite_agent.py

@@ -13,6 +13,7 @@ from crewai.agents.parser import (
     AgentFinish,
     OutputParserException,
 )
+from crewai.flow.flow_trackable import FlowTrackable
 from crewai.llm import LLM
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
@@ -80,7 +81,7 @@ class LiteAgentOutput(BaseModel):
         return self.raw
 
 
-class LiteAgent(BaseModel):
+class LiteAgent(FlowTrackable, BaseModel):
     """
     A lightweight agent that can process messages and use tools.
 
@@ -162,7 +163,7 @@ class LiteAgent(BaseModel):
     _messages: List[Dict[str, str]] = PrivateAttr(default_factory=list)
     _iterations: int = PrivateAttr(default=0)
     _printer: Printer = PrivateAttr(default_factory=Printer)
-    
+
     @model_validator(mode="after")
     def setup_llm(self):
         """Set up the LLM and other components after initialization."""

src/crewai/llm.py

@@ -245,6 +245,9 @@ class AccumulatedToolArgs(BaseModel):
     function: FunctionArgs = Field(default_factory=FunctionArgs)
 
 
+EMPTY = object()
+
+
 class LLM(BaseLLM):
     def __init__(
         self,
@@ -253,7 +256,7 @@ class LLM(BaseLLM):
         temperature: Optional[float] = None,
         top_p: Optional[float] = None,
         n: Optional[int] = None,
-        stop: Optional[Union[str, List[str]]] = None,
+        stop: Optional[Union[str, List[str], object, None]] = EMPTY,
         max_completion_tokens: Optional[int] = None,
         max_tokens: Optional[int] = None,
         presence_penalty: Optional[float] = None,
@@ -296,15 +299,16 @@ class LLM(BaseLLM):
         self.additional_params = kwargs
         self.is_anthropic = self._is_anthropic_model(model)
         self.stream = stream
-
         litellm.drop_params = True
 
         # Normalize self.stop to always be a List[str]
-        if stop is None:
-            self.stop: List[str] = []
+        if stop is EMPTY:
+            self.stop = []
+        elif stop is None:
+            self.stop = None
         elif isinstance(stop, str):
             self.stop = [stop]
-        else:
+        elif isinstance(stop, list):
             self.stop = stop
 
         self.set_callbacks(callbacks)

tests/cassettes/test_llm_testing_removing_stop_parameter.yaml

@@ -0,0 +1,512 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+      "model": "o3", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '111'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.10.16
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: "{\n  \"error\": {\n    \"message\": \"Unsupported parameter: 'stop'
+        is not supported with this model.\",\n    \"type\": \"invalid_request_error\",\n
+        \   \"param\": \"stop\",\n    \"code\": \"unsupported_parameter\"\n  }\n}"
+    headers:
+      CF-RAY:
+      - 939854b16c1b7e0a-GRU
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '196'
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 02 May 2025 14:50:25 GMT
+      Server:
+      - cloudflare
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '40'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999988'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8033d4a9265538858c4b2a8cc7d53fc7
+    status:
+      code: 400
+      message: Bad Request
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+      "model": "o3"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '99'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.10.16
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA3RWzW4bRwy++ymIPdmApFiy5NS6OS6cpoGDtE6bFnUgULPU7lSznA1nxms1CKB3
+        yClAcukT5BnyKHqSYmb1izSXxWJJfsOPHzncd0cAmc6zMWSqRK+q2nSf3Fanf1DTXD3/5Sb82VcX
+        fUd8PZ2b4e8vz7JOjLDTv0n5TVRP2ao25LXl1qyE0FNE7T8envcvHg8Ho2SobE4mhtmz7uB0MOqe
+        Drv983VQabUil43hryMAgHfpGdPjnB6yMZx2Nl8qcg4LysZbJ4BMrIlfMnROO4/ss87OqCx74pTx
+        M8gtr5YfPZR4T+BLApxqo/0CvIW3gWQBRt8TNIS+JIEcPXbAWXgGCttIT8bAwoYUTQ+o4qeqJkEf
+        hDrQaM7B1UR5B6yAMjbkoOw9CWiGW2S4FmSlnbKAHnypHVS2IvY9uLYCCLWQ0o46EOqut11fUrfS
+        HDzBzAopdD6ev1p+NAYaZB9zVyWpOSAIGY1TQ+BsEEXggioB3fiO73i1/BdeYJQKDbxeM7wludeK
+        4HhNuVfY+xOA1nvtFEWOXCLjTdxVicxkAOt6432pVFibO1u/3zgnKcQGbusRMaZBG9/VvC1zBLEM
+        lXUe6tIyuQ3mq5JgtfzkZqvlZ6hRzbEgqJCxIHFg9DyZG++lp/mRQ57MNtWNETOxFSBMxTaOJOlh
+        qwo5B6OZYlFel+hbdaGIykdltQOEt0GrORRB5xQL7Be1VmhAWc51rKGDCNPEcG+BHmpSPpX51drz
+        UOpNPV6i9yTs7rjfg1e7xhnDjTY5LAilm6rVg590UToILqAxC3DaxwaK9Qt1TQKjU9etdA7npw6+
+        frmG4/6w27+Ar1+uToDuiaO3C1UV1Wi0L8HYxh1CDNcQow3ED93+WULoRQEGsSOLcRJhhpUNDioU
+        zQQGFyRwvFp+eo5iEuK1LVbLzycg1ph0TFKzTQAqK6y5cI9iYvGlA+RqUjpR0ww/B6bV8sNlKILz
+        HZgT1ZqLOB1cOFDWmlTuQnABTNj2kbJxFppSGwLNJjqgELqk5jQ2P/MixQ1OE78GpSJJ3M568Ctq
+        bskJal6AI3SWo/piQ1GaBbyw91RNSVbLDzcoquzBbeLj4jlgZ54Yppapm8sioQ57cKOVWGV0hZ7c
+        GK52/aJK5ILAeSHycbLbt15K4UY7py1/m/rjdeqJZWR9G9iRhx+186KVj/nObFG03qNR9O7BpWlw
+        4WAqsYrIQA9esJUtJTrqwWvN+RguZ7EdreVIH6ZC9A85OO6PuoMRVHV5kqjGqbF8IBoamwQiaNCT
+        zMSyTynYtsOeWpMTw1P0BE9E5wX14nQ8m6URY6K81TCIEPv9uRJdlB7YNp3tGO6mdk7jO1ZBDGyG
+        /hZ5sp2zO44zHi/DSHy1/HQwhR24uozXgmZAXhxcP402ZncDYJyetElAqLbie/sbRWgWHMZlxsGY
+        PQMyW59u2LTL3qwt77fba6ZZu3IiqdPiRnLe1lmyvj8CeJO2YThYcFkttqr9xNs5Jdj+sIXLdqt3
+        Zzzvr1dl5q1Hs2cYbMIO8CY5edTG7e3TTKEqKd+F7pYvhlzbPcPRHrtv0/k/7Ja55mKPz8Xguwfs
+        DEpR7Smf1EK5Voekd25C8efke27bOqeUM9euvonXJFGLnGYYTPvvkLmF81RNZpoLklp0+oGIch+9
+        P/oPAAD//wMAuBpQTjoJAAA=
+    headers:
+      CF-RAY:
+      - 939854b31dda7e0a-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 02 May 2025 14:50:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '18374'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999988'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_444d8fb9f9d6ad89f75b28e7b0c95844
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+      "model": "o3-mini", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '116'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.10.16
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA3STz27bMAzG73kKQme7qJOmf3LrMAwoOuySrcMwFAYj0bEWWRQkOm1XFNhr7PX6
+        JIOdNHax9qKDfh8/UiT1OAFQ1qgFKF2j6Ca4/MOyKban16by5ve3+8v4EeVmc31TX3725ofKughe
+        /SItL1FHmpvgSCz7HdaRUKhzLc5OTouLs3lR9KBhQ64L41neWG/z6fF0nh8X+azYR9ZsNSW1gJ8T
+        AIDH/uxq9Ibu1QKOs5ebhlLCNanFQQSgIrvuRmFKNgl6UdkANXsh35d9BYb985+/AjVuCSKhy8U2
+        BAYFAbWmlDJIDFegcScMkbfWEEhNoNsYyQvcEUpN8Qi+MqxJoA25cG5QCDR7Y7uWJLAelujhU0Sv
+        bdKcQXCEiUDXpDeAILFNQubFDhLFrdUEzm7okENzk/XJv2Bniw6+7+XLvfyOVskKZcARHriNECJV
+        FOPIGUM4GrckUtUm7EbiW+dGAL1n6RP1w7jdk6dD+yvrbarLSJjYdy1NwkH19GkCcNuPs301IRUi
+        N0FK4Q31tsXJzk4NCzTA2Xmxp8KCbgQu5tkbfqUhQevSaCGURl2TGUKH7cHWWB6Byeh1/5fzlvfu
+        5davR5VN308wAK0pCJkyRDJWv370IIvUfbH3ZIc+9yWr/cKUYil2szBUYet2y6/SQxJqysr6NcUQ
+        7e4HVKE8X03PT85mK7NSk6fJPwAAAP//AwAuENFVCwQAAA==
+    headers:
+      CF-RAY:
+      - 939856cecf61f1cd-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 02 May 2025 14:51:54 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2897'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999987'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_978f3c657aa396dbd484126271a59372
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+      "model": "o3-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '104'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.10.16
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//dFNNb9swDL3nVxC6bAPsIJ9Nl9uGYlgu24AW6GEoAlpmbLWyJIhU26zo
+        fx9sJ3GKdRcd9MjHR/LxZQSgTKnWoHSNoptg86/XzYz2PyeVvrq8sH++J//M9Is296m42qiszfDF
+        PWk5Zo21b4IlMd71sI6EQi3rdLW4mH5eLZcXHdD4kmyb5ud5Y5zJZ5PZMp9M8/n0kFl7o4nVGn6P
+        AABeurfV6Ep6VmuYZMefhpixIrU+BQGo6G37o5DZsKATlQ2g9k7IdbI3UHr3QaDGRwKpCTQGLIw1
+        sgfxgFoTM0RCm4tpCJ4IpaYIJQqO4cZDRdLnpRjJySnAOLhGB98iOm1Y+ww2wKmqiAV0TfrBuAoQ
+        IlmDhSVgn6Im4KRrQAY8ET1RwUYIPlrzcKrfTjqDL1qn2/4jAx87HT+wHT9aOABwTfHRaPrUBiTu
+        qx65MQTwDvY+ReAGo4TaOxrDTU18lMTwZKwdBtR4FkghF5+XKATG7Xxsuqotl1ATKKKkSBmESNoE
+        Ix2aAboS/KGpXoD2rjQtyOPzBUXaJcbWIC5Zewagc75n66xxd0BeT2bYGWe43kZC9q5dMIsPqkNf
+        RwB3nbnSG7+oEH0TZCv+gTra6aKnU4OdB3C+mB9Q8YL2DFiusnf4tiUJGstn9lQadU3lkDp4GVNp
+        /BkwOuvuXznvcfedG1cNLLP+6N4tMABaUxAqtyFSafTbpoewSO3B/y/sNOdOsuLeelsxFNtdlLTD
+        ZPtTVLxnoWa7M66iGKLp73EXtpfF7HKxmhdloUavo78AAAD//wMAQyxLXZkEAAA=
+    headers:
+      CF-RAY:
+      - 939857e48bd27df2-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 02 May 2025 14:52:38 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2594'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999987'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_6daa33da631e130fca25451911beaf3b
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "What is the weather in San Francisco?"}],
+      "model": "o3-mini", "stop": ["\n"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '120'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.68.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.68.2
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-read-timeout:
+      - '600.0'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.10.16
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//dFNLT9tAEL7nV0z37CDiQBJyRKUSVVuh0sehQtFkPY6n2Ye7O24aIST+
+        Bn+PX1KtE2LTwmUP8z12nrcDAMWFmoPSFYq2tRmeX9txFcf51cXF228fzu3a/bKfv+bT98ur0UeV
+        JYVf/iQtT6oj7W1tSNi7HawDoVByHU1PJqOz6SQftYD1BZkk8+OhZcfD/Dg/HR6PhuPRXll51hTV
+        HH4MAABu2zfl6Ar6o+ZwnD1FLMWIK1LzAwlABW9SRGGMHAWdqKwDtXdCrk378vH+wUL0IWwzWDYC
+        l6DRPd4/CJQkuoJAaIbClmBDKBUFKFDwCL54WJGAVAS6CYGcHAjs4BodvAvoNEftM5CwBV2RXrNb
+        AUIgw7g0neWGlpGFwAfAugbDa2qdP2HqJRr4videU/jNmrKnQOp4lmRb3wSoA5UUAhUH47jjH8Fl
+        mSjgiAqoyNSwYamg9IE0RklpsSt9sO2HybDiKD6wRgPasEWhtvAk+bc6QwKWYO385k2/zYHKJmIa
+        s2uM6QHonJf2p3bAN3vk7jDSkh3HahEIo3dpTFF8rVr0bgBw065I82zqqg7e1rIQv6bWdnSys1Pd
+        UnZgPpntUfGCpgfM8uwFv0VBgmxib8mURl1R0Um7jcSmYN8DBr3q/k/nJe9d5exWvXrO8lc/6ACt
+        qRYqFnWggvXzojtaoHS2r9EOfW5TVvsdWghTSLMoqMTG7A5KxW0UsouS3YpCHXh3VWW9mE40lTSb
+        nWo1uBv8BQAA//8DAD51aKFfBAAA
+    headers:
+      CF-RAY:
+      - 939859809d7c7ded-GRU
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 02 May 2025 14:53:44 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '2803'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999987'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c95eeb550e9f00eaa22ba5cad8587985
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cli/cli_test.py

@@ -18,6 +18,7 @@ from crewai.cli.cli import (
     train,
     version,
 )
+from crewai.crew import Crew
 
 
 @pytest.fixture
@@ -55,81 +56,133 @@ def test_train_invalid_string_iterations(train_crew, runner):
     )
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_all_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+@pytest.fixture
+def mock_crew():
+    _mock = mock.Mock(spec=Crew, name="test_crew")
+    _mock.name = "test_crew"
+    return _mock
+
+
+@pytest.fixture
+def mock_get_crews(mock_crew):
+    with mock.patch(
+        "crewai.cli.reset_memories_command.get_crews", return_value=[mock_crew]
+    ) as mock_get_crew:
+        yield mock_get_crew
+
+
+def test_reset_all_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-a"])
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="all")
-    assert result.output == "All memories have been reset.\n"
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="all")
+        assert (
+            f"[Crew ({crew.name})] Reset memories command has been completed."
+            in result.output
+        )
+        call_count += 1
+
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_short_term_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_short_term_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-s"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="short")
+        assert (
+            f"[Crew ({crew.name})] Short term memory has been reset." in result.output
+        )
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="short")
-    assert result.output == "Short term memory has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_entity_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_entity_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-e"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="entity")
+        assert f"[Crew ({crew.name})] Entity memory has been reset." in result.output
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="entity")
-    assert result.output == "Entity memory has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_long_term_memories(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_long_term_memories(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-l"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="long")
+        assert f"[Crew ({crew.name})] Long term memory has been reset." in result.output
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="long")
-    assert result.output == "Long term memory has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_kickoff_outputs(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_kickoff_outputs(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-k"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
+        assert (
+            f"[Crew ({crew.name})] Latest Kickoff outputs stored has been reset."
+            in result.output
+        )
+        call_count += 1
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="kickoff_outputs")
-    assert result.output == "Latest Kickoff outputs stored has been reset.\n"
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_multiple_memory_flags(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_multiple_memory_flags(mock_get_crews, runner):
     result = runner.invoke(reset_memories, ["-s", "-l"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_has_calls(
+            [mock.call(command_type="long"), mock.call(command_type="short")]
+        )
+        assert (
+            f"[Crew ({crew.name})] Long term memory has been reset.\n"
+            f"[Crew ({crew.name})] Short term memory has been reset.\n" in result.output
+        )
+        call_count += 1
 
-    # Check that reset_memories was called twice with the correct arguments
-    assert mock_crew.reset_memories.call_count == 2
-    mock_crew.reset_memories.assert_has_calls(
-        [mock.call(command_type="long"), mock.call(command_type="short")]
-    )
-    assert (
-        result.output
-        == "Long term memory has been reset.\nShort term memory has been reset.\n"
-    )
+    assert call_count == 1, "reset_memories should have been called once"
 
 
-@mock.patch("crewai.cli.reset_memories_command.get_crew")
-def test_reset_knowledge(mock_get_crew, runner):
-    mock_crew = mock.Mock()
-    mock_get_crew.return_value = mock_crew
+def test_reset_knowledge(mock_get_crews, runner):
+    result = runner.invoke(reset_memories, ["--knowledge"])
+    call_count = 0
+    for crew in mock_get_crews.return_value:
+        crew.reset_memories.assert_called_once_with(command_type="knowledge")
+        assert f"[Crew ({crew.name})] Knowledge has been reset." in result.output
+        call_count += 1
+
+    assert call_count == 1, "reset_memories should have been called once"
+
+
+def test_reset_memory_from_many_crews(mock_get_crews, runner):
+
+    crews = []
+    for crew_id in ["id-1234", "id-5678"]:
+        mock_crew = mock.Mock(spec=Crew)
+        mock_crew.name = None
+        mock_crew.id = crew_id
+        crews.append(mock_crew)
+
+    mock_get_crews.return_value = crews
+
+    # Run the command
     result = runner.invoke(reset_memories, ["--knowledge"])
 
-    mock_crew.reset_memories.assert_called_once_with(command_type="knowledge")
-    assert result.output == "Knowledge has been reset.\n"
+    call_count = 0
+    for crew in crews:
+        call_count += 1
+        crew.reset_memories.assert_called_once_with(command_type="knowledge")
+        assert f"[Crew ({crew.id})] Knowledge has been reset." in result.output
+
+    assert call_count == 2, "reset_memories should have been called twice"
 
 
 def test_reset_no_memory_flags(runner):

tests/cli/tools/test_main.py

@@ -3,12 +3,13 @@ import tempfile
 import unittest
 import unittest.mock
 from contextlib import contextmanager
-from io import StringIO
 from unittest import mock
 from unittest.mock import MagicMock, patch
 
+import pytest
 from pytest import raises
 
+from crewai.cli.authentication.utils import TokenManager
 from crewai.cli.tools.main import ToolCommand
 
 
@@ -23,17 +24,20 @@ def in_temp_dir():
             os.chdir(original_dir)
 
 
-@patch("crewai.cli.tools.main.subprocess.run")
-def test_create_success(mock_subprocess):
-    with in_temp_dir():
-        tool_command = ToolCommand()
+@pytest.fixture
+def tool_command():
+    TokenManager().save_tokens("test-token", 36000)
+    tool_command = ToolCommand()
+    with patch.object(tool_command, "login"):
+        yield tool_command
 
-        with (
-            patch.object(tool_command, "login") as mock_login,
-            patch("sys.stdout", new=StringIO()) as fake_out,
-        ):
-            tool_command.create("test-tool")
-            output = fake_out.getvalue()
+
+@patch("crewai.cli.tools.main.subprocess.run")
+def test_create_success(mock_subprocess, capsys, tool_command):
+    with in_temp_dir():
+        tool_command.create("test-tool")
+        output = capsys.readouterr().out
+        assert "Creating custom tool test_tool..." in output
 
         assert os.path.isdir("test_tool")
         assert os.path.isfile(os.path.join("test_tool", "README.md"))
@@ -47,15 +51,12 @@ def test_create_success(mock_subprocess):
             content = f.read()
             assert "class TestTool" in content
 
-        mock_login.assert_called_once()
         mock_subprocess.assert_called_once_with(["git", "init"], check=True)
 
-        assert "Creating custom tool test_tool..." in output
-
 
 @patch("crewai.cli.tools.main.subprocess.run")
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
-def test_install_success(mock_get, mock_subprocess_run):
+def test_install_success(mock_get, mock_subprocess_run, capsys, tool_command):
     mock_get_response = MagicMock()
     mock_get_response.status_code = 200
     mock_get_response.json.return_value = {
@@ -65,11 +66,9 @@ def test_install_success(mock_get, mock_subprocess_run):
     mock_get.return_value = mock_get_response
     mock_subprocess_run.return_value = MagicMock(stderr=None)
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        tool_command.install("sample-tool")
-        output = fake_out.getvalue()
+    tool_command.install("sample-tool")
+    output = capsys.readouterr().out
+    assert "Successfully installed sample-tool" in output
 
     mock_get.assert_has_calls([mock.call("sample-tool"), mock.call().json()])
     mock_subprocess_run.assert_any_call(
@@ -86,54 +85,42 @@ def test_install_success(mock_get, mock_subprocess_run):
         env=unittest.mock.ANY,
     )
 
-    assert "Successfully installed sample-tool" in output
-
 
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
-def test_install_tool_not_found(mock_get):
+def test_install_tool_not_found(mock_get, capsys, tool_command):
     mock_get_response = MagicMock()
     mock_get_response.status_code = 404
     mock_get.return_value = mock_get_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.install("non-existent-tool")
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
+    with raises(SystemExit):
+        tool_command.install("non-existent-tool")
+    output = capsys.readouterr().out
+    assert "No tool found with this name" in output
 
     mock_get.assert_called_once_with("non-existent-tool")
-    assert "No tool found with this name" in output
 
 
 @patch("crewai.cli.plus_api.PlusAPI.get_tool")
-def test_install_api_error(mock_get):
+def test_install_api_error(mock_get, capsys, tool_command):
     mock_get_response = MagicMock()
     mock_get_response.status_code = 500
     mock_get.return_value = mock_get_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.install("error-tool")
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
+    with raises(SystemExit):
+        tool_command.install("error-tool")
+    output = capsys.readouterr().out
+    assert "Failed to get tool details" in output
 
     mock_get.assert_called_once_with("error-tool")
-    assert "Failed to get tool details" in output
 
 
 @patch("crewai.cli.tools.main.git.Repository.is_synced", return_value=False)
-def test_publish_when_not_in_sync(mock_is_synced):
-    with patch("sys.stdout", new=StringIO()) as fake_out, raises(SystemExit):
-        tool_command = ToolCommand()
+def test_publish_when_not_in_sync(mock_is_synced, capsys, tool_command):
+    with raises(SystemExit):
         tool_command.publish(is_public=True)
 
-    assert "Local changes need to be resolved before publishing" in fake_out.getvalue()
+    output = capsys.readouterr().out
+    assert "Local changes need to be resolved before publishing" in output
 
 
 @patch("crewai.cli.tools.main.get_project_name", return_value="sample-tool")
@@ -157,13 +144,13 @@ def test_publish_when_not_in_sync_and_force(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    tool_command,
 ):
     mock_publish_response = MagicMock()
     mock_publish_response.status_code = 200
     mock_publish_response.json.return_value = {"handle": "sample-tool"}
     mock_publish.return_value = mock_publish_response
 
-    tool_command = ToolCommand()
     tool_command.publish(is_public=True, force=True)
 
     mock_get_project_name.assert_called_with(require=True)
@@ -205,13 +192,13 @@ def test_publish_success(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    tool_command,
 ):
     mock_publish_response = MagicMock()
     mock_publish_response.status_code = 200
     mock_publish_response.json.return_value = {"handle": "sample-tool"}
     mock_publish.return_value = mock_publish_response
 
-    tool_command = ToolCommand()
     tool_command.publish(is_public=True)
 
     mock_get_project_name.assert_called_with(require=True)
@@ -251,25 +238,22 @@ def test_publish_failure(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    capsys,
+    tool_command,
 ):
     mock_publish_response = MagicMock()
     mock_publish_response.status_code = 422
     mock_publish_response.json.return_value = {"name": ["is already taken"]}
     mock_publish.return_value = mock_publish_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.publish(is_public=True)
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
-
-    mock_publish.assert_called_once()
+    with raises(SystemExit):
+        tool_command.publish(is_public=True)
+    output = capsys.readouterr().out
     assert "Failed to complete operation" in output
     assert "Name is already taken" in output
 
+    mock_publish.assert_called_once()
+
 
 @patch("crewai.cli.tools.main.get_project_name", return_value="sample-tool")
 @patch("crewai.cli.tools.main.get_project_version", return_value="1.0.0")
@@ -290,6 +274,8 @@ def test_publish_api_error(
     mock_get_project_description,
     mock_get_project_version,
     mock_get_project_name,
+    capsys,
+    tool_command,
 ):
     mock_response = MagicMock()
     mock_response.status_code = 500
@@ -297,14 +283,9 @@ def test_publish_api_error(
     mock_response.ok = False
     mock_publish.return_value = mock_response
 
-    tool_command = ToolCommand()
-
-    with patch("sys.stdout", new=StringIO()) as fake_out:
-        try:
-            tool_command.publish(is_public=True)
-        except SystemExit:
-            pass
-        output = fake_out.getvalue()
+    with raises(SystemExit):
+        tool_command.publish(is_public=True)
+    output = capsys.readouterr().out
+    assert "Request to Enterprise API failed" in output
 
     mock_publish.assert_called_once()
-    assert "Request to Enterprise API failed" in output

tests/crew_test.py

@@ -17,6 +17,7 @@ from crewai.agents.cache import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
+from crewai.flow import Flow, listen, start
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
@@ -2164,7 +2165,6 @@ def test_tools_with_custom_caching():
     with patch.object(
         CacheHandler, "add", wraps=crew._cache_handler.add
     ) as add_to_cache:
-
         result = crew.kickoff()
 
         # Check that add_to_cache was called exactly twice
@@ -4351,3 +4351,35 @@ def test_crew_copy_with_memory():
             raise e  # Re-raise other validation errors
     except Exception as e:
         pytest.fail(f"Copying crew raised an unexpected exception: {e}")
+
+
+def test_sets_parent_flow_when_outside_flow(researcher, writer):
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=[
+            Task(description="Task 1", expected_output="output", agent=researcher),
+            Task(description="Task 2", expected_output="output", agent=writer),
+        ],
+    )
+    assert crew.parent_flow is None
+
+
+def test_sets_parent_flow_when_inside_flow(researcher, writer):
+    class MyFlow(Flow):
+        @start()
+        def start(self):
+            return Crew(
+                agents=[researcher, writer],
+                process=Process.sequential,
+                tasks=[
+                    Task(
+                        description="Task 1", expected_output="output", agent=researcher
+                    ),
+                    Task(description="Task 2", expected_output="output", agent=writer),
+                ],
+            )
+
+    flow = MyFlow()
+    result = flow.kickoff()
+    assert result.parent_flow is flow

tests/llm_test.py

@@ -373,6 +373,7 @@ def get_weather_tool_schema():
         },
     }
 
+
 def test_context_window_exceeded_error_handling():
     """Test that litellm.ContextWindowExceededError is converted to LLMContextLengthExceededException."""
     from litellm.exceptions import ContextWindowExceededError
@@ -388,7 +389,7 @@ def test_context_window_exceeded_error_handling():
         mock_completion.side_effect = ContextWindowExceededError(
             "This model's maximum context length is 8192 tokens. However, your messages resulted in 10000 tokens.",
             model="gpt-4",
-            llm_provider="openai"
+            llm_provider="openai",
         )
 
         with pytest.raises(LLMContextLengthExceededException) as excinfo:
@@ -403,7 +404,7 @@ def test_context_window_exceeded_error_handling():
         mock_completion.side_effect = ContextWindowExceededError(
             "This model's maximum context length is 8192 tokens. However, your messages resulted in 10000 tokens.",
             model="gpt-4",
-            llm_provider="openai"
+            llm_provider="openai",
         )
 
         with pytest.raises(LLMContextLengthExceededException) as excinfo:
@@ -618,3 +619,53 @@ def test_handle_streaming_tool_calls_no_tools(mock_emit):
         expected_completed_llm_call=1,
         expected_final_chunk_result=response,
     )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_testing_removing_stop_parameter():
+    from litellm.exceptions import BadRequestError
+
+    # currently o3 does not support stop
+    llm = LLM(model="o3", temperature=0.5)
+    with pytest.raises(
+        BadRequestError,
+        match="parameter: 'stop' is not supported with this model",
+    ):
+        llm.call(
+            messages=[
+                {"role": "user", "content": "What is the weather in San Francisco?"},
+            ],
+        )
+
+    llm = LLM(model="o3", temperature=0.5, stop=None)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in San Francisco?"},
+        ],
+    )
+    assert isinstance(response, str)
+
+    # testing another model that supports stop
+    llm = LLM(model="o3-mini", temperature=0.5)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in San Francisco?"},
+        ],
+    )
+    assert isinstance(response, str)
+
+    llm = LLM(model="o3-mini", temperature=0.5, stop=None)
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in San Francisco?"},
+        ],
+    )
+    assert isinstance(response, str)
+
+    llm = LLM(model="o3-mini", temperature=0.5, stop=["\n"])
+    response = llm.call(
+        messages=[
+            {"role": "user", "content": "What is the weather in San Francisco?"},
+        ],
+    )
+    assert isinstance(response, str)

tests/test_lite_agent.py

@@ -1,13 +1,16 @@
 import asyncio
 from typing import cast
+from unittest.mock import Mock
 
 import pytest
 from pydantic import BaseModel, Field
 
 from crewai import LLM, Agent
+from crewai.flow import Flow, start
 from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.tools import BaseTool
 from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.agent_events import LiteAgentExecutionStartedEvent
 from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
 
 
@@ -255,3 +258,60 @@ async def test_lite_agent_returns_usage_metrics_async():
     assert "21 million" in result.raw or "37 million" in result.raw
     assert result.usage_metrics is not None
     assert result.usage_metrics["total_tokens"] > 0
+
+
+class TestFlow(Flow):
+    """A test flow that creates and runs an agent."""
+
+    def __init__(self, llm, tools):
+        self.llm = llm
+        self.tools = tools
+        super().__init__()
+
+    @start()
+    def start(self):
+        agent = Agent(
+            role="Test Agent",
+            goal="Test Goal",
+            backstory="Test Backstory",
+            llm=self.llm,
+            tools=self.tools,
+        )
+        return agent.kickoff("Test query")
+
+
+def verify_agent_parent_flow(result, agent, flow):
+    """Verify that both the result and agent have the correct parent flow."""
+    assert result.parent_flow is flow
+    assert agent is not None
+    assert agent.parent_flow is flow
+
+
+def test_sets_parent_flow_when_inside_flow():
+    captured_agent = None
+
+    mock_llm = Mock(spec=LLM)
+    mock_llm.call.return_value = "Test response"
+
+    class MyFlow(Flow):
+        @start()
+        def start(self):
+            agent = Agent(
+                role="Test Agent",
+                goal="Test Goal",
+                backstory="Test Backstory",
+                llm=mock_llm,
+                tools=[WebSearchTool()],
+            )
+            return agent.kickoff("Test query")
+
+    flow = MyFlow()
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(LiteAgentExecutionStartedEvent)
+        def capture_agent(source, event):
+            nonlocal captured_agent
+            captured_agent = source
+
+        result = flow.kickoff()
+        assert captured_agent.parent_flow is flow