feat: implement before and after LLM call hooks in CrewAgentExecutor (#3893)

- Added support for before and after LLM call hooks to allow modification of messages and responses during LLM interactions. - Introduced LLMCallHookContext to provide hooks with access to the executor state, enabling in-place modifications of messages. - Updated get_llm_response function to utilize the new hooks, ensuring that modifications persist across iterations. - Enhanced tests to verify the functionality of the hooks and their error handling capabilities, ensuring robust execution flow.
2025-12-16 12:28:30 +00:00 · 2025-11-12 08:38:13 -08:00
parent fcb5b19b2e
commit c205d2e8de
10 changed files with 1590 additions and 1 deletions
--- a/lib/crewai/src/crewai/agents/crew_agent_executor.py
+++ b/lib/crewai/src/crewai/agents/crew_agent_executor.py
@@ -38,6 +38,10 @@ from crewai.utilities.agent_utils import (
 )
 from crewai.utilities.constants import TRAINING_DATA_FILE
 from crewai.utilities.i18n import I18N, get_i18n
+from crewai.utilities.llm_call_hooks import (
+    get_after_llm_call_hooks,
+    get_before_llm_call_hooks,
+)
 from crewai.utilities.printer import Printer
 from crewai.utilities.tool_utils import execute_tool_and_check_finality
 from crewai.utilities.training_handler import CrewTrainingHandler
@@ -130,6 +134,10 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
        self.messages: list[LLMMessage] = []
        self.iterations = 0
        self.log_error_after = 3
+        self.before_llm_call_hooks: list[Callable] = []
+        self.after_llm_call_hooks: list[Callable] = []
+        self.before_llm_call_hooks.extend(get_before_llm_call_hooks())
+        self.after_llm_call_hooks.extend(get_after_llm_call_hooks())
        if self.llm:
            # This may be mutating the shared llm object and needs further evaluation
            existing_stop = getattr(self.llm, "stop", [])
@@ -226,6 +234,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                    from_task=self.task,
                    from_agent=self.agent,
                    response_model=self.response_model,
+                    executor_context=self,
                )
                formatted_answer = process_llm_response(answer, self.use_stop_words)  # type: ignore[assignment]

--- a/lib/crewai/src/crewai/utilities/agent_utils.py
+++ b/lib/crewai/src/crewai/utilities/agent_utils.py
@@ -33,6 +33,7 @@ from crewai.utilities.types import LLMMessage

 if TYPE_CHECKING:
    from crewai.agent import Agent
+    from crewai.agents.crew_agent_executor import CrewAgentExecutor
    from crewai.lite_agent import LiteAgent
    from crewai.llm import LLM
    from crewai.task import Task
@@ -236,6 +237,7 @@ def get_llm_response(
    from_task: Task | None = None,
    from_agent: Agent | LiteAgent | None = None,
    response_model: type[BaseModel] | None = None,
+    executor_context: CrewAgentExecutor | None = None,
 ) -> str:
    """Call the LLM and return the response, handling any invalid responses.

@@ -247,6 +249,7 @@ def get_llm_response(
        from_task: Optional task context for the LLM call
        from_agent: Optional agent context for the LLM call
        response_model: Optional Pydantic model for structured outputs
+        executor_context: Optional executor context for hook invocation

    Returns:
        The response from the LLM as a string
@@ -255,6 +258,11 @@ def get_llm_response(
        Exception: If an error occurs.
        ValueError: If the response is None or empty.
    """
+
+    if executor_context is not None:
+        _setup_before_llm_call_hooks(executor_context, printer)
+        messages = executor_context.messages
+
    try:
        answer = llm.call(
            messages,
@@ -272,7 +280,7 @@ def get_llm_response(
        )
        raise ValueError("Invalid response from LLM call - None or empty.")

-    return answer
+    return _setup_after_llm_call_hooks(executor_context, answer, printer)


 def process_llm_response(
@@ -661,3 +669,92 @@ def load_agent_from_repository(from_repository: str) -> dict[str, Any]:
            else:
                attributes[key] = value
    return attributes
+
+
+def _setup_before_llm_call_hooks(
+    executor_context: CrewAgentExecutor | None, printer: Printer
+) -> None:
+    """Setup and invoke before_llm_call hooks for the executor context.
+
+    Args:
+        executor_context: The executor context to setup the hooks for.
+        printer: Printer instance for error logging.
+    """
+    if executor_context and executor_context.before_llm_call_hooks:
+        from crewai.utilities.llm_call_hooks import LLMCallHookContext
+
+        original_messages = executor_context.messages
+
+        hook_context = LLMCallHookContext(executor_context)
+        try:
+            for hook in executor_context.before_llm_call_hooks:
+                hook(hook_context)
+        except Exception as e:
+            printer.print(
+                content=f"Error in before_llm_call hook: {e}",
+                color="yellow",
+            )
+
+        if not isinstance(executor_context.messages, list):
+            printer.print(
+                content=(
+                    "Warning: before_llm_call hook replaced messages with non-list. "
+                    "Restoring original messages list. Hooks should modify messages in-place, "
+                    "not replace the list (e.g., use context.messages.append() not context.messages = [])."
+                ),
+                color="yellow",
+            )
+            if isinstance(original_messages, list):
+                executor_context.messages = original_messages
+            else:
+                executor_context.messages = []
+
+
+def _setup_after_llm_call_hooks(
+    executor_context: CrewAgentExecutor | None,
+    answer: str,
+    printer: Printer,
+) -> str:
+    """Setup and invoke after_llm_call hooks for the executor context.
+
+    Args:
+        executor_context: The executor context to setup the hooks for.
+        answer: The LLM response string.
+        printer: Printer instance for error logging.
+
+    Returns:
+        The potentially modified response string.
+    """
+    if executor_context and executor_context.after_llm_call_hooks:
+        from crewai.utilities.llm_call_hooks import LLMCallHookContext
+
+        original_messages = executor_context.messages
+
+        hook_context = LLMCallHookContext(executor_context, response=answer)
+        try:
+            for hook in executor_context.after_llm_call_hooks:
+                modified_response = hook(hook_context)
+                if modified_response is not None and isinstance(modified_response, str):
+                    answer = modified_response
+
+        except Exception as e:
+            printer.print(
+                content=f"Error in after_llm_call hook: {e}",
+                color="yellow",
+            )
+
+        if not isinstance(executor_context.messages, list):
+            printer.print(
+                content=(
+                    "Warning: after_llm_call hook replaced messages with non-list. "
+                    "Restoring original messages list. Hooks should modify messages in-place, "
+                    "not replace the list (e.g., use context.messages.append() not context.messages = [])."
+                ),
+                color="yellow",
+            )
+            if isinstance(original_messages, list):
+                executor_context.messages = original_messages
+            else:
+                executor_context.messages = []
+
+    return answer
--- a/lib/crewai/src/crewai/utilities/llm_call_hooks.py
+++ b/lib/crewai/src/crewai/utilities/llm_call_hooks.py
@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+from collections.abc import Callable
+from typing import TYPE_CHECKING
+
+
+if TYPE_CHECKING:
+    from crewai.agents.crew_agent_executor import CrewAgentExecutor
+
+
+class LLMCallHookContext:
+    """Context object passed to LLM call hooks with full executor access.
+
+    Provides hooks with complete access to the executor state, allowing
+    modification of messages, responses, and executor attributes.
+
+    Attributes:
+        executor: Full reference to the CrewAgentExecutor instance
+        messages: Direct reference to executor.messages (mutable list).
+            Can be modified in both before_llm_call and after_llm_call hooks.
+            Modifications in after_llm_call hooks persist to the next iteration,
+            allowing hooks to modify conversation history for subsequent LLM calls.
+            IMPORTANT: Modify messages in-place (e.g., append, extend, remove items).
+            Do NOT replace the list (e.g., context.messages = []), as this will break
+            the executor. Use context.messages.append() or context.messages.extend()
+            instead of assignment.
+        agent: Reference to the agent executing the task
+        task: Reference to the task being executed
+        crew: Reference to the crew instance
+        llm: Reference to the LLM instance
+        iterations: Current iteration count
+        response: LLM response string (only set for after_llm_call hooks).
+            Can be modified by returning a new string from after_llm_call hook.
+    """
+
+    def __init__(
+        self,
+        executor: CrewAgentExecutor,
+        response: str | None = None,
+    ) -> None:
+        """Initialize hook context with executor reference.
+
+        Args:
+            executor: The CrewAgentExecutor instance
+            response: Optional response string (for after_llm_call hooks)
+        """
+        self.executor = executor
+        self.messages = executor.messages
+        self.agent = executor.agent
+        self.task = executor.task
+        self.crew = executor.crew
+        self.llm = executor.llm
+        self.iterations = executor.iterations
+        self.response = response
+
+
+# Global hook registries (optional convenience feature)
+_before_llm_call_hooks: list[Callable[[LLMCallHookContext], None]] = []
+_after_llm_call_hooks: list[Callable[[LLMCallHookContext], str | None]] = []
+
+
+def register_before_llm_call_hook(
+    hook: Callable[[LLMCallHookContext], None],
+) -> None:
+    """Register a global before_llm_call hook.
+
+    Global hooks are added to all executors automatically.
+    This is a convenience function for registering hooks that should
+    apply to all LLM calls across all executors.
+
+    Args:
+        hook: Function that receives LLMCallHookContext and can modify
+            context.messages directly. Should return None.
+            IMPORTANT: Modify messages in-place (append, extend, remove items).
+            Do NOT replace the list (context.messages = []), as this will break execution.
+    """
+    _before_llm_call_hooks.append(hook)
+
+
+def register_after_llm_call_hook(
+    hook: Callable[[LLMCallHookContext], str | None],
+) -> None:
+    """Register a global after_llm_call hook.
+
+    Global hooks are added to all executors automatically.
+    This is a convenience function for registering hooks that should
+    apply to all LLM calls across all executors.
+
+    Args:
+        hook: Function that receives LLMCallHookContext and can modify:
+            - The response: Return modified response string or None to keep original
+            - The messages: Modify context.messages directly (mutable reference)
+            Both modifications are supported and can be used together.
+            IMPORTANT: Modify messages in-place (append, extend, remove items).
+            Do NOT replace the list (context.messages = []), as this will break execution.
+    """
+    _after_llm_call_hooks.append(hook)
+
+
+def get_before_llm_call_hooks() -> list[Callable[[LLMCallHookContext], None]]:
+    """Get all registered global before_llm_call hooks.
+
+    Returns:
+        List of registered before hooks
+    """
+    return _before_llm_call_hooks.copy()
+
+
+def get_after_llm_call_hooks() -> list[Callable[[LLMCallHookContext], str | None]]:
+    """Get all registered global after_llm_call hooks.
+
+    Returns:
+        List of registered after hooks
+    """
+    return _after_llm_call_hooks.copy()
--- a/lib/crewai/tests/agents/test_agent.py
+++ b/lib/crewai/tests/agents/test_agent.py
@@ -2714,3 +2714,293 @@ def test_agent_without_apps_no_platform_tools():

    tools = crew._prepare_tools(agent, task, [])
    assert tools == []
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_before_llm_call_hook_modifies_messages():
+    """Test that before_llm_call hooks can modify messages."""
+    from crewai.utilities.llm_call_hooks import LLMCallHookContext, register_before_llm_call_hook
+
+    hook_called = False
+    original_message_count = 0
+
+    def before_hook(context: LLMCallHookContext) -> None:
+        nonlocal hook_called, original_message_count
+        hook_called = True
+        original_message_count = len(context.messages)
+        context.messages.append({
+            "role": "user",
+            "content": "Additional context: This is a test modification."
+        })
+
+    register_before_llm_call_hook(before_hook)
+
+    try:
+        agent = Agent(
+            role="Test Agent",
+            goal="Test goal",
+            backstory="Test backstory",
+            allow_delegation=False,
+        )
+
+        task = Task(
+            description="Say hello",
+            expected_output="A greeting",
+            agent=agent,
+        )
+
+        result = agent.execute_task(task)
+
+        assert hook_called, "before_llm_call hook should have been called"
+        assert len(agent.agent_executor.messages) > original_message_count
+        assert result is not None
+    finally:
+        pass
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_after_llm_call_hook_modifies_messages_for_next_iteration():
+    """Test that after_llm_call hooks can modify messages for the next iteration."""
+    from crewai.utilities.llm_call_hooks import LLMCallHookContext, register_after_llm_call_hook
+
+    hook_call_count = 0
+    hook_iterations = []
+    messages_added_in_iteration_0 = False
+    test_message_content = "HOOK_ADDED_MESSAGE_FOR_NEXT_ITERATION"
+
+    def after_hook(context: LLMCallHookContext) -> str | None:
+        nonlocal hook_call_count, hook_iterations, messages_added_in_iteration_0
+        hook_call_count += 1
+        current_iteration = context.iterations
+        hook_iterations.append(current_iteration)
+
+        if current_iteration == 0:
+            messages_before = len(context.messages)
+            context.messages.append({
+                "role": "user",
+                "content": test_message_content
+            })
+            messages_added_in_iteration_0 = True
+            assert len(context.messages) == messages_before + 1
+
+        return None
+
+    register_after_llm_call_hook(after_hook)
+
+    try:
+        agent = Agent(
+            role="Test Agent",
+            goal="Test goal",
+            backstory="Test backstory",
+            allow_delegation=False,
+            max_iter=3,
+        )
+
+        task = Task(
+            description="Count to 3, taking your time",
+            expected_output="A count",
+            agent=agent,
+        )
+
+        result = agent.execute_task(task)
+
+        assert hook_call_count > 0, "after_llm_call hook should have been called"
+        assert messages_added_in_iteration_0, "Message should have been added in iteration 0"
+
+        executor_messages = agent.agent_executor.messages
+        message_contents = [msg.get("content", "") for msg in executor_messages if isinstance(msg, dict)]
+        assert any(test_message_content in content for content in message_contents), (
+            f"Message added by hook in iteration 0 should be present in executor messages. "
+            f"Messages: {message_contents}"
+        )
+
+        assert len(executor_messages) > 2, "Executor should have more than initial messages"
+        assert result is not None
+    finally:
+        pass
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_after_llm_call_hook_modifies_messages():
+    """Test that after_llm_call hooks can modify messages for next iteration."""
+    from crewai.utilities.llm_call_hooks import LLMCallHookContext, register_after_llm_call_hook
+
+    hook_called = False
+    messages_before_hook = 0
+
+    def after_hook(context: LLMCallHookContext) -> str | None:
+        nonlocal hook_called, messages_before_hook
+        hook_called = True
+        messages_before_hook = len(context.messages)
+        context.messages.append({
+            "role": "user",
+            "content": "Remember: This is iteration 2 context."
+        })
+        return None  # Don't modify response
+
+    register_after_llm_call_hook(after_hook)
+
+    try:
+        agent = Agent(
+            role="Test Agent",
+            goal="Test goal",
+            backstory="Test backstory",
+            allow_delegation=False,
+            max_iter=2,
+        )
+
+        task = Task(
+            description="Count to 2",
+            expected_output="A count",
+            agent=agent,
+        )
+
+        result = agent.execute_task(task)
+
+        assert hook_called, "after_llm_call hook should have been called"
+        assert len(agent.agent_executor.messages) > messages_before_hook
+        assert result is not None
+    finally:
+        pass
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_hooks_with_crew():
+    """Test that LLM call hooks work with crew execution."""
+    from crewai.utilities.llm_call_hooks import (
+        LLMCallHookContext,
+        register_after_llm_call_hook,
+        register_before_llm_call_hook,
+    )
+
+    before_hook_called = False
+    after_hook_called = False
+
+    def before_hook(context: LLMCallHookContext) -> None:
+        nonlocal before_hook_called
+        before_hook_called = True
+        assert context.executor is not None
+        assert context.agent is not None
+        assert context.task is not None
+        context.messages.append({
+            "role": "system",
+            "content": "Additional system context from hook."
+        })
+
+    def after_hook(context: LLMCallHookContext) -> str | None:
+        nonlocal after_hook_called
+        after_hook_called = True
+        assert context.response is not None
+        assert len(context.messages) > 0
+        return None
+
+    register_before_llm_call_hook(before_hook)
+    register_after_llm_call_hook(after_hook)
+
+    try:
+        agent = Agent(
+            role="Researcher",
+            goal="Research topics",
+            backstory="You are a researcher",
+            allow_delegation=False,
+        )
+
+        task = Task(
+            description="Research AI frameworks",
+            expected_output="A research summary",
+            agent=agent,
+        )
+
+        crew = Crew(agents=[agent], tasks=[task])
+        result = crew.kickoff()
+
+        assert before_hook_called, "before_llm_call hook should have been called"
+        assert after_hook_called, "after_llm_call hook should have been called"
+        assert result is not None
+        assert result.raw is not None
+    finally:
+        pass
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_hooks_can_modify_executor_attributes():
+    """Test that hooks can access and modify executor attributes like tools."""
+    from crewai.utilities.llm_call_hooks import LLMCallHookContext, register_before_llm_call_hook
+    from crewai.tools import tool
+
+    @tool
+    def test_tool() -> str:
+        """A test tool."""
+        return "test result"
+
+    hook_called = False
+    original_tools_count = 0
+
+    def before_hook(context: LLMCallHookContext) -> None:
+        nonlocal hook_called, original_tools_count
+        hook_called = True
+        original_tools_count = len(context.executor.tools)
+        assert context.executor.max_iter > 0
+        assert context.executor.iterations >= 0
+        assert context.executor.tools is not None
+
+    register_before_llm_call_hook(before_hook)
+
+    try:
+        agent = Agent(
+            role="Test Agent",
+            goal="Test goal",
+            backstory="Test backstory",
+            tools=[test_tool],
+            allow_delegation=False,
+        )
+
+        task = Task(
+            description="Use the test tool",
+            expected_output="Tool result",
+            agent=agent,
+        )
+
+        result = agent.execute_task(task)
+
+        assert hook_called, "before_llm_call hook should have been called"
+        assert original_tools_count >= 0
+        assert result is not None
+    finally:
+        pass
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_llm_call_hooks_error_handling():
+    """Test that hook errors don't break execution."""
+    from crewai.utilities.llm_call_hooks import LLMCallHookContext, register_before_llm_call_hook
+
+    hook_called = False
+
+    def error_hook(context: LLMCallHookContext) -> None:
+        nonlocal hook_called
+        hook_called = True
+        raise ValueError("Test hook error")
+
+    register_before_llm_call_hook(error_hook)
+
+    try:
+        agent = Agent(
+            role="Test Agent",
+            goal="Test goal",
+            backstory="Test backstory",
+            allow_delegation=False,
+        )
+
+        task = Task(
+            description="Say hello",
+            expected_output="A greeting",
+            agent=agent,
+        )
+
+        result = agent.execute_task(task)
+
+        assert hook_called, "before_llm_call hook should have been called"
+        assert result is not None
+    finally:
+        pass
--- a/lib/crewai/tests/cassettes/test_after_llm_call_hook_modifies_messages.yaml
+++ b/lib/crewai/tests/cassettes/test_after_llm_call_hook_modifies_messages.yaml
@@ -0,0 +1,126 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal\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: Count to 2\n\nThis
+      is the expected criteria for your final answer: A count\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:"},{"role":"user","content":"Additional context:
+      This is a test modification."}],"model":"gpt-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '849'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFJNb5wwEL3zK0Y+QwSI7LLcokqVcujHoR9S2wg5ZsBujceyTdIo2v9e
+        GTYLaROpFyTmzXt+b2YeEwCmOtYAE5IHMVqdveH09UHKLx+/2eFzkAdZXL8XJPr9h3dFydLIoNuf
+        KMIT60LQaDUGRWaBhUMeMKoW+11ZH/K8rmZgpA51pA02ZNVFkY3KqKzMy8ssr7KiOtElKYGeNfA9
+        AQB4nL/RqOnwN2sgT58qI3rPB2TNuQmAOdKxwrj3ygduAktXUJAJaGbvnyRNgwwNXIOhexDcwKDu
+        EDgMMQBw4+/R/TBvleEarua/BooUyq2gw37yPKYyk9YbgBtDgcepzFFuTsjxbF7TYB3d+r+orFdG
+        edk65J5MNOoDWTajxwTgZh7S9Cw3s45GG9pAv3B+rtgdFj22LmeD1icwUOB6W9+nL+i1HQautN+M
+        mQkuJHYrdd0JnzpFGyDZpP7XzUvaS3Jlhv+RXwEh0AbsWuuwU+J54rXNYbzd19rOU54NM4/uTgls
+        g0IXN9Fhzye9HBTzDz7g2PbKDOisU8tV9batRFlfFn29K1lyTP4AAAD//wMApumqgWQDAAA=
+    headers:
+      CF-RAY:
+      - 99d044543db94e48-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:41:25 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=KLlCOQ_zxXquDvj96O28ObVFEoAbFE8R7zlmuiuXH1M-1762890085-1.0.1.1-UChItG1GnLDHrErY60dUpkbD3lEkSvfkTQpOmEtzd0fjjm_y1pJQiB.VDXVi2pPIMSelir0ZgiVXSh5.hGPb3RjQqbH3pv0Rr_2dQ59OIQ8;
+        path=/; expires=Tue, 11-Nov-25 20:11:25 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=u.Z6xV9tQd3ucK35BinKtlCkewcI6q_uQicyeEeeR18-1762890085355-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '559'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '735'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999817'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999817'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_bcaa0f8500714ed09f967488b238ce2e
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/test_after_llm_call_hook_modifies_messages_for_next_iteration.yaml
+++ b/lib/crewai/tests/cassettes/test_after_llm_call_hook_modifies_messages_for_next_iteration.yaml
@@ -0,0 +1,222 @@
+interactions:
+- request:
+    body: '{"trace_id": "aeb82647-004a-4a30-9481-d55f476d5659", "execution_type":
+      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      "crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "1.4.1", "privacy_level":
+      "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
+      0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-11T19:45:17.648657+00:00"}}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate, zstd
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '434'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - CrewAI-CLI/1.4.1
+      X-Crewai-Version:
+      - 1.4.1
+    method: POST
+    uri: https://app.crewai.com/crewai_plus/api/v1/tracing/batches
+  response:
+    body:
+      string: '{"error":"bad_credentials","message":"Bad credentials"}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '55'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 11 Nov 2025 19:45:17 GMT
+      cache-control:
+      - no-store
+      content-security-policy:
+      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self''
+        ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts
+        https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
+        https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
+        https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
+        https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
+        https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com
+        https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/
+        https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net
+        https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net
+        https://js.hscollectedforms.net https://js.usemessages.com https://snap.licdn.com
+        https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com
+        https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com
+        app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data:
+        *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com
+        https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com
+        https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com
+        https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com;
+        connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com
+        https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/*
+        https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io
+        https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com
+        https://api.hubspot.com https://forms.hscollectedforms.net https://api.hubapi.com
+        https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509
+        https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect
+        https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self''
+        *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com
+        https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com
+        https://drive.google.com https://slides.google.com https://accounts.google.com
+        https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/
+        https://www.youtube.com https://share.descript.com'
+      expires:
+      - '0'
+      permissions-policy:
+      - camera=(), microphone=(self), geolocation=()
+      pragma:
+      - no-cache
+      referrer-policy:
+      - strict-origin-when-cross-origin
+      strict-transport-security:
+      - max-age=63072000; includeSubDomains
+      vary:
+      - Accept
+      x-content-type-options:
+      - nosniff
+      x-frame-options:
+      - SAMEORIGIN
+      x-permitted-cross-domain-policies:
+      - none
+      x-request-id:
+      - 48a89b0d-206b-4c1b-aa0d-ecc3b4ab525c
+      x-runtime:
+      - '0.088251'
+      x-xss-protection:
+      - 1; mode=block
+    status:
+      code: 401
+      message: Unauthorized
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal\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: Count to 3, taking
+      your time\n\nThis is the expected criteria for your final answer: A count\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-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '790'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFJNa9wwEL37Vww6r43tOpuNb2nKQgslOSy0NA1mIo9tdWVJSHK2Jex/
+        L/J+2Ns20IuE5s0bzXszrxEAEzUrgfEOPe+NjO9Q41atP3/79GG7vX8QD0Xq15svX9/fUd+yRWDo
+        5x/E/YmVcN0bSV5odYC5JfQUqmbXy3x1k77LViPQ65pkoLXGx0WSxb1QIs7T/CpOizgrjvROC06O
+        lfAYAQC8jmdoVNX0k5WQLk6RnpzDllh5TgJgVssQYeiccB6VZ4sJ5Fp5UmPvm04PbedL+AhK74Cj
+        gla8ECC0QQCgcjuy39VaKJRwO75KuFeUJAlsdnq8OkuUzD+w1AwOg0o1SDkDUCntMbg0Sns6Ivuz
+        GKlbY/Wz+4PKGqGE6ypL6LQKjTuvDRvRfQTwNJo2XPjAjNW98ZXXWxq/y5ZH09g0rBl6cwS99ihn
+        8esTcFGvqsmjkG5mO+PIO6on6jQjHGqhZ0A0U/13N/+qfVAuVPs/5SeAczKe6spYqgW/VDylWQq7
+        /Fba2eWxYebIvghOlRdkwyRqanCQhwVj7pfz1FeNUC1ZY8VhyxpTFTxfXWXNapmzaB/9BgAA//8D
+        AL0LXHV0AwAA
+    headers:
+      CF-RAY:
+      - 99d04a06dc4d1949-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:45:18 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=KnsnYxgmlpoHf.5TWnNgU30xb2tc0gK7SC2BbUkud2M-1762890318-1.0.1.1-3KeaQY59x5mY6n8DINELLaH9_b68w7W4ZZ0KeOknBHmQyDwx5qbtDonfYxOjsO_KykjtJLHpB0bsINSNEa9TrjNQHqUWTlRhldfTLenUG44;
+        path=/; expires=Tue, 11-Nov-25 20:15:18 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=ekC35NRP79GCMP.eTi_odl5.6DIsAeFEXKlanWUZOH4-1762890318589-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '598'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '632'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999827'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999827'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_cb36cbe6c33b42a28675e8c6d9a36fe9
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/test_before_llm_call_hook_modifies_messages.yaml
+++ b/lib/crewai/tests/cassettes/test_before_llm_call_hook_modifies_messages.yaml
@@ -0,0 +1,127 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal\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: Say hello\n\nThis
+      is the expected criteria for your final answer: A greeting\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:"},{"role":"user","content":"Additional context:
+      This is a test modification."}],"model":"gpt-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '851'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFJdi9swEHz3r9jqOT5sk+RSvx2lJW1poXDQ0vYwirS21cpaIclJr0f+
+        +yE7F/s+Cn0xeGdnNLO7dwkAU5KVwETLg+isTt9w+rr/YESx27+93RaHVm4/ff7y8Vpcffv+ly0i
+        g3a/UIQH1oWgzmoMiswIC4c8YFTNL9fF5nWWbfIB6EiijrTGhnR5kaedMiotsmKVZss0X57oLSmB
+        npXwIwEAuBu+0aiR+IeVkC0eKh16zxtk5bkJgDnSscK498oHbgJbTKAgE9AM3q9b6ps2lPAeDB1A
+        cAON2iNwaGIA4MYf0P0075ThGq6GvxK2qDW9mks6rHvPYy7Taz0DuDEUeJzLEObmhBzP9jU11tHO
+        P6GyWhnl28oh92SiVR/IsgE9JgA3w5j6R8mZddTZUAX6jcNz+fpy1GPTembo6gQGClzP6pti8YJe
+        JTFwpf1s0Exw0aKcqNNWeC8VzYBklvq5m5e0x+TKNP8jPwFCoA0oK+tQKvE48dTmMF7vv9rOUx4M
+        M49urwRWQaGLm5BY816PJ8X8rQ/YVbUyDTrr1HhXta2Wotis8nqzLlhyTO4BAAD//wMAuV0QSWYD
+        AAA=
+    headers:
+      CF-RAY:
+      - 99d044428f103c35-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:41:22 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=jp.mByP87tLw_KZOIh7lXZ9UMACecreCMNwHwtJmUvQ-1762890082-1.0.1.1-D76UWkvWlN8e0zlQpgSlSHjrhx3Rkh_r8bz4XKx8kljJt8s9Okre9bo7M62ewJNFK9O9iuHkADMKeAEwlsc4Hg0MsF2vt2Hu1J0xikSInv0;
+        path=/; expires=Tue, 11-Nov-25 20:11:22 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=pzTqogdMFPJY2.Yrj49LODdUKbD8UBctCWNyIZVsvK4-1762890082258-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '460'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '478'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999817'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999820'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_3bda51e6d3e34f8cadcc12551dc29ab0
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/test_llm_call_hooks_can_modify_executor_attributes.yaml
+++ b/lib/crewai/tests/cassettes/test_llm_call_hooks_can_modify_executor_attributes.yaml
@@ -0,0 +1,262 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal\nYou ONLY have access to the following tools, and
+      should NEVER make up tools that are not listed here:\n\nTool Name: test_tool\nTool
+      Arguments: {}\nTool Description: A test tool.\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 [test_tool], 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: Use the test tool\n\nThis is the expected criteria for your final answer:
+      Tool result\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:"},{"role":"user","content":"Additional
+      context: This is a test modification."}],"model":"gpt-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1311'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA4xTy47bMAy85ysIneMgcbNp1reizwXaXrpAD83CVmTaViqLWolu2gb590LOw94+
+        gF504HBGw6F0mAAIXYoMhGokq9aZ5KWkz/vdTn14i/dv9h9f19tXi3dtun789H71U0wjg7Y7VHxh
+        zRS1ziBrsidYeZSMUXXxfJWub+fzddoDLZVoIq12nCxni6TVVifpPL1J5stksTzTG9IKg8jgywQA
+        4NCf0agt8bvIYD69VFoMQdYosmsTgPBkYkXIEHRgaVlMB1CRZbS996IoNva+oa5uOIM7CA11poQu
+        IHCDwBg4ZyIDTFAj90WPj532WIK2FflWxqGhIt+DlbbSgLRhj362sS9URLNB6FKCO+s6zuBw3Nii
+        KMb2PFZdkDEj2xkzAqS1xP11fTAPZ+R4jcJQ7Txtw29UUWmrQ5N7lIFsHDswOdGjxwnAQx959yRF
+        4Ty1Lnr+iv116Wp10hPDqgf02XkfgomlGbFuL6wnenmJLLUJo6UJJVWD5UAdNiy7UtMImIym/tPN
+        37RPk2tb/4/8ACiFjrHMncdSq6cTD20e40/4V9s15d6wCOi/aYU5a/RxEyVWsjOn5ynCj8DY5pW2
+        NXrn9emNVi5fqnR9s6jWq1RMjpNfAAAA//8DANALR4WyAwAA
+    headers:
+      CF-RAY:
+      - 99d044470bdeb976-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:41:23 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=p01_b1BsQgwR2woMBWf1E0gJMDDl7pvqkEVHpHAsMJA-1762890083-1.0.1.1-u8iYLTTx0lmfSR1.CzuuYiHgt03yVVUMsBD8WgExXWm7ts.grUwM1ifj9p6xIz.HElrnQdfDSBD5Lv045aNr61YcB8WW3Vz33W9N0Gn0P3w;
+        path=/; expires=Tue, 11-Nov-25 20:11:23 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=2gUmBgxb3VydVYt8.t_P6bY8U_pS.a4KeYpZWDDYM9Q-1762890083295-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '729'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '759'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999707'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999707'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_70c7033dbc5e4ced80d3fdcbcda2c675
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal\nYou ONLY have access to the following tools, and
+      should NEVER make up tools that are not listed here:\n\nTool Name: test_tool\nTool
+      Arguments: {}\nTool Description: A test tool.\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 [test_tool], 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: Use the test tool\n\nThis is the expected criteria for your final answer:
+      Tool result\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:"},{"role":"user","content":"Additional
+      context: This is a test modification."},{"role":"assistant","content":"```\nThought:
+      I should use the test_tool to get the required information for the final answer.\nAction:
+      test_tool\nAction Input: {}\n```\nObservation: test result"},{"role":"user","content":"Additional
+      context: This is a test modification."}],"model":"gpt-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1584'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=p01_b1BsQgwR2woMBWf1E0gJMDDl7pvqkEVHpHAsMJA-1762890083-1.0.1.1-u8iYLTTx0lmfSR1.CzuuYiHgt03yVVUMsBD8WgExXWm7ts.grUwM1ifj9p6xIz.HElrnQdfDSBD5Lv045aNr61YcB8WW3Vz33W9N0Gn0P3w;
+        _cfuvid=2gUmBgxb3VydVYt8.t_P6bY8U_pS.a4KeYpZWDDYM9Q-1762890083295-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFLBbtQwEL3nKyyfN1WS3S5pbhRRKCeEkCpgq8RrTxJTxzb2pC1U++/I
+        TrtJoUhcLNlv3vN7M/OQEEKloBWhvGfIB6vSN8xc3b+/FG/P3rX8x9X+y8dfHy7O8fYra88/0VVg
+        mP134PjEOuFmsApQGj3B3AFDCKr5q21RnmVZuY7AYASoQOssppuTPB2klmmRFadptknzzSO9N5KD
+        pxX5lhBCyEM8g1Et4J5WJFs9vQzgPeuAVsciQqgzKrxQ5r30yDTS1QxyoxF09N40zU5/7s3Y9ViR
+        S6LNHbkJB/ZAWqmZIkz7O3A7fRFvr+OtIggeiQM/KtzppmmW+g7a0bMQUo9KLQCmtUEWmhSTXT8i
+        h2MWZTrrzN7/QaWt1NL3tQPmjQ6+PRpLI3pICLmOPRuftYFaZwaLNZobiN+t83LSo/OsZvQIokGm
+        Fqz1dvWCXi0AmVR+0XXKGe9BzNR5RGwU0iyAZJH6bzcvaU/Jpe7+R34GOAeLIGrrQEj+PPFc5iCs
+        8r/Kjl2OhqkHdys51CjBhUkIaNmopv2i/qdHGOpW6g6cdXJastbWG16Up3lbbguaHJLfAAAA//8D
+        AJW0fwtzAwAA
+    headers:
+      CF-RAY:
+      - 99d0444cbd6db976-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:41:23 GMT
+      Server:
+      - cloudflare
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '527'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '578'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999655'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999655'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_6b1d84dcdde643cea5160e155ee624db
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/test_llm_call_hooks_error_handling.yaml
+++ b/lib/crewai/tests/cassettes/test_llm_call_hooks_error_handling.yaml
@@ -0,0 +1,159 @@
+interactions:
+- request:
+    body: '{"name":"llama3.2:3b"}'
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '22'
+      content-type:
+      - application/json
+      host:
+      - localhost:11434
+      user-agent:
+      - litellm/1.78.5
+    method: POST
+    uri: http://localhost:11434/api/show
+  response:
+    body:
+      string: '{"error":"model ''llama3.2:3b'' not found"}'
+    headers:
+      Content-Length:
+      - '41'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Tue, 11 Nov 2025 19:41:28 GMT
+    status:
+      code: 404
+      message: Not Found
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Test Agent. Test backstory\nYour
+      personal goal is: Test goal\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: Say hello\n\nThis
+      is the expected criteria for your final answer: A greeting\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:"},{"role":"user","content":"Additional context:
+      This is a test modification."}],"model":"gpt-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '851'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFLRbtQwEHzPVyx+vlRJmrte84KOSqgFCSFAqLRUkc/ZJAbHa9lOy6m6
+        f0dOrpe0gMRLpHh2Znd29jECYLJiBTDRci86o+ILTten/ccPFzyp398srz9/2/o3X/PN6btN84kt
+        AoO2P1D4J9aJoM4o9JL0CAuL3GNQTc9W2fo8SdbnA9BRhSrQGuPj/CSNO6llnCXZMk7yOM0P9Jak
+        QMcKuI0AAB6HbxhUV/iLFZAsnl46dI43yIpjEQCzpMIL485J57n2bDGBgrRHPcz+paW+aX0BV6Dp
+        AQTX0Mh7BA5NMABcuwe03/VbqbmCzfBXwCUqRa/g8sC4grEN7KgHTxXfvZ63s1j3jgfPuldqBnCt
+        yfOws8Ho3QHZH60paoylrXtBZbXU0rWlRe5IBxvOk2EDuo8A7oYV9s+2woylzvjS008c2qWrs1GP
+        TdFNaJYdQE+eqxlrTPGlXlmh51K5WQhMcNFiNVGnxHhfSZoB0cz1n9P8TXt0LnXzP/ITIAQaj1Vp
+        LFZSPHc8lVkMl/2vsuOWh4GZQ3svBZZeog1JVFjzXo3nxtzOeezKWuoGrbFyvLnalLnI1su0Xq8y
+        Fu2j3wAAAP//AwDurzwzggMAAA==
+    headers:
+      CF-RAY:
+      - 99d0446e698367ab-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:41:30 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=b52crfzdOm5rh4aOc2LfM8aQKFI.ZL9WCZXaPBDdG5k-1762890090-1.0.1.1-T2xhtwX0vuEnMIb8NRgP4w3RRn1N1ZwSjuhKBob1vDLDmN7XhCKkoIg3IrlC9KEyhA65IGa5DWsHfmlRKKxqw6sIPA98BSO6E3wsTRspHw4;
+        path=/; expires=Tue, 11-Nov-25 20:11:30 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=0TH0Kjp_5t6yhwXKA1wlKBHaczp.TeWhM2A5t6by1sI-1762890090153-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '1049'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '1387'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999817'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999817'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4b132b998ed941b5b6a85ddbb36e2b65
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/cassettes/test_llm_call_hooks_with_crew.yaml
+++ b/lib/crewai/tests/cassettes/test_llm_call_hooks_with_crew.yaml
@@ -0,0 +1,182 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"system","content":"You are Researcher. You are a
+      researcher\nYour personal goal is: Research topics\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:
+      Research AI frameworks\n\nThis is the expected criteria for your final answer:
+      A research summary\nyou MUST return the actual complete content as the final
+      answer, not a summary.\n\nYou MUST follow these instructions: \n - Include specific
+      examples and real-world case studies to enhance the credibility and depth of
+      the article ideas.\n - Incorporate mentions of notable companies, projects,
+      or tools relevant to each topic to provide concrete context.\n - Add diverse
+      viewpoints such as interviews with experts, users, or thought leaders to enrich
+      the narrative and lend authority.\n - Address ethical, social, and emotional
+      considerations explicitly to reflect a balanced and comprehensive analysis.\n
+      - Enhance the descriptions by including implications for future developments
+      and the potential impact on society.\n - Use more engaging and vivid language
+      that draws the reader into each topic''s nuances and importance.\n - Include
+      notes or summaries that contextualize each set of ideas in terms of relevance
+      and potential reader engagement.\n - In future tasks, focus on elaborating initial
+      outlines into more detailed and nuanced article proposals with richer content
+      and insights.\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:"},{"role":"user","content":"Additional
+      context: This is a test modification."}],"model":"gpt-4.1-mini"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1894'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.109.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.109.1
+      x-stainless-read-timeout:
+      - '600'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA2RXTXPbOBK9z6/o8smpkrRJJjPJ6OZy4ownceKKnY+qzaUJNMmOQTQLACUrc5kf
+        sZf9e/NLtrpBycrsRWWTINh4/V6/xz9/Ajhhf7KGE9djccMYlucoX57duvj+fXn/+hrzz8/v3j7f
+        dL/35y9efDlZ6BPSfCNX9k+tnAxjoMIS622XCAvprk+e//r0xW+PH//22G4M4inoY91Yls9WT5YD
+        R14+ffz0l+XjZ8snz+bHe2FH+WQN//4JAOBP+9VCo6f7kzXYZnZloJyxo5P1YRHASZKgV04wZ84F
+        YzlZPNx0EgtFq/22l6nryxouIcoWHEboeEOA0OkBAGPeUvoaLzhigDP7b/01fo0fKBMm18PNNAyY
+        diARzi7hIuFAW0l3WRddxpLET05hWX+NZ6lwy44xwGUsFAJ3FB3B6dnlI2gPTwImgtITNOjuGokE
+        0oLCluwVnjYUZBwolgWMSTbsOXaQS5pcmRJ5oLjhJFFXZMDooYiEDKXHAhSxCQRpLp9SXgDFjiPZ
+        n7paW4mRKUMR8JS5iwsoCTnW+57GIDsY0PUcCQJhilqBdTYDtXpGiiXsVnDbcz68DPKMlecNZeBY
+        BAb8JkmP9XD+BSTCsNxKCh5wHAM7VAS10tKzw2BlZDEkncTMntJ+id6i+5FSAY6Zu77kBXAIUy66
+        JnYKLSdokqAHHkZ0RZtXyPVRgnS7w+5Uditt45MVvN9Q2jBttRVvCQ3xH9q9/hqXcEsxS7oIsoXT
+        1yJdoEdreF8bqA0dJBcYZZwCJpCR4jLLlBxB4CZhUsinTB5aSf8Pb4WexsOV1dH7/v7rvxnaQPes
+        3VWwuZDRATAE2ea5a8oJQJckZzi//pgX8Np+dfPb6495BbVu22/KVvnRqTgq41T4GQLf0bwabhPG
+        HLCQbTRfvO6lSIaeuz5YH4BLhuwwYMOBSwV6lC2llaJ3vbsVZcnpFRX81wU6akTuHq3hTZRtNFB0
+        A7+LOLAzmk7F2o4BuoRjvzjswRla3IiqgeMRAakoBfJhM8J6Rk/N1HV7mI0/rFhhgDYReRmUy/TA
+        0lp3Bq3VwEK/weioio7jXB4l2HBmibZvxDIlDBAwdhN2pGA6ylnfe/ru7fUjw+FsRNcTXH15RwVO
+        zwb8LvHRGm4MuFAhPohsMa/L0zhKKnrsXKpa96fh2FLSQbOAQBtK2JGHZgd1Z/hMDdwoux1lOD37
+        fPOo6j7whlSZS594QxFckMlDnldapVesTJK2wLl0kYtOzluRcMcFTs/f3b5R+ret4nRUcN4f5Ac2
+        w0iplTQoiNaePBK5fgE8YEeVoYXuyxFmC5gKB/5em3woxtpxLqlgRHvs5m43PnBU0oHDdog/zr4c
+        qfVchoYjZXg3Ddc72HLpAaciAxZ24Lk1LAsb7yrbrz8COkdhnkEL6GbwS0Ib/T9Q0Hb8UUQvicYr
+        jt4KPwtjjxcSvI2epyv4oMPwsw3Dc2XrTZk8Ux04vxOG0js1DC3liryNx8sBlcvrY+n2mKEh7WOa
+        bHBy3FvJPMzyLhcaMjgcrT3SAmEKO3VFRwk86UjZH3tM+jIbqCMW7SzIVJwMlBeQJ9cDZht6+9NV
+        f7DWesaGFM9EhaOMWHo1BeyiZK5dOZuKRBlkyvCJenaB8vpY3T3hhsMOaNCxVgl9SznUjn9sKOkB
+        66jPFFpjsRa7b8RCnaMkbqZqClJdp/CgxHQm2uWAd3sVRTLpRiomfx7UeqvcrWBNCNGA3YtpPUtz
+        nhRtwskfgTjbJRb44/pKUocRznvMtKgere9VLVOy1w+iPXZuSjplS2/phL1SsZ390cq4MdXAB3JV
+        kRLX/1TGu9s3R3OMYq/t9darYw1Ke4RImcWjhe9HwAJmeJwMwxT3Lr23l/2Qy7X2TDgEyhWsGxsF
+        Wjnsg9TahKgsPYiJlGVSiHX4B/PcPev0Paakg1w0NWwkTHqPv+vahh/s3KepA8/ZyYZSdfWfV/Cq
+        5gRjTKYEn5i2o3Asqi6NaOb5Jg8+jkyzbNMKLoiXF8TwlheAkEidijzcFIytJKu/pZwlWXmEmo/u
+        HReqRtzIVAx4T4M4nR/fK8bSqiJrbtswqhWnZZuYog+7H7JSMxVAcDhVZdqOesiWzer2NFOw9NaY
+        ZDRtFEpjojJb8QqubVjpJnpALEcx0E777tPly8sz1VuPmb/XhBppTitH6bWIdlCGQbxSlQZKZqw9
+        Jr/FyuLaX0lzE/UTYFCrnXJewas55J1dqqmKw0IZMGR5iBKqXUcp7kMt5t1xwJG2iq6dbJcZgsGe
+        pHt0lBotrWHMmkNbiFJAp2g7haDJNqpHGkueHepZwI0lzmpFrwaZk8f5DwF0/TVqTkg4sj/OBHNH
+        j3BSqj+0nbzettGrDVHYrbN6bJ4/I8hD4nyX//7rP1o64DCGg/r1W4A36HZASbJd0Dq/SaO8HwPW
+        OlZwIUlB0M+1BQRMFkPIEgP5PVbNxKHG4p4yHZc94A449pS4MndM9G3yFh5oaMj76saHBOKx4Ooh
+        KIN9GGrntTqltSJhX1x+KjtlD2tphplNnRE1vFQZt8gpUs7QkkapY6v5RxauZuMwefDiJstyB++a
+        fcQWqhK6OmzofgzIcZ9OTX0r6zqVHQxTLtBgsOHIMcqmbmgMTtRNYZ5/NrOqM3L0vGE/YYBUI7CF
+        twN3thTCsiHLMpRHUn4FxRcyxVwDVcsU/CzC/uD3Rs5fVnAxWch/+fBRWN9Rq7YsoF84ysu3Ijau
+        W0lbTH4B/wMAAP//jFjNbtswDL73KQSfWiAo0Kwbgt2GXVZgP6fdVgSKTNtcZUnQT7ocCuwh9oR7
+        koGkYjtZBuxMR7Ep8vs7nUdaTULQfaXDqTFqLDYjrbOd1dr1QrqSLKs6rVoJXVr0Kvse8gDxZnWU
+        UDRg577mmqj+08cb+SXbbogKHMT+MMlGc/SSIfoRaWvTqGOGuJqYkV6GZAvBhjAQupZcHwJtTBf9
+        qKAtsi2qpKo5E10E79/stEJgGFv4aG3V6B1mH2sHlbFIH6TMoF0PasSMvdAwacglcn4J4OilXKs+
+        VJNB5oYbbquXROJqndkXZ0/Xw7Y5ELbUj1rgG48c+UeeUbGCA1TPStJOXK20q/PFtW8XnWR9ShdV
+        ejoNWjWUUbsT8FnN6HP03HvsUYZfTIWxJeGeFsUM2lpwPbuCb+49xSs/Mg39Z59BIPFSDIDVHB5U
+        BAt77TJ39t2DCksyWqngLZrDqJ+mjIKQhzkMEsuEsrNobtUD4Sz7Dc38FWGgPdqDSk6HNPhcCcMW
+        gy0Ty+CfzxaB/c7Jhg9o2auNgbfaRMzckgidrWrOu2WuQAPcdWwx+GZqt4TYDan4JCp+GVeQ1iB8
+        fQIRztkHNBTO6MmYGpI/O8sa0fgSa0W5IhqOFU6J5GmXiYakA4IUc7jBHkB2XNQjaR5mVnnXSwBB
+        RPmdgJAP5yYwTP7++SsPcOBnqhzMh6NzDFZnkpVJpUGHGsEQuJMH8pSddWfB1q366lqIlNy1c2Rz
+        OqDz1MlITOty5E9MClJisya2Y9BMHtXuoFPP+lAVBIPfkeclWbIHtQMHEtjVqSM+YoFMm3q7zBRJ
+        OyRNwaYr1i4K2jkv1MNp5mOtvEz5pfV9iH6Xzn7adOgwDdsIOnlHWWXKPjRcfblS6pFz0nISfTYy
+        o9vsn4D/7tV9zUmbOZ+dq5vNplazz9rOhbv1+lg5OXHbQtZo0yJrbQyFFe382zmYZRJYFK4W3/33
+        +1w6W74dXf8/x88FYyBkaLezWbj0WAQav389NvWZX7ipnmebESLdRQudLlZS5UaM87ZD15OoRomW
+        u7C9N+vN67tu82bdXL1c/QEAAP//AwBbY8c8aRcAAA==
+    headers:
+      CF-RAY:
+      - 99d0447958ce36e8-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Nov 2025 19:41:45 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=dSe1gQEFfPpE4AOsFi3S3RQkzPCQnV1.Ywe__K7cSSU-1762890105-1.0.1.1-I1CSTO8ri4tjbaHdIHQ9YP9c2pa.y9WwMQFRaUztT95T_OAe5V0ndTFN4pO1RiCXh15TUpWmBxRdxIWjcYDMqrDIvKWInLO5aavGFWZ1rys;
+        path=/; expires=Tue, 11-Nov-25 20:11:45 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=LMf_4EPFZGfTiqcjmjEk7WxOTuX2ukd3Cs_R8170wJ4-1762890105804-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Strict-Transport-Security:
+      - max-age=31536000; includeSubDomains; preload
+      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:
+      - '15065'
+      openai-project:
+      - proj_xitITlrFeen7zjNSzML82h9x
+      openai-version:
+      - '2020-10-01'
+      x-envoy-upstream-service-time:
+      - '15254'
+      x-openai-proxy-wasm:
+      - v0.1
+      x-ratelimit-limit-project-tokens:
+      - '150000000'
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-project-tokens:
+      - '149999560'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999560'
+      x-ratelimit-reset-project-tokens:
+      - 0s
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_c49c9fba20ff4f05903eff3c78797ce1
+    status:
+      code: 200
+      message: OK
+version: 1