fix(cli): forward trained-agents file through replay and test

lib/crewai/src/crewai/cli/cli.py

@@ -139,16 +139,29 @@ def train(n_iterations: int, filename: str) -> None:
     type=str,
     help="Replay the crew from this task ID, including all subsequent tasks.",
 )
-def replay(task_id: str) -> None:
-    """
-    Replay the crew execution from a specific task.
+@click.option(
+    "-f",
+    "--filename",
+    "trained_agents_file",
+    type=str,
+    default=None,
+    help=(
+        "Path to a trained-agents pickle (produced by `crewai train -f`). "
+        "When set, agents load suggestions from this file instead of the "
+        "default trained_agents_data.pkl. Equivalent to setting "
+        "CREWAI_TRAINED_AGENTS_FILE."
+    ),
+)
+def replay(task_id: str, trained_agents_file: str | None) -> None:
+    """Replay the crew execution from a specific task.
 
     Args:
-        task_id (str): The ID of the task to replay from.
+        task_id: The ID of the task to replay from.
+        trained_agents_file: Optional trained-agents pickle path.
     """
     try:
         click.echo(f"Replaying the crew from task {task_id}")
-        replay_task_command(task_id)
+        replay_task_command(task_id, trained_agents_file=trained_agents_file)
     except Exception as e:
         click.echo(f"An error occurred while replaying: {e}", err=True)
 
@@ -332,10 +345,23 @@ def memory(
     default="gpt-4o-mini",
     help="LLM Model to run the tests on the Crew. For now only accepting only OpenAI models.",
 )
-def test(n_iterations: int, model: str) -> None:
+@click.option(
+    "-f",
+    "--filename",
+    "trained_agents_file",
+    type=str,
+    default=None,
+    help=(
+        "Path to a trained-agents pickle (produced by `crewai train -f`). "
+        "When set, agents load suggestions from this file instead of the "
+        "default trained_agents_data.pkl. Equivalent to setting "
+        "CREWAI_TRAINED_AGENTS_FILE."
+    ),
+)
+def test(n_iterations: int, model: str, trained_agents_file: str | None) -> None:
     """Test the crew and evaluate the results."""
     click.echo(f"Testing the crew for {n_iterations} iterations with model {model}")
-    evaluate_crew(n_iterations, model)
+    evaluate_crew(n_iterations, model, trained_agents_file=trained_agents_file)
 
 
 @crewai.command(

lib/crewai/src/crewai/cli/evaluate_crew.py

@@ -2,22 +2,33 @@ import subprocess
 
 import click
 
+from crewai.cli.utils import build_env_with_all_tool_credentials
+from crewai.utilities.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
 
-def evaluate_crew(n_iterations: int, model: str) -> None:
-    """
-    Test and Evaluate the crew by running a command in the UV environment.
+
+def evaluate_crew(
+    n_iterations: int, model: str, trained_agents_file: str | None = None
+) -> None:
+    """Test and Evaluate the crew by running a command in the UV environment.
 
     Args:
-        n_iterations (int): The number of iterations to test the crew.
-        model (str): The model to test the crew with.
+        n_iterations: The number of iterations to test the crew.
+        model: The model to test the crew with.
+        trained_agents_file: Optional trained-agents pickle path forwarded to
+            the subprocess via the ``CREWAI_TRAINED_AGENTS_FILE`` env var.
     """
     command = ["uv", "run", "test", str(n_iterations), model]
+    env = build_env_with_all_tool_credentials()
+    if trained_agents_file:
+        env[CREWAI_TRAINED_AGENTS_FILE_ENV] = trained_agents_file
 
     try:
         if n_iterations <= 0:
             raise ValueError("The number of iterations must be a positive integer.")
 
-        result = subprocess.run(command, capture_output=False, text=True, check=True)  # noqa: S603
+        result = subprocess.run(  # noqa: S603
+            command, capture_output=False, text=True, check=True, env=env
+        )
 
         if result.stderr:
             click.echo(result.stderr, err=True)

lib/crewai/src/crewai/cli/replay_from_task.py

@@ -2,18 +2,27 @@ import subprocess
 
 import click
 
+from crewai.cli.utils import build_env_with_all_tool_credentials
+from crewai.utilities.constants import CREWAI_TRAINED_AGENTS_FILE_ENV
 
-def replay_task_command(task_id: str) -> None:
-    """
-    Replay the crew execution from a specific task.
+
+def replay_task_command(task_id: str, trained_agents_file: str | None = None) -> None:
+    """Replay the crew execution from a specific task.
 
     Args:
-      task_id (str): The ID of the task to replay from.
+        task_id: The ID of the task to replay from.
+        trained_agents_file: Optional trained-agents pickle path forwarded to
+            the subprocess via the ``CREWAI_TRAINED_AGENTS_FILE`` env var.
     """
     command = ["uv", "run", "replay", task_id]
+    env = build_env_with_all_tool_credentials()
+    if trained_agents_file:
+        env[CREWAI_TRAINED_AGENTS_FILE_ENV] = trained_agents_file
 
     try:
-        result = subprocess.run(command, capture_output=False, text=True, check=True)  # noqa: S603
+        result = subprocess.run(  # noqa: S603
+            command, capture_output=False, text=True, check=True, env=env
+        )
         if result.stderr:
             click.echo(result.stderr, err=True)
 

lib/crewai/tests/cli/test_cli.py

@@ -307,7 +307,7 @@ def test_version_command_with_tools(runner):
 def test_test_default_iterations(evaluate_crew, runner):
     result = runner.invoke(test)
 
-    evaluate_crew.assert_called_once_with(3, "gpt-4o-mini")
+    evaluate_crew.assert_called_once_with(3, "gpt-4o-mini", trained_agents_file=None)
     assert result.exit_code == 0
     assert "Testing the crew for 3 iterations with model gpt-4o-mini" in result.output
 
@@ -316,7 +316,7 @@ def test_test_default_iterations(evaluate_crew, runner):
 def test_test_custom_iterations(evaluate_crew, runner):
     result = runner.invoke(test, ["--n_iterations", "5", "--model", "gpt-4o"])
 
-    evaluate_crew.assert_called_once_with(5, "gpt-4o")
+    evaluate_crew.assert_called_once_with(5, "gpt-4o", trained_agents_file=None)
     assert result.exit_code == 0
     assert "Testing the crew for 5 iterations with model gpt-4o" in result.output
 

lib/crewai/tests/cli/test_crew_test.py

@@ -27,6 +27,7 @@ def test_crew_success(mock_subprocess_run, n_iterations, model):
         capture_output=False,
         text=True,
         check=True,
+        env=mock.ANY,
     )
     assert result is None
 
@@ -66,6 +67,7 @@ def test_test_crew_called_process_error(mock_subprocess_run, click):
         capture_output=False,
         text=True,
         check=True,
+        env=mock.ANY,
     )
     click.echo.assert_has_calls(
         [
@@ -91,7 +93,30 @@ def test_test_crew_unexpected_exception(mock_subprocess_run, click):
         capture_output=False,
         text=True,
         check=True,
+        env=mock.ANY,
     )
     click.echo.assert_called_once_with(
         "An unexpected error occurred: Unexpected error", err=True
     )
+
+
+@mock.patch("crewai.cli.evaluate_crew.subprocess.run")
+def test_evaluate_crew_sets_trained_agents_env_var(mock_subprocess_run):
+    mock_subprocess_run.return_value = subprocess.CompletedProcess(
+        args=["uv", "run", "test", "1", "gpt-4o"], returncode=0
+    )
+    evaluate_crew.evaluate_crew(1, "gpt-4o", trained_agents_file="my_custom.pkl")
+
+    _, kwargs = mock_subprocess_run.call_args
+    assert kwargs["env"]["CREWAI_TRAINED_AGENTS_FILE"] == "my_custom.pkl"
+
+
+@mock.patch("crewai.cli.evaluate_crew.subprocess.run")
+def test_evaluate_crew_omits_env_var_without_filename(mock_subprocess_run):
+    mock_subprocess_run.return_value = subprocess.CompletedProcess(
+        args=["uv", "run", "test", "1", "gpt-4o"], returncode=0
+    )
+    evaluate_crew.evaluate_crew(1, "gpt-4o")
+
+    _, kwargs = mock_subprocess_run.call_args
+    assert "CREWAI_TRAINED_AGENTS_FILE" not in kwargs["env"]

lib/crewai/tests/cli/test_replay_from_task.py

@@ -0,0 +1,61 @@
+"""Tests for ``crewai replay`` and the trained-agents file plumbing."""
+
+import subprocess
+from unittest import mock
+
+from click.testing import CliRunner
+import pytest
+
+from crewai.cli import replay_from_task
+from crewai.cli.cli import replay
+
+
+@pytest.fixture
+def runner() -> CliRunner:
+    return CliRunner()
+
+
+@mock.patch("crewai.cli.cli.replay_task_command")
+def test_replay_passes_filename(replay_task_command_mock: mock.Mock, runner: CliRunner) -> None:
+    result = runner.invoke(replay, ["-t", "abc123", "-f", "my_custom.pkl"])
+
+    replay_task_command_mock.assert_called_once_with(
+        "abc123", trained_agents_file="my_custom.pkl"
+    )
+    assert result.exit_code == 0
+
+
+@mock.patch("crewai.cli.cli.replay_task_command")
+def test_replay_without_filename_passes_none(
+    replay_task_command_mock: mock.Mock, runner: CliRunner
+) -> None:
+    result = runner.invoke(replay, ["-t", "abc123"])
+
+    replay_task_command_mock.assert_called_once_with(
+        "abc123", trained_agents_file=None
+    )
+    assert result.exit_code == 0
+
+
+@mock.patch("crewai.cli.replay_from_task.subprocess.run")
+def test_replay_task_command_sets_env_var(mock_subprocess_run: mock.Mock) -> None:
+    mock_subprocess_run.return_value = subprocess.CompletedProcess(
+        args=["uv", "run", "replay", "abc123"], returncode=0
+    )
+    replay_from_task.replay_task_command("abc123", trained_agents_file="my_custom.pkl")
+
+    _, kwargs = mock_subprocess_run.call_args
+    assert kwargs["env"]["CREWAI_TRAINED_AGENTS_FILE"] == "my_custom.pkl"
+
+
+@mock.patch("crewai.cli.replay_from_task.subprocess.run")
+def test_replay_task_command_omits_env_var_without_filename(
+    mock_subprocess_run: mock.Mock,
+) -> None:
+    mock_subprocess_run.return_value = subprocess.CompletedProcess(
+        args=["uv", "run", "replay", "abc123"], returncode=0
+    )
+    replay_from_task.replay_task_command("abc123")
+
+    _, kwargs = mock_subprocess_run.call_args
+    assert "CREWAI_TRAINED_AGENTS_FILE" not in kwargs["env"]