feat(eval): export Pi conversation transcripts

[TomCC7]

Superseded by #3470. During the stack reorder, GitHub marked this draft merged into its former feature-branch base; it did not merge to main. Review and continue the transcript change in #3470.

Contribution path

• Original stack position: 3/4
• Replacement PR: feat(eval): export Pi conversation transcripts #3470

This change retains Pi session JSONL and exports a self-contained HTML transcript with complete Python calls and results. The replacement PR carries the same rewritten commit on the corrected base.

[codecov]

❌ 4 Tests Failed:

Tests completed	Failed	Passed	Skipped
3792	4	3788	175

View the top 3 failed test(s) by shortest run time

dimos.codebase_checks.test_no_init_files::test_no_init_files

Stack Traces | 0.021s run time

def test_no_init_files():
        dimos_dir = DIMOS_PROJECT_ROOT / "dimos"
        init_files = sorted(dimos_dir.rglob("__init__.py"))
        # The root dimos/__init__.py is allowed for the porcelain lazy import.
        init_files = [f for f in init_files if f != dimos_dir / "__init__.py"]
        if init_files:
            listing = "\n".join(f"  - {f.relative_to(dimos_dir)}" for f in init_files)
>           raise AssertionError(
                f"Found __init__.py files in dimos/:\n{listing}\n\n"
                "__init__.py files are not allowed because they lead to unnecessary "
                "extraneous imports. Everything should be imported straight from the "
                "source module."
            )
E           AssertionError: Found __init__.py files in dimos/:
E             - benchmark/libero_pro/__init__.py
E             - .../libero_pro/proto/__init__.py
E           
E           __init__.py files are not allowed because they lead to unnecessary extraneous imports. Everything should be imported straight from the source module.

dimos_dir  = PosixPath('.../dimos/dimos/dimos')
init_files = [PosixPath('.../dimos/dimos/dimos/benchmark/libero_pro/__init__.py'), PosixPath('.../dimos/dimos/dimos/.../libero_pro/proto/__init__.py')]
listing    = '  - benchmark/libero_pro/__init__.py\n  - .../libero_pro/proto/__init__.py'

dimos/codebase_checks/test_no_init_files.py:25: AssertionError

dimos.benchmark.evaluation.test_policy_runtime::test_policy_result_larger_than_pipe_buffer_does_not_deadlock

Stack Traces | 2s run time

def test_policy_result_larger_than_pipe_buffer_does_not_deadlock() -> None:
        context = multiprocessing.get_context("spawn")
        messages, worker_messages = context.Pipe(duplex=False)
        start_event = context.Event()
        result_sending = context.Event()
        process = context.Process(
            target=_send_large_policy_error,
            args=(worker_messages, start_event, result_sending),
            daemon=True,
        )
        process.start()
        worker_messages.close()
        execution = _PolicyExecutionProcess(process, messages, start_event)
        execution.start()
>       assert result_sending.wait(timeout=2)
E       assert False
E        +  where False = wait(timeout=2)
E        +    where wait = <Event at 0xff2ae8a816d0 unset>.wait

context    = <multiprocessing.context.SpawnContext object at 0xff2be7374ec0>
execution  = <dimos.benchmark.evaluation.runtime._PolicyExecutionProcess object at 0xff2aeab523c0>
messages   = <multiprocessing.connection.Connection object at 0xff2ae8a82390>
process    = <SpawnProcess name='SpawnProcess-5' pid=15880 parent=3089 started daemon>
result_sending = <Event at 0xff2ae8a816d0 unset>
start_event = <Event at 0xff2ae8a82900 set>
worker_messages = <multiprocessing.connection.Connection object at 0xff2ae8a81580>

.../benchmark/evaluation/test_policy_runtime.py:192: AssertionError

dimos.codebase_checks.test_inline_heavy_imports::test_heavy_imports_are_inline

Stack Traces | 2.31s run time

def test_heavy_imports_are_inline() -> None:
        """Fail if any file imports cv2/open3d/rerun at module level."""
        hits = find_eager_heavy_imports()
        if hits:
            listing = "\n".join(
                f"  - dimos/{f}:{line}: `{module}`"
                for f, lines in sorted(hits.items())
                for line, module in lines
            )
>           raise AssertionError(
                f"Found module-level import(s) of {'/'.join(HEAVY_MODULES)}:\n{listing}\n\n"
                "These libraries load large native extensions into every process that "
                "transitively imports the module. Import them inside the function or "
                "method that uses them; imports needed only for type annotations go "
                "under `if TYPE_CHECKING:`."
            )
E           AssertionError: Found module-level import(s) of cv2/open3d/rerun:
E             - .../benchmark/libero_pro/video.py:9: `cv2`
E           
E           These libraries load large native extensions into every process that transitively imports the module. Import them inside the function or method that uses them; imports needed only for type annotations go under `if TYPE_CHECKING:`.

hits       = {'benchmark/libero_pro/video.py': [(9, 'cv2')]}
listing    = '  - .../benchmark/libero_pro/video.py:9: `cv2`'

dimos/codebase_checks/test_inline_heavy_imports.py:92: AssertionError

dimos.robot.test_all_blueprints_generation::test_all_blueprints_is_current

Stack Traces | 3.99s run time

def test_all_blueprints_is_current() -> None:
        root = DIMOS_PROJECT_ROOT / "dimos"
        all_blueprints, all_modules = _scan_for_blueprints(root)
    
        common = set(all_blueprints.keys()) & set(all_modules.keys())
        assert not common, (
            f"Names must be unique across blueprints and modules, "
            f"but these appear in both: {sorted(common)}"
        )
    
        generated_content = _generate_all_blueprints_content(all_blueprints, all_modules)
    
        file_path = root / "robot" / "all_blueprints.py"
    
        if "CI" in os.environ:
            if not file_path.exists():
                pytest.fail(f"all_blueprints.py does not exist at {file_path}")
    
            current_content = file_path.read_text()
            if current_content != generated_content:
                diff = difflib.unified_diff(
                    current_content.splitlines(keepends=True),
                    generated_content.splitlines(keepends=True),
                    fromfile="all_blueprints.py (current)",
                    tofile="all_blueprints.py (generated)",
                )
                diff_str = "".join(diff)
>               pytest.fail(
                    f"all_blueprints.py is out of date. Run "
                    f"`pytest dimos/robot/test_all_blueprints_generation.py` locally to update.\n\n"
                    f"Diff:\n{diff_str}"
                )
E               Failed: all_blueprints.py is out of date. Run `pytest dimos/robot/test_all_blueprints_generation.py` locally to update.
E               
E               Diff:
E               --- all_blueprints.py (current)
E               +++ all_blueprints.py (generated)
E               @@ -225,6 +225,9 @@
E                    "joystick-module": "dimos.robot.unitree.b1.joystick_module.JoystickModule",
E                    "keyboard-teleop": "dimos.robot.unitree.keyboard_teleop.KeyboardTeleop",
E                    "keyboard-teleop-module": "dimos.teleop.keyboard.keyboard_teleop_module.KeyboardTeleopModule",
E               +    "libero-connection": "dimos.benchmark.libero_pro.connection.LiberoConnection",
E               +    "libero-recorder": "dimos.benchmark.libero_pro.connection.LiberoRecorder",
E               +    "libero-video-recorder": "dimos.benchmark.libero_pro.video.LiberoVideoRecorder",
E                    "local-planner": "dimos.navigation.cmu_nav.modules.local_planner.local_planner.LocalPlanner",
E                    "manipulation-module": "dimos.manipulation.manipulation_module.ManipulationModule",
E                    "map": "dimos.robot.unitree.type.map.Map",

all_blueprints = {'a1z-planner-coordinator': 'dimos.robot.manipulators.a1z.blueprints.basic:a1z_planner_coordinator', 'alfred-nav': 'di...rs.a1z.blueprints.basic:coordinator_a1z', 'coordinator-basic': 'dimos.control.blueprints.basic:coordinator_basic', ...}
all_modules = {'alfred-high-level': 'dimos.robot.diy.alfred.effector_high_level.AlfredHighLevel', 'arm-command-module': 'dimos.teleo...t_extensions.ArmTeleopModule', 'b-box-navigation-module': 'dimos.navigation.bbox_navigation.BBoxNavigationModule', ...}
common     = set()
current_content = '# Copyright 2025-2026 Dimensional Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the "License");\n# you m...sted.blueprints.cloudflare.WristCamera",\n    "zed-camera": "dimos.hardware.sensors.camera.zed.camera.ZEDCamera",\n}\n'
diff       = <generator object unified_diff at 0xffd7a745dd80>
diff_str   = '--- all_blueprints.py (current)\n+++ all_blueprints.py (generated)\n@@ -225,6 +225,9 @@\n     "joystick-module": "dim...dule": "dimos.manipulation.manipulation_module.ManipulationModule",\n     "map": "dimos.robot.unitree.type.map.Map",\n'
file_path  = PosixPath('.../dimos/robot/all_blueprints.py')
generated_content = '# Copyright 2025-2026 Dimensional Inc.\n#\n# Licensed under the Apache License, Version 2.0 (the "License");\n# you m...sted.blueprints.cloudflare.WristCamera",\n    "zed-camera": "dimos.hardware.sensors.camera.zed.camera.ZEDCamera",\n}\n'
root       = PosixPath('.../dimos/dimos/dimos')

dimos/robot/test_all_blueprints_generation.py:76: Failed

To view more test analytics, go to the Test Analytics Dashboard
_{📋 Got 3 mins? Take this short survey to help us improve Test Analytics.}