rpa_vision_v3/tests/unit/test_navigate_handler_e2e.py

"""End-to-end mocked test for navigate action handler — 3 edge-case scenarios.

Tests the _handle_navigate_action handler with mocked OCR/VLM, verifying:
- Nominal: all resolved, coords populated in variables
- OCR miss + VLM fail: no phantom coords, all_resolved=False
- No screenshot: error="no_screenshot", False return

NOTE: The handler uses lazy imports inside its body. Mock targets must be
at the source module (core.navigation.action_resolver.navigate_login) rather
than the package-level re-export (core.navigation.navigate_login).
"""

import pytest
from unittest.mock import patch, MagicMock
from core.navigation.action_resolver import NavigateCoords, NavigateResult
from core.navigation import _handle_navigate_action


def _patch_all_deps(navigate_login_result=None, navigate_login_side_effect=None):
    """Return stacked patches for handler's lazy imports + navigate_login."""
    nl_mock = MagicMock(return_value=navigate_login_result) if navigate_login_result else None
    if navigate_login_side_effect:
        nl_mock = MagicMock(side_effect=navigate_login_side_effect)

    return (
        patch("core.llm.extract_grid_from_image", return_value=[]),
        patch("core.extraction.vlm_client.make_vllm_client", return_value=MagicMock()),
        patch("core.navigation.action_resolver.make_ocr_detailed_from_grid",
              return_value=MagicMock(return_value=[])),
        patch("core.navigation.action_resolver.navigate_login", nl_mock),
    )


class TestNominalCase:
    """All fields grounded → coords populated, all_resolved=True."""

    def test_nominal_coords_populated(self):
        mock_result = NavigateResult(
            login_coords=NavigateCoords(x_pct=0.15, y_pct=0.07, method="ocr_anchor"),
            password_coords=NavigateCoords(x_pct=0.15, y_pct=0.25, method="ocr_anchor"),
            submit_coords=NavigateCoords(x_pct=0.50, y_pct=0.35, method="ocr_anchor"),
            all_resolved=True,
        )

        action = {"parameters": {"action": "login"}}
        replay_state = {
            "last_screenshot_path": "/tmp/login_screen.png",
            "screen_width": 1920,
            "screen_height": 1080,
        }

        p1, p2, p3, p4 = _patch_all_deps(navigate_login_result=mock_result)
        with p1, p2, p3, p4:
            result = _handle_navigate_action(action, replay_state, "test-session")

        assert result is True
        vars_ = replay_state["variables"]
        assert "navigate_login_coords" in vars_
        assert vars_["navigate_login_coords"]["x_pct"] == 0.15
        assert "navigate_password_coords" in vars_
        assert "navigate_submit_coords" in vars_
        assert vars_["navigate_result"]["all_resolved"] is True


class TestOcrMissVlmFail:
    """OCR misses target + VLM grounder also fails → no phantom coords."""

    def test_no_phantom_coords_on_failure(self):
        mock_result = NavigateResult(
            login_coords=None,
            password_coords=None,
            submit_coords=None,
            all_resolved=False,
            error="grounding failed — no login form elements found",
        )

        action = {"parameters": {"action": "login"}}
        replay_state = {
            "last_screenshot_path": "/tmp/no_login_form.png",
            "screen_width": 1920,
            "screen_height": 1080,
        }

        p1, p2, p3, p4 = _patch_all_deps(navigate_login_result=mock_result)
        with p1, p2, p3, p4:
            result = _handle_navigate_action(action, replay_state, "test-session")

        assert result is False
        vars_ = replay_state["variables"]
        # No coords keys should be present (coords are None → not stored)
        assert "navigate_login_coords" not in vars_
        assert "navigate_password_coords" not in vars_
        assert "navigate_submit_coords" not in vars_
        # Error must be non-empty
        assert vars_["navigate_result"]["all_resolved"] is False
        assert "grounding failed" in vars_["navigate_result"]["error"]


class TestNoScreenshot:
    """No screenshot in replay_state → error="no_screenshot", False."""

    def test_no_screenshot_error(self):
        action = {"parameters": {"action": "login"}}
        replay_state = {}  # No screenshot at all

        result = _handle_navigate_action(action, replay_state, "test-session")

        assert result is False
        vars_ = replay_state["variables"]
        assert vars_["navigate_login_coords"]["error"] == "no_screenshot"

    def test_empty_screenshot_path(self):
        action = {"parameters": {"action": "login"}}
        replay_state = {"last_screenshot_path": ""}

        result = _handle_navigate_action(action, replay_state, "test-session")

        assert result is False
        vars_ = replay_state["variables"]
        assert vars_["navigate_login_coords"]["error"] == "no_screenshot"


class TestNeverFailReplay:
    """Handler must never raise — even on malformed input, returns False."""

    def test_missing_parameters(self):
        action = {}  # No "parameters" key
        replay_state = {"last_screenshot_path": "/tmp/x.png"}

        mock_result = NavigateResult(all_resolved=False, error="no params")
        p1, p2, p3, p4 = _patch_all_deps(navigate_login_result=mock_result)
        with p1, p2, p3, p4:
            result = _handle_navigate_action(action, replay_state, "test-session")
        assert result is False

    def test_exception_in_inner_call(self):
        action = {"parameters": {"action": "login"}}
        replay_state = {
            "last_screenshot_path": "/tmp/login.png",
            "screen_width": 1920,
            "screen_height": 1080,
        }

        p1, p2, p3, p4 = _patch_all_deps(navigate_login_side_effect=RuntimeError("boom"))
        with p1, p2, p3, p4:
            result = _handle_navigate_action(action, replay_state, "test-session")

        assert result is False
        vars_ = replay_state["variables"]
        assert vars_["navigate_result"]["all_resolved"] is False
        assert "boom" in vars_["navigate_result"]["error"]