From 6f1cedf200356d6c4f404501fd48524ae482f76c Mon Sep 17 00:00:00 2001
From: abrichr <richard.abrich@mldsai.com>
Date: Sun, 18 Oct 2026 14:56:07 -0400
Subject: [PATCH] test(flow): induce --probe-on probes a desktop or remote test
 copy

For a test copy declared on windows, macos, linux, rdp or citrix, each probe
run opens a fresh backend from the deployment file's backend section through
the factory, resets the copy with reset_command, and never opens a browser.
The read-back still decides.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 .../tests/test_probe_induction_surfaces.py    | 115 ++++++++++++++++++
 1 file changed, 115 insertions(+)
 create mode 100644 packages/flow/tests/test_probe_induction_surfaces.py

diff --git a/packages/flow/tests/test_probe_induction_surfaces.py b/packages/flow/tests/test_probe_induction_surfaces.py
new file mode 100644
index 000000000..c3b332205
--- /dev/null
+++ b/packages/flow/tests/test_probe_induction_surfaces.py
@@ -0,0 +1,115 @@
+"""``induce --probe-on`` probes a test copy on a desktop or remote surface.
+
+The deployment file declares a Windows, macOS, Linux, RDP or Citrix test copy.
+:class:`~openadapt_flow.compiler.probing.DeploymentProbeTarget` resets it with
+``reset_command`` and opens a fresh backend from the file's ``backend:``
+section for every probe run, through the factory. It never opens a browser.
+The screen side is the scripted MockMed session from test_probe_induction.py,
+standing in for the desktop app; writes land in the same HTTP test copy, and
+the read-back decides. See docs/BACKEND_PARITY.md.
+"""
+
+# ruff: noqa: F811 - pytest fixtures imported from test_probe_induction
+
+from __future__ import annotations
+
+import sys
+
+import pytest
+
+from openadapt_flow.compiler import probing
+from openadapt_flow.compiler.probing import (
+    DeploymentProbeTarget,
+    RunSignal,
+    probe_and_induce,
+    runtime_signal_of,
+)
+from openadapt_flow.deployment import DeploymentConfig
+from openadapt_flow.runtime.replayer import Replayer
+from tests.test_probe_induction import (  # noqa: F401 - pytest fixtures
+    MockMedBackend,
+    MockMedSession,
+    MockMedVision,
+    branch_traces,
+    contract,
+    mockmed,
+)
+
+SECTIONS = {
+    "windows": {"kind": "windows", "agent_url": "http://127.0.0.1:5001"},
+    "macos": {"kind": "macos", "macos_app": "TextEdit"},
+    "linux": {"kind": "linux", "linux_app": "notes", "linux_window_title": "Notes"},
+    "rdp": {"kind": "rdp", "rdp_host": "10.0.0.5"},
+    "citrix": {
+        "kind": "citrix",
+        "rdp_window": "wfica32",
+        "rdp_readiness_text": "Patient Notes",
+    },
+}
+
+
+@pytest.mark.parametrize("kind", sorted(SECTIONS))
+def test_a_desktop_test_copy_is_probed_through_its_own_backend(
+    tmp_path,
+    mockmed,
+    contract,
+    monkeypatch,
+    kind,
+):
+    import openadapt_flow.backends.factory as factory
+
+    url, _db = mockmed
+    built: list = []
+    closed: list = []
+
+    def build_backend(cfg, **kwargs):
+        assert kwargs.get("page") is None
+        built.append(cfg.kind)
+        backend = MockMedBackend(MockMedSession(url))
+        backend.close = lambda: closed.append(cfg.kind)  # type: ignore[attr-defined]
+        return backend
+
+    def replay(self, backend, workflow, bundle_dir, run_dir, params) -> RunSignal:
+        # The scripted session's templates are told apart by its own vision;
+        # everything else is the target's real code path.
+        report = Replayer(
+            backend, vision=MockMedVision(backend.session), poll_interval_s=0.01
+        ).run(workflow, bundle_dir=bundle_dir, run_dir=run_dir, params=params)
+        return RunSignal(runtime_signal_of(report), model_calls=report.model_calls)
+
+    monkeypatch.setattr(factory, "build_backend", build_backend)
+    monkeypatch.setattr(DeploymentProbeTarget, "_replay", replay)
+    sync_api = pytest.importorskip("playwright.sync_api")
+    monkeypatch.setattr(
+        sync_api, "sync_playwright", lambda: pytest.fail("no browser for a desktop")
+    )
+
+    reset = (
+        "import urllib.request; urllib.request.urlopen(urllib.request.Request("
+        f"{url + 'api/reset'!r}, data=b'{{}}', method='POST'), timeout=5).close()"
+    )
+    cfg = DeploymentConfig.model_validate(
+        {
+            "name": f"{kind}-test-copy",
+            "backend": SECTIONS[kind],
+            "test_copy": {
+                "declared": True,
+                "reset_command": [sys.executable, "-c", reset],
+                "reward_contract": str(contract),
+            },
+        }
+    )
+    assert probing.probe_target_refusals(cfg) == []
+    target = DeploymentProbeTarget(cfg)
+    result = probe_and_induce(
+        branch_traces(tmp_path),
+        target=target,
+        reward_contract=contract,
+        work_dir=tmp_path / "probe",
+    )
+
+    assert result.certified is True
+    assert result.probe_verdicts[0].certified == "conditional"
+    assert result.probe_runs and set(built) == {kind}
+    assert len(built) == len(result.probe_runs) == len(closed)
+    assert sum(r.model_calls for r in result.probe_runs) == 0