feat: release 2.4.0 with original cases and automatic human review

tests/unit/data_engine/test_evidence_sources.py

@@ -1,5 +1,7 @@
 from copy import deepcopy
 
+import pytest
+
 from artemis.data_engine.evidence_sources import recorded_sources
 
 
@@ -59,6 +61,21 @@ def test_sources_remain_separate_and_references_use_host_ids():
     assert value["sources"][1]["category"] == "interface"
 
 
+def test_window_label_change_does_not_attribute_all_steps_to_the_first_title():
+    first = record("computer", "window", call_id="c1")
+    second = record("computer", "window", call_id="c2")
+    first["source"]["label"] = "first page"
+    second["source"]["label"] = "second page"
+    result = recorded_sources(
+        [{"step_id": "s1", "action_taken": first}, {"step_id": "s2", "action_taken": second}]
+    )
+    source = result["sources"][0]
+    assert result["total_sources"] == 1
+    assert source["reference_count"] == 2
+    assert source["label"] == ""
+    assert source["label_varies"] is True
+
+
 def test_model_arguments_and_unsourced_images_do_not_fabricate_source_metadata():
     value = recorded_sources(
         [
@@ -103,3 +120,98 @@ def test_partial_source_metadata_does_not_hide_unknown_actions_in_the_same_step(
     )
     assert value["total_sources"] == 1
     assert value["unattributed_step_count"] == 1
+
+
+def android_receipt():
+    return {
+        "trace_id": "capture-trace",
+        "type": "tool",
+        "name": "android_file",
+        "status": "success",
+        "payload": {
+            "result": {
+                "ok": True,
+                "action": "screenshot",
+                "verified": True,
+                "device_serial": "test-phone",
+                "trace_path": "artifacts/android/home.png",
+                "sha256": "a" * 64,
+                "captured_at": "2026-10-28T00:00:00Z",
+            }
+        },
+    }
+
+
+def test_android_receipts_join_computer_sources_and_deduplicate_nested_tool_traces():
+    tool = android_receipt()
+    duplicate = {**deepcopy(tool), "trace_id": "outer-wrapper"}
+    steps = [
+        {
+            "step_id": "mixed",
+            "action_taken": record("computer", "window"),
+            "generic_tools": [tool, duplicate],
+        },
+        {"step_id": "final", "generic_tools": [tool]},
+        {"step_id": "empty", "action_taken": None, "generic_tools": []},
+    ]
+    before = deepcopy(steps)
+    result = recorded_sources(steps)
+    sources = {source["kind"]: source for source in result["sources"]}
+    assert set(sources) == {"android", "computer"}
+    assert sources["android"]["target_id"] == "test-phone"
+    assert sources["android"]["reference_count"] == 2
+    assert sources["android"]["references"][0]["trace_id"] == "capture-trace"
+    assert sources["android"]["references"][0]["artifact_path"] == "artifacts/android/home.png"
+    assert result["unattributed_step_count"] == 0
+    assert steps == before
+
+
+@pytest.mark.parametrize("invalid", ["failed", "unverified", "different_tool", "arguments_only"])
+def test_only_successful_android_capture_receipts_supply_provenance(invalid):
+    tool = android_receipt()
+    if invalid == "failed":
+        tool["status"] = "failed"
+    elif invalid == "unverified":
+        tool["payload"]["result"]["verified"] = False
+    elif invalid == "different_tool":
+        tool["name"] = "read_note"
+    else:
+        tool["payload"] = {"args": tool["payload"]["result"]}
+    value = recorded_sources(
+        [{"step_id": "s", "action_taken": {"action": "tap"}, "generic_tools": [tool]}]
+    )
+    assert value["sources"] == []
+    assert value["unattributed_step_count"] == 1
+
+
+def test_capture_receipt_does_not_cover_an_unattributed_action_in_the_same_step():
+    value = recorded_sources(
+        [{"step_id": "s", "action_taken": {"action": "tap"}, "generic_tools": [android_receipt()]}]
+    )
+    assert value["sources"][0]["kind"] == "android"
+    assert value["unattributed_step_count"] == 1
+
+
+def test_flash_capture_receipt_replaces_only_its_matching_action_record():
+    tool = android_receipt()
+    action = {"action": "android_file", "args": {"action": "screenshot", "filename": "home.png"}}
+    value = recorded_sources([{"step_id": "s", "action_taken": action, "generic_tools": [tool]}])
+    assert value["sources"][0]["reference_count"] == 1
+    assert value["unattributed_step_count"] == 0
+    action["args"]["filename"] = "missing.png"
+    value = recorded_sources([{"step_id": "s", "action_taken": action, "generic_tools": [tool]}])
+    assert value["unattributed_step_count"] == 1
+
+
+def test_note_and_final_report_actions_do_not_claim_device_evidence_or_missing_sources():
+    value = recorded_sources(
+        [
+            {
+                "step_id": "note",
+                "action_taken": {"action": "save_note", "args": {"content": "device claim"}},
+            },
+            {"step_id": "final", "action_taken": {"action": "report_task_status"}},
+        ]
+    )
+    assert value["sources"] == []
+    assert value["unattributed_step_count"] == 0