Add RX task watcher and approval workflow

tests/test_rx_agent_watcher.py

@@ -0,0 +1,189 @@
+"""Unit tests for the model-free RX task watcher."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import pytest
+
+from tools.rx_agent_watcher import (
+    ApprovalDecision,
+    ManualExecutor,
+    WatcherState,
+    handle_task,
+    is_new_task,
+    load_state,
+    mark_completed,
+    parse_task,
+    request_approval,
+    request_stop,
+    save_state,
+)
+
+
+HEAD = "1" * 40
+
+
+def task_text(*, task_id: str = "WATCHER_TEST_001", rf_tx: str = "NO") -> str:
+    hardware = "YES" if rf_tx == "YES" else "NO"
+    risk_level = "RED" if rf_tx == "YES" else "GREEN"
+    return f"""TASK_ID = {task_id}
+TASK_TITLE = Watcher test
+SOURCE_BRANCH = video-development
+EXPECTED_HEAD = {HEAD}
+REQUIRES_APPROVAL = YES
+HARDWARE_ACCESS = {hardware}
+RF_RX = NO
+RF_TX = {rf_tx}
+ALLOW_COMMIT = NO
+ALLOW_PUSH = RX_RESULT_ONLY
+RISK_LEVEL = {risk_level}
+
+# Body
+Do nothing.
+"""
+
+
+def responses(*values: str):
+    iterator = iter(values)
+    return lambda _prompt: next(iterator)
+
+
+def test_task_parsing_and_validation() -> None:
+    task = parse_task(task_text())
+    assert task.task_id == "WATCHER_TEST_001"
+    assert task.source_branch == "video-development"
+    assert task.safety_level == "GREEN"
+    assert not task.rf_tx
+    with pytest.raises(ValueError, match="missing task header"):
+        parse_task("TASK_ID = INCOMPLETE")
+    with pytest.raises(ValueError, match="duplicate"):
+        parse_task(task_text().replace(
+            "TASK_TITLE = Watcher test",
+            "TASK_TITLE = Watcher test\nTASK_TITLE = Duplicate",
+        ))
+
+
+def test_state_persistence_and_completion(tmp_path: Path) -> None:
+    path = tmp_path / "state.json"
+    original = WatcherState(last_seen_task_id="WATCHER_TEST_001", running=True, pid=123)
+    save_state(path, original)
+    assert load_state(path) == original
+    mark_completed(path, "WATCHER_TEST_001")
+    completed = load_state(path)
+    assert completed.last_completed_task_id == "WATCHER_TEST_001"
+    assert completed.deferred_task_id is None
+    with pytest.raises(ValueError, match="last seen"):
+        mark_completed(path, "WATCHER_TEST_002")
+
+
+def test_approval_defer_stop_and_yellow_approve() -> None:
+    green = parse_task(task_text())
+    assert request_approval(green, responses("D"), lambda _text: None) == ApprovalDecision.DEFER
+    assert request_approval(green, responses("S"), lambda _text: None) == ApprovalDecision.STOP
+    yellow_text = task_text().replace(
+        "HARDWARE_ACCESS = NO", "HARDWARE_ACCESS = YES"
+    ).replace("RISK_LEVEL = GREEN", "RISK_LEVEL = YELLOW")
+    yellow = parse_task(yellow_text)
+    assert yellow.safety_level == "YELLOW"
+    assert request_approval(yellow, responses("A"), lambda _text: None) == ApprovalDecision.APPROVE
+
+
+def test_rf_tx_red_gate_requires_separate_phrase() -> None:
+    red = parse_task(task_text(rf_tx="YES"))
+    assert red.safety_level == "RED"
+    assert request_approval(
+        red, responses("A", "yes"), lambda _text: None
+    ) == ApprovalDecision.BLOCKED
+    assert request_approval(
+        red, responses("A", "AUTHORIZE RF TX"), lambda _text: None
+    ) == ApprovalDecision.APPROVE
+
+
+def test_non_rf_red_task_also_requires_separate_phrase() -> None:
+    text = task_text(task_id="FIRMWARE_TEST_001").replace(
+        "RISK_LEVEL = GREEN", "RISK_LEVEL = RED"
+    )
+    red = parse_task(text)
+    assert not red.rf_tx
+    assert request_approval(
+        red, responses("A", "AUTHORIZE RF TX"), lambda _text: None
+    ) == ApprovalDecision.BLOCKED
+    assert request_approval(
+        red, responses("A", "AUTHORIZE FIRMWARE_TEST_001"), lambda _text: None
+    ) == ApprovalDecision.APPROVE
+
+
+def test_duplicate_task_is_suppressed_without_prompt(tmp_path: Path) -> None:
+    text = task_text()
+    task = parse_task(text)
+    state = WatcherState(last_seen_task_id=task.task_id)
+    assert not is_new_task(task, state)
+
+    def forbidden_input(_prompt: str) -> str:
+        raise AssertionError("duplicate task prompted the user")
+
+    status, returned = handle_task(
+        text,
+        HEAD,
+        state,
+        ManualExecutor(tmp_path),
+        dry_run=True,
+        input_function=forbidden_input,
+        output_function=lambda _text: None,
+    )
+    assert status == "DUPLICATE_SUPPRESSED"
+    assert returned == state
+    assert list(tmp_path.iterdir()) == []
+
+
+def test_defer_persists_seen_id_and_creates_no_result(tmp_path: Path) -> None:
+    state = WatcherState()
+    status, state = handle_task(
+        task_text(),
+        HEAD,
+        state,
+        ManualExecutor(tmp_path),
+        dry_run=True,
+        input_function=responses("D"),
+        output_function=lambda _text: None,
+    )
+    assert status == "DEFERRED"
+    assert state.last_seen_task_id == "WATCHER_TEST_001"
+    assert state.deferred_task_id == "WATCHER_TEST_001"
+    assert list(tmp_path.iterdir()) == []
+
+
+def test_dry_run_approval_writes_prompt_and_matching_results(tmp_path: Path) -> None:
+    status, state = handle_task(
+        task_text(),
+        HEAD,
+        WatcherState(),
+        ManualExecutor(tmp_path),
+        dry_run=True,
+        input_function=responses("A"),
+        output_function=lambda _text: None,
+    )
+    directory = tmp_path / "WATCHER_TEST_001"
+    assert status == "PREPARED"
+    assert state.last_seen_task_id == "WATCHER_TEST_001"
+    assert state.last_completed_task_id is None
+    assert (directory / "TASK.md").exists()
+    markdown = (directory / "RX_RESULT.md").read_text(encoding="utf-8")
+    result = json.loads((directory / "RX_RESULT.json").read_text(encoding="utf-8"))
+    assert "TASK_STATUS = DRY_RUN_PREPARED" in markdown
+    assert result["task_status"] == "DRY_RUN_PREPARED"
+    assert result["rf_tx"] == "NO"
+    assert result["hardware_actions"] == []
+    with pytest.raises(FileExistsError):
+        ManualExecutor(tmp_path).prepare(
+            parse_task(task_text()), task_text(), HEAD, dry_run=True
+        )
+
+
+def test_stop_request_for_idle_watcher(tmp_path: Path) -> None:
+    state_path = tmp_path / "state.json"
+    save_state(state_path, WatcherState(running=False, pid=None))
+    assert request_stop(state_path, timeout_s=0.1)
+    assert state_path.with_suffix(".json.stop").read_text(encoding="ascii") == "STOP\n"