test(harness): flag a mode that draws nothing without reporting it

scripts/check_plugin.py

@@ -41,6 +41,7 @@
 )
 from src.plugin_system.testing.harness import (  # noqa: E402
     RenderResult, render_plugin_matrix, compare_to_goldens, write_goldens,
+    check_empty_claimed,
     check_scale_up,
 )
 from src.plugin_system.testing.sizes import (  # noqa: E402
@@ -115,6 +116,11 @@ def check_one(plugin_id: str, search_dirs: List[str], sizes, mock_data: Dict,
     declared = load_manifest(plugin_dir).get("display", {}).get("design_size", {})
     design_size = (int(declared.get("width", 128)), int(declared.get("height", 32)))
     fill_strict = spec.get("fill_check") == "strict"
+    # A mode that renders nothing without returning False is never skipped by
+    # the display controller, so it holds a blank panel for its whole duration.
+    # Warn-only by default: a scroll mode's first frame is legitimately its
+    # blank scroll-in buffer.
+    empty_strict = spec.get("empty_check") == "strict"
 
     # Every run: the base config, plus one per harness.json "variant" —
     # a config overlay with its own golden dir (e.g. adaptive layout mode
@@ -142,6 +148,7 @@ def check_one(plugin_id: str, search_dirs: List[str], sizes, mock_data: Dict,
             compare_to_goldens(results, golden_dir)
 
         check_scale_up(results, design_size=design_size, strict=fill_strict)
+        check_empty_claimed(results, strict=empty_strict)
 
         # Tag variant runs so the report and PNG dumps stay distinguishable.
         if variant_name:
@@ -178,6 +185,9 @@ def print_report(all_results: Dict[str, List[RenderResult]]) -> bool:
                     # warn-only underfill: big panel left mostly empty
                     ex, ey = r.fill_extent
                     detail += f" (fill warn: extent {ex:.0%}x{ey:.0%})"
+                if r.empty_claimed and r.empty_ok is None:
+                    detail += (f" (empty warn: drew nothing but display() returned"
+                               f" {r.display_returned!r}, so the mode is not skipped)")
             else:
                 everything_ok = False
                 if r.error is not None:
@@ -191,6 +201,11 @@ def print_report(all_results: Dict[str, List[RenderResult]]) -> bool:
                     ex, ey = r.fill_extent or (0.0, 0.0)
                     status = "FAIL"
                     detail = f" fill: extent {ex:.0%}x{ey:.0%} below required coverage"
+                elif r.empty_ok is False:
+                    status = "FAIL"
+                    detail = (f" drew nothing but display() returned"
+                              f" {r.display_returned!r}; return False so the"
+                              f" controller skips the mode")
                 else:
                     status, detail = "FAIL", ""
             print(f"  [{status}] {r.size_label:>7}  {r.mode}{detail}")

src/plugin_system/testing/harness.py

@@ -73,6 +73,11 @@ class RenderResult:
     golden_ok: Optional[bool] = None
     golden_diff_pixels: int = 0
     golden_max_delta: int = 0
+    # what display() handed back; the controller skips a mode only on False
+    display_returned: Any = None
+    # empty-frame check: rendered nothing while not reporting "no content"
+    empty_claimed: Optional[bool] = None   # True when that happened
+    empty_ok: Optional[bool] = None        # False only in strict mode
     # fill / scale-up check (populated only for sizes >= 2x the design size)
     fill_checked: bool = False
     fill_ok: Optional[bool] = None       # False only in strict mode
@@ -92,6 +97,8 @@ def ok(self) -> bool:
             return False
         if self.fill_ok is False:
             return False
+        if self.empty_ok is False:
+            return False
         return True
 
 
@@ -132,21 +139,25 @@ def _instantiate(plugin_id: str, manifest: Dict[str, Any], plugin_dir: Path,
     return plugin_instance
 
 
-def _render_mode(plugin_instance: Any, mode: str) -> None:
+def _render_mode(plugin_instance: Any, mode: str) -> Any:
     """Render a specific screen. Prefer an explicit display_mode kwarg; otherwise
     drive the plugin's internal mode state machine (first display() call renders
-    modes[current_mode_index] when current_display_mode is None)."""
+    modes[current_mode_index] when current_display_mode is None).
+
+    Returns whatever display() returned. The display controller skips a mode
+    whose display() returns False, so that value decides whether an empty mode
+    is rotated past or sat on -- which makes it worth reporting rather than
+    discarding."""
     sig = inspect.signature(plugin_instance.display)
     if "display_mode" in sig.parameters:
-        plugin_instance.display(force_clear=True, display_mode=mode)
-        return
+        return plugin_instance.display(force_clear=True, display_mode=mode)
 
     modes = getattr(plugin_instance, "modes", None)
     if modes and mode in modes:
         plugin_instance.current_mode_index = list(modes).index(mode)
     if hasattr(plugin_instance, "current_display_mode"):
         plugin_instance.current_display_mode = None
-    plugin_instance.display(force_clear=False)
+    return plugin_instance.display(force_clear=False)
 
 
 def _freeze(freeze_time: Optional[str]):
@@ -234,7 +245,7 @@ def _render_size(plugin_id, manifest, plugin_dir, config, mock_data,
                     logger.warning("update() raised a non-connectivity error for %s [%s]: %s",
                                    plugin_id, mode, e)
             if result.error is None:
-                _render_mode(inst, mode)
+                result.display_returned = _render_mode(inst, mode)
                 result.image = dm.get_image()
                 result.overflow = dm.check_overflow()
         except Exception as e:  # noqa: BLE001 — a display crash is a real failure
@@ -341,6 +352,44 @@ def fill_metrics(image: Image.Image) -> Tuple[float, float, float]:
     return (extent_x, extent_y, ink)
 
 
+def check_empty_claimed(results: List[RenderResult],
+                        strict: bool = False) -> List[RenderResult]:
+    """Flag a mode that rendered nothing without reporting "no content".
+
+    The display controller skips a mode whose ``display()`` returns False, and
+    treats anything else -- including None -- as "content was shown". A mode
+    that draws nothing and does not return False therefore holds whatever is on
+    the panel for its whole display duration. Since a mode switch clears first,
+    that is a blank screen. Two sports plugins shipped exactly this: their
+    ``display()`` returned None on every path, so an out-of-season league sat
+    blank for its full duration rather than being rotated past.
+
+    Warn-only by default, because a blank frame is not automatically wrong: a
+    scroll mode whose first frame is its blank scroll-in buffer renders empty
+    and is behaving correctly. ``strict=True`` sets ``empty_claimed`` such that
+    ``RenderResult.ok`` fails -- opt in per plugin via harness.json
+    ``{"empty_check": "strict"}`` once its modes are known to draw on the
+    fixture data.
+
+    Note this can only catch what the fixtures actually render. A plugin whose
+    harness fixture seeds content never exercises its empty path here; the
+    source-level gate in the plugins repo covers that case.
+    """
+    for r in results:
+        if r.image is None or r.error is not None:
+            continue
+        # An explicit False is the plugin correctly saying "nothing to show".
+        if r.display_returned is False:
+            continue
+        if r.image.convert("L").point(
+                lambda p: 255 if p > _LIT_THRESHOLD else 0).getbbox() is not None:
+            continue
+        r.empty_claimed = True
+        if strict:
+            r.empty_ok = False
+    return results
+
+
 def check_scale_up(results: List[RenderResult],
                    design_size: Tuple[int, int] = (128, 32),
                    min_extent: float = _MIN_FILL_EXTENT,

test/test_harness_empty_claimed.py

@@ -0,0 +1,103 @@
+"""Tests for the harness empty-frame check (src/plugin_system/testing/harness.py).
+
+The display controller skips a mode whose display() returns False and treats
+anything else -- including None -- as "content was shown". A mode that draws
+nothing without returning False is therefore never skipped, and since a mode
+switch clears the panel first, it sits on a blank screen for its whole display
+duration.
+
+Two sports plugins shipped exactly that: their display() returned None on every
+path, so an out-of-season league held a blank panel instead of being rotated
+past. The harness rendered those modes and passed them, because it discarded
+the return value entirely.
+"""
+
+from PIL import Image
+
+from src.plugin_system.testing.harness import RenderResult, check_empty_claimed
+
+
+def _blank(w=64, h=32):
+    return Image.new("RGB", (w, h), (0, 0, 0))
+
+
+def _drawn(w=64, h=32):
+    img = _blank(w, h)
+    img.paste(Image.new("RGB", (10, 10), (255, 255, 255)), (5, 5))
+    return img
+
+
+def _result(image, returned=None, **kw):
+    return RenderResult("p", 64, 32, "mode", image=image,
+                        display_returned=returned, **kw)
+
+
+class TestCheckEmptyClaimed:
+    def test_blank_frame_returning_none_is_flagged(self):
+        # The shape that shipped: nothing drawn, nothing reported.
+        r = _result(_blank(), returned=None)
+        check_empty_claimed([r])
+        assert r.empty_claimed is True
+
+    def test_blank_frame_returning_true_is_flagged(self):
+        # Just as broken, and more explicit about it.
+        r = _result(_blank(), returned=True)
+        check_empty_claimed([r])
+        assert r.empty_claimed is True
+
+    def test_blank_frame_returning_false_is_fine(self):
+        # The plugin correctly said "no content"; the controller will skip it.
+        r = _result(_blank(), returned=False)
+        check_empty_claimed([r])
+        assert r.empty_claimed is None
+
+    def test_a_drawn_frame_is_fine_whatever_it_returns(self):
+        for returned in (None, True, False):
+            r = _result(_drawn(), returned=returned)
+            check_empty_claimed([r])
+            assert r.empty_claimed is None, returned
+
+    def test_near_black_still_counts_as_drawn(self):
+        # Guard the threshold: content dim enough to look black to the eye is
+        # still content, and flagging it would train people to ignore this.
+        img = _blank()
+        img.paste(Image.new("RGB", (4, 4), (60, 60, 60)), (2, 2))
+        r = _result(img, returned=None)
+        check_empty_claimed([r])
+        assert r.empty_claimed is None
+
+
+class TestWarnVersusStrict:
+    def test_warn_only_by_default(self):
+        # A scroll mode's first frame is legitimately its blank scroll-in
+        # buffer, so this must not fail a run unless opted in.
+        r = _result(_blank(), returned=None)
+        check_empty_claimed([r])
+        assert r.empty_ok is None
+        assert r.ok is True
+
+    def test_strict_fails_the_result(self):
+        r = _result(_blank(), returned=None)
+        check_empty_claimed([r], strict=True)
+        assert r.empty_ok is False
+        assert r.ok is False
+
+    def test_strict_still_allows_an_honest_false(self):
+        r = _result(_blank(), returned=False)
+        check_empty_claimed([r], strict=True)
+        assert r.empty_ok is None
+        assert r.ok is True
+
+
+class TestSkippedResults:
+    def test_a_crashed_render_is_left_alone(self):
+        # error already fails the result; adding a second reason just muddies
+        # the report.
+        r = _result(None, returned=None, error="boom")
+        check_empty_claimed([r], strict=True)
+        assert r.empty_claimed is None
+
+    def test_a_result_with_no_image_is_left_alone(self):
+        r = _result(None, returned=None)
+        check_empty_claimed([r], strict=True)
+        assert r.empty_claimed is None