Fix __all__ duplicates, add hover-label regression test, defer styling kwargs to TODO

- Remove duplicate plot_bacon/plot_power_curve/plot_pretrends_power from
  __all__ (were listed in both category sections)
- Add regression test asserting plotly event study traces preserve period
  labels in customdata/hovertemplate
- Add __all__ uniqueness assertion to export test
- Track plotly styling kwargs parity as deferred P2 in TODO.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: igerber

TODO.md

@@ -69,6 +69,7 @@ Deferred items from PR reviews that were not addressed before merge.
 | R comparison tests spawn separate `Rscript` per test (slow CI) | `tests/test_methodology_twfe.py:294` | #139 | Low |
 | CS R helpers hard-code `xformla = ~ 1`; no covariate-adjusted R benchmark for IRLS path | `tests/test_methodology_callaway.py` | #202 | Low |
 | ~376 `duplicate object description` Sphinx warnings — caused by autodoc `:members:` on dataclass attributes within manual API pages (not from autosummary stubs); fix requires restructuring `docs/api/*.rst` pages to avoid documenting the same attribute via both `:members:` and inline `autosummary` tables | `docs/api/*.rst` | — | Low |
+| Plotly renderers silently ignore styling kwargs (marker, markersize, linewidth, capsize, ci_linewidth) that the matplotlib backend honors; thread them through or reject when `backend="plotly"` | `visualization/_event_study.py`, `_diagnostic.py`, `_power.py` | #222 | Medium |
 
 ---
 

diff_diff/__init__.py

@@ -224,7 +224,6 @@
     "BaconDecompositionResults",
     "Comparison2x2",
     "bacon_decompose",
-    "plot_bacon",
     # Results
     "DiDResults",
     "MultiPeriodDiDResults",
@@ -319,14 +318,12 @@
     "simulate_mde",
     "simulate_power",
     "simulate_sample_size",
-    "plot_power_curve",
     # Pre-trends power analysis
     "PreTrendsPower",
     "PreTrendsPowerResults",
     "PreTrendsPowerCurve",
     "compute_pretrends_power",
     "compute_mdv",
-    "plot_pretrends_power",
     # Survey support
     "SurveyDesign",
     "SurveyMetadata",

tests/test_visualization_plotly.py

@@ -300,3 +300,30 @@ def test_all_plots_in_all(self):
             "plot_group_time_heatmap",
         ]:
             assert name in diff_diff.__all__, f"{name} missing from diff_diff.__all__"
+
+    def test_no_duplicates_in_all(self):
+        import diff_diff
+
+        seen = set()
+        for name in diff_diff.__all__:
+            assert name not in seen, f"Duplicate in __all__: {name}"
+            seen.add(name)
+
+
+class TestPlotlyEventStudyHover:
+    """Regression: plotly event study must preserve period labels in hover."""
+
+    def test_string_periods_in_customdata(self):
+        from diff_diff import plot_event_study
+
+        effects = {"pre": 0.0, "post": 0.5}
+        se = {"pre": 0.1, "post": 0.15}
+        fig = plot_event_study(
+            effects=effects, se=se, backend="plotly", show=False
+        )
+        # At least one point trace should have customdata with original labels
+        point_traces = [t for t in fig.data if t.mode == "markers"]
+        assert len(point_traces) > 0
+        for trace in point_traces:
+            assert trace.customdata is not None, "Missing customdata on point trace"
+            assert trace.hovertemplate is not None, "Missing hovertemplate"