Add outlier-robust reversal_rank alpha and investable-universe filter

reversal_rank weights the 5-day reversal signal by bounded cross-sectional
rank instead of z-score, so a few extreme A-share pct_change outliers
(newly listed / post-suspension / limit-up names) can no longer dominate
the book. compute_alpha gains an optional per-date investable-universe
mask (tradable, non-ST, seasoned, top-liquidity) applied to the signal
before weighting, exposed via --liquid-universe/--universe-top-n.

combo combine now accepts a single alpha as an identity passthrough so a
one-alpha pipeline run needs no synthetic second input.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

pipeline/combo/cli.py

@@ -26,8 +26,8 @@ def combo():
 def combine(alpha_paths, combo_name, method, output_dir):
     """Combine multiple alphas and save as parquet."""
     paths = [p.strip() for p in alpha_paths.split(",") if p.strip()]
-    if len(paths) < 2:
-        click.echo("Error: --alpha-paths requires at least 2 comma-separated paths", err=True)
+    if len(paths) < 1:
+        click.echo("Error: --alpha-paths requires at least 1 path", err=True)
         return
 
     result = combine_alphas(