fix(tests): make predict --truth flag test robust to terminal rendering

The --help-text assertion was brittle to CI's terminal width/color
settings (rich can wrap or re-color the flag name mid-word), causing a
false CI failure even though the flag itself is fine. Inspect the
click command's registered option directly instead of parsing rendered
--help output.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PpxE9nij3ujg9XcuzvQ26q

tests/test_cli_predict.py

@@ -233,6 +233,13 @@ def test_predict_truth_metadata_key_exists():
 
 
 def test_predict_has_truth_flag_default_on():
-    result = runner.invoke(app, ["predict", "--help"])
-    assert "--truth" in result.output
-    assert "--no-truth" in result.output
+    # Inspecting rendered --help text is brittle across terminal
+    # widths/color settings (wraps or re-colors mid-flag); go straight to
+    # the underlying click command's registered option instead.
+    import typer
+
+    predict_cmd = typer.main.get_command(app).commands["predict"]
+    truth_param = next(p for p in predict_cmd.params if p.name == "truth")
+    assert truth_param.opts == ["--truth"]
+    assert truth_param.secondary_opts == ["--no-truth"]
+    assert truth_param.default is True