trajectory plot (steer/heal zigzag + trait-coherence pareto) + barrier-vs-nll gradient pressure log

- plot.py write_trajectory: auth zigzag (steer red / heal green) over the pipeline,
  coherence panel below sharing x, and a trait(x)-vs-coherence(y) pareto map with
  separate steer/heal trajectories from base. PNG via kaleido + interactive html.
  Fixed coherence axes to [0.83,1.01] so ~0.001 noise does not fill the panel.
- run.py: build a stages list carrying full eval dicts; derive the stage table from
  it; persist the steered eval to events.jsonl; render trajectory at end of run.
- heal.py: log g_bar/g_nll = ||grad barrier|| / ||grad sft|| at each logged step.
  >>1 = barrier over-tight (undoing trait); 0 = inert.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

pyproject.toml

@@ -26,6 +26,7 @@ dependencies = [
     "iso-kl-figure",
     "tiny-mfv",
     "srsly>=2.5.3",
+    "kaleido>=1.3.0",
 ]
 
 [tool.uv.sources]