fix: type the health test mode, pace cards with the stream, and size the results panel

README.md

@@ -154,6 +154,11 @@ Forgejo/GitHub mirror, deployment, how the agents are used) is mapped in
 - A faster model on the intent call, which would cut most of the time to
   first card; the grounding stage already measures the trade-off to watch
   (fabrication rate), so the experiment is cheap to run safely.
+- A guaranteed minimum grounding budget. The request deadline is anchored
+  at request start, so an unusually slow intent call can leave grounding
+  with no time at all; raising the deadline works around it (env-tunable),
+  but grounding deserves a floor of its own regardless of what call 1
+  spent.
 - Deeper discovery. A repair loop that re-prompts the model for candidates
   that failed verification would let the prompt chase less obvious work
   without losing the pool, and a novelty signal beyond exact-id exclusion