fix(agent-loop): let a concluding tool result beat same-step steering

concludesTurn is terminal: a completed step now carries the concluded fact
to the driver, which ends the turn immediately instead of letting steering
that arrived during the tool batch (or from an agent/stopping listener)
reopen it. The steering is not lost — it drained into the log as
steering/message before the decision point, so it feeds the next turn's
request. Also annotates the driver's unreachable invariant guards
(exhaustiveness default, abort-slot ownership) for the coverage gate.

docs/architecture.md

@@ -100,6 +100,7 @@ forever:
         each model-order result -> ordered tools/post-execute -> 'tool/result'
       drain accepted tool context and steering
       'step/end'
+      a concluding tool result ends the turn; drained steering waits for the next turn
       continue when tools or steering require another step
       otherwise agent/stopping -> drain once more -> continue only for steering
     'turn/end' -> agent/idle