fix(tui): establish 2-tier readiness model, modal/hint token separation, and adapter modal contracts

- Separate TUI dialog detection into blocking gate layer (_MAM_MODAL_TOKENS) and recovery layer (_MAM_HINT_TOKENS) to eliminate idle dialog starvation
- Add modal_tokens contract across agent adapters (claude, cline) with dynamic scope facts resolution in send_keys_safe
- Implement fail-closed resolution for ambiguous same-kind panes (R-1) and enforce WORKSPACE_ROOT export (R-2)
- Preserve session on TUI readiness timeout when PID is alive for diagnostics
- Add comprehensive test suite in tests/test_c1_tui_readiness.py and adapter contract assertions in test_a4

.agents/skills/lib_py/agents/base.py

@@ -73,6 +73,18 @@ class BaseAgentAdapter:
     def input_rule_pattern(self) -> Optional[str]:
         return None
 
+    @property
+    def modal_tokens(self) -> Optional[str]:
+        return None
+
+    @property
+    def strong_ready_tokens(self) -> str:
+        return self.ready_tokens
+
+    @property
+    def weak_ready_tokens(self) -> str:
+        return ''
+
     def derive_session_name(self, slug: str, role: str = "creator") -> str:
         r = role.lower()
         return f"{slug}-{r}-{self.name}"