fix(status): correct context percentage calculation and sync consolidator

- Pass resolved self.context_window_tokens to Consolidator instead of
  raw parameter that could be None, preventing consolidation failures
- Calculate percentage against input budget (ctx - max_completion - 1024)
  instead of raw context window, consistent with Consolidator/snip formulas
- Pass actual max_completion_tokens from provider to build_status_content
- Cap percentage display at 999 to prevent runaway values
- Add tests for budget-based percentage and cap behavior

tests/test_build_status.py

@@ -59,3 +59,34 @@ def test_status_100_percent_cached():
         context_tokens_estimate=3000,
     )
     assert "100% cached" in content
+
+
+def test_status_context_pct_uses_budget_not_total():
+    """Percentage should be calculated against input budget, not raw context window."""
+    content = build_status_content(
+        version="0.1.0",
+        model="test",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=120000,
+        max_completion_tokens=8192,
+    )
+    # budget = 128000 - 8192 - 1024 = 118784; pct = 120000/118784*100 ≈ 101%
+    assert "(101% of input budget)" in content
+
+
+def test_status_context_pct_capped_at_999():
+    """Extreme overflow should be capped at 999."""
+    content = build_status_content(
+        version="0.1.0",
+        model="test",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300},
+        context_window_tokens=10000,
+        session_msg_count=10,
+        context_tokens_estimate=100000,
+        max_completion_tokens=4096,
+    )
+    assert "(999% of input budget)" in content