fix(metadata): qwen3.6-plus has a 1M context window (#27008)

qwen3.6-plus did not have an explicit entry in DEFAULT_CONTEXT_LENGTHS,
so the longest-substring fallback matched the generic 'qwen': 131072
catch-all. That dropped the effective context limit from 1,048,576
tokens to 131,072, prematurely lowered the compression threshold, and
produced misleading warnings about main/compression context mismatch
in long sessions.

Add an explicit 'qwen3.6-plus': 1048576 entry before the catch-all and
cover it with a regression test (bare, qwen/, and dashscope/ prefixes).

Note: PR #6599 also mentions touching model_metadata.py but the actual
diff only edits hermes_cli/models.py, so this fix is independent and
not duplicated by that PR.

Closes #27008

tests/agent/test_model_metadata.py

@@ -746,6 +746,16 @@ class TestGetModelContextLength:
         mock_fetch.return_value = {}
         assert get_model_context_length("qwen3-coder") == 262144
 
+    @patch("agent.model_metadata.fetch_model_metadata")
+    def test_qwen3_6_plus_context_length(self, mock_fetch):
+        """qwen3.6-plus has a 1M context window, not the generic 128K Qwen default."""
+        mock_fetch.return_value = {}
+        assert get_model_context_length("qwen3.6-plus") == 1048576
+        # Provider-prefixed variants must resolve to the same explicit entry
+        # via the longest-substring fallback (no portal/OR cache available).
+        assert get_model_context_length("qwen/qwen3.6-plus") == 1048576
+        assert get_model_context_length("dashscope/qwen3.6-plus") == 1048576
+
     @patch("agent.model_metadata.fetch_model_metadata")
     def test_qwen_generic_context_length(self, mock_fetch):
         """Generic qwen models still get the 128K default."""