From d9abbe7fa4c69333a226b7a2d366713b3f071187 Mon Sep 17 00:00:00 2001
From: haran2001 <56040092+haran2001@users.noreply.github.com>
Date: Sun, 17 May 2026 02:29:27 -0700
Subject: [PATCH] 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
---
 agent/model_metadata.py            |  1 +
 tests/agent/test_model_metadata.py | 10 ++++++++++
 2 files changed, 11 insertions(+)

diff --git a/agent/model_metadata.py b/agent/model_metadata.py
index 26a844ccb92..b8ec0d6509e 100644
--- a/agent/model_metadata.py
+++ b/agent/model_metadata.py
@@ -194,6 +194,7 @@ DEFAULT_CONTEXT_LENGTHS = {
     "llama": 131072,
     # Qwen — specific model families before the catch-all.
     # Official docs: https://help.aliyun.com/zh/model-studio/developer-reference/
+    "qwen3.6-plus": 1048576,      # 1M context (DashScope/Alibaba & OpenRouter)
     "qwen3-coder-plus": 1000000,  # 1M context
     "qwen3-coder": 262144,        # 256K context
     "qwen": 131072,
diff --git a/tests/agent/test_model_metadata.py b/tests/agent/test_model_metadata.py
index 7686364dcac..4f2b51293a6 100644
--- a/tests/agent/test_model_metadata.py
+++ b/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."""