[Bugfix] Fix misleading context length error messages (#36197)

Signed-off-by: AjAnubolu <anuboluajay@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

tests/entrypoints/llm/test_chat.py

@@ -200,7 +200,7 @@ def test_chat_batch_failure_cleanup(llm_for_failure_test):
     batch_2 = [valid_msg, valid_msg]
     sampling_params = SamplingParams(temperature=0, max_tokens=10)
 
-    with pytest.raises(ValueError, match="context length is only"):
+    with pytest.raises(ValueError, match="maximum context length is"):
         llm.chat(batch_1, sampling_params=sampling_params)
     assert llm.llm_engine.get_num_unfinished_requests() == 0