feat: add cache salt support to KV cache events (#30827)

Signed-off-by: jthomson04 <jwillthomson19@gmail.com>

test/registered/unit/entrypoints/openai/test_serving_chat.py

@@ -316,6 +316,8 @@ class ServingChatTestCase(unittest.TestCase):
             input_ids=[101, 102, 103],
             stop=["STOP"],
             return_prompt_token_ids=True,
+            cache_salt="tenant-a",
+            extra_key="classification",
         )
 
         with patch(
@@ -329,6 +331,8 @@ class ServingChatTestCase(unittest.TestCase):
         self.assertEqual(adapted.input_ids, [101, 102, 103])
         self.assertTrue(adapted.return_prompt_token_ids)
         self.assertEqual(adapted.sampling_params["stop"], ["STOP"])
+        self.assertEqual(adapted.cache_salt, "tenant-a")
+        self.assertEqual(adapted.extra_key, "classification")
         conv_mock.assert_not_called()
 
     def test_kimi_k3_usage_excludes_assistant_generation_stub(self):

test/registered/unit/entrypoints/openai/test_serving_completions.py

@@ -65,6 +65,29 @@ class ServingCompletionTestCase(unittest.TestCase):
         internal, _ = self.sc._convert_to_internal_request(req)
         self.assertEqual(internal.input_ids, [1, 2, 3, 4])
 
+    def test_cache_salt_and_extra_key_remain_distinct(self):
+        req = CompletionRequest(
+            model="x",
+            prompt=[1, 2, 3, 4],
+            max_tokens=1,
+            cache_salt="tenant-a",
+            extra_key="classification",
+        )
+        internal, _ = self.sc._convert_to_internal_request(req)
+        self.assertEqual(internal.cache_salt, "tenant-a")
+        self.assertEqual(internal.extra_key, "classification")
+
+    def test_single_request_rejects_batched_cache_salt(self):
+        req = CompletionRequest(
+            model="x",
+            prompt=[1, 2, 3, 4],
+            max_tokens=1,
+            cache_salt=["tenant-a"],
+        )
+        internal, _ = self.sc._convert_to_internal_request(req)
+        with self.assertRaisesRegex(ValueError, "single request"):
+            internal.normalize_batch_and_arguments()
+
     # ---------- echo-handling ----------
     def test_echo_with_list_of_strings_streaming(self):
         req = CompletionRequest(