test(minicpmo): teach the audio_embeds tokenizer stub the 0.29 token-id contract

main's #5730 added tests/model_executor/models/minicpmo_4_5/test_audio_embeds_input.py
with an identity tokenizer double that only implements encode/decode. On this
branch MiniCPMO45OmniLLMMultiModalProcessor._get_prompt_updates follows the
vLLM 0.29 prompt-update contract (PromptUpdateDetails.select_text is gone),
so it resolves the <unk> placeholder id once via
tokenizer.convert_tokens_to_ids("<unk>"), which the double lacks:

    AttributeError: '_IdentityTokenizer' object has no attribute 'convert_tokens_to_ids'

Give the double that method. The tests still read only the placeholder text
from PromptUpdateDetails.full, so the returned id is irrelevant to them.
Branch-only rebase fallout; no production code changed.

Validation: the four failing cases in test_audio_embeds_input.py pass (5 passed);
tests/model_executor/models/minicpmo_4_5 otherwise unchanged.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpXe2LeRrUQGjZfKFaocMZ
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/model_executor/models/minicpmo_4_5/test_audio_embeds_input.py

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
 """Regression tests for the MiniCPM-o 4.5 ``audio_embeds`` input path.
 
 Two defects made the OpenAI ``audio_embeds`` content part unusable with this model:
@@ -71,6 +71,12 @@ class _IdentityTokenizer:
     def decode(self, tokens: str) -> str:
         return tokens
 
+    def convert_tokens_to_ids(self, token: str) -> int:
+        # vLLM 0.29 prompt updates select placeholder positions by token id,
+        # so the processor resolves ``<unk>`` once; the value is irrelevant here.
+        assert token == "<unk>"
+        return 0
+
 
 def _processing_info() -> MiniCPMO45OmniLLMProcessingInfo:
     processor = _FakeProcessor()