[v0.18.0][Bugfix][Platform] Fix MiniMax M2 reasoning token usage accounting (#7700)

### What this PR does / why we need it?
This backports the MiniMax M2 reasoning-token usage accounting fix onto
`releases/v0.18.0` for vllm-ascend.

The release branch does not include the other local GLM patch commit, so
this PR keeps the MiniMax change self-contained by:
- registering `patch_minimax_usage_accounting` on the release branch
- backporting `completion_tokens_details.reasoning_tokens` into chat
usage generation
- fixing MiniMax reasoning token counting for `</think>`-delimited
outputs without depending on the GLM suffix patch

### Does this PR introduce _any_ user-facing change?
Yes. OpenAI-compatible chat usage accounting for MiniMax M2 responses
now reports corrected reasoning token counts on the release branch.

### How was this patch tested?
- `python -m compileall
vllm_ascend/patch/platform/patch_minimax_usage_accounting.py`
- `python - <<'PY'` import check for
`vllm_ascend.patch.platform.patch_minimax_usage_accounting` on top of
`releases/v0.18.0`

No targeted automated regression test exists for this release-branch
backport yet, so I validated syntax and module import compatibility on
the release branch.

---------

Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>

tests/ut/patch/platform/test_patch_minimax_usage_accounting.py

@@ -0,0 +1,67 @@
+# SPDX-License-Identifier: Apache-2.0
+
+import pytest
+
+from vllm.reasoning.minimax_m2_reasoning_parser import (
+    MiniMaxM2AppendThinkReasoningParser,
+    MiniMaxM2ReasoningParser,
+)
+
+
+class FakeTokenizer:
+    def get_vocab(self):
+        return {
+            "<think>": 1,
+            "</think>": 2,
+        }
+
+
+@pytest.mark.parametrize(
+    ("parser_cls", "token_ids", "expected_reasoning_tokens"),
+    [
+        pytest.param(
+            MiniMaxM2ReasoningParser,
+            [10, 11, 2, 20],
+            2,
+            id="minimax-reasoning-before-end-token",
+        ),
+        pytest.param(
+            MiniMaxM2AppendThinkReasoningParser,
+            [10, 11, 2, 20],
+            2,
+            id="append-think-reasoning-before-end-token",
+        ),
+        pytest.param(
+            MiniMaxM2ReasoningParser,
+            [10, 11, 20],
+            3,
+            id="minimax-all-tokens-are-reasoning-before-end-token",
+        ),
+        pytest.param(
+            MiniMaxM2AppendThinkReasoningParser,
+            [10, 11, 20],
+            3,
+            id="append-think-all-tokens-are-reasoning-before-end-token",
+        ),
+        pytest.param(
+            MiniMaxM2ReasoningParser,
+            [2, 20],
+            0,
+            id="minimax-end-token-first-means-no-reasoning-tokens",
+        ),
+        pytest.param(
+            MiniMaxM2AppendThinkReasoningParser,
+            [2, 20],
+            0,
+            id="append-think-end-token-first-means-no-reasoning-tokens",
+        ),
+    ],
+)
+def test_count_reasoning_tokens(
+    parser_cls,
+    token_ids,
+    expected_reasoning_tokens,
+):
+    parser = parser_cls(FakeTokenizer())
+
+    assert parser.count_reasoning_tokens(token_ids) == expected_reasoning_tokens