[Frontend] Support count_reasoning_tokens in the Streaming Parser Engine (#45802)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Chauncey
2026-08-15 06:51:14 -07:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 5cecfc0137
commit ac2ae8798c
16 changed files with 669 additions and 73 deletions
@@ -360,6 +360,10 @@ async def test_reasoning_tokens_counted_for_text_reasoning_model(monkeypatch):
def get_vocab(self):
return self._vocab
def decode(self, token_ids):
id_to_token = {v: k for k, v in self._vocab.items()}
return "".join(id_to_token.get(token_id, "x") for token_id in token_ids)
# Force non-harmony, SimpleContext path
monkeypatch.setattr(envs, "VLLM_USE_EXPERIMENTAL_PARSER_CONTEXT", False)