[Bugfix][Frontend] Respect max_output_tokens in the Harmony tool-call loop (#58551)

Signed-off-by: errmakov <ide404@gmail.com>
Co-authored-by: Du Bin <8174807+dubin555@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Denis Ermakov
2026-09-25 14:00:39 -07:00
committed by GitHub
co-authored by Du Bin Claude Opus 5.5 Flora Feng mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 83db8c8390
commit 7871963fcc
3 changed files with 57 additions and 2 deletions
@@ -615,12 +615,14 @@ class HarmonyContext(ConversationContext):
available_tools: list[str],
function_tool_names: frozenset[str],
response_parser: Parser | None = None,
request: ResponsesRequest | None = None,
):
from vllm.parser.harmony import HarmonyParser, Segment
assert isinstance(response_parser, HarmonyParser)
self._messages = messages
self.request = request
self.response_parser: HarmonyParser = response_parser
self.finish_reason: str | None = None
self.available_tools = available_tools