[Bugfix] Fix the bug in Hermes streaming parsing

Signed-off-by: zxy <zx0823y@163.com>

Author: pre-master

requirements/common.txt

@@ -28,6 +28,7 @@ lark == 1.2.2
 xgrammar == 0.1.19; platform_machine == "x86_64" or platform_machine == "aarch64" or platform_machine == "arm64"
 typing_extensions >= 4.10
 filelock >= 3.16.1 # need to contain https://github.com/tox-dev/filelock/pull/317
+json_repair  # used for repairing JSON outputs
 partial-json-parser # used for parsing partial JSON outputs
 pyzmq >= 25.0.0
 msgspec

vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py

@@ -7,7 +7,6 @@
 
 import partial_json_parser
 import regex as re
-from partial_json_parser.core.options import Allow
 from json_repair import repair_json
 
 from vllm.entrypoints.chat_utils import random_tool_call_id
@@ -171,6 +170,7 @@ def extract_tool_calls_streaming(
             # something with tools with this diff.
             # flags for partial JSON parting. exported constants from
             # "Allow" are handled via BIT MASK
+            from partial_json_parser.core.options import Allow
             flags = Allow.ALL if self.current_tool_name_sent \
                 else Allow.ALL & ~Allow.STR