[Bug] Kimi-k2.5 tool call parser may not work probabilistically. #18086
Description
Checklist
- I searched related issues but found no solution.
- The bug persists in the latest version.
- Issues without environment info and a minimal reproducible demo are hard to resolve and may receive no feedback.
- If this is not a bug report but a general question, please start a discussion at https://github.com/sgl-project/sglang/discussions. Otherwise, it will be closed.
- Please use English. Otherwise, it will be closed.
Describe the bug
I tested the locally deployed Kimi-k2.5 in Claude Code, OpenCode, and Kimi-Code. During tool calling, such tool call errors frequently occurred.
• Used ReadFile (frontend/lib/agentStream/agentStreamTypes.ts)
•
• <|tool_calls_section_begin|> <|tool_call_begin|> functions.ReadFile:5 <|tool_call_argument_begin|> {"path": "/Users/dongfangzan/Documents/workspace/open-claude-webui/frontend/lib/agentStream/agentStreamApi.ts"} <|tool_call_end|> <|tool_calls_section_end|>
I've tried this issue. #17914
I set SGLANG_TOOL_STRICT_LEVEL=2 and xgrammar==0.1.31, but it seems to have no effect.
Reproduction
nohup sglang serve --model-path /root/.cache/huggingface/hub/Kimi-K2___5 --tp 16 --trust-remote-code --tool-call-parser kimi_k2 --reasoning-parser kimi_k2 --dist-init-addr 10.0.41.2:20000 --nnodes 2 --node-rank 0 --host 0.0.0.0 --port 8000 &
Environment
Python: 3.12.3 (main, Jan 8 2026, 11:30:50) [GCC 13.3.0]
CUDA available: True
GPU 0,1,2,3,4,5,6,7: NVIDIA H100 80GB HBM3
GPU 0,1,2,3,4,5,6,7 Compute Capability: 9.0
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 12.9, V12.9.86
CUDA Driver Version: 550.54.15
PyTorch: 2.9.1+cu129
sglang: 0.5.8
sgl_kernel: 0.3.21
flashinfer_python: 0.6.2
flashinfer_cubin: 0.6.2
flashinfer_jit_cache: 0.6.2+cu129
triton: 3.5.1
transformers: 4.57.1
torchao: 0.9.0
numpy: 2.4.1
aiohttp: 3.13.3
fastapi: 0.128.0
hf_transfer: 0.1.9
huggingface_hub: 0.36.0
interegular: 0.3.3
modelscope: 1.34.0
orjson: 3.11.5
outlines: 0.1.11
packaging: 26.0
psutil: 7.2.1
pydantic: 2.12.5
python-multipart: 0.0.22
pyzmq: 27.1.0
uvicorn: 0.40.0
uvloop: 0.22.1
vllm: Module Not Found
xgrammar: 0.1.27
openai: 2.6.1
tiktoken: 0.12.0
anthropic: 0.76.0
litellm: Module Not Found
decord2: 3.0.0
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS 0-47,96-143 0 N/A
GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS 48-95,144-191 1 N/A
GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS 48-95,144-191 1 N/A
GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS SYS PIX PIX SYS 48-95,144-191 1 N/A
GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS SYS PIX PIX SYS 48-95,144-191 1 N/A
NIC0 SYS SYS SYS SYS SYS SYS SYS SYS X SYS SYS SYS SYS SYS SYS SYS SYS SYS
NIC1 PIX PIX SYS SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS SYS SYS
NIC2 PIX PIX SYS SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS SYS SYS
NIC3 SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS SYS SYS
NIC4 SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS SYS SYS
NIC5 SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS X PIX SYS SYS SYS
NIC6 SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS PIX X SYS SYS SYS
NIC7 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS X PIX SYS
NIC8 SYS SYS SYS SYS SYS SYS PIX PIX SYS SYS SYS SYS SYS SYS SYS PIX X SYS
NIC9 SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS SYS X
Legend:
X = Self
SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
PIX = Connection traversing at most a single PCIe bridge
NV# = Connection traversing a bonded set of # NVLinks
NIC Legend:
NIC0: mlx5_0
NIC1: mlx5_1
NIC2: mlx5_2
NIC3: mlx5_3
NIC4: mlx5_4
NIC5: mlx5_5
NIC6: mlx5_6
NIC7: mlx5_7
NIC8: mlx5_8
NIC9: mlx5_bond_0
ulimit soft: 1048576