[Bug]: Hermes tool call parser drops empty arguments for parameterless tools while streaming #28806
Description
Your current environment
The output of python collect_env.py
$ python collect_env.py
Collecting environment information...
==============================
System Info
==============================
OS : Linux Mint 20.3 (x86_64)
GCC version : (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version : 10.0.0-4ubuntu1
CMake version : version 3.16.3
Libc version : glibc-2.31
==============================
PyTorch Info
==============================
PyTorch version : 2.8.0+cu129
Is debug build : False
CUDA used to build PyTorch : 12.9
ROCM used to build PyTorch : N/A
==============================
Python Environment
==============================
Python version : 3.12.12 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 20:16:04) [GCC 11.2.0] (64-bit runtime)
Python platform : Linux-5.4.0-172-generic-x86_64-with-glibc2.31
==============================
CUDA / GPU Info
==============================
Is CUDA available : True
CUDA runtime version : 12.0.76
CUDA_MODULE_LOADING set to : LAZY
GPU models and configuration : GPU 0: NVIDIA TITAN RTX
Nvidia driver version : 525.147.05
cuDNN version : Could not collect
HIP runtime version : N/A
MIOpen runtime version : N/A
Is XNNPACK available : True
==============================
CPU Info
==============================
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
Address sizes: 43 bits physical, 48 bits virtual
CPU(s): 24
On-line CPU(s) list: 0-23
Thread(s) per core: 2
Core(s) per socket: 12
Socket(s): 1
NUMA node(s): 1
Vendor ID: AuthenticAMD
CPU family: 23
Model: 8
Model name: AMD Ryzen Threadripper 2920X 12-Core Processor
Stepping: 2
Frequency boost: enabled
CPU MHz: 1889.598
CPU max MHz: 3500,0000
CPU min MHz: 2200,0000
BogoMIPS: 6985.86
Virtualisation: AMD-V
L1d cache: 384 KiB
L1i cache: 768 KiB
L2 cache: 6 MiB
L3 cache: 32 MiB
NUMA node0 CPU(s): 0-23
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Vulnerable
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines, IBPB conditional, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid amd_dcm aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb hw_pstate ssbd ibpb vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt sha_ni xsaveopt xsavec xgetbv1 xsaves clzero irperf xsaveerptr arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca sme sev sev_es
==============================
Versions of relevant libraries
==============================
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.9.1.4
[pip3] nvidia-cuda-cupti-cu12==12.9.79
[pip3] nvidia-cuda-nvrtc-cu12==12.9.86
[pip3] nvidia-cuda-runtime-cu12==12.9.79
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cufft-cu12==11.4.1.4
[pip3] nvidia-cufile-cu12==1.14.1.1
[pip3] nvidia-curand-cu12==10.3.10.19
[pip3] nvidia-cusolver-cu12==11.7.5.82
[pip3] nvidia-cusparse-cu12==12.5.10.65
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-nccl-cu12==2.27.3
[pip3] nvidia-nvjitlink-cu12==12.9.86
[pip3] nvidia-nvtx-cu12==12.9.79
[pip3] pyzmq==27.1.0
[pip3] torch==2.8.0+cu129
[pip3] torchaudio==2.8.0+cu129
[pip3] torchvision==0.23.0+cu129
[pip3] transformers==4.57.1
[pip3] triton==3.4.0
[conda] numpy 2.2.6 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.9.1.4 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.9.79 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.9.86 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.9.79 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.10.2.21 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.4.1.4 pypi_0 pypi
[conda] nvidia-cufile-cu12 1.14.1.1 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.10.19 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.7.5.82 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.5.10.65 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.7.1 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.27.3 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.9.86 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.9.79 pypi_0 pypi
[conda] pyzmq 27.1.0 pypi_0 pypi
[conda] torch 2.8.0+cu129 pypi_0 pypi
[conda] torchaudio 2.8.0+cu129 pypi_0 pypi
[conda] torchvision 0.23.0+cu129 pypi_0 pypi
[conda] transformers 4.57.1 pypi_0 pypi
[conda] triton 3.4.0 pypi_0 pypi
==============================
vLLM Info
==============================
ROCM Version : Could not collect
vLLM Version : 0.11.0
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
GPU0 CPU Affinity NUMA Affinity
GPU0 X 0-23 N/A
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
==============================
Environment Variables
==============================
CUDA_ROOT=/usr/local/cuda/
VLLM_LOGGING_LEVEL=DEBUG
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
CUDA_MODULE_LOADING=LAZY
🐛 Describe the bug
Bug description
I am facing an issue when using the OpenAI-compatible server + hermes tool call parser (used with Qwen2.5-7B-Instruct in this case):
During streaming, the parser seems to incorrectly handle tool calls that don't require arguments. It seems to omit the empty "arguments" dict. However, due to that the server won't send a streaming chunk containing the arguments (in this case "{}"). Only the initial chunk containing the tool name, followed by a chunk with finish_reason "tool_calls".
Sample output with a parameterless "switch_led_on" tool:
data: {"id":"chatcmpl-e50cbabd787e4b3cb6a088cd7858ca41","object":"chat.completion.chunk","created":1763290465,"model":"Qwen/Qwen2.5-7B-Instruct-AWQ","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}],"prompt_token_ids":null}
data: {"id":"chatcmpl-e50cbabd787e4b3cb6a088cd7858ca41","object":"chat.completion.chunk","created":1763290465,"model":"Qwen/Qwen2.5-7B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"id":"chatcmpl-tool-7e08fc7ab28d41d1ab812c23ed2bd5c7","type":"function","index":0,"function":{"name":"switch_led_on"}}]},"logprobs":null,"finish_reason":null,"token_ids":null}]}
data: {"id":"chatcmpl-e50cbabd787e4b3cb6a088cd7858ca41","object":"chat.completion.chunk","created":1763290465,"model":"Qwen/Qwen2.5-7B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"tool_calls","stop_reason":null,"token_ids":null}]}
data: [DONE]
From my understanding, even in this case, the arguments should be sent as "{}".
For reference, here are the responses from the official OpenAI API, as they contain a response with said arguments string:
data: {"id":"chatcmpl-CcUjbqmbiSvXV69pLeAiXKOclJfaA","object":"chat.completion.chunk","created":1763290643,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_560af6e559","choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_bscmlHG7MLnaeTP6P0A6pYW7","type":"function","function":{"name":"switch_led_on","arguments":""}}],"refusal":null},"logprobs":null,"finish_reason":null}],"obfuscation":"mpKo4mtWWzopDLJ"}
data: {"id":"chatcmpl-CcUjbqmbiSvXV69pLeAiXKOclJfaA","object":"chat.completion.chunk","created":1763290643,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_560af6e559","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{}"}}]},"logprobs":null,"finish_reason":null}],"obfuscation":"Ws15DrXDjzV3"}
data: {"id":"chatcmpl-CcUjbqmbiSvXV69pLeAiXKOclJfaA","object":"chat.completion.chunk","created":1763290643,"model":"gpt-4o-mini-2024-07-18","service_tier":"default","system_fingerprint":"fp_560af6e559","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"tool_calls"}],"obfuscation":"a1Y8xbBFexqE"}
data: [DONE]
Steps to reproduce
- launch vllm server:
vllm serve "Qwen/Qwen2.5-7B-Instruct-AWQ" --gpu-memory-utilization 0.9 --enforce-eager --quantization awq --enable-auto-tool-choice --tool-call-parser hermes - query the server:
curl http://127.0.0.1:8000/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer no-key" -d '{ "stream": true, "model": "Qwen/Qwen2.5-7B-Instruct-AWQ", "messages": [ {"role": "system", "content": "You are a chatbot that uses tools/functions."}, {"role": "user", "content": "Turn the led on"} ], "tools": [{ "type":"function", "function":{ "name":"switch_led_on", "description":"Turns the led on", "parameters":{ "type":"object", "properties":{}, "required":[] } } }] }' - server should respond as described above
Debug log
Below is the debug log. The generated model response seems to be correct, but "{}" gets skipped
(EngineCore_DP0 pid=3924483) DEBUG 11-16 11:45:58 [v1/engine/core.py:743] EngineCore loop active.
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: <tool_call>
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [151657]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:248] Starting on a new tool 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text:
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [198]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:302] not enough tokens to parse into JSON yet
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: {"
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [4913]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: name
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [606]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: ":
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [788]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: "
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [330]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: switch
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [17338]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: _led
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [38367]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: _on
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [4470]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: ",
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [497]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on'}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: "
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [330]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on'}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:339] Trying to parse current tool call with ID 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:353] diffing old arguments: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:354] against new ones: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] Skipping text " - no arguments
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: arguments
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [16370]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on'}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:339] Trying to parse current tool call with ID 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:353] diffing old arguments: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:354] against new ones: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] Skipping text arguments - no arguments
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: ":
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [788]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on'}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:339] Trying to parse current tool call with ID 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:353] diffing old arguments: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:354] against new ones: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] Skipping text ": - no arguments
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [4687]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on', 'arguments': {}}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:339] Trying to parse current tool call with ID 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:353] diffing old arguments: None
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:354] against new ones: {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] Skipping text {} - no arguments
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: }
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [532]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on', 'arguments': {}}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:339] Trying to parse current tool call with ID 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:353] diffing old arguments: {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:354] against new ones: {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] Skipping text }
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] - no arguments
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text: </tool_call>
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [151658]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:214] tool_call_end_token in delta_text
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:300] Parsed tool call {'name': 'switch_led_on', 'arguments': {}}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:339] Trying to parse current tool call with ID 0
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:353] diffing old arguments: {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:354] against new ones: {}
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:358] Skipping text - no arguments
(EngineCore_DP0 pid=3924483) DEBUG 11-16 11:45:59 [v1/engine/core.py:737] EngineCore waiting for work.
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:186] delta_text:
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:187] delta_token_ids: [151645]
(APIServer pid=3924392) DEBUG 11-16 11:45:59 [entrypoints/.../tool_parsers/hermes_tool_parser.py:210] Generating text content! skipping tool parsing.
Before submitting a new issue...
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.