Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Using Qwen3.5 27B , 35B-A3B parse error [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#61838•Fetched 2026-04-08 02:53:45
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
poal5728-techpoal5728-tech
Participants
poal5728-techpoal5728-tech
Timeline (top)
labeled ×2

Both model happen with error: Failed to parse input at... Everything chat with bot at dashboard.

Failed to parse input at pos 11967: <tool_call> <function=tavily_search> <parameter=query> latest OpenClaw features 2026 </parameter> <parameter=count> 3 </parameter> </function> </tool_call>

Error Message

Both model happen with error: Failed to parse input at... both happen with openclaw error: Failed to parse input at... and a lot of XML, HTML tag No error happen

Root Cause

Both model happen with error: Failed to parse input at... Everything chat with bot at dashboard.

Failed to parse input at pos 11967: <tool_call> <function=tavily_search> <parameter=query> latest OpenClaw features 2026 </parameter> <parameter=count> 3 </parameter> </function> </tool_call>

RAW_BUFFERClick to expand / collapse

Bug type

Behavior bug (incorrect output/state without crash)

Beta release blocker

No

Summary

Both model happen with error: Failed to parse input at... Everything chat with bot at dashboard.

Failed to parse input at pos 11967: <tool_call> <function=tavily_search> <parameter=query> latest OpenClaw features 2026 </parameter> <parameter=count> 3 </parameter> </function> </tool_call>

Steps to reproduce

Name and Version

version: 8668 (https://github.com/ggml-org/llama.cpp/commit/5d3a4a7da5e3dd42f5922aba2fe21b520e96e830) built with Clang 19.1.5 for Windows x86_64 Operating systems

Windows GGML backends

CUDA Hardware

4090 Models

Qwen3.5-27B-Q4_K_M Qwen3.5-35B-A3B-UD-IQ4_NL Problem description & steps to reproduce

latest unsloth GGUF Qwen3.5-27B-Q4_K_M Qwen3.5-35B-A3B-UD-IQ4_NL

.\llama-server.exe -m Qwen3.5-27B-Q4_K_M.gguf ^ --mmproj mmproj-F16-Qwen3.5-27B.gguf ^ -ngl 99 -c 65536 --flash-attn on ^ --cache-type-k q8_0 --cache-type-v q8_0 ^ --no-webui ^ --temp 0.7 ^ --top-p 0.95 ^ --top-k 20 ^ --min-p 0.00 ^ --host 0.0.0.0 --port 10001

.\llama-server.exe -m Qwen3.5-35B-A3B-UD-IQ4_NL.gguf ^ --mmproj mmproj-F16-Qwen3.5-35B-A3B-GGUF.gguf ^ -ngl 99 -c 65536 --flash-attn on ^ --cache-type-k q8_0 --cache-type-v q8_0 ^ --no-webui ^ --temp 1.0 ^ --top-p 0.95 ^ --top-k 20 ^ --min-p 0.00 ^ --jinja ^ --host 0.0.0.0 --port 10001

both happen with openclaw error: Failed to parse input at... and a lot of XML, HTML tag

<function=exec> <parameter=command> openclaw security audit </tool_call> <tool_call> <function=exec> <parameter=command> openclaw update status </tool_call> rawError=Failed to parse input at pos 398: <tool_call> <function=exec> <parameter=command> openclaw security audit </tool_call> <tool_call> <function=exec> <parameter=command> openclaw…

Expected behavior

No error happen

Actual behavior

Failed to parse input at pos 11967: <tool_call> <function=tavily_search> <parameter=query> latest OpenClaw features 2026 </parameter> <parameter=count> 3 </parameter> </function> </tool_call>

OpenClaw version

v2026.4.5

Operating system

Windows 11

Install method

npm

Model

Qwen3.5

Provider / routing chain

llama

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

The issue is likely caused by incorrect input parsing in the OpenClaw tool, and a workaround may involve modifying the input or updating the OpenClaw version.

Guidance

  • Verify that the input to the OpenClaw tool is correctly formatted and does not contain any malformed XML or HTML tags.
  • Check the OpenClaw documentation to ensure that the input parameters, such as query and count, are correctly specified.
  • Consider updating the OpenClaw version to a newer release, as the current version (v2026.4.5) may contain a bug that is causing the parsing error.
  • Review the llama-server.exe command-line arguments to ensure that they are correctly configured and do not contain any typos or incorrect values.

Example

No code snippet is provided, as the issue is related to input parsing and configuration rather than code.

Notes

The issue may be specific to the OpenClaw tool and its interaction with the llama-server.exe application. Further investigation and debugging may be required to determine the root cause of the issue.

Recommendation

Apply a workaround, such as modifying the input or updating the OpenClaw version, as the issue is likely caused by a bug in the OpenClaw tool rather than a configuration error.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

No error happen

#vector store#embedding generation#cache error#pipeline error#runtime error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING