openclaw - 💡(How to fix) Fix Tool calls and chain-of-thought leaked to user in Telegram output (kimi-k2.6:cloud) [1 comments, 2 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#72071Fetched 2026-04-27 05:35:22
View on GitHub
Comments
1
Participants
2
Timeline
2
Reactions
0
Author
Timeline (top)
closed ×1commented ×1
RAW_BUFFERClick to expand / collapse

Bug Description

When using ollama/kimi-k2.6:cloud as the model, assistant responses leak raw tool call blocks and chain-of-thought text to the user in Telegram.

What Happened

During a conversation about researching a gymnastics club for a child, the assistant (powered by kimi-k2.6:cloud) produced a response that included:

  1. Chain-of-thought text in the user-visible text block: "Sending an email to inquire about gymnastics for Sophia. Let me draft it in German..."
  2. All 10 tool_call blocks (web_search, web_fetch calls) were rendered as visible output in Telegram

The user saw the entire internal reasoning and tool call flow instead of just the final response.

Evidence

Session transcript shows the problematic message at line 7960:

  • role: assistant
  • model: kimi-k2.6:cloud
  • provider: ollama
  • Content contains 1 text block + 10 toolCall blocks
  • The text block starts with internal reasoning ("Sending an email to inquire...") before the actual user-facing content

Session ID: 773b51bd-8ba4-41d0-92ec-25cf57ca22e5

Expected Behavior

  • Tool calls should be executed by OpenClaw and their results incorporated into the response
  • Chain-of-thought reasoning should NOT be included in the text block sent to the user
  • Only the final, polished response should be delivered to the Telegram channel

Environment

  • OpenClaw 2026.4.15
  • Model: ollama/kimi-k2.6:cloud (via Ollama Cloud)
  • Channel: Telegram
  • The same conversation with glm-5.1:cloud did NOT exhibit this behavior

Additional Context

The model kimi-k2.6:cloud was added to the config on 2026-04-23. The tool call leaking only appeared when this model was active. After switching back to glm-5.1:cloud, the behavior returned to normal.

This may be related to how Kimi K2.6 structures its tool call output differently from other models, or how OpenClaw parses the response from the Ollama Cloud provider for this specific model.

extent analysis

TL;DR

The issue can likely be resolved by adjusting the OpenClaw configuration to properly handle the tool call output from the ollama/kimi-k2.6:cloud model.

Guidance

  • Verify that the OpenClaw configuration is set up to parse the response from the Ollama Cloud provider correctly for the kimi-k2.6:cloud model, considering its unique output structure.
  • Check the documentation for ollama/kimi-k2.6:cloud to see if there are specific requirements or recommendations for handling tool call output.
  • Test the conversation with the kimi-k2.6:cloud model in a controlled environment to isolate the issue and identify any patterns or triggers for the tool call leaking.
  • Consider reaching out to the Ollama Cloud support team for guidance on how to properly integrate the kimi-k2.6:cloud model with OpenClaw.

Example

No code snippet is provided as the issue seems to be related to configuration and model integration rather than code.

Notes

The issue may be specific to the kimi-k2.6:cloud model and its interaction with OpenClaw, so any solution or workaround may need to be tailored to this particular model.

Recommendation

Apply a workaround by adjusting the OpenClaw configuration to handle the unique output of the kimi-k2.6:cloud model, as this is likely to be a more immediate solution than waiting for a potential fix in a future version.

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…

Still need to ship something?

×6

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

Back to top recommendations

TRENDING