Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Incomplete turn detected (openai-compatible endpoint) [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#72751•Fetched 2026-04-28 06:32:33
View on GitHub
Comments
1
Participants
2
Timeline
4
Reactions
0
Author
moooV252moooV252
Participants
moooV252moooV252steipetesteipete
Timeline (top)
labeled ×2closed ×1commented ×1

After upgrading from 2026.4.15 to 2026.4.22 I started getting errors in telegram (every 2nd-3rd message randomly)

⚠️ Agent couldn't generate a response. Please try again.

Error Message

incomplete turn detected: runId=b73b8dbf-d6d4-410e-a23b-9bc06173005f sessionId=2170070b-5108-4f21-a21a-9f0779d09267 stopReason=stop payloads=0 — surfacing error to user

Root Cause

After upgrading from 2026.4.15 to 2026.4.22 I started getting errors in telegram (every 2nd-3rd message randomly)

⚠️ Agent couldn't generate a response. Please try again.

Code Example

srv  log_server_r: done request: POST /chat/completions 127.0.0.1 200
slot print_timing: id  0 | task 3932 |
prompt eval time =     632.61 ms /   950 tokens (    0.67 ms per token,  1501.71 tokens per second)
       eval time =    1786.86 ms /   103 tokens (   17.35 ms per token,    57.64 tokens per second)
      total time =    2419.47 ms /  1053 tokens
slot      release: id  0 | task 3932 | stop processing: n_tokens = 30311, truncated = 0
srv  update_slots: all slots are idle

---
RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

After upgrading from 2026.4.15 to 2026.4.22 I started getting errors in telegram (every 2nd-3rd message randomly)

⚠️ Agent couldn't generate a response. Please try again.

Steps to reproduce

  1. start openclaw 2026.4.22+
  2. chat with the bot in telegram
  3. bot replies show "⚠️ Agent couldn't generate a response. Please try again."

Expected behavior

Proper chat, messages get delivered

Actual behavior

Logs show this: incomplete turn detected: runId=b73b8dbf-d6d4-410e-a23b-9bc06173005f sessionId=2170070b-5108-4f21-a21a-9f0779d09267 stopReason=stop payloads=0 — surfacing error to user

I'm using llama.cpp as a backend, configured as openai-completions in the config.

Judging from llama.cpp logs, the message was generated in full:

srv  log_server_r: done request: POST /chat/completions 127.0.0.1 200
slot print_timing: id  0 | task 3932 |
prompt eval time =     632.61 ms /   950 tokens (    0.67 ms per token,  1501.71 tokens per second)
       eval time =    1786.86 ms /   103 tokens (   17.35 ms per token,    57.64 tokens per second)
      total time =    2419.47 ms /  1053 tokens
slot      release: id  0 | task 3932 | stop processing: n_tokens = 30311, truncated = 0
srv  update_slots: all slots are idle

However, openclaw treats it as an incomplete message - thus fully breaking it for me. I didn't see this behavior on 2026.4.15 - it was working flawlessly with this backend.

OpenClaw version

2026.4.22

Operating system

ubuntu

Install method

docker

Model

Qwen3.6-27B, Qwen3.6-35B-A3B, Gemma4-31B

Provider / routing chain

openclaw -> llama.cpp

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 might be resolved by adjusting the configuration of openclaw to properly handle the response from the llama.cpp backend, possibly by increasing a timeout or modifying how incomplete turns are detected.

Guidance

  • Review the openclaw configuration for any settings related to response timeouts or turn completion detection that might have changed between versions 2026.4.15 and 2026.4.22.
  • Verify that the llama.cpp backend is correctly configured as openai-completions in the openclaw setup and that there are no version-specific requirements or changes needed for this configuration.
  • Check the openclaw documentation for any known issues or updates related to handling responses from backends like llama.cpp, especially concerning the incomplete turn detected error.
  • Consider temporarily adjusting the logging level of openclaw to debug to gather more detailed information about how it handles responses from llama.cpp, which might help in identifying the root cause.

Example

No specific code example can be provided without more details on the openclaw or llama.cpp configurations, but reviewing the configuration files for any version-specific settings or adjustments related to response handling is a good starting point.

Notes

The solution might depend on specifics of the openclaw and llama.cpp configurations that are not fully detailed in the issue. The fact that the issue started after an upgrade suggests a potential version-specific change or bug.

Recommendation

Apply workaround: Adjust the openclaw configuration to better handle responses from the llama.cpp backend, as the upgrade from 2026.4.15 to 2026.4.22 seems to have introduced a compatibility issue.

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

Proper chat, messages get delivered

#prompt formatting#chain error#conversation history#tool integration#LLM response

Still need to ship something?

×6

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

Back to top recommendations

TRENDING