Issue Station
Sign In
Tools hereToolbox

openclaw - ✅(Solved) Fix Regression in 2026.4.27: WhatsApp session became unstable, leaked thinking traces, and fell back from Codex to MiniMax [1 pull requests, 3 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#74886•Fetched 2026-05-01 05:40:19
View on GitHub
Comments
3
Participants
2
Timeline
5
Reactions
2
Author
ThiagoCAltoeThiagoCAltoe
Participants
clawsweeper[bot]clawsweeper[bot]ThiagoCAltoeThiagoCAltoe
Timeline (top)
commented ×3cross-referenced ×2

Fix Action

Fixed

PR fix notes

PR #75258: whatsapp: suppress reasoning at pipeline level via onReasoningStream no-op

Description (problem / solution / changelog)

Summary

Fix WhatsApp reasoning leak by routing reasoning chunks through the pipeline's built-in suppression rather than letting them fall through to the deliver callback.

Problem

When reasoning chunks are emitted by the model, they are routed to onReasoningStream by the agent runner. If WhatsApp's replyOptions doesn't provide this callback, the pipeline may fall through to the deliver layer, where reasoning payloads can leak to the WhatsApp channel.

Fix

Provide onReasoningStream: () => {} in WhatsApp's replyOptions. This no-op callback activates the pipeline's routing path for reasoning chunks. The onBlockReply callback already contains an explicit guard that drops isReasoning=true payloads. With onReasoningStream connected, the pipeline routes reasoning through this guard.

Changes

  • extensions/whatsapp/src/auto-reply/monitor/inbound-dispatch.ts: added onReasoningStream: () => {} to replyOptions

Changed files

  • extensions/whatsapp/src/auto-reply/monitor/inbound-dispatch.ts (modified, +5/-0)
  • src/auto-reply/reply/agent-runner-execution.ts (modified, +2/-2)
  • src/auto-reply/reply/agent-runner-payloads.test.ts (modified, +17/-0)
  • src/auto-reply/reply/agent-runner.runreplyagent.e2e.test.ts (modified, +27/-11)
RAW_BUFFERClick to expand / collapse

Regression in 2026.4.27: WhatsApp session became unstable, leaked thinking traces, and fell back from Codex to MiniMax; rollback to 2026.4.23 fixed it

After updating OpenClaw from 2026.4.23 to 2026.4.27, my WhatsApp main session became unstable.

Environment

  • OpenClaw before: 2026.4.23
  • OpenClaw after update: 2026.4.27
  • Channel: WhatsApp direct session
  • Primary model expected: openai-codex/gpt-5.5
  • Fallbacks: minimax/MiniMax-M2.7, zai/glm-4.7
  • Host: Raspberry Pi / Debian arm64

Symptoms observed after 2026.4.27

  • Gateway became noticeably slower / unstable
  • Assistant responses became fragmented and inconsistent
  • Internal reasoning/thinking traces were sent as normal WhatsApp messages
  • The session appeared to fall back or get stuck on minimax/MiniMax-M2.7 despite Codex being configured as primary
  • Session/model/thinking overrides seemed inconsistent after restart/update
  • Setting thinkingDefault: off and forcing Codex helped partially, but the session remained unreliable
  • Rolling back both installed OpenClaw paths to 2026.4.23 restored normal behavior

What fixed it

  • Downgraded OpenClaw back to 2026.4.23
  • Restarted gateway
  • Confirmed:
    • CLI: 2026.4.23
    • Gateway runtime: 2026.4.23
    • Primary model: openai-codex/gpt-5.5
    • Thinking: off
  • WhatsApp behavior returned to normal

Related issues that may overlap

  • #74860 — 2026.4.27 gateway event-loop stalls
  • #13607 — reasoning visibility/defaults
  • #39612 — thinking blocks/session corruption/errors leaking to messaging channels

Expected behavior

  • Updating to 2026.4.27 should not change/freeze the effective model away from the configured primary
  • Thinking/reasoning traces should never be delivered as normal user-visible WhatsApp messages unless explicitly enabled
  • WhatsApp sessions should remain stable after update/restart
  • Fallback behavior should be visible and deterministic, not silently “stick” to a fallback model

Actual behavior

After the update, the WhatsApp session became slow, unstable, leaked internal reasoning, and appeared to use MiniMax instead of the configured Codex primary.

Rollback to 2026.4.23 resolved the issue.

If useful, I can provide sanitized config/status excerpts.

extent analysis

TL;DR

Downgrade OpenClaw to version 2026.4.23 to resolve the instability and incorrect model fallback issues in WhatsApp sessions.

Guidance

  • Verify that the primary model is correctly configured as openai-codex/gpt-5.5 and that thinking defaults are set to off to prevent internal reasoning traces from being sent as messages.
  • Check for any related issues such as event-loop stalls (#74860) or reasoning visibility/defaults (#13607) that may be contributing to the problem.
  • If possible, provide sanitized config/status excerpts to further troubleshoot the issue.
  • Consider monitoring the gateway and session behavior after downgrading to 2026.4.23 to ensure that the issue is fully resolved.

Notes

The issue appears to be specific to the 2026.4.27 version of OpenClaw, and downgrading to 2026.4.23 has resolved the problem. However, it is unclear what changes in 2026.4.27 caused the issue, and further investigation may be needed to determine the root cause.

Recommendation

Apply workaround: Downgrade to 2026.4.23 until a fixed version of OpenClaw is available, as this has been confirmed to resolve the 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

  • Updating to 2026.4.27 should not change/freeze the effective model away from the configured primary
  • Thinking/reasoning traces should never be delivered as normal user-visible WhatsApp messages unless explicitly enabled
  • WhatsApp sessions should remain stable after update/restart
  • Fallback behavior should be visible and deterministic, not silently “stick” to a fallback model
#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

openclaw - ✅(Solved) Fix Regression in 2026.4.27: WhatsApp session became unstable, leaked thinking traces, and fell back from Codex to MiniMax [1 pull requests, 3 comments, 2 participants]