openclaw - 💡(How to fix) Fix <relevant-memories> block visible in webchat UI after v3.23 update [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#53696Fetched 2026-04-08 01:24:43
View on GitHub
Comments
0
Participants
1
Timeline
0
Reactions
0
Participants

Fix Action

Workaround

Disable autoRecall in memory-lancedb-pro config:

{
  "plugins": {
    "entries": {
      "memory-lancedb-pro": {
        "config": {
          "autoRecall": false
        }
      }
    }
  }
}

Code Example

{
  "plugins": {
    "entries": {
      "memory-lancedb-pro": {
        "config": {
          "autoRecall": false
        }
      }
    }
  }
}
RAW_BUFFERClick to expand / collapse

After updating to v3.23.2, the <relevant-memories> block (injected by memory-lancedb-pro auto-recall) is now visible in the webchat transcript. This block should be internal context only and was not visible before the v3.23 update.

Steps to Reproduce

  1. Install memory-lancedb-pro with autoCapture and autoRecall enabled
  2. Have some memories stored in LanceDB
  3. Chat via webchat (Control UI)
  4. The <relevant-memories> block appears in the chat transcript and is visible to the user

Expected Behavior

The <relevant-memories> block is internal context that should not be displayed in the webchat UI.

Environment

  • OpenClaw: v3.23.2 (also affected in v3.23)
  • Plugin: memory-lancedb-pro v1.0.32
  • Channel: webchat

Possible Cause

This is likely a webchat transcript rendering change in v3.23 that now displays what was previously internal-only context.

Workaround

Disable autoRecall in memory-lancedb-pro config:

{
  "plugins": {
    "entries": {
      "memory-lancedb-pro": {
        "config": {
          "autoRecall": false
        }
      }
    }
  }
}

extent analysis

Fix Plan

To fix the issue, we need to modify the webchat transcript rendering to exclude internal context.

  • Update the memory-lancedb-pro plugin configuration to disable autoRecall:
{
  "plugins": {
    "entries": {
      "memory-lancedb-pro": {
        "config": {
          "autoRecall": false
        }
      }
    }
  }
}
  • Alternatively, create a custom webchat transcript renderer that filters out internal context blocks:
function customRenderer(transcript) {
  return transcript.replace(/<relevant-memories>.*?<\/relevant-memories>/g, '');
}
  • Apply the custom renderer to the webchat UI.

Verification

To verify the fix, follow these steps:

  • Enable autoRecall in the memory-lancedb-pro plugin configuration.
  • Chat via webchat and check if the <relevant-memories> block is still visible.
  • If the block is not visible, the fix is successful.

Extra Tips

  • Consider updating the memory-lancedb-pro plugin to a version that is compatible with OpenClaw v3.23.2.
  • If the custom renderer approach is used, ensure that it does not introduce any performance issues or security vulnerabilities.

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

openclaw - 💡(How to fix) Fix <relevant-memories> block visible in webchat UI after v3.23 update [1 participants]