openclaw - 💡(How to fix) Fix [Feature]: sessions_send messages display sender as the sending agent instead of human user [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#60911Fetched 2026-04-08 02:45:48
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
Participants
Timeline (top)
labeled ×1

Inter-agent messages sent via sessions_send show the human user's identity in the UI instead of the actual sending agent's name/avatar.

Root Cause

Inter-agent messages sent via sessions_send show the human user's identity in the UI instead of the actual sending agent's name/avatar.

RAW_BUFFERClick to expand / collapse

Summary

Inter-agent messages sent via sessions_send show the human user's identity in the UI instead of the actual sending agent's name/avatar.

Problem to solve

When running a multi-agent setup (e.g., A as main agent + B as proofreading agent), sessions_send is the correct API for agent-to-agent communication. However, in the OpenClaw chat UI, these inter-agent messages render with the human user's avatar and name as sender, making them visually indistinguishable from messages the user actually typed. This makes it confusing to track which agent sent what, defeating the purpose of a visible multi-agent workflow.

Proposed solution

Add an optional sender or displayName field to sessions_send that tells the UI which agent identity to show.

Alternatives considered

No response

Impact

Affected users/systems/channels: Anyone using OpenClaw with multiple agents (web UI, all channels) Severity: Annoying UX issue — doesn't break functionality but makes multi-agent workflows hard to follow Frequency: Always — every sessions_send call exhibits this behavior Consequence: Users can't visually distinguish their own messages from agent-to-agent messages in the conversation log, making monitoring confusing

Evidence/examples

No response

Additional information

No response

extent analysis

TL;DR

Adding an optional sender or displayName field to the sessions_send API could help distinguish inter-agent messages from human user messages in the UI.

Guidance

  • Consider modifying the sessions_send API to accept an additional parameter that specifies the sender's identity, such as agent_name or agent_avatar.
  • Consider updating the OpenClaw chat UI to handle this new parameter and display the correct sender information for inter-agent messages.
  • Evaluate the impact of this change on existing workflows and user experiences to ensure it does not introduce new issues.
  • Test this modification with different multi-agent setups to verify its effectiveness in resolving the issue.

Example

No specific code example can be provided without more context, but the idea would be to modify the sessions_send API call to include the agent's identity, e.g., sessions_send(message, agent_name="Agent B").

Notes

The proposed solution assumes that adding a new field to the sessions_send API is feasible and does not introduce significant complexity or compatibility issues. Further testing and evaluation are necessary to ensure this solution works as expected.

Recommendation

Apply workaround: Add an optional sender or displayName field to the sessions_send API, as this seems to be the most direct way to address the issue without introducing more significant changes to the system.

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