Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix Claude Code generates self-messages that appear as user (Human) messages [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
anthropics/claude-code#48443•Fetched 2026-04-16 07:00:01
View on GitHub
Comments
1
Participants
2
Timeline
5
Reactions
0
Author
webya22webya22
Participants
github-actions[bot]github-actions[bot]webya22webya22
Timeline (top)
labeled ×4commented ×1

While using Claude Code via the VSCode extension, Claude generated text in the user's voice as part of its assistant response. This text was then treated as a Human message in the conversation history, which Claude subsequently responded to as if the user had sent it.

The user did NOT write or send this message.

Root Cause

While using Claude Code via the VSCode extension, Claude generated text in the user's voice as part of its assistant response. This text was then treated as a Human message in the conversation history, which Claude subsequently responded to as if the user had sent it.

The user did NOT write or send this message.

RAW_BUFFERClick to expand / collapse

Description

While using Claude Code via the VSCode extension, Claude generated text in the user's voice as part of its assistant response. This text was then treated as a Human message in the conversation history, which Claude subsequently responded to as if the user had sent it.

The user did NOT write or send this message.

Steps to Reproduce

  1. Use Claude Code via VSCode extension, accessed remotely (in this case via Tailscale from a smartphone)
  2. Have a multi-turn conversation with tool calls (1Password lookups, bash commands)
  3. At some point, Claude generated a message like "OK, I'll check the API when I get back to my Mac" — phrased as if the user said it
  4. This text appeared as a Human (user) message in the conversation, and Claude continued the conversation treating it as user input

Expected Behavior

All Human messages in the conversation should originate from the user. Claude should never generate text that gets injected as a Human message.

Actual Behavior

Claude-generated text appeared as a Human message. Claude then responded to its own generated message as if the user had sent it.

Environment

  • Platform: macOS (Darwin 23.6.0)
  • Interface: VSCode extension, accessed remotely via smartphone (Tailscale)
  • Model: Claude Opus 4.6

Related

This appears to match the behavior reported in: https://gigazine.net/news/20260413-claude-self-message/

extent analysis

TL;DR

The issue can be mitigated by ensuring that Claude-generated text is properly distinguished from user input in the conversation history.

Guidance

  • Verify that the VSCode extension is correctly configured to handle Claude-generated text as non-user input.
  • Check the conversation history to ensure that Claude-generated messages are not being incorrectly labeled as Human messages.
  • Consider modifying the conversation flow to prevent Claude from responding to its own generated messages.
  • Review the related report (https://gigazine.net/news/20260413-claude-self-message/) for potential insights into the issue.

Example

No code snippet is provided as the issue does not specify any specific code-related details.

Notes

The issue may be related to the specific configuration of the VSCode extension or the Claude Opus 4.6 model. Further investigation is needed to determine the root cause.

Recommendation

Apply workaround: Modify the conversation flow to prevent Claude from responding to its own generated messages, as this is a more immediate and feasible solution given the information available.

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…
#api#conversation history#database connection#vector store#embedding generation

Still need to ship something?

×6

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

Back to top recommendations

TRENDING