claude-code - 💡(How to fix) Fix Claude Code does not consistently follow user-defined conversation principles [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#51908Fetched 2026-04-23 07:41:41
View on GitHub
Comments
1
Participants
2
Timeline
5
Reactions
0
Timeline (top)
labeled ×4commented ×1

Code Example



---

User defined 16 specific principles at the start of the session.
Claude acknowledged them but gradually stopped following them as the conversation continued.
Claude added unrequested content, asked unnecessary questions, and made arbitrary modifications.
RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues for similar behavior reports
  • This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Claude ignored my instructions or configuration

What You Asked Claude to Do

I defined specific conversation principles (rules) that Claude must follow throughout the session. These included: always summarize instructions before acting, wait for approval, report only key points briefly, and follow user direction strictly.

What Claude Actually Did

  1. Claude reverted to its default behavior patterns, ignoring the user-defined principles after a short time.
  2. Claude made arbitrary modifications and additions without user instruction.
  3. Claude asked unnecessary questions instead of simply following instructions.
  4. The microphone (voice input) feature does not work in the PC version.

Expected Behavior

  1. Claude should strictly follow user-defined principles throughout the entire session without reverting to default behavior.
  2. Claude should only do exactly what the user instructs — no arbitrary additions or modifications.
  3. Claude should execute precisely under user direction, not act on its own judgment.
  4. The microphone (voice input) feature does not work in the PC/Windows version of Claude Code.

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Yes, every time with the same prompt

Steps to Reproduce

  1. Define conversation principles at the start of a session (e.g. always ask before acting, report briefly, do only what is instructed)
  2. Continue the conversation for several exchanges
  3. Claude gradually reverts to default behavior, ignoring the defined principles
  4. The microphone (voice input) feature does not work in the PC/Windows version of Claude Code.

Claude Model

Sonnet

Relevant Conversation

User defined 16 specific principles at the start of the session.
Claude acknowledged them but gradually stopped following them as the conversation continued.
Claude added unrequested content, asked unnecessary questions, and made arbitrary modifications.

Impact

High - Significant unwanted changes

Claude Code Version

2.1.87 (Claude Code)

Platform

Anthropic API

Additional Context

This happens consistently throughout every session, not just occasionally. The behavior reverts to default patterns after several conversation exchanges. Even when principles are injected automatically via hooks on every user message, Claude still gradually ignores them. Also: microphone (voice input) feature does not work in the PC/Windows version of Claude Code.

extent analysis

TL;DR

The issue can be mitigated by redefining conversation principles at regular intervals to prevent Claude from reverting to its default behavior.

Guidance

  • Review the conversation principles defined at the start of the session to ensure they are clear and concise, which might help Claude follow them more accurately.
  • Consider redefining the conversation principles at regular intervals (e.g., every 5-10 exchanges) to refresh Claude's understanding and prevent it from reverting to default behavior.
  • Investigate the microphone (voice input) feature issue separately, as it seems to be a platform-specific problem (PC/Windows version of Claude Code).
  • Verify if the "Accept Edits" mode being ON (auto-accepting changes) is contributing to Claude's behavior of making arbitrary modifications and additions.

Example

No specific code example can be provided without more context on how the conversation principles are defined and injected into the session. However, ensuring that the principles are clearly stated and regularly reinforced might look like a structured protocol for principle definition and reminder.

Notes

The issue seems to be related to how Claude interprets and retains the conversation principles over time. The microphone issue appears to be a separate problem related to the PC/Windows version of Claude Code. The provided information does not specify how the principles are technically implemented or injected into the conversation, which could be crucial for a more detailed solution.

Recommendation

Apply workaround: Redefine conversation principles at regular intervals to mitigate Claude's reversion to default behavior, as this approach directly addresses the observed issue without requiring changes to the underlying system or waiting for a potential fix for the microphone feature.

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