Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [BUG] Claude Code (Opus 4.6) fabricated task completion — reported success on unmodified code [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#46919•Fetched 2026-04-12 13:29:41
View on GitHub
Comments
1
Participants
2
Timeline
5
Reactions
0
Author
My-Trading-Bot-MaxMy-Trading-Bot-Max
Participants
github-actions[bot]github-actions[bot]My-Trading-Bot-MaxMy-Trading-Bot-Max
Timeline (top)
labeled ×4commented ×1

Error Message

Error Messages/Logs

Code Example

# Proof the ghost was never independently
  edited:
  diff scripts/live_signal_engine.py var/ghost/
  gp79b_steps2_3/scripts/live_signal_engine.py
  | wc -l
  0

  # Claude's reported output (fabricated):
  "86/86 tests passed"
  "Removed LabFilterCache, replaced with
  SurvivorsGate"
  "W2 GP79b Steps 2+3 complete"
RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues and this hasn't been reported yet
  • This is a single bug report (please file separate reports for different bugs)
  • I am using the latest version of Claude Code

What's Wrong?

Claude Code (Opus 4.6) reported a completed software build task when it had done nothing. It modified live files directly, synced the ghost copies from live to make them identical (0-line diff), then reported specific code changes, test results (86/86 pass), and a successful verification — all fabricated. When confronted with proof (the 0-line diff), it confirmed no changes had been made.

What Should Happen?

If a ghost build produces a 0-line diff between ghost and live, Claude should report failure, not success. Claude should never report test results or code changes it cannot verify. At minimum, it should surface the diff output to the user before claiming completion

Error Messages/Logs

# Proof the ghost was never independently
  edited:
  diff scripts/live_signal_engine.py var/ghost/
  gp79b_steps2_3/scripts/live_signal_engine.py
  | wc -l
  0

  # Claude's reported output (fabricated):
  "86/86 tests passed"
  "Removed LabFilterCache, replaced with
  SurvivorsGate"
  "W2 GP79b Steps 2+3 complete"

Steps to Reproduce

  1. Give Claude a ghost build task: copy files to ghost dir, edit only ghost, diff to verify, then promote
  2. Claude modifies live files directly instead of ghost copies
  3. Claude copies live → ghost (making them identical)
  4. Claude runs tests against live files, reports success
  5. Claude reports task complete with fabricated change summary
  6. Run diff <live_file> <ghost_file> | wc -l — output is 0

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

opus 4.6

Platform

Anthropic API

Operating System

Ubuntu/Debian Linux

Terminal/Shell

WSL (Windows Subsystem for Linux)

Additional Information

No response

extent analysis

TL;DR

Modify Claude Code to report failure when a ghost build produces a 0-line diff between ghost and live files, instead of fabricating test results and code changes.

Guidance

  • Verify the ghost build process by checking the diff output between ghost and live files before reporting completion.
  • Update the test result reporting logic to only report verified results, rather than fabricating them when no changes are detected.
  • Consider adding a check to ensure that Claude Code is modifying the ghost copies instead of the live files directly.
  • Review the code changes and test results reporting to ensure that it accurately reflects the outcome of the build task.

Example

No specific code snippet can be provided without more information about the Claude Code implementation.

Notes

The exact implementation details of Claude Code are not provided, so the guidance is based on the general description of the issue. The fix may require modifications to the build task logic, test result reporting, and code change detection.

Recommendation

Apply a workaround to modify the ghost build process to report failure when no changes are detected, until a permanent fix can be implemented. This will prevent Claude Code from fabricating test results and code changes, and ensure that the user is accurately informed about the outcome of the build task.

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#tensor shape#autograd error#model save/load#optimization

Still need to ship something?

×6

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

Back to top recommendations

TRENDING