claude-code - 💡(How to fix) Fix Opus 4.6 reasoning regression: fails simple file access tasks that Haiku handles correctly [3 comments, 3 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#48052Fetched 2026-04-15 06:34:41
View on GitHub
Comments
3
Participants
3
Timeline
6
Reactions
0
Author
Timeline (top)
commented ×3labeled ×2cross-referenced ×1

Opus 4.6 (1M context) is exhibiting significant reasoning regression — specifically, failing on simple tasks where smaller models (Haiku, Sonnet) do not. This is not a capability ceiling issue; it is a regression from expected Opus-tier behavior.

Error Message

When a file exists at a known absolute path and the model has full filesystem access, Opus 4.6 diagnosed the situation as a "tooling limitation" rather than simply reading the file. It produced multi-step diagnostic frameworks, offered "fix options," and explained why the file was inaccessible — without ever attempting to read it.

Root Cause

Opus 4.6 (1M context) is exhibiting significant reasoning regression — specifically, failing on simple tasks where smaller models (Haiku, Sonnet) do not. This is not a capability ceiling issue; it is a regression from expected Opus-tier behavior.

RAW_BUFFERClick to expand / collapse

Summary

Opus 4.6 (1M context) is exhibiting significant reasoning regression — specifically, failing on simple tasks where smaller models (Haiku, Sonnet) do not. This is not a capability ceiling issue; it is a regression from expected Opus-tier behavior.

Observed behavior

When a file exists at a known absolute path and the model has full filesystem access, Opus 4.6 diagnosed the situation as a "tooling limitation" rather than simply reading the file. It produced multi-step diagnostic frameworks, offered "fix options," and explained why the file was inaccessible — without ever attempting to read it.

The file was accessible. The model had the Read tool. No actual barrier existed.

A simpler model would have read the file.

Impact

  • Opus produces elaborate explanations for problems that don't exist
  • It mistakes its own inaction for environmental constraints
  • This compounds in longer sessions: wrong diagnosis → wrong fix → wasted turns

Expected behavior

When a tool is available and a path is known, use the tool. Do not theorize about access barriers before attempting access.

Severity

High. If Opus is less reliable than Haiku on straightforward tool-use tasks, the model tier premium is unjustified and the regression is user-visible.

Steps to reproduce

  1. Start a Claude Code session in directory A
  2. Tell the model a relevant file exists at directory B (different from cwd)
  3. Ask the model to use context from that file
  4. Observe whether the model reads the file or theorizes about why it cannot

extent analysis

TL;DR

The most likely fix for Opus 4.6's reasoning regression is to modify its decision-making process to attempt file access before diagnosing tooling limitations.

Guidance

  • Review the Opus 4.6 code to identify where it checks for tooling limitations and file accessibility, and consider reordering these checks to prioritize actual access attempts.
  • Verify that the model's Read tool is correctly configured and functional by testing it in isolation.
  • Compare the decision-making logic between Opus 4.6 and simpler models like Haiku to identify potential differences that could be contributing to the regression.
  • Consider adding logging or debugging statements to track the model's thought process and identify where it's going wrong.

Example

No code snippet is provided due to lack of specific implementation details in the issue.

Notes

The exact cause of the regression is unclear, and further investigation is needed to determine the root cause. The suggested fix is based on the observed behavior and may not be comprehensive.

Recommendation

Apply a workaround by modifying the Opus 4.6 decision-making process to prioritize file access attempts, as this is likely to improve the model's performance on straightforward tool-use tasks.

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…

FAQ

Expected behavior

When a tool is available and a path is known, use the tool. Do not theorize about access barriers before attempting access.

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix Opus 4.6 reasoning regression: fails simple file access tasks that Haiku handles correctly [3 comments, 3 participants]