claude-code - 💡(How to fix) Fix [BUG] Model silently stops mid-task after tool call without generating follow-up [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#47903Fetched 2026-04-15 06:39:03
View on GitHub
Comments
1
Participants
2
Timeline
5
Reactions
0
Timeline (top)
labeled ×4commented ×1

Claude Code silently stops execution mid-task after a tool call (typically an Edit) without generating any follow-up text or invoking the next tool. The conversation appears to hang - no output, no error, no indication that work has stopped. The user has to manually prompt to resume.

Error Message

Claude Code silently stops execution mid-task after a tool call (typically an Edit) without generating any follow-up text or invoking the next tool. The conversation appears to hang - no output, no error, no indication that work has stopped. The user has to manually prompt to resume. The turn ends after the tool result with no output. No error, no permission prompt, nothing. Claude just froze.

Error Messages/Logs

Root Cause

Claude Code silently stops execution mid-task after a tool call (typically an Edit) without generating any follow-up text or invoking the next tool. The conversation appears to hang - no output, no error, no indication that work has stopped. The user has to manually prompt to resume.

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?

Description

Claude Code silently stops execution mid-task after a tool call (typically an Edit) without generating any follow-up text or invoking the next tool. The conversation appears to hang - no output, no error, no indication that work has stopped. The user has to manually prompt to resume.

Actual behavior

The turn ends after the tool result with no output. No error, no permission prompt, nothing. Claude just froze.

Environment

  • Platform: Windows 11 Pro N (10.0.26200)
  • Claude Code: VS Code extension
  • Model: claude-opus-4-6 (1M context)
  • Frequency: Multiple occurrences over 2+ days
  • Context size: ~50-80K tokens (not near limit)

Additional context

  • NOT a permission issue - no prompt shown
  • NOT a user interruption - user had to re-engage after silence
  • Model resumes correctly when prompted - generation just stopped prematurely
  • Happens during sequences of Edit tool calls

What Should Happen?

Expected behavior

After a successful tool call, Claude should continue with the next step. The turn should not end silently mid-task.

Error Messages/Logs

Steps to Reproduce

Steps to reproduce

  1. Give Claude Code a multi-step implementation task (e.g., multiple file edits + typecheck)
  2. Claude starts executing: makes the first edit successfully
  3. After the edit tool result returns, Claude generates no response - the turn ends silently
  4. User sends a follow-up message and Claude resumes exactly where it left off

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

No response

Claude Code Version

Claude Code v2.1.107 (win32-x64)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

VS Code integrated terminal

Additional Information

No response

extent analysis

TL;DR

The issue can be mitigated by adjusting the task structure to avoid sequential Edit tool calls or investigating the Anthropic API's handling of long-running tasks.

Guidance

  • Investigate if the Anthropic API has limitations or specific requirements for handling sequential tool calls, especially for tasks involving multiple file edits.
  • Consider restructuring the task to minimize sequential Edit tool calls, potentially by batching edits or using alternative tools that can handle multiple operations in a single call.
  • Verify if the issue persists across different models or context sizes to determine if it's specific to the claude-opus-4-6 model or a more general problem.
  • Check for any updates or known issues in the Claude Code VS Code extension that might address silent task termination.

Example

No specific code example can be provided without more details on the task structure and tool calls, but adjusting the sequence or nature of tool calls could look like reordering tasks or using a different tool that can handle multiple edits at once.

Notes

The root cause of the silent termination is unclear without more information on the Anthropic API's behavior or the specific task structure. The issue might be related to how the API handles long-running tasks or sequential operations.

Recommendation

Apply workaround: Restructure tasks to minimize sequential Edit tool calls, as this approach can potentially mitigate the issue without requiring updates to the Claude Code extension or Anthropic API.

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

After a successful tool call, Claude should continue with the next step. The turn should not end silently mid-task.

Still need to ship something?

×6

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

Back to top recommendations

TRENDING