claude-code - 💡(How to fix) Fix Approve-once-per-session for repeated identical tool calls

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…

Fix Action

Fix / Workaround

The only current workaround is to permanently allowlist the tool via the project .claude/settings.json. While effective, this requires upfront configuration and is broader than a session-scoped approval.

RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing requests and this feature hasn't been requested yet
  • This is a single feature request (not multiple features)

Problem Statement

When a pipeline fans out to multiple parallel sub-agents (e.g., 10–15 simultaneous Jira lookups), each agent independently triggers a permission prompt for the same tool. The user is required to approve each prompt individually, which is impractical and inefficient at scale.

Proposed Solution

Implement a session-scoped approval mechanism. Once a user approves a tool call (same tool name + same permission scope) during a session, all subsequent calls to that tool within the same session should be auto-approved. This avoids the need for repeated prompts and does not require permanent allowlisting.

A confirmation banner, such as "Approved jira_search for this session (3 more auto-approved)," should be displayed to provide transparency and session-level visibility without interrupting workflow.

Alternative Solutions

The only current workaround is to permanently allowlist the tool via the project .claude/settings.json. While effective, this requires upfront configuration and is broader than a session-scoped approval.

Priority

Critical - Blocking my work

Feature Category

MCP server integration

Use Case Example

This feature is especially needed for multi-agent pipelines (fan-out orchestrators) that launch N parallel sub-agents, all calling the same MCP tool. The current model generates N blocking prompts, which undermines the benefits of parallel execution.

Additional Context

No response

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