[FEATURE] No indication of WHICH file for READ tool

### Preflight Checklist - [x] I have searched [existing requests](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20label%3Aenhancement) and this feature hasn't been requested yet - [x] This is a single feature request (not multiple features) ### Problem Statement Current behavior: Read 1 file (ctrl+o to expand) Problem: - No indication of WHICH file - User must expand every single Read to see the path - When hook blocks a read, user doesn't know what was blocked without expanding - Wastes time, breaks flow Expected behavior: Read: 00-project-manager\system.md or at minimum: Read: system.md (ctrl+o for full path) Why this matters: 1. Debugging - need to see what agent tried to access 2. Security - hook blocks should show blocked path immediately 3. Audit trail - scrolling through conversation, can't tell what was read 4. Multiple reads - "Read 3 files" tells me nothing Same issue applies to: - Write tool - Edit tool - Glob tool - Any tool that operates on files ### Proposed Solution Suggested fix: Show tool_name: primary_identifier in collapsed view. File path for file ops, search pattern for Grep/Glob. ### Alternative Solutions _No response_ ### Priority Critical - Blocking my work ### Feature Category CLI commands and flags ### Use Case Example _No response_ ### Additional Context _No response_

Posted by tristananh120-web on Jan 27, 2026, 3:04 AM

Tags

• github (Software)

Related issues

• [Meta] Feedback on granular control over Copilot changes
• unexpected status 401 Unauthorized issue
• [MODEL] Measurable quality regression in Claude generation 5 (Fable 5 / Opus 5 / Sonnet 5): worse nonsense detection, ~2x verbosity, under-disclosed model fallb
• [CRITICAL] Subagent spawning and subagent pattern bugs trigger infinite recursion, infinite token usage, grossly inefficient token usage, and lost accumulated s
• Video stops playing after some minutes
• [MODEL] Claude verbose code comments by default — ignores instructions to stop.