PulseAugur
EN
LIVE 19:13:14

Claude Code hook bug halts tool calls after first denial

By PulseAugur Editorial · [1 sources] ·

A user encountered an issue with Claude Code where tool-use hooks stopped functioning after the first denial. The user attempted to reduce token usage by redirecting file reads to a local LLM summarization tool via a PreToolUse hook. However, after the hook denied the 'Read' tool, subsequent calls to the local summary tool, though appearing to be made by the model, were not logged by the hook. This behavior was observed on Claude Code 2.1.227 running on Windows 11 Home. The user also noted that local summaries can be unreliable, leading the model to either re-verify information or produce inaccurate results. AI

IMPACT This bug in Claude Code's hook system could hinder developers from customizing tool usage and potentially reduce efficiency by preventing the use of local models for summarization.

RANK_REASON User reports a bug in a specific tool's hook functionality.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Claude Code hook bug halts tool calls after first denial

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · Chikoku_NEKO ·

    Claude Code hooks stop firing on MCP tools after the first deny (found it while trying to cut tokens)

    <h2> TL;DR </h2> <ul> <li>I tried to cut Claude Code's token use by having a <code>PreToolUse</code> hook <code>deny</code> Read and redirect the model to a local LLM summary tool.</li> <li>The hook log contained not a single row for the local summary tool. But the tool was being…

RELATED ENTITIES

RELATED TOPICS