anthropics / anthropics/claude-code

[BUG] Tool use rejection feedback entered in the permission prompt does not appear to influence the model's next turn

Ouverte
#89,231 1 commentaire 0 réactions 0 personnes assignées Voir sur GitHub
area:permissions area:tools bug platform:macos
Langage dominant
Python
Étoiles
145k
Forks
23.1k
Métriques de merge des PR
Métriques de PR en attente

Description

### Preflight Checklist

- [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code

### What's Wrong?

When the CLI prompts for permission to use a tool, the third option labelled along the lines of "No, and tell Claude what to do differently" lets the user type free-text feedback before confirming the rejection. The expectation is that this feedback is delivered to the model as part of the rejected tool's `tool_result` so it can adjust its next turn. In practice the model behaves as if the rejection had been a bare "no" with no feedback attached.

### What Should Happen?

The user-supplied feedback should reach the model in the next request as the content of the rejected tool's tool_result block and the model's next turn should visibly take it into account.

### Error Messages/Logs

```shell

```

### Steps to Reproduce

1. Ask Claude to do something that triggers a tool that isn't auto-allowed (e.g. Bash, an Edit, etc.).
2. At the permission prompt, focus the "No" option and press Tab to enter feedback mode.
3. Type something specific the model could act on, e.g. "don't use grep, use ripgrep instead".
4. Submit.
5. Observe the model's next assistant turn: it does not reflect the feedback; typically, it retries the exact same tool call, or moves on as if no instructions were given.

### Claude Model

Not sure / Multiple models

### Is this a regression?

Yes, this worked in a previous version

### Last Working Version

_No response_

### Claude Code Version

2.1.241

### Platform

Anthropic API

### Operating System

macOS

### Terminal/Shell

Other

### Additional Information

_No response_

Guide de contribution

Aucun guide de contribution indexé pour ce dépôt

Piste de recherche

Reproduce the permission prompt flow described in the issue, using a tool such as Bash or Edit and feedback such as "don't use grep, use ripgrep instead." Trace the rejected tool call into the next model request and verify that the feedback is present in the tool_result content and changes the following assistant turn.

Rédigé par le modèle d'indexation à partir du texte de l'issue.

Évaluation

Stack technique
python
Domaine
ai, cli
Type d'issue
Bug
Difficulté
4/5
Temps estimé
3-5 jours
Activité
Active
Clarté
Plutôt claire
Accessibilité débutants
55/100

Recevez les nouvelles issues par e-mail

Un résumé court des issues GitHub adaptées aux débutants.