Kimi K2.7 Code keeps stopping after thinking without doing the work
- Langage dominant
- Aucune donnée de langage
- Étoiles
- 2.1k
- Forks
- 153
- Métriques de merge des PR
- Aucune PR mergée en 30 j
Description
### Short summary
Kimi K2.7 Code from GitHub Copilot keeps stopping without doing the actual work
### Affected version or release
v1.0.18
### Installation context
_No response_
### What happened?
We've enabled Kimi K2.7 code in GitHub Copilot Enterprise, and while it kind of works, it frequently stops right after thinking without taking the action you'd expect it to do. This doesn't happen with other models like GPT 5.5 or MAI-Code-1-Flash. I suspect Kimi K2.7 Code signals something that makes GitHub Copilot think its done and should stop when it really shouldn't. This makes the model unusable most of the time, because when it refuses to just do the thing, it won't budge and I have to switch to another model to ask it to do something.
### Steps to reproduce
Ask a simple query like "open a pull request" or "watch the workflow run". It will show brief thinking, and then it'll stop. If you look at the thinking details, it shows it understood what the action to be taken is, except it doesn't do it. Repeatedly asking for the same thing doesn't help.
### Expected behavior
When asking Kimi K2.7 Code to do something, I would expect to do the action instead of stopping, like all other models.
### Additional context
Guide de contribution
Ouvrir le guide de contribution
Piste de recherche
Commencez par reproduire le problème dans v1.0.18 avec GitHub Copilot Enterprise et Kimi K2.7 Code en utilisant "open a pull request" ou "watch the workflow run", puis comparez le comportement avec GPT 5.5 ou MAI-Code-1-Flash. C'est terminé lorsque l'action demandée est exécutée au lieu de s'arrêter après la phase de réflexion.
Rédigé par le modèle d'indexation à partir du texte de l'issue.
Évaluation
- Stack technique
- github
- Domaine
- ai, desktop
- Type d'issue
- Bug
- Difficulté
- 4/5
- Temps estimé
- 3-5 jours
- Activité
- Calme
- Clarté
- Plutôt claire
- Accessibilité débutants
- 45/100