fix(llama.cpp): improve context shift handling

[mudler]

Description

This pull request includes changes to the backend/cpp/llama/grpc-server.cpp file to handle context capacity and prevent redundant checks. The most important changes include adding a check for context capacity and improving logging when context is exhausted.

Context capacity handling:

• Added a check to set truncated and stopped_limit flags and log a message when the context capacity is reached. (backend/cpp/llama/grpc-server.cpp)

Redundant check removal:

• Removed redundant checks and improved logging when context is exhausted by releasing the slot and logging an error message. (backend/cpp/llama/grpc-server.cpp)

Notes for Reviewers

Signed commits

• Yes, I signed my commits.

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	652d4b6
🔍 Latest deploy log	https://app.netlify.com/sites/localai/deploys/67af310860aaa80008ea81f9
😎 Deploy Preview	https://deploy-preview-4820--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.