Starstruk Logo MarkStarstruk

v0.25.7

tanchongmin/strictjsonv0.25.7Aug 21, 2026by mahimairaja

Upgrading?

What changed from v0.25.6 → v0.25.7?What's new in v0.25.8 after v0.25.7?

AI Summary

This release focuses on billing and reconciliation capabilities, including gating model enablement on declared rates and improving the naming of discrepancies in reconciliation processes.

Key Highlights

  • Documentation updates for the fourth pricing state
  • Billing feature to gate model enablement based on declared rates
  • Feature to let rate rules set what the operator pays
  • Reconciliation feature to name flagged row disagreements

New Features

  • Rate-based model enablement gating
  • Operator payment configuration in rate rules
  • Reconciliation discrepancy naming

Full Release Notes

## Docker Images

Published to Docker Hub:

- `mahimairaja/voicegateway:0.25.7`
- `mahimairaja/voicegateway:latest`
- `mahimairaja/voicegateway-dashboard:0.25.7`
- `mahimairaja/voicegateway-dashboard:latest`

Built for `linux/amd64` and `linux/arm64`.

## Quick Start

```bash
docker run -p 8080:8080 \
  -v $(pwd)/voicegw-data:/data \
  mahimairaja/voicegateway:0.25.7
```

See [docs.voicegateway.dev](https://docs.voicegateway.dev) for full documentation.


## What's Changed
* docs: describe the fourth pricing state everywhere it is listed by @mahimairaja in https://github.com/mahimailabs/voicegateway/pull/268
* feat(billing): gate model enablement on a declared rate, and list the gaps by @mahimairaja in https://github.com/mahimailabs/voicegateway/pull/269
* feat(billing): let a rate rule set what the operator pays by @mahimairaja in https://github.com/mahimailabs/voicegateway/pull/270
* feat(reconcile): name what a flagged row's disagreement is about by @mahimairaja in https://github.com/mahimailabs/voicegateway/pull/271


**Full Changelog**: https://github.com/mahimailabs/voicegateway/compare/v0.25.6...v0.25.7

Related Repositories

rasbt/LLMs-from-scratch★ 107,042

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

lyogavin/airllm★ 40,155

AirLLM 2.8T LLM inference with single 4GB GPU

NirDiamant/RAG_Techniques★ 29,958

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

microsoft/OmniParser★ 25,539

A simple screen parsing tool towards pure vision based GUI agent

karpathy/nn-zero-to-hero★ 24,906

Neural Networks: Zero to Hero