v1.7.17
qdm12/gluetun-serversv1.7.17Aug 24, 2026by Ed1s0nZ
Upgrading?
AI Summary
Fixes chat checkpoint auto-resume logic to prevent stale responses and adds per-turn token usage tracking capabilities.
Key Highlights
- Disables automatic Eino checkpoint resume to prevent stale responses
- Adds per-turn token usage tracking (input, output, cached, reasoning)
New Features
- Per-turn token usage statistics
Full Release Notes
这次修复关闭了聊天链路中的 Eino checkpoint 自动恢复，避免旧断点抢先恢复导致模型反复回复历史对话。 This update disables automatic Eino checkpoint resume in chat flows, preventing stale checkpoints from taking over and causing repeated old responses. 同时新增/完善了按轮次展示 Token 用量的统计能力，可查看每次对话的输入、输出、缓存、推理和模型调用次数。 It also adds/improves per-turn token usage tracking, showing input, output, cached, reasoning tokens, and model call counts for each conversation turn.
Related Repositories
ollama/ollama★ 184,236
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,064
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,631
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.
junegunn/fzf★ 83,714
:cherry_blossom: A command-line fuzzy finder