Articles

In-depth analysis of Gemini CLI core configuration parameters, covering key modules such as Checkpointing, Model Aliases, Context, and Tools. This article details the differences in parameter support between CLI mode and A2A-Server mode, helping developers accurately configure and optimize AI Agent workflows.

This post documents the troubleshooting process for a gemini-cli OAuth login failure on macOS. Since V2rayU lacks a native Tun mode, it cannot proxy the gemini-cli’s random port callback. This article introduces a clever solution: using sing-box to enable Tun mode for transparent proxying, intercepting all system traffic, and forwarding it back to V2rayU’s SOCKS port, perfectly solving the proxy challenge for CLI tools.

Through reverse engineering, this article provides a deep dive into the internal architecture and working principles of Anthropic’s AI coding assistant, Claude Code. It breaks down the collaborative mechanisms of its Main and Sub-Agents, system prompts, toolset definitions, and context management strategies, helping you to fully understand the autonomous execution flow of this powerful AI tool.

From Vision Transformers to image-text alignment, exploring the core technical principles and implementation methods behind multimodal models, including CLIP, SigLIP, and visual encoding strategies of mainstream multimodal large models.

Analyzing open source DeepResearch implementations based on source code, including the engineering architecture, Agent design, prompts, and core processes of solutions such as Dify, LangChain, HuggingFace, and Zilliz Cloud.

A brief overview of the technical features in reasoning capabilities of DeepSeek-R1 and Kimi k1.5: DeepSeek employs GRPO algorithm and model distillation to enhance reasoning performance, while Kimi explores the integration of long-form Chain of Thought with reinforcement learning.

After reviewing LightRAG, I found that its persistence support was still limited, missing the most important TiDB (not really). So I took some time to contribute and write about it.

This article aims to explore the architectural design and specific code implementation of the RAG algorithm through the interpretation of papers and source code. This article mainly discusses GraphRAG, LightRAG and RAPTOR RAG, and also mentions Contextual Retrieval proposed by Anthropic and the evaluation method of the RAG algorithm. In the end, it is recommended that different methods be selected according to the size of the knowledge base document.

With the popularity of the Transformer architecture, many Embedding and Rerank models are now based on this architecture. Taking this opportunity, we will sort out the process and history of the research, and take stock of the architectures adopted by several well-known Rerank models and the companies that developed them. Finally, we will return to the topic and briefly discuss whether Rerank should be used in RAG scenarios.

This article mainly introduces the HTTP/2 protocol and its CONTINUATION Flood problem. The article shows how to parse the Frame structure in Http2-related code through the golang.org/x/net source code, and analyzes in detail the three security risks of the CONTINUATION Flood attack and the corresponding solutions.

This article mainly sorts out the relevant concepts of the hybrid expert model (MoE), and introduces the architectures and optimization methods of several open source MoE models, such as GShard, Switch Transformers, DeepSeek-MoE, and LLaMA-MoE. The characteristics and optimization methods of these models are also introduced.

This paper provides a detailed introduction to various vector similarity search methods, such as KD trees, IVF inverted indexes, HNSW and LSH. It provides a detailed introduction from data structures to algorithm implementations by analyzing the specific implementations in the source codes of Annoy, Faiss, PGVector and FALCONN.

This paper compares in detail the threading models and scheduling mechanisms of the Java and Go programming languages. It analyzes their specific implementations and design ideas from a source code perspective, especially the 1:1 correspondence between Java’s Thread and operating system threads, and the n:m relationship between Go’s goroutine managed through the GPM model.

This article describes in detail the specific configuration steps for multiple Umami deployment solutions, and also briefly explains the advantages, disadvantages and applicable scenarios of each solution. The article focuses on the method of configuring Umami under the Hugo framework, including the specific steps for adding Umami tracking code to different themes, as well as some advanced configuration options such as the TrackEvent and Tracker parameters.

This article explores in detail the principles and use of the web servers built into Spring Boot (including Tomcat, Jetty, Undertow, and Netty), with a particular focus on the differences between the Servlet and Reactive frameworks and their implementations in Spring Framework 5.0, including the WebServer interface and the concrete implementation of WebServerFactory.

Take a look at the Spring source code and PR records to find out which version and commit introduced the support for Self-Injection.

The difference between Go value objects and pointer objects in terms of storage, performance and usage

It mainly introduces the use and inheritance relationship of Buffers in Java NIO, Netty and Spring Reactor.

This article details the process of setting up a blog using Hugo and a Docker image, including the selection of different image versions, the use of the Blowfish theme, custom icons, the integration of comment plugins, the deployment of GitHub Pages, and the integration of the Umami statistics panel.