Context Engineering on 卓琪的开发笔记

Claude's Tool Calling Paradigm Shift: A Deep Dive into Programmatic Tool Calling and Dynamic Filtering

Sat, 13 Jun 2026 00:00:00 +0000

The important change is not “two more tool features.” It is the movement of multi-step orchestration into a code-execution environment, with only a compact result returning to model context.

Background: The Cost Problem in Agent Tool Calling
#

In traditional agent tool-calling, every tool invocation requires a full cycle of “model inference → tool execution → result return → model re-inference.” This seemingly natural loop breaks down at scale in three ways:

RAG vs LLM Wiki vs Plain Text — A Decision Framework for Agent Long-Term Memory

Mon, 11 May 2026 00:00:00 +0000

Every Agent builder hits this question eventually: where do I store user data so the agent remembers it next session?

Three approaches dominate the landscape: RAG (vector retrieval), LLM Wiki (structured knowledge injection), and plain-text context memory (the CLAUDE.md / Cursor Rules pattern). Each has vocal advocates. But picking wrong is expensive — do RAG too light and it’s a noise generator; do plain text too heavy and it’s a token incinerator.

Context Engineering on 卓琪的开发笔记

Claude's Tool Calling Paradigm Shift: A Deep Dive into Programmatic Tool Calling and Dynamic Filtering

Background: The Cost Problem in Agent Tool Calling #

RAG vs LLM Wiki vs Plain Text — A Decision Framework for Agent Long-Term Memory

Background: The Cost Problem in Agent Tool Calling
#