Topic

#Prompt Caching

9 articles on Prompt Caching — news, releases, guides and analysis from the SourceFeed engine.

Claude Code Flips Subagents From Isolation to Inheritance

Version 2.1.232 makes forked subagents share your full conversation and prompt cache by default, and patches three trust-boundary bugs.

Anthropic's candid efficiency tips double as an admission: agent tooling still makes you manage its cache by hand.

Measure real token costs, then stack prompt caching and the Batches API to slash them.

Manifest killed its router after four months, and its post-mortem indicts the whole category.

An unedited LLaMA-generated tutorial gets the basics wrong — here's how the window really works in mid-2026.

OpenCode starts near 7k. The gap is design, not a glitch, and it changes session cost math.

Most of the bill is re-sent history and unused tool schemas, not hard thinking.

How VS Code's under-the-hood optimizations and smart developer habits can slash your GitHub AI Credit consumption.

GPT-5.6's multi-tier architecture forces developers to stop hardcoding model names and start building intelligent routing layers.