Lead story
Ask your AI
Top stories
Models & availability
Latest
Lead story
Ask your AI
Top stories
Models & availability
Latest
Amp rewrote its read_thread tool, which lets the platform pull context from other threads, to handle long, compacted threads. The new version uses a subagent that searches and extracts information from long threads, switching the underlying model to GLM 5.2 from Gemini 3.5 Flash and optimizing for correctness over speed. The change requires no user action.
From the source
read_thread is now a subagent tuned to extract information from long threads.
ampcode.com