Claude Code extended-thinking output described as a summary, not the raw trace

Category: Agentic coding
Status: discussion
Sources: patrickmccanna.net, HN
Summary: A post dated 2026-06-22 argues that the text Claude Code displays as "extended thinking" is a summary rather than the model's authentic reasoning trace. The author inspected Claude Code session logs and found only an encrypted signature of roughly 600 characters with no readable thinking text, then cross-referenced Anthropic's documentation and a cryptographic analysis by Matt Green. The underlying reasoning content is encrypted and not exposed to users. The technical findings rest on documentation and log inspection; the framing is the author's own assessment.
Why it matters: Developers who treat the displayed thinking as a faithful debugging trace of the agent's reasoning are acting on a summarized view rather than the raw chain.