{"version":"2.1.301","anchor":"thinking-blocks-counted-in-a-stop-detection-check-sidecar-p","canonical_anchor":"thinking-blocks-counted-in-a-stop-detection-check-sidecar-p","heading":"Message check now counts reasoning blocks, plus small internal additions","tier":"internal","area":"Messages","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.301\/e\/thinking-blocks-counted-in-a-stop-detection-check-sidecar-p","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.301","markdown":"### Message check now counts reasoning blocks, plus small internal additions\n\nA check that scans messages now counts the model's reasoning blocks and no longer reads a stale value for tool calls; subagent side files go under a folder\n\n**Unclear.** It is not stated what the message check decides, so the visible effect of counting reasoning blocks is unclear.\n\n**What**\n\nThis release brings a few small changes inside Claude Code:\n\n- A check that scans the conversation's messages now also counts thinking blocks, which hold the model's step-by-step reasoning.\n\n- The same check now tests for tool calls (requests the model makes to run a tool, such as reading a file) using the correct value; before, it read an out-of-date one.\n\n- Side files kept alongside a subagent's transcript are now stored under a folder named \"subagents\". A subagent is a helper agent Claude Code starts to work on part of a task, and its transcript is the saved record of its conversation.\n\n- Several new internal counters and timestamps are tracked.\n\n**Why**\n\nThese are mostly small internal bookkeeping additions. The correction to the tool-call test means that check no longer works from stale information.\n\n- Area: Messages\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}