Source Intelligence
Reading a new release v2.1.251 Analysing changes · 2/5 Sorting the findings · 1/4 steps 470 findings $18.91 so far

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.107 Home All releases olderv2.1.105 v2.1.108newer
Claude Code v2.1.107

Faster "Still Thinking" Progress Messages

What

The progress messages shown during long-running operations now appear much sooner, reducing the time users wait before seeing reassurance that the model is still working.

Details
  • "Thinking a bit longer… still working on it…" — now at 10s (was 30s)
  • "Hang tight… really working through this one…" — now at 30s (was 60s)
  • "This is a harder one… it might take another minute…" — now at 50s (was 90s)
  • "Still going… thanks for hanging in there…" — now at 80s (was 150s)
  • "Taking the time to get this right… thanks for your patience…" — now at 120s (was 240s)

The first progress indicator now appears 3x faster than before (10s vs 30s), providing much quicker feedback during complex reasoning.

Evidence

Timing thresholds in progress message array (search for "Thinking a bit longer")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

See this entry in the whole of v2.1.107 →