Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

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.

Prompt capture

v2.1.163 system prompt

1 of 25 tool descriptions changed. Compared against v2.1.162.

Agent SDK, print mode 27 model strings 25 tools released captured Markdown

Workflow +1 −1 of 159 lines

This edit reached all 27 arms

from line 76
   const c = await parallel(b.map(...))
 that middle transform doesn't need the barrier. Rewrite as a pipeline with the transform inside a stage. When in doubt: pipeline.
 
-Concurrent agent() calls are capped at min(16, cpu cores - 2) per workflow — excess calls queue and run as slots free up. You can still pass 100 items to parallel()/pipeline() and they all complete; only ~10 run at any moment. Total agent count across a workflow's lifetime is capped at 1000 — a runaway-loop backstop set far above any real workflow.
+Concurrent agent() calls are capped at min(16, cpu cores - 2) per workflow — excess calls queue and run as slots free up. You can still pass 100 items to parallel()/pipeline() and they all complete; only ~10 run at any moment. Total agent count across a workflow's lifetime is capped at 1000 — a runaway-loop backstop set far above any real workflow. A single parallel()/pipeline() call accepts at most 4096 items; passing more is an explicit error, not a silent truncation.
 
 The canonical multi-stage pattern — pipeline by default, each dimension verifies as soon as its review completes:
   export const meta = {

The full text

The whole documents, one page each, exactly as they were sent.