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 v2.1.58 Home All releases olderv2.1.56 v2.1.59newer
Claude Code v2.1.58

Optimized bridge polling for remote sessions

Feature flag
tengu_bridge_poll_interval_ms Not enough to say

Nothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.

This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.58: no gate table built for this version

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.58. It isn't a statement about your account. What a flag value here can and cannot tell you

What

The polling interval for the bridge connection (used in remote/cloud sessions) is now dynamically configurable from the server rather than being hardcoded.

Details
  • Poll interval is now controlled by the tengu_bridge_poll_interval_ms feature flag, with a default of 1000ms and a floor of 100ms
  • The flag value is cached and refreshed every 5 minutes (300,000ms TTL)
  • The block_ms parameter was removed from work-poll requests, simplifying the client-server protocol
  • These changes allow Anthropic to tune remote session responsiveness server-side without requiring client updates
Evidence

New cached config reader KL1() at line ~532330 (search for "tengu_bridge_poll_interval_ms")

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

See this entry in the whole of v2.1.58 →