Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.267 ·

Model-catalog shadow-compare fetch changes: network gating and caching

The background check that compares the served model catalog now handles network access and caching differently, with a bounded wait

TierNothing to try yethow much it should matter to you
Useful2my rating, 1 to 5
Signal3worth watching, 1 to 5
AreaModel Catalogwhat it touches
KindIn Developmentin v2.1.267,
Group of 2 Nothing to try yet

The background check that compares the served model catalog now handles network access and caching differently, with a bounded wait

What

  • The background "shadow compare" fetch that checks the served/published model catalog now unconditionally allows network access for its own fetch path (a related sibling call still gates access based on whether Claude Code is running headless). The shadow-compare fetch only runs at all if an internal mode check doesn't disable it (covering environment overrides, bare mode, non-first-party or non-claude.ai auth, missing organization, or policy).
  • The shadow-compare check now first looks at a local cache entry and checks whether it is stale before deciding whether to make a network fetch, then writes the fresh (or errored) result back to the cache.
  • If the fetch does not finish within a fixed time budget, it no longer blocks; instead it schedules a background check to finish later and logs a new model_catalog_late_fetch event.

Why These changes make the background catalog comparison less likely to block or make unnecessary repeated network requests, while keeping the feature itself gated off unless explicitly enabled.

What has happened since
Flag reading moved The flag server now returns {"mode":"off"} for tengu_delegated_quail, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading moved The flag server now returns nothing at all, having stopped carrying it for tengu_delegated_quail, read as this account. A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.

See this across every release →

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhether this gate is enabled for any given account isn't known; nothing has been read yet about the tengu_delegated_quail or…

See this entry in the whole of v2.1.267 →