Follow Discord
← All releases Home ←olderv2.1.275 v2.1.277newer→

Claude Code v2.1.276

2 entries read v2.1.275 → v2.1.276 Markdown Unofficial

Model-advisor's standby model selection now checks not just whether a fallback model is available but whether the account is actually talking to Anthropic's own API before picking it. Previously the base URL wasn't verified, which meant the standby pick could be selected even when requests were routed elsewhere. The check now confirms the API endpoint before allowing that selection to proceed.

Reading as
Show only
Tier
Flag state
Names
Pick an entry · j / k steps through · rest on a row to peek
Below the fold

Everything else

Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.

1 entry

Bug Fixesopen

✓Fixed
Under the hood
Useful2 Signal2
Elsewhere no docs found unclear

Model-advisor standby model selection now double-checks the base URL is Anthropic's own#

Model-advisor's standby model pick now also requires the account to actually be talking to Anthropic's own API

Unclear Whether the related tengu_sage_compass2 gate is enabled for any account is unknown; no reading of it has been taken under this release.

Feature flag
tengu_sage_compass2 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 v2.1.276: not a boolean we can read

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 v2.1.276. It isn't a statement about your account. What a flag value here can and cannot tell you

Details 0 0 Feedback
_CLAUDE_CODE_ASSUME_FIRST_PARTY_BASE_URL
What

Claude Code has an internal "model-advisor" feature that can automatically switch you to a standby (fallback) model. Previously, this switch only checked that the advisor tool was enabled and that it had ranked a standby model. Now it also checks that the connection is genuinely going to Anthropic's own servers: the account type must be firstParty, and either _CLAUDE_CODE_ASSUME_FIRST_PARTY_BASE_URL is set, or the effective ANTHROPIC_BASE_URL actually resolves to api.anthropic.com.

In practice, this means:

  • If you're signed in with a first-party Anthropic account but have ANTHROPIC_BASE_URL pointed at a custom proxy or gateway, the advisor will no longer silently substitute a standby model.
  • The standby-model switch now only kicks in when requests are verifiably reaching Anthropic's own API endpoint.
Why

This closes a gap where a proxied or gateway-routed session could still get its model silently swapped out by the advisor, even though it wasn't actually talking to Anthropic's servers. Anyone routing Claude Code through a custom ANTHROPIC_BASE_URL should expect the standby-model feature to stay off rather than kick in unexpectedly.

1 entry

Internal Changesopen

·Internal
Under the hood
Useful1 Signal0
Elsewhere

Version bump to 2.1.276#

Claude Code updated to version 2.1.276 with no functional changes

Details 0 0 Feedback
What

This release bumps Claude Code's internal build metadata (version number, build time, and git commit reference) to 2.1.276.

Why

There is no behavior change to be aware of here; only the version stamp embedded throughout the app was updated.

Related

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

Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v2.1.276. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.

Of these 1 bullets, 1 name something an entry on this page also names, 0 name something no entry here does, and 0 name nothing specific enough to line up either way. The pairings are made on names both sides wrote down, a flag or a setting or a slash command, so read one as probably the same thing rather than as a fact, and read the middle number as candidates rather than as a miss count.

Read it on GitHub →
System prompt

No change to the system prompt since v2.1.275.

Claude Code, interactive mode

Read the prompts for this release →
Documentation

What the docs did around this release

296 documentation changes were recorded within 24 hours either side of this release, nearest first. The closest 12 are below. They're here because they happened near this release in time. That's not a claim that this release caused the edit, or that the page documents anything in it.

sandboxing Changed +1 -1 recorded here claude-code plugins-reference Changed +9 -5 recorded here claude-code plugin-marketplaces Changed +27 -6 recorded here claude-code plugin-dependencies Changed +1 -1 recorded here claude-code discover-plugins Changed +33 -2 recorded here claude-code changelog Changed +4 -0 recorded here claude-code third-party/claude-desktop/configuration-changelog Changed +4 -0 recorded here claude-docs cowork/changelog Changed +20 -0 recorded here claude-docs workflows Changed +9 -9 recorded here claude-code ultrareview Changed +10 -3 recorded here claude-code tools-reference Changed +1 -0 recorded here claude-code settings-reference Changed +2 -4 recorded here claude-code

Every time above is when this site's poller recorded the change, which is up to half an hour after the edit on an ordinary read and up to a day after it on a full sweep. Upstream's own edit time is used instead wherever a capture carries one. None of these do.

The documentation ledger →
Switches

Every name in this release

The 1 literal strings found in the bundle, with the number of entries that name each one. Picking one searches for it. A name is here because this build's code mentions it, which is not the same as it working or being finished.

Settings and names in the code