Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-09-18 · high
Version 2.1.276 fixes a 400 error hitting proxy and gateway users, caused by 2.1.275's new default skill-syncing feature.
Why now: Anthropic's changelog dates the 2.1.276 fix to September 18, 2026.
Claude Code 2.1.276 fixes a 400 error that broke every request routed through a proxy or gateway, per the changelog. Anyone routing Claude Code through a corporate proxy or LLM gateway, rather than Anthropic's endpoint, couldn't make a single request until the patch arrived.
The break traces to 2.1.275, which started syncing skills and plugins enabled on a claude.ai account into terminal sessions signed in with that account. The sync runs by default; opting out means setting syncClaudeAiSkills or syncClaudeAiPlugins to false. That release also added ctrl+enter to interrupt a turn and flush every queued message.
The sync logic broke any request through a custom base URL, returning a 400 error reading "Input tag advisor_20260301." The changelog doesn't say what in the sync code triggered the failure, only that it hit requests using a non-default ANTHROPIC_BASE_URL. Nor does it say how many releases or days the bug was live before the fix went out.
Each link below shares sources, entities, or timing with this story.
I've been telling people for months that the agent code I review is *correct and awful*. Correct in the sense that it compiles, passes the tests, does the thing. Awful in the sense that a 400-line function does the work of 80, the same helper exists three times under different...
I have a skills directory. I have no idea whether most of it does anything. I suspect you're in the same position, because the honest answer for almost everyone is that skills are vibes all the way down: you wrote one, the agent seemed better, you kept it. Claude Code v2.1.269...
It now dedupes local CLAUDE.md files against checked-in ones, proposes trimming content it can derive from the codebase, ranks unused skills, MCP servers, and plugins by context cost, and flags slow hooks. Background subagents run by default and, when launched from claude agen...
Go rotate a key. I'll wait. Claude Code 2.1.246, released August 25, lists this in its changelog: a fix for "telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (ANTHROPIC_BASE_URL); a credential is now only sent to its own hos...
The Linux x64 payload is compressed with zstd for both install and auto-update, the binary drops another 2MB by storing bundled skill and prompt text more compactly, code loads on demand rather than staying resident, and the runtime garbage-collects sooner as the heap grows in...
Claude Code 2.1.232 shipped August 13 with a default flipped underneath everyone. Subagent forking is now on: a spawned subagent inherits the full parent conversation and shares its prompt-cache prefix instead of starting cold. Nested spawn depth defaults to 3. Practitioner wr...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.