Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-17 · high
The opt-in forward_user_identity flag sends signed-in headers through Anthropic upstreams, fixing gateways where every request looked identical.
Why now: The Claude Code changelog for release 2.1.233 is covered in the August 17, 2026 briefing.
Claude Code's 2.1.233 release added forward_user_identity, an opt-in gateway setting that sends a signed-in user's identity to Anthropic upstreams as request headers, per the Claude Code changelog.
The setting targets teams running Claude Code behind their own apps gateway, where a proxy sits between developers and Anthropic. Before this release, every request through that proxy looked the same, so nobody knew which developer generated which bill. For companies watching AI spend closely, that blind spot made it hard to enforce per-team budgets or spot a single account driving costs.
Turning on forward_user_identity gives the proxy something to key off. It's off by default, so nothing changes until an admin flips it on.
The same release also improved gateway error handling. A 400 or 413 from Vertex, Foundry, or Claude Platform on AWS now shows the upstream's actual error text instead of a generic wrapper. A rejected request finally says why it failed.
Each link below shares sources, entities, or timing with this story.
v2.1.211 stops Bedrock, Vertex, Mantle, and Foundry from rebilling cached system context as full-price input tokens.
SkillsMetric evaluated 2,266 skills across 16 attack types, hitting F1 of 73.4%±0.5% overall (arXiv 2608.08468). Host destruction via shell commands: 0% detection. Natural-language prompt injection: 42%. If you lint third-party skills before install, this tells you precisely w...
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...
Three separate Anthropic changes over about two weeks point the same direction, and none of them announced themselves as a strategy. Claude Code 2.1.238 added claude self-hosted-runner --defer-shutdown-max-min, which keeps serving attached sessions on SIGTERM, parks whatever's...
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...
Released July 10, /doctor scans checked-in CLAUDE.md files and flags content Claude could derive by reading the codebase itself. This is the first time Anthropic has shipped tooling treating context files as a cost surface to prune rather than a document to grow. Same release...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.