Tags
"An expandable usage limits section" is part of a new Claude Code layout for Claude Desktop, according to TestingCatalog, along with an updated model selector. Anthropic's official redesign announcement doesn't mention either one.
"Almost ready" is how a Threads post describes a Liquid Glass revamp of Claude's iOS app, which reportedly moves navigation to a bottom tab bar. Anthropic hasn't confirmed it, and the post gives no release date.
"Instead of cutting off mid-edit": Claude Code will try to wrap up when you hit the 5-hour limit mid-task, using a small allowance taken from your weekly limit. On Pro plans, that works once a week.
Plugin submissions for Claude got their own portal, where builders can track the review and see usage. Over the coming weeks, those plugins land in one discovery experience across Claude and Claude Code.
Claude Code 2.1.282 won't let a cloned repo's settings switch on telemetry. It ignores OpenTelemetry variables that turn on export or capture content, and names each skipped one at startup.
A small team that built a Claude agent can now list it on Claude Marketplace, the same catalog where buyers find Cursor, CrowdStrike and Deloitte. Anthropic hasn't said how those listings get vetted.
Threads in Claude Code Projects were built as cloud sessions that keep working after you close your device, but Anthropic says they can now run on your own machine as well.
A one-time $250 credit on Max and $100 on Pro sits outside your usage limits, so when you hit a cap locally, Claude Code keeps going in cloud sessions until the credit runs out. You have to claim it by Oct 7.
A platform team sending Claude Code traffic through its own gateway into Bedrock can apply one Amazon Bedrock guardrail to every request in version 2.1.281, though it has to go on all Bedrock upstreams or none.
Amazon opened its seller tools to Claude, with a plugin that checks inventory, adjusts prices and updates listings outside Seller Central. Setup takes about 60 seconds, and every action still waits for the seller's approval.
Anthropic's browser sandbox for the Claude API answers to Playground now, and every call comes back with its tokens, cost and latency, though it keeps no prompt history to go back to.
"Fable 5.2 is pure JS thats it one shot," posted X user Chetaslua, per TestingCatalog. No assets, no plugins, every sprite drawn in code, and Anthropic hasn't commented on the model it hasn't announced.
You clone a repo with an AGENTS.md in it and no CLAUDE.md, and Claude Code 2.1.277 reads it as the project instructions. Bedrock, Vertex and Foundry don't get that fallback yet.
Claude Code 2.1.275 adds a send-now key "Interrupts the current turn and sends all queued messages at once": that's ctrl+enter in Claude Code 2.1.275, and sent and queued messages stay gray until the model receives them.
Threads in a project can merge-conflict with each other Each thread in a Claude Code project is a full cloud session on its own branch, so two of them touching the same code land as a merge conflict. Beta today for select Pro and Max users on cloud sessions.
Mythos opens to verified biologists Mythos landed in biologists' hands for the first time, behind a verification program Anthropic opened for applications today. The beta takes teams of all kinds; Pro and Max plans come later.
A corrupted transcript could pin a Claude Code session in an endless retry of an "unexpected tool_use_id" 400 error. In 2.1.274 those transcripts self-heal where possible, and otherwise a clear error ends the loop.
Close the laptop and the handed-off report keeps moving: Cowork and chat are merging into one Claude, rolling out to Pro and Max over the next few weeks, with Claude Docs, Slides and Design in beta on all paid plans.
Five new request headers let an LLM gateway see which Claude Code request is which: class, agent type, compaction state. They stay off until you set CLAUDE_CODE_GATEWAY_HINT_HEADERS=1 in 2.1.273.
Per TestingCatalog on Threads, Claude Desktop may gain a Claude Code Hub that lists local and cloud sessions in one view, each with its own model, effort and permission mode. Anthropic hasn't announced it.
