Data and AI releases

2,010 this month · 180 companies

Claude Code 2.1.294

UpdateNot yet verified

- Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block Improved how prompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early

AI agentsLLMsCoding agents

Read on github.com

Also shipped Oct 8, 2026Anthropic in October 2026 →

Performance Risks Inbox is now generally available

Performance Risks Inbox is GA Performance Risks Inbox is now generally available (GA). It finds the performance anti-patterns that quietly slow your application down, such as N+1 queries and inefficient database calls, and groups them in one place so your team can fix them before they become incidents.

GA
Source ↗

CLI v0.9.0 | CLI, Beta

CLI v0.9.0 Manage cloud tasks with cr code , including interactive messages, side questions, plans, and delivery. Complete shell commands and read richer review JSON . Verify signed Linux releases and recover more reliably from login and update failures. Run cr update . See cloud tasks and upgrade details .

Beta
Source ↗

More from Claude CodeEvery Claude Code release →

Claude Code 2.1.295

- Added onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through Added Program Status Protocol (OSC 7501) support: terminals that implement it can show whether Claude Code is working, waiting on you, or done Added quoted text to the /copy picker, so a...

Update
Source ↗

Claude Code 2.1.296

- Added a code key to the Claude apps gateway's managed.policies[]: the same settings as cli, also applied in Claude Desktop's Code tab; beside desktop, it turns on Claude Desktop's gateway mode Added autoCompactWindow to subagent frontmatter and --agents definitions, so a subagent can auto-compact earlier than the main conversation's window Added...

Update
Source ↗

Claude Code 2.1.293

- Added Claude Haiku 5.5 (claude-haiku-5-5), now the default Haiku model on the Anthropic API , 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K) Added agentType to the subagentStatusLine payload, so scripts can tell custom subagent types apart Added isDeferred to $.tool.register for mods: false lists the tool's schema in the prompt from...

Update
Source ↗

Claude Code 2.1.291

- Fixed a regression in 2.1.290 where cloud sessions could drop answers to permission prompts Fixed a regression in 2.1.288 where the last messages of a session could be lost when quitting

Update
Source ↗

Claude Code 2.1.292

- Added --marketplace to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from it Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for Added CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS environment variable to set a...

Update
Source ↗

Claude Code 2.1.290

- Added serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end Added agentId to the tool.check event of plugin hooks, so a hook can tell a subagent's permission check from the main session's Added ceiling to the question and verdict a mod's tool.check hook reads...

Update
Source ↗

Claude Code 2.1.289

- Fixed a deny or ask rule on a nested part of a compound shell command not holding over a user-installed mod's approval on managed machines Fixed the terminal freezing on short code blocks with many unclosed tags or deeply nested ${ substitutions Fixed Read deny rules not applying to files @-mentioned, changed, or selected in the IDE through a symlink...

Update
Source ↗

Claude Code 2.1.299

- Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it all...

Update
Source ↗