Anthropic Release notes and new features

Claude Agent SDK 0.2.179

Claude Agent SDK version 0.2.179 is now available via PyPI.

Claude Code 2.1.319

Claude Code 2.1.319 adds support for background MCP tasks, new environment variables for auto-mode server checks, and a setting to deny tool calls that require permission prompts.

Claude Agent SDK 0.2.178

Claude Agent SDK 0.2.178 updates the bundled Claude CLI to version 2.1.318.

Claude Code 2.1.318

Claude Code 2.1.318 adds session answer recording, AWS role assumption for cost attribution, and improved credential expiration reporting.

Text generated by Claude Mythos 5, Claude Opus 4.7, and Claude Sonnet 4.6 carries Anthropic’s text watermark

Text generated by Claude Mythos 5, Claude Opus 4.7, and Claude Sonnet 4.6 carries Anthropic’s text watermark on the platforms listed in How Claude marks AI-generated content. On Claude Sonnet 4.6, text generated for a request that sets temperature, top_p, or top_k to a non-default value might not carry it. See Text watermark.

Claude Agent SDK 0.2.177

New Features on_failure option for HookMatcher: Control what happens when a hook callback fails. Set on_failure="block" to block the action when a callback raises, returns None, or returns a value the CLI rejects. Defaults to "continue" (treat failure as no decision).

Claude Code 2.1.317

- Added a warning to /schedule when a new cloud scheduled task gets connectors you did not ask for, with how to remove them Added a check that asks before a web or shell tool call sends your account email address to the network Added onFailure: "block" for Agent SDK hook callbacks, so a callback that fails blocks the action instead of letting it run Added a...

Claude Agent SDK 0.2.176

Claude Agent SDK 0.2.176 includes an updated bundled Claude CLI version 2.1.316.

Claude Code 2.1.316

This update adds pooled group budgets, configurable subagent effort levels, and new guardrail tagging for Bedrock upstreams. Fast mode for Opus 4.8 is deprecated and scheduled for removal on November 30, 2026.

Claude Agent SDK 0.2.175

The Claude Agent SDK has been updated to version 0.2.175, which includes an updated bundled Claude CLI and an increased PyPI project size limit.

Claude Code 2.1.314

Claude Code 2.1.314 adds write permissions for working directories, group-based upstream routing, and idle conversation compaction for VS Code and Claude Desktop.

Anthropic raises Messages and Token Counting API request limits to 128 MB

Anthropic increased the maximum request payload size for the Messages API and Token Counting API from 32 MB to 128 MB.

Claude Code 2.1.312

Claude Code 2.1.312 adds OIDC user ID claim support for the gateway and improves terminal interaction by allowing users to send queued messages via click. It also includes several bug fixes for session management, file reading, and command execution.

Claude Code 2.1.311

Claude Code 2.1.311 includes fixes for session freezes, MCP tool integration, and improved context management for long conversations.

Claude Agent SDK 0.2.174

Claude Agent SDK 0.2.174 includes an update to the bundled Claude CLI version 2.1.310.

Claude Code 2.1.310

Claude Code 2.1.310 adds a monitor tool, improves error handling for gateway requests, and fixes various file management and permission issues.

Claude Agent SDK

Claude Agent SDK 0.2.173 is available, featuring an updated bundled Claude CLI version 2.1.309.

• Claude Agent SDK 0.2.173
• Claude Agent SDK 0.2.172

Claude Code

Claude Code 2.1.309 includes multiple bug fixes for sandboxed Bash commands, improved permission checks, and better handling of worktree-isolated sessions.

• Claude Code 2.1.309
• Claude Code 2.1.308

Claude Code 2.1.305

- Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its reset Fixed...

Claude Agent SDK 0.2.169

Documentation Clarified that include_hook_events does not suppress SessionStart and Setup hook events, which the CLI emits regardless of the setting Internal/Other Changes Updated bundled Claude CLI to version 2.1.305 CI: hash-pinned the release build tools (build, twine, wheel, hatchling) so a tampered or unexpected download stops the job PyPI...

Claude Code 2.1.304

- Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked Added e.isReadOnly to a mod's tool.check event, set...

Claude Code 2.1.303

- Bug fixes and reliability improvements

Claude Code 2.1.302

- Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode Added an Idle compaction row to /config for turning idle compaction off or back on; the notices shown after an idle compaction now say how to turn it off Added a notice to /design-sync and /design-login...

Claude Agent SDK 0.2.168

Internal/Other Changes Updated bundled Claude CLI to version 2.1.301 PyPI: https://pypi.org/project/claude-agent-sdk/0.2.168/ bash pip install claude-agent-sdk==0.2.168

Claude Code 2.1.301

- Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI Added the % motion to vim mode: jump to the...

Claude Code

- Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime Added $.ui.view({ agentId }) for mods: shows an agent's transcript in the main view when you...

• Claude Code 2.1.300
• Claude Code 2.1.299

Claude Agent SDK

Internal/Other Changes Updated bundled Claude CLI to version 2.1.300 PyPI: https://pypi.org/project/claude-agent-sdk/0.2.167/ bash pip install claude-agent-sdk==0.2.167

• Claude Agent SDK 0.2.167
• Claude Agent SDK 0.2.166

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...

Claude Agent SDK 0.2.165

Internal/Other Changes Updated bundled Claude CLI to version 2.1.294 CI: alert Slack when a release is blocked or fails PyPI: https://pypi.org/project/claude-agent-sdk/0.2.165/ bash pip install claude-agent-sdk==0.2.165

Claude Code

- 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...

• Claude Code 2.1.295
• Claude Code 2.1.294

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...

We've added capabilities.server_tools to the Models API

We've added capabilities.server_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts the web search and code execution tools. To check whether a model accepts the code execution tool, read capabilities.server_tools.code_execution.

Claude Code

- 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...

• Claude Code 2.1.292
• Claude Code 2.1.291

Claude Agent SDK 0.2.164

Internal/Other Changes Updated bundled Claude CLI to version 2.1.292 CI: security hardening for GitHub Actions workflows that call Claude , egress-firewall runner, network allow list, auto permission mode, and a check workflow to enforce them CI: raised PyPI per-file limit guard to 250 MiB to match the updated project limit Tests: fixed thinking-deltas e2e...

We've added capabilities.thinking.types.disabled to the Models API

We've added capabilities.thinking.types.disabled to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "disabled"}, which turns thinking off. See Using the Models API.

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...

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...

Claude Code 2.1.288

- Added $.ui.selection() for mods: returns the text you last selected in fullscreen mode and, when the selection lies within one transcript row, that row Added a built-in gh api to cloud sessions whose image has no GitHub CLI, and fixed the built-in sending control characters from file names, jq filters or GitHub errors to the terminal Added recovery for a...

Claude Code 2.1.287

- Added Claude Mods: plugins may now modify deeper behavior Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss.

Claude Agent SDK 0.2.163

Internal/Other Changes Updated bundled Claude CLI to version 2.1.286 CI: pinned the model for issue triage to fix failures caused by the CLI's new default model PyPI: https://pypi.org/project/claude-agent-sdk/0.2.163/ bash pip install claude-agent-sdk==0.2.163

Claude Code 2.1.286

- Added a count such as "2 of 5" to the permission prompt when several permission requests stack up Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or...

Claude Agent SDK 0.2.162

Internal/Other Changes Updated bundled Claude CLI to version 2.1.285 PyPI: https://pypi.org/project/claude-agent-sdk/0.2.162/ bash pip install claude-agent-sdk==0.2.162

Claude Code 2.1.285

- Added CLAUDE_CODE_DISABLE_WEB_FETCH environment variable to turn off the WebFetch tool Added claude --desktop to open the Claude desktop app on the current directory, or on a session with --continue / --resume Added claude plugin configure to show a plugin's options and which are unset, or save new values read from stdin with --values-stdin Added .

Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways

Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways. To turn off up-front thinking, send thinking: {"type": "between_tools"} instead of "disabled", at high effort or below. Forced tool use (tool_choice types any and tool) returns a 400 error. Thinking blocks are tied to the model and the conversation.

• Code written for Claude Sonnet 5 can break on Claude Sonnet 5.5 in five ways
• Thinking blocks that Claude Sonnet 5.5 produces work only in the account that produced them, or in an account
• We've launched Claude Sonnet 5.5 (claude-sonnet-5-5)

Claude Agent SDK 0.2.161

Internal/Other Changes Updated bundled Claude CLI to version 2.1.284 PyPI: https://pypi.org/project/claude-agent-sdk/0.2.161/ bash pip install claude-agent-sdk==0.2.161