Claude Agent SDK 0.2.176
Claude Agent SDK 0.2.176 includes an updated bundled Claude CLI version 2.1.316.
Claude Agent SDK 0.2.176 includes an updated bundled Claude CLI version 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.
Fast mode for Claude Opus 4.8 is deprecated and will be removed on November 30, 2026. Users should migrate to Claude Opus 5.5 to continue using fast mode.
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 adds write permissions for working directories, group-based upstream routing, and idle conversation compaction for VS Code and Claude Desktop.
Anthropic designated the Usage and Cost API and related usage and cost report endpoints in the Claude Enterprise Analytics API as legacy while maintaining support.
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 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 includes fixes for session freezes, MCP tool integration, and improved context management for long conversations.
Claude Agent SDK 0.2.174 includes an update to the bundled Claude CLI version 2.1.310.
The Claude Tag API is now in beta for Claude Enterprise organizations. It allows programmatic management of Claude Tag settings on Slack channels and workspaces using Admin API keys.
Claude Code 2.1.310 adds a monitor tool, improves error handling for gateway requests, and fixes various file management and permission issues.
Anthropic has launched Claude Models on Google Cloud, allowing users to access the Claude API through their Google Cloud project with IAM-based access control and marketplace billing.
Claude Agent SDK 0.2.172 includes an updated bundled Claude CLI version.
Claude Code 2.1.308 includes bug fixes and reliability improvements.
Anthropic opened a research preview of Claude Duet for users on Pro and Max plans. Claude Duet is a new app where Claude operates as a proactive agent.
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...
- 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...
- 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...
- 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...
Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in the Start, Build, and Scale usage tiers.
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
- 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...
We've launched OpenTelemetry export in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability backend. The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP, and Ruby. To get spans from the API, add an OpenTelemetry destination in the Claude Console.
New Features Hook-specific output types: Added typed output classes and missing input fields for hooks, giving hook implementations precise type information instead of untyped dicts SystemInitData TypedDict: The init system message payload is now fully typed via SystemInitData, along with nested types SystemInitMcpServer, SystemInitPlugin...
- 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...
You can now let a Claude Managed Agents agent use dynamic workflows, in beta with the managed-agents-2026-04-01 beta header. For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results.
- 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...
The Compliance API can now download Claude Docs documents as Word files, in beta. See Retrieve files and artifacts.
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
- 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
We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See Prompt caching pricing.
- 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. 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.
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...
- 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
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.
- 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...
- 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...
- 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...
- 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.