SDK for building AI agents with Claude Code's capabilities. Programmatically interact with Claude to build autonomous agents that can understand codebases, edit files, and execute workflows.
Last release today
26 Aug 2026
Ships on a steady schedule
a new release about every 8 days
Nearly every release is documented
notes for 262 of 279 stable releases
Nothing withdrawn
no release was ever pulled
11 months old
279 releases · first in 2025
Release timeline
279 releases since 20252026
Releases
- 0.2.10915 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.109
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.10814 Apr 2026
Release notes
Open source →What's changed
SDKStatusnow includes'requesting'; whenincludePartialMessagesis enabled, a{type:'system', subtype:'status', status:'requesting'}message is emitted before each API request in the stream
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →SDKStatusnow includes'requesting'; whenincludePartialMessagesis enabled, a{type:'system', subtype:'status', status:'requesting'}message is emitted before each API request in the stream
- 0.2.10714 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.107
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.10513 Apr 2026
Release notes
Open source →What's changed
- Added
system/memory_recallevent andmemory_pathsonsystem/initfor SDK renderers to surface memory operations - Fixed
error_max_structured_output_retriesbeing emitted when the final retry attempt succeeded, discarding valid structured output
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
system/memory_recallevent andmemory_pathsonsystem/initfor SDK renderers to surface memory operations - Fixed
error_max_structured_output_retriesbeing emitted when the final retry attempt succeeded, discarding valid structured output
- Added
- 0.2.10412 Apr 2026
Nothing published for this version
- 0.2.10110 Apr 2026
Release notes
Open source →What's changed
- Security: bumped
@anthropic-ai/sdkto^0.81.0and@modelcontextprotocol/sdkto^1.29.0to resolve GHSA-5474-4w2j-mq4c and transitive hono advisories - Fixed resume-session temp directory leaking on Windows when subprocess file handles weren't released before cleanup, and on macOS/APFS when
await usingdisposal raced its own cleanup callback - Fixed
MaxListenersExceededWarningwhen running 11+ concurrentquery()calls
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Security: bumped
@anthropic-ai/sdkto^0.81.0and@modelcontextprotocol/sdkto^1.29.0to resolve GHSA-5474-4w2j-mq4c and transitive hono advisories - Fixed resume-session temp directory leaking on Windows when subprocess file handles weren't released before cleanup, and on macOS/APFS when
await usingdisposal raced its own cleanup callback - Fixed
MaxListenersExceededWarningwhen running 11+ concurrentquery()calls
- Security: bumped
- 0.2.10010 Apr 2026
- 0.2.989 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.98
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.978 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.97
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.968 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.96
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.947 Apr 2026
Release notes
Open source →What's changed
- Fixed
getContextUsage()to include agents passed viaoptions.agentsin theagentsbreakdown - Fixed CJK and other multibyte text being corrupted with U+FFFD in stream-json input/output when chunk boundaries split a UTF-8 sequence
- Fixed MCP server child processes not being cleaned up when an SDK
query()session ends - Fixed a failed error-report write crashing the SDK process with
unhandledRejection - Updated to parity with Claude Code v2.1.94
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Fixed
getContextUsage()to include agents passed viaoptions.agentsin theagentsbreakdown - Fixed CJK and other multibyte text being corrupted with U+FFFD in stream-json input/output when chunk boundaries split a UTF-8 sequence
- Fixed MCP server child processes not being cleaned up when an SDK
query()session ends - Fixed a failed error-report write crashing the SDK process with
unhandledRejection - Updated to parity with Claude Code v2.1.94
- Fixed
- 0.2.924 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.92
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.912 Apr 2026
Release notes
Open source →What's changed
- Added optional
terminal_reasonfield to result messages, exposing why the query loop terminated (completed,aborted_tools,max_turns,blocking_limit, etc.) - Added
'auto'to the publicPermissionModetype - Changed
sandboxoption to defaultfailIfUnavailabletotruewhenenabled: trueis passed —query()will emit an error result and exit if sandbox dependencies are missing, instead of silently running unsandboxed. SetfailIfUnavailable: falseto allow graceful degradation. - Updated to parity with Claude Code v2.1.91
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added optional
terminal_reasonfield to result messages, exposing why the query loop terminated (completed,aborted_tools,max_turns,blocking_limit, etc.) - Added
'auto'to the publicPermissionModetype - Changed
sandboxoption to defaultfailIfUnavailabletotruewhenenabled: trueis passed —query()will emit an error result and exit if sandbox dependencies are missing, instead of silently running unsandboxed. SetfailIfUnavailable: falseto allow graceful degradation. - Updated to parity with Claude Code v2.1.91
- Added optional
- 0.2.901 Apr 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.90
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.8931 Mar 2026
Release notes
Open source →What's changed
- Added
startup()to pre-warm the CLI subprocess beforequery(), making the first query ~20x faster when startup cost can be paid upfront - Added
includeSystemMessagesoption togetSessionMessages()to optionally include system messages in session history - Added
listSubagents()andgetSubagentMessages()functions to retrieve subagent conversation history from sessions - Added
includeHookEventsoption to enable hook lifecycle messages (hook_started,hook_progress,hook_response) for all hook event types - Fixed
ERR_STREAM_WRITE_AFTER_ENDerrors when single-turn queries with SDK MCP servers or hooks have control responses arriving after the result message - Fixed Zod v4 field
.describe()metadata being dropped fromcreateSdkMcpServertool schemas - Fixed
side_questionreturning null on resume before the first turn completes - Fixed
settingSourcesempty array causing--setting-sources ""to consume the next CLI flag - Fixed error result messages (
error_during_execution,error_max_turns,error_max_budget_usd) to correctly setis_error: truewith descriptive messages - Fixed MCP servers getting permanently stuck in a failed state after a connection race — they now retry on the next message
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
startup()to pre-warm the CLI subprocess beforequery(), making the first query ~20x faster when startup cost can be paid upfront - Added
includeSystemMessagesoption togetSessionMessages()to optionally include system messages in session history - Added
listSubagents()andgetSubagentMessages()functions to retrieve subagent conversation history from sessions - Added
includeHookEventsoption to enable hook lifecycle messages (hook_started,hook_progress,hook_response) for all hook event types - Fixed
ERR_STREAM_WRITE_AFTER_ENDerrors when single-turn queries with SDK MCP servers or hooks have control responses arriving after the result message - Fixed Zod v4 field
.describe()metadata being dropped fromcreateSdkMcpServertool schemas - Fixed
side_questionreturning null on resume before the first turn completes - Fixed
settingSourcesempty array causing--setting-sources ""to consume the next CLI flag - Fixed error result messages (
error_during_execution,error_max_turns,error_max_budget_usd) to correctly setis_error: truewith descriptive messages - Fixed MCP servers getting permanently stuck in a failed state after a connection race — they now retry on the next message
- Added
- 0.2.8729 Mar 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.87
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.8627 Mar 2026
Release notes
Open source →What's changed
- Added
getContextUsage()control method to retrieve a breakdown of context window usage by category - Made
session_idoptional inSDKUserMessagetype — callers no longer need to provide a session ID when sending user messages, as the SDK assigns one automatically - Fixed TypeScript types resolving to
anyby adding@anthropic-ai/sdkand@modelcontextprotocol/sdkas dependencies - Updated to parity with Claude Code v2.1.86
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
getContextUsage()control method to retrieve a breakdown of context window usage by category - Made
session_idoptional inSDKUserMessagetype — callers no longer need to provide a session ID when sending user messages, as the SDK assigns one automatically - Fixed TypeScript types resolving to
anyby adding@anthropic-ai/sdkand@modelcontextprotocol/sdkas dependencies - Updated to parity with Claude Code v2.1.86
- Added
- 0.2.8526 Mar 2026
Release notes
Open source →What's changed
- Added
reloadPlugins()SDK method to reload plugins and receive refreshed commands, agents, and MCP server status - Fixed PreToolUse hooks with
permissionDecision: "ask"being ignored in SDK mode - Updated to parity with Claude Code v2.1.85
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
reloadPlugins()SDK method to reload plugins and receive refreshed commands, agents, and MCP server status - Fixed PreToolUse hooks with
permissionDecision: "ask"being ignored in SDK mode - Updated to parity with Claude Code v2.1.85
- Added
- 0.2.8426 Mar 2026
Release notes
Open source →What's changed
- Added
taskBudgetoption for API-side token budget awareness, allowing the model to pace tool use within a token limit - Added
enableChannel()method andcapabilitiesfield onMcpServerStatusfor SDK-driven MCP channel activation - Exported
EffortLeveltype ('low' | 'medium' | 'high' | 'max') for consumers to reference effort values directly - Fixed showing "[Request interrupted by user]" for errors that were not caused by user interruption
- Updated to parity with Claude Code v2.1.84
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
taskBudgetoption for API-side token budget awareness, allowing the model to pace tool use within a token limit - Added
enableChannel()method andcapabilitiesfield onMcpServerStatusfor SDK-driven MCP channel activation - Exported
EffortLeveltype ('low' | 'medium' | 'high' | 'max') for consumers to reference effort values directly - Fixed showing "[Request interrupted by user]" for errors that were not caused by user interruption
- Updated to parity with Claude Code v2.1.84
- Added
- 0.2.8325 Mar 2026
Release notes
Open source →What's changed
- Added
seed_read_statecontrol subtype to seedreadFileStatewith{path, mtime}soEditworks after the originatingReadwas removed from context - Changed
session_state_changedevents to opt-in: setCLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1to receive them - Updated to parity with Claude Code v2.1.83
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
seed_read_statecontrol subtype to seedreadFileStatewith{path, mtime}soEditworks after the originatingReadwas removed from context - Changed
session_state_changedevents to opt-in: setCLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1to receive them - Updated to parity with Claude Code v2.1.83
- Added
- 0.2.8120 Mar 2026
Release notes
Open source →What's changed
- Fixed
canUseToolnot providing a workingaddRulessuggestion when a write under.claude/skills/{name}/hits the bypass-immune safety check - Updated to parity with Claude Code v2.1.81
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Fixed
canUseToolnot providing a workingaddRulessuggestion when a write under.claude/skills/{name}/hits the bypass-immune safety check - Updated to parity with Claude Code v2.1.81
- Fixed
- 0.2.8019 Mar 2026
Release notes
Open source →What's changed
- Fixed
getSessionMessages()dropping parallel tool results — sessions with parallel tool calls now return all tool_use/tool_result pairs - Updated to parity with Claude Code v2.1.80
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Fixed
getSessionMessages()dropping parallel tool results — sessions with parallel tool calls now return all tool_use/tool_result pairs - Updated to parity with Claude Code v2.1.80
- Fixed
- 0.2.7918 Mar 2026
Release notes
Open source →What's changed
- Added
'resume'to theExitReasontype for distinguishing resume-triggered session ends in hooks - Updated to parity with Claude Code v2.1.79
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
'resume'to theExitReasontype for distinguishing resume-triggered session ends in hooks - Updated to parity with Claude Code v2.1.79
- Added
- 0.2.7817 Mar 2026
- 0.2.7716 Mar 2026
Release notes
Open source →What's changed
- Added
api_retrysystem messages when retrying transient API errors, exposing attempt count, max retries, delay, and error status - Updated to parity with Claude Code v2.1.77
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
api_retrysystem messages when retrying transient API errors, exposing attempt count, max retries, delay, and error status - Updated to parity with Claude Code v2.1.77
- Added
- 0.2.7614 Mar 2026
Release notes
Open source →What's changed
- Added
forkSession(sessionId, opts?)for branching conversations from a point - Added
cancel_async_messagecontrol subtype to drop a queued user message by UUID before execution - Added
planFilePathfield toExitPlanModetool input for hooks and SDK consumers - Added MCP elicitation hook types and
SDKElicitationCompleteMessagesystem message for handling MCP server input requests programmatically - Updated to parity with Claude Code v2.1.76
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
forkSession(sessionId, opts?)for branching conversations from a point - Added
cancel_async_messagecontrol subtype to drop a queued user message by UUID before execution - Added
planFilePathfield toExitPlanModetool input for hooks and SDK consumers - Added MCP elicitation hook types and
SDKElicitationCompleteMessagesystem message for handling MCP server input requests programmatically - Updated to parity with Claude Code v2.1.76
- Added
- 0.2.7513 Mar 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.75
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
tagandcreatedAtfields toSDKSessionInfo - Added
getSessionInfo(sessionId, opts?)for single-session metadata lookup - Added
offsetoption tolistSessionsfor pagination - Added
tagSession(sessionId, tag, opts?)for tagging session files - Added
queued_to_runningstatus toAgentToolOutput— returned whenAgent({resume})targets a still-running agent - Improved error messages when the Claude Code subprocess returns an error result — the SDK now surfaces the actual error text instead of a generic "process exited with code 1"
- Updated to parity with Claude Code v2.1.75
- 0.2.7412 Mar 2026
Release notes
Open source →What's changed
- Added
renameSession(sessionId, title, opts?)for renaming session files - Fixed
import typefrom@anthropic-ai/claude-agent-sdk/sdk-toolsfailing under NodeNext/Bundler module resolution (missing exports map entry since v0.2.69) - Fixed skills with
user-invocable: falsebeing included insupportedCommands()and thesystem:initmessage'sslash_commands/skillslists - Updated to parity with Claude Code v2.1.74
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
renameSession(sessionId, title, opts?)for renaming session files - Fixed
import typefrom@anthropic-ai/claude-agent-sdk/sdk-toolsfailing under NodeNext/Bundler module resolution (missing exports map entry since v0.2.69) - Fixed skills with
user-invocable: falsebeing included insupportedCommands()and thesystem:initmessage'sslash_commands/skillslists - Updated to parity with Claude Code v2.1.74
- Added
- 0.2.7311 Mar 2026
Release notes
Open source →What's changed
- Fixed
options.envbeing overridden by the~/.claude/settings.jsonenv block when not usinguseras asettingSourcesoption - Updated to parity with Claude Code v2.1.73
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Fixed
options.envbeing overridden by the~/.claude/settings.jsonenv block when not usinguseras asettingSourcesoption - Updated to parity with Claude Code v2.1.73
- Fixed
- 0.2.7210 Mar 2026
Release notes
Open source →What's changed
- Added
agentProgressSummariesoption to enable periodic AI-generated progress summaries for running subagents (foreground and background), emitted ontask_progressevents via the newsummaryfield - Added
getSettings()appliedsection with runtime-resolvedmodelandeffortvalues - Fixed
toggleMcpServerandreconnectMcpServerfailing with "Server not found" for servers passed viaquery({mcpServers}) - Updated to parity with Claude Code v2.1.72
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
agentProgressSummariesoption to enable periodic AI-generated progress summaries for running subagents (foreground and background), emitted ontask_progressevents via the newsummaryfield - Added
getSettings()appliedsection with runtime-resolvedmodelandeffortvalues - Fixed
toggleMcpServerandreconnectMcpServerfailing with "Server not found" for servers passed viaquery({mcpServers}) - Updated to parity with Claude Code v2.1.72
- Added
- 0.2.716 Mar 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.71
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.706 Mar 2026
Release notes
Open source →What's changed
- Fixed
type: "http"MCP servers failing with HTTP 406 "Not Acceptable" on Streamable HTTP servers that strictly enforce theAccept: application/json, text/event-streamheader - Changed
AgentToolInput.subagent_typeto optional — defaults to thegeneral-purposeagent when omitted - Updated to parity with Claude Code v2.1.70
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Fixed
type: "http"MCP servers failing with HTTP 406 "Not Acceptable" on Streamable HTTP servers that strictly enforce theAccept: application/json, text/event-streamheader - Changed
AgentToolInput.subagent_typeto optional — defaults to thegeneral-purposeagent when omitted - Updated to parity with Claude Code v2.1.70
- Fixed
- 0.2.695 Mar 2026
Release notes
Open source →What's changed
- Added
toolConfig.askUserQuestion.previewFormatoption to configure the content format ('markdown'or'html') for thepreviewfield on AskUserQuestion tool options. Thepreviewfield andannotationsoutput are now exposed in the public SDK types. - Added
supportsFastModefield toModelInfoindicating whether a model supports fast mode - Added
agent_id(for subagents) andagent_type(for subagents and--agent) fields to hook events - Fixed SDK-mode MCP servers (registered via
sdkMcpServersin theinitializecontrol request) getting disconnected when background plugin installation refreshes project MCP config - Fixed breaking change:
system:initandresultevents now emit'Task'as the Agent tool name again (reverted from'Agent', which was an unintentional breaking change in a patch release). The wire name will migrate to'Agent'in the next minor release. - Fixed control responses with malformed
updatedPermissionsfrom SDK hosts blocking tool calls with a ZodError; the invalid field is now stripped and a warning is logged instead. - Improved memory usage of
getSessionMessages()for large sessions with compacted history
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
toolConfig.askUserQuestion.previewFormatoption to configure the content format ('markdown'or'html') for thepreviewfield on AskUserQuestion tool options. Thepreviewfield andannotationsoutput are now exposed in the public SDK types. - Added
supportsFastModefield toModelInfoindicating whether a model supports fast mode - Added
agent_id(for subagents) andagent_type(for subagents and--agent) fields to hook events - Fixed SDK-mode MCP servers (registered via
sdkMcpServersin theinitializecontrol request) getting disconnected when background plugin installation refreshes project MCP config - Fixed breaking change:
system:initandresultevents now emit'Task'as the Agent tool name again (reverted from'Agent', which was an unintentional breaking change in a patch release). The wire name will migrate to'Agent'in the next minor release. - Fixed control responses with malformed
updatedPermissionsfrom SDK hosts blocking tool calls with a ZodError; the invalid field is now stripped and a warning is logged instead. - Improved memory usage of
getSessionMessages()for large sessions with compacted history
- Added
- 0.2.684 Mar 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.68
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.664 Mar 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.66
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.643 Mar 2026
Nothing published for this version
- 0.2.6328 Feb 2026
Release notes
Open source →What's changed
- SDK: Fixed
pathToClaudeCodeExecutablefailing when set to a bare command name (e.g.,"claude") that should resolve via PATH - Added
supportedAgents()method to the Query interface to view available subagents - Fixed MCP replacement tools being incorrectly denied in subagents when using unprefixed MCP tool names
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- SDK: Fixed
pathToClaudeCodeExecutablefailing when set to a bare command name (e.g.,"claude") that should resolve via PATH - Added
supportedAgents()method to the Query interface to view available subagents - Fixed MCP replacement tools being incorrectly denied in subagents when using unprefixed MCP tool names
- SDK: Fixed
- 0.2.6227 Feb 2026
Nothing published for this version
- 0.2.6126 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.61
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.5926 Feb 2026
Release notes
Open source →What's changed
- Added
getSessionMessages()function for reading a session's conversation history from its transcript file, with support for pagination vialimitandoffsetoptions
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
getSessionMessages()function for reading a session's conversation history from its transcript file, with support for pagination vialimitandoffsetoptions
- Added
- 0.2.5825 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.58
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.5625 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.56
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.5525 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.55
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.5425 Feb 2026
- 0.2.5324 Feb 2026
Release notes
Open source →What's changed
- Added
listSessions()for discovering and listing past sessions with light metadata
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added
listSessions()for discovering and listing past sessions with light metadata
- Added
- 0.2.5224 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.52
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.5124 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.51
- Fixed SDK crashing with
ReferenceErrorwhen used inside compiled Bun binaries (bun build --compile) - Fixed unbounded memory growth in long-running SDK sessions caused by message UUID tracking never evicting old entries
- Fixed local slash command output not being returned to SDK clients
- Added
task_progressevents for real-time background agent progress reporting with cumulative usage metrics, tool counts, and duration - Fixed
session.close()in the v2 session API killing the subprocess before it could persist session data, which brokeresumeSession()
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Updated to parity with Claude Code v2.1.51
- Fixed SDK crashing with
ReferenceErrorwhen used inside compiled Bun binaries (bun build --compile) - Fixed unbounded memory growth in long-running SDK sessions caused by message UUID tracking never evicting old entries
- Fixed local slash command output not being returned to SDK clients
- Added
task_progressevents for real-time background agent progress reporting with cumulative usage metrics, tool counts, and duration - Fixed
session.close()in the v2 session API killing the subprocess before it could persist session data, which brokeresumeSession()
- 0.2.5020 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.50
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.4919 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.49
- SDK model info now includes
supportsEffort,supportedEffortLevels, andsupportsAdaptiveThinkingfields so consumers can discover model capabilities. - Permission suggestions are now populated when safety checks trigger an ask response, enabling SDK consumers to display permission options.
- Added
ConfigChangehook event that fires when configuration files change during a session, enabling enterprise security auditing and optional blocking of settings changes.
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Updated to parity with Claude Code v2.1.49
- SDK model info now includes
supportsEffort,supportedEffortLevels, andsupportsAdaptiveThinkingfields so consumers can discover model capabilities. - Permission suggestions are now populated when safety checks trigger an ask response, enabling SDK consumers to display permission options.
- Added
ConfigChangehook event that fires when configuration files change during a session, enabling enterprise security auditing and optional blocking of settings changes.
- 0.2.4819 Feb 2026
Nothing published for this version
- 0.2.4718 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.47
- Added
promptSuggestion()method onQueryto request prompt suggestions based on the current conversation context - Added
tool_use_idfield totask_notificationevents for correlating task completions with originating tool calls
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Updated to parity with Claude Code v2.1.47
- Added
promptSuggestion()method onQueryto request prompt suggestions based on the current conversation context - Added
tool_use_idfield totask_notificationevents for correlating task completions with originating tool calls
- 0.2.4517 Feb 2026
Release notes
Open source →What's changed
- Added support for Claude Sonnet 4.6
- Added
task_startedsystem message to the SDK stream, emitted when subagent tasks are registered - Fixed
Session.stream()returning prematurely when background subagents are still running, by holding back intermediate result messages until all tasks complete - Improved memory usage for shell commands that produce large output — RSS no longer grows unboundedly with command output size
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]Release notes
Open source →- Added support for Claude Sonnet 4.6
- Added
task_startedsystem message to the SDK stream, emitted when subagent tasks are registered - Fixed
Session.stream()returning prematurely when background subagents are still running, by holding back intermediate result messages until all tasks complete - Improved memory usage for shell commands that produce large output — RSS no longer grows unboundedly with command output size
- 0.2.4416 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.44
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.4213 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.42
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.4113 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.41
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.4012 Feb 2026
- 0.2.3910 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.39
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.3810 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.38
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.377 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.37
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected] - 0.2.367 Feb 2026
Release notes
Open source →What's changed
- Updated to parity with Claude Code v2.1.36
Update
npm install @anthropic-ai/[email protected] # or yarn add @anthropic-ai/[email protected] # or pnpm add @anthropic-ai/[email protected] # or bun add @anthropic-ai/[email protected]