NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
npm, #3768 most downloaded on npm
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.
Latest stable
0.3.325
Last release 4 days ago
13 Nov 2026
Ships on a steady schedule
a new release about every 8 days
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
345 releases · first in 2025
Drag across the ruler to compare, or tap a release to open it.
Updated to parity with Claude Code v2.1.116
npm install @anthropic-ai/claude-agent-sdk@0.2.116
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.116
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.116
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.116
Updated to parity with Claude Code v2.1.114
npm install @anthropic-ai/claude-agent-sdk@0.2.114
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.114
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.114
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.114
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Changed the SDK to spawn a native Claude Code binary (via a per-platform optional dependency) instead of bundled JavaScript
sessionStore option (alpha) to query() and session helpers for mirroring session transcripts to external storage, with SessionStore/SessionKey/SessionStoreEntry types, InMemorySessionStore reference implementation, and importSessionToStore() for migrating existing sessionsdeleteSession() for removing a session from disk or a SessionStoreSDKMirrorErrorMessage (subtype: 'mirror_error') to the SDKMessage union — emitted when a sessionStore.append() batch failsoptions.env once again replaces process.env for the CLI subprocess instead of overlaying it. To add or override individual variables, pass env: { ...process.env, MY_VAR: "x" }title option to query() — sets the session title and skips auto-generationnpm install @anthropic-ai/claude-agent-sdk@0.2.113
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.113
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.113
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.113
Updated to parity with Claude Code v2.1.112
npm install @anthropic-ai/claude-agent-sdk@0.2.112
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.112
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.112
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.112
Opus 4.7 is now available! This version of the SDK is required to use it.
mcp_set_servers control request: remote (http/sse) server entries can now carry per-tool permission_policy values, which are applied to the session's allow/deny rulesstartup() and WarmQuery are now part of the public TypeScript APIoptions.env to overlay the inherited process.env instead of replacing itnpm install @anthropic-ai/claude-agent-sdk@0.2.111
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.111
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.111
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.111
Fixed unstable_v2_createSession not respecting cwd, settingSources, and allowDangerouslySkipPermissions options
unstable_v2_createSession not respecting cwd, settingSources, and allowDangerouslySkipPermissions optionsshouldQuery field to SDKUserMessage — set to false to append a user message without triggering an assistant turn; fixed shouldQuery: false messages incorrectly triggering auto-title generation, prompt suggestions, and UserPromptSubmit hooksCLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC and CLAUDE_CODE_DISABLE_TERMINAL_TITLEnpm install @anthropic-ai/claude-agent-sdk@0.2.110
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.110
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.110
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.110
Updated to parity with Claude Code v2.1.109
npm install @anthropic-ai/claude-agent-sdk@0.2.109
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.109
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.109
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.109
SDKStatus now includes 'requesting'; when includePartialMessages is enabled, a {type:'system', subtype:'status', status:'requesting'} message is emitt
SDKStatus now includes 'requesting'; when includePartialMessages is enabled, a {type:'system', subtype:'status', status:'requesting'} message is emitted before each API request in the streamnpm install @anthropic-ai/claude-agent-sdk@0.2.108
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.108
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.108
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.108
Updated to parity with Claude Code v2.1.107
npm install @anthropic-ai/claude-agent-sdk@0.2.107
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.107
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.107
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.107
Added system/memory_recall event and memory_paths on system/init for SDK renderers to surface memory operations
system/memory_recall event and memory_paths on system/init for SDK renderers to surface memory operationserror_max_structured_output_retries being emitted when the final retry attempt succeeded, discarding valid structured outputnpm install @anthropic-ai/claude-agent-sdk@0.2.105
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.105
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.105
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.105
Nothing published for this version
Security: bumped @anthropic-ai/sdk to ^0.81.0 and @modelcontextprotocol/sdk to ^1.29.0 to resolve GHSA-5474-4w2j-mq4c and transitive hono advisories
@anthropic-ai/sdk to ^0.81.0 and @modelcontextprotocol/sdk to ^1.29.0 to resolve GHSA-5474-4w2j-mq4c and transitive hono advisoriesawait using disposal raced its own cleanup callbackMaxListenersExceededWarning when running 11+ concurrent query() callsnpm install @anthropic-ai/claude-agent-sdk@0.2.101
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.101
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.101
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.101
Updated to parity with Claude Code v2.1.100
Updated to parity with Claude Code v2.1.98
npm install @anthropic-ai/claude-agent-sdk@0.2.98
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.98
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.98
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.98
Updated to parity with Claude Code v2.1.97
npm install @anthropic-ai/claude-agent-sdk@0.2.97
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.97
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.97
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.97
Updated to parity with Claude Code v2.1.96
npm install @anthropic-ai/claude-agent-sdk@0.2.96
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.96
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.96
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.96
Fixed getContextUsage() to include agents passed via options.agents in the agents breakdown
getContextUsage() to include agents passed via options.agents in the agents breakdownquery() session endsunhandledRejectionnpm install @anthropic-ai/claude-agent-sdk@0.2.94
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.94
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.94
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.94
Updated to parity with Claude Code v2.1.92
npm install @anthropic-ai/claude-agent-sdk@0.2.92
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.92
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.92
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.92
Added optional terminal_reason field to result messages, exposing why the query loop terminated (completed, aborted_tools, max_turns, blocking_limit,
terminal_reason field to result messages, exposing why the query loop terminated (completed, aborted_tools, max_turns, blocking_limit, etc.)'auto' to the public PermissionMode typesandbox option to default failIfUnavailable to true when enabled: true is passed — query() will emit an error result and exit if sandbox dependencies are missing, instead of silently running unsandboxed. Set failIfUnavailable: false to allow graceful degradation.npm install @anthropic-ai/claude-agent-sdk@0.2.91
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.91
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.91
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.91
Updated to parity with Claude Code v2.1.90
npm install @anthropic-ai/claude-agent-sdk@0.2.90
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.90
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.90
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.90
Added startup() to pre-warm the CLI subprocess before query(), making the first query ~20x faster when startup cost can be paid upfront
startup() to pre-warm the CLI subprocess before query(), making the first query ~20x faster when startup cost can be paid upfrontincludeSystemMessages option to getSessionMessages() to optionally include system messages in session historylistSubagents() and getSubagentMessages() functions to retrieve subagent conversation history from sessionsincludeHookEvents option to enable hook lifecycle messages (hook_started, hook_progress, hook_response) for all hook event typesERR_STREAM_WRITE_AFTER_END errors when single-turn queries with SDK MCP servers or hooks have control responses arriving after the result message.describe() metadata being dropped from createSdkMcpServer tool schemasside_question returning null on resume before the first turn completessettingSources empty array causing --setting-sources "" to consume the next CLI flagerror_during_execution, error_max_turns, error_max_budget_usd) to correctly set is_error: true with descriptive messagesnpm install @anthropic-ai/claude-agent-sdk@0.2.89
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.89
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.89
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.89
Updated to parity with Claude Code v2.1.87
npm install @anthropic-ai/claude-agent-sdk@0.2.87
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.87
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.87
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.87
Added getContextUsage() control method to retrieve a breakdown of context window usage by category
getContextUsage() control method to retrieve a breakdown of context window usage by categorysession_id optional in SDKUserMessage type — callers no longer need to provide a session ID when sending user messages, as the SDK assigns one automaticallyany by adding @anthropic-ai/sdk and @modelcontextprotocol/sdk as dependenciesnpm install @anthropic-ai/claude-agent-sdk@0.2.86
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.86
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.86
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.86
Added reloadPlugins() SDK method to reload plugins and receive refreshed commands, agents, and MCP server status
reloadPlugins() SDK method to reload plugins and receive refreshed commands, agents, and MCP server statuspermissionDecision: "ask" being ignored in SDK modenpm install @anthropic-ai/claude-agent-sdk@0.2.85
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.85
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.85
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.85
Added taskBudget option for API-side token budget awareness, allowing the model to pace tool use within a token limit
taskBudget option for API-side token budget awareness, allowing the model to pace tool use within a token limitenableChannel() method and capabilities field on McpServerStatus for SDK-driven MCP channel activationEffortLevel type ('low' | 'medium' | 'high' | 'max') for consumers to reference effort values directlynpm install @anthropic-ai/claude-agent-sdk@0.2.84
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.84
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.84
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.84
Added seed_read_state control subtype to seed readFileState with {path, mtime} so Edit works after the originating Read was removed from context
seed_read_state control subtype to seed readFileState with {path, mtime} so Edit works after the originating Read was removed from contextsession_state_changed events to opt-in: set CLAUDE_CODE_EMIT_SESSION_STATE_EVENTS=1 to receive themnpm install @anthropic-ai/claude-agent-sdk@0.2.83
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.83
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.83
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.83
Fixed canUseTool not providing a working addRules suggestion when a write under .claude/skills/{name}/ hits the bypass-immune safety check
canUseTool not providing a working addRules suggestion when a write under .claude/skills/{name}/ hits the bypass-immune safety checknpm install @anthropic-ai/claude-agent-sdk@0.2.81
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.81
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.81
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.81
Fixed getSessionMessages() dropping parallel tool results — sessions with parallel tool calls now return all tool_use/tool_result pairs
getSessionMessages() dropping parallel tool results — sessions with parallel tool calls now return all tool_use/tool_result pairsnpm install @anthropic-ai/claude-agent-sdk@0.2.80
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.80
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.80
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.80
Added 'resume' to the ExitReason type for distinguishing resume-triggered session ends in hooks
'resume' to the ExitReason type for distinguishing resume-triggered session ends in hooksnpm install @anthropic-ai/claude-agent-sdk@0.2.79
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.79
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.79
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.79
Updated to parity with Claude Code v2.1.78
Added api_retry system messages when retrying transient API errors, exposing attempt count, max retries, delay, and error status
api_retry system messages when retrying transient API errors, exposing attempt count, max retries, delay, and error statusnpm install @anthropic-ai/claude-agent-sdk@0.2.77
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.77
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.77
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.77
Added forkSession(sessionId, opts?) for branching conversations from a point
forkSession(sessionId, opts?) for branching conversations from a pointcancel_async_message control subtype to drop a queued user message by UUID before executionplanFilePath field to ExitPlanMode tool input for hooks and SDK consumersSDKElicitationCompleteMessage system message for handling MCP server input requests programmaticallynpm install @anthropic-ai/claude-agent-sdk@0.2.76
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.76
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.76
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.76
Updated to parity with Claude Code v2.1.75
npm install @anthropic-ai/claude-agent-sdk@0.2.75
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.75
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.75
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.75
tag and createdAt fields to SDKSessionInfogetSessionInfo(sessionId, opts?) for single-session metadata lookupoffset option to listSessions for paginationtagSession(sessionId, tag, opts?) for tagging session filesqueued_to_running status to AgentToolOutput — returned when Agent({resume}) targets a still-running agentAdded renameSession(sessionId, title, opts?) for renaming session files
renameSession(sessionId, title, opts?) for renaming session filesimport type from @anthropic-ai/claude-agent-sdk/sdk-tools failing under NodeNext/Bundler module resolution (missing exports map entry since v0.2.69)user-invocable: false being included in supportedCommands() and the system:init message's slash_commands / skills listsnpm install @anthropic-ai/claude-agent-sdk@0.2.74
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.74
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.74
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.74
Fixed options.env being overridden by the ~/.claude/settings.json env block when not using user as a settingSources option
options.env being overridden by the ~/.claude/settings.json env block when not using user as a settingSources optionnpm install @anthropic-ai/claude-agent-sdk@0.2.73
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.73
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.73
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.73
Added agentProgressSummaries option to enable periodic AI-generated progress summaries for running subagents (foreground and background), emitted on t
agentProgressSummaries option to enable periodic AI-generated progress summaries for running subagents (foreground and background), emitted on task_progress events via the new summary fieldgetSettings() applied section with runtime-resolved model and effort valuestoggleMcpServer and reconnectMcpServer failing with "Server not found" for servers passed via query({mcpServers})npm install @anthropic-ai/claude-agent-sdk@0.2.72
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.72
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.72
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.72
Updated to parity with Claude Code v2.1.71
npm install @anthropic-ai/claude-agent-sdk@0.2.71
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.71
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.71
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.71
Fixed type: "http" MCP servers failing with HTTP 406 "Not Acceptable" on Streamable HTTP servers that strictly enforce the Accept: application/json, t
type: "http" MCP servers failing with HTTP 406 "Not Acceptable" on Streamable HTTP servers that strictly enforce the Accept: application/json, text/event-stream headerAgentToolInput.subagent_type to optional — defaults to the general-purpose agent when omittednpm install @anthropic-ai/claude-agent-sdk@0.2.70
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.70
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.70
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.70
Fixed breaking change: system:init and result events now emit 'Task' as the Agent tool name again (reverted from 'Agent', which was an unintentional b…
toolConfig.askUserQuestion.previewFormat option to configure the content format ('markdown' or 'html') for the preview field on AskUserQuestion tool options. The preview field and annotations output are now exposed in the public SDK types.supportsFastMode field to ModelInfo indicating whether a model supports fast modeagent_id (for subagents) and agent_type (for subagents and --agent) fields to hook eventssdkMcpServers in the initialize control request) getting disconnected when background plugin installation refreshes project MCP configsystem:init and result events 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.updatedPermissions from SDK hosts blocking tool calls with a ZodError; the invalid field is now stripped and a warning is logged instead.getSessionMessages() for large sessions with compacted historynpm install @anthropic-ai/claude-agent-sdk@0.2.69
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.69
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.69
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.69
Updated to parity with Claude Code v2.1.68
npm install @anthropic-ai/claude-agent-sdk@0.2.68
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.68
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.68
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.68
Updated to parity with Claude Code v2.1.66
npm install @anthropic-ai/claude-agent-sdk@0.2.66
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.66
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.66
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.66
Nothing published for this version
SDK: Fixed pathToClaudeCodeExecutable failing when set to a bare command name (e.g., "claude") that should resolve via PATH
pathToClaudeCodeExecutable failing when set to a bare command name (e.g., "claude") that should resolve via PATHsupportedAgents() method to the Query interface to view available subagentsnpm install @anthropic-ai/claude-agent-sdk@0.2.63
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.63
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.63
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.63
Nothing published for this version
Updated to parity with Claude Code v2.1.61
npm install @anthropic-ai/claude-agent-sdk@0.2.61
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.61
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.61
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.61
Added getSessionMessages() function for reading a session's conversation history from its transcript file, with support for pagination via limit and o
getSessionMessages() function for reading a session's conversation history from its transcript file, with support for pagination via limit and offset optionsnpm install @anthropic-ai/claude-agent-sdk@0.2.59
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.59
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.59
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.59
Updated to parity with Claude Code v2.1.58
npm install @anthropic-ai/claude-agent-sdk@0.2.58
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.58
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.58
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.58
Updated to parity with Claude Code v2.1.56
npm install @anthropic-ai/claude-agent-sdk@0.2.56
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.56
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.56
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.56
Updated to parity with Claude Code v2.1.55
npm install @anthropic-ai/claude-agent-sdk@0.2.55
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.55
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.55
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.55
Updated to parity with Claude Code v2.1.54
Added listSessions() for discovering and listing past sessions with light metadata
listSessions() for discovering and listing past sessions with light metadatanpm install @anthropic-ai/claude-agent-sdk@0.2.53
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.53
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.53
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.53
Updated to parity with Claude Code v2.1.52
npm install @anthropic-ai/claude-agent-sdk@0.2.52
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.52
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.52
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.52
Updated to parity with Claude Code v2.1.51
ReferenceError when used inside compiled Bun binaries (bun build --compile)task_progress events for real-time background agent progress reporting with cumulative usage metrics, tool counts, and durationsession.close() in the v2 session API killing the subprocess before it could persist session data, which broke resumeSession()npm install @anthropic-ai/claude-agent-sdk@0.2.51
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.51
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.51
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.51
Updated to parity with Claude Code v2.1.50
npm install @anthropic-ai/claude-agent-sdk@0.2.50
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.50
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.50
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.50
Updated to parity with Claude Code v2.1.49
supportsEffort, supportedEffortLevels, and supportsAdaptiveThinking fields so consumers can discover model capabilities.ConfigChange hook event that fires when configuration files change during a session, enabling enterprise security auditing and optional blocking of settings changes.npm install @anthropic-ai/claude-agent-sdk@0.2.49
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.49
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.49
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.49
Nothing published for this version
Updated to parity with Claude Code v2.1.47
promptSuggestion() method on Query to request prompt suggestions based on the current conversation contexttool_use_id field to task_notification events for correlating task completions with originating tool callsnpm install @anthropic-ai/claude-agent-sdk@0.2.47
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.47
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.47
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.47
Added support for Claude Sonnet 4.6
task_started system message to the SDK stream, emitted when subagent tasks are registeredSession.stream() returning prematurely when background subagents are still running, by holding back intermediate result messages until all tasks completenpm install @anthropic-ai/claude-agent-sdk@0.2.45
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.45
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.45
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.45
Updated to parity with Claude Code v2.1.44
npm install @anthropic-ai/claude-agent-sdk@0.2.44
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.44
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.44
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.44
Updated to parity with Claude Code v2.1.42
npm install @anthropic-ai/claude-agent-sdk@0.2.42
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.42
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.42
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.42
One column per month.