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Nothing withdrawn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.
Added sandbox.credentials to SDK settings types for configuring credential file and environment variable denial in sandboxed commands
sandbox.credentials to SDK settings types for configuring credential file and environment variable denial in sandboxed commandsnpm install @anthropic-ai/claude-agent-sdk@0.3.187
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.187
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.187
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.187
Added agent_id field to can_use_tool control requests — background agents now forward permission prompts to canUseTool instead of auto-denying, and st
agent_id field to can_use_tool control requests — background agents now forward permission prompts to canUseTool instead of auto-denying, and stdin stays open while background tasks are runningReadMcpResourceDirTool tool type to SDK schemas — MCP resource directory listing is now a dedicated tool instead of a fallback inside ReadMcpResourceToolrewind_conversation control request for rewinding a conversation to a previous point with durable resume anchor supportnpm install @anthropic-ai/claude-agent-sdk@0.3.186
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.186
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.186
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.186
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Updated to parity with Claude Code v2.1.185
npm install @anthropic-ai/claude-agent-sdk@0.3.185
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.185
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.185
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.185
Updated to parity with Claude Code v2.1.183
npm install @anthropic-ai/claude-agent-sdk@0.3.183
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.183
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.183
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.183
Updated to parity with Claude Code v2.1.182
Added errorCode, canUserPurchaseCredits, and hasChargeableSavedPaymentMethod fields to SDKRateLimitInfo for detecting credits-required rate limits
errorCode, canUserPurchaseCredits, and hasChargeableSavedPaymentMethod fields to SDKRateLimitInfo for detecting credits-required rate limitstool_use_meta.icon_url to assistant messages, populated from MCP server directory metadatafile_attachments from inbound user messagesnpm install @anthropic-ai/claude-agent-sdk@0.3.181
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.181
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.181
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.181
Added optional tool_use_meta sidecar to assistant messages with display-friendly names for tool calls, so SDK consumers can render human-readable labe
tool_use_meta sidecar to assistant messages with display-friendly names for tool calls, so SDK consumers can render human-readable labels instead of raw wire names-p mode exiting before a completed background agent's notification was delivered, causing interim text to ship as the final resultnpm install @anthropic-ai/claude-agent-sdk@0.3.179
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.179
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.179
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.179
Spawn failures on an existing native binary now explain the likely libc mismatch (musl binary on a glibc host) and suggest options.pathToClaudeCodeExe
options.pathToClaudeCodeExecutablesafetyCheck, asyncAgent), enabling SDK consumers to programmatically match denial causesUserPromptSubmit hook block feedback not being emitted to the SDK event stream — consumers can now see why a prompt was blocked by a hook instead of a silent hangworker_shutting_down system message on graceful exit so remote clients can show why the session endedmcp__server, mcp__server__*) in disallowedTools being silently ignored — they now correctly remove all tools from the named servernpm install @anthropic-ai/claude-agent-sdk@0.3.178
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.178
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.178
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.178
Updated to parity with Claude Code v2.1.177
npm install @anthropic-ai/claude-agent-sdk@0.3.177
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.177
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.177
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.177
Fixed turn result messages being dropped when multiple turns complete while a background agent or workflow is running
result messages being dropped when multiple turns complete while a background agent or workflow is runningnpm install @anthropic-ai/claude-agent-sdk@0.3.176
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.176
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.176
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.176
Updated to parity with Claude Code v2.1.175
npm install @anthropic-ai/claude-agent-sdk@0.3.175
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.175
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.175
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.175
SDK consumers now receive the system/model_fallback message for all fallback triggers — overloaded, server_error, and last_resort in addition to model
system/model_fallback message for all fallback triggers — overloaded, server_error, and last_resort in addition to model_not_found and permission_denied — and the message's trigger field gained the server_error and last_resort valuesnpm install @anthropic-ai/claude-agent-sdk@0.3.174
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.174
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.174
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.174
Updated to parity with Claude Code v2.1.173
npm install @anthropic-ai/claude-agent-sdk@0.3.173
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.173
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.173
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.173
SDK plugins option now accepts skipMcpDiscovery: true per plugin, so a host that manages a plugin's MCP connections itself can load skills/hooks from
plugins option now accepts skipMcpDiscovery: true per plugin, so a host that manages a plugin's MCP connections itself can load skills/hooks from the plugin path without the engine re-reading its .mcp.json/ add tests) being silently dropped instead of treated as a plain promptnpm install @anthropic-ai/claude-agent-sdk@0.3.172
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.172
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.172
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.172
Added claude-fable-5 model and the fable alias to SDK model types. https://www.anthropic.com/news/claude-fable-5-mythos-5
npm install @anthropic-ai/claude-agent-sdk@0.3.170
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.170
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.170
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.170
Added an experimental usage_EXPERIMENTAL_MAY_CHANGE_DO_NOT_RELY_ON_THIS_API_YET() method on Query returning structured session cost, plan rate-limit,
usage_EXPERIMENTAL_MAY_CHANGE_DO_NOT_RELY_ON_THIS_API_YET() method on Query returning structured session cost, plan rate-limit, and local usage-behaviors datasse option (SSEOptions) to BrowserQueryOptions as an alternative to websocket, for browser SDK consumers who prefer Server-Sent Eventsnpm install @anthropic-ai/claude-agent-sdk@0.3.169
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.169
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.169
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.169
Updated to parity with Claude Code v2.1.168
npm install @anthropic-ai/claude-agent-sdk@0.3.168
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.168
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.168
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.168
Updated to parity with Claude Code v2.1.167
npm install @anthropic-ai/claude-agent-sdk@0.3.167
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.167
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.167
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.167
Fixed MCP resource tools not being injected for servers added at runtime via the mcp_set_servers control request
mcp_set_servers control requestnpm install @anthropic-ai/claude-agent-sdk@0.3.166
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.166
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.166
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.166
Updated to parity with Claude Code v2.1.165
npm install @anthropic-ai/claude-agent-sdk@0.3.165
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.165
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.165
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.165
stop_task control requests now return success when the target task is already gone (not_found or not_running), so SDK clients can reliably prune stale
stop_task control requests now return success when the target task is already gone (not_found or not_running), so SDK clients can reliably prune stale task chipsclaude-in-chrome) via setMcpServers when the CLI was launched without themadditionalContext in hookSpecificOutput, enabling non-error feedback that continues the turnnpm install @anthropic-ai/claude-agent-sdk@0.3.163
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.163
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.163
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.163
Refusal error messages now carry stop_reason: "refusal" and stop_details on the assistant message and in session transcripts, so SDK consumers can det
stop_reason: "refusal" and stop_details on the assistant message and in session transcripts, so SDK consumers can detect refusals without text-matching the error contentfind/grep search in Bash, matching the interactive CLI, instead of always registering the dedicated Grep/Glob tools. To keep the dedicated tools (e.g. to intercept searches via canUseTool or hooks), name them in the tools option or reference them in allowedToolsnpm install @anthropic-ai/claude-agent-sdk@0.3.162
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.162
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.162
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.162
The initialize control request is now idempotent: a second initialize returns the same success payload instead of an Already initialized error. Contro
initialize control request is now idempotent: a second initialize returns the same success payload instead of an Already initialized error. ControlResponse gains an optional pending_permission_requests field, mirroring ControlErrorResponseapplyFlagSettings now live-applies agent changes: switching the active agent (or passing null to reset) takes effect on the next turn in a running sessionnpm install @anthropic-ai/claude-agent-sdk@0.3.161
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.161
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.161
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.161
Fixed SDK hook callbacks swallowing abort signals: aborting during a PostToolUse hook now ends the turn with a final result message instead of hanging
result message instead of hanging the calling processnpm install @anthropic-ai/claude-agent-sdk@0.3.160
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.160
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.160
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.160
Updated to parity with Claude Code v2.1.159
npm install @anthropic-ai/claude-agent-sdk@0.3.159
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.159
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.159
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.159
Updated to parity with Claude Code v2.1.158
npm install @anthropic-ai/claude-agent-sdk@0.3.158
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.158
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.158
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.158
Updated to parity with Claude Code v2.1.157
npm install @anthropic-ai/claude-agent-sdk@0.3.157
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.157
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.157
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.157
Updated to parity with Claude Code v2.1.156
npm install @anthropic-ai/claude-agent-sdk@0.3.156
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.156
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.156
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.156
Fixed stdio MCP servers being incorrectly restarted on every reconcile pass due to config-equality false positives
npm install @anthropic-ai/claude-agent-sdk@0.3.154
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.154
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.154
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.154
Updated to parity with Claude Code v2.1.153
npm install @anthropic-ai/claude-agent-sdk@0.3.153
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.153
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.153
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.153
SessionStart hooks can now return reloadSkills: true to trigger a skill re-scan, and set the session title via hookSpecificOutput.sessionTitle
SessionStart hooks can now return reloadSkills: true to trigger a skill re-scan, and set the session title via hookSpecificOutput.sessionTitleMessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayednpm install @anthropic-ai/claude-agent-sdk@0.3.152
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.152
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.152
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.152
Updated to parity with Claude Code v2.1.150
npm install @anthropic-ai/claude-agent-sdk@0.3.150
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.150
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.150
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.150
api_retry system message now reports error: 'overloaded' for 529 responses, instead of 'rate_limit' (which is now reserved for 429). Consumers that handled 529 via error === 'rate_limit' should also match 'overloaded', or switch to error_status === 529.Fixed options.env dropping CLAUDE_AGENT_SDK_VERSION (used for User-Agent and telemetry) when a custom environment is supplied, and corrected the Optio
options.env dropping CLAUDE_AGENT_SDK_VERSION (used for User-Agent and telemetry) when a custom environment is supplied, and corrected the Options.env docs to state that the value replaces the subprocess environment rather than merging with process.envnpm install @anthropic-ai/claude-agent-sdk@0.3.149
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.149
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.149
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.149
Updated to parity with Claude Code v2.1.148
npm install @anthropic-ai/claude-agent-sdk@0.3.148
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.148
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.148
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.148
Updated to parity with Claude Code v2.1.147
npm install @anthropic-ai/claude-agent-sdk@0.3.147
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.147
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.147
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.147
Updated to parity with Claude Code v2.1.146
npm install @anthropic-ai/claude-agent-sdk@0.3.146
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.146
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.146
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.146
Updated to parity with Claude Code v2.1.145
npm install @anthropic-ai/claude-agent-sdk@0.3.145
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.145
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.145
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.145
Assistant messages and StopFailure hooks now report error: 'model_not_found' when the selected model doesn't exist or isn't available, instead of the
StopFailure hooks now report error: 'model_not_found' when the selected model doesn't exist or isn't available, instead of the generic 'invalid_request'. The api_error_status field on result messages is now documented.@anthropic-ai/claude-agent-sdk/extract export for bun build --compile consumers: import the platform native binary with with { type: 'file' }, call extractFromBunfs(binPath) to copy it out of the compiled executable's virtual filesystem, and pass the result to options.pathToClaudeCodeExecutablenpm install @anthropic-ai/claude-agent-sdk@0.3.144
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.144
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.144
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.144
@anthropic-ai/sdk and @modelcontextprotocol/sdk are now peerDependencies instead of dependencies. Runtime is unaffected (both are bundled); npm/bun/pn
@anthropic-ai/sdk and @modelcontextprotocol/sdk are now peerDependencies instead of dependencies. Runtime is unaffected (both are bundled); npm/bun/pnpm auto-install them. yarn classic users should add them explicitly for full TypeScript type resolutionnpm install @anthropic-ai/claude-agent-sdk@0.3.143
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.143
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.143
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.143
…SDKSession, SDKSessionOptions), deprecated since 0.2.133. Use query() — pass an AsyncIterable for multi-turn, or options.resume to continue a session.
unstable_v2_createSession, unstable_v2_resumeSession, unstable_v2_prompt, SDKSession, SDKSessionOptions), deprecated since 0.2.133. Use query() — pass an AsyncIterable<SDKUserMessage> for multi-turn, or options.resume to continue a session.status: "pending" in init until ready. Set MCP_CONNECTION_NONBLOCKING=0 to restore the old behavior of waiting up to 5s before the first query, or mark a server alwaysLoad: true to require it in turn 1.TaskCreate / TaskUpdate / TaskGet / TaskList) instead of TodoWrite, deprecated since 0.2.136. Tool consumers should accumulate by task ID instead of replacing a snapshot list.request_id, subagent_type, and task_description on SDK message types and task system events--sdk-url sessions now exit non-zero with a stderr diagnostic when the remote transport closes permanently (401/403/404 or WS permanent close), instead of silently exiting 0npm install @anthropic-ai/claude-agent-sdk@0.3.142
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.142
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.142
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.142
TaskCreateInput, TaskCreateOutput, TaskGetInput, TaskGetOutput, TaskUpdateInput, TaskUpdateOutput, TaskListInput, and TaskListOutput types are now exp
TaskCreateInput, TaskCreateOutput, TaskGetInput, TaskGetOutput, TaskUpdateInput, TaskUpdateOutput, TaskListInput, and TaskListOutput types are now exported from @anthropic-ai/claude-agent-sdk/sdk-tools and included in the ToolInputSchemas/ToolOutputSchemas unions@anthropic-ai/sdk dependency to ^0.93.0npm install @anthropic-ai/claude-agent-sdk@0.2.141
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.141
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.141
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.141
Updated to parity with Claude Code v2.1.140
npm install @anthropic-ai/claude-agent-sdk@0.2.140
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.140
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.140
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.140
Updated to parity with Claude Code v2.1.139
npm install @anthropic-ai/claude-agent-sdk@0.2.139
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.139
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.139
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.139
Updated to parity with Claude Code v2.1.138
npm install @anthropic-ai/claude-agent-sdk@0.2.138
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.138
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.138
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.138
Updated to parity with Claude Code v2.1.137
npm install @anthropic-ai/claude-agent-sdk@0.2.137
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.137
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.137
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.137
Deprecated TodoWrite tool — future versions will switch to Task tools (TaskCreate, TaskGet, TaskUpdate, TaskList)
resolveSettings() (alpha) to inspect effective merged settings without spawning the Claude CLI; reads MDM (plist/HKLM/HKCU) for parity with CLI startupTodoWrite tool — future versions will switch to Task tools (TaskCreate, TaskGet, TaskUpdate, TaskList)npm install @anthropic-ai/claude-agent-sdk@0.2.136
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.136
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.136
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.136
Deprecated the unstable V2 session API (unstable_v2_createSession / unstable_v2_resumeSession / unstable_v2_prompt) — use query() instead
unstable_v2_createSession / unstable_v2_resumeSession / unstable_v2_prompt) — use query() instead'Skill' in allowedTools — use the skills option insteadnpm install @anthropic-ai/claude-agent-sdk@0.2.133
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.133
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.133
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.133
Documented applyFlagSettings() in the TypeScript Agent SDK reference and added support for null on top-level keys to clear flag-settings overrides
applyFlagSettings() in the TypeScript Agent SDK reference and added support for null on top-level keys to clear flag-settings overridesnpm install @anthropic-ai/claude-agent-sdk@0.2.132
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.132
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.132
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.132
Updated to parity with Claude Code v2.1.131
npm install @anthropic-ai/claude-agent-sdk@0.2.131
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.131
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.131
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.131
Updated to parity with Claude Code v2.1.129
npm install @anthropic-ai/claude-agent-sdk@0.2.129
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.129
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.129
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.129
Updated to parity with Claude Code v2.1.128
npm install @anthropic-ai/claude-agent-sdk@0.2.128
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.128
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.128
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.128
Added origin to result messages (SDKResultSuccess / SDKResultError) — forwards the triggering message's SDKMessageOrigin so consumers can distinguish
origin to result messages (SDKResultSuccess / SDKResultError) — forwards the triggering message's SDKMessageOrigin so consumers can distinguish user-prompted results from task-notification followupsnpm install @anthropic-ai/claude-agent-sdk@0.2.126
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.126
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.126
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.126
Updated to parity with Claude Code v2.1.124
Updated to parity with Claude Code v2.1.123
npm install @anthropic-ai/claude-agent-sdk@0.2.123
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.123
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.123
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.123
Updated to parity with Claude Code v2.1.122
npm install @anthropic-ai/claude-agent-sdk@0.2.122
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.122
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.122
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.122
Added updatedToolOutput to PostToolUseHookSpecificOutput for replacing tool output on all tools. updatedMCPToolOutput is deprecated.
updatedToolOutput to PostToolUseHookSpecificOutput for replacing tool output on all tools. updatedMCPToolOutput is deprecated.npm install @anthropic-ai/claude-agent-sdk@0.2.121
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.121
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.121
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.121
Added skills option (string[] | 'all') to control which Skills are loaded into the main session, matching the Python SDK
skills option (string[] | 'all') to control which Skills are loaded into the main session, matching the Python SDKexcludeDynamicSections now keeps static auto-memory instructions in the cacheable system-prompt block; only the per-user memory directory path and per
excludeDynamicSections now keeps static auto-memory instructions in the cacheable system-prompt block; only the per-user memory directory path and per-machine environment values are relocated to the first user messageSessionStore.append() failures are now retried up to 3 times with short backoff before the batch is dropped and mirror_error is emittednpm install @anthropic-ai/claude-agent-sdk@0.2.119
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.119
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.119
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.119
forwardSubagentText option to stream subagent text deltas to SDK consumersexcludeDynamicSections now keeps static auto-memory instructions in the cacheable system-prompt block; only the per-user memory directory path and per-machine environment values are relocated to the first user messageSessionStore.append() failures are now retried up to 3 times with short backoff before the batch is dropped and mirror_error is emittedAdded Options.managedSettings for embedders to pass policy-tier settings to the spawned CLI in-memory, honored below IT-controlled managed sources
Options.managedSettings for embedders to pass policy-tier settings to the spawned CLI in-memory, honored below IT-controlled managed sourcesnpm install @anthropic-ai/claude-agent-sdk@0.2.118
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.118
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.118
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.118
Updated to parity with Claude Code v2.1.117
npm install @anthropic-ai/claude-agent-sdk@0.2.117
# or
yarn add @anthropic-ai/claude-agent-sdk@0.2.117
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.2.117
# or
bun add @anthropic-ai/claude-agent-sdk@0.2.117
One column per month.