NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →

npm · #3768 most downloaded on npm

@anthropic-ai/claude-agent-sdk

0.3.275anthropics/claude-agent-sdk-typescript ↗New releases in your daily digest, changelog included.

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
17 Sep 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Nothing withdrawn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
11 months old
300 releases · first in 2025

Release timeline

300 releases since 2025

20252026

Releases

0.3.2069 Jul 20262 sources agree
Added command_lifecycle frames to stream-json and SDK sessions, reporting each uuid-stamped message's terminal state (queued/started/completed/cancell
What's changed

Added command_lifecycle frames to stream-json and SDK sessions, reporting each uuid-stamped message's terminal state (queued/started/completed/cancelled/discarded); zero-API results no longer report stale duration_api_ms

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.206 # or yarn add @anthropic-ai/claude-agent-sdk@0.3.206 # or pnpm add @anthropic-ai/claude-agent-sdk@0.3.206 # or bun add @anthropic-ai/claude-agent-sdk@0.3.206
Open source →
0.3.2058 Jul 20262 sources agree
Interrupt control responses now include still_queued (UUIDs of queued async messages that will still run), Query.interrupt() returns the typed receipt
What's changed

Interrupt control responses now include still_queued (UUIDs of queued async messages that will still run), Query.interrupt() returns the typed receipt, and system/init advertises an interrupt_receipt_v1 capability for feature detection

Added structured name and body fields to peer-message session events, exposing the sender display name and decoded message body

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.205 # or yarn add @anthropic-ai/claude-agent-sdk@0.3.205 # or pnpm add @anthropic-ai/claude-agent-sdk@0.3.205 # or bun add @anthropic-ai/claude-agent-sdk@0.3.205

0.3.2048 Jul 2026

Updated to parity with Claude Code v2.1.204

What's changed

Updated to parity with Claude Code v2.1.204

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.204
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.204
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.204
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.204

Open source →

Additional notes

Added terminal_reason values tool_deferred_unavailable (deferred tool resume found the tool gone — previously an is_error result with no reason, read as a clean completion by lifecycle sweeps) and turn_setup_failed (the turn-input builder threw before the turn started). Both classify as dead turns, so commands consumed by them report command_lifecycle state cancelled
Fixed the post-merge cancel backstop cancelling every member of a coalesced prompt batch when a cancel named only one: uncancelled siblings now re-merge and run (previously they were reported cancelled — on remote transports that acknowledged them as processed, silently dropping messages nobody cancelled)
Added terminal_reason values api_error, malformed_tool_use_exhausted, budget_exhausted, and structured_output_retry_exhausted. Turns that die on an exhausted-API-retry or malformed-tool-use give-up previously reported completed; budget and structured-output exhaustion results previously omitted terminal_reason. Commands consumed by such turns now report command_lifecycle state cancelled instead of completed (dup-over-loss)
Updated to parity with Claude Code v2.1.204

Open source →

0.3.2037 Jul 20262 sources agree

Added a background_tasks_changed system message with the full set of live background tasks on every membership change, so consumers can track backgrou

What's changed

Added a background_tasks_changed system message with the full set of live background tasks on every membership change, so consumers can track background activity as a level instead of pairing task_started/task_notification edges
Fixed stable releases shipping a sdk.d.ts with unresolved type references that broke consumer typechecking with skipLibCheck disabled

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.203
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.203
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.203
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.203

Open source →

0.3.2026 Jul 20262 sources agree

Added parent_agent_id field to subagent session messages for building depth-2+ agent trees from disk-persisted metadata

What's changed

Added parent_agent_id field to subagent session messages for building depth-2+ agent trees from disk-persisted metadata
Fixed apply_flag_settings with a non-object settings value crashing the session instead of returning a control error

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.202
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.202
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.202
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.202

Open source →

0.3.2013 Jul 20262 sources agree

Updated to parity with Claude Code v2.1.201

What's changed

Updated to parity with Claude Code v2.1.201

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.201
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.201
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.201
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.201

Open source →

0.3.2003 Jul 20262 sources agree

Added 'manual' as an accepted alias for the 'default' permission mode in SDK inputs

What's changed

Added 'manual' as an accepted alias for the 'default' permission mode in SDK inputs
Fixed onSetPermissionMode callback not firing for SDK-hosted Remote Control sessions
Fixed set_model control request accepting unrecognized model strings; invalid models are now rejected before latching

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.200
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.200
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.200
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.200

Open source →

0.3.1992 Jul 20262 sources agree

Added requestId to canUseTool callback options for correlating out-of-band permission responses, and support for returning null to suppress the SDK's

What's changed

Added requestId to canUseTool callback options for correlating out-of-band permission responses, and support for returning null to suppress the SDK's automatic control response
Added blocked field to workflow_agent progress events indicating when an agent was blocked by the auto-mode safety classifier
Added mode:"mask" and per-credential injectHosts to sandbox.credentials settings types for injecting masked credentials into sandboxed commands

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.199
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.199
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.199
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.199

Open source →

0.3.1981 Jul 20262 sources agree

Added a runtime warning when canUseTool is configured alongside allowedTools or bypassPermissions, which shadow the callback

What's changed

Added a runtime warning when canUseTool is configured alongside allowedTools or bypassPermissions, which shadow the callback
Added per-server request_timeout_ms option to mcp_set_servers control request
Fixed SDKUserMessage.isSynthetic not being mapped to isMeta on ingestion, which could cause synthetic messages to be treated as real user messages
Fixed workflow progress events silently dropping earliest agents from the list while the phase counter remained correct

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.198
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.198
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.198
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.198

Open source →

0.3.19730 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.197

What's changed

Updated to parity with Claude Code v2.1.197

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.197
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.197
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.197
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.197

Open source →

0.3.19629 Jun 20262 sources agree

Added prompt_id field to hook input payloads for correlating hook events with OpenTelemetry prompt-level events

What's changed

Added prompt_id field to hook input payloads for correlating hook events with OpenTelemetry prompt-level events
Fixed control protocol deduplication dropping tool-use IDs after 1000 resolutions, which could cause duplicate tool_result deliveries in long-running sessions

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.196
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.196
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.196
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.196

Open source →

0.3.19526 Jun 20262 sources agree

Added Query.reinitialize() to re-send the initialize control request and redeliver pending permission/dialog prompts after a transport gap

What's changed

Added Query.reinitialize() to re-send the initialize control request and redeliver pending permission/dialog prompts after a transport gap
Fixed commands_changed event not being emitted for synced skills when the skill list resolves before the change-detector subscribes

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.195
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.195
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.195
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.195

Open source →

0.3.19325 Jun 20262 sources agree

Added promptSuggestions option to Browser SDK query() to opt the remote CLI into emitting follow-up suggestions

What's changed

Added promptSuggestions option to Browser SDK query() to opt the remote CLI into emitting follow-up suggestions
Fixed brief console window flashes on Windows when spawning CLI subprocesses

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.193
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.193
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.193
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.193

Open source →

0.3.19124 Jun 20262 sources agree

Added old_source field to NotebookEdit tool results for replace and delete operations, enabling inline diffs

What's changed

Added old_source field to NotebookEdit tool results for replace and delete operations, enabling inline diffs
Added seven_day_overage_included to SDKRateLimitInfo.rateLimitType for per-model weekly usage limits
Added model_scoped array to usage response for per-model weekly limit windows with utilization and reset times
Fixed fast mode reverting to standard after the first turn when settingSources includes user/project settings

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.191
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.191
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.191
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.191

Open source →

0.3.19024 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.190

What's changed

Updated to parity with Claude Code v2.1.190

Update

npm install @anthropic-ai/claude-agent-sdk@0.3.190
# or
yarn add @anthropic-ai/claude-agent-sdk@0.3.190
# or
pnpm add @anthropic-ai/claude-agent-sdk@0.3.190
# or
bun add @anthropic-ai/claude-agent-sdk@0.3.190

Open source →

0.3.18723 Jun 20262 sources agree

Added sandbox.credentials to SDK settings types for configuring credential file and environment variable denial in sandboxed commands

What's changed

Added sandbox.credentials to SDK settings types for configuring credential file and environment variable denial in sandboxed commands

Update

npm 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

Open source →

0.3.18622 Jun 20262 sources agree

Added agent_id field to can_use_tool control requests — background agents now forward permission prompts to canUseTool instead of auto-denying, and st

What's changed

Added 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 running
Added ReadMcpResourceDirTool tool type to SDK schemas — MCP resource directory listing is now a dedicated tool instead of a fallback inside ReadMcpResourceTool
Added rewind_conversation control request for rewinding a conversation to a previous point with durable resume anchor support

Update

npm 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

Open source →

0.3.18520 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.185

What's changed

Updated to parity with Claude Code v2.1.185

Update

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

Open source →

0.3.18319 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.183

What's changed

Updated to parity with Claude Code v2.1.183

Update

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

Open source →

0.3.18117 Jun 20262 sources agree

Added errorCode, canUserPurchaseCredits, and hasChargeableSavedPaymentMethod fields to SDKRateLimitInfo for detecting credits-required rate limits

What's changed

Added errorCode, canUserPurchaseCredits, and hasChargeableSavedPaymentMethod fields to SDKRateLimitInfo for detecting credits-required rate limits
Added tool_use_meta.icon_url to assistant messages, populated from MCP server directory metadata
Fixed SDK-hosted Remote Control sessions dropping file_attachments from inbound user messages

Update

npm 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

Open source →

0.3.17916 Jun 20262 sources agree

Added optional tool_use_meta sidecar to assistant messages with display-friendly names for tool calls, so SDK consumers can render human-readable labe

What's changed

Added optional 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
Fixed -p mode exiting before a completed background agent's notification was delivered, causing interim text to ship as the final result
Fixed remote (stream-json) sessions appearing busy for the entire duration of a background workflow — the turn result is now emitted at the turn boundary and the session reports idle while background tasks continue

Update

npm 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

Open source →

0.3.17815 Jun 20262 sources agree

Spawn failures on an existing native binary now explain the likely libc mismatch (musl binary on a glibc host) and suggest options.pathToClaudeCodeExe

What's changed

Spawn failures on an existing native binary now explain the likely libc mismatch (musl binary on a glibc host) and suggest options.pathToClaudeCodeExecutable
Permission-denied advisory messages now carry typed denial reasons (safetyCheck, asyncAgent), enabling SDK consumers to programmatically match denial causes
Fixed UserPromptSubmit 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 hang
Remote Control workers now send a worker_shutting_down system message on graceful exit so remote clients can show why the session ended
Fixed MCP server-level specs (mcp__server, mcp__server__*) in disallowedTools being silently ignored — they now correctly remove all tools from the named server

Update

npm 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

Open source →

0.3.17713 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.177

What's changed

Updated to parity with Claude Code v2.1.177

Update

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

Open source →

0.3.17612 Jun 20262 sources agree

Fixed turn result messages being dropped when multiple turns complete while a background agent or workflow is running

What's changed

Fixed turn result messages being dropped when multiple turns complete while a background agent or workflow is running
Fixed background agent, remote agent, and MCP task state not being restored when resuming a session via the SDK

Update

npm 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

Open source →

0.3.17512 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.175

What's changed

Updated to parity with Claude Code v2.1.175

Update

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

Open source →

0.3.17411 Jun 20262 sources agree

SDK consumers now receive the system/model_fallback message for all fallback triggers — overloaded, server_error, and last_resort in addition to model

What's changed

SDK consumers now receive the 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 values

Update

npm 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

Open source →

0.3.17311 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.173

What's changed

Updated to parity with Claude Code v2.1.173

Update

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

Open source →

0.3.17210 Jun 20262 sources agree

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

What's changed

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 the plugin path without the engine re-reading its .mcp.json
Fixed slash-followed-by-whitespace input (e.g. / add tests) being silently dropped instead of treated as a plain prompt

Update

npm 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

Open source →

0.3.1709 Jun 20262 sources agree

Added claude-fable-5 model and the fable alias to SDK model types. https://www.anthropic.com/news/claude-fable-5-mythos-5

What's changed

Added claude-fable-5 model and the fable alias to SDK model types. https://www.anthropic.com/news/claude-fable-5-mythos-5
Updated to parity with Claude Code v2.1.170

Update

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

Open source →

0.3.1698 Jun 20262 sources agree

Added an experimental usage_EXPERIMENTAL_MAY_CHANGE_DO_NOT_RELY_ON_THIS_API_YET() method on Query returning structured session cost, plan rate-limit,

What's changed

Added an experimental 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 data
Added an sse option (SSEOptions) to BrowserQueryOptions as an alternative to websocket, for browser SDK consumers who prefer Server-Sent Events

Update

npm 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

Open source →

0.3.1686 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.168

What's changed

Updated to parity with Claude Code v2.1.168

Update

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

Open source →

0.3.1676 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.167

What's changed

Updated to parity with Claude Code v2.1.167

Update

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

Open source →

0.3.1665 Jun 20262 sources agree

Fixed MCP resource tools not being injected for servers added at runtime via the mcp_set_servers control request

What's changed

Fixed MCP resource tools not being injected for servers added at runtime via the mcp_set_servers control request

Update

npm 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

Open source →

0.3.1655 Jun 20262 sources agree

Updated to parity with Claude Code v2.1.165

What's changed

Updated to parity with Claude Code v2.1.165

Update

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

Open source →

0.3.1634 Jun 20262 sources agree

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

What's changed

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 chips
Fixed SDK hosts being unable to add builtin MCP servers (e.g. claude-in-chrome) via setMcpServers when the CLI was launched without them
Stop and SubagentStop hook events now support additionalContext in hookSpecificOutput, enabling non-error feedback that continues the turn

Update

npm 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

Open source →

0.3.1623 Jun 20262 sources agree

Refusal error messages now carry stop_reason: "refusal" and stop_details on the assistant message and in session transcripts, so SDK consumers can det

What's changed

Refusal error messages now carry 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 content
Agent SDK sessions on native builds now default to fast embedded find/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 allowedTools

Update

npm 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

Open source →

0.3.1612 Jun 20262 sources agree

The initialize control request is now idempotent: a second initialize returns the same success payload instead of an Already initialized error. Contro

What's changed

The 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 ControlErrorResponse
applyFlagSettings now live-applies agent changes: switching the active agent (or passing null to reset) takes effect on the next turn in a running session

Update

npm 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

Open source →

0.3.1601 Jun 20262 sources agree

Fixed SDK hook callbacks swallowing abort signals: aborting during a PostToolUse hook now ends the turn with a final result message instead of hanging

What's changed

Fixed SDK hook callbacks swallowing abort signals: aborting during a PostToolUse hook now ends the turn with a final result message instead of hanging the calling process

Update

npm 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

Open source →

0.3.15931 May 20262 sources agree

Updated to parity with Claude Code v2.1.159

What's changed

Updated to parity with Claude Code v2.1.159

Update

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

Open source →

0.3.15830 May 20262 sources agree

Updated to parity with Claude Code v2.1.158

What's changed

Updated to parity with Claude Code v2.1.158

Update

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

Open source →

0.3.15729 May 20262 sources agree

Updated to parity with Claude Code v2.1.157

What's changed

Updated to parity with Claude Code v2.1.157

Update

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

Open source →

0.3.15628 May 20262 sources agree

Updated to parity with Claude Code v2.1.156

What's changed

Updated to parity with Claude Code v2.1.156

Update

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

Open source →

0.3.15428 May 20262 sources agree

Fixed stdio MCP servers being incorrectly restarted on every reconcile pass due to config-equality false positives

What's changed

Fixed stdio MCP servers being incorrectly restarted on every reconcile pass due to config-equality false positives

Update

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

Open source →

0.3.15327 May 20262 sources agree

Updated to parity with Claude Code v2.1.153

What's changed

Updated to parity with Claude Code v2.1.153

Update

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

Open source →

0.3.15226 May 20262 sources agree

SessionStart hooks can now return reloadSkills: true to trigger a skill re-scan, and set the session title via hookSpecificOutput.sessionTitle

What's changed

SessionStart hooks can now return reloadSkills: true to trigger a skill re-scan, and set the session title via hookSpecificOutput.sessionTitle
Added a MessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayed

Update

npm 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

Open source →

0.3.15023 May 2026

Updated to parity with Claude Code v2.1.150

What's changed

Updated to parity with Claude Code v2.1.150

Update

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

Open source →

Additional notes

The 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.
Updated to parity with Claude Code v2.1.150

Open source →

0.3.14922 May 20262 sources agree

Fixed options.env dropping CLAUDE_AGENT_SDK_VERSION (used for User-Agent and telemetry) when a custom environment is supplied, and corrected the Optio

What's changed

Fixed 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.env

Update

npm 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

Open source →

0.3.14822 May 20262 sources agree

Updated to parity with Claude Code v2.1.148

What's changed

Updated to parity with Claude Code v2.1.148

Update

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

Open source →

0.3.14721 May 20262 sources agree

Updated to parity with Claude Code v2.1.147

What's changed

Updated to parity with Claude Code v2.1.147

Update

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

Open source →

0.3.14620 May 20262 sources agree

Updated to parity with Claude Code v2.1.146

What's changed

Updated to parity with Claude Code v2.1.146

Update

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

Open source →

0.3.14519 May 20262 sources agree

Updated to parity with Claude Code v2.1.145

What's changed

Updated to parity with Claude Code v2.1.145

Update

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

Open source →

0.3.14418 May 20262 sources agree

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

What's changed

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 generic 'invalid_request'. The api_error_status field on result messages is now documented.
Added @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.pathToClaudeCodeExecutable

Update

npm 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

Open source →

0.3.14315 May 20262 sources agree

@anthropic-ai/sdk and @modelcontextprotocol/sdk are now peerDependencies instead of dependencies. Runtime is unaffected (both are bundled); npm/bun/pn

What's changed

@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 resolution

Update

npm 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

Open source →

0.3.14214 May 2026Deprecated2 sources agree

…SDKSession, SDKSessionOptions), deprecated since 0.2.133. Use query() — pass an AsyncIterable for multi-turn, or options.resume to continue a session.

What's changed

Breaking: Removed the v2 session API (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.
Breaking: MCP servers now connect in the background by default; sessions start immediately and slow servers report 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.
Breaking: Headless and SDK sessions now use Task tools (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.
Surfaced request_id, subagent_type, and task_description on SDK message types and task system events
Headless --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 0

Update

npm 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

Open source →

0.2.14113 May 20262 sources agree

TaskCreateInput, TaskCreateOutput, TaskGetInput, TaskGetOutput, TaskUpdateInput, TaskUpdateOutput, TaskListInput, and TaskListOutput types are now exp

What's changed

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
Aligned @anthropic-ai/sdk dependency to ^0.93.0

Update

npm 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

Open source →

0.2.14012 May 20262 sources agree

Updated to parity with Claude Code v2.1.140

What's changed

Updated to parity with Claude Code v2.1.140

Update

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

Open source →

0.2.13911 May 20262 sources agree

Updated to parity with Claude Code v2.1.139

What's changed

Updated to parity with Claude Code v2.1.139

Update

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

Open source →

0.2.1389 May 20262 sources agree

Updated to parity with Claude Code v2.1.138

What's changed

Updated to parity with Claude Code v2.1.138

Update

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

Open source →

0.2.1379 May 20262 sources agree

Updated to parity with Claude Code v2.1.137

What's changed

Updated to parity with Claude Code v2.1.137

Update

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

Open source →