Update dependency @anthropic-ai/claude-agent-sdk to ^0.3.0

[renovate]

This PR contains the following updates:

Package	Change	Age	Confidence
@anthropic-ai/claude-agent-sdk	^0.2.92 → ^0.3.0

---

Release Notes

anthropics/claude-agent-sdk-typescript (@​anthropic-ai/claude-agent-sdk)

v0.3.201

Compare Source

• Updated to parity with Claude Code v2.1.201

v0.3.200

Compare Source

• 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

v0.3.199

Compare Source

• 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

v0.3.198

Compare Source

• 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

v0.3.197

Compare Source

• Updated to parity with Claude Code v2.1.197

v0.3.196

Compare Source

• 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

v0.3.195

Compare Source

• 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

v0.3.193

Compare Source

• 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

v0.3.191

Compare Source

• 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

v0.3.190

Compare Source

• Updated to parity with Claude Code v2.1.190

v0.3.187

Compare Source

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

v0.3.186

Compare Source

• 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

v0.3.185

Compare Source

• Updated to parity with Claude Code v2.1.185

v0.3.183

• Updated to parity with Claude Code v2.1.183

v0.3.182

• Updated to parity with Claude Code v2.1.182

v0.3.181

Compare Source

• 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

v0.3.179

Compare Source

• 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

v0.3.178

Compare Source

• 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

v0.3.177

Compare Source

• Updated to parity with Claude Code v2.1.177

v0.3.176

Compare Source

• 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

v0.3.175

Compare Source

• Updated to parity with Claude Code v2.1.175

v0.3.174

Compare Source

• 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

v0.3.173

Compare Source

• Updated to parity with Claude Code v2.1.173

v0.3.172

Compare Source

• 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

v0.3.170

Compare Source

• 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

v0.3.169

Compare Source

• 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

v0.3.168

Compare Source

• Updated to parity with Claude Code v2.1.168

v0.3.167

Compare Source

• Updated to parity with Claude Code v2.1.167

v0.3.166

Compare Source

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

v0.3.165

Compare Source

• Updated to parity with Claude Code v2.1.165

v0.3.163

Compare Source

• 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

v0.3.162

Compare Source

• 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

v0.3.161

Compare Source

• 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

v0.3.160

Compare Source

• 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

v0.3.159

Compare Source

• Updated to parity with Claude Code v2.1.159

v0.3.158

Compare Source

• Updated to parity with Claude Code v2.1.158

v0.3.157

Compare Source

• Updated to parity with Claude Code v2.1.157

v0.3.156

Compare Source

• Updated to parity with Claude Code v2.1.156

v0.3.154

Compare Source

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

v0.3.153

Compare Source

• Updated to parity with Claude Code v2.1.153

v0.3.152

Compare Source

• 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

v0.3.150

Compare Source

• Updated to parity with Claude Code v2.1.150

v0.3.149

Compare Source

• 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

v0.3.148

Compare Source

• Updated to parity with Claude Code v2.1.148

v0.3.147

Compare Source

• Updated to parity with Claude Code v2.1.147

v0.3.146

Compare Source

• Updated to parity with Claude Code v2.1.146

v0.3.145

Compare Source

• Updated to parity with Claude Code v2.1.145

v0.3.144

Compare Source

• 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

v0.3.143

Compare Source

• @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

v0.3.142

Compare Source

• 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

---

Configuration

📅 Schedule: (UTC)

• Branch creation
  • At any time (no schedule defined)
• Automerge
  • At any time (no schedule defined)

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about these updates again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.