chore(deps): bump the production group across 1 directory with 2 updates

[dependabot]

Bumps the production group with 2 updates in the / directory: @anthropic-ai/claude-agent-sdk and @anthropic-ai/sdk.

Updates @anthropic-ai/claude-agent-sdk from 0.2.141 to 0.3.168

Release notes

Sourced from @​anthropic-ai/claude-agent-sdk's releases.

v0.3.168

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

v0.3.167

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

v0.3.166

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

... (truncated)

Changelog

Sourced from @​anthropic-ai/claude-agent-sdk's changelog.

0.3.168

• Updated to parity with Claude Code v2.1.168

0.3.167

• Updated to parity with Claude Code v2.1.167

0.3.166

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

0.3.165

• Updated to parity with Claude Code v2.1.165

0.3.164

• Updated to parity with Claude Code v2.1.164

0.3.163

• 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

0.3.162

• 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

0.3.161

• 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

0.3.160

• 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

0.3.159

• Updated to parity with Claude Code v2.1.159

0.3.158

• Updated to parity with Claude Code v2.1.158

0.3.157

... (truncated)

Commits

• 2c2eeb8 chore: Update CHANGELOG.md
• 3e35050 chore: Update CHANGELOG.md
• bc853fc chore: Update CHANGELOG.md
• 3bdcdcb chore: Update CHANGELOG.md
• 9f0a1ce chore: Update CHANGELOG.md
• e9f26a0 chore: Update CHANGELOG.md
• 2f67c51 chore: Update CHANGELOG.md
• b33e8d5 chore: Update CHANGELOG.md
• 84f8395 chore: Update CHANGELOG.md
• e3a2056 chore: Update CHANGELOG.md
• Additional commits viewable in compare view

Updates @anthropic-ai/sdk from 0.81.0 to 0.102.0

Release notes

Sourced from @​anthropic-ai/sdk's releases.

sdk: v0.102.0

0.102.0 (2026-06-06)

Full Changelog: sdk-v0.101.0...sdk-v0.102.0

Features

• api: small updates to Managed Agents types (8ba4f92)

Bug Fixes

• client: run middleware before request signing (#45) (95f1a4a)

sdk: v0.101.0

0.101.0 (2026-06-05)

Full Changelog: sdk-v0.100.1...sdk-v0.101.0

Features

• client: add support for middleware (9b01120)

Bug Fixes

• apply request timeout to inner fetch only, not middleware chain (#40) (25c13f6)
• streaming: carry stop_details through beta message_delta accumulation (ed3fec7)
• streaming: correctly parse json numbers with scientific notation (#9) (7d5e642)

Chores

• internal: fix artifact url (925ec27)
• internal: fix branch names (fa3cf2c)
• internal: update private repo name (a8ac213)

Documentation

• point security reports to Anthropic's HackerOne program (#16) (5c7912c)

sdk: v0.100.1

0.100.1 (2026-05-29)

Full Changelog: sdk-v0.100.0...sdk-v0.100.1

Bug Fixes

• streaming: carry encrypted_content on beta compaction blocks (#1025) (eccddf3)

... (truncated)

Changelog

Sourced from @​anthropic-ai/sdk's changelog.

0.102.0 (2026-06-06)

Full Changelog: sdk-v0.101.0...sdk-v0.102.0

Features

• api: small updates to Managed Agents types (8ba4f92)

Bug Fixes

• client: run middleware before request signing (#45) (95f1a4a)

0.101.0 (2026-06-05)

Full Changelog: sdk-v0.100.1...sdk-v0.101.0

Features

• client: add support for middleware (9b01120)

Bug Fixes

• apply request timeout to inner fetch only, not middleware chain (#40) (25c13f6)
• streaming: carry stop_details through beta message_delta accumulation (ed3fec7)
• streaming: correctly parse json numbers with scientific notation (#9) (7d5e642)

Chores

• internal: fix artifact url (925ec27)
• internal: fix branch names (fa3cf2c)
• internal: update private repo name (a8ac213)

Documentation

• point security reports to Anthropic's HackerOne program (#16) (5c7912c)

0.100.1 (2026-05-29)

Full Changelog: sdk-v0.100.0...sdk-v0.100.1

Bug Fixes

• streaming: carry encrypted_content on beta compaction blocks (#1025) (eccddf3)

Chores

... (truncated)

Commits

• f7dfb97 chore: release main
• a3f3c97 feat(api): small updates to Managed Agents types
• a5c98d1 fix(client): run middleware before request signing (#45)
• 185ec06 chore: release main
• fab8910 codegen metadata
• 7ff4036 fix: apply request timeout to inner fetch only, not middleware chain (#40)
• 257bc1f feat(client): add support for middleware
• 5b3ace5 chore(internal): fix artifact url
• 70966be fix(streaming): correctly parse json numbers with scientific notation (#9)
• 7e22f20 docs: point security reports to Anthropic's HackerOne program (#16)
• Additional commits viewable in compare view

Maintainer changes

This version was pushed to npm by GitHub Actions, a new releaser for @​anthropic-ai/sdk since your current version.

[github-actions]

⚠️ Deprecation Warning: The deny-licenses option is deprecated for possible removal in the next major release. For more information, see issue 997.

Dependency Review

The following issues were found:

• ✅ 0 vulnerable package(s)
• ✅ 0 package(s) with incompatible licenses
• ✅ 0 package(s) with invalid SPDX license definitions
• ⚠️ 2 package(s) with unknown licenses.

See the Details below.

License Issues

package.json

Package	Version	License	Issue Type
@anthropic-ai/claude-agent-sdk	^0.3.168	Null	Unknown License
@anthropic-ai/sdk	^0.102.0	Null	Unknown License

Denied Licenses:

GPL-2.0-only, GPL-3.0-only

OpenSSF Scorecard

Package	Version	Score	Details
npm/@anthropic-ai/claude-agent-sdk	^0.3.168	Unknown	Unknown
npm/@anthropic-ai/sdk	^0.102.0	Unknown	Unknown

Scanned Files

• package.json