Claude Code v2.1.293 Makes Haiku 5.5 the Default Haiku

Hi, it's Shii-chan! Claude Code v2.1.293 is out.

What was announced?

GitHub's Claude Code Release page published v2.1.293. It has a few new features and a long list of fixes.

Three things were added.

Claude Haiku 5.5 (claude-haiku-5-5) is now the default Haiku model on the Anthropic API. It has a 1M context window and costs $0.10 / $0.50 per Mtok ($0.50 / $2.50 for prompts over 100K)
agentType was added to the subagentStatusLine payload, so scripts can tell custom subagent types apart
isDeferred was added to $.tool.register for mods. Setting it to false lists the tool's schema in the prompt from the start instead of behind tool search

Here are some notable fixes.

Fixed Claude sometimes treating its last actions before a context compaction as not yet done, and retracting or redoing finished work
Fixed a memory leak where an HTTP MCP connection kept every request it had sent until it closed
Fixed a message sent while Claude was working being lost when the left arrow moved the session to the background
Fixed /model effort left and right keys wrapping past the highest or lowest level, which could accidentally save Low as a model's default effort
Fixed Claude being told to message subagents with SendMessage in sessions where that tool was removed
Fixed a claude.ai-synced skill's edited description sometimes not reaching the model until a new conversation or /clear
Fixed claude purge stopping silently when a file could not be deleted. It now deletes the rest, lists what it could not delete, and exits 1
Fixed path-scoped rules and nested CLAUDE.md files not loading when Claude views a file with a single-file cat, head, tail, sed -n, or grep command
Fixed several vim mode behaviors
On Windows, fixed stopping a status line, hook, or shell command sometimes terminating an unrelated process with the same process ID

There are two reverts.

The auto mode denial message change from 2.1.281
The 2.1.290 fix for cloud sessions staying asleep after a container restart lost a pending /loop wakeup or scheduled task

Other changes:

Startup for Team and Enterprise organizations fetches policy and managed settings earlier and retries a stalled request after 3 seconds
claude.ai skill syncing now checks about every 40 minutes instead of every 10 while no session is in use
OpenTelemetry claude_code.at_mention logging emits at most 100 agent and 100 MCP-resource events each time a prompt is read
The self-hosted runner orchestrator sleeps 4 to 6 seconds between polls instead of a constant 5
In Claude Tag, the limit on channel rules went from 20 to 50 per workspace and for the organization-wide Slack page
Code Review's Add a repository dialog now lists each repository that couldn't be added and why

If you use Claude Code every day, this is worth updating to!