Follow Discord
Sweep 09 Oct 2026 · 17:27Z Build v2.1.296 517 read Stable v2.1.287 Latest v2.1.296 Next v2.1.296 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeReleasesv2.1.296entry #231

Claude Code v2.1.296 ·

New diagnostic categories for transcripts, cloud tools and MCP tasks

Claude Code adds diagnostic categories for unreadable transcript lines, cloud built-in tools and MCP task registration

Under the hood Internal Changes
JSON All of v2.1.296
Under the hoodTier: how much it should matter to you
1Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
TelemetryArea: what it touches
Internal ChangesKind: in v2.1.296,
Internal ChangesSection of the release
What

Claude Code's lists of error and telemetry categories gain new values. Telemetry is the anonymous measurements Claude Code sends about how it runs. The new values are:

  • transcript_unparsable_lines: lines in a session transcript that could not be read
  • cloud_builtin_tools_create: creating cloud built-in tools
  • mcp_task_registration: registering tasks over MCP, the protocol Claude Code uses to talk to outside tool servers
  • a flag for summarised rows that were kept but not loaded
Why

These are diagnostic labels. They suggest that unreadable transcript lines, cloud built-in tools and MCP task registration are now being tracked.

See this entry in the whole of v2.1.296 →

Feedback