{"version":"2.1.296","anchor":"new-telemetry-and-error-categories","canonical_anchor":"new-telemetry-and-error-categories","heading":"New diagnostic categories for transcripts, cloud tools and MCP tasks","tier":"internal","area":"Telemetry","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296\/e\/new-telemetry-and-error-categories","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.296","markdown":"### New diagnostic categories for transcripts, cloud tools and MCP tasks\n\nClaude Code adds diagnostic categories for unreadable transcript lines, cloud built-in tools and MCP task registration\n\n**What**\n\nClaude 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:\n\n- `transcript_unparsable_lines`: lines in a session transcript that could not be read\n\n- `cloud_builtin_tools_create`: creating cloud built-in tools\n\n- `mcp_task_registration`: registering tasks over MCP, the protocol Claude Code uses to talk to outside tool servers\n\n- a flag for summarised rows that were kept but not loaded\n\n**Why**\n\nThese are diagnostic labels. They suggest that unreadable transcript lines, cloud built-in tools and MCP task registration are now being tracked.\n\n- Area: Telemetry\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}