Changelog

• tr_diagnose_run listed every failure with a blank test name, an error_type stuck on "Error", an empty message, and zero duration — the count was right, so it looked like a working tool returning useless data. That's fixed.
• Timed-out tests were previously dropped entirely; they're now counted and correctly inferred as TimeoutError.
• Failures now collapse per test instead of per timeline step, so one failing test no longer produces multiple duplicate "failures."
• This also fixes tr_compare_runs and both healing tools.

Released as @testrelic/mcp v3.4.1.

The MCP server's tool list was trimmed by over 20% so assistants start faster, all supported AI assistants now get the same guidance out of the box, and small version mismatches between the server and your assistant no longer break the connection.

Added repository memory: your AI assistant now retains context about a codebase across sessions instead of starting fresh every time you open it.