Claude Code (v2.1.274) adds memory usage warnings, OpenTelemetry attributes for LLM reques

EXHIBIT 1409

Sep 17, 2026 00:55 UTC github_releases+npm+pages https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md

Claude Code (v2.1.274) adds memory usage warnings, OpenTelemetry attributes for LLM requests, and various bug fixes for sessions and tool calls.

READY TO POST:

claude code v2.1.274 is out with some useful fixes for session handling and mcp tool calls. good to see continued improvements for devs!

anthropic's claude code gets an update including better memory management warnings and more detailed opentelemetry traces for llm requests. sounds like better visibility for debugging!

[MERGED across 3 sources: github_releases, npm, pages] shared signal: claude-code --- npm :: @anthropic-ai/claude-code --- @anthropic-ai/claude-code 2.1.273 -> 2.1.274: +3 strings, -5 strings, 1 flagged as interesting [sentence] (1) + manage live-update subscriptions through which a session keeps track of new versions of an artifact published elsewhere, and those aren --- github_releases :: anthropics/claude-code --- anthropics/claude-code release: v2.1.274 name: v2.1.274 published: 2026-09-17T00:12:02Z url: https://github.com/anthropics/claude-code/releases/tag/v2.1.274 ## What's changed - Added a visible warning when memory usage is critical, with steps to free memory or restart safely - Added `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` to bound how long the first non-interactive turn waits for connecting MCP servers (`0` = don't wait) - Added `effort` attribute to the `claude_code.llm_request` OpenTelemetry trace span, matching the `api_request` event - Added `claude_code.managed_settings_resolved` OTel event: managed-settings sources and policy helper state; redacted settings and digests with `OTEL_LOG_MANAGED_SETTINGS=1` - Added `store.connect_timeout_seconds` to the Claude apps gateway config to lengthen the Postgres connect timeout (default 5 seconds), and improved the boot error when the database is unreachable to point to `store.postgres_url` and the configured timeout - Added `enduser.sub`, the IdP subject, to the telemetry Claude Desktop and Cowork send through a Claude apps gateway - Added a Claude apps gateway warning when a replica has more requests open than the 256 it sends upstream at once, and a startup log line showing that limit - Added click-to-expand for collapsed teammate and agent messages in fullscreen mode - Fixed sessions getting stuck endlessly retrying "unexpected tool_use_id" 400 errors: corrupted transcripts now self-heal where possible, and otherwise a clear error (with a `/rewind` hint) ends the loop - Fixed MCP servers configured as `h