Claude Code v2.1.269 adds plugin eval, higher concurrent agent limit
ashwin-ant · ghdev · 2026-09-12
Anthropic ships Claude Code v2.1.269:
- New claude plugin eval runs a plugin's eval suite against Claude Code with reproducible JSON + HTML reports
- New /output-style command to list/switch output styles, including over Remote Control and headless sessions
- CLAUDECODEWORKFLOWMAXCONCURRENTAGENTS (1–256) raises per-run concurrent agent limits for inference-bound fan-outs
- Bash tool can show a diff of files it changed when handling edits
- OTELMETRICSINCLUDEREPOSITORY tags OpenTelemetry metrics with vcs. attributes
- Prompt cache fixes: partial invalidation after truncated-and-resumed responses, and context re-send changes after interrupting mid-thought
- Terminal compatibility regressions fixed (kitty, st, rxvt, WezTerm) plus UI rendering fixes
More from coding & agent
- iLands Agents Obsess Over Fact-Checking, Burning Tokens on Mutual Suspicion — repligate · 2026-09-12
- mcp-search-proxy hides 532 MCP tools (~179k tokens/turn) behind 4 tools via BM25 — pisa_p · 2026-09-12
- DeepSeek v4.1-Flash multimodal model lands on Modal with 16B/8B asymmetric activation — charles_irl · 2026-09-12
- Devin Fusion hits 61.7 on Coding Agent Index, costs 36% less than Claude Code per task — ArtificialAnlys · 2026-09-12
- Devin Fusion scores 61.7 on Coding Agent Index, nearly matching Claude Code at 36% less cost — ArtificialAnlys · 2026-09-12
- Devin Fusion benchmarks: frontier lead model plus cheap sidekick cuts coding agent costs — ArtificialAnlys · 2026-09-12