dongarandClaude Opus 5.5 5e1086c501 Expert and integration roles on claude-haiku-5-5 ...

claude-haiku-4-5 is being replaced by claude-haiku-5-5 in LiteLLM: the
integration tests' roles and the example config's expert move to it.
Its profile keeps the predecessor's benchmark figures, marked as such
until it's measured. The plan's models-by-role line also gains the
local classifier (M3.2). Results measured on 4.5 stay as they were.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE

2026-10-08 16:38:06 +00:00

..

Architecture.md

M3.3: the trust dial (the agent merges approved PRs)

2026-10-08 13:48:16 +00:00

Development-Plan.md

Expert and integration roles on claude-haiku-5-5

2026-10-08 16:38:06 +00:00

Tuning-Guide.md

M4.1: toolchain preflight

2026-10-08 15:43:30 +00:00