vh
d710e56aca
Split the 53 over-threshold dated log entries (Recent decisions, Tried and abandoned) into per-entry persistent-memory.d/<slug>.md detail files, leaving one-line pointers in the index; the 10 short entries stay inline. Startup index drops 60,527 -> 25,256 bytes (492 -> 270 lines); entry bodies move verbatim to on-demand detail files, so a fresh session loads ~25 KB instead of ~60 KB and pulls a detail file only when its pointer is relevant. Top matter (Repo purpose, Tools & conventions, Current state) is unchanged; both archival back-references preserved. CLAUDE.md persistent-memory section now documents the index<->detail read discipline (read the index, pull details on demand, never bulk-read the dir, commit both together). Auto-archival still held every dated entry back (all <30 days old); the July burst begins aging past the 30-day guard ~2026-07-31.
496 B
496 B
[2026-07-07]Engine invocation footguns cost several wasted serve-bounces this session —docker run --rmate crash logs; duplicatedserve(vLLM image entrypoint is already["vllm","serve"]);--max-lora-rank 48invalid (choices 1/8/16/32/64… → use 64); parens inechoinsidessh host -c "…"break the remote shell. LESSON: verify engine launch flags (--help, GPU-free) + never--rma container whose crash logs you need, BEFORE bouncing a production serve.