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.
713 B
713 B
[2026-07-08]Mistral3 + vLLM tokenizer/vision traps (serveMS3.2-24b, vLLM 0.24). (a) HFtokenizer.jsonfor Mistral = GARBAGE output — the card's "use the official Mistral tokenizer" warning is REAL; must use thetekken.json/mistral tokenizer. (b) BUT--tokenizer-mode mistral+ vision CRASHES (Failed to apply PixtralProcessor on {'text': '[IMG]'}; and with tekken.json present in auto mode,CachedMistralCommonBackend has no attribute is_fast). So it's mistral-tokenizer OR vision, not both on this vLLM. Text-only + mistral tokenizer serves clean (--limit-mm-per-prompt '{"image": 0}'). GGUF/llama.cpp avoids all of this (native mistral tokenizer + vision).