memory: snapshot — sec rebuilt on DFlash2 + newer vLLM; quant tokenizer defect fixed fleet-wide

Browse Source

Rewrites the in-flight section (140 lines to 18) now that the AI-seat work
has settled, promoting the durable calls into the dated decision log where
they will not decay: DFlash2 measured and promoted to sec's compose stack,
the calibration-truncation defect fixed at source in the quant pipeline,
sec retuned after a runtime OOM, the Max-Q spread disproved by telemetry,
ESH dual-stack with the Cityside static proven unprovisioned, and speaches
live with the weak-gate finding.

Carries forward the two things a fresh session must not get wrong: the sec
degeneration question is confounded because engine and drafter changed
together, and neither the 2k nor the 10k observation is evidence.

Auto-archived one entry (Recent decisions: 1) to archival-memory.md.
Eight further candidates were held back by the guards -- open deferred work
or referenced by in-flight state.

...

This commit is contained in:

vh

2026-08-22 09:46:11 -07:00

parent 6e82899ba7

commit 837fa362fc

2 changed files with 20 additions and 153 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

persistent-memory.md

+17 -153

File diff suppressed because one or more lines are too long