vh
ff1f9ca1e8
- #368 (user,character) memory silo test DONE + PASSED live (WT b127): write-side conjunctive {end_user,agent_self} scoping + read-side cross- character isolation both proven end-to-end; betty (throwaway) deleted, Sindra intact. Full record in persistent-memory.d/2026-07-18-368-silo- test-passed.md. Retired the stale "silo test in progress" in-flight blocks. - Two-tier migration: split 152 over-threshold dated entries into persistent-memory.d/ detail files, leaving one-line pointers in the index (startup load ~196KB -> ~53KB; bodies now load on demand). - Tier-3 stores scrubbed clean (memory 0 / affect 0, provider restarted empty); persistent-memory + detail file updated to reflect the scrub.
2 lines
1.1 KiB
Markdown
2 lines
1.1 KiB
Markdown
`[2026-07-12]` **R34/R35 character-self-report reframe LIVE (WT b53); affect-half VALIDATED in prod, powered memory-half eval GREENLIT + designed.** worldtree-dev's reframe: affect + memory now driven by the character's OWN model self-report on our RP seat (Deckard/Magidonia), replacing external Vili inference; conditioned on an authored `persona.psychological_profile` (else a deterministic OCEAN scaffold). Affect-half smoke GREEN in prod (bound sindra turn on Deckard → contextually-apt `disappointment`); TIER LOCKED (Tier-3 bound-character path). Vuong approved brokkr's prereg for the powered eval (Q1 salience-divergence / Q2 floor-recall / Q3 firewall / Q4 graded-slot / Q5 authored-vs-scaffold / Q6 sliding; ~300 drive-runs). Role split: brokkr generates sets + authors ground-truth + scores; ratatoskr DRIVES the b53 producers; worldtree supplies the pair + a producer-probe. Three eval characters authored + peer-validated (sindra relational + Torvald low-A operational = divergence pair; Ilva high-N = affect-magnitude arm) — wire-ready in `scratchpad/eval_profiles_WIRE_READY.md`. Full in-flight detail in Current state; eval thread althing `01KXAN073B`.
|