From ffcd3bf9ba479d3ac135368905fabde905e654dc Mon Sep 17 00:00:00 2001 From: Meta Vens Date: Fri, 12 Jun 2026 12:10:09 +0100 Subject: [PATCH] Record Raven Kimodo provisioning --- state/evidence.jsonl | 1 + 1 file changed, 1 insertion(+) diff --git a/state/evidence.jsonl b/state/evidence.jsonl index 1bad344..a4cc45f 100644 --- a/state/evidence.jsonl +++ b/state/evidence.jsonl @@ -348,3 +348,4 @@ {"ts":"2026-06-11T21:32:25Z","type":"implementation","status":"ok","note":"Reworked persona friendly intake projection so memories, affect, bonds, doctrine, agency pressure, and actions read as human-editable cards with compact source blocks instead of raw typed-state schema dumps; regenerated Sai and Metame examples."} {"ts":"2026-06-11T21:39:59Z","type":"implementation","status":"ok","note":"Changed friendly Persona intake export to omit per-item source/provenance by default, with --include-source as the opt-in forensic path. Regenerated Sai and Metame so memory sections read as compact human-editable cards."} {"ts":"2026-06-12T10:09:54Z","type":"research","status":"ok","note":"Distilled RPG cinematic-dialogue production patterns from Mass Effect 2, Witcher 3/Cyberpunk quest design, Witcher 3 dialogue tooling, and AC Odyssey procedural dialogue sources into docs/research/rpg-sprawl-limited-animation-budget.md for Ghostlight scenario-runner design."} +{"ts":"2026-06-12T11:08:21Z","type":"implementation","status":"ok","note":"Provisioned Raven as the Kimodo GPU target: enabled WSL2/VirtualMachinePlatform, installed Ubuntu 24.04 WSL, installed Docker Engine plus NVIDIA container toolkit inside WSL, verified CUDA container GPU access, cloned Kimodo, built gamecult/kimodo:latest with a Raven-local filter removing missing kimodo-viser, and confirmed kimodo_gen reaches CUDA but generation is blocked on missing Hugging Face gated Llama 3 token."}