memory: R22 stood down to gateway, full-access key minted, Phase B parked; phantom qwen3.6 entry to clean

persistent-memory.md

@@ -291,6 +291,23 @@ _As of 2026-06-20:_
 
 ## Recent decisions
 
+- `[2026-06-20]` **R22 (brokkr/eitri/dwarves) stood down to gateway; full-access R22
+  key minted; Phase B parked.** Operator caught the raw-weights/GPU ask as premature —
+  Phase A (P00 + NL-rendering) is PROMPT-LEVEL on the LiteLLM gateway, not raw weights
+  (no GPU, no Blackwell displacement). Real blocker was gateway ACCESS: the shared
+  `all-agents-local` key only serves granite chat, and granite-8b is too weak to be the
+  P00 model-under-test (capability-confound). Operator said "full access" → minted
+  `r22-brokkr-phaseA` LiteLLM key (scope **all-proxy-models**, incl PAID GLM), dropped
+  `~/.r22-gateway-key` (mode 600) for eitri. **P00 MUT = `qwen3.5-122-a10b` (alias
+  `gen`)** — 122B, capable, FREE-LOCAL (no per-token cost); told them keep frozen
+  calibration on it, NOT the paid GLM the key can now reach. **PHASE B** (raw-weights
+  hooks: Dvalin activation-steering on hidden states + Regin ECM logit-injection on a
+  7-8B Qwen/Llama via transformers LogitsProcessor) **PARKED until P00 PASS** → fits the
+  irv-ml1 A6000 ~18GB slice, NO Blackwell displacement; they'll send sizing + grant
+  claude-bot read on vh/brokkr-smithy at P00-PASS. **FOLLOW-UP: clean phantom
+  `qwen3.6-35b-a3b` off the gateway** (shows in /v1/models but 400s "invalid model" —
+  backend displaced 2026-06-19; the no-false-alias footgun).
+
 - `[2026-06-20]` **claude-bot issue-scope token minted for worldtree-dev self-serve**
   (closes their last `tea`-as-vh fallback — issues; they already self-serve Actions +
   deploys). Gitea PAT scopes are IMMUTABLE → minted a NEW claude-bot PAT