memory: Worldtree reward config live on demo+personal; Blender MCP registration is per task (Prime)

persistent-memory.md

@@ -142,6 +142,17 @@ _As of 2026-09-27 ~0900 PT._
   commissioning misbehaves, the UniFi mDNS reflector on esh-iot is the first knob
   (a Prime/infra-ops change). → `servers/esh-matter/README.md`
 
+### Worldtree reward path: code + config live (2026-09-27, Prime)
+
+- `d8726a13` (Domari's Skywork/Selene fix) was ALREADY on origin/main when Prime said to push it: it
+  was pushed as part of `79cce92f` at 1221. Demo runs image `79cce92f`. **Personal still runs
+  `51168a2e`**, which is older and lacks the fix; its image follows worldtree CI, never a manual up.
+- `deploy-wt-config` deployed demo and personal (1437): `providers.yaml` `reward_models.scalar-judge`
+  (6d4ac44), plus a77639d's corrected selene description, which had never reached the hosts. Both
+  are healthy, with 0 drift. It is inert on personal until that image picks up d8726a13.
+- ⚠ worldtree-instance-configs has **6 unpushed local commits** (53349f8…6d4ac44, from Aug 2 to
+  Sep 27). The hosts match the repo, but origin is behind. Pushing is Prime's call.
+
 ### SemIf on fv-ml1 GPU 1 (2026-09-27, Prime)
 
 - **LIVE: `semif-serve` 0.1.4** (was 0.1.3 until 1014 on 2026-09-27) at `http://10.251.50.54:8032` (`semif.fv.internal`), with order averaging
@@ -184,7 +195,7 @@ _As of 2026-09-27 ~0900 PT._
   server runs INSIDE the container, and agents reach it as ssh+docker-exec stdio via
   `scripts/blender-mcp`. No port is published, and screenshots work because server and Blender
   share a filesystem. Telemetry is off and safe mode is on. Verified end to end (render, screenshot,
-  safe-mode refusal). **Not yet registered in any Claude Code config**; that is Prime's call.
+  safe-mode refusal). **Registration: PER TASK (Prime, 2026-09-27)**: a session that needs Blender runs `claude mcp add blender -- …/scripts/blender-mcp`. It goes in NO user- or project-wide config.
   → `stacks/blender/README.md`
 
 ### Zigbee2MQTT on esh-docker-vm (2026-09-27, Prime go-ahead; ha-dev request)

stacks/blender/README.md

@@ -73,7 +73,7 @@ not a sandbox.
 ```bash
 scripts/blender-mcp up          # GPU 3 is borrowed: start only when needed
 scripts/blender-mcp status      # wait for "mcp add-on: answering" (~10-40 s)
-claude mcp add blender -- /home/lkraven/development/eshpfi-management/scripts/blender-mcp   # once per session/scope
+claude mcp add blender -- /home/lkraven/development/eshpfi-management/scripts/blender-mcp   # PER TASK (Prime 2026-09-27): never user/project-wide
 scripts/blender-mcp down        # when finished: the card goes back to 0
 ```