diff --git a/gpu-fleet.prose.md b/gpu-fleet.prose.md
index f3b4aab..847c589 100644
--- a/gpu-fleet.prose.md
+++ b/gpu-fleet.prose.md
@@ -220,7 +220,8 @@ If no SSH access, send Zulip DM via abiba-bot with vault update instructions.
 | `/root/scripts/gpu_benchmark.py` | pi (.24) | GPU inference benchmark module (tok/s tracking) |
 | `/root/scripts/gpu-saturation-watchdog.py` | pi (.24) | Auto-restart stuck llama-server |
 | `/root/dashboard/gpu-fleet.html` | pi (.24) | Live HTML dashboard |
-| `/etc/systemd/system/llama-server.service` | .8, .110 | llama-server daemons (Nvidia GPUs) |
+| `/etc/systemd/system/llama-chat-api.service` | .8 | RTX 3090 GPU daemon — active unit since 2026-09-06; the old `llama-server.service` file on .8 is stale/inactive |
+| `/etc/systemd/system/llama-server.service` | .110 | llama-server daemon (RTX 5070) |
 | `/etc/systemd/system/strix-server.service` | .15 (amdpve) | llama-server daemon (Vulkan, Strix Halo) running unsloth/Qwen3.6-35B-A3B-MTP-GGUF. Note: `llama-server.service` and `llama-server@.service` are **masked** on .15 to prevent port 8080 collisions. |
 
 ## Prometheus & Grafana
diff --git a/infrastructure-control.prose.md b/infrastructure-control.prose.md
index fe3e350..65b87fe 100644
--- a/infrastructure-control.prose.md
+++ b/infrastructure-control.prose.md
@@ -593,7 +593,7 @@ curl -s -X POST http://192.168.68.116:9000/admin/roster/reload \
   -H "Authorization: Bearer sk-admin-ee09fffd04978b61a1569ac670c68814"
 
 # Restart stuck GPU (saturation watchdog alternative)
-ssh root@192.168.68.8 "systemctl restart llama-server"
+ssh root@192.168.68.8 "systemctl restart llama-chat-api.service"   # .8 active unit since 2026-09-06; llama-server.service file on .8 is stale/inactive
 ssh root@192.168.68.110 "systemctl restart llama-server"
 ```
 
diff --git a/litellm-self-heal.prose.md b/litellm-self-heal.prose.md
index c7680a8..66972b1 100644
--- a/litellm-self-heal.prose.md
+++ b/litellm-self-heal.prose.md
@@ -113,7 +113,7 @@ Preferred implementation: uncap shared pool, add capped alias for crew-only.
 
 - **Health-check script** (`/opt/inference-harness/scripts/litellm-health-check.sh` on CT 116): `gpu-fleet` check fails only on **critical** alerts (warnings are informational). Tests `strix-moe` (not `ornith-1.0-35b`).
 - **GPU monitor** (`/root/scripts/gpu-monitor-server.py` on pi .24): runs as **systemd unit `gpu-monitor.service`** (was bare `&` process). `gpu_count` includes Strix Halo (was 2, now 3). VRAM alert thresholds: warning 93%, critical 97% (raised from 90/95 — 128K context steady-state is ~70% on RTX 3090, not a fault).
-- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): v2 (2026-07-26) — reads each agent's **agent-specific** `{NAME}_LITELLM_API_KEY` from Infisical vault (not the shared master key). Covers: LiteLLM keys, GPU ports, agent gateways (all 5 agents now SSHa ble), CT liveness (pct status on PVE nodes), config.yaml YAML integrity, wrapper/CLI integrity, vault secret non-emptiness checks. Fleet roster: tanko (.122), mumuni (.24, inside abiba CT100), koby (.129), koonimo (.114), abiba (.24). Legacy `tdunna`/`baggy` replaced with canonical agent hostnames.
+- **Agent key monitor** (`/root/scripts/agent-health-check.py` on pi .24, cron `*/10`): v3 (2026-09-08) — vault-backed agents (tanko/koby/koonimo) read their **agent-specific** `{NAME}_LITELLM_API_KEY` from Infisical vault (not the shared master key); abiba (pi agent) reads `LITELLM_API_KEY` from its local `/root/.pi/agent/env.sh` (#735 — moved out of shared `/root/.bashrc`), not from the vault. Covers: LiteLLM keys, GPU ports, agent gateways (all 5 agents now SSHa ble), CT liveness (pct status on PVE nodes), config.yaml YAML integrity, wrapper/CLI integrity, vault secret non-emptiness checks. Fleet roster: tanko (.122), mumuni (.24, inside abiba CT100), koby (.129), koonimo (.114), abiba (.24). Legacy `tdunna`/`baggy` replaced with canonical agent hostnames.
 - **Stale keys cleaned**: `daily-infra-report.py` SYNTHETIC_API_KEY was stale (`sk-U_ydi3B` → 401); now reads `LITELLM_MASTER_KEY` from env. Deprecated scripts (`router-original.py`, `router-phase0-backup.py`, `apply-fixes.py`) still reference `sk-syslog-local-master-key` but do not actively poll LiteLLM.
 
 ## Maintains