diff --git a/gpu-fleet.prose.md b/gpu-fleet.prose.md
index e539ee4..6f2b80b 100644
--- a/gpu-fleet.prose.md
+++ b/gpu-fleet.prose.md
@@ -83,10 +83,11 @@ When a model is swapped on a GPU, ONLY the infrastructure layer changes — agen
 |-------|-----|---------------|---------------|
 | `strix-moe` | Strix Halo (.15) | qwen3.6-35B-udq4 | Whatever runs on Strix Halo |
 | `gpu-dense` | RTX 3090 (.8) | Qwen3.8-27B-Uncensored-Q4_K_M | Whatever runs on RTX 3090 |
-| `gpu-light` | RTX 5070 (.110) | gemma-4-12b | Whatever runs on RTX 5070 |
+| `gpu-vision` | RTX 5070 (.110) | gpu-vision | Whatever runs on RTX 5070 |
 
-**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, gemma-4-12b, qwen3.5-9b-it) still work
-but are deprecated for agent configs. Only the stable aliases survive model swaps.
+**Backward compatibility**: Old model-specific names (qwen3.6-27B-code, qwen3.5-9b-it) still work
+but are deprecated for agent configs. Only the stable aliases survive model swaps. `gemma-4-12b`
+is retired and returns 400 `Invalid model name`.
 
 ## Current Model Assignments (2026-07-15)
 
@@ -114,13 +115,12 @@ Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`.
 |-------|---------|-----------|---------|
 | `strix-moe` | 40 | Strix Halo | Compression tasks (MoE models) |
 | `gpu-dense` | 500 | RTX 3090 | Heavy reasoning |
-| `gpu-light` | 500 | RTX 5070 | Vision, web extract, light tasks |
+| `gpu-vision` | 500 | RTX 5070 | Vision, web extract, light tasks |
 
-### Fallback Chains
-- gemma → qwen
-- qwen → gemma
-- strix-moe → qwen → gemma
-- syslog-auto → qwen → gemma → qwen3.6-35B-udq4
+### Fallback Chains (live `router_settings.fallbacks`, request_timeout 300s throughout)
+- syslog-auto → qwen3.6-27B-code → strix-moe → gpu-vision
+- qwen3.6-27B-code → strix-moe
+- strix-moe → qwen3.6-27B-code → gpu-vision
 
 ### Why Strix Halo RPM Is Capped
 - Direct (strix-moe): 40 RPM (tight) — Strix Halo is shared with compression tasks
@@ -266,9 +266,9 @@ History stored at `/root/data/toks-history.json` with 7-day rolling window.
 
 All agent configs MUST use stable role-based aliases, never model-specific names:
 - `compression.model: strix-moe` (NOT `qwen3.6-35B-udq4`)
-- `auxiliary.vision.model: gpu-light` (NOT `gemma-4-12b`)
+- `auxiliary.vision.model: gpu-vision` (NOT `gemma-4-12b`)
 - `delegation.model: gpu-dense` (NOT `qwen3.6-27B-code`)
-- `auxiliary.web_extract.model: gpu-light`
+- `auxiliary.web_extract.model: gpu-vision`
 
 When the underlying model is swapped, only the LiteLLM config changes — agent configs are untouched.
 
@@ -285,12 +285,12 @@ Mumuni (kagentz CT105, 192.168.68.14 — migrated from CT100 2026-08-29) is the
 
 | Setting | Value | Notes |
 |---------|-------|-------|
-| `model.default` | `syslog-auto` | Weighted pool (55% qwen, 30% strix, 15% gemma) |
+| `model.default` | `syslog-auto` | Weighted pool (70% qwen, 20% strix, 10% gpu-vision) |
 | `model.provider` | `custom:litellm` | LiteLLM on CT116 |
 | `compression.model` | `strix-moe` | Stable alias — survives model swaps |
 | `aux.compression.model` | `strix-moe` | Compression auxiliary model |
-| `aux.vision.model` | `gpu-light` | Vision tasks (RTX 5070) |
-| `aux.web_extract.model` | `gpu-light` | Web extraction |
+| `aux.vision.model` | `gpu-vision` | Vision tasks (RTX 5070) |
+| `aux.web_extract.model` | `gpu-vision` | Web extraction |
 | `delegation.model` | `gpu-dense` | Sub-agent reasoning (RTX 3090) |
 | `context.max_context_window` | 131072 (128K) | Reduced from 256K 2026-07-17 — stable 128K ceiling |
 | `compression.threshold` | 0.60 | Triggers at ~77K (~60% of 128K) — optimized for 128K context |
diff --git a/litellm-health.prose.md b/litellm-health.prose.md
index c4e383f..f0134a2 100644
--- a/litellm-health.prose.md
+++ b/litellm-health.prose.md
@@ -149,21 +149,26 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
    - Verify GPUs reporting status "healthy"
    - Check alerts array for active warnings/critical
 
-7. **Check model inference via LiteLLM** — Test one model on each GPU host:
-   - POST /v1/chat/completions model=qwen3.6-27B-code → expect 200 (RTX 3090, .8)
-   - POST /v1/chat/completions model=gpu-vision → expect 200 (RTX 5070, .110)
-   - POST /v1/chat/completions model=strix-moe → expect 200 (Strix Halo, .15)
-   - Use master key for auth
+7. **Check model inference via LiteLLM** — Test one model on each GPU host. The health
+   check runs on the **backend edge**, not the public edge, so these paths carry the
+   `/litellm/` prefix:
+   - POST http://{{backend_host}}/litellm/v1/chat/completions model=qwen3.6-27B-code → expect 200 (RTX 3090, .8)
+   - POST http://{{backend_host}}/litellm/v1/chat/completions model=gpu-vision → expect 200 (RTX 5070, .110)
+   - POST http://{{backend_host}}/litellm/v1/chat/completions model=strix-moe → expect 200 (Strix Halo, .15)
+   - Auth uses the dedicated `monitor` agent key, read on CT 116 from
+     `/etc/litellm-monitor.env` (root-only 0600). Do NOT use the master key for inference —
+     the master key is for admin endpoints only (`/key/list`, `/key/generate`, `/key/info`).
    - `gemma-4-12b` was retired and returns 400 `Invalid model name` — do not re-add it to
      this list. The RTX 5070 host now serves `gpu-vision`.
    - `/v1/models` is **key-scoped**: a model is only visible to keys allowed to use it, so
      an agent key can return a different set than the master key. Always state which key a
-     model list was read with. Verified 2026-09-12 with the master key:
+     model list was read with. Verified 2026-09-12 on the backend surface
+     (`http://{{backend_host}}/litellm/v1/models`) with the `monitor` key:
      `qwen3.6-27B-code`, `gpu-vision`, `gpu-dense`, `qwen3.6-35B-udq4`,
      `qwen3.8-27B-uncensored`, `strix-moe`, `syslog-auto`.
 
 8. **Check agent keys**:
-   - GET /key/list with master key → verify all 6 agents have keys
+   - GET http://{{backend_host}}/litellm/key/list with master key (admin endpoint) → verify all 6 agents have keys
 
 9. **Check Grafana**:
    - GET {{grafana_url}}/api/health → expect 200
diff --git a/litellm-self-heal.prose.md b/litellm-self-heal.prose.md
index f961460..3768941 100644
--- a/litellm-self-heal.prose.md
+++ b/litellm-self-heal.prose.md
@@ -61,14 +61,14 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 | Host | IP | Hardware | Models Served | Engine | Context | Parallel |
 |------|-----|----------|---------------|--------|---------|----------|
 | llm-gpu | 192.168.68.8 | NVIDIA RTX 3090 (24 GB) | qwen3.6-27B-code | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `-c 131072 --parallel 2 --ngl 99`) | **128K** | 2 |
-| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gemma-4-12b | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `--ctx-size 131072 --parallel 2`, IQ4_NL + MTP draft) | **128K** | 2 |
+| ocu-llm | 192.168.68.110 | NVIDIA RTX 5070 (12 GB) | gpu-vision | llama-server systemd (`/home/llmuser/llama-wrapper.sh`, `--ctx-size 131072 --parallel 2`, IQ4_NL + MTP draft) | **128K** | 2 |
 | amdpve | 192.168.68.15 | AMD Strix Halo 64GB UMA | qwen3.6-35B-udq4 (LiteLLM alias: `strix-moe`) | llama-server systemd (Vulkan) | 128K | 2 |
 
 > Verified on ground 2026-07-16 via `curl /v1/models` on each host + `llama-wrapper.sh`. The AMD host's underlying model is `qwen3.6-35B-udq4`; LiteLLM exposes it under two `model_name`s: `qwen3.6-35B-udq4` and `strix-moe` (rpm 40). The legacy name `ornith-1.0-35b` does NOT exist in LiteLLM and must not be referenced.
 
 ## LiteLLM Model Surface (ground truth — `/opt/inference-harness/litellm_config.yaml` on CT 116)
 
-`model_name`s served: `qwen3.6-27B-code`, `gemma-4-12b`, `qwen3.6-35B-udq4`, `strix-moe`, `gpu-dense`, `gpu-light`, `syslog-auto`, `crew-auto` (new 2026-08-20).
+`model_name`s served (live registry, verified 2026-09-12 with the master key): `qwen3.6-27B-code`, `gpu-vision`, `gpu-dense`, `qwen3.6-35B-udq4`, `qwen3.8-27B-uncensored`, `strix-moe`, `syslog-auto`. `gemma-4-12b`, `gpu-light`, and `crew-auto` are retired and absent from the registry.
 
 ### Context Cap Split (2026-08-20)
 
@@ -78,19 +78,19 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 
 Preferred implementation: uncap shared pool, add capped alias for crew-only.
 
-- `syslog-auto` is a weighted router model: qwen3.6-27B-code (0.55, rpm 500) + qwen3.6-35B-udq4 (0.30, rpm 60) + gemma-4-12b (0.15, rpm 200).
-- `gpu-dense` / `gpu-light` are high-rpm aliases (rpm 500) onto qwen3.6-27B-code / gemma-4-12b respectively.
-- Key scoping: agent keys are restricted to `['syslog-auto','qwen3.6-27B-code','gemma-4-12b','strix-moe','gpu-dense','gpu-light']`. As of 2026-07-16 the `baggy`/`koby`/`mumuni`/`abiba-pi` keys ALSO include `qwen3.6-35B-udq4`; `abiba-pi` additionally includes `deepseek-v4-pro` (cloud fallback). `kagenz0`/`koonimo`/`pi-agents-unified` have the standard 6 only. Agents should still use the stable alias `strix-moe` (not the raw `qwen3.6-35B-udq4`) so model swaps don't break them.
+- `syslog-auto` is a weighted router model: qwen3.6-27B-code (0.70, rpm 500, api_base .8) + strix-moe (0.20, rpm 60, api_base .15) + gpu-vision (0.10, rpm 200, api_base .110).
+- `gpu-dense` is the high-rpm alias (rpm 500) onto qwen3.6-27B-code; `gpu-light` is retired — the RTX 5070 alias is now `gpu-vision`.
+- Key scoping: agent keys are restricted to `['syslog-auto','qwen3.6-27B-code','strix-moe','gpu-dense']`. As of 2026-07-16 the `baggy`/`koby`/`mumuni`/`abiba-pi` keys ALSO include `qwen3.6-35B-udq4`; `abiba-pi` additionally includes `deepseek-v4-pro` (cloud fallback). `kagenz0`/`koonimo`/`pi-agents-unified` have the standard set only. Agents should still use the stable alias `strix-moe` (not the raw `qwen3.6-35B-udq4`) so model swaps don't break them. `/v1/models` is key-scoped, so a model list is only meaningful with the key it was read with.
 - **NEVER use `litellm_proxy_master_key` (the `sk-litellm-...` master key) for inference.** It is for admin endpoints only (`/key/list`, `/key/generate`, `/key/info`). All inference — agent traffic, health-check model tests, monitor scripts — uses agent-specific keys. The health-check script's model tests use a dedicated `monitor` agent key stored at `/etc/litellm-monitor.env` on CT 116 (root-only, `chmod 600`); `/key/list` is the only call that legitimately uses `$MASTER_KEY`.
 
 ## Model Fallback Chains (LiteLLM)
 
-| Primary | Timeout | Fallback | Timeout |
-|---------|---------|----------|---------|
-| qwen3.6-27B-code | 300s | gemma-4-12b | 120s |
-| gemma-4-12b | 120s | qwen3.6-27B-code | 300s |
-| qwen3.6-35B-udq4 / strix-moe | 300s | qwen → gemma | — |
-| syslog-auto (balanced) | 300s | qwen → gemma | — |
+| Primary | Timeout | Fallback chain (live `router_settings.fallbacks`) | Timeout |
+|---------|---------|--------------------------------------------------|---------|
+| syslog-auto (balanced) | 300s | qwen3.6-27B-code → strix-moe → gpu-vision | 300s |
+| qwen3.6-27B-code | 300s | strix-moe | 300s |
+| strix-moe | 300s | qwen3.6-27B-code → gpu-vision | 300s |
+| gpu-vision | 300s | — (leaf) | — |
 
 > Global: request_timeout=300s, nginx proxy_read_timeout=600s
 
@@ -137,10 +137,19 @@ Preferred implementation: uncap shared pool, add capped alias for crew-only.
 
 Run this first on every cycle. Results feed into remediation rules below.
 
-### 1. Check public endpoints
-- GET {{public_url}}/litellm/ui/ → expect 200 ("LiteLLM Dashboard")  # served directly by nginx
-- GET {{public_url}}/litellm/docs → expect 200 ("LiteLLM API - Swagger UI")  # served directly by nginx
-- GET {{public_url}}/ui/ and {{public_url}}/docs → expect 301 → /litellm/... → 200 (one-hop redirect helpers, added 2026-09-11)
+### 1. Check the end-user surfaces
+The public edge and the backend edge serve the same app under different paths; they are not
+interchangeable, so every probe names the surface it targets.
+
+Public edge — `{{public_url}}` serves the app at the ROOT (the `/litellm/` prefix 404s):
+- GET {{public_url}}/ui/ → expect 200 ("LiteLLM Dashboard")
+- GET {{public_url}}/docs → expect 200 ("LiteLLM API - Swagger UI")
+- GET {{public_url}}/litellm/ui/ and {{public_url}}/litellm/docs → expect 404 (not served on this edge)
+
+Backend edge — `http://{{backend_host}}` (port 80) serves the app UNDER `/litellm/`:
+- GET http://{{backend_host}}/litellm/ui/ → expect 200 ("LiteLLM Dashboard")
+- GET http://{{backend_host}}/litellm/docs → expect 200 ("LiteLLM API - Swagger UI")
+- GET http://{{backend_host}}/ui/ and /docs → expect 301 → /litellm/... → 200 (one-hop redirect helpers, added 2026-09-11)
 
 ### 2. Check LiteLLM health (no-auth)
 - GET http://{{backend_host}}/litellm/health/liveliness → expect 200
@@ -158,14 +167,14 @@ Run this first on every cycle. Results feed into remediation rules below.
 - Verify GPUs reporting status "healthy"
 - Check alerts array for active warnings/critical
 
-### 5. Check model inference via LiteLLM — test each model
-- POST /v1/chat/completions model=gemma-4-12b → expect 200
-- POST /v1/chat/completions model=qwen3.6-27B-code → expect 200
-- POST /v1/chat/completions model=strix-moe → expect 200
-- Use master key for auth
+### 5. Check model inference via LiteLLM — test one model per GPU host (backend surface)
+- POST http://{{backend_host}}/litellm/v1/chat/completions model=qwen3.6-27B-code → expect 200 (RTX 3090, .8)
+- POST http://{{backend_host}}/litellm/v1/chat/completions model=gpu-vision → expect 200 (RTX 5070, .110)
+- POST http://{{backend_host}}/litellm/v1/chat/completions model=strix-moe → expect 200 (Strix Halo, .15)
+- Auth uses the dedicated `monitor` agent key, read on CT 116 from `/etc/litellm-monitor.env` (root-only 0600) — never the master key
 
 ### 6. Check agent keys
-- GET /key/list with master key → verify all 6 agents have keys
+- GET http://{{backend_host}}/litellm/key/list with master key (admin endpoint) → verify all 6 agents have keys
 
 ### 7. Check Grafana
 - GET {{grafana_url}}/api/health → expect 200