fix(audit): reject retired aliases; sweep gpu-light/gemma-4-12b to gpu-vision

audit-hermes-config.py Rule 8 required auxiliary.vision.model and
auxiliary.web_extract.model to equal the retired 'gpu-light', so a config
adopting the live canonical 'gpu-vision' FAILED our own audit - the audit was
enforcing a dead alias (400 Invalid model name). Rule 8 now requires
gpu-vision; retired names gpu-light/crew-auto join the raw-name rejection set;
the guidance message names the live aliases.

Sweep of the remaining references: gpu-self-heal stops canonicalizing
gpu-light; hermes-config-template, hermes-agent-baseline, hermes-key-enforcement,
inference-optimization, litellm-client-timeouts and gpu-fleet now use the live
gpu-vision alias. Where a file restated model/rpm/weight/fallback state it now
points at CT 116 /opt/inference-harness/litellm_config.yaml instead of
duplicating it. koby's .129 config is report-only and recorded, not edited.

Adds tests/test_audit_hermes_config_alias.py: executes the audit CLI and asserts
gpu-vision passes while gpu-light and gemma-4-12b fail.

litellm-client-timeouts.prose.md

@@ -28,7 +28,7 @@ description: >
 | syslog-auto | 28.8s | 25.4s | 68 calls took 30-120s; tail to ~300s under load |
 | qwen3.6-27B-code | 23.0s | — | same backend class as syslog-auto |
 | strix-moe | 7.5s | — | Strix Halo, healthy |
-| gemma-4-12b | 2.6s | — | RTX 5070, healthy |
+| gpu-vision | 2.6s | — | RTX 5070, healthy |
 
 Sep 6 incident timeline: failures 04:00-07:00 EDT (0% GPU util = wedged
 backend), full recovery 07:00-08:00 with ZERO client failures once requests
@@ -53,7 +53,7 @@ proxy queuing.
 
 ### 2. Auxiliary tasks — keep template timeouts, one correction
 
-- vision: 60s (keep), web_extract: 30s (keep) — gemma-4-12b averages 2.6s;
+- vision: 60s (keep), web_extract: 30s (keep) — gpu-vision averages 2.6s;
   these are fine.
 - compression: 300s (keep — this was already raised from 60 per gpu-fleet).
 - **gpu-dense delegation/x_search: set timeout >= 120s.** The RTX 3090