From dc42ecc235816bde0b22e12fc9149bf10b37919f Mon Sep 17 00:00:00 2001
From: root <root@abiba.dns.sysloggh.net>
Date: Sat, 12 Sep 2026 15:56:16 +0000
Subject: [PATCH] no-mistakes(document): Align gpu-vision and
 single-source-of-truth documentation

---
 README.md               | 2 +-
 docs/AUTHORING-GUIDE.md | 2 +-
 gpu-fleet.prose.md      | 7 +++----
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 46b8968..ac61914 100644
--- a/README.md
+++ b/README.md
@@ -88,7 +88,7 @@ prose run memory-audit-maintenance memory_threshold=90 verify_configs=true
 prose run hermes-config-template agent_name=syslog-devops default_model=claude-sonnet-4
 
 # Configure an agent with a different auxiliary model
-prose run hermes-config-template agent_name=syslog-code default_model=qwen3.6-27B-code auxiliary_model=gemma-4-12b
+prose run hermes-config-template agent_name=syslog-code default_model=qwen3.6-27B-code auxiliary_model=gpu-vision
 ```
 
 ### Option B: Manual Execution
diff --git a/docs/AUTHORING-GUIDE.md b/docs/AUTHORING-GUIDE.md
index f73129e..adf2f78 100644
--- a/docs/AUTHORING-GUIDE.md
+++ b/docs/AUTHORING-GUIDE.md
@@ -13,7 +13,7 @@ the description:
 
 1. **What system does this contract touch?** Name the hosts, CTs, containers,
    and services explicitly. "The inference fleet" is vague. "GPU .8 (RTX 3090,
-   qwen), .110 (RTX 5070, gemma), .15 (Strix Halo, strix-moe), and LiteLLM on CT
+   qwen), .110 (RTX 5070, gpu-vision), .15 (Strix Halo, strix-moe), and LiteLLM on CT
    116" is specific.
 
 2. **Who runs this contract, and when?** State the agent, the trigger (cron,
diff --git a/gpu-fleet.prose.md b/gpu-fleet.prose.md
index 04cd136..fefebba 100644
--- a/gpu-fleet.prose.md
+++ b/gpu-fleet.prose.md
@@ -25,7 +25,7 @@ triggers:
 
 ## Maintains
 
-- gpu_roster: { models: map, hosts: map } — Single source of truth for all GPU models
+- gpu_roster: { models: map, hosts: map } — GPU host/model roster; the authoritative alias/weight/fallback registry is CT 116 `litellm_config.yaml`
 - router: { status: "healthy", roster_loaded: bool, models: array }
 - litellm: { status: "healthy", keys: array, models: array }
 - agent_keys: { agent: api_key } — All agent API keys registered in LiteLLM DB
@@ -97,9 +97,8 @@ is retired and returns 400 `Invalid model name`.
 
 ## Routing Configuration (LiteLLM — July 2026)
 
-Single source of truth for models, aliases, rpm caps, weights and fallback chains:
-CT 116 `/opt/inference-harness/litellm_config.yaml`. Do not duplicate those values in
-contracts — read them there.
+Model, alias, rpm/weight and fallback values are owned by CT 116
+`/opt/inference-harness/litellm_config.yaml` (see § Stable Role-Based Aliases above).
 
 Note: All syslog-auto entries route directly to GPUs with `api_key: not-needed`. The router (port 9000) was decommissioned 2026-09-11 and is NOT in the inference path.