hermes-config-template.prose.md

@@ -143,23 +143,25 @@ compression:
 
 # ─── Auxiliary Tasks (CONSISTENCY RULE) ───
 # All auxiliary services MUST use identical model, base_url, and api_key_env:
-#   model: gemma-4-12b
+#   model: gpu-light                 # stable alias (NOT raw "gemma-4-12b")
 #   base_url: http://192.168.68.116/v1
 #   api_key_env: LITELLM_API_KEY
 # Do NOT use syslog-auto for auxiliary tasks — it routes to the primary GPU.
-# gemma-4-12b is a lightweight 12B model on the RTX 5070, freeing the Strix Halo
+# gpu-light = RTX 5070 (12B), freeing the Strix Halo for agent reasoning.
-# for agent reasoning.
+# Heavy aux (delegation, x_search) use gpu-dense (RTX 3090) instead.
+# NEVER use raw model names (gemma-4-12b, qwen3.6-27B-code, qwen3.6-35B-udq4)
+# in agent configs — use the stable aliases so model swaps don't break agents.
 auxiliary:
   vision:
     provider: harness
-    model: gemma-4-12b
+    model: gpu-light            # stable alias for RTX 5070 (was raw gemma-4-12b)
     base_url: http://192.168.68.116/v1
     api_key_env: LITELLM_API_KEY
     timeout: 60
     download_timeout: 30
   web_extract:
     provider: harness
-    model: gemma-4-12b
+    model: gpu-light            # stable alias for RTX 5070
     base_url: http://192.168.68.116/v1
     api_key_env: LITELLM_API_KEY
     timeout: 30
@@ -170,10 +172,19 @@ auxiliary:
     api_key_env: LITELLM_API_KEY
     timeout: 300                 # gpu-fleet: 300s for large-history summarization (was 60)
 
+# ─── Delegation / Heavy Aux (use gpu-dense = RTX 3090) ───
+# delegation.model and x_search.model use gpu-dense (NOT raw qwen3.6-27B-code).
+
+delegation:
+  model: gpu-dense              # stable alias for RTX 3090 (was raw qwen3.6-27B-code)
+  provider: harness
+  base_url: http://192.168.68.116/v1
+  api_key_env: LITELLM_API_KEY
+
 # ─── Custom Provider ───
 custom_providers:
   - name: harness
-    model: <agent_model>
+    model: syslog-auto            # weighted pool (default)
     base_url: http://192.168.68.116/v1
     api_key_env: LITELLM_API_KEY
     api_mode: chat_completions

litellm-self-heal.prose.md

@@ -69,7 +69,8 @@ Request → nginx:80 → LiteLLM:4000 → GPU(llama-server, parallel 2)
 
 - `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']`. Note `qwen3.6-35B-udq4` is NOT in the agent-key allowlist — agents must use `strix-moe` to reach the AMD model.
+- 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.
+- **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)