From 9bc29508d7320091d67115d68570c138c2198c29 Mon Sep 17 00:00:00 2001
From: Hermes Agent service account
 <hermes@carousel-of-progress.local.mk-labs.cloud>
Date: Fri, 28 Aug 2026 21:00:47 -0500
Subject: [PATCH] hindsight: move LLM to local astro-orbiter Qwen3.8-27B (off
 Nous free tier)

---
 cluster/applications/hindsight/values.yaml | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/cluster/applications/hindsight/values.yaml b/cluster/applications/hindsight/values.yaml
index ee780d1..ba5c825 100644
--- a/cluster/applications/hindsight/values.yaml
+++ b/cluster/applications/hindsight/values.yaml
@@ -49,18 +49,19 @@ existingSecret: hindsight-credentials
 
 # ----------------------------------------------------------------------------
 # API container environment (explicit env entries; the chart renders this map
-# to individual env vars). LLM points at the Nous free-tier inference API
-# (OpenAI-compatible). HINDSIGHT_API_LLM_API_KEY is NOT set here — it comes from
-# the existingSecret via envFrom (1Password `nous` item).
+# to individual env vars). LLM points at the LOCAL astro-orbiter Qwen node
+# (OpenAI-compatible) — moved OFF the Nous free tier (solar-pro4 was 404/dead).
+# HINDSIGHT_API_LLM_API_KEY is NOT set here — it comes from the existingSecret
+# via envFrom (1Password `nous` item); the local node ignores it but the secret
+# still satisfies the chart's envFrom contract.
 # ----------------------------------------------------------------------------
 api:
   env:
-    HINDSIGHT_API_LLM_BASE_URL: "https://inference-api.nousresearch.com/v1"
+    HINDSIGHT_API_LLM_BASE_URL: "http://astro-orbiter:8001/v1"
     HINDSIGHT_API_LLM_PROVIDER: "openai"
-    # Primary LLM. Timeout raised to 300s (ingress) so a slow agentic reflect
-    # (~132s on solar-pro4) completes; verified tool-calling + grounded output.
-    HINDSIGHT_API_LLM_MODEL: "upstage/solar-pro4:free"
-    # Fallback (documented, NOT deployed): stepfun/step-3.7-flash:free
+    # Primary LLM: local astro-orbiter Qwen3.8-27B-Q4_K_M (LAN-fast, off Nous free tier).
+    HINDSIGHT_API_LLM_MODEL: "Qwen3.8-27B-Q4_K_M"
+    # Fallback (documented, NOT deployed): upstage/solar-pro4:free (Nous) — use if the local node is ever down.
 
 # ----------------------------------------------------------------------------
 # Ingress via the chart's native template.