From 9bfc9384e4426f3d517e60d8be4d8d9290c84209 Mon Sep 17 00:00:00 2001 From: Hermes Agent service account Date: Tue, 25 Aug 2026 12:05:54 -0500 Subject: [PATCH] hindsight: re-promote upstage/solar-pro4:free as primary LLM (ingress timeout fixed) Ingress proxy timeout now 300s (commit 152230c), so a slow agentic reflect (~132s) completes before nginx cuts the connection. solar-pro4:free passed tool-calling + grounded-output probes (t_d0dffc3d). BASE_URL/PROVIDER unchanged; fallback comment -> stepfun/step-3.7-flash:free. Refs t_e3375410. --- cluster/applications/hindsight/values.yaml | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/cluster/applications/hindsight/values.yaml b/cluster/applications/hindsight/values.yaml index 4081a42..ee780d1 100644 --- a/cluster/applications/hindsight/values.yaml +++ b/cluster/applications/hindsight/values.yaml @@ -14,8 +14,8 @@ # HINDSIGHT_API_DATABASE_URL (verified with a live envFrom test pod). # - LLM is the Nous free-tier inference endpoint # (https://inference-api.nousresearch.com/v1), model -# `stepfun/step-3.7-flash:free` (mandatory reasoning, 262K ctx). Fallback -# (documented, NOT deployed): `solar-pro4:free`. API key via existingSecret +# `upstage/solar-pro4:free` (tool-calling, verified reflect). Fallback +# (documented, NOT deployed): `stepfun/step-3.7-flash:free`. API key via existingSecret # envFrom (hindsight-credentials / HINDSIGHT_API_LLM_API_KEY), sourced from # 1Password `nous` item per decision 4. # - Ingress is driven through the chart's NATIVE ingress template (approved @@ -57,8 +57,10 @@ api: env: HINDSIGHT_API_LLM_BASE_URL: "https://inference-api.nousresearch.com/v1" HINDSIGHT_API_LLM_PROVIDER: "openai" - # Primary LLM. Fallback (documented, NOT deployed): solar-pro4:free - HINDSIGHT_API_LLM_MODEL: "stepfun/step-3.7-flash:free" + # 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 # ---------------------------------------------------------------------------- # Ingress via the chart's native template.