diff --git a/cluster/applications/hindsight/externalsecret.yaml b/cluster/applications/hindsight/externalsecret.yaml index 1787622..1813803 100644 --- a/cluster/applications/hindsight/externalsecret.yaml +++ b/cluster/applications/hindsight/externalsecret.yaml @@ -69,9 +69,11 @@ spec: remoteRef: key: hindsight property: HINDSIGHT_API_MCP_AUTH_TOKEN - # 1Password item "hindsight", field "HINDSIGHT_API_LLM_API_KEY" - # (literal "local-placeholder" — astro-orbiter does not validate, D1) + # 1Password item "nous" (vault mk-labs), field "api-key" (Ryan-provisioned, + # decision 4). Replaces the prior "local-placeholder" value — astro-orbiter + # did not validate; now wired to the Nous free-tier inference API. Materialized + # Secret key name stays HINDSIGHT_API_LLM_API_KEY (env-var-named, envFrom). - secretKey: HINDSIGHT_API_LLM_API_KEY remoteRef: - key: hindsight - property: HINDSIGHT_API_LLM_API_KEY + key: nous + property: api-key diff --git a/cluster/applications/hindsight/values.yaml b/cluster/applications/hindsight/values.yaml index bdf1205..2008ad0 100644 --- a/cluster/applications/hindsight/values.yaml +++ b/cluster/applications/hindsight/values.yaml @@ -12,9 +12,12 @@ # HINDSIGHT_API_LLM_API_KEY / HINDSIGHT_API_MCP_AUTH_TOKEN are injected # automatically; POSTGRES_PASSWORD is a secretKeyRef that K8s expands into # HINDSIGHT_API_DATABASE_URL (verified with a live envFrom test pod). -# - LLM is the local OpenAI-compatible astro-orbiter endpoint (VLAN service -# `astro-orbiter:8001`), model pinned to the bare id (no `openai/` prefix — -# that form 404s on the local router). +# - 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 +# 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 # plan: "Ingress driven through values.yaml"). api.service.port=8888, # controlPlane.service.port=3000. @@ -46,15 +49,16 @@ existingSecret: hindsight-credentials # ---------------------------------------------------------------------------- # API container environment (explicit env entries; the chart renders this map -# to individual env vars). LLM points at the local astro-orbiter OpenAI- -# compatible server. HINDSIGHT_API_LLM_API_KEY is NOT set here — it comes from -# the existingSecret via envFrom. +# 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). # ---------------------------------------------------------------------------- api: env: - HINDSIGHT_API_LLM_BASE_URL: "http://astro-orbiter:8001/v1" + HINDSIGHT_API_LLM_BASE_URL: "https://inference-api.nousresearch.com/v1" HINDSIGHT_API_LLM_PROVIDER: "openai" - HINDSIGHT_API_LLM_MODEL: "Qwen3.8-27B-Q4_K_M" + # Primary LLM. Fallback (documented, NOT deployed): solar-pro4:free + HINDSIGHT_API_LLM_MODEL: "stepfun/step-3.7-flash:free" # ---------------------------------------------------------------------------- # Ingress via the chart's native template.