hindsight: swap LLM astro-orbiter Qwen3.8-27B -> Nous free-tier stepfun/step-3.7-flash:free (t_90261bb1)
- values.yaml: HINDSIGHT_API_LLM_BASE_URL -> https://inference-api.nousresearch.com/v1, MODEL -> stepfun/step-3.7-flash:free (fallback solar-pro4:free documented, not deployed) - externalsecret.yaml: HINDSIGHT_API_LLM_API_KEY remoteRef -> 1Password nous/api-key (replaces local-placeholder) - PROVIDER stays openai; API key via envFrom, never plaintext per decision 4
This commit is contained in:
@@ -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
|
||||
|
||||
@@ -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.
|
||||
|
||||
Reference in New Issue
Block a user