b3b925ff77
t_d7f8cd65 — astro-orbiter is a single serial llama-swap process; Hindsight's default LLM_MAX_CONCURRENT=32 burst N parallel retains -> node rejects/times out extras -> 502. Cap global + retain concurrency to 1 (native semaphore config, no code change). Raise client timeout 120->600s and ingress proxy-read/send 300->600s so a single long retain (~90s under load) survives.
126 lines
6.4 KiB
YAML
126 lines
6.4 KiB
YAML
# ============================================================================
|
|
# Hindsight — helm values (Phase C). Consumed by the ArgoCD Application source 1
|
|
# via `helm.valueFiles: ["$values/values.yaml"]` (openviking multi-source pattern).
|
|
#
|
|
# Design decisions (all verified against chart v0.9.1 + rendered output):
|
|
# - Chart is the single source for the app (api, control-plane, services,
|
|
# probes, ingress). We do NOT hand-roll Deployments/Services.
|
|
# - Postgres is EXTERNAL (separate Deployment in this dir, firecrawl pattern)
|
|
# => postgresql.enabled: false, external.* points at hindsight-postgres:5432.
|
|
# - Secrets come from 1Password via ExternalSecret => existingSecret:
|
|
# hindsight-credentials. The chart does envFrom(secretRef) so
|
|
# HINDSIGHT_API_LLM_API_KEY / HINDSIGHT_API_MCP_AUTH_TOKEN are injected
|
|
# automatically; POSTGRES_PASSWORD is a secretKeyRef that K8s expands into
|
|
# HINDSIGHT_API_DATABASE_URL (verified with a live envFrom test pod).
|
|
# - LLM is the Nous free-tier inference endpoint
|
|
# (https://inference-api.nousresearch.com/v1), model
|
|
# `upstage/solar-pro4:free` (tool-calling, verified reflect). Fallback
|
|
# (documented, NOT deployed): `stepfun/step-3.7-flash:free`. API key via existingSecret
|
|
# envFrom (hindsight-credentials / HINDSIGHT_API_LLM_API_KEY), sourced from
|
|
# 1Password `nous` item per decision 4.
|
|
# - Ingress is driven through the chart's NATIVE ingress template (approved
|
|
# plan: "Ingress driven through values.yaml"). api.service.port=8888,
|
|
# controlPlane.service.port=3000.
|
|
# - Image tag defaults to .Values.version (root) when api.image.tag is unset,
|
|
# so version: "0.9.1" pins the API image to 0.9.1.
|
|
# ============================================================================
|
|
|
|
version: "0.9.1"
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# External PostgreSQL (chart's bundled postgresql is disabled).
|
|
# password is the K8s env expansion `$(POSTGRES_PASSWORD)` — the chart defines
|
|
# POSTGRES_PASSWORD as a secretKeyRef (hindsight-credentials / postgres-password)
|
|
# earlier in the same container, so K8s substitutes it at container start.
|
|
# ----------------------------------------------------------------------------
|
|
postgresql:
|
|
enabled: false
|
|
external:
|
|
host: hindsight-postgres
|
|
port: 5432
|
|
username: hindsight
|
|
database: hindsight
|
|
password: $(POSTGRES_PASSWORD)
|
|
|
|
# ExternalSecret (from 1Password) that the chart injects via envFrom(secretRef).
|
|
# Keys it must expose: postgres-password, HINDSIGHT_API_LLM_API_KEY,
|
|
# HINDSIGHT_API_MCP_AUTH_TOKEN. See externalsecret.yaml in this dir.
|
|
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 endpoint
|
|
# (https://inference-api.nousresearch.com/v1), model upstage/solar-pro4:free
|
|
# (tool-calling, verified retain/recall). stepfun/step-3.7-flash was swapped out
|
|
# because it rejects Hindsight's tagged fact-extraction (BadRequestError 400
|
|
# 'missing tags'); solar-pro4 is the previously-verified-good Nous model for the
|
|
# extract/retain path (tasks t_e3375410 / t_d0dffc3d).
|
|
# HINDSIGHT_API_LLM_API_KEY is NOT set here — it comes from the existingSecret
|
|
# via envFrom (1Password `nous` item).
|
|
# ----------------------------------------------------------------------------
|
|
api:
|
|
env:
|
|
# Restore (2026-08-29, t_e0e6f7ca): astro-orbiter back online; move LLM back
|
|
# to local Qwen3.8-27B-Q4_K_M on llama-swap. Nous free tier returns 400
|
|
# 'missing tags' on Hindsight structured fact-extraction (retain broken).
|
|
HINDSIGHT_API_LLM_BASE_URL: "http://astro-orbiter:8001/v1"
|
|
HINDSIGHT_API_LLM_PROVIDER: "openai"
|
|
HINDSIGHT_API_LLM_MODEL: "Qwen3.8-27B-Q4_K_M"
|
|
# --- t_d7f8cd65: fix 502s on the serial astro-orbiter node ---
|
|
# astro-orbiter is a single llama-swap process (serial: 1 generate at a
|
|
# time, ctx 64K). Hindsight's default LLM concurrency is 32, so a retain
|
|
# burst hits the node with N parallel calls -> the node rejects/times out
|
|
# the extras -> hindsight-api surfaces APITimeoutError as 502. astro-orbiter
|
|
# is the ONLY LLM endpoint (all ops route there), so cap the whole pool to
|
|
# 1 and pin retain to 1 as well. The upstream chart exposes these as native
|
|
# semaphore config (HINDSIGHT_API_*_MAX_CONCURRENT); no code change needed.
|
|
HINDSIGHT_API_LLM_MAX_CONCURRENT: "1"
|
|
HINDSIGHT_API_RETAIN_LLM_MAX_CONCURRENT: "1"
|
|
# Client + per-request timeout. Default is 120s; a 29K-token retain runs
|
|
# ~29s and under load a single long retain can reach ~90s. Raise to 600s to
|
|
# cover the longest round-trip so the serial call never times out the client
|
|
# (keep >= ingress proxy-read-timeout below). Per-op retain timeout pins the
|
|
# retain path explicitly; the global timeout covers reflect/consolidation.
|
|
HINDSIGHT_API_LLM_TIMEOUT: "600"
|
|
HINDSIGHT_API_RETAIN_LLM_TIMEOUT: "600"
|
|
|
|
# ----------------------------------------------------------------------------
|
|
# Ingress via the chart's native template.
|
|
# /health,/v1,/mcp,/ext -> api:8888 (longest-prefix wins in nginx)
|
|
# / -> controlPlane:3000
|
|
# TLS secret hindsight-tls provisioned by the letsencrypt-prod issuer.
|
|
# ----------------------------------------------------------------------------
|
|
ingress:
|
|
enabled: true
|
|
className: "nginx"
|
|
annotations:
|
|
cert-manager.io/cluster-issuer: "letsencrypt-prod"
|
|
# Raised read/send timeout so a slow agentic reflect / long single retain
|
|
# (up to ~90s under load on the serial astro-orbiter node; client timeout
|
|
# is 600s per t_d7f8cd65) can complete before nginx cuts the connection.
|
|
# Raised 300 -> 600 (t_d7f8cd65) to cover the longest retain round-trip.
|
|
nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
|
|
nginx.ingress.kubernetes.io/proxy-send-timeout: "600"
|
|
hosts:
|
|
- host: cosmic-rewind.local.mk-labs.cloud
|
|
paths:
|
|
- path: /health
|
|
pathType: Prefix
|
|
service: api
|
|
- path: /v1
|
|
pathType: Prefix
|
|
service: api
|
|
- path: /mcp
|
|
pathType: Prefix
|
|
service: api
|
|
- path: /ext
|
|
pathType: Prefix
|
|
service: api
|
|
- path: /
|
|
pathType: Prefix
|
|
service: controlPlane
|
|
tls:
|
|
- hosts:
|
|
- cosmic-rewind.local.mk-labs.cloud
|
|
secretName: hindsight-tls
|