litellm/deploy/lens/stack.yaml
moe-berri e9cfba2c17
feat(lens): isolate ingestion and investigations in a Rust service (#45148)
* feat(lens): isolate trace storage and investigation in a Rust service

* fix(lens): include Rust sources in the image build context

* feat(lens): wire service setup, scoped delivery receipts and lease attempts

* fix(lens): complete service routing and reject stale investigation results

* fix(lens): retry key propagation and validate isolated Compose setup

* fix(lens): seed through isolated ingestion and preserve upstream queue fixes

* chore: sync schema.prisma copies from root

* fix(lens): bind nullable due timestamps as text for Prisma

* chore(ui): remove stale lint suppressions

* fix(lens): address CI failures and review findings

* refactor(lens): remove retired Python worker and run evaluations in Rust

* fix(lens): reuse control connections and satisfy review checks

* test(lens): install and upgrade both Helm charts on Kubernetes

* test(lens): run connection reuse coverage as an integration test

* fix(ui): upgrade Next.js to 16.3.8 security release

* fix(lens): fence stale attempts and preserve reviewed evidence

* Revert "fix(ui): upgrade Next.js to 16.3.8 security release"

This reverts commit 2f79a51b25.

* fix(lens): stop failed investigations and stream history excerpts

* test(lens): cover model tool and result contracts

* test(lens): fix retired routes and reuse installation build artifacts

* test(lens): use portable grep in Helm installation smoke

* test(lens): wait for migrations before forwarding Helm services

* fix(lens): keep failed evidence reads retryable

* fix(lens): preserve sandbox output during process exit

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2026-10-07 17:18:58 -07:00

100 lines
3.3 KiB
YAML

name: litellm-lens
services:
litellm:
image: ghcr.io/berriai/litellm:${LITELLM_VERSION:?Set LITELLM_VERSION to a published release, without the v prefix}
entrypoint:
- python3
- -c
- |
import os, sys
from urllib.parse import quote
postgres_password = quote(os.environ["POSTGRES_PASSWORD"], safe="")
os.environ["DATABASE_URL"] = f"postgresql://litellm:{postgres_password}@db:5432/litellm"
os.execv("docker/prod_entrypoint.sh", ["docker/prod_entrypoint.sh", *sys.argv[1:]])
command: ["--config", "/app/lens-config.yaml", "--port", "4000"]
environment:
LITELLM_MASTER_KEY: ${LITELLM_MASTER_KEY:?Set a strong master key}
LITELLM_SALT_KEY: ${LITELLM_SALT_KEY:?Set a permanent encryption key and keep it across upgrades}
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?Set a permanent database password}
STORE_MODEL_IN_DB: "True"
LITELLM_LENS_URL: http://lens-worker:4318
LITELLM_LENS_PUBLIC_URL: ${LITELLM_LENS_PUBLIC_URL:-http://localhost:4318}
LITELLM_LENS_SERVICE_TOKEN: ${LITELLM_LENS_SERVICE_TOKEN:?Set the shared Lens service secret}
LENS_WORKER_IMAGE: ghcr.io/berriai/litellm-lens-worker:v${LITELLM_VERSION}
volumes:
- ./config.yaml:/app/lens-config.yaml:ro
ports:
- "127.0.0.1:${LITELLM_PORT:-4000}:4000"
networks: [proxy, database]
depends_on:
db:
condition: service_healthy
restart: unless-stopped
lens-worker:
image: ghcr.io/berriai/litellm-lens-worker:v${LITELLM_VERSION}
environment:
LITELLM_URL: http://litellm:4000
LENS_WORKER_TOKEN: ${LENS_WORKER_TOKEN:-}
LITELLM_LENS_SERVICE_TOKEN: ${LITELLM_LENS_SERVICE_TOKEN}
CLICKHOUSE_HOST: clickhouse
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:?Set a permanent ClickHouse password}
CLICKHOUSE_DATABASE: ${CLICKHOUSE_DATABASE:-litellm}
AGENT_TRACING_RETENTION_DAYS: ${AGENT_TRACING_RETENTION_DAYS:-14}
depends_on: [litellm]
networks: [proxy, storage]
ports:
- "127.0.0.1:${LENS_PORT:-4318}:4318"
mem_limit: 2g
cpus: 2
pids_limit: 64
restart: unless-stopped
read_only: true
tmpfs:
- /tmp:rw,noexec,nosuid,size=${LENS_WORKER_TMP_SIZE:-1g}
cap_drop: [ALL]
security_opt: [no-new-privileges:true]
db:
image: postgres:16
environment:
POSTGRES_DB: litellm
POSTGRES_USER: litellm
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
networks: [database]
volumes:
- postgres_data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U litellm -d litellm"]
interval: 5s
timeout: 5s
retries: 20
restart: unless-stopped
clickhouse:
image: clickhouse/clickhouse-server:26.9.6.6
environment:
CLICKHOUSE_USER: default
CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD}
CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT: "1"
volumes:
- clickhouse_data:/var/lib/clickhouse
healthcheck:
test: ["CMD", "clickhouse-client", "--user", "default", "--password", "${CLICKHOUSE_PASSWORD}", "--query", "SELECT 1"]
interval: 5s
timeout: 5s
retries: 20
restart: unless-stopped
networks: [storage]
networks:
proxy:
database:
internal: true
storage:
internal: true
volumes:
postgres_data:
clickhouse_data: