litellm/tests/e2e/docker-compose.yml
yucheng-berri 948a43cd64
test(e2e): otel trace completeness on /chat/completions (#33132)
* test(e2e): OTEL trace completeness on /chat/completions against a local Jaeger destination

Adds the logging-suite infrastructure for LIT-3787 trace-completeness coverage:
a jaeger service in the compose stack as the OTEL v2 destination (arize_phoenix
preset pointed at it via PHOENIX_COLLECTOR_HTTP_ENDPOINT, so gen-AI spans export
through a preset-owned provider - the code path where trace splits happen), a
typed Jaeger query read-back client, and the first test: one successful
non-streaming /chat/completions call exports ONE complete trace (root SERVER
span + auth/db/cost children + gen-AI CLIENT span, no dangling parents).

* test(e2e): harden the otel trace read-back per review

Jaeger reads now query server-side by the litellm.call_id span tag instead of
paging recent traces and filtering client-side; the compose stack's background
jobs alone can push a request trace past the page. A failed query hard-fails
instead of reading as an empty result, the settle predicate now also waits for
the prefix-matched db span the assertion demands, parent-chain walking follows
CHILD_OF references only, the zero-trace and split-trace failures get distinct
messages, jaeger gets a healthcheck so the depends_on condition is accurate,
and the chat docstring names the route the code actually asserts

* test(e2e): author the chat trace test docstring

* Update logging section in CLAUDE.md

Removed mention of OTEL trace-tree completeness from logging integration section.
2026-07-13 19:06:12 -07:00

139 lines
4.3 KiB
YAML

# local setup to run e2e tests
configs:
litellm_config:
content: |
general_settings:
master_key: os.environ/LITELLM_MASTER_KEY
database_url: os.environ/DATABASE_URL
store_prompts_in_spend_logs: true
proxy_budget_rescheduler_min_time: 5
proxy_budget_rescheduler_max_time: 10
litellm_settings:
drop_params: true
num_retries: 3
request_timeout: 600
cache: true
cache_params:
type: redis
host: redis
port: 6379
# OTEL v2 trace destination for the logging suite's trace-completeness
# tests: the arize_phoenix preset is OTLP with a configurable endpoint
# (PHOENIX_COLLECTOR_HTTP_ENDPOINT below points it at the jaeger service),
# so gen-AI spans export through a preset-owned provider - the code path
# where trace splits actually happen - with no cloud credentials needed.
callbacks: ["arize_phoenix"]
router_settings:
routing_strategy: simple-shuffle
num_retries: 3
allowed_fails: 5
cooldown_time: 30
fallbacks:
- gemini-2.5-flash: ["gpt-5.5", "claude-haiku-4-5"]
finetune_settings:
- custom_llm_provider: openai
api_key: os.environ/OPENAI_API_KEY
files_settings:
- custom_llm_provider: openai
api_key: os.environ/OPENAI_API_KEY
- custom_llm_provider: azure
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY
api_version: "2024-05-01-preview"
model_list:
- model_name: gpt-5.5
litellm_params:
model: openai/gpt-5.5
api_key: os.environ/OPENAI_API_KEY
- model_name: claude-haiku-4-5
litellm_params:
model: anthropic/claude-haiku-4-5
api_key: os.environ/ANTHROPIC_API_KEY
- model_name: gemini-2.5-flash
litellm_params:
model: gemini/gemini-2.5-flash
api_key: os.environ/GEMINI_API_KEY
- model_name: openai-text-embedding-3-small
litellm_params:
model: openai/text-embedding-3-small
api_key: os.environ/OPENAI_API_KEY
services:
litellm:
image: ghcr.io/berriai/litellm:main-latest
depends_on:
db:
condition: service_healthy
redis:
condition: service_healthy
jaeger:
condition: service_healthy
env_file: .env
environment:
LITELLM_MASTER_KEY: sk-1234
LITELLM_OTEL_V2: "true"
PHOENIX_COLLECTOR_HTTP_ENDPOINT: http://jaeger:4318/v1/traces
PHOENIX_API_KEY: local-jaeger-noauth
DATABASE_URL: postgresql://litellm:litellm@db:5432/litellm
UI_USERNAME: admin
UI_PASSWORD: sk-1234
AWS_S3_BUCKET_NAME: ${AWS_S3_BUCKET_NAME:-${AWS_BATCH_S3_BUCKET:-}}
AWS_BATCH_S3_BUCKET: ${AWS_BATCH_S3_BUCKET:-${AWS_S3_BUCKET_NAME:-}}
AWS_BATCH_ROLE_ARN: ${AWS_BATCH_ROLE_ARN:-}
AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID:-}
AWS_SECRET_ACCESS_KEY: ${AWS_SECRET_ACCESS_KEY:-}
AWS_REGION: ${AWS_REGION:-us-east-1}
GCS_BUCKET_NAME: ${GCS_BUCKET_NAME:-}
VERTEXAI_PROJECT: ${VERTEXAI_PROJECT:-}
VERTEXAI_CREDENTIALS: ${VERTEXAI_CREDENTIALS:-}
GOOGLE_APPLICATION_CREDENTIALS: ${GOOGLE_APPLICATION_CREDENTIALS:-}
MISTRAL_API_KEY: ${MISTRAL_API_KEY:-}
AZURE_API_BASE: ${AZURE_API_BASE:-}
AZURE_API_KEY: ${AZURE_API_KEY:-}
ports:
- "4000:4000"
configs:
- source: litellm_config
target: /app/config.yaml
command: ["--config", "/app/config.yaml", "--port", "4000"]
# throwaway db
db:
image: postgres:16
environment:
POSTGRES_USER: litellm
POSTGRES_PASSWORD: litellm
POSTGRES_DB: litellm
healthcheck:
test: ["CMD-SHELL", "pg_isready -U litellm"]
interval: 3s
timeout: 3s
retries: 20
redis:
image: redis:7
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 3s
timeout: 3s
retries: 20
# throwaway OTEL trace destination (OTLP ingest on 4318 inside the network,
# query API on host 16686 for test read-back; see E2E_OTEL_QUERY_URL)
jaeger:
image: jaegertracing/all-in-one:1.62.0
ports:
- "16686:16686"
healthcheck:
test: ["CMD", "wget", "-qO-", "http://localhost:14269/"]
interval: 3s
timeout: 3s
retries: 20