mirror of
https://github.com/katanemo/plano.git
synced 2026-05-05 05:42:49 +02:00
3a6a672c9d
Introduce a new mock-based E2E test suite that uses pytest_httpserver to simulate LLM provider responses, eliminating the need for real API keys on PR builds. The mock tests cover model alias routing, protocol transformation (OpenAI↔Anthropic), Responses API passthrough/translation, streaming, tool calls, thinking mode, and multi-turn state management. CI changes: - Add mock-e2e-tests job (zero secrets, runs on every PR) - Gate all live E2E jobs to main pushes + nightly schedule - Scope secrets to only the keys each job actually needs - Add daily cron schedule for full live test coverage Also relaxes exact-match assertions in live e2e tests to structural checks (non-null, non-empty) since LLM output is non-deterministic. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
42 lines
978 B
YAML
42 lines
978 B
YAML
version: v0.3.0
|
|
|
|
listeners:
|
|
- type: model
|
|
name: model_listener
|
|
port: 12000
|
|
|
|
model_providers:
|
|
# OpenAI Models - all point to mock server
|
|
- model: openai/gpt-5-mini-2025-08-07
|
|
access_key: $OPENAI_API_KEY
|
|
default: true
|
|
base_url: http://host.docker.internal:51001
|
|
|
|
- model: openai/gpt-4o-mini
|
|
access_key: $OPENAI_API_KEY
|
|
base_url: http://host.docker.internal:51001
|
|
|
|
- model: openai/o3
|
|
access_key: $OPENAI_API_KEY
|
|
base_url: http://host.docker.internal:51001
|
|
|
|
- model: openai/gpt-4o
|
|
access_key: $OPENAI_API_KEY
|
|
base_url: http://host.docker.internal:51001
|
|
|
|
# Anthropic Models - point to mock server
|
|
- model: anthropic/claude-sonnet-4-20250514
|
|
access_key: $ANTHROPIC_API_KEY
|
|
base_url: http://host.docker.internal:51001
|
|
|
|
# Model aliases
|
|
model_aliases:
|
|
arch.summarize.v1:
|
|
target: gpt-5-mini-2025-08-07
|
|
|
|
arch.v1:
|
|
target: o3
|
|
|
|
# State storage for v1/responses API multi-turn tests
|
|
state_storage:
|
|
type: memory
|