项目文件夹

文件
2026-06-25 13:28:57 +01:00

61 行
2.2 KiB
YAML

name: Harness (E2E)
# Runs the end-to-end harnesses for agents, services, flows, and provider
# conformance. The default job uses deterministic mock LLMs and needs no
# secrets. A second job runs the same harnesses against the live provider set and
# fails if any selected provider secret is missing, so scheduled conformance
# cannot silently degrade.
on:
push:
branches: ["**"]
pull_request:
branches: ["**"]
schedule:
- cron: "17 6 * * *" # daily, so the world is exercised even without changes
workflow_dispatch:
jobs:
harness:
name: Harnesses (mock LLM)
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: stable
cache: true
- name: Build
run: go build ./...
- name: Universe end-to-end (asserts; exits non-zero on failure)
run: go run ./internal/harness/universe
- name: Agent-flow harness
run: go run ./internal/harness/agent-flow
- name: Plan-delegate harness
run: go run ./internal/harness/plan-delegate
harness-live:
name: Provider harnesses (live LLM conformance)
runs-on: ubuntu-latest
# Only on the daily schedule or a manual run — never automatically on
# every push/PR, so changes don't quietly burn API credits. Trigger it
# by hand (Actions → Harness → Run workflow) when changing the agent,
# flow, or AI internals and you want a real-model check.
if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
steps:
- uses: actions/checkout@v4
- uses: actions/setup-go@v5
with:
go-version: stable
cache: true
- name: Provider conformance against live models
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
ATLASCLOUD_API_KEY: ${{ secrets.ATLASCLOUD_API_KEY }}
run: go run ./internal/harness/provider-conformance -require-configured