chore: import upstream snapshot with attribution
govulncheck / govulncheck (push) Has been cancelled
Lint / golangci-lint (push) Has been cancelled
Run Tests / Unit Tests (push) Has been cancelled
Run Tests / Etcd Integration Tests (push) Has been cancelled
Harness (E2E) / Harnesses (mock LLM) (push) Has been cancelled
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Has been cancelled
govulncheck / govulncheck (push) Has been cancelled
Lint / golangci-lint (push) Has been cancelled
Run Tests / Unit Tests (push) Has been cancelled
Run Tests / Etcd Integration Tests (push) Has been cancelled
Harness (E2E) / Harnesses (mock LLM) (push) Has been cancelled
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Has been cancelled
This commit is contained in:
@@ -0,0 +1,116 @@
|
||||
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
|
||||
# skips providers whose secrets are absent, so scheduled conformance
|
||||
# remains safe in no-key forks while still failing configured providers that drift.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: ["**"]
|
||||
pull_request:
|
||||
branches: ["**"]
|
||||
schedule:
|
||||
- cron: "17 * * * *" # hourly, so real-model conformance keeps pace with the dev/loop velocity
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
providers:
|
||||
description: "Comma-separated providers for live conformance (default: all supported)"
|
||||
required: false
|
||||
default: "anthropic,openai,gemini,groq,minimax,mistral,together,atlascloud"
|
||||
harnesses:
|
||||
description: "Comma-separated harnesses for live conformance"
|
||||
required: false
|
||||
default: "agent,universe,agent-flow,plan-delegate,a2a-stream-fallback"
|
||||
require_configured:
|
||||
description: "Fail selected live providers that do not have repository secrets"
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
|
||||
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: 0→1 and 0→hero developer-flow harness
|
||||
run: make harness
|
||||
|
||||
harness-live:
|
||||
name: Provider harnesses (live LLM conformance)
|
||||
runs-on: ubuntu-latest
|
||||
# Only on the hourly 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 }}
|
||||
MINIMAX_API_KEY: ${{ secrets.MINIMAX_API_KEY }}
|
||||
MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
|
||||
TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
|
||||
ATLASCLOUD_API_KEY: ${{ secrets.ATLASCLOUD_API_KEY }}
|
||||
# Atlas Cloud's default chat model was failing the agent/tool-use
|
||||
# conformance harnesses; run it against a stronger tool-use model.
|
||||
# Override with an Actions variable ATLASCLOUD_MODEL if the exact
|
||||
# catalog id differs (Atlas uses org/model ids).
|
||||
ATLASCLOUD_MODEL: ${{ vars.ATLASCLOUD_MODEL || 'minimaxai/minimax-m3' }}
|
||||
run: |
|
||||
PROVIDERS="${{ github.event.inputs.providers || 'anthropic,openai,gemini,groq,minimax,mistral,together,atlascloud' }}"
|
||||
HARNESSES="${{ github.event.inputs.harnesses || 'agent,universe,agent-flow,plan-delegate,a2a-stream-fallback' }}"
|
||||
REQUIRE_CONFIGURED="${{ github.event.inputs.require_configured || 'false' }}"
|
||||
|
||||
args=(
|
||||
-providers "$PROVIDERS"
|
||||
-harnesses "$HARNESSES"
|
||||
-summary-json provider-conformance-summary.json
|
||||
-summary-markdown provider-conformance-summary.md
|
||||
-capabilities-markdown provider-capabilities.md
|
||||
)
|
||||
if [ "$REQUIRE_CONFIGURED" = "true" ]; then
|
||||
args+=( -require-configured )
|
||||
fi
|
||||
|
||||
go run ./internal/harness/provider-conformance "${args[@]}"
|
||||
- name: Publish provider conformance summary
|
||||
if: always()
|
||||
run: |
|
||||
if [ -f provider-conformance-summary.md ]; then
|
||||
cat provider-conformance-summary.md >> "$GITHUB_STEP_SUMMARY"
|
||||
fi
|
||||
if [ -f provider-capabilities.md ]; then
|
||||
{
|
||||
echo
|
||||
echo "## Registered provider capabilities"
|
||||
echo
|
||||
cat provider-capabilities.md
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
fi
|
||||
- name: Upload provider conformance summary
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: provider-conformance
|
||||
path: |
|
||||
provider-conformance-summary.json
|
||||
provider-conformance-summary.md
|
||||
provider-capabilities.md
|
||||
if-no-files-found: ignore
|
||||
Reference in New Issue
Block a user