Files
netbird/.github/workflows/agent-network-e2e.yml
Maycon Santos 4e624a25c2 [e2e] validate stored totals and cache costs against published rates
The provider matrix now sends a long-form prompt, recomputes each
access-log row's expected cost_usd and cache_cost_usd from hardcoded
published per-1k rates and the row's persisted token buckets, and
finishes with a raw-SQL audit of every usage row straight in the
management sqlite store. Bedrock defaults to Sonnet 4.6 and the
workflow gains a bedrock_model dispatch input plus a push trigger on
this branch while it is under review.
2026-07-25 19:31:55 +00:00

85 lines
3.7 KiB
YAML

name: Agent Network E2E
on:
# Nightly at 03:00 UTC, plus on demand from the Actions tab.
schedule:
- cron: "0 3 * * *"
workflow_dispatch:
inputs:
bedrock_model:
description: >-
Bedrock inference-profile id to drive the matrix with, exactly as
AWS issues it. Leave empty for the Sonnet 4.6 default.
required: false
default: ""
# Auto-run on pushes to the cache-accounting branch until its PR opens.
push:
branches:
- "anet-cache-cost-accounting"
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
e2e:
name: Agent Network E2E
runs-on: ubuntu-latest
timeout-minutes: 45
steps:
- name: Checkout code
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Install Go
uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c # v6.4.0
with:
go-version-file: "go.mod"
# Container-driver builder so the harness can build the combined/proxy/
# client images from source with a local layer cache.
- name: Set up Buildx
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
# Persist the Docker layer cache across runs. This caches the base, apt,
# and go-mod-download layers; the Go compile still re-runs, as BuildKit
# mount caches cannot be exported to the GitHub cache.
- name: Cache Docker layers
uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-anet-e2e-buildx-${{ hashFiles('go.sum', 'combined/Dockerfile.multistage', 'proxy/Dockerfile.multistage', 'e2e/harness/Dockerfile.client') }}
restore-keys: |
${{ runner.os }}-anet-e2e-buildx-
- name: Run agent-network e2e
env:
# Build the images from source (this branch's code) with the shared
# local layer cache.
NB_E2E_BUILDX_CACHE: /tmp/.buildx-cache
# Provider credentials. Each provider scenario skips if its
# token (and URL, for gateways) is unset, so partial coverage is fine.
OPENAI_TOKEN: ${{ secrets.E2E_OPENAI_TOKEN }}
ANTHROPIC_TOKEN: ${{ secrets.E2E_ANTHROPIC_TOKEN }}
# Moonshot AI platform key (platform.kimi.ai); drives both Kimi wire
# shapes (OpenAI /v1 and Anthropic /anthropic) through kimi_api.
KIMI_TOKEN: ${{ secrets.E2E_KIMI_TOKEN }}
VERCEL_URL: ${{ secrets.E2E_VERCEL_URL }}
VERCEL_TOKEN: ${{ secrets.E2E_VERCEL_TOKEN }}
OPENROUTER_URL: ${{ secrets.E2E_OPENROUTER_URL }}
OPENROUTER_TOKEN: ${{ secrets.E2E_OPENROUTER_TOKEN }}
CLOUDFLARE_URL: ${{ secrets.E2E_CLOUDFLARE_URL }}
CLOUDFLARE_TOKEN: ${{ secrets.E2E_CLOUDFLARE_TOKEN }}
AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.E2E_AWS_BEARER_TOKEN_BEDROCK }}
AWS_REGION: ${{ secrets.E2E_AWS_REGION }}
# Bedrock model override: dispatch input wins, then the repo variable, else the test default.
AWS_BEDROCK_MODEL: ${{ inputs.bedrock_model || vars.E2E_AWS_BEDROCK_MODEL }}
# Vertex (Anthropic-on-Vertex): SA + project required; region defaults
# to "global", model to a pinned claude snapshot.
GOOGLE_VERTEX_SA_BASE64: ${{ secrets.E2E_GOOGLE_VERTEX_SA_BASE64 }}
GOOGLE_VERTEX_PROJECT: ${{ secrets.E2E_GOOGLE_VERTEX_PROJECT }}
GOOGLE_VERTEX_REGION: ${{ secrets.E2E_GOOGLE_VERTEX_REGION }}
GOOGLE_VERTEX_MODEL: ${{ secrets.E2E_GOOGLE_VERTEX_MODEL }}
run: go test -tags e2e -timeout 40m -v ./e2e/...