Files
shockbot/.github/workflows/test.yml
T
Colin McDonnell e52206b8ca test: switch opus defaults to sonnet/kimi for cheaper coverage
- opencode test default: claude-sonnet-4-6 → moonshotai/kimi-k2. claude-code
  default stays on sonnet (the agent-under-test for that path is Claude
  Code); the opencode path doesn't need an Anthropic model.
- byok-no-keys-fallback fixture: anthropic/claude-opus → moonshotai/kimi-k2.
  test verifies fallback to opencode/big-pickle, so the configured model
  is never invoked; picking a non-opus alias avoids burning credits if
  the fallback ever regresses.
- BEDROCK_MODEL_ID in both test workflows: us.anthropic.claude-opus-4-6-v1
  → us.anthropic.claude-sonnet-4-6. env var is required by the ci.test
  invariant that every provider's env vars are wired into the workflow.
2026-05-23 01:07:20 +00:00

122 lines
3.7 KiB
YAML

name: Test
on:
pull_request:
jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: "pnpm"
- run: pnpm install --frozen-lockfile
- run: pnpm typecheck
- run: pnpm test
agents:
runs-on: ubuntu-latest
timeout-minutes: 20
permissions:
contents: read
id-token: write
strategy:
fail-fast: true
matrix:
agent: [claude, opencode]
test:
[
codex-auth,
mcpmerge,
nobash,
restricted,
skill-invoke-claude,
skill-invoke-opencode,
smoke,
token-exfil,
# vertex-claude, # disabled: 0 anthropic quota on pullfrog GCP vertex
vertex-opencode,
]
exclude:
- agent: claude
test: skill-invoke-opencode
- agent: claude
test: codex-auth
- agent: opencode
test: skill-invoke-claude
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
GOOGLE_GENERATIVE_AI_API_KEY: ${{ secrets.GOOGLE_GENERATIVE_AI_API_KEY }}
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
MOONSHOT_API_KEY: ${{ secrets.MOONSHOT_API_KEY }}
OPENCODE_API_KEY: ${{ secrets.OPENCODE_API_KEY }}
AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.AWS_BEARER_TOKEN_BEDROCK }}
AWS_REGION: us-east-1
BEDROCK_MODEL_ID: us.anthropic.claude-sonnet-4-6
VERTEX_SERVICE_ACCOUNT_JSON: ${{ secrets.VERTEX_SERVICE_ACCOUNT_JSON }}
GOOGLE_CLOUD_PROJECT: pullfrog
VERTEX_LOCATION: global
VERTEX_MODEL_ID: gemini-2.5-flash
PULLFROG_MODEL: ${{ vars.PULLFROG_MODEL }}
# CI smoke-testing shortcut only — production stores this in Pullfrog's
# per-org secret store (Postgres), set via `pullfrog auth codex`. GH
# Actions secrets are immutable at runtime so the post-hook can't write
# back the rotated refresh token; CI accepts the staleness and we
# manually re-provision when smoke tests start failing. Do not copy this
# pattern into user-facing workflows. See wiki/codex-auth.md.
CODEX_AUTH_JSON: ${{ secrets.CODEX_AUTH_JSON }}
steps:
- uses: actions/checkout@v6
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: "pnpm"
- run: pnpm install --frozen-lockfile
- run: pnpm runtest ${{ matrix.test }} ${{ matrix.agent }}
agnostic:
runs-on: ubuntu-latest
timeout-minutes: 15
permissions:
contents: read
id-token: write
strategy:
fail-fast: true
matrix:
test:
[
byok-no-keys-fallback,
git-permissions,
githooks,
pkg-json-scripts,
push-disabled,
push-enabled,
push-restricted,
timeout,
]
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
steps:
- uses: actions/checkout@v6
- uses: pnpm/action-setup@v4
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: "pnpm"
- run: pnpm install --frozen-lockfile
- run: pnpm runtest ${{ matrix.test }}