wehub-resource-sync
188 lines
7.7 KiB
YAML
188 lines
7.7 KiB
YAML
name: "Run integration suite"
|
|
description: >
|
|
Run the tests/integration journey suite exactly as the integration.yml gate
|
|
does (mock LLM, one wrapped harness per invocation). When `server_version`
|
|
is set, the omnigent SERVER subprocess is pinned to that released tag while
|
|
the client, runner, and tests stay on the checked-out ref — the
|
|
server-version backwards-compat configuration. Shared verbatim by
|
|
integration.yml (normal gate) and server-compat.yml (backcompat jobs) so the
|
|
two never drift. The caller owns the preceding `actions/checkout` (backcompat
|
|
needs fetch-depth 0 for tags).
|
|
|
|
inputs:
|
|
harness:
|
|
description: "Wrapped harness (claude-sdk | openai-agents | codex)"
|
|
required: true
|
|
model:
|
|
description: "Model name passed to --model"
|
|
required: true
|
|
workers:
|
|
description: "pytest workers (-n)"
|
|
required: true
|
|
server_version:
|
|
description: >
|
|
Empty = run the checked-out server (normal gate). Set to a release tag
|
|
= build that old server into a venv and redirect the server subprocess
|
|
to it (backwards-compat run).
|
|
required: false
|
|
default: ""
|
|
runner_version:
|
|
description: >
|
|
Empty = run the checked-out runner (normal gate). Set to a release tag =
|
|
build that old runner into a venv and redirect the runner subprocess to it
|
|
(Config 2 backwards-compat run). Orthogonal to server_version.
|
|
required: false
|
|
default: ""
|
|
artifact_suffix:
|
|
description: >
|
|
Appended to uploaded-artifact names so they stay unique across matrix
|
|
cells (e.g. "-sv0.2.0-rmain"). Default empty — the normal gate runs one
|
|
cell, so its harness-scoped names are already unique.
|
|
required: false
|
|
default: ""
|
|
|
|
runs:
|
|
using: composite
|
|
steps:
|
|
- name: Configure environment
|
|
shell: bash
|
|
run: |
|
|
{
|
|
echo "OMNIGENT_SKIP_WEB_UI=true"
|
|
echo "ANTHROPIC_API_KEY="
|
|
echo "OPENAI_API_KEY="
|
|
echo "CODEX="
|
|
echo "CLAUDE_CODE="
|
|
} >> "$GITHUB_ENV"
|
|
|
|
- name: Set up Python
|
|
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5
|
|
with:
|
|
python-version-file: ".python-version"
|
|
|
|
- name: Install uv
|
|
uses: astral-sh/setup-uv@38f3f104447c67c051c4a08e39b64a148898af3a # v4
|
|
with:
|
|
enable-cache: true
|
|
|
|
- name: Cache virtualenv
|
|
uses: actions/cache@5a3ec84eff668545956fd18022155c47e93e2684 # v4
|
|
with:
|
|
path: .venv
|
|
key: venv-${{ runner.os }}-${{ hashFiles('.python-version') }}-${{ hashFiles('uv.lock') }}
|
|
|
|
- name: Install project and dev dependencies
|
|
shell: bash
|
|
run: uv sync --locked --extra all --extra dev
|
|
|
|
- name: Install binary dependencies
|
|
# Mirrors e2e.yml. --ignore-scripts blocks npm postinstall hooks; we run
|
|
# claude-code's install.cjs explicitly (audited, no network). bubblewrap
|
|
# backs the linux_bwrap sandbox in tests/inner/*.
|
|
working-directory: .github/ci-deps
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
sudo apt-get update
|
|
sudo apt-get install -y tmux ripgrep bubblewrap
|
|
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0
|
|
npm install --ignore-scripts
|
|
node node_modules/@anthropic-ai/claude-code/install.cjs
|
|
echo "${GITHUB_WORKSPACE}/.github/ci-deps/node_modules/.bin" >> "$GITHUB_PATH"
|
|
|
|
- name: Build pinned old server (backwards-compat only)
|
|
# See e2e-run for the full rationale. Requires fetch-depth 0 in the caller.
|
|
if: ${{ inputs.server_version != '' }}
|
|
shell: bash
|
|
env:
|
|
SERVER_VERSION_INPUT: ${{ inputs.server_version }}
|
|
run: |
|
|
tag="$SERVER_VERSION_INPUT"
|
|
if ! [[ "$tag" =~ ^v?[0-9]+\.[0-9]+(\.[0-9]+)?([a-z0-9.]*)?$ ]]; then
|
|
echo "Invalid server_version: '$tag'" >&2; exit 1
|
|
fi
|
|
src="$RUNNER_TEMP/server-src"
|
|
venv="$RUNNER_TEMP/server-env"
|
|
git worktree add --detach "$src" "$tag"
|
|
uv venv --python 3.12 "$venv"
|
|
uv pip install --python "$venv/bin/python" \
|
|
-e "$src" -e "$src/sdks/python-client" -e "$src/sdks/ui"
|
|
"$venv/bin/omnigent" --version
|
|
echo "OMNIGENT_COMPAT_SERVER_PYTHON=$venv/bin/python" >> "$GITHUB_ENV"
|
|
echo "OMNIGENT_COMPAT_SERVER_VERSION=${tag#v}" >> "$GITHUB_ENV"
|
|
|
|
- name: Build pinned old runner (backwards-compat only)
|
|
# Config 2: redirect the runner subprocess to the pinned old build via
|
|
# OMNIGENT_COMPAT_RUNNER_PYTHON. See e2e-run for the full rationale.
|
|
# Distinct paths from the server build. Requires fetch-depth 0 in the caller.
|
|
if: ${{ inputs.runner_version != '' }}
|
|
shell: bash
|
|
env:
|
|
RUNNER_VERSION_INPUT: ${{ inputs.runner_version }}
|
|
run: |
|
|
tag="$RUNNER_VERSION_INPUT"
|
|
if ! [[ "$tag" =~ ^v?[0-9]+\.[0-9]+(\.[0-9]+)?([a-z0-9.]*)?$ ]]; then
|
|
echo "Invalid runner_version: '$tag'" >&2; exit 1
|
|
fi
|
|
src="$RUNNER_TEMP/runner-src"
|
|
venv="$RUNNER_TEMP/runner-env"
|
|
git worktree add --detach "$src" "$tag"
|
|
uv venv --python 3.12 "$venv"
|
|
uv pip install --python "$venv/bin/python" \
|
|
-e "$src" -e "$src/sdks/python-client" -e "$src/sdks/ui"
|
|
"$venv/bin/omnigent" --version
|
|
echo "OMNIGENT_COMPAT_RUNNER_PYTHON=$venv/bin/python" >> "$GITHUB_ENV"
|
|
echo "OMNIGENT_COMPAT_RUNNER_VERSION=${tag#v}" >> "$GITHUB_ENV"
|
|
|
|
- name: Run integration tests
|
|
shell: bash
|
|
env:
|
|
HARNESS: ${{ inputs.harness }}
|
|
MODEL: ${{ inputs.model }}
|
|
WORKERS: ${{ inputs.workers }}
|
|
INTEGRATION_TMP_BASE: /tmp/omnigent-integration-${{ github.run_id }}-${{ inputs.harness }}
|
|
CLAUDE_CODE_STREAM_CLOSE_TIMEOUT: "60000"
|
|
OMNIGENT_CLAUDE_SDK_NO_SANDBOX: ${{ inputs.harness == 'claude-sdk' && '1' || '' }}
|
|
PYTEST_PROGRESS_LOG_DIR: ${{ github.workspace }}/artifacts/progress-${{ inputs.harness }}
|
|
OMNIGENT_TOKEN_USAGE_JSON: ${{ github.workspace }}/artifacts/tokens-${{ inputs.harness }}.json
|
|
OMNIGENT_TEST_MODEL_SPREAD: "1"
|
|
OMNIGENT_TEST_MODEL_POOL_GPT: "databricks-gpt-5-5,databricks-gpt-5-4-mini"
|
|
run: |
|
|
set -euo pipefail
|
|
mkdir -p artifacts "$INTEGRATION_TMP_BASE"
|
|
# --capture=no + --log-cli-level=INFO stream live so progress shows
|
|
# even if the step hits its timeout before buffered output renders.
|
|
# --timeout=180 caps a single hung test (see e2e.yml).
|
|
env -u OPENAI_API_KEY -u ANTHROPIC_API_KEY -u DATABRICKS_TOKEN \
|
|
uv run pytest tests/integration/ \
|
|
--model "$MODEL" \
|
|
--harness "$HARNESS" \
|
|
-n "$WORKERS" \
|
|
--dist=loadscope \
|
|
--timeout=180 \
|
|
--timeout-method=thread \
|
|
--basetemp="$INTEGRATION_TMP_BASE" \
|
|
--junitxml="artifacts/integration-${HARNESS}.xml" \
|
|
--capture=no --log-cli-level=INFO \
|
|
-v --tb=long --showlocals --log-level=INFO -r a
|
|
|
|
- name: Upload server/runner logs on failure
|
|
if: ${{ failure() || cancelled() }}
|
|
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
|
|
with:
|
|
name: integration-server-logs-${{ inputs.harness }}-${{ github.run_id }}${{ inputs.artifact_suffix }}
|
|
path: |
|
|
/tmp/omnigent-integration-${{ github.run_id }}-${{ inputs.harness }}/**/server.log
|
|
/tmp/omnigent-integration-${{ github.run_id }}-${{ inputs.harness }}/**/runner.log
|
|
retention-days: 7
|
|
if-no-files-found: warn
|
|
|
|
- name: Upload junit + logs
|
|
if: ${{ always() }}
|
|
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
|
|
with:
|
|
name: integration-${{ inputs.harness }}-${{ github.run_id }}${{ inputs.artifact_suffix }}
|
|
path: artifacts/
|
|
retention-days: 14
|
|
if-no-files-found: ignore
|