mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 13:20:43 +00:00
feat(qa): add Mantis Discord status reaction scenario (#76747)
* feat(qa): add Mantis Discord status reaction scenario * fix(qa): retry Discord rate limits in Mantis runs * refactor(qa): reuse Discord API retry helper * fix(qa): import Discord API through package surface * fix(ci): generate Discord boundary declarations * fix(ci): keep xai boundary overrides stable
This commit is contained in:
Peter Steinberger
committed by
GitHub
GitHub
parent
1e8de7661e
commit
77a50db9ea
256
.github/workflows/mantis-discord-status-reactions.yml
vendored
Normal file
256
.github/workflows/mantis-discord-status-reactions.yml
vendored
Normal file
@@ -0,0 +1,256 @@
|
||||
name: Mantis Discord Status Reactions
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
baseline_ref:
|
||||
description: Ref, tag, or SHA expected to reproduce queued-only behavior
|
||||
required: true
|
||||
default: 0bf06e953fdda290799fc9fb9244a8f67fdae593
|
||||
type: string
|
||||
candidate_ref:
|
||||
description: Ref, tag, or SHA expected to show queued -> thinking -> done
|
||||
required: true
|
||||
default: main
|
||||
type: string
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: read
|
||||
|
||||
concurrency:
|
||||
group: mantis-discord-status-reactions-${{ inputs.baseline_ref }}-${{ inputs.candidate_ref }}-${{ github.run_attempt }}
|
||||
cancel-in-progress: false
|
||||
|
||||
env:
|
||||
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
|
||||
NODE_VERSION: "24.x"
|
||||
PNPM_VERSION: "10.33.0"
|
||||
OPENCLAW_BUILD_PRIVATE_QA: "1"
|
||||
OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
|
||||
|
||||
jobs:
|
||||
authorize_actor:
|
||||
name: Authorize workflow actor
|
||||
runs-on: blacksmith-8vcpu-ubuntu-2404
|
||||
steps:
|
||||
- name: Require maintainer-level repository access
|
||||
uses: actions/github-script@v8
|
||||
with:
|
||||
script: |
|
||||
const allowed = new Set(["admin", "maintain", "write"]);
|
||||
const { owner, repo } = context.repo;
|
||||
const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
|
||||
owner,
|
||||
repo,
|
||||
username: context.actor,
|
||||
});
|
||||
const permission = data.permission;
|
||||
core.info(`Actor ${context.actor} permission: ${permission}`);
|
||||
if (!allowed.has(permission)) {
|
||||
core.setFailed(
|
||||
`Workflow requires write/maintain/admin access. Actor "${context.actor}" has "${permission}".`,
|
||||
);
|
||||
}
|
||||
|
||||
validate_refs:
|
||||
name: Validate selected refs
|
||||
needs: authorize_actor
|
||||
runs-on: blacksmith-8vcpu-ubuntu-2404
|
||||
outputs:
|
||||
baseline_revision: ${{ steps.validate.outputs.baseline_revision }}
|
||||
candidate_revision: ${{ steps.validate.outputs.candidate_revision }}
|
||||
steps:
|
||||
- name: Checkout harness ref
|
||||
uses: actions/checkout@v6
|
||||
with:
|
||||
persist-credentials: false
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Validate refs are trusted
|
||||
id: validate
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
BASELINE_REF: ${{ inputs.baseline_ref }}
|
||||
CANDIDATE_REF: ${{ inputs.candidate_ref }}
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
git fetch --no-tags origin +refs/heads/main:refs/remotes/origin/main
|
||||
|
||||
validate_ref() {
|
||||
local label="$1"
|
||||
local input_ref="$2"
|
||||
local revision=""
|
||||
local reason=""
|
||||
|
||||
revision="$(git rev-parse "${input_ref}^{commit}")"
|
||||
if git merge-base --is-ancestor "$revision" refs/remotes/origin/main; then
|
||||
reason="main-ancestor"
|
||||
elif git tag --points-at "$revision" | grep -Eq '^v'; then
|
||||
reason="release-tag"
|
||||
else
|
||||
local pr_head_count
|
||||
pr_head_count="$(
|
||||
gh api \
|
||||
-H "Accept: application/vnd.github+json" \
|
||||
"repos/${GITHUB_REPOSITORY}/commits/${revision}/pulls" \
|
||||
--jq '[.[] | select(.state == "open" and .head.repo.full_name == "'"${GITHUB_REPOSITORY}"'" and .head.sha == "'"${revision}"'")] | length'
|
||||
)"
|
||||
if [[ "$pr_head_count" != "0" ]]; then
|
||||
reason="open-pr-head"
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ -z "$reason" ]]; then
|
||||
echo "${label} ref '${input_ref}' resolved to ${revision}, which is not trusted for this secret-bearing Mantis run." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "${label}_revision=${revision}" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "${label}: \`${input_ref}\`"
|
||||
echo "${label} SHA: \`${revision}\`"
|
||||
echo "${label} trust reason: \`${reason}\`"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
}
|
||||
|
||||
validate_ref baseline "$BASELINE_REF"
|
||||
validate_ref candidate "$CANDIDATE_REF"
|
||||
|
||||
run_status_reactions:
|
||||
name: Run Discord status reaction before/after
|
||||
needs: validate_refs
|
||||
runs-on: blacksmith-8vcpu-ubuntu-2404
|
||||
timeout-minutes: 180
|
||||
environment: qa-live-shared
|
||||
steps:
|
||||
- name: Checkout harness ref
|
||||
uses: actions/checkout@v6
|
||||
with:
|
||||
persist-credentials: false
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Setup Node environment
|
||||
uses: ./.github/actions/setup-node-env
|
||||
with:
|
||||
node-version: ${{ env.NODE_VERSION }}
|
||||
pnpm-version: ${{ env.PNPM_VERSION }}
|
||||
install-bun: "true"
|
||||
|
||||
- name: Build Mantis harness
|
||||
run: pnpm build
|
||||
|
||||
- name: Prepare baseline and candidate worktrees
|
||||
shell: bash
|
||||
env:
|
||||
BASELINE_SHA: ${{ needs.validate_refs.outputs.baseline_revision }}
|
||||
CANDIDATE_SHA: ${{ needs.validate_refs.outputs.candidate_revision }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
mkdir -p .artifacts/qa-e2e/mantis/discord-status-reactions/worktrees
|
||||
git worktree add --detach .artifacts/qa-e2e/mantis/discord-status-reactions/worktrees/baseline "$BASELINE_SHA"
|
||||
git worktree add --detach .artifacts/qa-e2e/mantis/discord-status-reactions/worktrees/candidate "$CANDIDATE_SHA"
|
||||
|
||||
for lane in baseline candidate; do
|
||||
lane_dir=".artifacts/qa-e2e/mantis/discord-status-reactions/worktrees/${lane}"
|
||||
echo "Installing ${lane} worktree dependencies"
|
||||
pnpm --dir "$lane_dir" install --frozen-lockfile
|
||||
echo "Building ${lane} worktree"
|
||||
pnpm --dir "$lane_dir" build
|
||||
done
|
||||
|
||||
- name: Run baseline and candidate
|
||||
id: run_mantis
|
||||
shell: bash
|
||||
env:
|
||||
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
||||
OPENCLAW_QA_CONVEX_SITE_URL: ${{ secrets.OPENCLAW_QA_CONVEX_SITE_URL }}
|
||||
OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
|
||||
OPENCLAW_QA_REDACT_PUBLIC_METADATA: "1"
|
||||
OPENCLAW_QA_DISCORD_CAPTURE_CONTENT: "1"
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
require_var() {
|
||||
local key="$1"
|
||||
if [[ -z "${!key:-}" ]]; then
|
||||
echo "Missing required ${key}." >&2
|
||||
exit 1
|
||||
fi
|
||||
}
|
||||
|
||||
require_var OPENAI_API_KEY
|
||||
require_var OPENCLAW_QA_CONVEX_SITE_URL
|
||||
require_var OPENCLAW_QA_CONVEX_SECRET_CI
|
||||
|
||||
root=".artifacts/qa-e2e/mantis/discord-status-reactions"
|
||||
mkdir -p "$root"
|
||||
echo "output_dir=${root}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
run_lane() {
|
||||
local lane="$1"
|
||||
local repo_root="$root/worktrees/$lane"
|
||||
local output_dir="$root/$lane"
|
||||
pnpm openclaw qa discord \
|
||||
--repo-root "$repo_root" \
|
||||
--output-dir "$output_dir" \
|
||||
--provider-mode live-frontier \
|
||||
--model openai/gpt-5.4 \
|
||||
--alt-model openai/gpt-5.4 \
|
||||
--fast \
|
||||
--credential-source convex \
|
||||
--credential-role ci \
|
||||
--scenario discord-status-reactions-tool-only \
|
||||
--allow-failures
|
||||
}
|
||||
|
||||
run_lane baseline
|
||||
run_lane candidate
|
||||
|
||||
baseline_status="$(jq -r '.scenarios[0].status' "$root/baseline/discord-qa-summary.json")"
|
||||
candidate_status="$(jq -r '.scenarios[0].status' "$root/candidate/discord-qa-summary.json")"
|
||||
|
||||
jq -n \
|
||||
--arg baseline_status "$baseline_status" \
|
||||
--arg candidate_status "$candidate_status" \
|
||||
--arg baseline_sha "${{ needs.validate_refs.outputs.baseline_revision }}" \
|
||||
--arg candidate_sha "${{ needs.validate_refs.outputs.candidate_revision }}" \
|
||||
'{
|
||||
scenario: "discord-status-reactions-tool-only",
|
||||
baseline: { sha: $baseline_sha, expected: "queued-only", status: $baseline_status, reproduced: ($baseline_status == "fail") },
|
||||
candidate: { sha: $candidate_sha, expected: "queued -> thinking -> done", status: $candidate_status, fixed: ($candidate_status == "pass") },
|
||||
pass: (($baseline_status == "fail") and ($candidate_status == "pass"))
|
||||
}' > "$root/comparison.json"
|
||||
|
||||
{
|
||||
echo "# Mantis Discord Status Reactions"
|
||||
echo
|
||||
echo "- Scenario: \`discord-status-reactions-tool-only\`"
|
||||
echo "- Baseline status: \`${baseline_status}\`"
|
||||
echo "- Candidate status: \`${candidate_status}\`"
|
||||
echo "- Baseline screenshot: \`baseline/discord-status-reactions-tool-only-timeline.png\`"
|
||||
echo "- Candidate screenshot: \`candidate/discord-status-reactions-tool-only-timeline.png\`"
|
||||
} > "$root/mantis-report.md"
|
||||
|
||||
cat "$root/mantis-report.md" >> "$GITHUB_STEP_SUMMARY"
|
||||
|
||||
if [[ "$baseline_status" != "fail" ]]; then
|
||||
echo "Baseline did not reproduce queued-only behavior." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$candidate_status" != "pass" ]]; then
|
||||
echo "Candidate did not show queued -> thinking -> done." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
- name: Upload Mantis status reaction artifacts
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: mantis-discord-status-reactions-${{ github.run_id }}-${{ github.run_attempt }}
|
||||
path: ${{ steps.run_mantis.outputs.output_dir }}
|
||||
retention-days: 14
|
||||
if-no-files-found: warn
|
||||
Reference in New Issue
Block a user