Files
stack/packages/mosaic/framework/tools/git/ci-queue-wait.sh
Jason Woltje 505b6f799c
ci/woodpecker/pr/ci Pipeline was canceled
fix(git): ci-queue-wait.sh — parse the payload it was handed, not stdin (#1019)
Both python sites piped a status payload into `python3 - <<'PY'`. The heredoc binds
stdin to the program text, so `json.load(sys.stdin)` saw EOF, the bare `except` fired,
and the parser returned "unknown" for every input — success, pending and failure alike.
"unknown" then reaches a silent `exit 0` arm.

Consequence: the gate-6 queue guard has never made a determination. It exits 0 on every
invocation, on both the gitea and github paths (one shared parser). The pending wait
loop, --require-status and the 124 timeout were all unreachable code. What it still
validated was connectivity — an unresolved token, head sha, or platform could exit 1.

Fix is the one already shipped in the sibling: capture the payload with `payload=$(cat)`
before invoking python, pass it by environment. pr-ci-wait.sh:38 has carried a comment
describing this exact bug — "yielding EOF and returning unknown every time" — along with
the remedy. It was never backported to the sibling the constitution makes mandatory
before every push and merge.

Adds test-ci-queue-wait-parse.sh, enumerated in test:framework-shell. Every assertion is
on the RETURNED STATE STRING; a suite asserting only rc=0 passes against the broken build,
which is how this survived. Verified by mutation: against the pre-fix wrapper the suite
fails 10 of 14, and the four that pass are the four for which passing is correct (the
undecodable-input control, the unknown-vocabulary case, and both needle halves).

The needle scans with heredoc semantics rather than matching text. `json.load(sys.stdin)`
is correct under `python3 -c`, where the program comes from argv and stdin really is the
payload — ci-queue-wait.sh uses that form legitimately in gitea_get_branch_head_sha. A
flat grep flags that innocent site; the scanner names only the two defective ones.

Out of scope, deliberately, and recorded on #1019: token-in-argv (ps-visible) and the
hardcoded BRANCH="main". Bundling them would make a safety-critical parse fix harder to
review.

Refs #1019
2026-07-31 08:42:48 -05:00

301 lines
8.9 KiB
Bash
Executable File

#!/bin/bash
# ci-queue-wait.sh - Wait until project CI queue is clear (no running/queued pipeline on branch head)
# Usage: ci-queue-wait.sh [-B branch] [-t timeout_sec] [-i interval_sec] [--purpose push|merge] [--require-status]
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/detect-platform.sh"
BRANCH="main"
TIMEOUT_SEC=900
INTERVAL_SEC=15
PURPOSE="merge"
REQUIRE_STATUS=0
usage() {
cat <<EOF
Usage: $(basename "$0") [-B branch] [-t timeout_sec] [-i interval_sec] [--purpose push|merge] [--require-status]
Options:
-B, --branch BRANCH Branch head to inspect (default: main)
-t, --timeout SECONDS Max wait time in seconds (default: 900)
-i, --interval SECONDS Poll interval in seconds (default: 15)
--purpose VALUE Log context: push|merge (default: merge)
--require-status Fail if no CI status contexts are present
-h, --help Show this help
Examples:
$(basename "$0")
$(basename "$0") --purpose push -B main -t 600 -i 10
EOF
}
# get_remote_host and get_gitea_token are provided by detect-platform.sh
get_state_from_status_json() {
# Capture piped JSON BEFORE invoking `python3 - <<PY`. The heredoc binds
# stdin to the Python program text — so json.load(sys.stdin) inside would
# try to re-read stdin after `-` already consumed it for the program,
# yielding EOF and returning "unknown" every time. Pass payload via env.
local payload
payload=$(cat)
CI_QUEUE_STATUS_JSON="$payload" python3 - <<'PY'
import json
import os
try:
payload = json.loads(os.environ.get("CI_QUEUE_STATUS_JSON", ""))
except Exception:
print("unknown")
raise SystemExit(0)
statuses = payload.get("statuses") or []
state = (payload.get("state") or "").lower()
pending_values = {"pending", "queued", "running", "waiting"}
failure_values = {"failure", "error", "failed"}
success_values = {"success"}
if state in pending_values:
print("pending")
raise SystemExit(0)
if state in failure_values:
print("terminal-failure")
raise SystemExit(0)
if state in success_values:
print("terminal-success")
raise SystemExit(0)
values = []
for item in statuses:
if not isinstance(item, dict):
continue
value = (item.get("status") or item.get("state") or "").lower()
if value:
values.append(value)
if not values and not state:
print("no-status")
elif any(v in pending_values for v in values):
print("pending")
elif any(v in failure_values for v in values):
print("terminal-failure")
elif values and all(v in success_values for v in values):
print("terminal-success")
else:
print("unknown")
PY
}
print_pending_contexts() {
# Same stdin hazard as get_state_from_status_json above — pass payload via env.
local payload
payload=$(cat)
CI_QUEUE_STATUS_JSON="$payload" python3 - <<'PY'
import json
import os
try:
payload = json.loads(os.environ.get("CI_QUEUE_STATUS_JSON", ""))
except Exception:
print("[ci-queue-wait] unable to decode status payload")
raise SystemExit(0)
statuses = payload.get("statuses") or []
if not statuses:
print("[ci-queue-wait] no status contexts reported")
raise SystemExit(0)
pending_values = {"pending", "queued", "running", "waiting"}
found = False
for item in statuses:
if not isinstance(item, dict):
continue
name = item.get("context") or item.get("name") or "unknown-context"
value = (item.get("status") or item.get("state") or "unknown").lower()
target = item.get("target_url") or item.get("url") or ""
if value in pending_values:
found = True
if target:
print(f"[ci-queue-wait] pending: {name}={value} ({target})")
else:
print(f"[ci-queue-wait] pending: {name}={value}")
if not found:
print("[ci-queue-wait] no pending contexts")
PY
}
github_get_branch_head_sha() {
local owner="$1"
local repo="$2"
local branch="$3"
gh api "repos/${owner}/${repo}/branches/${branch}" --jq '.commit.sha'
}
github_get_commit_status_json() {
local owner="$1"
local repo="$2"
local sha="$3"
gh api "repos/${owner}/${repo}/commits/${sha}/status"
}
gitea_get_branch_head_sha() {
local host="$1"
local repo="$2"
local branch="$3"
local token="$4"
local url="https://${host}/api/v1/repos/${repo}/branches/${branch}"
# Capture HTTP status so an absent branch (404) is distinguished from an API
# error. A not-yet-pushed feature branch has no in-flight pipeline, so the
# pre-push queue guard must treat 404 as "queue clear", not crash.
local resp code body
resp=$(curl -sS -H "User-Agent: curl/8" -H "Authorization: token ${token}" -w $'\n%{http_code}' "$url")
code="${resp##*$'\n'}"
body="${resp%$'\n'*}"
if [[ "$code" == "404" ]]; then
echo "__BRANCH_ABSENT__"
return 0
fi
if [[ "$code" != "200" ]]; then
return 1
fi
printf '%s' "$body" | python3 -c '
import json, sys
data = json.load(sys.stdin)
commit = data.get("commit") or {}
print((commit.get("id") or "").strip())
'
}
gitea_get_commit_status_json() {
local host="$1"
local repo="$2"
local sha="$3"
local token="$4"
local url="https://${host}/api/v1/repos/${repo}/commits/${sha}/status"
curl -fsSL -H "User-Agent: curl/8" -H "Authorization: token ${token}" "$url"
}
while [[ $# -gt 0 ]]; do
case "$1" in
-B|--branch)
BRANCH="$2"
shift 2
;;
-t|--timeout)
TIMEOUT_SEC="$2"
shift 2
;;
-i|--interval)
INTERVAL_SEC="$2"
shift 2
;;
--purpose)
PURPOSE="$2"
shift 2
;;
--require-status)
REQUIRE_STATUS=1
shift
;;
-h|--help)
usage
exit 0
;;
*)
echo "Unknown option: $1" >&2
usage >&2
exit 1
;;
esac
done
if ! [[ "$TIMEOUT_SEC" =~ ^[0-9]+$ ]] || ! [[ "$INTERVAL_SEC" =~ ^[0-9]+$ ]]; then
echo "Error: timeout and interval must be integer seconds." >&2
exit 1
fi
OWNER=$(get_repo_owner)
REPO=$(get_repo_name)
detect_platform > /dev/null
PLATFORM="${PLATFORM:-unknown}"
if [[ "$PLATFORM" == "github" ]]; then
if ! command -v gh >/dev/null 2>&1; then
echo "Error: gh CLI is required for GitHub CI queue guard." >&2
exit 1
fi
HEAD_SHA=$(github_get_branch_head_sha "$OWNER" "$REPO" "$BRANCH")
if [[ -z "$HEAD_SHA" ]]; then
echo "Error: Could not resolve ${BRANCH} head SHA." >&2
exit 1
fi
echo "[ci-queue-wait] platform=github purpose=${PURPOSE} branch=${BRANCH} sha=${HEAD_SHA}"
elif [[ "$PLATFORM" == "gitea" ]]; then
HOST=$(get_remote_host) || {
echo "Error: Could not determine remote host." >&2
exit 1
}
TOKEN=$(get_gitea_token "$HOST") || {
echo "Error: Gitea token not found. Set GITEA_TOKEN or configure ~/.git-credentials." >&2
exit 1
}
HEAD_SHA=$(gitea_get_branch_head_sha "$HOST" "$OWNER/$REPO" "$BRANCH" "$TOKEN")
if [[ "$HEAD_SHA" == "__BRANCH_ABSENT__" ]]; then
echo "[ci-queue-wait] branch ${BRANCH} not yet on remote — no in-flight pipeline; queue clear."
exit 0
fi
if [[ -z "$HEAD_SHA" ]]; then
echo "Error: Could not resolve ${BRANCH} head SHA." >&2
exit 1
fi
echo "[ci-queue-wait] platform=gitea purpose=${PURPOSE} branch=${BRANCH} sha=${HEAD_SHA}"
else
echo "Error: Unsupported platform '${PLATFORM}'." >&2
exit 1
fi
START_TS=$(date +%s)
DEADLINE_TS=$((START_TS + TIMEOUT_SEC))
while true; do
NOW_TS=$(date +%s)
if (( NOW_TS > DEADLINE_TS )); then
echo "Error: Timed out waiting for CI queue to clear on ${BRANCH} after ${TIMEOUT_SEC}s." >&2
exit 124
fi
if [[ "$PLATFORM" == "github" ]]; then
STATUS_JSON=$(github_get_commit_status_json "$OWNER" "$REPO" "$HEAD_SHA")
else
STATUS_JSON=$(gitea_get_commit_status_json "$HOST" "$OWNER/$REPO" "$HEAD_SHA" "$TOKEN")
fi
STATE=$(printf '%s' "$STATUS_JSON" | get_state_from_status_json)
echo "[ci-queue-wait] state=${STATE} purpose=${PURPOSE} branch=${BRANCH}"
case "$STATE" in
pending)
printf '%s' "$STATUS_JSON" | print_pending_contexts
sleep "$INTERVAL_SEC"
;;
no-status)
if [[ "$REQUIRE_STATUS" -eq 1 ]]; then
echo "Error: No CI status contexts found for ${BRANCH} while --require-status is set." >&2
exit 1
fi
echo "[ci-queue-wait] no status contexts present; proceeding."
exit 0
;;
terminal-success|terminal-failure|unknown)
# Queue guard only blocks on pending/running/queued states.
exit 0
;;
*)
echo "[ci-queue-wait] unrecognized state '${STATE}', proceeding conservatively."
exit 0
;;
esac
done