chore: consolidate new foundation and archive v1 (#1495)

2026-09-07 12:32:57 -05:00
parent 9a5fbdbda7 5d27700026
commit 127a54fdff
3511 changed files with 727899 additions and 10 deletions
@@ -0,0 +1,372 @@
+#!/bin/bash
+# pr-ci-wait.sh - Wait for PR CI status to reach terminal state (GitHub/Gitea)
+# Usage: pr-ci-wait.sh -n <pr_number> [-r owner/repo] [-t timeout_sec] [-i interval_sec]
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "$SCRIPT_DIR/detect-platform.sh"
+
+PR_NUMBER=""
+TIMEOUT_SEC=1800
+INTERVAL_SEC=15
+REPO_OVERRIDE=""
+HOST_OVERRIDE=""
+
+usage() {
+    cat <<EOF
+Usage: $(basename "$0") -n <pr_number> [-t timeout_sec] [-i interval_sec]
+
+Options:
+  -n, --number NUMBER      PR number (required)
+  -r, --repo OWNER/REPO    Repository slug (default: infer from git origin)
+      --host HOST          Gitea host for --repo API calls (or set GITEA_HOST/GITEA_URL)
+  -t, --timeout SECONDS    Max wait time in seconds (default: 1800)
+  -i, --interval SECONDS   Poll interval in seconds (default: 15)
+  -h, --help               Show this help
+
+Examples:
+  $(basename "$0") -n 643
+  $(basename "$0") -n 643 --repo ddk/ai-bma
+  $(basename "$0") -n 643 -t 900 -i 10
+EOF
+}
+
+# get_remote_host and get_gitea_token are provided by detect-platform.sh
+
+extract_state_from_status_json() {
+    # Capture piped JSON BEFORE invoking `python3 - <<PY`. The heredoc binds
+    # stdin to the Python program text — so json.load(sys.stdin) inside would
+    # try to re-read stdin after `-` already consumed it for the program,
+    # yielding EOF and returning "unknown" every time. Pass payload via env.
+    local payload
+    payload=$(cat)
+    PR_CI_STATUS_JSON="$payload" python3 - <<'PY'
+import json
+import os
+import sys
+
+try:
+    payload = json.loads(os.environ.get("PR_CI_STATUS_JSON", ""))
+except Exception:
+    print("unknown")
+    raise SystemExit(0)
+
+state = (payload.get("state") or "").lower()
+if state in {"success", "pending", "failure", "error"}:
+    print(state)
+    raise SystemExit(0)
+
+statuses = payload.get("statuses") or []
+values = []
+for item in statuses:
+    if not isinstance(item, dict):
+        continue
+    value = (item.get("status") or item.get("state") or "").lower()
+    if value:
+        values.append(value)
+
+if any(v in {"failure", "error"} for v in values):
+    print("failure")
+elif values and all(v == "success" for v in values):
+    print("success")
+elif any(v in {"pending", "running", "queued", "waiting"} for v in values):
+    print("pending")
+elif not values and not state:
+    # No pipeline/status of any kind reported for this commit. Distinct from
+    # "unknown" (an ambiguous/unrecognized status that should keep polling):
+    # this signals a repo/commit that simply has no CI configured.
+    print("no-status")
+else:
+    print("unknown")
+PY
+}
+
+print_status_summary() {
+    # Same stdin-collision fix as extract_state_from_status_json above.
+    local payload
+    payload=$(cat)
+    PR_CI_STATUS_JSON="$payload" python3 - <<'PY'
+import json
+import os
+import sys
+
+try:
+    payload = json.loads(os.environ.get("PR_CI_STATUS_JSON", ""))
+except Exception:
+    print("[pr-ci-wait] status payload unavailable")
+    raise SystemExit(0)
+
+statuses = payload.get("statuses") or []
+if not statuses:
+    print("[pr-ci-wait] no status contexts reported yet")
+    raise SystemExit(0)
+
+for item in statuses:
+    if not isinstance(item, dict):
+        continue
+    name = item.get("context") or item.get("name") or "unknown-context"
+    state = item.get("status") or item.get("state") or "unknown-state"
+    target = item.get("target_url") or item.get("url") or ""
+    if target:
+        print(f"[pr-ci-wait] {name}: {state} ({target})")
+    else:
+        print(f"[pr-ci-wait] {name}: {state}")
+PY
+}
+
+github_get_pr_head_sha() {
+    gh pr view "$PR_NUMBER" --repo "$OWNER/$REPO" --json headRefOid --jq '.headRefOid'
+}
+
+github_get_commit_status_json() {
+    local owner="$1"
+    local repo="$2"
+    local sha="$3"
+    gh api "repos/${owner}/${repo}/commits/${sha}/status"
+}
+
+gitea_get_pr_head_sha() {
+    local host="$1"
+    local repo="$2"
+    local token="$3"
+    local url="https://${host}/api/v1/repos/${repo}/pulls/${PR_NUMBER}"
+    curl -fsSL -H "User-Agent: curl/8" -H "Authorization: token ${token}" "$url" | python3 -c '
+import json, sys
+data = json.load(sys.stdin)
+print((data.get("head") or {}).get("sha", ""))
+'
+}
+
+gitea_get_commit_status_json() {
+    local host="$1"
+    local repo="$2"
+    local token="$3"
+    local sha="$4"
+    local url="https://${host}/api/v1/repos/${repo}/commits/${sha}/status"
+    curl -fsSL -H "User-Agent: curl/8" -H "Authorization: token ${token}" "$url"
+}
+
+gitea_get_default_branch() {
+    local host="$1"
+    local repo="$2"
+    local token="$3"
+    local url="https://${host}/api/v1/repos/${repo}"
+    curl -fsSL -H "User-Agent: curl/8" -H "Authorization: token ${token}" "$url" | python3 -c '
+import json, sys
+print((json.load(sys.stdin) or {}).get("default_branch", ""))
+'
+}
+
+github_get_default_branch() {
+    gh api "repos/${OWNER}/${REPO}" --jq '.default_branch'
+}
+
+while [[ $# -gt 0 ]]; do
+    case "$1" in
+        -n|--number)
+            PR_NUMBER="$2"
+            shift 2
+            ;;
+        -r|--repo)
+            REPO_OVERRIDE="$2"
+            shift 2
+            ;;
+        --host)
+            HOST_OVERRIDE="$2"
+            shift 2
+            ;;
+        -t|--timeout)
+            TIMEOUT_SEC="$2"
+            shift 2
+            ;;
+        -i|--interval)
+            INTERVAL_SEC="$2"
+            shift 2
+            ;;
+        -h|--help)
+            usage
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1" >&2
+            usage >&2
+            exit 1
+            ;;
+    esac
+done
+
+if [[ -z "$PR_NUMBER" ]]; then
+    echo "Error: PR number is required (-n)." >&2
+    usage >&2
+    exit 1
+fi
+
+if ! [[ "$TIMEOUT_SEC" =~ ^[0-9]+$ ]] || ! [[ "$INTERVAL_SEC" =~ ^[0-9]+$ ]]; then
+    echo "Error: timeout and interval must be integer seconds." >&2
+    exit 1
+fi
+
+if [[ -n "$REPO_OVERRIDE" ]]; then
+    REPO_INFO="$REPO_OVERRIDE"
+    PLATFORM=$(detect_platform 2>/dev/null || echo gitea)
+else
+    detect_platform > /dev/null
+    REPO_INFO=$(get_repo_info)
+fi
+
+if [[ -z "$REPO_INFO" || "$REPO_INFO" == error:* || "$REPO_INFO" != */* ]]; then
+    echo "Error: Could not determine repository from git origin. Run from a repo or pass --repo owner/repo." >&2
+    exit 1
+fi
+
+OWNER=${REPO_INFO%%/*}
+REPO=${REPO_INFO##*/}
+START_TS=$(date +%s)
+DEADLINE_TS=$((START_TS + TIMEOUT_SEC))
+
+if [[ "$PLATFORM" == "github" ]]; then
+    if ! command -v gh >/dev/null 2>&1; then
+        echo "Error: gh CLI is required for GitHub CI status polling." >&2
+        exit 1
+    fi
+    HEAD_SHA=$(github_get_pr_head_sha)
+    if [[ -z "$HEAD_SHA" ]]; then
+        echo "Error: Could not resolve head SHA for PR #$PR_NUMBER." >&2
+        exit 1
+    fi
+    echo "[pr-ci-wait] Platform=github PR=#${PR_NUMBER} head_sha=${HEAD_SHA}"
+elif [[ "$PLATFORM" == "gitea" ]]; then
+    if [[ -n "$HOST_OVERRIDE" ]]; then
+        HOST="$HOST_OVERRIDE"
+    elif [[ -n "$REPO_OVERRIDE" ]]; then
+        HOST=$(get_gitea_api_host_for_repo_override) || {
+            echo "Error: Gitea host is required with --repo. Pass --host or set GITEA_HOST/GITEA_URL." >&2
+            exit 1
+        }
+    else
+        HOST=$(get_remote_host) || {
+            echo "Error: Could not determine Gitea host from git origin." >&2
+            exit 1
+        }
+    fi
+    TOKEN=$(get_gitea_token "$HOST") || {
+        echo "Error: Gitea token not found. Set GITEA_TOKEN or configure ~/.git-credentials." >&2
+        exit 1
+    }
+    HEAD_SHA=$(gitea_get_pr_head_sha "$HOST" "$OWNER/$REPO" "$TOKEN")
+    if [[ -z "$HEAD_SHA" ]]; then
+        echo "Error: Could not resolve head SHA for PR #$PR_NUMBER." >&2
+        exit 1
+    fi
+    echo "[pr-ci-wait] Platform=gitea host=${HOST} repo=${OWNER}/${REPO} PR=#${PR_NUMBER} head_sha=${HEAD_SHA}"
+else
+    echo "Error: Unsupported platform '${PLATFORM}'." >&2
+    exit 1
+fi
+
+# No-CI determination is TWO-TIER (primary: CI history; secondary: empty-poll streak).
+#
+# PRIMARY — "does this repo run CI at all?" Probed once, up front, from the DEFAULT
+# BRANCH's commit status. A repo whose default branch carries CI statuses
+# demonstrably runs CI, so an EMPTY status on the PR head means the pipeline simply
+# has not registered YET (webhook/queue lag) — NOT that the repo is CI-less. In that
+# case we must NEVER fast-green; we keep polling until the pipeline registers or the
+# timeout fires (both safe). This closes the webhook-lag false-green: a slow-to-
+# register pipeline feeding a merge gate can no longer be mistaken for "no CI".
+#
+# SECONDARY — the empty-poll streak below applies ONLY to genuinely CI-less repos
+# (default branch also has no CI history, e.g. device-imaging class), where burning
+# the full timeout would be pure waste. There, NO_CI_MAX empty polls => fast-exit 0.
+#
+# Probe failure is treated conservatively as REPO_HAS_CI=1 (assume CI present): we
+# would rather wait-then-timeout than risk a false-green, per the merge-gate priority.
+REPO_HAS_CI=1
+detect_repo_ci() {
+    local def_branch def_status
+    # Every early exit returns 0: a probe miss must leave the conservative
+    # REPO_HAS_CI=1 default in place, never abort the caller under `set -e`.
+    if [[ "$PLATFORM" == "github" ]]; then
+        def_branch=$(github_get_default_branch 2>/dev/null) || {
+            echo "[pr-ci-wait] WARN: default-branch probe failed; assuming CI-enabled (will not fast-green on empty status)."; return 0; }
+        [[ -n "$def_branch" ]] || return 0
+        def_status=$(github_get_commit_status_json "$OWNER" "$REPO" "$def_branch" 2>/dev/null | extract_state_from_status_json) || return 0
+    else
+        def_branch=$(gitea_get_default_branch "$HOST" "$OWNER/$REPO" "$TOKEN" 2>/dev/null) || {
+            echo "[pr-ci-wait] WARN: default-branch probe failed; assuming CI-enabled (will not fast-green on empty status)."; return 0; }
+        [[ -n "$def_branch" ]] || return 0
+        def_status=$(gitea_get_commit_status_json "$HOST" "$OWNER/$REPO" "$TOKEN" "$def_branch" 2>/dev/null | extract_state_from_status_json) || return 0
+    fi
+    if [[ "$def_status" == "no-status" || -z "$def_status" ]]; then
+        REPO_HAS_CI=0
+        echo "[pr-ci-wait] default branch '${def_branch}' has no CI status history — treating repo as CI-less (empty-poll fast-exit enabled)."
+    else
+        REPO_HAS_CI=1
+        echo "[pr-ci-wait] default branch '${def_branch}' has CI history (state=${def_status}) — repo runs CI; empty status on PR head => awaiting registration, will not fast-green."
+    fi
+}
+detect_repo_ci || true
+
+NO_CI_STREAK=0
+NO_CI_MAX=3
+
+while true; do
+    NOW_TS=$(date +%s)
+    if (( NOW_TS > DEADLINE_TS )); then
+        echo "Error: Timed out waiting for CI status on PR #$PR_NUMBER 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" "$TOKEN" "$HEAD_SHA")
+    fi
+
+    STATE=$(printf '%s' "$STATUS_JSON" | extract_state_from_status_json)
+    echo "[pr-ci-wait] state=${STATE} pr=#${PR_NUMBER} sha=${HEAD_SHA}"
+
+    case "$STATE" in
+        success)
+            printf '%s' "$STATUS_JSON" | print_status_summary
+            echo "[pr-ci-wait] CI is green for PR #$PR_NUMBER."
+            exit 0
+            ;;
+        failure|error)
+            printf '%s' "$STATUS_JSON" | print_status_summary
+            echo "Error: CI reported ${STATE} for PR #$PR_NUMBER." >&2
+            exit 1
+            ;;
+        no-status)
+            if [[ "$REPO_HAS_CI" == "1" ]]; then
+                # PRIMARY tier: repo demonstrably runs CI but this commit's pipeline
+                # has not registered yet (webhook/queue lag). Do NOT fast-green — keep
+                # polling until it registers or the timeout fires. Reset the streak so
+                # a later genuine CI-less misread can't accumulate across this state.
+                NO_CI_STREAK=0
+                echo "[pr-ci-wait] empty status on PR head but repo runs CI — awaiting pipeline registration (webhook lag), not fast-greening."
+            else
+                # SECONDARY tier: genuinely CI-less repo (default branch has no CI
+                # history either). Empty polls => fast-exit green after NO_CI_MAX.
+                NO_CI_STREAK=$((NO_CI_STREAK + 1))
+                if (( NO_CI_STREAK >= NO_CI_MAX )); then
+                    echo "[INFO] no CI configured for this repo/commit (PR #$PR_NUMBER, ${NO_CI_STREAK} consecutive empty polls, default branch also CI-less); treating as green."
+                    exit 0
+                fi
+            fi
+            sleep "$INTERVAL_SEC"
+            ;;
+        pending|unknown)
+            # A pipeline exists but hasn't reached a terminal state (or is
+            # transiently ambiguous) — keep waiting, and reset the no-CI streak
+            # since this commit is not in the "no CI at all" condition.
+            NO_CI_STREAK=0
+            sleep "$INTERVAL_SEC"
+            ;;
+        *)
+            echo "[pr-ci-wait] Unrecognized state '${STATE}', continuing to poll..."
+            NO_CI_STREAK=0
+            sleep "$INTERVAL_SEC"
+            ;;
+    esac
+done