feat(framework/tools): orchestration helpers — lane-brief.sh + ci-wait.sh (#547)

packages/mosaic/framework/tools/woodpecker/README.md

@@ -31,6 +31,7 @@ A Woodpecker API token is required. To configure:
 | `pipeline-list.sh`    | List recent pipelines for a repo            |
 | `pipeline-status.sh`  | Get status of a specific or latest pipeline |
 | `pipeline-trigger.sh` | Trigger a new pipeline build                |
+| `ci-wait.sh`          | Block until pipeline(s) reach terminal state |
 
 ## Common Options
 
@@ -55,4 +56,7 @@ A Woodpecker API token is required. To configure:
 
 # Trigger a build on a specific branch
 ~/.config/mosaic/tools/woodpecker/pipeline-trigger.sh -b feature/my-branch
+
+# Block until one or more pipelines finish (event-driven CI wait)
+~/.config/mosaic/tools/woodpecker/ci-wait.sh -r usc/uconnect -n 3917 -n 3918
 ```

packages/mosaic/framework/tools/woodpecker/ci-wait.sh

@@ -0,0 +1,86 @@
+#!/usr/bin/env bash
+# ci-wait.sh — block until one or more Woodpecker pipelines reach terminal state.
+#
+# Problem it solves: orchestrators hand-author a `while true; curl .../repos/1/pipelines/$n
+# ...; sleep` loop for every CI wait. Those loops HARDCODE Woodpecker repo id 1 (only
+# correct for whichever repo happens to be id 1), re-implement URL building with raw
+# curl, and tend to get armed as tight <300s ScheduleWakeup polls (each poll = a full
+# wake+reload+recheck cycle). This encapsulates the loop once, on top of the existing
+# `pipeline-status.sh` wrapper (which resolves repo->id correctly and is instance-aware),
+# so a CI wait becomes a one-liner.
+#
+# Intended use: as the COMMAND of a Monitor / event-driven re-invoke (primary), paired
+# with a single long (>=1500s) timed fallback — NOT as a tight standalone poll.
+#
+# Usage:
+#   ci-wait.sh -r <owner/repo> -n <num> [-n <num> ...] [-a <instance>] [-i <interval>] [-t <timeout>]
+#   ci-wait.sh -r usc/uconnect -n 3917 -n 3918              # wait for both, infer instance
+#   ci-wait.sh -r usc/uconnect -n 3922 -a usc -i 30 -t 2400
+#
+# Instance is inferred from the owner (usc->usc, mosaicstack/mosaic->mosaic) unless -a given.
+# Exit: 0 = all pipelines terminal AND all 'success'; 1 = >=1 terminal non-success;
+#       2 = usage/precondition error; 3 = timeout before all terminal.
+set -euo pipefail
+
+# Resolve pipeline-status.sh as a sibling, matching how the woodpecker tools source
+# _lib.sh — works under the installed runtime AND an in-repo checkout, no MOSAIC_HOME dep.
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PS="$SCRIPT_DIR/pipeline-status.sh"
+
+REPO="" INSTANCE="" INTERVAL=30 TIMEOUT=3600
+NUMS=()
+while getopts "r:n:a:i:t:h" opt; do
+  case "$opt" in
+    r) REPO="$OPTARG" ;;
+    n) NUMS+=("$OPTARG") ;;
+    a) INSTANCE="$OPTARG" ;;
+    i) INTERVAL="$OPTARG" ;;
+    t) TIMEOUT="$OPTARG" ;;
+    h) grep '^#' "$0" | sed 's/^# \?//'; exit 0 ;;
+    *) echo "see -h" >&2; exit 2 ;;
+  esac
+done
+[[ -n "$REPO" ]] || { echo "FATAL: -r <owner/repo> required" >&2; exit 2; }
+[[ ${#NUMS[@]} -gt 0 ]] || { echo "FATAL: at least one -n <pipeline-number> required" >&2; exit 2; }
+[[ -x "$PS" ]] || { echo "FATAL: pipeline-status.sh not found/executable at $PS" >&2; exit 2; }
+
+# Infer Woodpecker instance from owner unless overridden (matches the git-wrapper convention).
+if [[ -z "$INSTANCE" ]]; then
+  case "${REPO%%/*}" in
+    usc|USC) INSTANCE=usc ;;
+    mosaicstack|mosaic) INSTANCE=mosaic ;;
+    *) echo "FATAL: cannot infer Woodpecker instance for owner '${REPO%%/*}' — pass -a <instance>" >&2; exit 2 ;;
+  esac
+fi
+
+command -v jq >/dev/null || { echo "FATAL: jq not found" >&2; exit 2; }
+
+TERMINAL_RE='^(success|failure|error|killed|declined|blocked)$'
+declare -A STATE=()        # num -> terminal status, once reached
+start=$(date +%s 2>/dev/null || echo 0)
+
+echo "ci-wait: $REPO pipelines [${NUMS[*]}] (instance=$INSTANCE, every ${INTERVAL}s, timeout ${TIMEOUT}s)"
+while true; do
+  for n in "${NUMS[@]}"; do
+    [[ -n "${STATE[$n]:-}" ]] && continue
+    s=$("$PS" -r "$REPO" -n "$n" -a "$INSTANCE" -f json 2>/dev/null | jq -r '.status // empty' 2>/dev/null || true)
+    if [[ "$s" =~ $TERMINAL_RE ]]; then
+      STATE[$n]="$s"
+      echo "  pipeline $n TERMINAL: $s"
+    fi
+  done
+  # all terminal?
+  if [[ ${#STATE[@]} -eq ${#NUMS[@]} ]]; then
+    bad=0
+    for n in "${NUMS[@]}"; do [[ "${STATE[$n]}" == "success" ]] || bad=1; done
+    if [[ $bad -eq 0 ]]; then echo "ci-wait: ALL SUCCESS"; exit 0; fi
+    echo "ci-wait: all terminal, NOT all success — $(for n in "${NUMS[@]}"; do printf '%s=%s ' "$n" "${STATE[$n]}"; done)"
+    exit 1
+  fi
+  now=$(date +%s 2>/dev/null || echo 0)
+  if [[ "$start" != 0 && $((now - start)) -ge $TIMEOUT ]]; then
+    echo "ci-wait: TIMEOUT after ${TIMEOUT}s — pending: $(for n in "${NUMS[@]}"; do [[ -z "${STATE[$n]:-}" ]] && printf '%s ' "$n"; done)"
+    exit 3
+  fi
+  sleep "$INTERVAL"
+done

packages/mosaic/framework/tools/woodpecker/test-ci-wait-exit-matrix.sh

@@ -0,0 +1,76 @@
+#!/usr/bin/env bash
+# Regression harness for ci-wait.sh terminal-state aggregation and exit codes.
+#
+# ci-wait.sh wraps pipeline-status.sh and blocks until every requested pipeline
+# reaches a terminal Woodpecker state, then maps the aggregate to an exit code.
+# That contract is what callers arm a Monitor/timed-fallback around, so it must be
+# exact. This harness drives ci-wait.sh against a stub pipeline-status.sh whose
+# per-pipeline status is fixture-controlled, and asserts the full exit matrix:
+#
+#   0 = every pipeline terminal AND all 'success'
+#   1 = every pipeline terminal, at least one non-success
+#   2 = usage/precondition error (missing -n)
+#   3 = timeout before all pipelines terminal
+#
+# Non-vacuity: each case pins a DISTINCT exit code to a distinct fixture, so a
+# regression in success-aggregation (case 0 vs 1), terminal detection (case 3),
+# or arg validation (case 2) flips exactly one assertion RED.
+
+set -euo pipefail
+
+CIW_SRC="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/ci-wait.sh"
+WORK_DIR="${MOSAIC_TEST_WORK_DIR:-$PWD/.mosaic-test-work/ci-wait-exit-matrix}"
+TOOL_DIR="$WORK_DIR/tool"
+
+rm -rf "$WORK_DIR"
+mkdir -p "$TOOL_DIR"
+
+# ci-wait.sh resolves pipeline-status.sh as a sibling ($SCRIPT_DIR/pipeline-status.sh),
+# so we run a COPY of ci-wait.sh next to a stub sibling we control.
+cp "$CIW_SRC" "$TOOL_DIR/ci-wait.sh"
+chmod +x "$TOOL_DIR/ci-wait.sh"
+
+# Stub pipeline-status.sh: emits {"status":"<s>"} where <s> comes from env
+# CIW_STATUS_<num> (default "running" = non-terminal, drives the timeout path).
+cat > "$TOOL_DIR/pipeline-status.sh" <<'SH'
+#!/usr/bin/env bash
+set -euo pipefail
+num=""
+while getopts "r:n:a:f:" opt; do case "$opt" in n) num="$OPTARG" ;; *) : ;; esac; done
+var="CIW_STATUS_${num}"
+printf '{"status":"%s"}\n' "${!var:-running}"
+SH
+chmod +x "$TOOL_DIR/pipeline-status.sh"
+
+CIW="$TOOL_DIR/ci-wait.sh"
+
+run_expect() { # $1 = expected exit  $2 = label ; rest = args
+  local want="$1" label="$2"; shift 2
+  local rc=0
+  "$CIW" "$@" >/dev/null 2>&1 || rc=$?
+  if [[ "$rc" -ne "$want" ]]; then
+    echo "FAIL [$label]: expected exit $want, got $rc" >&2; exit 1
+  fi
+  echo "PASS [$label]: exit $rc"
+}
+
+# 0 — both pipelines terminal + success
+CIW_STATUS_100=success CIW_STATUS_101=success \
+  run_expect 0 "all-success" -r mosaic/stack -n 100 -n 101 -a mosaic -i 1 -t 30
+
+# 1 — both terminal, one failure
+CIW_STATUS_100=success CIW_STATUS_101=failure \
+  run_expect 1 "terminal-not-success" -r mosaic/stack -n 100 -n 101 -a mosaic -i 1 -t 30
+
+# 1 — other terminal non-success states still map to 1 (error/killed)
+CIW_STATUS_100=error CIW_STATUS_101=killed \
+  run_expect 1 "terminal-error-killed" -r mosaic/stack -n 100 -n 101 -a mosaic -i 1 -t 30
+
+# 3 — a pipeline never reaches terminal state before timeout
+CIW_STATUS_100=success CIW_STATUS_101=running \
+  run_expect 3 "timeout-pending" -r mosaic/stack -n 100 -n 101 -a mosaic -i 1 -t 0
+
+# 2 — usage error: no -n
+run_expect 2 "usage-missing-n" -r mosaic/stack -a mosaic
+
+echo "ALL PASS: test-ci-wait-exit-matrix.sh"