feat(fleet): launcher heartbeat sidecar — HB for all runtimes (pi/claude/codex) (#584)

packages/mosaic/framework/tools/fleet/start-agent-session.sh

@@ -6,6 +6,8 @@ MOSAIC_TMUX_SOCKET=${MOSAIC_TMUX_SOCKET:-mosaic-factory}
 MOSAIC_AGENT_RUNTIME=${MOSAIC_AGENT_RUNTIME:-pi}
 MOSAIC_AGENT_WORKDIR=${MOSAIC_AGENT_WORKDIR:-$HOME}
 MOSAIC_AGENT_COMMAND=${MOSAIC_AGENT_COMMAND:-}
+MOSAIC_HEARTBEAT_RUN_DIR=${MOSAIC_HEARTBEAT_RUN_DIR:-$HOME/.config/mosaic/fleet/run}
+MOSAIC_HEARTBEAT_INTERVAL=${MOSAIC_HEARTBEAT_INTERVAL:-15}
 
 if [ -z "$AGENT_NAME" ]; then
   echo "ERROR: agent name argument or MOSAIC_AGENT_NAME is required" >&2
@@ -96,5 +98,55 @@ else
 fi
 
 mkdir -p "$MOSAIC_AGENT_WORKDIR"
-exec tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
+
+# ── Launch the tmux session (no exec — we continue to wire the heartbeat) ────
+tmux -L "$MOSAIC_TMUX_SOCKET" new-session -d -s "$AGENT_NAME" -c "$MOSAIC_AGENT_WORKDIR" \
   bash -c "$PANE_SHELL_SNIPPET"
+
+# ── Resolve the pane PID (retry briefly to let the session initialise) ────────
+PANE_PID=""
+for _retry in 1 2 3 4 5; do
+  PANE_PID=$(tmux -L "$MOSAIC_TMUX_SOCKET" list-panes \
+    -t "=${AGENT_NAME}:0.0" -F '#{pane_pid}' 2>/dev/null || true)
+  [ -n "$PANE_PID" ] && break
+  sleep 0.2
+done
+
+# ── Spawn the heartbeat sidecar (detached, best-effort) ──────────────────────
+# The sidecar writes ~/.config/mosaic/fleet/run/<AGENT>.hb atomically while the
+# pane process is alive, then exits so the file goes stale (fleet ps shows stale
+# then PANE=dead).  It is runtime-agnostic: it only cares about the pane PID.
+_start_heartbeat_sidecar() {
+  local agent="$1"
+  local pane_pid="$2"
+  local run_dir="$3"
+  local interval="$4"
+  local hb_file="${run_dir}/${agent}.hb"
+
+  mkdir -p "$run_dir"
+
+  # Write the sidecar as a self-contained bash one-liner so it carries no
+  # references to any variables from this script's environment.
+  local sidecar_script
+  sidecar_script=$(printf \
+    'hb=%s; pid=%s; iv=%s; mkdir -p "$(dirname "$hb")"; while kill -0 "$pid" 2>/dev/null; do tmp="$hb.tmp.$$"; printf "ts=%%s\npid=%%s\nstatus=ok\n" "$(date +%%Y-%%m-%%dT%%H:%%M:%%S%%z)" "$pid" > "$tmp" && mv "$tmp" "$hb"; sleep "$iv"; done' \
+    "$hb_file" "$pane_pid" "$interval")
+
+  # setsid + disown ensures the sidecar survives this script exiting.
+  # stderr/stdout go to /dev/null; failures are non-fatal.
+  if command -v setsid >/dev/null 2>&1; then
+    setsid bash -c "$sidecar_script" </dev/null >/dev/null 2>&1 &
+  else
+    bash -c "$sidecar_script" </dev/null >/dev/null 2>&1 &
+  fi
+  disown $! 2>/dev/null || true
+}
+
+if [ -n "$PANE_PID" ]; then
+  # Guard: do not let sidecar startup failures abort the launcher (set -e).
+  _start_heartbeat_sidecar "$AGENT_NAME" "$PANE_PID" \
+    "$MOSAIC_HEARTBEAT_RUN_DIR" "$MOSAIC_HEARTBEAT_INTERVAL" || \
+    echo "WARNING: heartbeat sidecar could not be started for $AGENT_NAME" >&2
+else
+  echo "WARNING: could not resolve pane PID for $AGENT_NAME — heartbeat sidecar not started" >&2
+fi