no-mistakes(review): fix pending-reload path, token modes, restart check

scripts/capture-dsh-token.sh

@@ -71,6 +71,21 @@ if [ -e "$LEGACY_8081" ] || [ -L "$LEGACY_8081" ]; then
   log "removed legacy :8081 endpoint -> $STASHED"
 fi
 
+# ── 1b. Honor a recorded pending reload regardless of token selection ───────
+# A failed reload leaves PENDING_FILE set so a stashed legacy :8081 file can
+# never remain loaded in the running nginx while dsh-web is down or not yet
+# answering. Reconcile it before the token wait.
+if [ -e "$PENDING_FILE" ]; then
+  if ! nginx -t >/dev/null 2>&1; then
+    die "pending nginx reload recorded but 'nginx -t' fails; fix the config and rerun"
+  fi
+  if ! nginx -s reload; then
+    die "pending nginx reload recorded but 'nginx -s reload' failed; will retry next run"
+  fi
+  rm -f "$PENDING_FILE"
+  log "completed pending nginx reload"
+fi
+
 # ── 2. Select the token the RUNNING service actually accepts ────────────────
 # Functionally verify each journal candidate against the local dsh-web using the
 # public authority, exactly as the /dsh-web-login proxy does. A token from a
@@ -114,6 +129,7 @@ if ! printf '%s\n' "$TOKEN" | cmp -s - "$TOKEN_FILE" 2>/dev/null; then
   mv "$TOKEN_FILE.tmp" "$TOKEN_FILE"
   log "recorded live launch token in $TOKEN_FILE"
 fi
+chmod 600 "$TOKEN_FILE"
 
 # ── 4. Regenerate the nginx login include (reload only when it changes) ────
 NEW_INCLUDE="$(mktemp "$INCLUDE_FILE.XXXXXX")"
@@ -126,6 +142,8 @@ chmod 600 "$NEW_INCLUDE"
 # reload path so the include can never silently diverge from what nginx serves.
 APPLIED=""
 [ -f "$STAMP_FILE" ] && APPLIED="$(cat "$STAMP_FILE" 2>/dev/null || true)"
+[ -f "$INCLUDE_FILE" ] && chmod 600 "$INCLUDE_FILE"
+[ -f "$STAMP_FILE" ] && chmod 600 "$STAMP_FILE"
 
 if [ "$APPLIED" = "$TOKEN" ] && [ -f "$INCLUDE_FILE" ] && cmp -s "$NEW_INCLUDE" "$INCLUDE_FILE" \
   && [ ! -e "$PENDING_FILE" ]; then
@@ -140,6 +158,7 @@ RESTORE=""
 if [ -f "$INCLUDE_FILE" ]; then
   RESTORE="$(mktemp "$INCLUDE_FILE.bak.XXXXXX")"
   cp -p "$INCLUDE_FILE" "$RESTORE"
+  chmod 600 "$RESTORE"
 fi
 
 mv "$NEW_INCLUDE" "$INCLUDE_FILE"

zulip-health.prose.md

@@ -305,10 +305,11 @@ reloading nginx only when the on-disk include differs from the generated one or
 the applied-state stamp does not match the token (`nginx -t` guards the reload,
 and the stamp is written only after a successful `nginx -s reload`, so a failed
 or interrupted reload is retried on the next run). Any failed reload records a
-pending-reload marker under `/etc/dsh-web/` that forces the next run through the
+pending-reload marker under `/etc/dsh-web/`; the next run honors it before the
-reload path even when the token is unchanged, so a disabled legacy `:8081` file
+token wait, reloading nginx and clearing the marker regardless of token state,
-can never leave the running nginx unreloaded. Runs are serialized with
+so a disabled legacy `:8081` file can never leave the running nginx unreloaded.
-`flock` on `/run/capture-dsh-token.lock`. It **never stops or starts `dsh-web`**.
+Runs are serialized with `flock` on `/run/capture-dsh-token.lock`. It **never
+stops or starts `dsh-web`**.
 It is triggered by the `dsh-web.service` drop-in
 `/etc/systemd/system/dsh-web.service.d/20-token-refresh.conf`
 (`ExecStartPost=/bin/systemctl --no-block start dsh-web-token.service`) and by
@@ -393,11 +394,20 @@ fresh cookie. Both verified live 2026-09-11.
 ```bash
 # 5. Cookie survives a dsh-web restart, and the new token mints a new cookie.
 ssh root@192.168.68.15 "pct exec 112 -- systemctl restart dsh-web"
-ssh root@192.168.68.15 "pct exec 112 -- /opt/deepseek-harness/capture-dsh-token.sh"
 ssh root@192.168.68.15 "pct exec 112 -- curl -s -b /tmp/dsh.jar -o /dev/null \
   -w '%{http_code}\n' -H 'Host: tankodhs.sysloggh.net' http://127.0.0.1:3080/"
 # Expected: 200 — the pre-restart cookie is still accepted.
-TOKEN=$(ssh root@192.168.68.15 "pct exec 112 -- cat /etc/dsh-web/launch-token")
+# The restart's ExecStartPost (or the 2-minute timer) refreshes the include. A
+# manual run may no-op on the flock, so poll until the include carries a token
+# the running process accepts (bounded wait) before the mint+reuse check.
+for i in $(seq 1 60); do
+  TOKEN=$(ssh root@192.168.68.15 "pct exec 112 -- sed -n 's/.*token=//p' /etc/dsh-web/nginx-login.conf | tr -d ';\n'")
+  CODE=$(ssh root@192.168.68.15 "pct exec 112 -- curl -s -o /dev/null -w '%{http_code}' \
+    -H 'Host: tankodhs.sysloggh.net' 'http://127.0.0.1:3080/?token=$TOKEN'")
+  [ "$CODE" = "303" ] && break
+  sleep 2
+done
+# Expected: 303 — the include now holds the token the running process accepts.
 ssh root@192.168.68.15 "pct exec 112 -- curl -s -c /tmp/dsh-new.jar -o /dev/null \
   -H 'Host: tankodhs.sysloggh.net' 'http://127.0.0.1:3080/?token=$TOKEN'"
 ssh root@192.168.68.15 "pct exec 112 -- curl -s -b /tmp/dsh-new.jar -o /dev/null \