Inspector 0.9.5: stack redeploy no longer blocks other checks

CHANGELOG.md

@@ -7,6 +7,41 @@ Version numbers follow [Semantic Versioning](https://semver.org/spec/v2.0.0.html
 
 ---
 
+## [0.9.5] — 2026-10-28
+
+### Fixed
+
+- **A stack redeploy no longer freezes Inspector.** After a successful Portainer
+  redeploy, Inspector used to stop everything for `post_redeploy_wait_seconds`
+  (default 90 s): no other container was checked, dashboard times stood still, and
+  stopping Inspector during the wait wasn't clean. Now the redeployed app is left to
+  settle while every other container keeps being checked, and its one-time HTTP
+  re-check (with the "recheck failed" alert) happens on its first check after the wait.
+- The redeployed app's cooldown now starts after the settle time. Before, the wait
+  ate into it (with the defaults, 300 s cooldown became 210 s).
+
+---
+
+## [0.9.4] — 2026-10-28
+
+### Fixed
+
+- **Containers without a Docker health check now "recover" properly.** Many images
+  don't define a health check, so Docker reports them as `NO HEALTH CHECK` even when
+  they work. Inspector only treated `HEALTHY` as back to normal, so for these
+  containers:
+  - the error count never reset, and one-off failures days apart added up to a restart;
+  - no "recovered" alert was sent;
+  - with *Restart, then redeploy*, the next unrelated problem skipped the restart and
+    redeployed the whole stack.
+
+  Now `NO HEALTH CHECK` counts as working (unless you made it a restart trigger): the
+  count resets, the "recovered" alert is sent ("back to running (no health check)"),
+  and the next problem starts with a plain restart. Containers with a health check
+  behave exactly as before.
+
+---
+
 ## [0.9.3] — 2026-10-28
 
 ### Changed

src/inspector/__init__.py

@@ -1 +1 @@
-__version__ = "0.9.3"
+__version__ = "0.9.5"

src/inspector/assets/guide/guide.html

@@ -356,8 +356,9 @@ folder (or a backup of it) can read the token.</p>
   <tr><td>stack_redeploy_cooldown_seconds</td><td>Minimum time between two redeploys of the same
     stack (default 300). Several apps often share a stack; this stops them triggering a redeploy
     each.</td></tr>
-  <tr><td>post_redeploy_wait_seconds</td><td>How long Inspector waits after a redeploy for the
-    stack to come up before judging it again (default 90).</td></tr>
+  <tr><td>post_redeploy_wait_seconds</td><td>How long Inspector gives the stack to come up after
+    a redeploy before judging that app again (default 90). Everything else keeps being checked
+    meanwhile.</td></tr>
 </table>
 
 <h3>If Test connection fails</h3>

src/inspector/main.py

@@ -41,7 +41,7 @@ from .maintenance import MaintenanceTracker
 from .notification_mute import NotificationMuteTracker
 from .notifier import GotifyNotifier, MultiNotifier, NullNotifier, PushoverNotifier
 from .portainer_client import PortainerClient
-from .recovery import perform_recovery
+from .recovery import perform_recovery, run_post_redeploy_recheck
 from .uptime_kuma import HeartbeatSnapshot, UptimeKumaClient
 from .state import (
     ContainerState,
@@ -63,6 +63,19 @@ def _request_stop(signum, _frame):
     _stop = True
 
 
+def _is_normal(status: str | None, container_config: ContainerConfig) -> bool:
+    """True when `status` means the container is working.
+
+    HEALTHY always counts. NO HEALTH CHECK (running, but the image defines no
+    health check) counts too, unless the user made it a restart trigger.
+    Many images have no health check, and without this their error count and
+    restart episode would never reset.
+    """
+    if status == HEALTHY:
+        return True
+    return status == NO_HEALTH_CHECK and NO_HEALTH_CHECK not in container_config.restart_on
+
+
 def _apply_reachability_override(
     container_config: ContainerConfig,
     result: HealthResult,
@@ -140,6 +153,11 @@ def _check_one(
     if notification_mute.is_muted(name):
         notifier = NullNotifier()
 
+    if state.redeploy_recheck_at is not None and now >= state.redeploy_recheck_at:
+        run_post_redeploy_recheck(
+            container_config=container_config, state=state, notifier=notifier, now=now,
+        )
+
     if state.previous_status != state.current_status:
         log.info(
             "%-*s status: %s -> %s%s",
@@ -158,17 +176,23 @@ def _check_one(
             message=result.message,
         )
 
+    is_normal = _is_normal(state.current_status, container_config)
     if (
         state.previous_status is not None
-        and state.previous_status != HEALTHY
-        and state.current_status == HEALTHY
+        and not _is_normal(state.previous_status, container_config)
+        and is_normal
+        # HEALTHY here means "a recovery was already announced", for either status.
         and state.last_notification_state != HEALTHY
     ):
-        log.info("%-*s recovered: %s -> HEALTHY", width, name, state.previous_status)
+        log.info("%-*s recovered: %s -> %s", width, name, state.previous_status, state.current_status)
+        back_to = (
+            "**HEALTHY**" if state.current_status == HEALTHY
+            else "**running** (no health check)"
+        )
         notifier.notify(
             title=f"✅ Inspector: {name} recovered",
             message=(
-                f"**{name}** is back to **HEALTHY** (was *{state.previous_status}*).\n\n"
+                f"**{name}** is back to {back_to} (was *{state.previous_status}*).\n\n"
                 f"- Errors before recovery: **{state.error_count}**\n"
                 f"- Time: {format_timestamp(now, with_zone=True)}"
             ),
@@ -178,7 +202,7 @@ def _check_one(
             container=name,
             event_type=EVENT_RECOVERY,
             old_status=state.previous_status,
-            new_status=HEALTHY,
+            new_status=state.current_status,
             error_count=state.error_count,
         )
         state.last_notification_state = HEALTHY
@@ -253,9 +277,9 @@ def _check_one(
                 message=result.message,
             )
             state.last_notification_state = result.status
-    elif result.status == HEALTHY:
+    elif is_normal:
         if state.error_count != 0:
-            log.info("%-*s healthy again; resetting error count", width, name)
+            log.info("%-*s back to normal; resetting error count", width, name)
         state.error_count = 0
         state.restarted_this_episode = False
 

src/inspector/recovery.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import logging
-import time
 from datetime import datetime, timedelta
 
 from .config import AppConfig, ContainerConfig, PortainerConfig
@@ -175,7 +174,8 @@ def _perform_restart_then_redeploy(
       - the container is still failing on a later recovery cycle
         (`state.restarted_this_episode` is already set), meaning the restart didn't stick.
 
-    The episode flag resets when the container is next seen HEALTHY (see main._check_one).
+    The episode flag resets when the container is next seen working: HEALTHY, or
+    NO HEALTH CHECK when that isn't a restart trigger (see main._is_normal).
     """
     name = container_config.name
 
@@ -521,24 +521,46 @@ def _perform_portainer_redeploy(
         priority=4,
     )
 
-    log.info("waiting %d seconds after stack redeploy", wait_seconds)
-    time.sleep(wait_seconds)
-
+    # Don't block the loop while the stack settles: keep this container in
+    # cooldown for the wait plus its normal cooldown, and do the one-time HTTP
+    # re-check on its first regular check after the wait (main._check_one).
+    log.info(
+        "%-*s letting stack %s settle for %ds; other containers keep being checked",
+        width, name, key, wait_seconds,
+    )
+    state.record_restart(now, wait_seconds + container_config.cooldown_seconds)
     if container_config.http_check.enabled:
+        state.redeploy_recheck_at = now + timedelta(seconds=wait_seconds)
+
+
+def run_post_redeploy_recheck(
+    *,
+    container_config: ContainerConfig,
+    state: ContainerState,
+    notifier: GotifyNotifier,
+    now: datetime,
+) -> None:
+    """One HTTP re-check after a stack redeploy has had time to settle.
+
+    Called by main._check_one once `state.redeploy_recheck_at` has passed;
+    alerts if the app still doesn't answer.
+    """
+    state.redeploy_recheck_at = None
+    name = container_config.name
+    if not container_config.http_check.enabled:
+        return
     recheck = check_http(container_config.http_check)
     if recheck.ok:
         log.info("recheck succeeded for %s", name)
-        else:
+        return
     log.warning("recheck failed for %s: %s", name, recheck.message)
     notifier.notify(
         title=f"⚠️ Inspector: {name} recheck failed after redeploy",
         message=(
-                    f"Portainer stack **{stack_name}** was redeployed, but the HTTP recheck "
+            f"Portainer stack **{container_config.portainer_stack_name}** was redeployed, but the HTTP recheck "
             f"for **{name}** still reports a failure.\n\n"
             f"- Recheck result: *{recheck.message}*\n"
             f"- Time: {format_timestamp(now, with_zone=True)}"
         ),
         priority=6,
     )
-
-    state.record_restart(now, container_config.cooldown_seconds)

src/inspector/state.py

@@ -29,6 +29,8 @@ class ContainerState:
     restart_limit_notified: bool = False
     restarted_this_episode: bool = False
     last_check_at: datetime | None = None
+    # After a stack redeploy: when to do the one-time HTTP re-check.
+    redeploy_recheck_at: datetime | None = None
 
     def in_cooldown(self, now: datetime) -> bool:
         return self.cooldown_until is not None and now < self.cooldown_until