From 0e26696b79b2281c1d2420cf228857efe47787d7 Mon Sep 17 00:00:00 2001 From: Bobban Rydh Date: Sun, 25 Oct 2026 23:01:33 +0100 Subject: [PATCH] Regroup the sidebar: Monitoring was 16 links, now 7 New Apps group (Home Assistant, Jellyfin, Immich, Paperless, Nextcloud, Authentik). Hetzner Cloud moves to Infrastructure, NetBox to Network and n8n to Automation. Docs now name the new locations. Co-Authored-By: Claude Sonnet 5.5 --- INTEGRATIONS.md | 16 ++++++++-------- README.md | 20 ++++++++++---------- ROLES.md | 14 +++++++------- docs/MONITORING.md | 16 ++++++++-------- web/src/layout/nav.tsx | 22 +++++++++++++++------- 5 files changed, 48 insertions(+), 40 deletions(-) diff --git a/INTEGRATIONS.md b/INTEGRATIONS.md index 3451983..e11e4b3 100644 --- a/INTEGRATIONS.md +++ b/INTEGRATIONS.md @@ -321,7 +321,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Config fields:** Home Assistant's address (with the port, usually 8123), a long-lived access token, and a checkbox to allow a self-signed certificate. - **Required access:** read only. Make the token on a user's profile page (*Security → Long-lived access tokens*); the user needs no more rights than a viewer's. Only `GET /api/` and `GET /api/states` are used — **nothing is ever sent** to Home Assistant. -- **What it does:** you choose which entities to watch on **Monitoring → Home Assistant** (search by name, then *Watch*; at most 60 per Home Assistant). Every five minutes (and on **Read now**) Home Assistant's +- **What it does:** you choose which entities to watch on **Apps → Home Assistant** (search by name, then *Watch*; at most 60 per Home Assistant). Every five minutes (and on **Read now**) Home Assistant's entities are read in one call and the watched ones are kept: their state, and for a number a reading for the chart (one at most every two minutes, kept 35 days). - An entity that has been *unavailable* or *unknown* — or has disappeared from Home Assistant — for 15 minutes is an alert. A number past a limit you set (*alert when under / over*) is an alert. Both are in the *Monitoring* category, link to the page and can be silenced with maintenance on the integration. @@ -354,7 +354,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Config fields:** the **address** of Jellyfin (`http://host:8096`), an **API key** (Jellyfin → Dashboard → API Keys → add one; stored encrypted) and, for an https address with a certificate you made yourself, *insecure*. - **Required access:** read only. The API key is Jellyfin's own, which is administrator-level in Jellyfin; this app only ever sends GET requests for the server's information, its sessions, its scheduled tasks, the item counts and the activity log. **Nothing is ever changed or played.** - **What it does:** every **two minutes** Jellyfin is read and stored — its version, whether it **wants a restart** or has an update, **who is streaming what** and whether it is being **transcoded**, how its **scheduled tasks** (a library scan) last ended, how many films, series, episodes and songs there are, and how many - **sign-ins failed** in the last day. **Monitoring → Jellyfin** shows it, with a chart of the most that were streaming at once (readings kept 35 days). + **sign-ins failed** in the last day. **Apps → Jellyfin** shows it, with a chart of the most that were streaming at once (readings kept 35 days). - **Alerts** (category *Monitoring*, source *Jellyfin*; held back by maintenance on the integration): **waiting to be restarted** (warning), **a scheduled task failed** (warning; the task's name and error), **10 or more sign-ins failed in a day** (warning). - **Somebody is watching.** If the Jellyfin runs on a server this app knows (the Jellyfin's address is that server's address or host name), then **before an update run restarts that machine** the update drawer says who is streaming and asks again, and the server answers `409 watching` to a run started without saying it should go ahead anyway. A **patch plan** that comes to that server while people are streaming **waits for them, up to two hours**, then goes ahead and says so in its message; the server's row in the run reads *Waiting: 2 people are streaming from Cinema (Ann: Dune, …)*. Only a reading from the last ten minutes counts: if Jellyfin cannot be read, nobody is assumed to be watching. @@ -369,7 +369,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Required access:** read only. Give the key just these permissions: `server.about`, `server.storage`, `server.statistics` and `job.read` (`queue.read` on newer versions) — statistics and jobs need an administrator's key. This app only ever sends GET requests; **nothing is changed, and no job is started, paused or cleared**. If one of those is refused, that part is left out and the rest still works. - **What it does:** every **five minutes** Immich is read and stored — its version (and whether a newer one is out), how full the **disk under the library** is, how many **photos and videos** there are and what they take, and the **background job queues** with how many jobs **failed** in each. - **Monitoring → Immich** shows it. + **Apps → Immich** shows it. - **Alerts** (source *Immich*; held back by maintenance on the integration): **the disk under the library is 90 % full** (warning; **95 %**, critical) and **10 or more background jobs have failed**, all queues together (warning; the worst queues are named — thumbnails or metadata that were never made. Failed jobs stay counted until you run them again or clear them in Immich, so the alert stays until you do). - If Immich cannot be read for 20 minutes its alerts are neither raised nor cleared, the Alerts page says it could not check, and the integration is raised as failing like any other. A part that could not be asked is *unknown*, never *none*. @@ -383,7 +383,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * yourself, *insecure*. - **Required access:** read only. Without a login only `/status.php` is read, which Nextcloud answers to anyone. With one, the *Monitoring* app (`serverinfo`, installed by default) is also asked, which needs an **administrator**; if it is refused or the app is off, the status is still read and the page says so. This app only ever sends GET requests, and **nothing is changed**. -- **What it does:** every **five minutes** Nextcloud is read and stored — its version, whether it is in **maintenance mode**, whether it **needs its database upgrading**, and (with the login) the **room left where the data is kept**, the users, the files, who was active in the last day and how many **app updates** wait. **Monitoring → Nextcloud** shows it. +- **What it does:** every **five minutes** Nextcloud is read and stored — its version, whether it is in **maintenance mode**, whether it **needs its database upgrading**, and (with the login) the **room left where the data is kept**, the users, the files, who was active in the last day and how many **app updates** wait. **Apps → Nextcloud** shows it. - **Alerts** (source *Nextcloud*; held back by maintenance on the integration): **the database needs upgrading** (critical — nobody can use it until `occ upgrade`), **maintenance mode is on** (warning — nobody can sign in), and **less than 20 GB is left for the data** (warning; under **5 GB**, critical), **the background jobs are not running** (warning — Nextcloud's own *Cron last run* check says error, which it does when the last run was more than an hour ago; see below) and **Nextcloud's own checks report an error** (warning; one alert naming them). - If Nextcloud cannot be read for 20 minutes its alerts are neither raised nor cleared, the Alerts page says it could not check, and the integration is raised as failing like any other. - `/metrics` has `homelab_nextcloud_maintenance_mode`, `homelab_nextcloud_free_bytes`, `homelab_nextcloud_active_users_24h` and `homelab_nextcloud_app_updates` for each Nextcloud that was read lately. @@ -406,7 +406,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Config fields:** the **address** of NetBox (`https://netbox.example.lan`), an **API token** (your profile → API Tokens; stored encrypted; **write enabled off** is enough — both the older `Token` tokens and NetBox 4.5's `nbt_…` tokens work) and, for an https address with a certificate you made yourself, *insecure*. - **Required access:** read only. `/api/status/`, and the counts and addresses of devices, virtual machines, prefixes and IP addresses. This app only ever sends GET requests; **nothing is changed**. - **What it does:** every **five minutes** NetBox is read and stored — its version, **how many background workers are running** (they run its webhooks, scripts, jobs and reports; in the Docker image they are a separate container that can be down while the pages still load), how many devices, VMs, prefixes and addresses it holds, and the addresses - themselves (up to 5000). **Monitoring → NetBox** shows it. + themselves (up to 5000). **Network → NetBox** shows it. - **Alert** (source *NetBox*; held back by maintenance on the integration): **no background worker is running** (warning). - **Not in NetBox**: the page lists the servers this app manages **none of whose addresses are in NetBox** (an address that is the same on every host, like Docker's bridge, is left out as on the Consistency page; loopback and link-local addresses say nothing). That is a **list, not an alert** — documentation that is behind is not an outage. If NetBox holds more than 5000 addresses the page says what is missing may be in the part that was not read. @@ -418,7 +418,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Config fields:** the **address** of n8n (`http://host:5678`), an **API key** (Settings → n8n API → *Create an API key*; stored encrypted) and, for an https address with a certificate you made yourself, *insecure*. - **Required access:** read only. `GET /api/v1/workflows` and `GET /api/v1/executions` — the public API has to be switched on (it is on by default in current versions). This app only ever sends GET requests: **no workflow is started, changed or switched off**. -- **What it does:** every **five minutes** n8n is read and stored — the workflows and whether each is switched on, and, from the **newest 250 runs**, each workflow's **last outcome** and how many of its runs failed in the last day. **Monitoring → n8n** shows it. +- **What it does:** every **five minutes** n8n is read and stored — the workflows and whether each is switched on, and, from the **newest 250 runs**, each workflow's **last outcome** and how many of its runs failed in the last day. **Automation → n8n** shows it. - **Alert** (source *n8n*, category *Automation*; held back by maintenance on the integration): **a workflow that is switched on failed on its last run** (warning; one alert for each workflow, saying when and, if more than one run failed, how many in the last day). It **clears by itself** when the workflow next succeeds. A workflow that is switched off, or whose failure is more than a week old, is not raised. - If n8n cannot be read for 20 minutes its alerts are neither raised nor cleared, and the Alerts page says it could not check. If the runs could not be read (but the workflows could), the last outcomes are *unknown* and nothing is claimed. @@ -431,7 +431,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Required access:** read only, and a **superuser's token** is best: the system status (the worker, Redis, the index, the disk) is only given to a superuser. With an ordinary user's token the document counts and the failed imports are still read, and the page says the status is unknown. This app only ever sends GET requests; **nothing is changed, and no failed task is dismissed**. - **What it does:** every **five minutes** Paperless is read and stored — its version (and whether a newer one is out), the status of the **database, Redis, the worker that consumes documents, the search index, the classifier and the sanity check**, the **disk**, the **document and inbox counts** and the **imports that failed** - in the last week and that nobody has dismissed. **Monitoring → Paperless** shows it. + in the last week and that nobody has dismissed. **Apps → Paperless** shows it. - **Alerts** (source *Paperless-ngx*; held back by maintenance on the integration): **the database, Redis or the worker in error** (critical — nothing can be consumed or found), **the index or the classifier in error** (warning), **the sanity check found problems** (warning), **documents failed to import** (warning; the files are named and the latest error shown — it clears when you dismiss them in Paperless, or after a week), and **the disk under the documents is 90 % full** (warning; **95 %**, critical). A classifier that simply has not been trained yet (Paperless's *warning*) is not an alert. - If Paperless cannot be read for 20 minutes its alerts are neither raised nor cleared, the Alerts page says it could not check, and the integration is raised as failing like any other. A part that could not be asked is *unknown*, never *none*. @@ -456,7 +456,7 @@ osTicket's API cannot close a ticket, so this is the one place in the app that * - **Required access:** read only. This app only ever sends GET requests: the version, the workers, the outposts and their health, the certificates, the tokens and the events log. **Nothing is ever changed.** Give the token a user with just enough to read these (an administrator, or a user in a role that may view them); if one of the lists is refused, that part is left out and the rest still works. - **What it does:** every **five minutes** Authentik is read and stored — its version (and whether a newer one is out), whether a **worker** is connected, each **outpost** (the proxy outpost that guards your apps, an LDAP one) with how many instances reported in during the last five minutes and whether they run the right version, the - **certificates** (those Authentik does not renew by itself) with their expiry, the **API tokens and app passwords** that expire, and how many **sign-ins failed** and **configuration errors** happened in the last day. **Monitoring → Authentik** shows it, with what runs out soonest first. + **certificates** (those Authentik does not renew by itself) with their expiry, the **API tokens and app passwords** that expire, and how many **sign-ins failed** and **configuration errors** happened in the last day. **Apps → Authentik** shows it, with what runs out soonest first. - **Alerts** (source *Authentik*; held back by maintenance on the integration): **an outpost that serves applications has not reported in** (critical — the apps behind it stop letting anyone in; an outpost with no applications is left alone), **an outpost runs another version** (warning), **a certificate runs out** (warning within 14 days, critical within 3 and once it has), **an API token or app password runs out** (warning within 7 days, critical within 2 — the token this app uses to read Authentik is among them), **no worker is connected** (warning; mail, outpost changes and scheduled tasks stop), **20 or more sign-ins failed in a day** (warning; shown as "100 or more" when the log's page is full) and **3 or more configuration errors in a day** (warning; a flow or stage that is set up wrongly, with the newest message). diff --git a/README.md b/README.md index bd46cff..f13a913 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ Authentik (OIDC), with local admin/operator/viewer roles. All modules from the original plan are built: -- Monorepo scaffold, Tabler-themed app shell with a grouped sidebar (Infrastructure, Backups, Network, Monitoring, Automation, Operations, Administration; groups open on demand, the one holding the current page is always open, and what you leave open is remembered) +- Monorepo scaffold, Tabler-themed app shell with a grouped sidebar (Infrastructure, Backups, Network, Monitoring, Apps, Automation, Operations, Administration; groups open on demand, the one holding the current page is always open, and what you leave open is remembered) - Authentik OIDC login, roles (first user to sign in becomes admin), audit log (changes made in the app, sign-ins and sign-outs with the IP they came from, new accounts, and the log's own automatic trimming — attributed to "system"; settings changes show what changed, but never credentials) @@ -529,30 +529,30 @@ meant to be kept and how far back it actually reaches. A history that holds far address once, and paste three options into Duplicati's default options; no password for Duplicati is kept and the app never calls it. Every job then appears with when it last succeeded, how the last run went, how long it took, how big the source is and what changed, with a history; a failed run is a warning (critical from the second in a row), an overdue one (2 days by default, per job) a warning (critical at three times that), and maintenance on the machine's server silences them. See INTEGRATIONS.md and docs/MONITORING.md. -**Nextcloud** (Monitoring → Nextcloud). Add a Nextcloud integration (its address; an administrator's app password adds more) and the app tells you when people **cannot use it**: **critical** when its database needs upgrading, a warning when it is stuck in **maintenance mode**, and a warning (critical under 5 GB) when the **data disk is low**. +**Nextcloud** (Apps → Nextcloud). Add a Nextcloud integration (its address; an administrator's app password adds more) and the app tells you when people **cannot use it**: **critical** when its database needs upgrading, a warning when it is stuck in **maintenance mode**, and a warning (critical under 5 GB) when the **data disk is low**. The page also shows the users, the files and the app updates waiting. Whether its **background jobs (cron) are running** is read from Nextcloud's own setup checks (Nextcloud 28 or later), and a warning is raised when they are not — a stopped cron would otherwise go unnoticed for weeks. See INTEGRATIONS.md and docs/MONITORING.md. -**Hetzner Cloud** (Monitoring → Hetzner Cloud). Add a project's read-only API token and the app lists its servers with their status, this month's traffic against the quota, backups, volumes and snapshots, and roughly what it costs a month. It warns when a server that was running is **off**, when one has used **80% of its traffic** (critical at 100%), when **rescue mode** is left on (the next reboot would not come back up), and when **backups** are enabled but late. A server that is also one the app knows by its agent gets a Hetzner card on its own page. Nothing at Hetzner is ever changed. See INTEGRATIONS.md and docs/MONITORING.md. +**Hetzner Cloud** (Infrastructure → Hetzner Cloud). Add a project's read-only API token and the app lists its servers with their status, this month's traffic against the quota, backups, volumes and snapshots, and roughly what it costs a month. It warns when a server that was running is **off**, when one has used **80% of its traffic** (critical at 100%), when **rescue mode** is left on (the next reboot would not come back up), and when **backups** are enabled but late. A server that is also one the app knows by its agent gets a Hetzner card on its own page. Nothing at Hetzner is ever changed. See INTEGRATIONS.md and docs/MONITORING.md. -**NetBox** (Monitoring → NetBox). Add a NetBox integration (its address and a read-only token): a warning when **no background worker** is running (they are a separate container in the Docker image, and can be down while the pages load), and a list on the page of **the servers you run that have no address in NetBox**. That list is +**NetBox** (Network → NetBox). Add a NetBox integration (its address and a read-only token): a warning when **no background worker** is running (they are a separate container in the Docker image, and can be down while the pages load), and a list on the page of **the servers you run that have no address in NetBox**. That list is not an alert; documentation that is behind is not an outage. See INTEGRATIONS.md and docs/MONITORING.md. -**n8n** (Monitoring → n8n). Add an n8n integration (its address and an API key): a warning for each **workflow that is switched on and failed on its last run** — an automation that has quietly stopped — which clears when it next succeeds. The page lists the workflows with their last run and the failures of the last day. See +**n8n** (Automation → n8n). Add an n8n integration (its address and an API key): a warning for each **workflow that is switched on and failed on its last run** — an automation that has quietly stopped — which clears when it next succeeds. The page lists the workflows with their last run and the failures of the last day. See INTEGRATIONS.md and docs/MONITORING.md. -**Immich** (Monitoring → Immich). Add an Immich integration (its address and a read-only API key) and the app watches the thing you cannot recreate: it warns when the **disk under the photo library** is filling (critical at 95 %) and when **background jobs have failed** — the thumbnails and metadata that Immich +**Immich** (Apps → Immich). Add an Immich integration (its address and a read-only API key) and the app watches the thing you cannot recreate: it warns when the **disk under the photo library** is filling (critical at 95 %) and when **background jobs have failed** — the thumbnails and metadata that Immich quietly never made. The page shows the photo and video counts, what the library takes and each job queue. See INTEGRATIONS.md and docs/MONITORING.md. -**Paperless-ngx** (Monitoring → Paperless). Add a Paperless-ngx integration (its address and a superuser's API token) and the app tells you when it has stopped taking documents in: **critical** when the database, Redis or the **worker that consumes documents** is in error, and a warning for **documents that failed to import** +**Paperless-ngx** (Apps → Paperless). Add a Paperless-ngx integration (its address and a superuser's API token) and the app tells you when it has stopped taking documents in: **critical** when the database, Redis or the **worker that consumes documents** is in error, and a warning for **documents that failed to import** (named, with the error), a failing index or sanity check, and a filling disk. The page shows the documents, the inbox and Paperless's own system status. See INTEGRATIONS.md and docs/MONITORING.md. **Prometheus** (Monitoring → Prometheus). Add a Prometheus integration (just its address) and what you already measure there joins the one list of what is wrong: a **scrape target that stops answering** (five minutes, grouped by job — a node exporter on each host, say) and **alerts that Prometheus's own rules are firing** (critical when labelled so). The page shows targets by job and what is down or firing. Alerts managed by Grafana itself are not seen. See INTEGRATIONS.md and docs/MONITORING.md. -**Authentik** (Monitoring → Authentik). Add an Authentik integration (its address and an API token) and the app watches the sign-in in front of everything else: it raises a **critical** alert when an **outpost** that guards applications stops reporting, and warns when a **certificate** or an **API token** is +**Authentik** (Apps → Authentik). Add an Authentik integration (its address and an API token) and the app watches the sign-in in front of everything else: it raises a **critical** alert when an **outpost** that guards applications stops reporting, and warns when a **certificate** or an **API token** is about to run out (the token it reads Authentik with included), when **no worker** is connected, and when **sign-ins are failing** or flows are misconfigured. The page lists the outposts, what runs out soonest and the failed sign-ins of the last day. See INTEGRATIONS.md and docs/MONITORING.md. -**Jellyfin** (Monitoring → Jellyfin). Add a Jellyfin integration (its address and an API key) and the app shows whether it is up, **who is streaming what** and whether it is being transcoded, the scheduled tasks that failed, and a chart of how many watched at once; it warns when Jellyfin **wants a restart**, a +**Jellyfin** (Apps → Jellyfin). Add a Jellyfin integration (its address and an API key) and the app shows whether it is up, **who is streaming what** and whether it is being transcoded, the scheduled tasks that failed, and a chart of how many watched at once; it warns when Jellyfin **wants a restart**, a **task failed** or **sign-ins are failing**. And when the Jellyfin runs on a server the app manages, **an update run asks first if people are watching**, and a patch plan **waits for them (up to two hours)** instead of restarting the machine in the middle of a film. See INTEGRATIONS.md and docs/MONITORING.md. **Database backups** (Settings → Data → Backup). A copy of Homelab Manager's own database is taken every day (03:30 @@ -942,7 +942,7 @@ points as a tree by what each is connected through, with the servers plugged int host NPM itself says is not working, are alerts; a host that is switched off is left alone. The hosts it serves are also offered as endpoint checks (Endpoints → Suggested) on the name people really use, linked to the server it forwards to. It only reads. -**Home Assistant.** Add it under Integrations with a long-lived access token (made at the bottom of your profile page in Home Assistant). **Monitoring → Home Assistant** is where you *choose* the few entities worth an +**Home Assistant.** Add it under Integrations with a long-lived access token (made at the bottom of your profile page in Home Assistant). **Apps → Home Assistant** is where you *choose* the few entities worth an alert — a UPS battery, a freezer's temperature, a pump — not all of them. Each is read every five minutes; a number keeps a history (35 days, with a chart), and you can set a limit under and/or over which it is an alert. An entity that has been *unavailable* (or has gone missing) for 15 minutes is an alert too. If Home Assistant cannot be read for twenty minutes its entities are neither raised nor cleared, and the Alerts page says it could not check. Nothing is ever sent to Home Assistant. Neither integration has been tried against the real thing — see INTEGRATIONS.md. diff --git a/ROLES.md b/ROLES.md index 1f9d604..65df2c7 100644 --- a/ROLES.md +++ b/ROLES.md @@ -135,19 +135,19 @@ even further, to admin only: - **To do and Notes** (Operations → To do, the *To do* and *Notes* cards on a server's page, a device's *Notes* drawer): everyone signed in reads them; adding, editing, ticking off and removing a job, and writing a note, and adding, captioning and removing a photo on one, need operator. - **Racks** (Inventory → Racks) and the **network diagram**: everyone signed in. A rack is made from the hardware's *where* and *rack unit*, which operators edit on the inventory page. - **Proxy hosts** (Network → Proxy hosts): everyone signed in sees what Nginx Proxy Manager serves; **Read now** needs operator; adding the integration (its login) is an administrator's job. -- **Home Assistant** (Monitoring → Home Assistant): everyone signed in sees what is watched, its state and history; choosing what to watch, its limits, stopping and **Read now** need operator (the list of all +- **Home Assistant** (Apps → Home Assistant): everyone signed in sees what is watched, its state and history; choosing what to watch, its limits, stopping and **Read now** need operator (the list of all entities is read live, so only operators see it); adding the integration (its token) is an administrator's job. - **Service levels** (Monitoring → Service levels): everyone signed in sees the targets and what is left of the budget; setting, changing and removing one is administrator-only, and each is in the audit log. - **UPS** (Monitoring → UPS): everyone signed in sees each UPS, its history and what is on it; adding one (its address and SNMP community) is an administrator's job, like any integration, and what it powers is written in the dependency map. - **Endpoints**: everyone sees the checks and how they are doing; adding, changing and removing one is administrator-only (each makes the server connect somewhere); that includes the value a check judges and the header (a token) it sends, whose value is never shown again to anyone; *Check now* needs operator. -- **Hetzner Cloud** (Monitoring → Hetzner Cloud, and the card on a server's page): everyone signed in sees the servers, their addresses, traffic and cost estimate, volumes and snapshots; adding a project (its API token) is an administrator's job, like any integration. Nothing on the page changes anything at Hetzner. -- **Nextcloud, NetBox and n8n** (Monitoring → each): everyone signed in sees the status, the counts and what is wrong — for NetBox, the names and addresses of the servers that are not in it; for n8n, the names of the workflows; adding one (its address and a login, token or key) is an administrator's job, like any integration. -- **Immich** (Monitoring → Immich): everyone signed in sees the counts, the disk and the job queues; adding one (its address and API key) is an administrator's job, like any integration. -- **Paperless-ngx** (Monitoring → Paperless): everyone signed in sees the counts, the system status and the names of the files that failed to import; adding one (its address and a superuser's token) is an administrator's job, like any integration. +- **Hetzner Cloud** (Infrastructure → Hetzner Cloud, and the card on a server's page): everyone signed in sees the servers, their addresses, traffic and cost estimate, volumes and snapshots; adding a project (its API token) is an administrator's job, like any integration. Nothing on the page changes anything at Hetzner. +- **Nextcloud, NetBox and n8n** (Apps → Nextcloud, Network → NetBox, Automation → n8n): everyone signed in sees the status, the counts and what is wrong — for NetBox, the names and addresses of the servers that are not in it; for n8n, the names of the workflows; adding one (its address and a login, token or key) is an administrator's job, like any integration. +- **Immich** (Apps → Immich): everyone signed in sees the counts, the disk and the job queues; adding one (its address and API key) is an administrator's job, like any integration. +- **Paperless-ngx** (Apps → Paperless): everyone signed in sees the counts, the system status and the names of the files that failed to import; adding one (its address and a superuser's token) is an administrator's job, like any integration. - **Prometheus** (Monitoring → Prometheus): everyone signed in sees the targets, what is down and the alerts firing; adding one (its address, and a token if it needs one) is an administrator's job, like any integration. -- **Authentik** (Monitoring → Authentik): everyone signed in sees the outposts, what runs out and the failed-sign-in count (the names of tokens and certificates, not their values); adding one (its address and API token) is an administrator's job, like any integration. -- **Jellyfin** (Monitoring → Jellyfin): everyone signed in sees who is streaming and what is wrong; adding one (its address and API key) is an administrator's job, like any integration. Starting an update run on a server people are streaming from needs `startAnyway` — the update drawer asks (operators). +- **Authentik** (Apps → Authentik): everyone signed in sees the outposts, what runs out and the failed-sign-in count (the names of tokens and certificates, not their values); adding one (its address and API token) is an administrator's job, like any integration. +- **Jellyfin** (Apps → Jellyfin): everyone signed in sees who is streaming and what is wrong; adding one (its address and API key) is an administrator's job, like any integration. Starting an update run on a server people are streaming from needs `startAnyway` — the update drawer asks (operators). - **Duplicati** (Backups → Duplicati): everyone signed in sees every backup and how it went; setting how often one is expected, muting it and forgetting it need operator; adding a machine (which makes an address that can write to this app) and removing one are administrators'. Reports arrive on a secret address with no sign-in: the token is the access. - **Restore tests**: everyone sees them on the Backup coverage page; recording one needs operator; removing one is administrator-only. - **Change log**: operators and administrators (it is made from the audit log, which has the same readers). diff --git a/docs/MONITORING.md b/docs/MONITORING.md index 4f48278..1e41b09 100644 --- a/docs/MONITORING.md +++ b/docs/MONITORING.md @@ -236,7 +236,7 @@ What is kept: the last result of each job, and each report for 400 days or 400 r ## Nextcloud -An integration of type *Nextcloud* ([INTEGRATIONS.md](../INTEGRATIONS.md#nextcloud)) is read every five minutes, and **Monitoring → Nextcloud** shows its version, whether it is usable, and — with an administrator's app password — the room left for the data, the users, the files and the app updates waiting. +An integration of type *Nextcloud* ([INTEGRATIONS.md](../INTEGRATIONS.md#nextcloud)) is read every five minutes, and **Apps → Nextcloud** shows its version, whether it is usable, and — with an administrator's app password — the room left for the data, the users, the files and the app updates waiting. | Alert | When | Severity | |---|---|---| @@ -250,7 +250,7 @@ Maintenance on the integration holds them. A reading older than 20 minutes is no ## Hetzner Cloud -An integration of type *Hetzner Cloud* ([INTEGRATIONS.md](../INTEGRATIONS.md#hetzner-cloud)) is one project, read every five minutes, and **Monitoring → Hetzner Cloud** shows its servers (status, type, place, addresses, this month's traffic against what the type includes, whether backups are on), volumes, snapshots, and roughly what the project costs. Nothing is started, stopped or changed. +An integration of type *Hetzner Cloud* ([INTEGRATIONS.md](../INTEGRATIONS.md#hetzner-cloud)) is one project, read every five minutes, and **Infrastructure → Hetzner Cloud** shows its servers (status, type, place, addresses, this month's traffic against what the type includes, whether backups are on), volumes, snapshots, and roughly what the project costs. Nothing is started, stopped or changed. | Alert | When | Severity | |---|---|---| @@ -268,7 +268,7 @@ Hetzner does not say when a server went off or when rescue mode was switched on, ## NetBox -An integration of type *NetBox* ([INTEGRATIONS.md](../INTEGRATIONS.md#netbox)) is read every five minutes, and **Monitoring → NetBox** shows its workers, what it holds and — the other half — **which of your servers are not in it**. +An integration of type *NetBox* ([INTEGRATIONS.md](../INTEGRATIONS.md#netbox)) is read every five minutes, and **Network → NetBox** shows its workers, what it holds and — the other half — **which of your servers are not in it**. | Alert | When | Severity | |---|---|---| @@ -278,7 +278,7 @@ The list of servers with no address in NetBox is not an alert: it is the app's s ## n8n -An integration of type *n8n* ([INTEGRATIONS.md](../INTEGRATIONS.md#n8n)) is read every five minutes, and **Monitoring → n8n** lists the workflows with their last run and the failures of the last day. +An integration of type *n8n* ([INTEGRATIONS.md](../INTEGRATIONS.md#n8n)) is read every five minutes, and **Automation → n8n** lists the workflows with their last run and the failures of the last day. | Alert | When | Severity | |---|---|---| @@ -288,7 +288,7 @@ A workflow that is switched off says nothing, and what each workflow last did is ## Immich -An integration of type *Immich* ([INTEGRATIONS.md](../INTEGRATIONS.md#immich)) is read every five minutes, and **Monitoring → Immich** shows the photo and video counts, what the library takes, the disk under it and each background job queue with how many failed. Photos cannot be made again, and Immich fails quietly: +An integration of type *Immich* ([INTEGRATIONS.md](../INTEGRATIONS.md#immich)) is read every five minutes, and **Apps → Immich** shows the photo and video counts, what the library takes, the disk under it and each background job queue with how many failed. Photos cannot be made again, and Immich fails quietly: | Alert | When | Severity | |---|---|---| @@ -299,7 +299,7 @@ Failed jobs stay counted until they are run again or cleared in Immich (Administ ## Paperless-ngx -An integration of type *Paperless-ngx* ([INTEGRATIONS.md](../INTEGRATIONS.md#paperless-ngx)) is read every five minutes, and **Monitoring → Paperless** shows the documents and the inbox, the disk, Paperless's own system status and the imports that failed in the last week. +An integration of type *Paperless-ngx* ([INTEGRATIONS.md](../INTEGRATIONS.md#paperless-ngx)) is read every five minutes, and **Apps → Paperless** shows the documents and the inbox, the disk, Paperless's own system status and the imports that failed in the last week. | Alert | When | Severity | |---|---|---| @@ -326,7 +326,7 @@ Grafana manages itself are not in Prometheus's list; to see one here, write it a ## Authentik -An integration of type *Authentik* ([INTEGRATIONS.md](../INTEGRATIONS.md#authentik)) is read every five minutes, and **Monitoring → Authentik** shows its version, workers, each outpost (and whether it is reporting), the certificates and API tokens that run out — soonest first — and the failed sign-ins of the last day. +An integration of type *Authentik* ([INTEGRATIONS.md](../INTEGRATIONS.md#authentik)) is read every five minutes, and **Apps → Authentik** shows its version, workers, each outpost (and whether it is reporting), the certificates and API tokens that run out — soonest first — and the failed sign-ins of the last day. Authentik is the front door to everything behind it, so what is raised early is what would shut it: | Alert | When | Severity | @@ -343,7 +343,7 @@ Maintenance on the integration holds them. A reading older than 20 minutes is no ## Jellyfin -An integration of type *Jellyfin* ([INTEGRATIONS.md](../INTEGRATIONS.md#jellyfin)) is read every two minutes, and **Monitoring → Jellyfin** shows whether it is up, who is **streaming** right now (and whether that is transcoded, which is what loads the machine), the scheduled tasks that failed, and a chart of the most that were streaming at once. +An integration of type *Jellyfin* ([INTEGRATIONS.md](../INTEGRATIONS.md#jellyfin)) is read every two minutes, and **Apps → Jellyfin** shows whether it is up, who is **streaming** right now (and whether that is transcoded, which is what loads the machine), the scheduled tasks that failed, and a chart of the most that were streaming at once. It raises three warnings: **a restart is wanted**, **a scheduled task failed**, **10 or more sign-ins failed in a day** (the last is the one to look at if the server is open to the internet). Maintenance on the integration holds them. Its other use is **not cutting off a film**. When the Jellyfin runs on a server the app knows, an update run on that server asks first if people are streaming (the update drawer says who; *Update anyway* goes ahead), and a patch plan waits for them for up to two hours before it updates that server. diff --git a/web/src/layout/nav.tsx b/web/src/layout/nav.tsx index ecbecff..dc7b82e 100644 --- a/web/src/layout/nav.tsx +++ b/web/src/layout/nav.tsx @@ -36,6 +36,7 @@ import { IconTool, IconListCheck, IconRefresh, + IconApps, IconDownload, IconBox, IconHeartbeat, @@ -90,6 +91,7 @@ export const NAV: NavEntry[] = [ { to: "/proxmox", label: "Proxmox", icon: }, { to: "/synology", label: "Synology", icon: }, { to: "/docker", label: "Docker", icon: }, + { to: "/hetzner", label: "Hetzner Cloud", icon: }, { to: "/tailscale", label: "Tailscale", icon: }, { to: "/map", label: "Map", icon: }, { to: "/inventory", label: "Inventory", icon: }, @@ -115,6 +117,7 @@ export const NAV: NavEntry[] = [ { to: "/network/devices", label: "Network devices", icon: }, { to: "/proxy-hosts", label: "Proxy hosts", icon: }, { to: "/ipam", label: "IP Addresses", icon: }, + { to: "/netbox", label: "NetBox", icon: }, { to: "/ports", label: "Ports", icon: }, { to: "/consistency", label: "Consistency", icon: }, ], @@ -128,18 +131,22 @@ export const NAV: NavEntry[] = [ { to: "/alert-rules", label: "Alert rules", icon: }, { to: "/heartbeats", label: "Heartbeats", icon: }, { to: "/uptime-kuma", label: "Uptime Kuma", icon: }, - { to: "/home-assistant", label: "Home Assistant", icon: }, { to: "/ups", label: "UPS", icon: }, - { to: "/jellyfin", label: "Jellyfin", icon: }, - { to: "/authentik", label: "Authentik", icon: }, { to: "/prometheus", label: "Prometheus", icon: }, + { to: "/service-levels", label: "Service levels", icon: }, + ], + }, + { + id: "apps", + label: "Apps", + icon: , + items: [ + { to: "/home-assistant", label: "Home Assistant", icon: }, + { to: "/jellyfin", label: "Jellyfin", icon: }, { to: "/immich", label: "Immich", icon: }, { to: "/paperless", label: "Paperless", icon: }, - { to: "/n8n", label: "n8n", icon: }, - { to: "/netbox", label: "NetBox", icon: }, { to: "/nextcloud", label: "Nextcloud", icon: }, - { to: "/hetzner", label: "Hetzner Cloud", icon: }, - { to: "/service-levels", label: "Service levels", icon: }, + { to: "/authentik", label: "Authentik", icon: }, ], }, { @@ -150,6 +157,7 @@ export const NAV: NavEntry[] = [ { to: "/semaphore", label: "Semaphore", icon: }, { to: "/gitea", label: "Gitea", icon: }, { to: "/osticket", label: "osTicket", icon: }, + { to: "/n8n", label: "n8n", icon: }, ], }, { to: "/secrets", label: "Secrets", icon: },