Files
verdande/rune/verdande.yaml
T
Kristian WindandClaude Opus 5 0dbea0ea4b
Release / Build and publish image (push) Failing after 9m56s
feat: make it possible to see which version is actually running
"I have updated and restarted, but I cannot tell whether it worked" is
not a question the panel could answer. The version was on the startup
line and in the settings page, and nowhere you can reach from outside.

/healthz carries it now. That is the one endpoint answering without a
session, which makes it the only way to ask the question from a terminal
or from the panel itself. The "listening" line repeats it too, because
that is the line the Rune's done_regex matches and therefore the one
sitting at the bottom of the console after a deploy.

The update notice could also never have worked. It reads GitHub's
releases/latest, and this repository had only tags — a tag is not a
release, and that endpoint answers 404 for a repository without any. The
release workflow creates one now, after the image is pushed so a release
never announces a version that failed to build.

VERDANDE_UPDATE_CHECK is a Rune variable, so it can be switched on
without editing the container. Still off by default: it is an outbound
request, and that is a choice to make rather than a default to inherit.

Rune version 1 -> 2, so the panel offers the update.

Note that the check still cannot see anything while the repository is
private — releases/latest is 404 anonymously, exactly as the GHCR package
was. Making the repo public, or teaching the check to carry a token, is a
separate decision.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-17 14:35:36 +02:00

133 lines
4.7 KiB
YAML

gameskill:
id: verdande
name: "verdande"
category: "Apps"
description: >
Self-hosted tasks and projects, shared with other people. Natural-language
quick add in Danish and English, sub-tasks, labels, saved filters, board and
calendar views, recurring tasks, reminders, comments and attachments. One
binary with SQLite inside it — no database to set up. Set BASE_URL to the
address you reach it on, point the SMTP settings at your mail server for
invites and reminders, then start it and open the URL to create the first
admin account.
author: "kristianwind"
version: 2
icon: "app"
# The image is distroless — no shell — so keep_entrypoint runs the binary the
# image already declares as its ENTRYPOINT, and startup.exec passes it argv
# directly rather than through /bin/sh, which does not exist in there.
docker:
image: "ghcr.io/kristianwind/verdande:latest"
data_path: /data
keep_entrypoint: true
variables:
# verdande cannot work out its own public address: the host port is not chosen
# until the server is created. {{PUBLIC_URL}} is what the panel knows and this
# is what invite links, password resets and ICS feeds are built from — get it
# wrong and the links in your email point somewhere that does not answer.
- key: VERDANDE_BASE_URL
name: "Public address (used in invite and reset links)"
type: string
default: "{{PUBLIC_URL}}"
required: true
- key: VERDANDE_SMTP_HOST
name: "SMTP host (blank = show invite links in the app instead of mailing them)"
type: string
default: ""
- key: VERDANDE_SMTP_PORT
name: "SMTP port"
type: int
default: 587
min: 1
max: 65535
- key: VERDANDE_SMTP_USER
name: "SMTP username"
type: string
default: ""
- key: VERDANDE_SMTP_PASS
name: "SMTP password"
type: string
default: ""
secret: true
- key: VERDANDE_SMTP_FROM
name: "Sender address"
type: string
default: ""
pattern: '^$|^[^@\s]+@[^@\s]+\.[^@\s]+$'
hint: "must be an email address like verdande@example.dk, or blank to leave it unset"
- key: VERDANDE_SMTP_STARTTLS
name: "Use STARTTLS (turn off only for port 465, which is TLS from the start)"
type: bool
default: true
- key: VERDANDE_SESSION_TTL
name: "How long a login lasts (Go duration, e.g. 720h for 30 days)"
type: string
default: "720h"
pattern: '^[0-9]+(ns|us|ms|s|m|h)$'
hint: "must be a duration like 720h, 30m or 45s"
# Off by default because it is an outbound request nobody asked for. It sends
# no identifier and reads one public URL — GitHub's releases API — but that is
# a choice to make rather than a default to inherit.
- key: VERDANDE_UPDATE_CHECK
name: "Look for new releases (asks GitHub once a day; sends nothing about you)"
type: bool
default: false
install:
# The image has no shell, so the install step borrows one. It only has to make
# the directory layout exist; verdande creates and migrates its own database on
# first start.
image: "busybox:latest"
script: |
set -eu
mkdir -p /data/files /data/backups
echo "verdande data directory ready at /data"
startup:
# No command: with keep_entrypoint the image's own ENTRYPOINT (/verdande) runs,
# and everything is configured through the environment above.
done_regex: '"msg":"listening"'
ports:
- { name: web, default: 8080, protocol: tcp }
# Everything worth keeping is under /data. The -wal and -shm files are included
# deliberately: a WAL-mode SQLite database copied without them can be missing the
# most recent writes.
backup:
include: ["."]
# The container logs JSON — VERDANDE_DEV is off in production — so these patterns
# match the JSON form, not the human-readable one seen when developing locally.
watchers:
- name: "Database errors"
pattern: 'database is locked|disk I/O error|database disk image is malformed'
threshold: 1
window_secs: 300
action: kvasir
- name: "Failed logins"
pattern: '"path":"/api/v1/auth/login".*"status":401'
threshold: 10
window_secs: 300
action: notify
- name: "Server errors"
pattern: '"status":5[0-9][0-9]'
threshold: 5
window_secs: 300
action: kvasir
events:
# Capture group 1 is the client address, which the panel rolls up per source —
# so a brute-force run shows up as one row per address per hour.
- key: login_failed
label: "Failed login"
match: '"path":"/api/v1/auth/login".*"status":401.*"remote":"([^"]+)"'
- key: http_5xx
label: "HTTP 5xx"
match: '"status":5[0-9][0-9].*"remote":"([^"]+)"'