feat: master/agent phase 3 — webhook and auto mode (#8) (#22)
Docker Build / docker (push) Successful in 38s
Docker Build / docker (push) Successful in 38s
## Summary
- `POST /update` on the master (outside OIDC, bearer `UPDATER_API_KEY`; unset → 503). Matches `image` against `image_repo` on all agents, marks `available_*` on every match, starts webhook-triggered jobs for `auto` services targeting `<image_repo>:<tag>` (followed tag when no tag is given), and waits for them up to `UPDATE_TIMEOUT` (default 5m). 404 on no match, 500 if any auto job failed or timed out, otherwise 200.
- Manual/auto toggle per service on the overview and service page (`POST /services/{id}/mode`, CSRF); auto is blocked for self, `build:` and container services with the reason shown. "Update available" badge and an "Available" row.
- `FinishJob` clears `available_*` only when the successful job was created for that exact ref, after it was reported. Migration `0003_webhook.sql`, phase-3 plan doc, README / gitea-action README / CLAUDE.md / deploy example updated. `action.yml` unchanged.
Closes #8
## Behaviour changes for CI
- Mixed results now return 500 (the old 207 is gone); no match returns 404 instead of 200.
- With a `tag`, Compose services get pinned to `<image_repo>:<tag>` via `compose.override.yaml`; the tag must be a pushed tag.
- `busy` (job already active) and `refused` (not updatable) are reported but return 200.
- The reverse proxy read timeout must exceed `UPDATE_TIMEOUT`.
## Test plan
- [x] `go test ./...` and `go test -race ./internal/agent/... ./internal/master/... ./internal/e2e/`
- [x] `go test -tags integration ./internal/master/store/` against throwaway Postgres
- [x] UI verified in browser (mode toggle, disabled reason, badge via SSE, Available row)
- [ ] Manual: webhook with manual service → `marked` + badge
- [ ] Manual: webhook with auto service → waits, `succeeded`, badge cleared, override pinned
- [ ] Manual: wrong token 401, unknown image 404, offline agent 500
- [ ] Gitea action pointed at the master's `/update` in a real CI run
Reviewed-on: #22
This commit was merged in pull request #22.
This commit is contained in:
@@ -2,6 +2,7 @@ package config
|
||||
|
||||
import (
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
@@ -21,7 +22,7 @@ func setAll(t *testing.T) {
|
||||
for k, v := range required {
|
||||
t.Setenv(k, v)
|
||||
}
|
||||
for _, k := range []string{"PORT", "AGENT_PORT", "AGENT_IMAGE", "LOG_LEVEL"} {
|
||||
for _, k := range []string{"PORT", "AGENT_PORT", "AGENT_IMAGE", "LOG_LEVEL", "UPDATER_API_KEY", "UPDATE_TIMEOUT"} {
|
||||
t.Setenv(k, "")
|
||||
}
|
||||
}
|
||||
@@ -35,6 +36,29 @@ func TestLoad_Defaults(t *testing.T) {
|
||||
assert.Equal(t, "gitea.shcizo.se/shcizo/package-updater:latest", cfg.AgentImage)
|
||||
assert.Equal(t, "info", cfg.LogLevel)
|
||||
assert.Equal(t, "updater-admins", cfg.AllowedGroup)
|
||||
assert.Empty(t, cfg.UpdaterAPIKey)
|
||||
assert.Equal(t, 5*time.Minute, cfg.UpdateTimeout)
|
||||
}
|
||||
|
||||
func TestLoad_WebhookSettings(t *testing.T) {
|
||||
setAll(t)
|
||||
t.Setenv("UPDATER_API_KEY", "s3cret")
|
||||
t.Setenv("UPDATE_TIMEOUT", "90s")
|
||||
cfg, err := Load()
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "s3cret", cfg.UpdaterAPIKey)
|
||||
assert.Equal(t, 90*time.Second, cfg.UpdateTimeout)
|
||||
}
|
||||
|
||||
func TestLoad_InvalidUpdateTimeout(t *testing.T) {
|
||||
for _, v := range []string{"abc", "0s", "-5m", "30"} {
|
||||
t.Run(v, func(t *testing.T) {
|
||||
setAll(t)
|
||||
t.Setenv("UPDATE_TIMEOUT", v)
|
||||
_, err := Load()
|
||||
assert.ErrorContains(t, err, "UPDATE_TIMEOUT must be a positive duration")
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestLoad_EachRequiredVariable(t *testing.T) {
|
||||
|
||||
Reference in New Issue
Block a user