feat(mail): M365 Graph sync + bot ETL loop (OO+Gmail) (#38)
Tests / Test (push) Failing after 5s
Tests / OCR (tesseract fixture) (push) Failing after 4s
Tests / Release (semver) (push) Skipped

* feat(mail): add Microsoft 365 Graph sync source with delta state

Adds a GET-only Microsoft Graph source to bin/mail/sync (client-credentials,
delta query). Wires it into the CLI (--source m365), the worker pool and the
compose stack:

- m365.go: M365Client (token cache, delta pagination, message normalization,
  attachment download) + m365Source adapter (per-mailbox folders + delta link)
- sync.go: M365Credentials in SyncConfig; Committer interface so delta links
  only advance after a fully successful run (no skips on failure)
- cli.go: --source m365 with M365_/MS_ env passthrough
- Dockerfile: mail-build stage produces /mail-sync into the index image
- docker-entrypoint: mail-sync loop (sync -> import -> index, default 10s)
- compose.yaml: mail-sync service (index image, kb-var volume, secrets ro)

* feat(mail): adapt M365 ETL loop for OO+Gmail bots.

Default compose mail-sync to onlyoffice,gmail every 300s with import on new
mail; gate full --rebuild behind MAIL_SYNC_INDEX. Fix mail-build stage order
and add bin/stack/start-mail-sync.
This commit is contained in:
2026-08-14 18:02:13 +01:00
committed by GitHub
co-authored by GitHub
parent fc2723c39f
commit e28fb9f428
17 changed files with 788 additions and 19 deletions
+43 -1
View File
@@ -106,6 +106,7 @@ func Retry(ctx context.Context, policy RetryPolicy, fn func() error) error {
type SyncConfig struct {
OO *OOConfig // OnlyOffice source (optional)
Gmail *GmailCredentials // Gmail source (optional)
M365 *M365Credentials // Microsoft 365 Graph source (optional)
Out string // var/mail root; default <repo>/var/mail
Workers int // concurrency; default 4
Limit int // max messages per source (0 = all)
@@ -133,6 +134,14 @@ type Source interface {
Folder() string
}
// Committer is an optional Source capability: Commit is called after all listed
// ids have been downloaded successfully. Sources that only advance durable state
// on success (e.g. a Graph delta link) implement this so a killed or failed run
// stays retryable without gaps.
type Committer interface {
Commit() error
}
type ooSource struct {
c *OOClient
page int
@@ -222,8 +231,22 @@ func Run(ctx context.Context, cfg SyncConfig) (*SyncStats, error) {
}
sources = append(sources, &gmailSource{c: gm, query: cfg.Query})
}
if cfg.M365 != nil {
stateDir := filepath.Join(cfg.Out, ".m365")
for _, mb := range cfg.M365.Users {
if !strings.Contains(mb, "@") {
return nil, fmt.Errorf("m365 user %q is not an email address", mb)
}
c, err := NewM365Client(*cfg.M365)
if err != nil {
return nil, fmt.Errorf("m365 init for %s: %w", mb, err)
}
local := strings.SplitN(mb, "@", 2)[0]
sources = append(sources, &m365Source{c: c, mailbox: mb, localpart: strings.ToLower(local), stateDir: stateDir})
}
}
if len(sources) == 0 {
return nil, errors.New("sync: no source configured (need OO, Gmail, or both)")
return nil, errors.New("sync: no source configured (need OO, Gmail, M365, or a combination)")
}
stats := &SyncStats{}
@@ -296,6 +319,25 @@ func Run(ctx context.Context, cfg SyncConfig) (*SyncStats, error) {
close(jobsCh)
wg.Wait()
// Only advance durable source state (e.g. delta links) when everything
// downloaded. A killed or failed run must be retryable without gaps.
if len(failures) == 0 {
seen := map[Source]bool{}
for _, j := range jobs {
if seen[j.src] {
continue
}
seen[j.src] = true
if c, ok := j.src.(Committer); ok {
if err := c.Commit(); err != nil {
mu.Lock()
failures = append(failures, j.src.Folder()+"/commit: "+err.Error())
mu.Unlock()
}
}
}
}
if len(failures) > 0 {
fmt.Fprintf(os.Stderr, "sync: %d failures:\n %s\n", len(failures), strings.Join(failures, "\n "))
}