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
+22 -3
View File
@@ -55,7 +55,7 @@ func bind(v *flagVals) *flaggy.Parser {
p.Bool(&v.force, "", "force", "overwrite existing message.json")
p.Bool(&v.dryRun, "", "dry-run", "list counts without writing")
p.String(&v.query, "", "query", "Gmail search query")
p.String(&v.srcs, "", "source", "comma list: onlyoffice,gmail")
p.String(&v.srcs, "", "source", "comma list: onlyoffice,gmail,m365")
return p
}
@@ -110,6 +110,24 @@ func ParseCLI(args []string) (CLIConfig, int, error) {
CredentialsPath: filepath.Join(home, ".gmail-mcp", "credentials.json"),
KeysPath: filepath.Join(home, ".gmail-mcp", "gcp-oauth.keys.json"),
}
case "m365":
tenant := pick(envVars["M365_TENANT"], envVars["MS_TENANT"])
cid := pick(envVars["M365_CLIENT_ID"], envVars["MS_CLIENT_ID"])
sec := pick(envVars["M365_CLIENT_SECRET"], envVars["MS_CLIENT_SECRET"])
users := pick(envVars["M365_USERS"], envVars["MS_USERS"])
if tenant == "" || cid == "" || sec == "" || users == "" {
return CLIConfig{}, 2, fmt.Errorf("m365 source needs M365_TENANT/CLIENT_ID/CLIENT_SECRET/USERS in %s", v.env)
}
var userList []string
for _, u := range strings.Split(users, ",") {
if u = strings.TrimSpace(u); u != "" {
userList = append(userList, u)
}
}
if len(userList) == 0 {
return CLIConfig{}, 2, fmt.Errorf("m365 source: M365_USERS empty")
}
cfg.M365 = &M365Credentials{Tenant: tenant, ClientID: cid, ClientSecret: sec, Users: userList}
default:
return CLIConfig{}, 2, fmt.Errorf("unknown source %q", s)
}
@@ -126,7 +144,7 @@ func Main(args []string) int {
return code
}
if cfg.Help {
fmt.Fprintln(os.Stderr, "usage: bin/mail/sync.go [--source onlyoffice,gmail] [--query GMAIL_Q] [--limit N] [--offset N] [--workers N] [--force] [--dry-run]")
fmt.Fprintln(os.Stderr, "usage: bin/mail/sync.go [--source onlyoffice,gmail,m365] [--query GMAIL_Q] [--limit N] [--offset N] [--workers N] [--force] [--dry-run]")
return 0
}
ctx, cancel := context.WithTimeout(context.Background(), 6*time.Hour)
@@ -169,7 +187,8 @@ func readEnv(path string) map[string]string {
if !ok {
continue
}
if strings.HasPrefix(k, "ONLYOFFICE_") || strings.HasPrefix(k, "OO_") {
if strings.HasPrefix(k, "ONLYOFFICE_") || strings.HasPrefix(k, "OO_") ||
strings.HasPrefix(k, "M365_") || strings.HasPrefix(k, "MS_") {
out[k] = v
}
}