Add Gmail --query to mail/sync (default in:inbox) (#4)

* Add --query to Gmail mail/sync instead of always listing in:inbox.

Callers keep the search string; default remains in:inbox.

* Document Gmail --query on the mail/sync pipeline.

* test(mail): assert Gmail --query reaches ListIDs, not only the CLI flag.

ParseCLI coverage left a hole: an empty query still has to become in:inbox
and a custom q has to be the string the client lists with.

AGENTS.md

@@ -52,6 +52,7 @@ var/          kb.lbug, var/mail/*, caches (gitignored)
 
 ```bash
 bin/mail/sync.go --source onlyoffice,gmail --workers 8 --out var/mail   # raw message.json + attachments
+bin/mail/sync.go --source gmail --query 'from:example.com' --out var/mail  # Gmail search (default in:inbox)
 bin/mail/import --from-raw var/mail                                     # message.json → message.md (convert only)
 bin/mail/index_mail                                                     # rebuild brain incl. all mail (fresh DB)
 ```

bin/mail/sync/cli.go

@@ -32,6 +32,7 @@ func ParseCLI(args []string) (CLIConfig, int, error) {
 		offset = fs.Int("offset", 0, "skip first N messages per source")
 		force  = fs.Bool("force", false, "overwrite existing message.json + attachments")
 		dryRun = fs.Bool("dry-run", false, "list message counts without writing")
+		query  = fs.String("query", "in:inbox", "Gmail search query (gmail source only)")
 		srcs   = fs.String("source", "onlyoffice", "comma list: onlyoffice,gmail (default onlyoffice)")
 		help   = fs.Bool("help", false, "usage")
 	)
@@ -60,6 +61,7 @@ func ParseCLI(args []string) (CLIConfig, int, error) {
 		Offset:  *offset,
 		Force:   *force,
 		DryRun:  *dryRun,
+		Query:   *query,
 		Policy:  RetryPolicy{},
 	}
 	cli := CLIConfig{Sync: cfg, Env: *env, Sources: *srcs}
@@ -95,7 +97,7 @@ func Main(args []string) int {
 		return code
 	}
 	if cli.Help {
-		fmt.Fprintln(os.Stderr, "usage: bin/mail/sync.go [--source onlyoffice,gmail] [--limit N] [--offset N] [--workers N] [--force] [--dry-run]")
+		fmt.Fprintln(os.Stderr, "usage: bin/mail/sync.go [--source onlyoffice,gmail] [--query GMAIL_Q] [--limit N] [--offset N] [--workers N] [--force] [--dry-run]")
 		return 0
 	}
 	ctx, cancel := context.WithTimeout(context.Background(), 6*time.Hour)

bin/mail/sync/sync.go

@@ -112,6 +112,7 @@ type SyncConfig struct {
 	Offset  int                // skip first N messages per source
 	Force   bool               // overwrite existing message.json + attachments
 	DryRun  bool               // list without writing
+	Query   string             // Gmail search query; default in:inbox
 	Policy  RetryPolicy
 }
 
@@ -136,9 +137,17 @@ type ooSource struct {
 	c    *OOClient
 	page int
 }
+// gmailAPI is the Gmail client surface gmailSource needs. *GmailClient implements it.
+type gmailAPI interface {
+	ListIDs(ctx context.Context, q string, maxIDs int, pageToken string) ([]string, string, error)
+	GetMessage(ctx context.Context, id string) (*Message, error)
+	DownloadAttachment(ctx context.Context, msgID, attID string) ([]byte, error)
+}
+
 type gmailSource struct {
-	c   *GmailClient
+	c     gmailAPI
-	cur string
+	cur   string
+	query string
 }
 
 func (s *ooSource) Folder() string      { return "inbox" }
@@ -171,7 +180,11 @@ func (s *ooSource) DownloadAttachment(ctx context.Context, msg *Message, att Att
 }
 
 func (s *gmailSource) ListIDs(ctx context.Context, limit int, cursor string) ([]string, string, error) {
-	ids, next, err := s.c.ListIDs(ctx, "in:inbox", limit, cursor)
+	q := s.query
+	if q == "" {
+		q = "in:inbox"
+	}
+	ids, next, err := s.c.ListIDs(ctx, q, limit, cursor)
 	return ids, next, err
 }
 
@@ -207,7 +220,7 @@ func Run(ctx context.Context, cfg SyncConfig) (*SyncStats, error) {
 		if err != nil {
 			return nil, fmt.Errorf("gmail init: %w", err)
 		}
-		sources = append(sources, &gmailSource{c: gm})
+		sources = append(sources, &gmailSource{c: gm, query: cfg.Query})
 	}
 	if len(sources) == 0 {
 		return nil, errors.New("sync: no source configured (need OO, Gmail, or both)")

bin/mail/sync/sync_test.go

@@ -221,6 +221,71 @@ func TestCollectParts(t *testing.T) {
 	}
 }
 
+type fakeGmailAPI struct {
+	lastQ     string
+	lastLimit int
+	ids       []string
+}
+
+func (f *fakeGmailAPI) ListIDs(_ context.Context, q string, maxIDs int, _ string) ([]string, string, error) {
+	f.lastQ = q
+	f.lastLimit = maxIDs
+	return f.ids, "", nil
+}
+func (f *fakeGmailAPI) GetMessage(context.Context, string) (*Message, error) {
+	return nil, errors.New("unused")
+}
+func (f *fakeGmailAPI) DownloadAttachment(context.Context, string, string) ([]byte, error) {
+	return nil, errors.New("unused")
+}
+
+func TestGmailSourcePassesQueryToListIDs(t *testing.T) {
+	fake := &fakeGmailAPI{ids: []string{"m1"}}
+	src := &gmailSource{c: fake, query: "from:alice@example.com"}
+	ids, _, err := src.ListIDs(context.Background(), 10, "")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if fake.lastQ != "from:alice@example.com" {
+		t.Fatalf("ListIDs q=%q, want from:alice@example.com", fake.lastQ)
+	}
+	if fake.lastLimit != 10 {
+		t.Fatalf("ListIDs limit=%d, want 10", fake.lastLimit)
+	}
+	if len(ids) != 1 || ids[0] != "m1" {
+		t.Fatalf("ids=%v", ids)
+	}
+}
+
+func TestGmailSourceEmptyQueryDefaultsToInbox(t *testing.T) {
+	fake := &fakeGmailAPI{}
+	src := &gmailSource{c: fake, query: ""}
+	if _, _, err := src.ListIDs(context.Background(), 5, ""); err != nil {
+		t.Fatal(err)
+	}
+	if fake.lastQ != "in:inbox" {
+		t.Fatalf("empty query q=%q, want in:inbox", fake.lastQ)
+	}
+}
+
+func TestParseCLIGmailQuery(t *testing.T) {
+	cli, code, err := ParseCLI([]string{
+		"--source", "gmail",
+		"--query", "from:letrado@example.com",
+		"--out", t.TempDir(),
+		"--dry-run",
+	})
+	if err != nil || code != 0 {
+		t.Fatalf("ParseCLI: code=%d err=%v", code, err)
+	}
+	if cli.Sync.Query != "from:letrado@example.com" {
+		t.Fatalf("query=%q", cli.Sync.Query)
+	}
+	if cli.Sync.Gmail == nil {
+		t.Fatal("gmail source not configured")
+	}
+}
+
 func b64(s string) string {
 	return base64.URLEncoding.EncodeToString([]byte(s))
 }