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)
 ```
@@ -89,7 +90,7 @@ parameter. Search before reading whole files.
    Test data must be synthetic (Alice, Bob, Charlie, Diana, example.com).
 3. **No credentials/secrets in commits.** API keys, tokens, passwords, session
    strings, phone numbers only in gitignored `.env` files, referenced by path.
-4. **Curasoft — no files, no mentions.** Remove all traces if found.
+4. **Curasoft, edelweiss — no files, no mentions.** Remove all traces if found.
 5. **Check git history before push.** If any commit contains leaks, rewrite
    history (rebase + force push) AND delete affected GitHub releases/tags.
 6. **`docs/chat-import-plan.md`** — reference Gitea issue, never embed secrets.

bin/chats/linkedin.go

@@ -0,0 +1,356 @@
+package main
+
+import (
+	"bufio"
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"time"
+)
+
+type LinkedInMCPSource struct {
+	userDataDir string
+	limit       int
+}
+
+type lnInboxItem struct {
+	ThreadID         string `json:"thread_id"`
+	Participants     string `json:"participants"`
+	LastMessage      string `json:"last_message"`
+	LastMessageDate  string `json:"last_message_date"`
+	Unread           bool   `json:"unread"`
+}
+
+type lnInboxEnvelope struct {
+	Results    []lnInboxItem `json:"results"`
+	HasMore    bool          `json:"hasMore"`
+}
+
+type lnMessage struct {
+	From       string `json:"from"`
+	Date       string `json:"date"`
+	Text       string `json:"text"`
+}
+
+type lnConvEnvelope struct {
+	Results    []lnMessage `json:"results"`
+	HasMore    bool        `json:"hasMore"`
+	TotalCount int         `json:"total_count"`
+}
+
+func NewLinkedInMCPSource(userDataDir string) *LinkedInMCPSource {
+	return &LinkedInMCPSource{userDataDir: userDataDir}
+}
+
+func (s *LinkedInMCPSource) Name() string { return "linkedin" }
+
+func (s *LinkedInMCPSource) Sync(ctx context.Context, outDir string, limit int) error {
+	if limit > 0 {
+		s.limit = limit
+	}
+
+	client, err := newLinkedInMCP(ctx, s.userDataDir)
+	if err != nil {
+		return fmt.Errorf("linkedin mcp: %w", err)
+	}
+	defer client.Close()
+
+	inbox, err := client.GetInbox(ctx, 50)
+	if err != nil {
+		return fmt.Errorf("get_inbox: %w", err)
+	}
+	if len(inbox) == 0 {
+		fmt.Println("chats: no LinkedIn conversations found")
+		return nil
+	}
+
+	fmt.Printf("chats: found %d LinkedIn conversations\n", len(inbox))
+
+	for _, conv := range inbox {
+		convID := sanitizeDir(conv.ThreadID)
+		if convID == "" {
+			convID = fmt.Sprintf("conv_%d", time.Now().UnixNano())
+		}
+
+		parts := strings.SplitN(conv.Participants, ",", 2)
+		chatName := strings.TrimSpace(parts[0])
+		if chatName == "" {
+			chatName = convID
+		}
+
+		chatDir := filepath.Join(outDir, "linkedin", convID)
+		if err := os.MkdirAll(chatDir, 0755); err != nil {
+			fmt.Fprintf(os.Stderr, "chats: mkdir %s: %v\n", chatDir, err)
+			continue
+		}
+
+		msgLimit := 100
+		if s.limit > 0 {
+			msgLimit = s.limit
+		}
+
+		msgs, err := client.GetConversation(ctx, "", conv.ThreadID, msgLimit)
+		if err != nil {
+			fmt.Fprintf(os.Stderr, "chats: get_conversation %s: %v\n", convID, err)
+			continue
+		}
+
+		jsonlPath := filepath.Join(chatDir, "messages.jsonl")
+		f, err := os.Create(jsonlPath)
+		if err != nil {
+			fmt.Fprintf(os.Stderr, "chats: create %s: %v\n", jsonlPath, err)
+			continue
+		}
+
+		enc := json.NewEncoder(f)
+		written := 0
+		for i, m := range msgs {
+			text := m.Text
+			if text == "" {
+				continue
+			}
+
+			ts := m.Date
+			if t, err := time.Parse("2006-01-02T15:04:05Z07:00", m.Date); err == nil {
+				ts = t.UTC().Format(time.RFC3339)
+			} else if t, err := time.Parse(time.RFC3339, m.Date); err == nil {
+				ts = t.UTC().Format(time.RFC3339)
+			}
+
+			chatMsg := Message{
+				ID:        fmt.Sprintf("li_%s_%d", convID, i),
+				Timestamp: ts,
+				From:      m.From,
+				Text:      text,
+				Platform:  "linkedin",
+			}
+			if err := enc.Encode(chatMsg); err != nil {
+				fmt.Fprintf(os.Stderr, "chats: encode: %v\n", err)
+				continue
+			}
+			written++
+		}
+		f.Close()
+
+		fmt.Printf("chats: synced %s (%s) — %d messages\n", chatName, convID, written)
+	}
+
+	return nil
+}
+
+type linkedInMCPClient struct {
+	cmd    *exec.Cmd
+	stdin  *bufio.Writer
+	stdout *bufio.Scanner
+	msgID  int
+}
+
+func newLinkedInMCP(ctx context.Context, userDataDir string) (*linkedInMCPClient, error) {
+	args := []string{
+		"mcp-server-linkedin@latest",
+		"--user-data-dir", userDataDir,
+		"--no-auto-import",
+		"--transport", "stdio",
+		"--login-timeout", "10",
+		"--browser-wait", "1",
+		"--browser-idle-timeout", "10",
+		"--log-level", "ERROR",
+	}
+
+	cmd := exec.CommandContext(ctx, "uvx", args...)
+	cmd.Env = os.Environ()
+
+	stdin, err := cmd.StdinPipe()
+	if err != nil {
+		return nil, fmt.Errorf("stdin pipe: %w", err)
+	}
+	stdout, err := cmd.StdoutPipe()
+	if err != nil {
+		return nil, fmt.Errorf("stdout pipe: %w", err)
+	}
+	cmd.Stderr = os.Stderr
+
+	if err := cmd.Start(); err != nil {
+		return nil, fmt.Errorf("start: %w", err)
+	}
+
+	c := &linkedInMCPClient{
+		cmd:    cmd,
+		stdin:  bufio.NewWriter(stdin),
+		stdout: bufio.NewScanner(stdout),
+		msgID:  0,
+	}
+	c.stdout.Buffer(make([]byte, 1<<20), 1<<20)
+
+	if err := c.initialize(ctx); err != nil {
+		c.Close()
+		return nil, fmt.Errorf("init: %w", err)
+	}
+	return c, nil
+}
+
+func (c *linkedInMCPClient) nextID() int {
+	c.msgID++
+	return c.msgID
+}
+
+func (c *linkedInMCPClient) initialize(ctx context.Context) error {
+	params := map[string]interface{}{
+		"protocolVersion": "2024-11-05",
+		"capabilities":    map[string]interface{}{},
+		"clientInfo": map[string]string{
+			"name":    "chats-sync",
+			"version": "0.1.0",
+		},
+	}
+	_, err := c.send(ctx, "initialize", params)
+	return err
+}
+
+func (c *linkedInMCPClient) send(ctx context.Context, method string, params interface{}) (json.RawMessage, error) {
+	id := c.nextID()
+	req := map[string]interface{}{
+		"jsonrpc": "2.0",
+		"id":      id,
+		"method":  method,
+	}
+	if params != nil {
+		req["params"] = params
+	}
+	body, err := json.Marshal(req)
+	if err != nil {
+		return nil, fmt.Errorf("marshal: %w", err)
+	}
+
+	if _, err := c.stdin.Write(body); err != nil {
+		return nil, fmt.Errorf("write: %w", err)
+	}
+	if err := c.stdin.WriteByte('\n'); err != nil {
+		return nil, fmt.Errorf("newline: %w", err)
+	}
+	if err := c.stdin.Flush(); err != nil {
+		return nil, fmt.Errorf("flush: %w", err)
+	}
+
+	for c.stdout.Scan() {
+		line := c.stdout.Text()
+		if line == "" {
+			continue
+		}
+		var resp struct {
+			JSONRPC string          `json:"jsonrpc"`
+			ID      int             `json:"id"`
+			Result  json.RawMessage `json:"result,omitempty"`
+			Error   *struct {
+				Code    int    `json:"code"`
+				Message string `json:"message"`
+			} `json:"error,omitempty"`
+		}
+		if err := json.Unmarshal([]byte(line), &resp); err != nil {
+			return nil, fmt.Errorf("unmarshal: %w\nline: %s", err, line[:min(len(line), 500)])
+		}
+		if resp.Error != nil {
+			return nil, fmt.Errorf("rpc error %d: %s", resp.Error.Code, resp.Error.Message)
+		}
+		return resp.Result, nil
+	}
+	return nil, fmt.Errorf("no response: %w", c.stdout.Err())
+}
+
+func (c *linkedInMCPClient) GetInbox(ctx context.Context, limit int) ([]lnInboxItem, error) {
+	params := map[string]interface{}{
+		"limit": limit,
+	}
+	result, err := c.send(ctx, "tools/call", map[string]interface{}{
+		"name":      "get_inbox",
+		"arguments": params,
+	})
+	if err != nil {
+		return nil, err
+	}
+
+	var toolRes struct {
+		Content []struct {
+			Type string `json:"type"`
+			Text string `json:"text"`
+		} `json:"content"`
+		IsError bool `json:"isError"`
+	}
+	if err := json.Unmarshal(result, &toolRes); err != nil {
+		return nil, fmt.Errorf("unmarshal tool: %w", err)
+	}
+	if toolRes.IsError {
+		return nil, fmt.Errorf("get_inbox error")
+	}
+	if len(toolRes.Content) == 0 {
+		return nil, nil
+	}
+
+	text := toolRes.Content[0].Text
+	var env lnInboxEnvelope
+	if err := json.Unmarshal([]byte(text), &env); err != nil {
+		var arr []lnInboxItem
+		if err2 := json.Unmarshal([]byte(text), &arr); err2 == nil {
+			return arr, nil
+		}
+		return nil, fmt.Errorf("parse inbox: %w", err)
+	}
+	return env.Results, nil
+}
+
+func (c *linkedInMCPClient) GetConversation(ctx context.Context, username, threadID string, limit int) ([]lnMessage, error) {
+	params := map[string]interface{}{
+		"linkedin_username": username,
+		"thread_id":         threadID,
+		"index":             limit,
+	}
+	result, err := c.send(ctx, "tools/call", map[string]interface{}{
+		"name":      "get_conversation",
+		"arguments": params,
+	})
+	if err != nil {
+		return nil, err
+	}
+
+	var toolRes struct {
+		Content []struct {
+			Type string `json:"type"`
+			Text string `json:"text"`
+		} `json:"content"`
+		IsError bool `json:"isError"`
+	}
+	if err := json.Unmarshal(result, &toolRes); err != nil {
+		return nil, fmt.Errorf("unmarshal tool: %w", err)
+	}
+	if toolRes.IsError {
+		return nil, nil
+	}
+	if len(toolRes.Content) == 0 {
+		return nil, nil
+	}
+
+	text := toolRes.Content[0].Text
+	var env lnConvEnvelope
+	if err := json.Unmarshal([]byte(text), &env); err != nil {
+		var arr []lnMessage
+		if err2 := json.Unmarshal([]byte(text), &arr); err2 == nil {
+			return arr, nil
+		}
+		return nil, fmt.Errorf("parse conv: %w", err)
+	}
+	return env.Results, nil
+}
+
+func (c *linkedInMCPClient) Close() error {
+	if c.stdin != nil {
+		c.stdin.Flush()
+	}
+	if c.cmd != nil && c.cmd.Process != nil {
+		c.cmd.Process.Kill()
+	}
+	return nil
+}

bin/chats/main.go

@@ -40,8 +40,7 @@ func main() {
 			fmt.Fprintf(os.Stderr, "chats: WhatsApp not implemented yet\n")
 			os.Exit(1)
 		case "linkedin":
-			fmt.Fprintf(os.Stderr, "chats: LinkedIn not implemented yet\n")
-			os.Exit(1)
+			os.Exit(runSyncLinkedIn(platformArgs))
 		default:
 			fmt.Fprintf(os.Stderr, "chats: unknown platform %q\n", platform)
 			os.Exit(2)

bin/chats/sync_linkedin_cmd.go

@@ -0,0 +1,69 @@
+package main
+
+import (
+	"context"
+	"flag"
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+	"time"
+)
+
+func checkLinkedInSession(userDataDir string) (bool, error) {
+	cmd := exec.Command("uvx", "mcp-server-linkedin@latest",
+		"--user-data-dir", userDataDir,
+		"--no-auto-import",
+		"--status",
+	)
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		return true, fmt.Errorf("status check: %w\n%s", err, string(out))
+	}
+	return !strings.Contains(string(out), "✅"), nil
+}
+
+func runSyncLinkedIn(args []string) int {
+	fs := flag.NewFlagSet("chats sync linkedin", flag.ContinueOnError)
+	limit := fs.Int("limit", 0, "max messages per conversation (0 = all)")
+	help := fs.Bool("help", false, "")
+	fs.SetOutput(os.Stderr)
+	if err := fs.Parse(args); err != nil {
+		return 2
+	}
+	if *help {
+		fmt.Fprintln(os.Stderr, "usage: chats sync linkedin [--limit N]")
+		return 0
+	}
+
+	userDataDir := envVar("LINKEDIN_USER_DATA_DIR", "")
+	if userDataDir == "" {
+		home, _ := os.UserHomeDir()
+		userDataDir = home + "/.linkedin-mcp/profile"
+	}
+
+	// Check session first
+	loginNeeded, err := checkLinkedInSession(userDataDir)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "chats: linkedin status check: %v\n", err)
+	}
+	if loginNeeded {
+		fmt.Fprintf(os.Stderr, "chats: LinkedIn session expired. Run:\n")
+		fmt.Fprintf(os.Stderr, "  uvx mcp-server-linkedin@latest --user-data-dir %s --login\n", userDataDir)
+		fmt.Fprintf(os.Stderr, "Then retry 'chats sync linkedin'\n")
+		return 1
+	}
+
+	src := NewLinkedInMCPSource(userDataDir)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Minute)
+	defer cancel()
+
+	start := time.Now()
+	if err := src.Sync(ctx, chatsDir(), *limit); err != nil {
+		fmt.Fprintf(os.Stderr, "chats sync linkedin: %v\n", err)
+		return 1
+	}
+	fmt.Printf("chats sync linkedin: completed in %s\n", time.Since(start).Round(time.Millisecond))
+	return 0
+}

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
-	cur string
+	c     gmailAPI
+	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))
 }